Compare commits
201
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
4575bb23ee | ||
|
|
0ad3ddd627 | ||
|
|
a002781ef9 | ||
|
|
879a3a58d7 | ||
|
|
09d1b6f967 | ||
|
|
35ba2d7fdb | ||
|
|
a5aad0da7e | ||
|
|
ce5b96f373 | ||
|
|
11fac3d123 | ||
|
|
f0ad900565 | ||
|
|
36478863a2 | ||
|
|
ec667a75b6 | ||
|
|
f864f9894d | ||
|
|
73104a1a4c | ||
|
|
d66e68a5df | ||
|
|
d2b4f74cd2 | ||
|
|
1a826973a9 | ||
|
|
d13e7cda26 | ||
|
|
ec85d5f5f6 | ||
|
|
1139b00743 | ||
|
|
e9712cef23 | ||
|
|
a62c952097 | ||
|
|
1220ee54fb | ||
|
|
92e334dcd2 | ||
|
|
bc8e9fb7fa | ||
|
|
c3be745efa | ||
|
|
680ecd1c06 | ||
|
|
38797d687d | ||
|
|
fa3e66fb31 | ||
|
|
cc0f57758a | ||
|
|
2a6c437a08 | ||
|
|
c9d71c0179 | ||
|
|
9d5e16455c | ||
|
|
2a26e4fecf | ||
|
|
94bb4a8199 | ||
|
|
fd7a2dac6d | ||
|
|
8d0a6dd487 | ||
|
|
06f83e2ffc | ||
|
|
026c51b6b5 | ||
|
|
7d6fdab812 | ||
|
|
5cda485458 | ||
|
|
cd29c7d433 | ||
|
|
ca8cee990b | ||
|
|
a7859f0050 | ||
|
|
58ddde6b1e | ||
|
|
08eae86ddc | ||
|
|
9d47c4ef84 | ||
|
|
e4e8c70cd2 | ||
|
|
c570e67a09 | ||
|
|
574af61349 | ||
|
|
934b915357 | ||
|
|
c6e8371d5a | ||
|
|
f718785145 | ||
|
|
9fdb02ff8b | ||
|
|
1f51c32521 | ||
|
|
766b64cd64 | ||
|
|
3296dfca28 | ||
|
|
db9952525a | ||
|
|
196b6c5cf1 | ||
|
|
cf7379b2f6 | ||
|
|
48508c164e | ||
|
|
19a88e4f97 | ||
|
|
1b01f5e6d0 | ||
|
|
424270f0e8 | ||
|
|
df8e732709 | ||
|
|
d5325acee6 | ||
|
|
b7062d32bf | ||
|
|
5fa2ea2e6b | ||
|
|
f97d15288d | ||
|
|
736dc58d81 | ||
|
|
0a27533262 | ||
|
|
7388776b29 | ||
|
|
a515a5d563 | ||
|
|
12d4d7c63b | ||
|
|
f34e46b04f | ||
|
|
3664f53c51 | ||
|
|
fb2e0803c0 | ||
|
|
bb01283727 | ||
|
|
bc60b9f5c9 | ||
|
|
fbeabcde97 | ||
|
|
ba474b0a57 | ||
|
|
790e6df8ef | ||
|
|
057df0afc8 | ||
|
|
ba04e0c0b6 | ||
|
|
f5ce1ec941 | ||
|
|
2deb6510f8 | ||
|
|
0eac40abf6 | ||
|
|
e915d3fb13 | ||
|
|
60f6cf3c6d | ||
|
|
46b703e5a2 | ||
|
|
e09cbc112e | ||
|
|
f6b3182a80 | ||
|
|
cb3aa48999 | ||
|
|
77f1ed14c5 | ||
|
|
25c4ecfd48 | ||
|
|
08c9cccdcc | ||
|
|
4b6e1bed11 | ||
|
|
72eb94d186 | ||
|
|
90a27846ca | ||
|
|
4d81ea2cf3 | ||
|
|
d7cefdd9e9 | ||
|
|
caeed3fbaa | ||
|
|
4868e44882 | ||
|
|
a9a414b956 | ||
|
|
baeddd7c13 | ||
|
|
41bf593d4c | ||
|
|
04e23d8115 | ||
|
|
052ba195cc | ||
|
|
2ea5f905c4 | ||
|
|
e9e094c6a4 | ||
|
|
61a5bb39ae | ||
|
|
b5f745fc3e | ||
|
|
549c31431e | ||
|
|
3fa01dd686 | ||
|
|
c9357d4c0e | ||
|
|
f3a61091c7 | ||
|
|
10d24bbef7 | ||
|
|
ff8104a533 | ||
|
|
3b7f89a214 | ||
|
|
ba773e677b | ||
|
|
2443b5ac3a | ||
|
|
4c9e0e3c98 | ||
|
|
0ce98e8973 | ||
|
|
d803f39de3 | ||
|
|
300d96a9d8 | ||
|
|
28b6fb28d5 | ||
|
|
8b731313df | ||
|
|
3541c416f9 | ||
|
|
8d89b23db1 | ||
|
|
c0525cf2d2 | ||
|
|
88f0b5a0a4 | ||
|
|
aeb0ee6ad9 | ||
|
|
a4c8b4bd9a | ||
|
|
8f6d60681e | ||
|
|
65500c899b | ||
|
|
a1723db387 | ||
|
|
b453ce63c6 | ||
|
|
12893cba78 | ||
|
|
ebca44829e | ||
|
|
0629f88b37 | ||
|
|
6945b748cb | ||
|
|
08a2485f43 | ||
|
|
894ee1dd02 | ||
|
|
a9bd3faabb | ||
|
|
5b96bd4f75 | ||
|
|
c5b0540b11 | ||
|
|
1855f6e57a | ||
|
|
5a0c71dd90 | ||
|
|
e60976e1cc | ||
|
|
b7cd710c32 | ||
|
|
ad7aa2d255 | ||
|
|
a51ee1d304 | ||
|
|
e35d167055 | ||
|
|
c0fcdea1fe | ||
|
|
8b67f7ab55 | ||
|
|
8ee9fb84ba | ||
|
|
fe7a69fb07 | ||
|
|
bb6eefc837 | ||
|
|
0d0ab62674 | ||
|
|
d6d7e738a5 | ||
|
|
41cc0ed2a8 | ||
|
|
26ab11eb7b | ||
|
|
b4cc3cb934 | ||
|
|
c10da55ec6 | ||
|
|
338163ac0b | ||
|
|
5e5f3b4e5a | ||
|
|
7e9da46fe5 | ||
|
|
66979f3f51 | ||
|
|
851018b3b9 | ||
|
|
36417bfdf3 | ||
|
|
4a771f6a83 | ||
|
|
09439ad1a5 | ||
|
|
75736dadec | ||
|
|
8d56c352fc | ||
|
|
ebea9946a7 | ||
|
|
9fb04af7df | ||
|
|
3f5b9b8b58 | ||
|
|
5bbea036c2 | ||
|
|
c762495b6f | ||
|
|
979e734bd9 | ||
|
|
79cb3e0100 | ||
|
|
9d22e7e8af | ||
|
|
f46c367c27 | ||
|
|
ac4c6760d7 | ||
|
|
5a6a140dfd | ||
|
|
931012c16b | ||
|
|
03f4b871a9 | ||
|
|
601fc80178 | ||
|
|
3ff2a1bf45 | ||
|
|
51aa57f304 | ||
|
|
ca4411f30f | ||
|
|
b551365fb5 | ||
|
|
272c123952 | ||
|
|
9387670a7b | ||
|
|
d4a8401a6a | ||
|
|
aaf88a6f12 | ||
|
|
b789c1bd44 | ||
|
|
5062aa8068 | ||
|
|
8a042589e7 | ||
|
|
3898b5ad45 | ||
|
|
9d15336144 |
No files matched your search
@@ -12,6 +12,7 @@ Dieser Ordner ist der **primäre Orientierungspunkt** für Claude Code / Cursor-
|
||||
| 2 | **`rules/DOCUMENTATION.md`** – Ablage- und Dokumentationsregeln |
|
||||
| 3 | `rules/ARCHITECTURE.md`, `rules/CODING_RULES.md`, `rules/LESSONS_LEARNED.md` |
|
||||
| 4 | Issue-Landkarte: **`.claude/docs/GITEA_ISSUES_INDEX.md`** |
|
||||
| 5 | **Universal CSV Import** (Modul/Executor/Vorlagen): **`docs/technical/UNIVERSAL_CSV_IMPORT_AGENT_GUIDE.md`** (unter `.claude/`) |
|
||||
|
||||
Themen mit UI/Nav/PWA: siehe `../docs/issues/GUI_IA_ADMIN_NAV_2026-04-05.md` (im **Projekt**-`docs/`, nicht hier).
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Gitea Issues – Landkarte (Auswertung)
|
||||
|
||||
**Quelle:** Gitea `Lars/mitai-jinkendo`, Stand **2026-04-08** (Abfrage `state=all`).
|
||||
**Quelle:** Gitea `Lars/mitai-jinkendo`, Stand **2026-04-11** (Abfrage `state=all`, ergänzt: #71, #76).
|
||||
**URL:** http://192.168.2.144:3000/Lars/mitai-jinkendo/issues
|
||||
|
||||
Dieses Dokument ist ein **Orientierungs-Index** für Agenten und Entwickler. Verbindliches Tracking bleibt **in Gitea**; hier: Kategorien, Dubletten-Hinweise, grobe Prioritätseinschätzung.
|
||||
@@ -88,7 +88,7 @@ Dieses Dokument ist ein **Orientierungs-Index** für Agenten und Entwickler. Ver
|
||||
| # | Titel |
|
||||
|---|--------|
|
||||
| 15 | [FEAT-002] Quality-Filter für KI-Auswertungen & Charts integrieren |
|
||||
| 21 | [FEATURE] Universeller CSV-Parser mit lernbarem Feldmapping |
|
||||
| 76 | Trainings-Qualität: zielbezogene Logik + Listen-Filter statt globalem „Hochwertig“-Hide |
|
||||
| 36 | BUG-009: Trainingstyp-Erstellung führt zu Internal Server Error |
|
||||
|
||||
---
|
||||
|
||||
+10
-1
@@ -54,6 +54,8 @@ _Dieser Ordner `.claude/docs/` ist per `.gitignore`-Ausnahme **versioniert** (Sp
|
||||
| Platzhalter / Registry | `technical/PLACEHOLDER_REGISTRY_FRAMEWORK.md`, `technical/PLACEHOLDER_DEVELOPMENT_GUIDE.md` | `backend/placeholder_registrations/`, `backend/placeholder_resolver.py` |
|
||||
| Dashboard-Lab-Widgets | `technical/DASHBOARD_WIDGETS_AGENT_GUIDE.md` | Widget-Katalog + Registrierung (siehe Guide) |
|
||||
| Training Profiler / Resolver | `technical/TRAINING_PROFILE_RESOLVER_LAYER1.md`, `functional/TRAINING_TYPE_PROFILES.md` | Resolver-Module wie im Guide genannt |
|
||||
| Universal CSV Import | `technical/UNIVERSAL_CSV_IMPORT_AGENT_GUIDE.md` | `backend/csv_parser/`, `routers/csv_import.py`, `routers/admin_csv_templates.py` |
|
||||
| Aktivität Produktionsreife | `technical/ACTIVITY_PRODUCTION_ARCHITECTURE_AND_PHASES.md` (+ EAV-Guide) | `backend/data_layer/activity_session_metrics.py`, `activity_metrics.py`, CSV-Orchestrierung |
|
||||
| Mitgliedschaft / Features | `technical/MEMBERSHIP_SYSTEM.md`, `architecture/FEATURE_ENFORCEMENT.md` | `backend/auth.py`, Feature-Logging, Router mit Enforcement |
|
||||
|
||||
---
|
||||
@@ -111,6 +113,13 @@ _Dieser Ordner `.claude/docs/` ist per `.gitignore`-Ausnahme **versioniert** (Sp
|
||||
| `PROFILE_REFERENCE_VALUES.md` | Profil-Referenzwerte |
|
||||
| `TRAINING_PROFILE_RESOLVER_LAYER1.md` | Training-Resolver Schicht 1 |
|
||||
| `TRAINING_TYPE_PROFILES_TECHNICAL.md` | Trainingsprofile technisch |
|
||||
| `UNIVERSAL_CSV_IMPORT_AGENT_GUIDE.md` | Universal CSV: Registry, Executor, Vorlagen, Agent-Checkliste |
|
||||
| `ACTIVITY_SESSION_METRICS_EAV_AGENT_GUIDE.md` | Session-Metriken EAV, Attributprofile, Layer-1, Prod-Migration |
|
||||
| `ACTIVITY_COMPOSITE_METRICS_IMPLEMENTATION_CONCEPT.md` | Composite-Metriken in EAV (JSONB), Archetypen, CSV-Slots, Layer-1-Expand, Migration/Test-Checkliste |
|
||||
| `ACTIVITY_PRODUCTION_ARCHITECTURE_AND_PHASES.md` | **Zielarchitektur** Aktivität (Spine/EAV/Composites/Import/Layer 1–2) + **Phasenplan A–F** Produktionsreife |
|
||||
| `ACTIVITY_LAYER2A_PLACEHOLDER_AUDIT.md` | Issue #53: Aktivitäts-Platzhalter Layer 1 ↔ 2a (Audit Schritt 1) |
|
||||
| `ACTIVITY_SCALAR_KANON_TABLE.md` | **Skalar-Kanon** Aktivität (eine Semantik → eine Quelle); Phase A |
|
||||
| *(Code)* `backend/data_layer/activity_data_canon.py` | **Kanon** activity CSV-Modul vs. EAV-primär; Legacy-Lesefallback |
|
||||
| `V9D_PHASE2_VITALS_SLEEP.md` | v9d Vitalwerte/Schlaf (Release-Bezug) |
|
||||
|
||||
---
|
||||
@@ -174,4 +183,4 @@ Siehe [`audit/README.md`](./audit/README.md).
|
||||
|
||||
---
|
||||
|
||||
**Letzte Aktualisierung:** 8. April 2026 (Struktur-Index, Duplikatbereinigung, Abgleich-Hinweise)
|
||||
**Letzte Aktualisierung:** 9. April 2026 (Universal CSV Agent-Guide, Abgleich-Tabelle)
|
||||
@@ -0,0 +1,317 @@
|
||||
# Activity Session Metrics: Composite-Daten (EAV) – Umsetzungskonzept
|
||||
|
||||
**Stand:** 2026-04-16
|
||||
**Status:** Normatives Konzept zur nahtlosen Weiterarbeit durch Code-Agenten
|
||||
**Bezieht sich auf:** `ACTIVITY_PRODUCTION_ARCHITECTURE_AND_PHASES.md` (§2.3–2.4, Phasen D–E), `ACTIVITY_SESSION_METRICS_EAV_AGENT_GUIDE.md`, Issue #53 (Layer-1-Prinzip: Auswertungen nur über `data_layer`)
|
||||
|
||||
---
|
||||
|
||||
## 1. Ziel und Abgrenzung
|
||||
|
||||
### 1.1 Ziel
|
||||
|
||||
- **Composite-Messgrößen** (strukturierte Werte mit mehreren benannten Slots) werden wie **normale Trainingsparameter** im Katalog geführt, **Kategorie-/Typ-Profilen** zugeordnet und pro Session in der **EAV-Tabelle** persistiert.
|
||||
- **Persistenz:** ein JSON-Dokument pro Session und `training_parameter_id` (kanonisch **JSONB**), kompatibel mit der bestehenden „eine Zeile pro Parameter“-Semantik.
|
||||
- **Import:** CSV liefert typischerweise **eine Spalte pro atomarem Slot**; das Mapping verweist auf **`(Parameter-Key, Slot-Key)`** (stabile Strings, nicht Spaltenreihenfolge).
|
||||
- **Layer 1:** liefert für Consumer weiterhin **eine konsistente API**: Rohdokument **und** optional **aufgelöste Einzelwerte** (flach oder namenspaced), ohne dass Charts/Platzhalter direkt JSON parsen müssen.
|
||||
|
||||
### 1.2 Nicht-Ziele (explizit)
|
||||
|
||||
- Kein „freies“ JSON-Schema im Admin ohne Archetyp-Bindung (verhindert Datenmüll und nicht validierbare Dokumente).
|
||||
- Keine Abschwächung bestehender **Skalar-Parameter** (`integer`, `float`, `string`, `boolean`): alle bisherigen Pfade bleiben gültig.
|
||||
- Kein Ersatz für `activity_log`-**Spine** oder Session-Qualitätsblobs (`evaluation`, …).
|
||||
|
||||
### 1.3 Kompatibilitätsgarantie („keine Regression“)
|
||||
|
||||
| Bereich | Maßnahme |
|
||||
|---------|----------|
|
||||
| DB | Nur **additive** Migrationen; bestehende `CHECK`-Regeln für Skalare bleiben für Zeilen **ohne** Composite erhalten bzw. werden zu einer **Oder-Verknüpfung** erweitert (siehe §4). |
|
||||
| `training_parameters` | Neuer `data_type`-Wert **`composite`** zusätzlich zu den vier bestehenden; bestehende CHECK-Constraint muss erweitert werden (Migration). |
|
||||
| `activity_session_metrics` | Skalare Zeilen unverändert; Composite-Zeilen nutzen **`value_json`** (neu), alle `value_*` NULL. |
|
||||
| Layer 1 | `resolve_activity_attribute_schema`, Merge, Replace: Composite erscheint als **ein** Schema-Eintrag; Lese-/Schreibpfade erweitern, nicht ersetzen. |
|
||||
| CSV | Bestehende Map-Ziele auf Skalare/Registry unverändert; neue Zielnotation nur für Composites. |
|
||||
| Admin | tcp/ttp-UI: gleiche Zuordnung wie heute; Zusatzfelder nur bei `data_type === composite`. |
|
||||
|
||||
### 1.4 Abgleich mit `functional_concept_composite_data.md` (fachliches Konzept)
|
||||
|
||||
Das **fachliche Konzeptpapier** (Composite Scalar/Layer-Trennung) und dieses **Umsetzungskonzept** sind **vereinbar**, wenn die Rollen klar getrennt bleiben:
|
||||
|
||||
| Thema | Fachliches Konzept (`functional_concept_composite_data.md`) | Dieses Umsetzungskonzept (technisch) |
|
||||
|--------|-------------------------------------------------------------|--------------------------------------|
|
||||
| **Speicher in der DB** | Einheitlicher Store; Composite = `jsonb` mit **kleinem Basisschema** (`v`, `kind`, `domain`, `items`, optional `basis`, `meta`) | `activity_session_metrics.value_json`; CHECK Skalar vs. Composite |
|
||||
| **Technische Container** | Genau **vier** `kind`-Werte: `group_set`, `distribution_set`, `sequence_set`, `model_set` | Layer-1-Validierung **muss** diese Hülle durchsetzen; kein freies JSON ohne `kind`/`v`/`items` |
|
||||
| **„Archetypen“** | **Fachliche** Ausprägungen werden in **Layer 2a** aus L1-Objekten abgeleitet | Benannte **Preset-/Validierungsprofile** im Code (z. B. Zonenverteilung HF) sind **kein** zweites Persistenz-Schema: sie legen fest, *welches* der vier `kind`-Muster, *welches* `domain`, *welche* Item-Keys/Typen erlaubt sind — inkl. CSV-Slot-Mapping |
|
||||
| **Layer 1** | Validiert, minimal normalisiert, **keine** Scores/Bewertungen/KI-Texte | Validator + Merge + optional `expand_*` (**technische** Flachstellung für Consumer, z. B. `param.slot` → Skalar) |
|
||||
| **Layer 2** | Diagramme, Kennzahlen, KI-Platzhalter-**Formulierung** | unverändert; konsumiert L1 (und ggf. L2a) |
|
||||
|
||||
**Konsequenz für die Registry:** Statt „8 freie JSON-Archetypen“ implementiert die Code-Registry **Validierungs-Presets**, die alle auf die **vier technischen `kind`-Formen** abbilden. Die Tabelle in §3 beschreibt weiterhin **fachlich benannte MVP-Anker** — technisch übersetzen sie sich in `(kind, domain, Item-Regeln, v)`.
|
||||
|
||||
**Konsequenz für Platzhalter:** Roh-JSON aus der DB **nicht** ungefiltert in Prompts; L2b nutzt L1/L2a-Aufbereitung (wie im fachlichen Konzept).
|
||||
|
||||
---
|
||||
|
||||
## 2. Begriffe
|
||||
|
||||
| Begriff | Bedeutung |
|
||||
|---------|-----------|
|
||||
| **Archetyp** | Im **Repo versionierte** Strukturvorlage (erlaubte Slots, Typen, Pflichtfelder, Validator, Version). **7–8** Stück geplant; Erweiterung nur per Code-Release. |
|
||||
| **Slot** | Benanntes Teilfeld innerhalb des Composite-Dokuments, z. B. `z1_sec`, `z2_sec`, `avg_cadence`. |
|
||||
| **Parameter-Instanz** | Eine Zeile in `training_parameters` mit `data_type = composite` und Metadaten, **welcher** Archetyp gilt (siehe §5). |
|
||||
| **Dokument** | Ein JSON-Objekt, das alle Slots abbildet; gespeichert in `activity_session_metrics.value_json`. |
|
||||
|
||||
---
|
||||
|
||||
## 3. Archetypen-Katalog (Planungsstand) — fachliche Namen → technische `kind`-Presets
|
||||
|
||||
Die **konkrete** Slot-Liste und Validierung wird im Code als **Registry** geführt (z. B. `backend/data_layer/activity_composite_archetypes.py`). Jedes Preset **mappt** auf genau eines von **`group_set` | `distribution_set` | `sequence_set` | `model_set`** und erfüllt das **Basisschema** aus `functional_concept_composite_data.md` §7.
|
||||
|
||||
Inhaltlich orientiert an `ACTIVITY_PRODUCTION_ARCHITECTURE_AND_PHASES.md` §2.4.
|
||||
|
||||
**Beispielhafte fachliche MVP-Anker** (8 Kandidaten; im Code als Preset-Key + `kind`/`domain` abbilden):
|
||||
|
||||
| `archetype_key` (stabil) | Kurzbeschreibung | Typische Slots (Beispiel) |
|
||||
|--------------------------|------------------|---------------------------|
|
||||
| `hr_zone_distribution` | Zeit-/Anteil je HF-Zone | `z1_sec`…`z5_sec` oder `zones[]` |
|
||||
| `power_zone_distribution` | Leistungszonen | analog |
|
||||
| `pace_band_profile` | Pace-Bänder / Histogramm | bucket-Struktur |
|
||||
| `interval_block_summary` | Intervallblöcke aggregiert | `blocks[]` mit Dauer, Ziel, Ist |
|
||||
| `event_marker_sequence` | Ereignisse mit Zeitstempel | `events[]` |
|
||||
| `coupling_efficiency_profile` | Kopplungs-/Effizienzmetriken | sportabhängig |
|
||||
| `model_parameter_profile` | Modell-/Schwellenparameter | key-value-ähnlich, validiert |
|
||||
| `readiness_recovery_snapshot` | optional: kurzes Multi-Signal-Bundle | nur wenn fachlich gewünscht |
|
||||
|
||||
**Regel:** Jeder Archetyp hat `version` (Integer). Validator lehnt Dokumente mit falscher/fehlender Version ab oder migriert definiert (nur wenn spezifiziert).
|
||||
|
||||
---
|
||||
|
||||
## 4. Datenmodell-Erweiterungen
|
||||
|
||||
### 4.1 `training_parameters`
|
||||
|
||||
**Migration (additiv):**
|
||||
|
||||
1. `CHECK (data_type IN (...))` erweitern um **`composite`**.
|
||||
2. Optional eigene Spalte **`composite_archetype_key` `VARCHAR(64)`** (NOT NULL wenn `data_type = composite`, sonst NULL) — **oder** ausschließlich in `validation_rules` speichern (siehe unten).
|
||||
**Empfehlung:** Spalte `composite_archetype_key` + `composite_archetype_version INT` für einfache Admin-Queries und klare Semantik; `validation_rules` für archetyp-spezifische Feinheiten (z. B. erlaubte Zonenanzahl).
|
||||
|
||||
**Konsistenz-Constraint (DB oder App):**
|
||||
|
||||
- Wenn `data_type = composite`: `composite_archetype_key` gesetzt, `source_field` typischerweise **NULL** (kein `activity_log`-Skalar-Shadowing).
|
||||
- `unit` am Parameter: optional für „Anzeige-Einheit“ des Gesamtwerts oder leer; Slots haben Einheiten im Archetyp oder in Slot-Metadaten.
|
||||
|
||||
### 4.2 `activity_session_metrics`
|
||||
|
||||
**Migration (additiv):**
|
||||
|
||||
```text
|
||||
value_json JSONB NULL
|
||||
```
|
||||
|
||||
**CHECK-Constraint ersetzen/erweitern** (Konzept):
|
||||
|
||||
- **Modus Skalar:** genau eine der Spalten `value_num`, `value_int`, `value_text`, `value_bool` ist NOT NULL; `value_json` IS NULL.
|
||||
- **Modus Composite:** `value_json` IS NOT NULL; alle vier Skalar-Spalten IS NULL.
|
||||
|
||||
Damit bleibt die bestehende Semantik „eine Zeile = ein Parameter“ erhalten.
|
||||
|
||||
**Kommentar:** Tabelle trägt weiterhin „EAV“; Composites sind **keine** zusätzlichen Zeilen pro Slot.
|
||||
|
||||
### 4.3 Profil-Zuordnung (tcp / ttp)
|
||||
|
||||
**Keine** Tabellenänderung: `training_category_parameter` und `training_type_parameter` verweisen weiter nur auf `training_parameter_id`. Composite-Parameter verhalten sich wie Skalare in Bezug auf **Zuordnung**, **sort_order**, **required**, **ui_group**.
|
||||
|
||||
**`required`:** bedeutet „Dokument muss nach Validator vollständig sein“, nicht „jede CSV-Spalte muss in jeder Zeile vorkommen“.
|
||||
|
||||
---
|
||||
|
||||
## 5. Metadaten pro Composite-Parameter
|
||||
|
||||
Minimal in der DB (Beispiel):
|
||||
|
||||
| Feld | Zweck |
|
||||
|------|--------|
|
||||
| `data_type` | `composite` |
|
||||
| `composite_archetype_key` | Verweis auf Code-Registry |
|
||||
| `composite_archetype_version` | Schema-Version |
|
||||
| `validation_rules` | optional: Overrides (z. B. `max_zones`, sport-spezifisch) — nur was der Validator explizit auswertet |
|
||||
|
||||
**Admin-API:** bestehende Endpoints erweitern (Payload-Validierung): bei `composite` müssen Archetyp + Version gesetzt sein und in der **Registry** existieren.
|
||||
|
||||
---
|
||||
|
||||
## 6. Layer 1 – Kontrakt (`activity_session_metrics.py` + Helfer)
|
||||
|
||||
### 6.1 Schema-Auflösung
|
||||
|
||||
`resolve_activity_attribute_schema` liefert pro Composite **einen** Eintrag wie bei Skalaren, mit:
|
||||
|
||||
- `data_type: "composite"`
|
||||
- `composite_archetype_key`, `composite_archetype_version` (aus DB oder Join)
|
||||
- ggf. `composite_slot_catalog`: **nur wenn** für Admin/UI gewünscht — alternativ separater Endpoint `GET .../composite-archetypes` (read-only) aus Registry, um Bundle-Größe klein zu halten.
|
||||
|
||||
### 6.2 Lesen / Merge
|
||||
|
||||
- `fetch_activity_session_metrics`: SELECT inkl. `value_json`.
|
||||
- `merge_column_backed_and_eav_metrics`: Composites **nur** aus EAV (`value_json`), kein `activity_log`-Shadowing (außer später explizit im Kanon — Standard: nein).
|
||||
- Ausgabe in `metrics`-Liste: ein Eintrag pro Parameter mit z. B.
|
||||
`value: { "_composite": true, "document": { ... } }` **oder** kanonisch getrennt: `value_document` + `value` null — **festlegen beim Implementieren** und in API-Doku halten; Empfehlung: **`value` = deserialisiertes Objekt (dict)** für Composites, damit Frontend dieselbe Struktur wie Speicher hat.
|
||||
|
||||
### 6.3 „Einzelwerte für Layer 1 / Issue 53“
|
||||
|
||||
Neue **pure** Funktion (kein SQL im Router), z. B.:
|
||||
|
||||
```text
|
||||
expand_composite_metrics_for_session(
|
||||
schema: list[dict],
|
||||
metrics: list[dict],
|
||||
) -> dict[str, Any]
|
||||
```
|
||||
|
||||
- Input: effektives Schema + gemergte Metriken.
|
||||
- Output: flaches Dict **`slot_path → typisierter Wert`**, z. B.
|
||||
`hr_zones.z1_sec → 1200`, oder namespaced Keys `training_param_key.slot_key` zur Kollisionssicherheit.
|
||||
- Nutzung: `activity_metrics`, Chart-Builder, später Platzhalter-Registry (`data_layer_function`), **ohne** JSON-Parsing in Layer 2.
|
||||
|
||||
**Wichtig:** Skalare Parameter erscheinen im expandierten Dict mit ihrem `parameter_key` wie bisher (kein Breaking Change für Consumer, die nur Skalare erwarten).
|
||||
|
||||
### 6.4 Validierung / Schreiben
|
||||
|
||||
- **`replace_activity_session_metrics`:** Payload-Item für Composite: `value` ist **Objekt** (dict) oder JSON-String — Server normalisiert zu dict, validiert mit Archetyp-Validator, speichert als `value_json`.
|
||||
- **`upsert_session_metrics_from_csv_mapped`:** siehe §7 (Zusammenbau aus Partial-Updates pro Zeile).
|
||||
|
||||
**Pflicht:** Keine Teil-Updates in DB, die ein halbes Dokument hinterlassen, ohne Validierung — außer explizit als „Draft“-Modus spezifiziert (nicht Teil dieses Konzepts).
|
||||
|
||||
---
|
||||
|
||||
## 7. CSV / Universal Import
|
||||
|
||||
### 7.1 Map-Ziel-Notation
|
||||
|
||||
Stabiles Muster (Vorschlag, im Import-Modul zentral parsen):
|
||||
|
||||
```text
|
||||
"<parameter_key>.<slot_key>"
|
||||
```
|
||||
|
||||
Beispiel: `my_hr_zones.z1_sec` → nach Import-Zusammenfügung in den Parameter `my_hr_zones` unter Slot `z1_sec`.
|
||||
|
||||
**Alternative:** explizites Präfix `composite:` in der Vorlage — nur nötig, wenn Kollisionen mit normalen Keys befürchtet werden; sonst Punkt-Notation reicht.
|
||||
|
||||
### 7.2 Executor-Flow (Konzept)
|
||||
|
||||
1. `build_row_after_mapping` liefert flache Keys inkl. `param.slot`.
|
||||
2. Nach Schreiben von `activity_log` / Skalar-EAV: **Composite-Accumulator** pro `activity_log_id` und `parameter_key`:
|
||||
- Sammelt alle Slot-Werte aus der Zeile.
|
||||
3. Vor Commit der Zeile (oder am Ende der Datei — **pro Zeile empfohlen**, damit SAVEPOINT pro Row funktioniert):
|
||||
- Dokument aus Slots bauen → Validator → Upsert `activity_session_metrics` mit `value_json`.
|
||||
|
||||
**Teilbefüllung:** Validator entscheidet (Archetyp: optional vs. required Slots). CSV darf nur Teilmengen liefern, wenn Archetyp erlaubt.
|
||||
|
||||
### 7.3 Typkonvertierung
|
||||
|
||||
Pro **Slot** im Archetyp: definierter skalarer Typ (`float`, `int`, …). Converter wie bei Skalaren (Executor / zentrale Converter), **keine** Parallel-Logik in Routern.
|
||||
|
||||
---
|
||||
|
||||
## 8. Admin-UI / Mapping-UX
|
||||
|
||||
### 8.1 Parameter anlegen
|
||||
|
||||
- Auswahl **Datentyp „Composite“** → Dropdown **Archetyp** (aus Registry-API), Version readonly oder wählbar gemäß Policy.
|
||||
- Rest wie Skalar: Name, Kategorie (`training_parameters.category`), Aktiv-Flag.
|
||||
|
||||
### 8.2 Profil zuordnen
|
||||
|
||||
Unverändert: Kategorie-/Typ-Matrix wie heute.
|
||||
|
||||
### 8.3 Universal-CSV-Vorlage
|
||||
|
||||
- Mapping-Ziele: neben bisherigen Keys **Slot-Ziele** `parameter_key.slot_key`.
|
||||
- UI-Gruppierung: optisch **Composite-Block** (wie in `ACTIVITY_PRODUCTION_ARCHITECTURE` §2.5 angedeutet), um Verwechslung mit Spine-Spalten zu vermeiden.
|
||||
|
||||
---
|
||||
|
||||
## 9. API-Oberflächen (Erweiterungen)
|
||||
|
||||
| Bereich | Änderung |
|
||||
|---------|-----------|
|
||||
| `GET /api/activity/{id}` | `metrics` enthält Composite-Werte als Objekt; `schema` kennzeichnet `data_type: composite`. |
|
||||
| `PUT /api/activity/{id}/metrics` | Eintrag `{ parameter_key, value: { ... } }` für Composites. |
|
||||
| Admin `training-parameters` | Create/Update mit Composite-Feldern. |
|
||||
| Optional | `GET /api/admin/composite-archetypes` | Registry export für UI (Keys, Slot-Liste, Version). |
|
||||
|
||||
**Rückwärtskompatibilität:** Clients, die nur Skalare senden, unverändert.
|
||||
|
||||
---
|
||||
|
||||
## 10. Frontend (Kurz)
|
||||
|
||||
- `ActivityPage` / Session-Metrik-Editor: für `data_type === composite` **strukturierte Teilfelder** aus Slot-Katalog rendern (oder JSON-Editor nur als Entwickler-Fallback — Produkt: strukturierte Felder).
|
||||
- Sortierung/Gruppierung: bestehende `param_category` / `ui_group` / `sort_order` gelten unverändert.
|
||||
|
||||
---
|
||||
|
||||
## 11. Tests (pytest)
|
||||
|
||||
| Test | Beschreibung |
|
||||
|------|----------------|
|
||||
| Archetyp-Validator | gültige / ungültige Dokumente je Version |
|
||||
| DB-Constraint | Skalar vs. Composite Ausschluss |
|
||||
| `expand_composite_metrics_for_session` | flache Keys, Kollisionen |
|
||||
| CSV-Zusammenbau | mehrere Spalten → ein `value_json` |
|
||||
| Regression | bestehende `test_activity_session_metrics.py` unverändert grün halten |
|
||||
|
||||
---
|
||||
|
||||
## 12. Rollout-Phasen (operativ)
|
||||
|
||||
Stimmt mit `ACTIVITY_PRODUCTION_ARCHITECTURE_AND_PHASES.md` überein:
|
||||
|
||||
1. **Phase D – MVP:** ein Preset (z. B. HF-Zonen → `distribution_set`, `domain: heart_rate`), Migration `value_json` + `composite` data_type, Validator gegen Basisschema §7, Import 3–5 Spalten → `items`, GET/PUT, minimale Admin-Anbindung.
|
||||
2. **Phase E:** weitere Presets / `kind`-Varianten, Mapping-UX, `expand_*` für ausgewählte Layer-1-Consumer.
|
||||
3. **Phase F:** Observability, Performance, Doku, Gitea-Issues schließen.
|
||||
|
||||
### 12.1 Empfohlene Reihenfolge: Skalar-Pipeline vs. Composite-Speicherung
|
||||
|
||||
**Frage:** Zuerst Skalar-EAV vollständig bis Platzhalter/Orchestrator abschließen, oder zuerst Composite-Speicherung?
|
||||
|
||||
| Option | Vorteil | Risiko |
|
||||
|--------|---------|--------|
|
||||
| **A: Nur Skalar zuerst** (Kanon, L1-Härtung, Platzhalter aus EAV/L1) | Eine klare, end-to-end **Referenzpipeline**; weniger gleichzeitige Variablen | Composite-Datenstrome verzögern sich |
|
||||
| **B: Composite-Speicher zuerst** | JSON landet früh in der DB | Platzhalter/Charts nutzen noch **alte** Pfade → **zwei Wahrheiten** (Detail-API vs. KI) bis L1 vereinheitlicht ist |
|
||||
| **C (Empfehlung): Skalar L1 + Platzhalter-Orchestrierung *vor* Composite-MVP**, oder **eng parallel** mit gemeinsamem L1-Einstieg | `get_activity_session_logical_unit` / `activity_metrics` werden **kanonisch**; Platzhalter lesen **dieselbe** Schicht; Composite wird **additiv** (`value_json` + Validator + später `expand_*`) | Erfordert kurze Planungsdisziplin: Composite-MVP **ohne** sofort alle KI-Platzhalter |
|
||||
|
||||
**Konkrete Empfehlung**
|
||||
|
||||
1. **`ACTIVITY_PRODUCTION` Phase A–B** nicht überspringen: Kanon „eine Semantik / eine Quelle“ + alle relevanten Consumer über **Layer 1** (mind. Session-Detail, Listen-Anreicherung, erste Platzhalter-Pfade für **Skalare**).
|
||||
2. **Dann Phase D (Composite-MVP):** Migration + Speichern/Lesen mit **Basisschema** (`kind`/`items`/…); L1 liefert dasselbe API-Objekt wie Skalare, nur `value` als strukturiertes Dokument.
|
||||
3. **Platzhalter für Composite:** erst **nach** L1 liefert stabil `value_json` **und** optional `expand_composite_metrics_*` — ein Orchestrator-Endpoint bzw. Resolver-Aufruf, der **eine** L1-Funktion nutzt, vermeidet doppelte Logik für Skalar vs. Composite.
|
||||
|
||||
**Kurz:** Composite **persistieren** kann kurz nach stabiler **Skalar-Lese-/Merge-API** folgen; **KI/Platzhalter für Composite** sinnvoll **gemeinsam** mit der erweiterten L1-Ausgabe bauen, nicht gegen eine noch nicht vereinheitlichte Skalar-Pipeline.
|
||||
|
||||
---
|
||||
|
||||
## 13. Checkliste für den nächsten Agenten
|
||||
|
||||
- [ ] Migration: `value_json`, erweiterte CHECKs, `training_parameters.data_type` + ggf. `composite_archetype_*` Spalten.
|
||||
- [ ] Registry-Modul: Archetypen + Versionen + Slot-Metadaten + Validator-Einstieg.
|
||||
- [ ] `activity_session_metrics.py`: Fetch/Merge/Replace/Upsert-Integration; keine Regression für Skalare.
|
||||
- [ ] Optional: `expand_composite_metrics_for_session` + erste Nutzung in einem Layer-1-Consumer (Tests).
|
||||
- [ ] CSV: Parser für `parameter_key.slot_key`, Row-Accumulator, Fehler melden wie bestehender Import.
|
||||
- [ ] Admin-API + UI: Composite anlegen, tcp/ttp unverändert nutzbar.
|
||||
- [ ] Doku: dieses Dokument mit **festgelegter** JSON-Beispielstruktur pro MVP-Archetyp ergänzen.
|
||||
|
||||
---
|
||||
|
||||
## 14. Referenzen
|
||||
|
||||
- `functional_concept_composite_data.md` – **fachliches** Schichtenmodell, vier technische `kind`-Container, Basisschema JSON
|
||||
- `ACTIVITY_PRODUCTION_ARCHITECTURE_AND_PHASES.md` – Zielbild, Phasen A–F
|
||||
- `ACTIVITY_SESSION_METRICS_EAV_AGENT_GUIDE.md` – Ist-Layer-1, APIs
|
||||
- `UNIVERSAL_CSV_IMPORT_AGENT_GUIDE.md` – Executor, Vorlagen
|
||||
- Migration `054_activity_session_metrics_eav.sql` – Ist-Constraint Skalar
|
||||
- Migration `013_training_parameters.sql` – Ist-`data_type`-Enum
|
||||
|
||||
---
|
||||
|
||||
**Version:** 1.1 · Abgleich mit fachlichem Konzept (§1.4, §3, §12.1); MVP auf `distribution_set` o. ä. konkretisieren.
|
||||
@@ -0,0 +1,70 @@
|
||||
# Aktivität: Layer-2a-Platzhalter — Audit Schritt 1 (Issue #53)
|
||||
|
||||
**Stand:** 2026-04-16
|
||||
**Bezug:** [Issue #53 — Multi-Layer Architecture](../../../docs/issues/issue-53-phase-0c-multi-layer-architecture.md): Layer 1 = strukturierte Daten, Layer 2a = KI-Formatierung (keine parallele Domänen-Logik im Resolver).
|
||||
|
||||
**Ziel dieses Dokuments:** Jeder Aktivitäts-Platzhalter hat genau eine **Layer‑1‑Quelle** (`data_layer/activity_metrics.py`); `placeholder_resolver.py` formatiert oder serialisiert nur noch.
|
||||
|
||||
---
|
||||
|
||||
## 1. Ergebnisübersicht
|
||||
|
||||
| Kategorie | Anzahl | Resolver-SQL für Aktivität? |
|
||||
|-----------|--------|------------------------------|
|
||||
| Gebündelt in `PLACEHOLDER_MAP` (Training/Aktivität) | 20 | **Nein** |
|
||||
| Abweichungen / offene Punkte | 0 | — |
|
||||
|
||||
**Hinweis:** `{{rest_days_count}}` steht in der Karte unter „Schlaf & Erholung“ und nutzt `recovery_metrics.get_rest_days_data` — nicht in dieser Tabelle.
|
||||
|
||||
---
|
||||
|
||||
## 2. Platzhalter → Layer 1 → Layer 2a
|
||||
|
||||
| Key | Layer 1 (`activity_metrics`) | Layer 2a (`placeholder_resolver`) | Bemerkung |
|
||||
|-----|------------------------------|-------------------------------------|-----------|
|
||||
| `activity_summary` | `get_activity_summary_data` | `get_activity_summary` | String-Zusammenfassung |
|
||||
| `activity_detail` | `get_activity_detail_data` (+ `enrich_sessions_with_metrics`) | `get_activity_detail` | Dynamische `session_metrics[]` pro Zeile (Profil/EAV) |
|
||||
| `trainingstyp_verteilung` | `get_training_type_distribution_data` | `get_trainingstyp_verteilung` | Ausgabe: Top-3-Text (kein JSON); Registry 2026-04 an Ist angeglichen |
|
||||
| `training_minutes_week` | `calculate_training_minutes_week` | `_safe_int` | |
|
||||
| `training_frequency_7d` | `calculate_training_frequency_7d` | `_safe_int` | |
|
||||
| `quality_sessions_pct` | `calculate_quality_sessions_pct` | `_safe_int` | |
|
||||
| `proxy_internal_load_7d` | `calculate_proxy_internal_load_7d` | `_safe_int` | |
|
||||
| `monotony_score` | `calculate_monotony_score` | `_safe_float` | |
|
||||
| `strain_score` | `calculate_strain_score` | `_safe_int` | |
|
||||
| `rest_day_compliance` | `calculate_rest_day_compliance` | `_safe_int` | |
|
||||
| `ability_balance_strength` | `calculate_ability_balance_strength` | `_safe_int` | abilities in `activity_log` |
|
||||
| `ability_balance_endurance` | `calculate_ability_balance_endurance` | `_safe_int` | |
|
||||
| `ability_balance_mental` | `calculate_ability_balance_mental` | `_safe_int` | |
|
||||
| `ability_balance_coordination` | `calculate_ability_balance_coordination` | `_safe_int` | |
|
||||
| `ability_balance_mobility` | `calculate_ability_balance_mobility` | `_safe_int` | |
|
||||
| `vo2max_trend_28d` | `calculate_vo2max_trend_28d` | `_safe_float` | |
|
||||
| `activity_score` | `calculate_activity_score` | `_safe_int` | |
|
||||
| `training_frequency_by_type_md` | `get_training_frequency_by_type_data` | `get_training_frequency_by_type_md` | Markdown-Tabelle |
|
||||
| `training_inter_session_gap_md` | `get_training_inter_session_gap_data` | `get_training_inter_session_gap_md` | Markdown-Text |
|
||||
| `training_sessions_recent_json` | `get_training_sessions_recent_weeks_data` (+ `enrich_sessions_with_metrics`) | `_safe_json('training_sessions_recent_json')` | JSON inkl. `session_metrics[]` pro Session |
|
||||
|
||||
---
|
||||
|
||||
## 3. Schichten-Disziplin (Checkliste)
|
||||
|
||||
- [x] Kein `SELECT` auf `activity_log` / `activity_session_metrics` in den **Layer‑2a**-Funktionen oben — nur Aufrufe in Layer 1 bzw. `_safe_*`-Wrapper.
|
||||
- [x] `get_activity_detail` / `get_training_sessions_recent_json` liefern EAV nur über **bereits gemergte** `session_metrics` (Merge-Kanon: `activity_log` vor EAV).
|
||||
- [x] Registry-Metadaten: `data_layer_module` / `data_layer_function` pro Key in `placeholder_registrations/activity_metrics.py` und `activity_session_insights.py`.
|
||||
- [x] Korrektur Registry: `activity_summary.resolver_function` = `get_activity_summary` (war veraltet: `_format_activity_summary`).
|
||||
|
||||
---
|
||||
|
||||
## 4. Nächste Schritte (Roadmap)
|
||||
|
||||
2. ~~**Registry-Texte:** `semantic_contract` / `known_limitations` für dynamische `session_metrics` (tcp/ttp) und Merge-Kanon — **erledigt** (`activity_detail`, `training_sessions_recent_json`); dazu **`trainingstyp_verteilung`**-Metadaten von veraltetem „JSON/Resolver-SQL“ auf Ist (**Layer 1 + Top-3-Text**) korrigiert.~~
|
||||
3. **History / Layer 2b:** EAV-Zeitreihen nicht über Platzhalter, sondern dedizierte Layer‑1-/Chart-Pfade.
|
||||
4. **Optional:** Gitea-Issue „Activity Layer 2a“ bei Änderungen an `activity_metrics` pflegen.
|
||||
|
||||
---
|
||||
|
||||
## 5. Referenzen
|
||||
|
||||
- `backend/placeholder_resolver.py` — `PLACEHOLDER_MAP` (Training/Aktivität)
|
||||
- `backend/placeholder_registrations/activity_metrics.py`
|
||||
- `backend/placeholder_registrations/activity_session_insights.py`
|
||||
- `ACTIVITY_PRODUCTION_ARCHITECTURE_AND_PHASES.md` §2.1a (Navigation Read vs. Berechnen)
|
||||
@@ -0,0 +1,215 @@
|
||||
# Aktivität: Zielarchitektur & Phasenplan (Produktionsreife)
|
||||
|
||||
**Stand:** 2026-04-16
|
||||
**Status:** Normative Zielrichtung für `activity_log`, EAV, Composites, Import, Layer 1/2.
|
||||
**Ergänzt:** `ACTIVITY_SESSION_METRICS_EAV_AGENT_GUIDE.md` (Ist-Modell, APIs, Tests).
|
||||
**Phase A:** abgeschlossen — Kanon-Tabelle [`ACTIVITY_SCALAR_KANON_TABLE.md`](./ACTIVITY_SCALAR_KANON_TABLE.md).
|
||||
**Phase B:** in Arbeit — Consumer-Audit und Lesepfad-Härtung (siehe §4 Phase B).
|
||||
|
||||
---
|
||||
|
||||
## 1. Leitprinzipien
|
||||
|
||||
| Prinzip | Bedeutung |
|
||||
|---------|-----------|
|
||||
| **Layer 1 = Single Source of Truth** | Alle Auswertungen (Charts, Scores, strukturierte Platzhalter) lesen **nur** über `data_layer` (kanonische Funktionen). Keine parallele SQL-Logik in Routern oder im Placeholder-Resolver für Aktivität. |
|
||||
| **Eine semantische Größe, eine kanonische Quelle** | Kein Dauer-Sync derselben Bedeutung in `activity_log`-Spalte **und** EAV. Übergang: dokumentierte Abschaltung, nicht implizites Driften. |
|
||||
| **Spine vs. Parameter** | `activity_log` trägt Identität, Zeit, Typ, Notizen, Audit + **heiße** universelle Skalare (siehe §2.2). Alles Typ-/Admin-Dynamische über EAV. |
|
||||
| **Composites = Archetyp im Code, Konfiguration in der DB** | Struktur (7+2 Archetypen) und Validierung **versioniert im Repo**; Admin **wählt** Archetyp, **benennt** Slots, **bindet** Sportarten, **mappt** CSV → `(parameter_id, slot_key)`. Kein freies JSON-Schema im Admin. |
|
||||
| **Import explizit** | Jede CSV-Spalte hat ein klares Ziel: Spine-Spalte, skalarer Parameter oder **Slot** eines Composite-Parameters. Typkonvertierung zentral (Executor / Converter), nicht verteilt. |
|
||||
|
||||
---
|
||||
|
||||
## 2. Zielarchitektur (Gesamtbild)
|
||||
|
||||
### 2.1 Schichtenmodell
|
||||
|
||||
```
|
||||
[CSV / UI / API Write]
|
||||
↓
|
||||
Orchestrator & Router (Auth, Transaktionen, Feature-Checks)
|
||||
↓
|
||||
Persistenz: activity_log (Spine + heiße Skalare) + activity_session_metrics (EAV)
|
||||
↓
|
||||
Layer 1: data_layer (activity_session_metrics.py, activity_metrics.py, …)
|
||||
↓
|
||||
Layer 2a/2b: Platzhalter-Resolver (Formatierung), Chart-Endpoints (Chart.js-Shapes)
|
||||
↓
|
||||
KI / UI / Export
|
||||
```
|
||||
|
||||
- **Orchestrator:** Schreibpfad, Konsistenz nach Write (kein zweites „Lesen der Wahrheit“ neben Layer 1; optional nur Post-Write-Hooks).
|
||||
- **Resolver:** für Aktivität **kein** direkter DB-Zugriff; nur Aufruf von Layer 1.
|
||||
|
||||
### 2.1a Navigationsregel: wo nachsehen (ohne Datei-Zwang)
|
||||
|
||||
Die **physische** Aufteilung ist dreigeteilt: **`activity_log`** (Spine + heiße Spalten), **EAV-Skalare** (`activity_session_metrics` + numerische/textuelle `value_*`), **EAV-Composites** (ein Parameter, Nutzlast z. B. JSON/JSONB im EAV-Datensatz). **Fachlich** soll nach außen **eine homogene Session-Sicht** entstehen — Consumer sollen nicht selbst entscheiden, aus welcher Tabelle/Welche Form ein Wert kommt.
|
||||
|
||||
| Thema | Wo nachsehen (Ist; Ziel: Schnittstelle stabil, Datei optional splittbar) |
|
||||
|--------|--------------------------------------------------------------------------|
|
||||
| **Homogene Session lesen** (Merge Spalte + EAV-Skalare + später Composite-Payload) | `data_layer/activity_session_metrics.py` — u. a. `get_activity_session_logical_unit`, `enrich_sessions_with_metrics`, `merge_column_backed_and_eav_metrics` |
|
||||
| **Schreiben / Import / API-Persistenz** | `data_layer/activity_persistence_orchestrator.py` (+ Router) |
|
||||
| **Berechnungen, Aggregationen, Scores** über viele Sessions oder Zeitfenster | `data_layer/activity_metrics.py` — arbeitet auf der **vereinheitlichten** Session-Datenlage (über die Read-Funktionen oben), nicht durch paralleles Mergen der drei Quellen im Caller |
|
||||
|
||||
**Hinweis:** Orchestrator und Read-Merge **müssen nicht** in derselben Datei stehen. Entscheidend ist, dass es **genau eine dokumentierte Read-Fassade** für „Session inkl. aller effektiven Metriken“ gibt und Layer‑1‑Berechnungen **nur** diese Fassade (oder deren Ergebnisstrukturen) nutzen. Eine spätere Umbenennung oder Auslagerung in z. B. `activity_read_gateway.py` ändert die Rolle nicht — nur der **eine Einstieg** muss in dieser Doku und im Code auffindbar bleiben.
|
||||
|
||||
### 2.2 `activity_log` (Spine + heiße Skalare)
|
||||
|
||||
**Maschinenlesbarer Kanon:** `backend/data_layer/activity_data_canon.py` (`ACTIVITY_MODULE_REGISTRY_FIELD_KEYS`, `ACTIVITY_EAV_PRIMARY_PARAMETER_KEYS`, Legacy-Lesefallback für EAV-primäre Parameter).
|
||||
|
||||
**Immer (fachlich minimal + listenfähig):** `id`, `profile_id`, Kalender-/Zeitfenster (`date`, `started_at`/`ended_at`, ggf. `start_time`/`end_time` bis Konsolidierung), `duration_min`, `training_type_id` (+ ggf. denormalisierte Kategorie), Legacy `activity_type`, `notes`, `source`, `created`.
|
||||
|
||||
**Heiße Skalare (CSV-Modul + `source_field` nach Migration 057):** u. a. `kcal_active`, `kcal_resting`, `distance_km`, `hr_avg`/`hr_max` (Parameter `avg_hr`/`max_hr`), `duration_min`, `rpe` – für Listen und Standard-Aggregate ohne EAV-Join.
|
||||
|
||||
**EAV-primär (erweiterte Metriken):** z. B. Kadenz, Pace, Leistung, Höhe, Umgebung — `training_parameters.source_field` = NULL; Import schreibt EAV; bei leerem EAV optional Lesefallback auf bestehende `activity_log`-Spalte (Migration 057 + Merge-Logik).
|
||||
|
||||
**Session-Qualität / Auswertungsblob:** z. B. `evaluation`, `quality_label`, `overall_score` – **kein** EAV-Parameter-Raster; semantisch „Ergebnis der Einheit“.
|
||||
|
||||
**Nicht dauerhaft doppelt:** dieselbe Semantik nicht parallel pflegen; siehe entfallener Spalte→EAV-Schreib-Sync, Lesepfad `merge_column_backed_and_eav_metrics`.
|
||||
|
||||
### 2.3 EAV (`activity_session_metrics`)
|
||||
|
||||
- **Skalare:** ein `training_parameter`, genau eine `value_*`-Spalte (wie heute).
|
||||
- **Composites:** ein `training_parameter` pro Composite-Instanz, **ein** gespeichertes Dokument pro Session (serialisiert z. B. in `value_text` als JSON **oder** künftig dedizierte JSONB-Spalte – technische Entscheidung in eigener Migration, Vertrag im Archetyp).
|
||||
- **Merge-/Schema-Logik:** weiterhin zentral in `activity_session_metrics.py` (effektives Schema aus Kategorie + Typ-Overrides).
|
||||
|
||||
### 2.4 Composite-Metamodell (Ziel)
|
||||
|
||||
**Archetypen (Code, begrenzte Menge):** u. a. Band-/Zonenverteilung, Sequenz-/Übergangsprofil, Intervallblock-, Ereignis-/Aktions-, Kopplungs-/Effizienz-, Modellparameter-Profil; optional Technik-/Zyklus-, Readiness-/Recovery-Profil.
|
||||
|
||||
**Pro Archetyp:** feste strukturelle Regeln (erlaubte Slots, Typen, Pflicht/Optional), Validator + Version.
|
||||
|
||||
**In der DB (Admin):** Zuordnung „Parameter X hat Archetyp A“, Slot-Labels (DE/EN), Einheiten, Aktivierung pro Sportart/Kategorie, Sortierung.
|
||||
|
||||
**Import:** CSV-Spalten → `(training_parameter_id, slot_key)` mit stabilen Keys (`z1_sec`, …), nie nur „Spaltenreihenfolge“.
|
||||
|
||||
### 2.5 Universal CSV & Admin
|
||||
|
||||
- Vorlagen: Mapping inkl. **Composite-Slots** und Typkonvertierung (vollständige Matrix Ziel).
|
||||
- UI: Trennung **Kern activity_log** vs. **Parameter/EAV** vs. **Composite-Blöcke** (optisch/UX), um Doppel-Tabellen-Chaos zu vermeiden.
|
||||
|
||||
### 2.6 Layer 2 (Platzhalter & Diagramme)
|
||||
|
||||
- Datenbezug **nur** Layer 1.
|
||||
- Registry-Einträge: `data_layer_module` / `data_layer_function` pflegen; Composite-Auswertung ggf. über Hilfsfunktionen, die JSON → normierte Struktur für Prompts/Charts liefern.
|
||||
|
||||
---
|
||||
|
||||
## 3. Ist → Soll (Kurz)
|
||||
|
||||
| Bereich | Ist (typisch) | Soll |
|
||||
|---------|----------------|------|
|
||||
| Schreibpfad | Teilweise Doppelhaltung Spalte ↔ EAV, Sync-Hooks | Kanon + gezielte Abschaltung; eine Quelle pro Semantik |
|
||||
| Lesepfad | Layer 1 wächst; Legacy-Spalten noch relevant | `get_activity_session_logical_unit` / `activity_metrics` als alleinige Wahrheit für Consumer |
|
||||
| Composites | Noch nicht im Einklang mit EAV-Metamodell | Archetypen + Slot-Admin + ein Dokument pro Parameter/Session |
|
||||
| Import | Mapping teilweise; Typkonvertierung lückenhaft | Vollständige Konvertierung + Composite-Zusammenbau |
|
||||
| Resolver | Aktivität sauber über Layer 1 | Profil/Focus ggf. später ebenfalls aus Layer 1 |
|
||||
|
||||
---
|
||||
|
||||
## 4. Vorgehensmodell (Phasen)
|
||||
|
||||
Phasen sind **sequentiell** wo „Abhängigkeit“ steht; Teile können parallel (z. B. UI-Polish) laufen, wenn der Kanon steht.
|
||||
|
||||
### Phase A – Kanon & Abschaltplan (Grundlage) ✅
|
||||
|
||||
**Inhalt:** Schriftliche **Kanon-Tabelle**: pro Messgröße genau eine Quelle (`activity_log` | `eav_scalar` | `eav_composite` | `session_quality`). Liste der Keys, für die **Sync/Spiegelung** endet.
|
||||
|
||||
**Definition of Done:** Review im Team; Referenz in diesem Dokument oder Verweis auf Gitea-Kommentar; keine Code-Änderung zwingend.
|
||||
|
||||
**Erledigt (2026-04-16):** [`ACTIVITY_SCALAR_KANON_TABLE.md`](./ACTIVITY_SCALAR_KANON_TABLE.md) — eine Semantik pro Zeile, verlinkt mit `activity_data_canon.py` und Merge-Logik.
|
||||
|
||||
---
|
||||
|
||||
### Phase B – Lesepfad härten (Layer 1) 🔄
|
||||
|
||||
**Inhalt:** Sicherstellen, dass **alle** relevanten Consumer (mind. `activity_metrics` für Platzhalter/Charts, Activity-Detail-API) dieselbe Merge-/Fallback-Logik nutzen; Legacy-Spalten nur noch als dokumentierter Fallback bis Enddatum.
|
||||
|
||||
**Definition of Done:** Kurze Audit-Liste „Router/Resolver greifen nicht an Aktivität vorbei“; Tests oder manuelle Stichprobe für Detail + ein Chart + 2 Platzhalter.
|
||||
|
||||
**Abhängigkeit:** Phase A für „welche Spalten noch Fallback sind“.
|
||||
|
||||
**Audit-Stand (2026-04-16, ergänzt Export):**
|
||||
|
||||
| Consumer | Nutzt Layer-1-Merge (`enrich_sessions_with_metrics` / `get_activity_session_logical_unit`) | Anmerkung |
|
||||
|----------|---------------------------------------------------------------------------------------------|-----------|
|
||||
| `GET /api/activity/{eid}` | ✅ `get_activity_session_logical_unit` | Referenz-Detail |
|
||||
| `GET /api/activity` (Liste) | ✅ seit 2026-04-16 `enrich_sessions_with_metrics` auf jeder Listen-Antwort | vorher nur Roh-Spalten |
|
||||
| `activity_metrics.get_activity_detail_data` | ✅ | Platzhalter `{{activity_detail}}` |
|
||||
| `activity_metrics.get_training_sessions_recent_weeks_data` | ✅ | KI-Kontext |
|
||||
| `placeholder_resolver` (Aktivität) | ✅ nur `activity_metrics` | kein paralleles SQL |
|
||||
| `GET /api/export/json` (`activity`) | ✅ `enrich_sessions_with_metrics` + `serialize_dates` | `session_metrics` pro Zeile |
|
||||
| `GET /api/export/csv` (Training-Zeilen) | ✅ `enrich_sessions_with_metrics` | gemergte EAV in Spalte „Details“ |
|
||||
| `GET /api/export/zip` (`data/activity.csv`) | ✅ `enrich_sessions_with_metrics` | Zusatzspalte `session_metrics_json` (Import ignoriert sie) |
|
||||
| `get_activity_summary_data` | n. a. | rein aggregiert (`SUM`/`COUNT`), keine Session-EAV |
|
||||
| `routers/charts.py` (A1–A8) | Spalten-Aggregate | bewusst: Dauer/RPE/HF aus **`activity_log`**-Kanon; kein EAV-Join nötig für definierte Charts |
|
||||
| `activity_stats` (`GET /api/activity/stats`) | nur Spalten | Kacheln: `kcal`/`duration` aus Kernspalten |
|
||||
|
||||
---
|
||||
|
||||
### Phase C – Schreibpfad entschlacken
|
||||
|
||||
**Inhalt:** Orchestrierung/CSV: kein Schreiben derselben Semantik an zwei Orten; `sync_column_backed_session_metrics` (o. ä.) **stufig abschalten** oder auf Notfall-Flag; Import schreibt gemäß Kanon.
|
||||
|
||||
**Definition of Done:** Deploy auf Prod mit Monitoring; Stichprobe Import + manuelle Bearbeitung; keine Regression in Listenansicht.
|
||||
|
||||
**Abhängigkeit:** Phase A + B (sonst Lücken beim Lesen).
|
||||
|
||||
**Analyse (2026-04-16, nur Ist-Review):** Es gibt **keinen aktiven** Schreibpfad mehr, der `activity_log`-Spalten für `source_field`-Parameter **dauerhaft nach EAV spiegelt**.
|
||||
|
||||
| Prüfpunkt | Ergebnis |
|
||||
|-----------|----------|
|
||||
| `sync_column_backed_session_metrics` | Nur noch **Definition** in `activity_session_metrics.py`, als veraltet markiert; **keine Aufrufer** im Repo (grep). Laufzeit-Sync: **abgestellt**. |
|
||||
| `run_activity_post_write_hooks` / `…_import` | Nur **Auto-Eval** (optional); Kommentar: **kein** Spalte→EAV-Sync. |
|
||||
| Universal-CSV (`executor.py`) | Kernfelder → `activity_log` (`activity_csv_registry_updates_from_mapped` + `update_activity_columns` / Insert); EAV → `upsert_session_metrics_from_csv_mapped`. Registry-Keys werden **nicht** nach EAV geschrieben; bei `source_field` wird EAV **übersprungen**, wenn die Spalte **bereits befüllt** ist — vermeidet bewusst doppelte Speicherung. |
|
||||
| REST `PUT /metrics` | Kommentar in Code: **kein** `sync_column_backed` nach EAV-Ersatz. |
|
||||
| Migrationen 055 / 057 | **Einmaliger** Backfill/Schwenk, kein fortlaufender Sync. |
|
||||
|
||||
**Lesepfad (2026-04-16):** `merge_column_backed_and_eav_metrics` bevorzugt **immer** `activity_log`, wenn ein kanonischer Spaltenwert existiert: zuerst `source_field`, dann Registry-Spalte gleichen Keys, dann Legacy-Spalten für EAV-primäre Parameter, zuletzt EAV. Doppelte physische Schreiborte sind damit in der effektiven Sicht **ohne EAV-Vorrang** behoben.
|
||||
|
||||
---
|
||||
|
||||
### Phase D – Composite MVP
|
||||
|
||||
**Inhalt:** Ein Archetyp end-to-end (z. B. **Band-/Zonenverteilung**): Code-Validator, DB-Binding (Parameter + Slots), Admin-UI minimal, Import **5 Spalten → ein JSON-Dokument** mit festen Keys, Layer-1-Read (Roh + optional `expand_*`).
|
||||
|
||||
**Definition of Done:** Eine Sportart/Kategorie befüllbar; Dokumentation des JSON-Vertrags im Repo; pytest für Validator/Zusammenbau wo möglich.
|
||||
|
||||
**Abhängigkeit:** Phase A (Kanon „Composites nur als Dokument, nicht doppelt in Spalten“).
|
||||
|
||||
---
|
||||
|
||||
### Phase E – Composite-Ausbau & Typkonvertierung Import
|
||||
|
||||
**Inhalt:** Weitere Archetypen nach Priorität; Universal-CSV **vollständige** Typkonvertierung für alle gemappten Ziele; Dialog-/Mapping-Konzept (Kern vs. Parameter vs. Composite).
|
||||
|
||||
**Definition of Done:** Matrix „Zieltyp × Converter“ gepflegt; Admin-Flow reviewt.
|
||||
|
||||
---
|
||||
|
||||
### Phase F – Produktionshärtung
|
||||
|
||||
**Inhalt:** Performance-Indizes bei Bedarf; Observability (Import-Fehler, Validierungs-Fails); Resolver/Profil optional komplett ohne `get_db` für domänische Daten; Doku + Gitea-Issues geschlossen/aktualisiert.
|
||||
|
||||
---
|
||||
|
||||
## 5. Was zuerst?
|
||||
|
||||
**Erledigt:** Phase A — [`ACTIVITY_SCALAR_KANON_TABLE.md`](./ACTIVITY_SCALAR_KANON_TABLE.md).
|
||||
|
||||
**Aktuell:** Phase B fortsetzen (weitere Consumer prüfen: Export, Import-Vorschau, ggf. zukünftige Chart-Metriken aus EAV), dann **Phase C** (Schreibpfad), dann **Phase D** (Composite-MVP).
|
||||
|
||||
---
|
||||
|
||||
## 6. Referenzen
|
||||
|
||||
- `ACTIVITY_SCALAR_KANON_TABLE.md` – **Skalar-Kanon** (Phase A)
|
||||
- `ACTIVITY_SESSION_METRICS_EAV_AGENT_GUIDE.md` – Tabellen, APIs, Tests, Backfill-Hinweise
|
||||
- `ACTIVITY_COMPOSITE_METRICS_IMPLEMENTATION_CONCEPT.md` – Composite-EAV (JSONB), Archetypen, Import-Slots, Layer-1-Expand, Migrations- und Testplan
|
||||
- `UNIVERSAL_CSV_IMPORT_AGENT_GUIDE.md` – Executor, Vorlagen, Typen
|
||||
- `PLACEHOLDER_REGISTRY_FRAMEWORK.md` – Layer-2-Registrierung
|
||||
- `functional/DATA_ARCHITECTURE.md` – fachliche Datenarchitektur (Querschnitt)
|
||||
|
||||
---
|
||||
|
||||
**Version:** 1.5 · Merge: activity_log (Registry + Legacy-Spalten) vor EAV bei Lesen.
|
||||
@@ -0,0 +1,95 @@
|
||||
# Aktivität: Skalar-Kanon (eine Semantik → eine Quelle)
|
||||
|
||||
**Stand:** 2026-04-16
|
||||
**Normativer Code:** `backend/data_layer/activity_data_canon.py`
|
||||
**Kontext:** `ACTIVITY_PRODUCTION_ARCHITECTURE_AND_PHASES.md` (Phase A abgeschlossen)
|
||||
|
||||
---
|
||||
|
||||
## 1. Spine & Identität (`activity_log`, nicht EAV)
|
||||
|
||||
Diese Felder sind **keine** `training_parameters`-Skalare. Sie gehören zur Session-Zeile.
|
||||
|
||||
| Semantik | DB / API | Kanonische Quelle | Lesefallback | Sync Spalte↔EAV |
|
||||
|----------|----------|-------------------|--------------|-----------------|
|
||||
| Primärschlüssel | `activity_log.id` | `activity_log` | — | — |
|
||||
| Profil | `profile_id` | `activity_log` | — | — |
|
||||
| Kalendertag | `date` | `activity_log` | — | — |
|
||||
| Start / Ende (Zeit) | `start_time`, `end_time`, `started_at`, `ended_at` | `activity_log` | — | — |
|
||||
| Trainingsart (Freitext/Legacy) | `activity_type` | `activity_log` | — | — |
|
||||
| Referenz Trainingstyp | `training_type_id`, `training_category`, … | `activity_log` (+ `training_types`) | — | — |
|
||||
| Notiz | `notes` | `activity_log` | — | — |
|
||||
| Quelle / Import | `source`, `created`, … | `activity_log` | — | — |
|
||||
| Session-Auswertung | `evaluation`, `quality_label`, `overall_score`, … | `activity_log` (Blob/Ergebnis) | — | Kein EAV-Raster |
|
||||
|
||||
---
|
||||
|
||||
## 2. Kernfelder CSV-Modul `activity` (= „heiße“ Skalare)
|
||||
|
||||
Abgeleitet aus `csv_parser.module_registry.MODULE_DEFINITIONS["activity"].fields` — maschinenlesbar über `ACTIVITY_MODULE_REGISTRY_FIELD_KEYS` in `activity_data_canon.py`.
|
||||
|
||||
| Semantik | Key (Registry/API) | Kanonische Quelle | Lesefallback | Bemerkung |
|
||||
|----------|-------------------|-------------------|--------------|-----------|
|
||||
| Dauer | `duration_min` | **`activity_log`** | — | Aggregates, Listen |
|
||||
| Aktive Energie | `kcal_active` | **`activity_log`** | — | |
|
||||
| Ruhe-Energie | `kcal_resting` | **`activity_log`** | — | |
|
||||
| Distanz | `distance_km` | **`activity_log`** | — | |
|
||||
| Ø HF | `hr_avg` (Parameter oft `avg_hr` in EAV-Schema) | **`activity_log`** | EAV nur wenn `source_field` / Profil-Schema | `merge_column_backed_and_eav_metrics`: Spalte schlägt EAV |
|
||||
| Max-HF | `hr_max` | **`activity_log`** | analog | |
|
||||
| RPE | `rpe` | **`activity_log`** | analog | |
|
||||
|
||||
Schreibpfad: Universal-CSV und API sollen diese Keys auf **`activity_log`** mappen, sofern nicht ausdrücklich ein EAV-primärer Parameter (§3) gewählt ist.
|
||||
|
||||
---
|
||||
|
||||
## 3. EAV-primäre Parameter (erweiterte Skalare)
|
||||
|
||||
`ACTIVITY_EAV_PRIMARY_PARAMETER_KEYS` in `activity_data_canon.py`. **`training_parameters.source_field`** = NULL (nach Kanon / Migration 057): kanonischer Speicher ist **`activity_session_metrics`**.
|
||||
|
||||
| Parameter-Key (`training_parameters.key`) | Legacy-Spalte `activity_log` | Schreib-Kanon (Ziel) |
|
||||
|-------------------------------------------|------------------------------|------------------------|
|
||||
| `min_hr` | `hr_min` | **EAV** |
|
||||
| `pace_min_per_km` | `pace_min_per_km` | **EAV** |
|
||||
| `cadence` | `cadence` | **EAV** |
|
||||
| `avg_power` | `avg_power` | **EAV** |
|
||||
| `elevation_gain` | `elevation_gain` | **EAV** |
|
||||
| `temperature_celsius` | `temperature_celsius` | **EAV** |
|
||||
| `humidity_percent` | `humidity_percent` | **EAV** |
|
||||
| `avg_hr_percent` | `avg_hr_percent` | **EAV** |
|
||||
| `kcal_per_km` | `kcal_per_km` | **EAV** |
|
||||
|
||||
**Lesen:** `merge_column_backed_and_eav_metrics` — wenn Legacy-Spalte **und** EAV einen Wert haben, **gewinnt die Spalte** (kanonische `activity_log`-Sicht). EAV nur, wenn die Spalte leer/nicht koerzierbar ist.
|
||||
|
||||
---
|
||||
|
||||
## 4. Profil-/Typ-dynamische Skalare (EAV, nicht in Registry-Kernliste)
|
||||
|
||||
| Semantik | Kanonische Quelle | Lesefallback |
|
||||
|----------|-------------------|--------------|
|
||||
| Admin-definierte Parameter (Attributprofil Kategorie/Typ) | **`activity_session_metrics`** + `training_parameters` | — |
|
||||
| Parameter mit `source_field` → Spalte | **`activity_log`** (Spalte) | EAV ergänzend; Leseregel: Spalte bevorzugt (kein veraltetes EAV) |
|
||||
|
||||
---
|
||||
|
||||
## 5. Composites (Zielbild, noch nicht Kanon-Zeile pro Slot)
|
||||
|
||||
| Semantik | Kanonische Quelle (Ziel) |
|
||||
|----------|---------------------------|
|
||||
| Strukturierte Composite-Dokumente (z. B. Zonen/Bänder) | **EAV** ein Dokument pro Parameter/Session (siehe `ACTIVITY_COMPOSITE_METRICS_IMPLEMENTATION_CONCEPT.md`) |
|
||||
|
||||
Kein dauerhaftes Spiegeln derselben Semantik in `activity_log`-Spalten.
|
||||
|
||||
---
|
||||
|
||||
## 6. Sync & Übergang
|
||||
|
||||
- **Kein** automatischer Dauer-Sync „Spalte → EAV“ für dieselbe Semantik; Lesepfad vereinheitlicht die Sicht (`merge_column_backed_and_eav_metrics`).
|
||||
- Optionale **Backfill**-Migration/Skript (idempotent) nur nach fachlicher Freigabe — siehe EAV-Agent-Guide §6.
|
||||
|
||||
---
|
||||
|
||||
## 7. Referenzen
|
||||
|
||||
- `ACTIVITY_PRODUCTION_ARCHITECTURE_AND_PHASES.md` — Phasen A–F
|
||||
- `ACTIVITY_SESSION_METRICS_EAV_AGENT_GUIDE.md` — APIs, Tests
|
||||
- `activity_data_canon.py` — `ACTIVITY_LOG_PATCHABLE_COLUMNS`, Legacy-Map
|
||||
@@ -0,0 +1,146 @@
|
||||
# Activity Session Metrics (EAV) – Umsetzungs- & Agent-Guide
|
||||
|
||||
**Stand:** 2026-04-14
|
||||
**Status:** Kern-Backend (Migration 054, Layer 1, Admin- & Nutzer-API) umgesetzt; Admin-UI & CSV-Mapping folgen.
|
||||
**Ziel:** Sportspezifische **Attributprofile** (Kategorie + optional Trainingstyp-Override) administrierbar; Messwerte pro Session in **EAV**; **alle Auswertungen** sollen künftig über **Layer 1** (`data_layer`) laufen.
|
||||
|
||||
**Zielarchitektur, Phasenplan (Produktionsreife):** [`ACTIVITY_PRODUCTION_ARCHITECTURE_AND_PHASES.md`](./ACTIVITY_PRODUCTION_ARCHITECTURE_AND_PHASES.md) – Kanon `activity_log`/EAV, Composites, Import, Layer 1/2, Reihenfolge A–F.
|
||||
|
||||
**Composite-Parameter (EAV, JSONB, Archetypen):** detailliertes Umsetzungskonzept für Agenten: [`ACTIVITY_COMPOSITE_METRICS_IMPLEMENTATION_CONCEPT.md`](./ACTIVITY_COMPOSITE_METRICS_IMPLEMENTATION_CONCEPT.md).
|
||||
|
||||
**Kanon (Code):** `backend/data_layer/activity_data_canon.py` (Repo-Root) — CSV-Modul `activity` vs. EAV-primär; Migration **057**.
|
||||
|
||||
---
|
||||
|
||||
## 1. Produktions-Migrationen (Pflicht)
|
||||
|
||||
- **Nur additive Änderungen** bis zur Stabilisierung: neue Tabellen/Spalten **nullable**, kein `DROP COLUMN` / `DELETE` von Altbestand in derselben Story.
|
||||
- Neue Migrationen: **`backend/migrations/054_*.sql`** (nächste freie Nummer nach 053 einhalten).
|
||||
- **Prod-Checkliste vor Deploy:**
|
||||
1. Backup / Snapshot der DB.
|
||||
2. Migration auf **Kopie** der Prod-DB laufen lassen; Container-Start (`db_init`) verifizieren.
|
||||
3. Stichprobe: `activity_log`-Zeilen unverändert; neue Tabellen leer oder nur Seed.
|
||||
- **Datenhaltung:** Bestehende Spalten in `activity_log` bleiben **Quelle für Alt-Daten**; EAV (`activity_session_metrics`) ist der **kanonische Ort für konfigurierte Session-Metriken**, sobald geschrieben. Backfill Altspalten → EAV ist **separater Schritt** (siehe §6).
|
||||
|
||||
---
|
||||
|
||||
## 2. Datenmodell (Ist nach Migration 054)
|
||||
|
||||
| Tabelle | Zweck |
|
||||
|---------|--------|
|
||||
| `training_parameters` | Katalog messbarer Größen (`key`, `data_type`, `unit`, `validation_rules`, …) – bereits Migration 013; Admin-API ergänzt. |
|
||||
| `training_category_parameter` | Welche Parameter für welche **`training_types.category`** (z. B. `cardio`) gelten: `sort_order`, `required`, `ui_group`. |
|
||||
| `training_type_parameter` | Zusatzparameter oder **Overrides** pro **`training_types.id`**: `sort_order`, `required`, `ui_group` (NULL = von Kategorie erben). |
|
||||
| `activity_session_metrics` | EAV: `(activity_log_id, training_parameter_id)` eindeutig; genau eine Wertspalte `value_num` / `value_int` / `value_text` / `value_bool`. |
|
||||
| `activity_log` | **Neu:** `started_at`, `ended_at` (`TIMESTAMPTZ`, nullable) – für spätere Dedupe/Intervalle; **kein** Pflichtfeld in v1. |
|
||||
|
||||
**Merge-Logik effektives Schema** (Layer 1, eine Funktion):
|
||||
|
||||
1. Kategorie ermitteln: aus Zeile `training_category` oder aus `training_types.category` via `training_type_id`.
|
||||
2. Basis = alle Zeilen `training_category_parameter` für diese Kategorie, Join auf `training_parameters` (aktiv).
|
||||
3. Für jeden Eintrag in `training_type_parameter` zum gewählten Typ: gleiche `training_parameter_id` → Overrides anwenden; nur im Typ vorhanden → anhängen.
|
||||
4. Sortierung: `sort_order` aufsteigend, dann `key`.
|
||||
|
||||
---
|
||||
|
||||
## 3. Layer 1 – Kanonische Module
|
||||
|
||||
| Modul | Pfad | Aufgabe |
|
||||
|-------|------|---------|
|
||||
| Session-Metriken & Schema | `backend/data_layer/activity_session_metrics.py` | `resolve_activity_attribute_schema`, `fetch_activity_session_metrics`, `replace_activity_session_metrics`, `get_activity_session_logical_unit`, `enrich_sessions_with_metrics`, `merge_column_backed_and_eav_metrics`. |
|
||||
|
||||
**Spalten vs. EAV (Lesepfad):** `merge_column_backed_and_eav_metrics` / `get_activity_session_logical_unit` / `enrich_sessions_with_metrics` werten Parameter mit `source_field` **primär aus `activity_log`** aus; EAV ist Fallback (z. B. Legacy) oder für Parameter ohne Spalte. **Kein** automatischer Spalte→EAV-Schreib-Sync mehr in `run_activity_post_write_hooks` / Import-Hooks (vermeidet Doppelhaltung).
|
||||
|
||||
**Regeln für Agenten:**
|
||||
|
||||
- **Keine** zweite Implementierung derselben Merge- oder Validierungslogik in Routern.
|
||||
- Platzhalter / Charts, die Session-Details brauchen: **nur** diese Layer-1-Helfer erweitern oder aufrufen (z. B. `activity_metrics.get_training_sessions_recent_weeks_data` nutzt `enrich_sessions_with_metrics`).
|
||||
- Router: `get_db`, `get_cursor`, Auth; Business-Validierung delegieren an `activity_session_metrics`.
|
||||
|
||||
**KI-Kontext:** In `training_sessions_recent_json` enthält jedes Element von `session_metrics` neben `key`/`value` die Felder `name_de`, `name_en`, `description_de`, `description_en` (aus dem effektiven Schema). Für nicht selbsterklärende Keys soll im Katalog `training_parameters.description_*` gepflegt werden (Admin). Ergänzend liefert der Platzhalter `{{training_parameters_glossary_md}}` die gesamte aktive Parameter-Legende als Markdown-Tabelle (`get_training_parameters_ki_glossary_data` → `get_training_parameters_glossary_md`).
|
||||
|
||||
---
|
||||
|
||||
## 4. API (Ist / geplant)
|
||||
|
||||
### Admin (`require_admin`)
|
||||
|
||||
| Methode | Pfad | Beschreibung |
|
||||
|---------|------|--------------|
|
||||
| GET/POST | `/api/admin/training-parameters` | Katalog lesen / Parameter anlegen |
|
||||
| PUT/DELETE | `/api/admin/training-parameters/{id}` | Aktualisieren / Soft-deaktivieren (`is_active`) |
|
||||
| GET | `/api/admin/training-category-parameters?category=` | Zuordnungen Kategorie |
|
||||
| POST | `/api/admin/training-category-parameters` | Zuordnung anlegen |
|
||||
| DELETE | `/api/admin/training-category-parameters/{id}` | Zuordnung entfernen |
|
||||
| GET | `/api/admin/training-type-parameters?training_type_id=` | Zuordnungen Typ |
|
||||
| POST | `/api/admin/training-type-parameters` | Zuordnung anlegen |
|
||||
| DELETE | `/api/admin/training-type-parameters/{id}` | Zuordnung entfernen |
|
||||
|
||||
Router: `backend/routers/admin_training_parameters.py`, `backend/routers/admin_activity_attribute_profiles.py`.
|
||||
|
||||
### Nutzer (`require_auth`)
|
||||
|
||||
| Methode | Pfad | Beschreibung |
|
||||
|---------|------|--------------|
|
||||
| GET | `/api/activity/{eid}` | Session-Kopf + `schema` + `metrics` (Layer 1) |
|
||||
| PUT | `/api/activity/{eid}/metrics` | **Voller Ersatz** der EAV-Metriken für diese Session (Liste `{parameter_key, value}`) |
|
||||
|
||||
`ActivityEntry` unverändert für bestehende Create/Update-Routen; optionale Erweiterung um `started_at`/`ended_at` in späterem Schritt.
|
||||
|
||||
---
|
||||
|
||||
## 5. Agent-Checkliste (nächste Iterationen)
|
||||
|
||||
**Layer 2a (Platzhalter Aktivität):** Abgleich Registry ↔ Resolver ↔ Layer 1 — [`ACTIVITY_LAYER2A_PLACEHOLDER_AUDIT.md`](./ACTIVITY_LAYER2A_PLACEHOLDER_AUDIT.md) (Issue #53). **Schritt 2:** `semantic_contract` / `known_limitations` für dynamische `session_metrics` und Korrektur `trainingstyp_verteilung` in der Registry.
|
||||
|
||||
Siehe **Phasen A–F** in [`ACTIVITY_PRODUCTION_ARCHITECTURE_AND_PHASES.md`](./ACTIVITY_PRODUCTION_ARCHITECTURE_AND_PHASES.md). Kurz:
|
||||
|
||||
- [x] **Phase A:** Kanon-Tabelle (eine Quelle pro Semantik) — [`ACTIVITY_SCALAR_KANON_TABLE.md`](./ACTIVITY_SCALAR_KANON_TABLE.md).
|
||||
- [ ] **Phase B:** Lesepfad Layer 1 härten (Consumer-Audit fortlaufend — siehe `ACTIVITY_PRODUCTION_ARCHITECTURE_AND_PHASES.md` §4 Phase B).
|
||||
- [ ] **Phase C:** Schreibpfad: Doppelhaltung / Sync stufenweise abschalten.
|
||||
- [ ] **Phase D:** Composite-MVP (ein Archetyp E2E).
|
||||
- [ ] **Phase E:** Archetypen ausbauen + CSV-Typkonvertierung vollständig + Mapping-UX.
|
||||
- [ ] **Phase F:** Härtung Prod (Indizes, Observability, Doku).
|
||||
|
||||
Legacy-Punkte:
|
||||
|
||||
- [x] Admin-UI: `frontend/src/pages/AdminActivityAttributeProfilesPage.jsx`, Route `/admin/activity-attribute-profiles`, Admin-Nav-Gruppe „Trainingstypen“.
|
||||
- [x] `/activity` Frontend: Bearbeiten lädt `GET /api/activity/{id}`, dynamische Felder + `PUT /api/activity/{id}/metrics`.
|
||||
- [ ] Universal CSV: Mapping inkl. EAV/Composite-Ziele + Executor (fortlaufend).
|
||||
- [ ] Optional: Backfill / Abschluss `source_field`-Pfad nach Kanon (Phase A/C).
|
||||
- [ ] Dedupe Polar/Apple: nach stabilen `started_at`/`ended_at` + Policy (eigenes Issue).
|
||||
|
||||
---
|
||||
|
||||
## 6. Backfill (nicht in Migration 054)
|
||||
|
||||
Separates Skript oder Migration **055+**, wenn fachlich freigegeben:
|
||||
|
||||
- Pro aktivem `training_parameter` mit gesetztem `source_field`: Wert aus `activity_log` lesen, in EAV schreiben, wenn noch keine Zeile existiert.
|
||||
- Idempotent (`ON CONFLICT DO NOTHING` oder Upsert-Regel dokumentieren).
|
||||
|
||||
---
|
||||
|
||||
## 7. Automatische Tests (pytest, ohne DB)
|
||||
|
||||
Aus **`backend/`**:
|
||||
|
||||
```bash
|
||||
python -m pytest tests/test_activity_session_metrics.py -v
|
||||
```
|
||||
|
||||
Abdeckung: reine Merge-Logik (`merge_parameter_schema_rows`), Validierung (`_validate_single_value`), `resolve_activity_attribute_schema` mit Mock-Cursor, `enrich_sessions_with_metrics` mit Mock-Cursor.
|
||||
|
||||
---
|
||||
|
||||
## 8. Referenzen
|
||||
|
||||
- Migration 013: `training_parameters`
|
||||
- Migration 004/014: `training_types`, `activity_log`-Erweiterungen
|
||||
- Pattern Admin-Katalog: `routers/admin_reference_value_types.py`
|
||||
- Platzhalter Session-JSON: `data_layer/activity_metrics.py` → `get_training_sessions_recent_weeks_data`
|
||||
- KI-Legende: `get_training_parameters_ki_glossary_data`, Platzhalter `{{training_parameters_glossary_md}}`
|
||||
|
||||
---
|
||||
|
||||
**Version:** 1.1 · Bei Schema- oder API-Änderungen dieses Dokument und ggf. `CLAUDE.md` Kurzverweis aktualisieren.
|
||||
@@ -92,16 +92,10 @@ registry = get_registry()
|
||||
|
||||
**Package:** `backend/placeholder_registrations/`
|
||||
|
||||
**Struktur:**
|
||||
```
|
||||
placeholder_registrations/
|
||||
├── __init__.py # Auto-Import aller Registrations
|
||||
├── nutrition_part_a.py # Nutrition Basis-Metriken (4 Placeholder)
|
||||
├── nutrition_part_b.py # Protein-Ziele (5 Placeholder) - TODO
|
||||
├── body_metrics.py # Körper-Metriken - TODO
|
||||
├── activity_metrics.py # Aktivitäts-Metriken - TODO
|
||||
└── ... # Weitere Cluster
|
||||
```
|
||||
**Struktur:** Vollständige Cluster-Module (u. a. Ernährung, Körper, Aktivität, Schlaf,
|
||||
Vitalwerte, Profil/Zeitraum, Phase-0b-Ziele, Korrelationen); siehe `__init__.py` für die
|
||||
Import-Liste. **Anzahl:** 114 Platzhalter, identisch zu `PLACEHOLDER_MAP` in
|
||||
`placeholder_resolver.py`.
|
||||
|
||||
**Auto-Registration:**
|
||||
- Import des Package triggert automatische Registrierung aller Placeholder
|
||||
|
||||
@@ -0,0 +1,63 @@
|
||||
# Universal CSV Import – Agent-Leitfaden
|
||||
|
||||
**Stand:** 2026-04-09 · **Kontext:** Issue #21 (Universeller CSV-Parser), Prod-Migrationen u. a. 051–053.
|
||||
|
||||
Dieses Dokument ist **normativ für Agenten**, die ein neues Import-Zielmodul anlegen oder bestehende Import-Pfade (Executor, Vorlagen, DB) ändern.
|
||||
|
||||
---
|
||||
|
||||
## 1. Architektur (Kurz)
|
||||
|
||||
| Komponente | Pfad / Rolle |
|
||||
|------------|----------------|
|
||||
| Modul-Definitionen | `backend/csv_parser/module_registry.py` (`MODULE_DEFINITIONS`) |
|
||||
| Typ-/Einheiten-Konvertierung | `backend/csv_parser/type_converter.py`, `field_units.py` |
|
||||
| Zeilen-Aggregation (z. B. Ernährung pro Tag) | `backend/csv_parser/import_row_processing.py` |
|
||||
| Import-Ausführung | `backend/csv_parser/executor.py` |
|
||||
| Fehlertexte / Transaktions-Hinweise | `backend/csv_parser/import_errors.py` (`enrich_row_error`) |
|
||||
| Admin-Systemvorlagen | `backend/routers/admin_csv_templates.py` |
|
||||
| Nutzer-Import (Profil-Mappings) | `backend/routers/csv_import.py` |
|
||||
| Vorlagen-Validierung (strukturell + Sample) | `backend/csv_parser/template_validator.py` (`validate_csv_template`) |
|
||||
|
||||
**Single Source of Truth** für erlaubte Zielfelder, Typen und Duplikat-Keys ist **`module_registry.py`**. Keine parallele Feldliste in Routern duplizieren.
|
||||
|
||||
---
|
||||
|
||||
## 2. Checkliste: Neues Zielmodul
|
||||
|
||||
1. **`MODULE_DEFINITIONS`** um Eintrag erweitern: `table`, `fields` (Typen `date` / `datetime` / `float` / `int` / `string`), `duplicate_key`, `duplicate_strategy`, ggf. `derive_date_from_datetime_field`, `import_mode` (Spezialpfade wie Schlaf).
|
||||
2. **DB:** Migration nur nach Projektregel (`backend/migrations/NNN_*.sql`). Spaltenbreiten/Typen so wählen, dass importierte Werte (z. B. kJ→kcal, große Energiebeträge) **keinen NUMERIC-Overflow** verursachen.
|
||||
3. **`source` / CHECK-Constraints:** Wenn die Zieltabelle `source` hat, muss der Wert **`csv`** (oder der vereinbarte Import-Tag) in der DB erlaubt sein (Migration anpassen, nicht nur App-Code).
|
||||
4. **Executor:** Einfügen/Aktualisieren in `executor.py` nur über bestehende Muster (ein Cursor, **kein** verschachteltes `get_db()` im gleichen Request). Bei mehreren Zeilen pro Transaktion: bei **Zeilenfehlern** SAVEPOINT pro Zeile nutzen (siehe Activity-Pattern), damit die Transaktion nicht dauerhaft abgebrochen ist.
|
||||
5. **Trainingstyp / FK-Auflösung:** DB-Zugriffe für abhängige Entitäten (z. B. `get_training_type_for_activity_with_cursor`) **mit dem gleichen Cursor** wie der Import – keine zweite Connection aus dem Importpfad.
|
||||
6. **Vorlagen:** System-Templates in Migration/Seed pflegen (`csv_field_mappings`, `is_system=true`). `type_conversions` und `source_unit` dort setzen, wo Einheiten aus Exporten abweichen (z. B. Apple kJ).
|
||||
7. **Validierung:** Neue/angepasste Admin-Vorlagen müssen **`validate_csv_template`** passieren (Create/Update liefert bei Fehlern **422** mit `validation`). Tests für Randfälle ergänzen (`tests/test_template_validator.py` o. ä.).
|
||||
8. **API / Frontend:** Neue Admin-Endpunkte in `main.py` registrieren; Frontend **nur** über `api.js`. Bei strukturierten FastAPI-Fehlern (`detail` als Objekt/Liste) bestehende Hilfen (`formatFastApiDetail`) nutzen.
|
||||
|
||||
---
|
||||
|
||||
## 3. Checkliste: Bestehendes Modul ändern
|
||||
|
||||
- Schema-Änderung: Migration + ggf. **`module_registry`**-Felder anpassen.
|
||||
- Neue Spalte im Import: Executor-Mapping, optional `type_conversions` / Validator.
|
||||
- Änderung an Duplikatlogik: `duplicate_key` / `ON CONFLICT`-Pfad im Executor prüfen.
|
||||
- Datums-/Zeit-Parsing: **`type_converter`** – ISO-Daten `YYYY-MM-DD` konsistent (**`dayfirst=False`**), Zeiten `HH:MM` ohne Sekunden unterstützen wo nötig.
|
||||
|
||||
---
|
||||
|
||||
## 4. Bekannte Einschränkungen (Follow-up in Gitea)
|
||||
|
||||
- Admin **„Format prüfen“** kann `import_row_processing` derzeit weglassen; volle Parität mit dem gespeicherten Template erst beim Speichern / echten Import.
|
||||
- Nutzer-Mappings (Copy aus Systemvorlage) laufen nicht automatisch durch **`validate_csv_template`** – Tracking: **Gitea #71** (http://192.168.2.144:3000/Lars/mitai-jinkendo/issues/71).
|
||||
|
||||
---
|
||||
|
||||
## 5. Verwandte Regeln
|
||||
|
||||
- `.claude/rules/ARCHITECTURE.md` – Router, DB, `source`-Tracking
|
||||
- `.claude/rules/CODING_RULES.md` – Kurzverweis Universal CSV
|
||||
- `.claude/rules/DOCUMENTATION.md` – Ablage technischer Specs
|
||||
|
||||
---
|
||||
|
||||
**Version:** 1.0
|
||||
File diff suppressed because it is too large.
Load diff
@@ -0,0 +1,13 @@
|
||||
Folgende Ergebnisse des Tests:
|
||||
- Valididierung gibt immer noch keine Aufschlüsse was für Fehler und Warning es sind, Es zeigt immer nur noch die Anzahl der entsprechenden Fehler/Warnungen
|
||||
- Speichern als kurzes PopUp -- gut
|
||||
- In der Node selbst wird nun eine Fehlermeldung ausgegeben. Das ist gut. In größen Workflows aber schwierig den Fehler zu lokalisieren.
|
||||
- In der automatischen Zusammenfassung in der Endnode kommt als Überschrift, z.B. Node 10, anstatt den Node-Name auszugeben.
|
||||
- Alle Änderungen an Nodes scheinen automatisch in den Gesamtflow übernommen zu werden. Diese werden dann nach dem Speichern aktiv. Da muss man sehr vorsichtig sein, bei kurzen Änderungen und dem Ausprobieren.
|
||||
- Der Testlauf "Execute" sollte auf dem aktuellen Workflowstand ausgeführt werden, auch wenn dieser vom gespeicherten Abweicht. Ich würde natürlich vor dem Speichern den Workflow testen können. Prüfe und bewerte diesen Punkt, setze ihn aber noch nicht um.
|
||||
- Das löschen von Knoten und Kanten funktioniert aktuell nur über Backspace nicht über entfernen
|
||||
- Wir sollten auch dafür sorgen, dass jeweils nur eine Start-Node, End-Node in einem Workflow existiert, Prüfe ob mehrere End-Nodes sinnvoll sind, da wir ja auch Logik-Pfade abbilden und ggf. auch eine route beschreiten, die ein anderes Ende hat. (Prüfe, ob das heute schon möglich wäre!)
|
||||
- Als zukünftige Ausbaustufe sollten wir überlegen, ob wir auch Trigger implementieren, z.B. um Kurzstatements zu generieren, wenn neue Daten hereinkommen und wir diese Bewertungen aktualisieren wollen
|
||||
- Exportieren aller KI-Prompts/Templates/Workflows im Admin --> KI-Prompts führt zu einem "internal Server Error", Importieren konnte daraufhin nicht getestet werden
|
||||
- Das duplizieren von Workflows funktioniert nicht
|
||||
-
|
||||
@@ -0,0 +1,458 @@
|
||||
-- Migration XXX: CSV Parser - System Templates Seed Data
|
||||
-- Legt Standard-Import-Konfigurationen für bekannte CSV-Formate an
|
||||
-- Diese Templates sind für alle User verfügbar (is_system = true, profile_id = NULL)
|
||||
|
||||
-- ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
-- NUTRITION (Ernährung)
|
||||
-- ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
|
||||
-- 1. FDDB Export (Deutsch)
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions
|
||||
) VALUES (
|
||||
NULL,
|
||||
true,
|
||||
'nutrition',
|
||||
'FDDB Export (Standard)',
|
||||
'Standard-Format für FDDB.de CSV-Exporte (Deutsch). Delimiter Semikolon, kJ → kcal Konvertierung.',
|
||||
ARRAY['datum_tag_monat_jahr_stunde_minute', 'fett_g', 'kh_g', 'kj', 'protein_g']::TEXT[],
|
||||
';',
|
||||
'utf-8',
|
||||
true,
|
||||
'{
|
||||
"datum_tag_monat_jahr_stunde_minute": "date",
|
||||
"kj": "kcal",
|
||||
"fett_g": "fat_g",
|
||||
"kh_g": "carbs_g",
|
||||
"protein_g": "protein_g"
|
||||
}'::JSONB,
|
||||
'{
|
||||
"date": {
|
||||
"type": "date",
|
||||
"format": "dd.mm.yyyy HH:MM",
|
||||
"extract": "date_only"
|
||||
},
|
||||
"kcal": {
|
||||
"type": "float",
|
||||
"source_unit": "kj",
|
||||
"decimal_separator": ","
|
||||
},
|
||||
"fat_g": {
|
||||
"type": "float",
|
||||
"decimal_separator": ","
|
||||
},
|
||||
"carbs_g": {
|
||||
"type": "float",
|
||||
"decimal_separator": ","
|
||||
},
|
||||
"protein_g": {
|
||||
"type": "float",
|
||||
"decimal_separator": ","
|
||||
}
|
||||
}'::JSONB
|
||||
);
|
||||
|
||||
-- 2. MyFitnessPal Export (English)
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions
|
||||
) VALUES (
|
||||
NULL,
|
||||
true,
|
||||
'nutrition',
|
||||
'MyFitnessPal Export',
|
||||
'Standard CSV export from MyFitnessPal (English)',
|
||||
ARRAY['Carbohydrates (g)', 'Calories', 'Date', 'Fat (g)', 'Protein (g)']::TEXT[],
|
||||
',',
|
||||
'utf-8',
|
||||
true,
|
||||
'{
|
||||
"Date": "date",
|
||||
"Calories": "kcal",
|
||||
"Fat (g)": "fat_g",
|
||||
"Carbohydrates (g)": "carbs_g",
|
||||
"Protein (g)": "protein_g"
|
||||
}'::JSONB,
|
||||
'{
|
||||
"date": {
|
||||
"type": "date",
|
||||
"format": "yyyy-mm-dd"
|
||||
},
|
||||
"kcal": {
|
||||
"type": "float",
|
||||
"decimal_separator": "."
|
||||
},
|
||||
"fat_g": {
|
||||
"type": "float",
|
||||
"decimal_separator": "."
|
||||
},
|
||||
"carbs_g": {
|
||||
"type": "float",
|
||||
"decimal_separator": "."
|
||||
},
|
||||
"protein_g": {
|
||||
"type": "float",
|
||||
"decimal_separator": "."
|
||||
}
|
||||
}'::JSONB
|
||||
);
|
||||
|
||||
-- 3. Cronometer Export
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions
|
||||
) VALUES (
|
||||
NULL,
|
||||
true,
|
||||
'nutrition',
|
||||
'Cronometer Export',
|
||||
'Cronometer daily nutrition export (English)',
|
||||
ARRAY['Day', 'Energy (kcal)', 'Fat (g)', 'Net Carbs (g)', 'Protein (g)']::TEXT[],
|
||||
',',
|
||||
'utf-8',
|
||||
true,
|
||||
'{
|
||||
"Day": "date",
|
||||
"Energy (kcal)": "kcal",
|
||||
"Fat (g)": "fat_g",
|
||||
"Net Carbs (g)": "carbs_g",
|
||||
"Protein (g)": "protein_g"
|
||||
}'::JSONB,
|
||||
'{
|
||||
"date": {
|
||||
"type": "date",
|
||||
"format": "yyyy-mm-dd"
|
||||
},
|
||||
"kcal": {"type": "float", "decimal_separator": "."},
|
||||
"fat_g": {"type": "float", "decimal_separator": "."},
|
||||
"carbs_g": {"type": "float", "decimal_separator": "."},
|
||||
"protein_g": {"type": "float", "decimal_separator": "."}
|
||||
}'::JSONB
|
||||
);
|
||||
|
||||
-- ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
-- ACTIVITY (Aktivität)
|
||||
-- ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
|
||||
-- 1. Apple Health Workout Export (English)
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions
|
||||
) VALUES (
|
||||
NULL,
|
||||
true,
|
||||
'activity',
|
||||
'Apple Health Workout Export (English)',
|
||||
'Apple Health CSV-Export für Workouts (English). Automatisches Training-Type-Mapping.',
|
||||
ARRAY['Active Energy (kcal)', 'Distance (km)', 'Duration', 'End', 'Heart Rate Average (bpm)', 'Start', 'Workout Type']::TEXT[],
|
||||
',',
|
||||
'utf-8',
|
||||
true,
|
||||
'{
|
||||
"Workout Type": "activity_type",
|
||||
"Start": "start_time",
|
||||
"End": "end_time",
|
||||
"Duration": "duration_min",
|
||||
"Distance (km)": "distance_km",
|
||||
"Active Energy (kcal)": "kcal_active",
|
||||
"Heart Rate Average (bpm)": "hr_avg"
|
||||
}'::JSONB,
|
||||
'{
|
||||
"start_time": {
|
||||
"type": "datetime",
|
||||
"format": "yyyy-mm-dd HH:MM:SS",
|
||||
"extract": "date_and_time"
|
||||
},
|
||||
"end_time": {
|
||||
"type": "datetime",
|
||||
"format": "yyyy-mm-dd HH:MM:SS"
|
||||
},
|
||||
"duration_min": {
|
||||
"type": "duration",
|
||||
"format": "HH:MM:SS",
|
||||
"target_unit": "minutes"
|
||||
},
|
||||
"distance_km": {
|
||||
"type": "float",
|
||||
"decimal_separator": "."
|
||||
},
|
||||
"kcal_active": {
|
||||
"type": "float",
|
||||
"decimal_separator": "."
|
||||
},
|
||||
"hr_avg": {
|
||||
"type": "int"
|
||||
}
|
||||
}'::JSONB
|
||||
);
|
||||
|
||||
-- 2. Apple Health Workout Export (Deutsch)
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions
|
||||
) VALUES (
|
||||
NULL,
|
||||
true,
|
||||
'activity',
|
||||
'Apple Health Workout Export (Deutsch)',
|
||||
'Apple Health CSV-Export für Workouts (Deutsch). Automatisches Training-Type-Mapping.',
|
||||
ARRAY['Aktive Energie (kcal)', 'Dauer', 'Durchschnittliche Herzfrequenz (bpm)', 'Ende', 'Start', 'Strecke (km)', 'Trainingsart']::TEXT[],
|
||||
',',
|
||||
'utf-8',
|
||||
true,
|
||||
'{
|
||||
"Trainingsart": "activity_type",
|
||||
"Start": "start_time",
|
||||
"Ende": "end_time",
|
||||
"Dauer": "duration_min",
|
||||
"Strecke (km)": "distance_km",
|
||||
"Aktive Energie (kcal)": "kcal_active",
|
||||
"Durchschnittliche Herzfrequenz (bpm)": "hr_avg"
|
||||
}'::JSONB,
|
||||
'{
|
||||
"start_time": {
|
||||
"type": "datetime",
|
||||
"format": "yyyy-mm-dd HH:MM:SS",
|
||||
"extract": "date_and_time"
|
||||
},
|
||||
"end_time": {
|
||||
"type": "datetime",
|
||||
"format": "yyyy-mm-dd HH:MM:SS"
|
||||
},
|
||||
"duration_min": {
|
||||
"type": "duration",
|
||||
"format": "HH:MM:SS",
|
||||
"target_unit": "minutes"
|
||||
},
|
||||
"distance_km": {
|
||||
"type": "float",
|
||||
"decimal_separator": ","
|
||||
},
|
||||
"kcal_active": {
|
||||
"type": "float",
|
||||
"decimal_separator": ","
|
||||
},
|
||||
"hr_avg": {
|
||||
"type": "int"
|
||||
}
|
||||
}'::JSONB
|
||||
);
|
||||
|
||||
-- 3. Garmin Connect Export
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions
|
||||
) VALUES (
|
||||
NULL,
|
||||
true,
|
||||
'activity',
|
||||
'Garmin Connect Export',
|
||||
'Garmin Connect activity CSV export (English)',
|
||||
ARRAY['Activity Type', 'Avg HR', 'Calories', 'Date', 'Distance', 'Duration', 'Time']::TEXT[],
|
||||
',',
|
||||
'utf-8',
|
||||
true,
|
||||
'{
|
||||
"Activity Type": "activity_type",
|
||||
"Date": "date",
|
||||
"Time": "start_time",
|
||||
"Duration": "duration_min",
|
||||
"Distance": "distance_km",
|
||||
"Calories": "kcal_active",
|
||||
"Avg HR": "hr_avg"
|
||||
}'::JSONB,
|
||||
'{
|
||||
"date": {
|
||||
"type": "date",
|
||||
"format": "yyyy-mm-dd"
|
||||
},
|
||||
"start_time": {
|
||||
"type": "time",
|
||||
"format": "HH:MM:SS"
|
||||
},
|
||||
"duration_min": {
|
||||
"type": "duration",
|
||||
"format": "HH:MM:SS",
|
||||
"target_unit": "minutes"
|
||||
},
|
||||
"distance_km": {
|
||||
"type": "float",
|
||||
"decimal_separator": "."
|
||||
},
|
||||
"kcal_active": {
|
||||
"type": "float",
|
||||
"decimal_separator": "."
|
||||
},
|
||||
"hr_avg": {
|
||||
"type": "int"
|
||||
}
|
||||
}'::JSONB
|
||||
);
|
||||
|
||||
-- ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
-- BLOOD PRESSURE (Blutdruck)
|
||||
-- ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
|
||||
-- 1. Omron Export (Deutsch)
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions
|
||||
) VALUES (
|
||||
NULL,
|
||||
true,
|
||||
'blood_pressure',
|
||||
'Omron Export (Deutsch)',
|
||||
'Omron Blutdruckmessgerät CSV-Export (Deutsch)',
|
||||
ARRAY['Datum', 'Diastolisch (mmHg)', 'Puls (bpm)', 'Systolisch (mmHg)', 'Zeit']::TEXT[],
|
||||
',',
|
||||
'utf-8',
|
||||
true,
|
||||
'{
|
||||
"Datum": "measured_date",
|
||||
"Zeit": "measured_time",
|
||||
"Systolisch (mmHg)": "systolic",
|
||||
"Diastolisch (mmHg)": "diastolic",
|
||||
"Puls (bpm)": "pulse"
|
||||
}'::JSONB,
|
||||
'{
|
||||
"measured_date": {
|
||||
"type": "date",
|
||||
"format": "dd.mm.yyyy"
|
||||
},
|
||||
"measured_time": {
|
||||
"type": "time",
|
||||
"format": "HH:MM"
|
||||
},
|
||||
"systolic": {"type": "int"},
|
||||
"diastolic": {"type": "int"},
|
||||
"pulse": {"type": "int"}
|
||||
}'::JSONB
|
||||
);
|
||||
|
||||
-- 2. Omron Export (English)
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions
|
||||
) VALUES (
|
||||
NULL,
|
||||
true,
|
||||
'blood_pressure',
|
||||
'Omron Export (English)',
|
||||
'Omron blood pressure monitor CSV export (English)',
|
||||
ARRAY['Date', 'Diastolic (mmHg)', 'Pulse (bpm)', 'Systolic (mmHg)', 'Time']::TEXT[],
|
||||
',',
|
||||
'utf-8',
|
||||
true,
|
||||
'{
|
||||
"Date": "measured_date",
|
||||
"Time": "measured_time",
|
||||
"Systolic (mmHg)": "systolic",
|
||||
"Diastolic (mmHg)": "diastolic",
|
||||
"Pulse (bpm)": "pulse"
|
||||
}'::JSONB,
|
||||
'{
|
||||
"measured_date": {
|
||||
"type": "date",
|
||||
"format": "mm/dd/yyyy"
|
||||
},
|
||||
"measured_time": {
|
||||
"type": "time",
|
||||
"format": "HH:MM"
|
||||
},
|
||||
"systolic": {"type": "int"},
|
||||
"diastolic": {"type": "int"},
|
||||
"pulse": {"type": "int"}
|
||||
}'::JSONB
|
||||
);
|
||||
|
||||
-- ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
-- WEIGHT (Gewicht)
|
||||
-- ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
|
||||
-- 1. Apple Health Weight Export
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions
|
||||
) VALUES (
|
||||
NULL,
|
||||
true,
|
||||
'weight',
|
||||
'Apple Health Weight Export',
|
||||
'Apple Health body mass CSV export',
|
||||
ARRAY['Body Mass (kg)', 'Start']::TEXT[],
|
||||
',',
|
||||
'utf-8',
|
||||
true,
|
||||
'{
|
||||
"Start": "date",
|
||||
"Body Mass (kg)": "weight"
|
||||
}'::JSONB,
|
||||
'{
|
||||
"date": {
|
||||
"type": "datetime",
|
||||
"format": "yyyy-mm-dd HH:MM:SS",
|
||||
"extract": "date_only"
|
||||
},
|
||||
"weight": {
|
||||
"type": "float",
|
||||
"decimal_separator": "."
|
||||
}
|
||||
}'::JSONB
|
||||
);
|
||||
|
||||
-- 2. Withings Export
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions
|
||||
) VALUES (
|
||||
NULL,
|
||||
true,
|
||||
'weight',
|
||||
'Withings Export',
|
||||
'Withings smart scale CSV export (weight, body fat, muscle mass)',
|
||||
ARRAY['Body Fat (%)', 'Date', 'Muscle Mass (kg)', 'Weight (kg)']::TEXT[],
|
||||
',',
|
||||
'utf-8',
|
||||
true,
|
||||
'{
|
||||
"Date": "date",
|
||||
"Weight (kg)": "weight"
|
||||
}'::JSONB,
|
||||
'{
|
||||
"date": {
|
||||
"type": "date",
|
||||
"format": "yyyy-mm-dd"
|
||||
},
|
||||
"weight": {
|
||||
"type": "float",
|
||||
"decimal_separator": "."
|
||||
}
|
||||
}'::JSONB
|
||||
);
|
||||
|
||||
-- ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
-- SUMMARY
|
||||
-- ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
|
||||
DO $$
|
||||
DECLARE
|
||||
template_count INTEGER;
|
||||
BEGIN
|
||||
SELECT COUNT(*) INTO template_count FROM csv_field_mappings WHERE is_system = true;
|
||||
RAISE NOTICE '✓ CSV Parser: % System-Templates created', template_count;
|
||||
RAISE NOTICE ' - Nutrition: 3 (FDDB, MyFitnessPal, Cronometer)';
|
||||
RAISE NOTICE ' - Activity: 3 (Apple Health DE/EN, Garmin)';
|
||||
RAISE NOTICE ' - Blood Pressure: 2 (Omron DE/EN)';
|
||||
RAISE NOTICE ' - Weight: 2 (Apple Health, Withings)';
|
||||
END $$;
|
||||
File diff suppressed because it is too large.
Load diff
@@ -7,7 +7,7 @@
|
||||
|
||||
## Gesamt-Übersicht
|
||||
|
||||
**Aktuelle Platzhalter:** 116
|
||||
**Aktuelle Platzhalter:** 114 (PLACEHOLDER_MAP / Registry)
|
||||
**Nach Phase 0c Migration:**
|
||||
- ✅ **Bleiben einfach (kein Data Layer):** 8 Platzhalter
|
||||
- 🔄 **Gehen zu Data Layer:** 108 Platzhalter
|
||||
|
||||
@@ -216,8 +216,11 @@ updated_at TIMESTAMP DEFAULT NOW()
|
||||
Tabellen die Daten aus externen Quellen empfangen brauchen:
|
||||
```sql
|
||||
source VARCHAR(50) DEFAULT 'manual'
|
||||
-- Werte: 'manual' | 'apple_health' | 'garmin' | 'withings'
|
||||
-- Werte u. a.: 'manual' | 'apple_health' | 'garmin' | 'withings' | 'csv'
|
||||
```
|
||||
Importe über den **Universal CSV**-Pfad setzen `source = 'csv'`, sofern die Tabelle ein `source`-Feld hat; CHECK-Constraints und Migrationen müssen diesen Wert erlauben.
|
||||
|
||||
**Agent-Pflicht bei neuen Import-Zielen oder Executor-Änderungen:** `.claude/docs/technical/UNIVERSAL_CSV_IMPORT_AGENT_GUIDE.md`
|
||||
|
||||
Manuelle Einträge (`source = 'manual'`) haben IMMER Vorrang bei Reimport:
|
||||
```sql
|
||||
@@ -384,26 +387,55 @@ Dev-URL: dev.mitai.jinkendo.de
|
||||
|
||||
---
|
||||
|
||||
## 8. Test-Regeln
|
||||
## 8. CSV-Import vs. Data Layer (Issue #53)
|
||||
|
||||
### 8.1 Tests schreiben ist Pflicht
|
||||
### 8.1 Leitlinie: Wo Interpretation stattfindet
|
||||
|
||||
| Schicht | Erlaubt | Nicht Sinn der Schicht |
|
||||
|--------|---------|-------------------------|
|
||||
| **Import (Ingest)** | Zuordnung CSV→Speicherfeld, **Typ-/Einheits-Konvertierung** (`type_conversions`), Duplikat-/Constraint-Logik | Fachliche **Interpretation**, Aggregation von „Bedeutung“, Metriken für Auswertung |
|
||||
| **Data Layer (Issue #53, Layer 1+)** | Daten lesen, aufbereiten, ableiten, für Charts/KI/Prompts bereitstellen | — |
|
||||
|
||||
Verbindlich: **Semantik und Auswertung** nicht dauerhaft im Import verstecken; neue Features werden an dieser Grenze geprüft.
|
||||
|
||||
**Detail & Zielbild (Multi-Layer, Single Source of Truth):** `docs/issues/issue-53-phase-0c-multi-layer-architecture.md`
|
||||
|
||||
**Umsetzung Schlaf-Import (Refactoring, Offen):** Gitea http://192.168.2.144:3000/Lars/mitai-jinkendo/issues/69
|
||||
|
||||
### 8.2 Ist-Einordnung Import-Pfade (Übergang)
|
||||
|
||||
Bis sukzessive auf das Zielbild umgestellt ist, gilt:
|
||||
|
||||
| Pfad | Einordnung |
|
||||
|------|----------------|
|
||||
| Universal-CSV (`csv_parser`, `routers/csv_import.py`, Executor für u. a. Gewicht/Ernährung/Blutdruck/Aktivität/Vitals) | **Zielrichtung:** Mapping + Typkonvertierung |
|
||||
| Apple-Schlaf-Aggregat (`csv_parser/sleep_apple_import.py`, `import_mode: apple_sleep_aggregate`) | **Legacy-Adapter** (quellenspezifische Aufbereitung) – Austausch gegen mapping-nah + Layer 1 geplant |
|
||||
| Dedizierte Import-Endpoints (z. B. `/api/activity/import-csv`, Vitals Apple) | **Legacy/Parallel** – neue Quellen bevorzugt über Universal-Pfad + Vorlagen |
|
||||
|
||||
Änderungen an Import-Pfaden: Legacy nur erweitern mit **expliziter** Issue-/Review-Begründung; kein neues „wir rechnen Auswertung beim Insert“ ohne Data-Layer-Bezug.
|
||||
|
||||
---
|
||||
|
||||
## 9. Test-Regeln
|
||||
|
||||
### 9.1 Tests schreiben ist Pflicht
|
||||
Jedes neue Feature bekommt mindestens einen Playwright-Test in
|
||||
`tests/dev-smoke-test.spec.js`.
|
||||
|
||||
### 8.2 Reihenfolge: Test vor Commit
|
||||
### 9.2 Reihenfolge: Test vor Commit
|
||||
```
|
||||
Implementieren → Tests schreiben → Tests grün → Committen
|
||||
NIEMALS: Implementieren → Committen → Tests später
|
||||
```
|
||||
|
||||
### 8.3 Claude Code schreibt Tests selbst
|
||||
### 9.3 Claude Code schreibt Tests selbst
|
||||
Nach jeder Implementierung:
|
||||
1. Passende Tests in dev-smoke-test.spec.js ergänzen
|
||||
2. `npx playwright test` ausführen
|
||||
3. Fehler korrigieren bis alle Tests grün
|
||||
4. Erst dann committen
|
||||
|
||||
### 8.4 Test-Kategorien
|
||||
### 9.4 Test-Kategorien
|
||||
```javascript
|
||||
// UI-Test (Playwright)
|
||||
test('FEATURE: Beschreibung', async ({ page }) => { ... })
|
||||
@@ -412,18 +444,18 @@ test('FEATURE: Beschreibung', async ({ page }) => { ... })
|
||||
test('API: Endpoint', async ({ request }) => { ... })
|
||||
```
|
||||
|
||||
### 8.5 Screenshots bei Fehlern
|
||||
### 9.5 Screenshots bei Fehlern
|
||||
Fehlgeschlagene Tests erzeugen automatisch Screenshots in:
|
||||
`test-results/TESTNAME/test-failed-1.png`
|
||||
→ Immer ansehen bevor Code geändert wird
|
||||
|
||||
### 8.6 Prod nie testen
|
||||
### 9.6 Prod nie testen
|
||||
Tests laufen IMMER gegen dev.mitai.jinkendo.de
|
||||
NIEMALS gegen mitai.jinkendo.de
|
||||
|
||||
---
|
||||
|
||||
## 9. Dashboard-Lab-Widgets und Feature-System
|
||||
## 10. Dashboard-Lab-Widgets und Feature-System
|
||||
|
||||
**Kontext:** Dashboard-Widgets (`backend/widget_catalog.py`, Lab unter `/api/app/...`) und das **Subscription-/Feature-Modell** (`features`, `tier_limits`, `check_feature_access` in `backend/auth.py`) sind **getrennte Schichten**, müssen aber bei tariffrelevanten Widgets **verknüpft** werden.
|
||||
|
||||
|
||||
@@ -0,0 +1,339 @@
|
||||
# Architektur-Regeln – Mitai Jinkendo
|
||||
|
||||
> **PFLICHTLEKTÜRE für Claude Code vor jeder Implementierung.**
|
||||
> Diese Regeln sind verbindlich und dürfen nicht ohne explizite
|
||||
> Genehmigung des Nutzers abgeändert werden.
|
||||
|
||||
---
|
||||
|
||||
## 1. Router-Architektur
|
||||
|
||||
### 1.1 Ein Modul = Ein Router
|
||||
Jedes fachliche Modul hat genau eine Router-Datei in `backend/routers/`.
|
||||
|
||||
```
|
||||
backend/routers/
|
||||
├── auth.py # Authentifizierung
|
||||
├── profiles.py # Nutzerprofile
|
||||
├── weight.py # Gewichts-Tracking
|
||||
├── sleep.py # Schlaf-Modul
|
||||
├── training_types.py # Trainingstypen + HF
|
||||
└── ... # je neues Modul = neue Datei
|
||||
```
|
||||
|
||||
**Regeln:**
|
||||
- Kein Endpoint darf außerhalb seines thematischen Routers definiert werden
|
||||
- Neue Module immer als neue Router-Datei anlegen, nie in bestehende einfügen
|
||||
- Router in `main.py` registrieren: `app.include_router(modul.router, prefix="/api")`
|
||||
- Router-Datei-Name = Modul-Name in `version.py` MODULE_VERSIONS
|
||||
|
||||
### 1.2 API-First Prinzip
|
||||
Jede Funktion ist zuerst als API-Endpoint implementiert – die UI nutzt ausschließlich
|
||||
diese Endpoints über `api.js`. Keine Business-Logik im Frontend.
|
||||
|
||||
```python
|
||||
# ✅ Richtig: Logik im Backend-Endpoint
|
||||
@router.get("/sleep/stats")
|
||||
def get_sleep_stats(session=Depends(require_auth)):
|
||||
# Berechnung hier
|
||||
return {"avg_duration": ..., "sleep_debt": ...}
|
||||
|
||||
# ❌ Falsch: Berechnung im Frontend
|
||||
const sleepDebt = entries.reduce((sum, e) => sum + (goal - e.duration), 0)
|
||||
```
|
||||
|
||||
### 1.3 Einheitliche Fehlerbehandlung
|
||||
```python
|
||||
# ✅ Immer dieses Format:
|
||||
raise HTTPException(status_code=404, detail="Eintrag nicht gefunden")
|
||||
# Response: {"detail": "Eintrag nicht gefunden"}
|
||||
|
||||
# ❌ Nie eigene Formate:
|
||||
return {"error": "not found"}
|
||||
return {"message": "Fehler", "success": False}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 2. Versionskontrollsystem
|
||||
|
||||
### 2.1 Versionierungsschema
|
||||
**Semantic Versioning: `MAJOR.MINOR.PATCH`**
|
||||
|
||||
| Typ | Wann | Beispiel |
|
||||
|-----|------|---------|
|
||||
| MAJOR | Breaking Change, DB-Migration inkompatibel | 9.0.0 → 10.0.0 |
|
||||
| MINOR | Neues Feature, neues Modul | 9.2.0 → 9.3.0 |
|
||||
| PATCH | Bugfix, kleine Änderung, Refactor | 9.3.0 → 9.3.1 |
|
||||
|
||||
### 2.2 Versions-Dateien
|
||||
|
||||
**Backend: `backend/version.py`**
|
||||
```python
|
||||
APP_VERSION = "9.3.0"
|
||||
BUILD_DATE = "2026-03-22"
|
||||
|
||||
MODULE_VERSIONS = {
|
||||
"auth": "1.2.0",
|
||||
"profiles": "1.1.0",
|
||||
"weight": "1.0.3",
|
||||
"circumference": "1.0.1",
|
||||
"caliper": "1.0.1",
|
||||
"activity": "1.1.0",
|
||||
"nutrition": "1.0.2",
|
||||
"photos": "1.0.0",
|
||||
"insights": "1.3.0",
|
||||
"prompts": "1.1.0",
|
||||
"admin": "1.2.0",
|
||||
"stats": "1.0.1",
|
||||
"exportdata": "1.1.0",
|
||||
"importdata": "1.0.0",
|
||||
"membership": "2.1.0",
|
||||
}
|
||||
|
||||
CHANGELOG = [
|
||||
{
|
||||
"version": "9.3.0",
|
||||
"date": "2026-03-22",
|
||||
"changes": [
|
||||
"Feature: Sleep Module (sleep_log, JSONB-Segmente)",
|
||||
"Feature: Vitalwerte-Seite in Navigation",
|
||||
"Feature: Trainingstypen-Kategorisierung",
|
||||
]
|
||||
},
|
||||
{
|
||||
"version": "9.2.1",
|
||||
"date": "2026-03-20",
|
||||
"changes": [
|
||||
"Fix: Feature-Enforcement Rollback",
|
||||
"Fix: Erholungsstatus-Gewichtung korrigiert",
|
||||
]
|
||||
},
|
||||
]
|
||||
```
|
||||
|
||||
**Frontend: `frontend/src/version.js`**
|
||||
```javascript
|
||||
export const APP_VERSION = "9.3.0"
|
||||
export const BUILD_DATE = "2026-03-22"
|
||||
|
||||
export const PAGE_VERSIONS = {
|
||||
Dashboard: "1.3.0",
|
||||
LoginScreen: "1.1.0",
|
||||
WeightPage: "1.0.3",
|
||||
ActivityPage: "1.2.0",
|
||||
NutritionPage: "1.1.0",
|
||||
AnalysisPage: "1.3.0",
|
||||
SettingsPage: "1.4.0",
|
||||
AdminPanel: "1.2.0",
|
||||
SubscriptionPage: "1.0.0",
|
||||
// Neue Seiten hier eintragen
|
||||
}
|
||||
```
|
||||
|
||||
### 2.3 Versions-Endpoint
|
||||
|
||||
**`GET /api/version`** – öffentlich (kein Auth erforderlich)
|
||||
|
||||
```json
|
||||
{
|
||||
"app_version": "9.3.0",
|
||||
"build_date": "2026-03-22",
|
||||
"backend_version": "9.3.0",
|
||||
"modules": {
|
||||
"auth": "1.2.0",
|
||||
"sleep": "1.0.0"
|
||||
},
|
||||
"db_schema_version": "20260322",
|
||||
"environment": "production"
|
||||
}
|
||||
```
|
||||
|
||||
Dieser Endpoint wird in `backend/routers/version.py` implementiert und liest
|
||||
direkt aus `version.py`.
|
||||
|
||||
### 2.4 Versions-Anzeige in der App
|
||||
|
||||
**Settings-Seite – Versions-Panel:**
|
||||
```
|
||||
System-Versionen
|
||||
─────────────────────────────────────
|
||||
App (gesamt) 9.3.0
|
||||
Backend 9.3.0 ✓ erreichbar
|
||||
Frontend 9.3.0 ✓ geladen
|
||||
DB-Schema 20260322
|
||||
Umgebung production
|
||||
─────────────────────────────────────
|
||||
Module
|
||||
auth 1.2.0
|
||||
sleep 1.0.0
|
||||
membership 2.1.0
|
||||
[alle Module...]
|
||||
─────────────────────────────────────
|
||||
[Changelog] [Cache leeren]
|
||||
```
|
||||
|
||||
Frontend ruft beim Laden der Settings-Seite `/api/version` ab und vergleicht
|
||||
mit der eigenen `APP_VERSION` aus `version.js`. Bei Abweichung: Warnung anzeigen.
|
||||
|
||||
### 2.5 Pflicht-Regel: Versions-Bump bei jedem Commit
|
||||
|
||||
**Jede Code-Änderung erfordert:**
|
||||
1. Versions-Bump in `backend/version.py` (APP_VERSION + betroffenes MODULE_VERSION)
|
||||
2. Versions-Bump in `frontend/src/version.js` (APP_VERSION + betroffene PAGE_VERSION)
|
||||
3. Changelog-Eintrag in `backend/version.py` CHANGELOG
|
||||
|
||||
**Claude Code prüft das im `/deploy` Command automatisch.**
|
||||
|
||||
Kein Commit ohne Versions-Bump – keine Ausnahme.
|
||||
|
||||
### 2.6 DB-Schema-Version
|
||||
|
||||
Format: `YYYYMMDD` (Datum der letzten Migration)
|
||||
|
||||
Gespeichert in `backend/version.py`:
|
||||
```python
|
||||
DB_SCHEMA_VERSION = "20260322"
|
||||
```
|
||||
|
||||
Bei jeder Schema-Änderung (ALTER TABLE, neue Tabelle) → DB_SCHEMA_VERSION aktualisieren.
|
||||
|
||||
---
|
||||
|
||||
## 3. Datenbankregeln
|
||||
|
||||
### 3.1 Pflichtfelder für neue Tabellen
|
||||
```sql
|
||||
-- Jede neue Tabelle braucht:
|
||||
id SERIAL PRIMARY KEY,
|
||||
created_at TIMESTAMP DEFAULT NOW(),
|
||||
updated_at TIMESTAMP DEFAULT NOW()
|
||||
```
|
||||
|
||||
### 3.2 Source-Tracking bei Import-Daten
|
||||
Tabellen die Daten aus externen Quellen empfangen brauchen:
|
||||
```sql
|
||||
source VARCHAR(50) DEFAULT 'manual'
|
||||
-- Werte: 'manual' | 'apple_health' | 'garmin' | 'withings'
|
||||
```
|
||||
|
||||
Manuelle Einträge (`source = 'manual'`) haben IMMER Vorrang bei Reimport:
|
||||
```sql
|
||||
-- Reimport überschreibt nur nicht-manuelle Einträge:
|
||||
INSERT INTO sleep_log (...) ON CONFLICT (profile_id, date)
|
||||
DO UPDATE SET ... WHERE sleep_log.source != 'manual'
|
||||
```
|
||||
|
||||
### 3.3 Profile-ID Isolation
|
||||
Jede Tabelle mit Nutzerdaten hat `profile_id` als Foreign Key.
|
||||
Kein Endpoint gibt Daten eines anderen Profils zurück.
|
||||
Profile-ID kommt IMMER aus der Session, nie aus Request-Parametern.
|
||||
|
||||
### 3.4 Boolean-Werte
|
||||
```sql
|
||||
-- PostgreSQL Boolean (nicht SQLite 0/1):
|
||||
WHERE active = true ✓
|
||||
WHERE active = 1 ✗
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 4. Frontend-Regeln
|
||||
|
||||
### 4.1 Alle API-Calls über api.js
|
||||
```javascript
|
||||
// ✅ Richtig:
|
||||
import { api } from '../utils/api'
|
||||
const data = await api.listSleep()
|
||||
|
||||
// ❌ Falsch:
|
||||
const r = await fetch('/api/sleep')
|
||||
```
|
||||
|
||||
### 4.2 Neue Seite = Eintrag in PAGE_VERSIONS
|
||||
Jede neue Seite in `frontend/src/version.js` registrieren.
|
||||
|
||||
### 4.3 CSS-Variablen statt Hardcoded-Farben
|
||||
```javascript
|
||||
// ✅ Richtig:
|
||||
style={{color: 'var(--accent)'}}
|
||||
|
||||
// ❌ Falsch:
|
||||
style={{color: '#1D9E75'}}
|
||||
```
|
||||
|
||||
### 4.4 Fehlerbehandlung in allen async Funktionen
|
||||
```javascript
|
||||
try {
|
||||
const data = await api.meinEndpoint()
|
||||
setData(data)
|
||||
} catch(e) {
|
||||
setError(e.message)
|
||||
} finally {
|
||||
setLoading(false)
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 5. Git & Deployment-Regeln
|
||||
|
||||
### 5.1 Nie direkt auf main pushen
|
||||
Immer über Pull Request in Gitea: develop → main.
|
||||
develop Branch niemals löschen.
|
||||
|
||||
### 5.2 Commit-Message Format
|
||||
```
|
||||
feat: neues Feature oder Modul
|
||||
fix: Bugfix
|
||||
refactor: Umbau ohne Funktionsänderung
|
||||
docs: Dokumentation
|
||||
version: Versions-Bump
|
||||
ci: CI/CD Änderungen
|
||||
chore: Maintenance
|
||||
```
|
||||
|
||||
### 5.3 Versions-Bump im Commit
|
||||
```
|
||||
feat: Sleep Module v1.0.0
|
||||
|
||||
- sleep_log Tabelle mit JSONB-Segmenten
|
||||
- Import aus Apple Health CSV
|
||||
- Korrelationen Schlaf <-> Ruhepuls
|
||||
|
||||
version: 9.3.0 (backend + frontend)
|
||||
module: sleep 1.0.0
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 6. Dokumentations-Regeln
|
||||
|
||||
### 6.1 Neue Module dokumentieren
|
||||
Bei jedem neuen Modul:
|
||||
1. Fachliche Spec: `.claude/docs/functional/MODUL_NAME.md`
|
||||
2. Technische Spec: `.claude/docs/technical/MODUL_NAME.md`
|
||||
3. Nach Fertigstellung: `.claude/library/` aktualisieren
|
||||
|
||||
### 6.2 CLAUDE.md aktuell halten
|
||||
Nach größeren Änderungen CLAUDE.md Versions-Tabelle aktualisieren.
|
||||
|
||||
### 6.3 Lessons Learned dokumentieren
|
||||
Jeder Rollback oder schwerer Bug → Eintrag in `.claude/rules/LESSONS_LEARNED.md`
|
||||
|
||||
---
|
||||
|
||||
## Zusammenfassung: Checkliste vor jedem Commit
|
||||
|
||||
```
|
||||
[ ] Versions-Bump in backend/version.py (APP_VERSION + MODULE)
|
||||
[ ] Versions-Bump in frontend/src/version.js (APP_VERSION + PAGE)
|
||||
[ ] Changelog-Eintrag in backend/version.py
|
||||
[ ] DB_SCHEMA_VERSION aktualisiert (wenn Schema geändert)
|
||||
[ ] Neues Modul in PAGE_VERSIONS / MODULE_VERSIONS eingetragen
|
||||
[ ] Auth auf alle neuen Endpoints (require_auth)
|
||||
[ ] Fehlerformat einheitlich (HTTPException mit detail)
|
||||
[ ] Neue Tabellen haben created_at + updated_at
|
||||
[ ] Import-Tabellen haben source-Feld
|
||||
[ ] api.js für alle Frontend API-Calls
|
||||
```
|
||||
@@ -39,6 +39,13 @@ from slowapi import Limiter
|
||||
def sensitive(request: Request, ...):
|
||||
```
|
||||
|
||||
### 6. Universal CSV Import / Admin-Vorlagen
|
||||
Neues **Import-Zielmodul**, Änderungen an **`csv_parser`**, Executor, DB-`source`/`CHECK`, oder System-CSV-Vorlagen:
|
||||
|
||||
- Pflichtlektüre und Checkliste: **`.claude/docs/technical/UNIVERSAL_CSV_IMPORT_AGENT_GUIDE.md`**
|
||||
- Keine zweite DB-Connection im Importpfad; Zeilenfehler ohne „aborted transaction“ (SAVEPOINT-Muster wo nötig)
|
||||
- Admin Create/Update von Systemvorlagen: Validierung über `validate_csv_template` nicht umgehen
|
||||
|
||||
## Frontend
|
||||
|
||||
### 1. api.js für alle API-Calls
|
||||
|
||||
@@ -3,22 +3,82 @@ name: Build Test
|
||||
on:
|
||||
push:
|
||||
branches: [main, develop]
|
||||
workflow_run:
|
||||
workflows: ["Deploy Development", "Deploy Production"]
|
||||
types: [completed]
|
||||
|
||||
jobs:
|
||||
lint-backend:
|
||||
pytest-backend:
|
||||
if: ${{ github.event_name != 'workflow_run' || github.event.workflow_run.conclusion == 'success' }}
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Check backend syntax
|
||||
- name: Run backend pytest suite in deployed container
|
||||
run: |
|
||||
python3 -m py_compile /home/lars/docker/bodytrack/backend/main.py
|
||||
EVENT_NAME="${{ github.event_name }}"
|
||||
REF_NAME="${{ github.ref_name }}"
|
||||
RUN_WORKFLOW="${{ github.event.workflow_run.name }}"
|
||||
APP_DIR="/home/lars/docker/bodytrack"
|
||||
COMPOSE_FILE="docker-compose.yml"
|
||||
|
||||
if [ "$EVENT_NAME" = "workflow_run" ]; then
|
||||
if [ "$RUN_WORKFLOW" = "Deploy Development" ]; then
|
||||
APP_DIR="/home/lars/docker/bodytrack-dev"
|
||||
COMPOSE_FILE="docker-compose.dev-env.yml"
|
||||
fi
|
||||
elif [ "$REF_NAME" = "develop" ]; then
|
||||
APP_DIR="/home/lars/docker/bodytrack-dev"
|
||||
COMPOSE_FILE="docker-compose.dev-env.yml"
|
||||
fi
|
||||
|
||||
cd "$APP_DIR"
|
||||
docker compose -f "$COMPOSE_FILE" exec -T backend sh -lc "
|
||||
pip install -r /app/requirements-dev.txt &&
|
||||
cd /app &&
|
||||
python -m pytest tests -m 'not slow' -ra -vv --tb=short
|
||||
"
|
||||
|
||||
lint-backend:
|
||||
if: ${{ github.event_name != 'workflow_run' || github.event.workflow_run.conclusion == 'success' }}
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Check backend syntax on deployed app
|
||||
run: |
|
||||
EVENT_NAME="${{ github.event_name }}"
|
||||
REF_NAME="${{ github.ref_name }}"
|
||||
RUN_WORKFLOW="${{ github.event.workflow_run.name }}"
|
||||
APP_DIR="/home/lars/docker/bodytrack"
|
||||
|
||||
if [ "$EVENT_NAME" = "workflow_run" ]; then
|
||||
if [ "$RUN_WORKFLOW" = "Deploy Development" ]; then
|
||||
APP_DIR="/home/lars/docker/bodytrack-dev"
|
||||
fi
|
||||
elif [ "$REF_NAME" = "develop" ]; then
|
||||
APP_DIR="/home/lars/docker/bodytrack-dev"
|
||||
fi
|
||||
|
||||
python3 -m py_compile "$APP_DIR/backend/main.py"
|
||||
echo "✓ Backend syntax OK"
|
||||
|
||||
build-frontend:
|
||||
if: ${{ github.event_name != 'workflow_run' || github.event.workflow_run.conclusion == 'success' }}
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Build frontend
|
||||
- name: Build frontend on deployed app
|
||||
run: |
|
||||
cd /home/lars/docker/bodytrack/frontend
|
||||
EVENT_NAME="${{ github.event_name }}"
|
||||
REF_NAME="${{ github.ref_name }}"
|
||||
RUN_WORKFLOW="${{ github.event.workflow_run.name }}"
|
||||
APP_DIR="/home/lars/docker/bodytrack"
|
||||
|
||||
if [ "$EVENT_NAME" = "workflow_run" ]; then
|
||||
if [ "$RUN_WORKFLOW" = "Deploy Development" ]; then
|
||||
APP_DIR="/home/lars/docker/bodytrack-dev"
|
||||
fi
|
||||
elif [ "$REF_NAME" = "develop" ]; then
|
||||
APP_DIR="/home/lars/docker/bodytrack-dev"
|
||||
fi
|
||||
|
||||
cd "$APP_DIR/frontend"
|
||||
npm install
|
||||
npm run build
|
||||
echo "✓ Frontend build OK"
|
||||
@@ -8,9 +8,11 @@
|
||||
> | Coding-Regeln | `.claude/rules/CODING_RULES.md` |
|
||||
> | Lessons Learned | `.claude/rules/LESSONS_LEARNED.md` |
|
||||
> | **Gitea-Landkarte (lokal gepflegt)** | **`.claude/docs/GITEA_ISSUES_INDEX.md`** |
|
||||
> | **Universal CSV Import** (neues Modul / Executor / Vorlagen) | **`.claude/docs/technical/UNIVERSAL_CSV_IMPORT_AGENT_GUIDE.md`** |
|
||||
> | **GUI / IA / Admin / Nav / PWA-Leiste** | **`docs/issues/GUI_IA_ADMIN_NAV_2026-04-05.md`** |
|
||||
> | **Dashboard-Lab-Widgets** (Katalog, Registrierung, `config`) | **`.claude/docs/technical/DASHBOARD_WIDGETS_AGENT_GUIDE.md`** |
|
||||
> | **Agent-Einstieg** | **`.claude/README.md`** |
|
||||
> | **Activity Session Metrics (EAV, Attributprofile)** | **`.claude/docs/technical/ACTIVITY_SESSION_METRICS_EAV_AGENT_GUIDE.md`** |
|
||||
|
||||
## Claude Code Verantwortlichkeiten
|
||||
|
||||
@@ -98,6 +100,43 @@ frontend/src/
|
||||
**Branch:** develop
|
||||
**Nächster Schritt:** Frontend Chart Integration → Testing → Prod Deploy v0.9i
|
||||
|
||||
### Updates (09.04.2026 - Universal CSV Import, Prod-Migration abgeschlossen)
|
||||
|
||||
- **Agent-Leitfaden:** `.claude/docs/technical/UNIVERSAL_CSV_IMPORT_AGENT_GUIDE.md` (Checkliste für neue Import-Module, Executor, Vorlagen, `source=csv`, SAVEPOINT-/Cursor-Regeln)
|
||||
- **Regeln:** Verweise in `.claude/rules/ARCHITECTURE.md` (§3.2 `source`), `.claude/rules/CODING_RULES.md` (§6)
|
||||
- **Follow-ups:** **Gitea #71** – Dry-Run inkl. `import_row_processing`, Nutzer-Mapping-Validierung, Fehler-Hints in der Import-UI ([Issue](http://192.168.2.144:3000/Lars/mitai-jinkendo/issues/71))
|
||||
|
||||
### Updates (11.04.2026 - Placeholder Phase A)
|
||||
|
||||
- **`main.py`:** `import placeholder_registrations` beim Start, damit die Registry (**114 Keys**, deckungsgleich `PLACEHOLDER_MAP`) und `get_placeholder_catalog()` ohne vorherigen Export-Request konsistent sind.
|
||||
- **`placeholder_resolver.py`:** `{{top_goal_progress_pct}}` nutzt `_safe_int` statt `_safe_str` (Verdrahtung zu `scores.get_top_priority_goal` korrigiert).
|
||||
|
||||
### Updates (11.04.2026 - Gitea #75, nutrition_score Registry)
|
||||
|
||||
- **Gitea #75** (offen): Zucker/Ballaststoffe/Lebensmittelqualität, automatisches Lebensmittelprofil, später Mahlzeiten-Timing/Abgleich mit Training — http://192.168.2.144:3000/Lars/mitai-jinkendo/issues/75
|
||||
- **`nutrition_score`:** Registry in `backend/placeholder_registrations/nutrition_score.py`, Import in `placeholder_registrations/__init__.py`; Legacy-Duplikat unter „Scores“ im Platzhalter-Katalog entfernt.
|
||||
|
||||
### Updates (14.04.2026 - Activity Session Metrics EAV, Kern-Backend)
|
||||
|
||||
- **Agent-Guide:** `.claude/docs/technical/ACTIVITY_SESSION_METRICS_EAV_AGENT_GUIDE.md` (Prod: nur additive Migration **054**; Layer1 `data_layer/activity_session_metrics.py`).
|
||||
- **DB:** `training_category_parameter`, `training_type_parameter`, `activity_session_metrics`; `activity_log.started_at` / `ended_at` (nullable).
|
||||
- **API:** Admin `/api/admin/training-parameters`, `/api/admin/training-category-parameters`, `/api/admin/training-type-parameters`; Nutzer `GET /api/activity/{id}`, `PUT /api/activity/{id}/metrics`; Platzhalter-Pfad `training_sessions_recent_json` liefert pro Session `session_metrics` inkl. `name_*` / `description_*`; **`{{training_parameters_glossary_md}}`** = Markdown-Legende aller aktiven Parameter (KI).
|
||||
- **Frontend:** Admin `/admin/activity-attribute-profiles`; Aktivität → Verlauf → Bearbeiten: Profil-Kennwerte; `api.js` ergänzt.
|
||||
|
||||
### Updates (16.04.2026 - Aktivität Phase A abgeschlossen, Phase B gestartet)
|
||||
|
||||
- **Phase A:** Skalar-Kanon schriftlich fixiert — `.claude/docs/technical/ACTIVITY_SCALAR_KANON_TABLE.md`; `ACTIVITY_PRODUCTION_ARCHITECTURE_AND_PHASES.md` v1.1; Agent-Guide Checkliste Phase A erledigt.
|
||||
- **Phase B:** `GET /api/activity` (Liste) reichert jede Zeile mit `session_metrics` über `enrich_sessions_with_metrics` an (gleiche Merge-Logik wie Detail); Consumer-Audit-Tabelle in Produktions-Architektur-Dok §4 Phase B.
|
||||
- **Phase B (Export):** `routers/exportdata.py` — JSON-Export `activity` mit `session_metrics`; CSV-Gesamtexport Training-Details mit EAV-Zusammenfassung; ZIP `data/activity.csv` mit Zusatzspalte `session_metrics_json` (Standard-Import unverändert).
|
||||
- **Issue #53 / Layer 2a:** `ACTIVITY_LAYER2A_PLACEHOLDER_AUDIT.md` — alle 20 Aktivitäts-Platzhalter gegen Layer 1 geprüft; Registry-Fix `activity_summary.resolver_function` → `get_activity_summary`.
|
||||
- **Layer 2a Schritt 2:** Registry-Texte `activity_detail`, `training_sessions_recent_json` (dynamische session_metrics, Merge-Kanon); `trainingstyp_verteilung` Metadaten an Phase-0c-Code angeglichen.
|
||||
|
||||
### Updates (11.04.2026 - Ernährung: TDEE, Bilanz, Kalorien-Score)
|
||||
|
||||
- **`data_layer/nutrition_metrics.py`:** TDEE für Bilanz: primär **Mifflin–St Jeor BMR × PAL 1,55**, wenn Profil (Größe, Geschlecht, DOB) und Gewicht vorhanden; sonst Fallback **kg × 32,5** (`estimate_tdee_kcal_from_latest_weight`). `get_energy_balance_data` / `calculate_energy_balance_7d` nutzen **tägliche kcal-Summen**. **`_score_calorie_adherence`** (Komponente von `calculate_nutrition_score`) wertet die 7-Tage-Bilanz nach **`profiles.goal_mode`** aus (weight_loss vs. strength/recomposition vs. maintenance/health/endurance).
|
||||
- **`routers/charts.py`:** `/charts/energy-balance` und Protein-Timeline nutzen dieselbe TDEE-/Tageslogik; ohne `weight_log` liefert Energiebilanz-Chart eine klare Fehlermeldung. Adherence-Endpoint: Kcal-CV über **Tages-Summen**.
|
||||
- **Doku:** Normative Platzhalter-Zahl **114** (`docs/PLACEHOLDER_*.md`); `placeholder_metadata_complete.py` als **Legacy** gekennzeichnet — maßgeblich `placeholder_registrations/` + `PLACEHOLDER_REGISTRY_FRAMEWORK.md`.
|
||||
|
||||
### GUI / Informationsarchitektur (Abnahme dieser Iteration, 2026-04-05)
|
||||
|
||||
Admin-Bereich (`AdminShell`, Hub-Routen), Hauptnavigation inkl. **Ziele** (`config/appNav.js`), Einstellungen nur aktives Profil + E-Mail, KI-Analyse Ergebnis in rechter Spalte, **PWA** Bottom-Nav inkl. iOS Safe Area. Zentrale Agent-Doku: **`docs/issues/GUI_IA_ADMIN_NAV_2026-04-05.md`**. Responsive-Epic **Gitea #30:** Phasenplan `docs/issues/PHASE_PLAN_RESPONSIVE_UI.md` — **P7 Kern erledigt**, **P8** (Regression/Abnahme) ausstehend; Issue bewusst **nicht** geschlossen.
|
||||
|
||||
+8
-3
@@ -13,6 +13,8 @@ import bcrypt
|
||||
|
||||
from db import get_db, get_cursor
|
||||
|
||||
print("[AUTH.PY] Module loaded - require_auth_flexible will be defined")
|
||||
|
||||
|
||||
def hash_pin(pin: str) -> str:
|
||||
"""Hash password with bcrypt. Falls back gracefully from legacy SHA256."""
|
||||
@@ -76,21 +78,24 @@ def require_auth(x_auth_token: Optional[str] = Header(default=None)):
|
||||
return session
|
||||
|
||||
|
||||
def require_auth_flexible(x_auth_token: Optional[str] = Header(default=None), token: Optional[str] = Query(default=None)):
|
||||
def require_auth_flexible(x_auth_token: Optional[str] = Header(default=None), ssetoken: Optional[str] = Query(default=None)):
|
||||
"""
|
||||
FastAPI dependency - auth via header OR query parameter.
|
||||
|
||||
Used for endpoints accessed by <img> tags that can't send headers.
|
||||
Used for endpoints accessed by <img> tags and SSE connections that can't send headers.
|
||||
Query parameter is 'ssetoken' to avoid conflicts with endpoint 'token' parameters.
|
||||
|
||||
Usage:
|
||||
@app.get("/api/photos/{id}")
|
||||
def get_photo(id: str, session: dict = Depends(require_auth_flexible)):
|
||||
...
|
||||
|
||||
Call with: ?ssetoken=XXX or Header: X-Auth-Token: XXX
|
||||
|
||||
Raises:
|
||||
HTTPException 401 if not authenticated
|
||||
"""
|
||||
session = get_session(x_auth_token or token)
|
||||
session = get_session(x_auth_token or ssetoken)
|
||||
if not session:
|
||||
raise HTTPException(401, "Nicht eingeloggt")
|
||||
return session
|
||||
|
||||
@@ -509,17 +509,24 @@ def calculate_sleep_quality_7d(profile_id: str) -> Optional[int]:
|
||||
|
||||
quality_scores = []
|
||||
for s in sleep_data:
|
||||
if s['deep_minutes'] and s['rem_minutes']:
|
||||
quality_pct = ((s['deep_minutes'] + s['rem_minutes']) / s['duration_minutes']) * 100
|
||||
# 40-60% deep+REM is good
|
||||
if quality_pct >= 45:
|
||||
quality_scores.append(100)
|
||||
elif quality_pct >= 35:
|
||||
quality_scores.append(75)
|
||||
elif quality_pct >= 25:
|
||||
quality_scores.append(50)
|
||||
else:
|
||||
quality_scores.append(30)
|
||||
dur = s["duration_minutes"]
|
||||
if not dur or dur <= 0:
|
||||
continue
|
||||
d = s["deep_minutes"]
|
||||
r = s["rem_minutes"]
|
||||
if d is None and r is None:
|
||||
continue
|
||||
di, ri = (d or 0), (r or 0)
|
||||
quality_pct = ((di + ri) / dur) * 100
|
||||
# 40-60% deep+REM is good
|
||||
if quality_pct >= 45:
|
||||
quality_scores.append(100)
|
||||
elif quality_pct >= 35:
|
||||
quality_scores.append(75)
|
||||
elif quality_pct >= 25:
|
||||
quality_scores.append(50)
|
||||
else:
|
||||
quality_scores.append(30)
|
||||
|
||||
if not quality_scores:
|
||||
return None
|
||||
|
||||
@@ -0,0 +1,27 @@
|
||||
"""Universal CSV import foundation (Issue #21)."""
|
||||
|
||||
from csv_parser.core import (
|
||||
decode_raw_bytes,
|
||||
sniff_delimiter,
|
||||
parse_csv_sample,
|
||||
column_signature,
|
||||
normalize_header_for_signature,
|
||||
)
|
||||
from csv_parser.module_registry import MODULE_DEFINITIONS, get_module_definition, list_modules
|
||||
from csv_parser.type_converter import convert_value, build_row_after_mapping
|
||||
from csv_parser.permissions import user_may_delete_mapping, user_may_edit_mapping_row
|
||||
|
||||
__all__ = [
|
||||
"decode_raw_bytes",
|
||||
"sniff_delimiter",
|
||||
"parse_csv_sample",
|
||||
"column_signature",
|
||||
"normalize_header_for_signature",
|
||||
"MODULE_DEFINITIONS",
|
||||
"get_module_definition",
|
||||
"list_modules",
|
||||
"convert_value",
|
||||
"build_row_after_mapping",
|
||||
"user_may_delete_mapping",
|
||||
"user_may_edit_mapping_row",
|
||||
]
|
||||
@@ -0,0 +1,220 @@
|
||||
"""
|
||||
CSV bytes → text, delimiter sniffing, strukturierte Erstzeilen für Analyse (Issue #21).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import csv
|
||||
import io
|
||||
import re
|
||||
from typing import Any, Dict, Iterator, List, Sequence, Tuple
|
||||
|
||||
_DEFAULT_DELIMS = [",", ";", "\t"]
|
||||
|
||||
|
||||
def decode_raw_bytes(raw: bytes) -> str:
|
||||
"""UTF-8 bevorzugt, Fallback Latin-1; BOM entfernen."""
|
||||
if not raw:
|
||||
return ""
|
||||
for enc in ("utf-8-sig", "utf-8", "latin-1"):
|
||||
try:
|
||||
text = raw.decode(enc)
|
||||
break
|
||||
except UnicodeDecodeError:
|
||||
text = ""
|
||||
continue
|
||||
else:
|
||||
text = raw.decode("utf-8", errors="replace")
|
||||
if text.startswith("\ufeff"):
|
||||
text = text[1:]
|
||||
return text
|
||||
|
||||
|
||||
def sniff_delimiter(sample_line: str) -> str:
|
||||
"""
|
||||
Heuristik: Zähle Vorkommen der Kandidaten in der ersten Datenzeile.
|
||||
Kein csv.Sniffer (robuster gegen kurze Zeilen).
|
||||
"""
|
||||
if not sample_line or not sample_line.strip():
|
||||
return ","
|
||||
best = ","
|
||||
best_count = -1
|
||||
for d in _DEFAULT_DELIMS:
|
||||
c = sample_line.count(d)
|
||||
if c > best_count:
|
||||
best_count = c
|
||||
best = d
|
||||
return best
|
||||
|
||||
|
||||
def _split_first_lines(text: str, max_lines: int = 5) -> List[str]:
|
||||
lines: List[str] = []
|
||||
for line in text.splitlines():
|
||||
if line.strip():
|
||||
lines.append(line)
|
||||
if len(lines) >= max_lines:
|
||||
break
|
||||
return lines
|
||||
|
||||
|
||||
def canonical_csv_header_label(name: str | None) -> str:
|
||||
"""
|
||||
Einheitlicher Spalten-Key für Analyse (Vorlage/Dialog), Import und Signatur.
|
||||
BOM und NBSP (häufig in Excel/Apple-Exporten) werden vereinheitlicht, damit
|
||||
field_mappings exakt zu DictReader-Zeilen passt.
|
||||
"""
|
||||
if name is None:
|
||||
return ""
|
||||
s = str(name).replace("\ufeff", "").replace("\u00a0", " ").strip()
|
||||
return s
|
||||
|
||||
|
||||
def parse_csv_sample(
|
||||
text: str,
|
||||
delimiter: str | None = None,
|
||||
has_header: bool = True,
|
||||
max_data_rows: int = 5,
|
||||
) -> Tuple[List[str], List[dict[str, str]], str]:
|
||||
"""
|
||||
Gibt (headers, rows_as_dicts, verwendetes_delimiter) zurück.
|
||||
rows sind Rohstrings pro Zelle.
|
||||
"""
|
||||
lines = _split_first_lines(text, max_lines=50)
|
||||
if not lines:
|
||||
return [], [], ","
|
||||
|
||||
delim = delimiter if delimiter is not None else sniff_delimiter(lines[0])
|
||||
reader = csv.reader(io.StringIO(text.replace("\r\n", "\n").replace("\r", "\n")), delimiter=delim)
|
||||
rows_raw: List[List[str]] = []
|
||||
for i, row in enumerate(reader):
|
||||
if i >= 1 + max_data_rows + (1 if has_header else 0):
|
||||
break
|
||||
if not any(c.strip() for c in row):
|
||||
continue
|
||||
rows_raw.append(row)
|
||||
|
||||
if not rows_raw:
|
||||
return [], [], delim
|
||||
|
||||
if has_header:
|
||||
headers = [canonical_csv_header_label(h) for h in rows_raw[0]]
|
||||
data = rows_raw[1 : 1 + max_data_rows]
|
||||
else:
|
||||
n = len(rows_raw[0])
|
||||
headers = [f"col_{i}" for i in range(n)]
|
||||
data = rows_raw[:max_data_rows]
|
||||
|
||||
dict_rows: List[dict[str, str]] = []
|
||||
for r in data:
|
||||
row_dict: dict[str, str] = {}
|
||||
for j, h in enumerate(headers):
|
||||
row_dict[h] = r[j].strip() if j < len(r) else ""
|
||||
dict_rows.append(row_dict)
|
||||
|
||||
return headers, dict_rows, delim
|
||||
|
||||
|
||||
def normalize_header_for_signature(name: str) -> str:
|
||||
s = canonical_csv_header_label(name).lower()
|
||||
s = re.sub(r"\s+", "_", s)
|
||||
s = re.sub(r"[^a-z0-9_äöüß().%-]+", "_", s)
|
||||
return s.strip("_")
|
||||
|
||||
|
||||
def column_signature(headers: List[str]) -> List[str]:
|
||||
"""Sortierte normalisierte Spaltennamen für Signatur-Vergleich."""
|
||||
return sorted(
|
||||
{normalize_header_for_signature(h) for h in headers if h is not None and canonical_csv_header_label(str(h))}
|
||||
)
|
||||
|
||||
|
||||
def headers_signature_match_score(sig_csv: List[str], sig_template: List[str]) -> float:
|
||||
"""Jaccard-Überlappung 0..1 (|A∩B|/|A∪B|). Fällt stark, wenn die CSV viele Zusatzspalten hat."""
|
||||
a, b = set(sig_csv), set(sig_template)
|
||||
if not a and not b:
|
||||
return 1.0
|
||||
if not a or not b:
|
||||
return 0.0
|
||||
inter = len(a & b)
|
||||
union = len(a | b)
|
||||
return inter / union if union else 0.0
|
||||
|
||||
|
||||
def headers_signature_template_recall(sig_csv: Sequence[str], sig_template: Sequence[str]) -> float:
|
||||
"""
|
||||
Anteil der Template-Spalten (Signatur), die in der CSV vorkommen: |A∩B|/|B|.
|
||||
100 %, sobald alle für die Vorlage relevanten Spalten in der Datei sind — unabhängig von
|
||||
Zusatzspalten (Gewicht + Ernährung in einer Datei erzeugt keinen „Abzug“ für die jeweilige Vorlage).
|
||||
"""
|
||||
a = set(sig_csv)
|
||||
b = {normalize_header_for_signature(str(x)) for x in sig_template}
|
||||
b.discard("")
|
||||
if not b:
|
||||
return 1.0 if not a else 0.0
|
||||
inter = len(a & b)
|
||||
return inter / len(b)
|
||||
|
||||
|
||||
def headers_signature_rank_metrics(sig_csv: List[str], sig_template: List[str]) -> dict[str, Any]:
|
||||
"""
|
||||
Einheitliche Kennzahlen für Vorlagen-Ranking und UI.
|
||||
confidence = template_recall (empfohlen für Anzeige / Sortierung primär).
|
||||
"""
|
||||
a = set(sig_csv)
|
||||
b = {normalize_header_for_signature(str(x)) for x in sig_template}
|
||||
b.discard("")
|
||||
inter = a & b
|
||||
n_inter = len(inter)
|
||||
n_b = len(b)
|
||||
n_a = len(a)
|
||||
union = len(a | b)
|
||||
template_recall = n_inter / n_b if n_b else (1.0 if not n_a else 0.0)
|
||||
jaccard = n_inter / union if union else 0.0
|
||||
return {
|
||||
"confidence": round(template_recall, 4),
|
||||
"template_recall": round(template_recall, 4),
|
||||
"jaccard": round(jaccard, 4),
|
||||
"columns_matched": n_inter,
|
||||
"columns_in_template": n_b,
|
||||
"columns_in_csv": n_a,
|
||||
}
|
||||
|
||||
|
||||
def get_csv_import_limits(conn_row: dict | None) -> dict[str, int]:
|
||||
"""Liest Limits aus system_config.csv_import; Fallback bei fehlendem Key."""
|
||||
defaults = {"max_rows_per_file": 50_000, "max_file_bytes": 52_428_800}
|
||||
if not conn_row or "value" not in conn_row:
|
||||
return defaults
|
||||
val = conn_row["value"]
|
||||
if isinstance(val, dict):
|
||||
out = {**defaults, **{k: int(v) for k, v in val.items() if k in defaults}}
|
||||
return out
|
||||
return defaults
|
||||
|
||||
|
||||
def iter_csv_dict_rows(
|
||||
text: str,
|
||||
delimiter: str,
|
||||
*,
|
||||
has_header: bool = True,
|
||||
) -> Iterator[Dict[str, str]]:
|
||||
"""
|
||||
Vollständige Datei zeilenweise als Dict (Header = Keys).
|
||||
Spaltenreihenfolge ist egal; zusätzliche Spalten werden ignoriert, wenn sie nicht
|
||||
in field_mappings vorkommen. Keine Obergrenze für die Spaltenanzahl (nur Zeilenlimits
|
||||
kommen aus system_config / Import-Router).
|
||||
"""
|
||||
if not has_header:
|
||||
raise ValueError("CSV ohne Kopfzeile wird für Import noch nicht unterstützt")
|
||||
normalized = text.replace("\r\n", "\n").replace("\r", "\n")
|
||||
reader = csv.DictReader(io.StringIO(normalized), delimiter=delimiter)
|
||||
for row in reader:
|
||||
if row is None:
|
||||
continue
|
||||
if not any(v and str(v).strip() for v in row.values()):
|
||||
continue
|
||||
yield {
|
||||
canonical_csv_header_label(k): (v or "").strip()
|
||||
for k, v in row.items()
|
||||
if canonical_csv_header_label(k)
|
||||
}
|
||||
@@ -0,0 +1,987 @@
|
||||
"""
|
||||
CSV → Zieltabellen: Upsert, Fehlerliste, affected_ids für csv_import_log (Issue #21).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import datetime as dt
|
||||
import uuid
|
||||
from collections import defaultdict
|
||||
from typing import Any
|
||||
|
||||
import logging
|
||||
|
||||
from csv_parser.core import iter_csv_dict_rows
|
||||
from csv_parser.import_row_processing import (
|
||||
aggregate_mapped_rows,
|
||||
resolve_import_row_processing,
|
||||
validate_import_row_processing,
|
||||
)
|
||||
from csv_parser.module_registry import get_module_definition
|
||||
from csv_parser.import_errors import enrich_row_error
|
||||
from csv_parser.type_converter import build_row_after_mapping
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def _resolve_training_type_for_activity(cur, activity_type: str, profile_id: str):
|
||||
"""Lazy import — gleicher DB-Cursor wie der Import (kein verschachteltes get_db / Pool-Deadlock)."""
|
||||
from routers.activity import get_training_type_for_activity_with_cursor
|
||||
|
||||
return get_training_type_for_activity_with_cursor(cur, activity_type, profile_id)
|
||||
|
||||
|
||||
def coerce_date(val: Any) -> dt.date | None:
|
||||
if val is None:
|
||||
return None
|
||||
if isinstance(val, dt.datetime):
|
||||
return val.date()
|
||||
if isinstance(val, dt.date):
|
||||
return val
|
||||
return None
|
||||
|
||||
|
||||
def _derive_bp_context(hour: int) -> str:
|
||||
if 5 <= hour < 10:
|
||||
return "morning_fasted"
|
||||
if 18 <= hour < 23:
|
||||
return "evening"
|
||||
return "other"
|
||||
|
||||
|
||||
def run_universal_csv_import(
|
||||
cur,
|
||||
profile_id: str,
|
||||
module: str,
|
||||
text: str,
|
||||
filename: str,
|
||||
mapping: dict[str, Any],
|
||||
) -> dict[str, Any]:
|
||||
"""
|
||||
Nutzt cur innerhalb einer bestehenden Transaktion.
|
||||
Gibt Statistik + affected_ids (+ error_details) zurück.
|
||||
"""
|
||||
mod = get_module_definition(module)
|
||||
if not mod:
|
||||
raise ValueError(f"Unbekanntes Modul: {module}")
|
||||
|
||||
rows_total = 0
|
||||
error_details: list[dict[str, Any]] = []
|
||||
affected_ids: dict[str, list[str]] = defaultdict(list)
|
||||
|
||||
if module == "sleep":
|
||||
from csv_parser.sleep_apple_import import import_apple_sleep_nights
|
||||
|
||||
try:
|
||||
r = import_apple_sleep_nights(cur, profile_id, text)
|
||||
except ValueError as e:
|
||||
raise ValueError(str(e)) from e
|
||||
error_details.extend(r.get("error_details") or [])
|
||||
for sid in r.get("affected_ids") or []:
|
||||
affected_ids["sleep_log"].append(sid)
|
||||
return {
|
||||
"rows_total": r["rows_total"],
|
||||
"rows_imported": r["inserted"],
|
||||
"rows_updated": r["updated"],
|
||||
"rows_skipped": r["skipped"],
|
||||
"rows_errors": len(error_details),
|
||||
"error_details": error_details[:50],
|
||||
"new_entries": r.get("new_entries", r["inserted"]),
|
||||
"affected_ids": dict(affected_ids),
|
||||
}
|
||||
|
||||
fm = mapping.get("field_mappings") or {}
|
||||
if isinstance(fm, str):
|
||||
raise ValueError("field_mappings muss ein Objekt sein")
|
||||
tc = mapping.get("type_conversions")
|
||||
if tc is not None and not isinstance(tc, dict):
|
||||
tc = None
|
||||
|
||||
delim = mapping.get("delimiter") or ","
|
||||
has_header = mapping.get("has_header", True)
|
||||
|
||||
if module == "nutrition":
|
||||
stats = _import_nutrition(
|
||||
cur,
|
||||
profile_id,
|
||||
text,
|
||||
delim,
|
||||
bool(has_header),
|
||||
fm,
|
||||
tc,
|
||||
mapping,
|
||||
error_details,
|
||||
affected_ids,
|
||||
)
|
||||
rows_total = stats.pop("rows_total")
|
||||
elif module == "weight":
|
||||
stats = _import_weight(
|
||||
cur,
|
||||
profile_id,
|
||||
text,
|
||||
delim,
|
||||
bool(has_header),
|
||||
fm,
|
||||
tc,
|
||||
mapping,
|
||||
error_details,
|
||||
affected_ids,
|
||||
)
|
||||
rows_total = stats.pop("rows_total")
|
||||
elif module == "blood_pressure":
|
||||
stats = _import_blood_pressure(
|
||||
cur,
|
||||
profile_id,
|
||||
text,
|
||||
delim,
|
||||
bool(has_header),
|
||||
fm,
|
||||
tc,
|
||||
error_details,
|
||||
affected_ids,
|
||||
)
|
||||
rows_total = stats.pop("rows_total")
|
||||
elif module == "activity":
|
||||
stats = _import_activity(
|
||||
cur,
|
||||
profile_id,
|
||||
text,
|
||||
delim,
|
||||
bool(has_header),
|
||||
fm,
|
||||
tc,
|
||||
error_details,
|
||||
affected_ids,
|
||||
)
|
||||
rows_total = stats.pop("rows_total")
|
||||
elif module == "vitals_baseline":
|
||||
stats = _import_vitals_baseline(
|
||||
cur,
|
||||
profile_id,
|
||||
text,
|
||||
delim,
|
||||
bool(has_header),
|
||||
fm,
|
||||
tc,
|
||||
mapping,
|
||||
error_details,
|
||||
affected_ids,
|
||||
)
|
||||
rows_total = stats.pop("rows_total")
|
||||
else:
|
||||
raise ValueError(f"Modul '{module}' wird für Universal-Import noch nicht unterstützt")
|
||||
|
||||
out = {
|
||||
"rows_total": rows_total,
|
||||
"rows_imported": stats.get("inserted", 0),
|
||||
"rows_updated": stats.get("updated", 0),
|
||||
"rows_skipped": stats.get("skipped", 0),
|
||||
"rows_errors": len(error_details),
|
||||
"error_details": error_details[:50],
|
||||
"new_entries": stats.get("new_entries", stats.get("inserted", 0)),
|
||||
"affected_ids": dict(affected_ids),
|
||||
}
|
||||
return out
|
||||
|
||||
|
||||
def _import_nutrition(
|
||||
cur,
|
||||
profile_id: str,
|
||||
text: str,
|
||||
delim: str,
|
||||
has_header: bool,
|
||||
fm: dict,
|
||||
tc: dict | None,
|
||||
mapping: dict[str, Any],
|
||||
error_details: list,
|
||||
affected_ids: dict,
|
||||
) -> dict[str, int]:
|
||||
spec = resolve_import_row_processing("nutrition", mapping)
|
||||
mapped_rows: list[dict[str, Any]] = []
|
||||
rows_total = 0
|
||||
for csv_row in iter_csv_dict_rows(text, delim, has_header=has_header):
|
||||
rows_total += 1
|
||||
mapped = build_row_after_mapping(csv_row, fm, tc, module="nutrition")
|
||||
d = coerce_date(mapped.get("date"))
|
||||
if d is None:
|
||||
error_details.append({"row": rows_total, "error": "Datum fehlt oder ungültig"})
|
||||
continue
|
||||
mapped["date"] = d
|
||||
mapped_rows.append(mapped)
|
||||
|
||||
if spec:
|
||||
try:
|
||||
validate_import_row_processing("nutrition", spec, fm)
|
||||
except ValueError as e:
|
||||
raise ValueError(str(e)) from e
|
||||
merged_rows, agg_notes = aggregate_mapped_rows(mapped_rows, spec)
|
||||
error_details.extend(agg_notes)
|
||||
else:
|
||||
merged_rows = list(mapped_rows)
|
||||
agg_notes = []
|
||||
|
||||
skipped_groups = sum(n.get("rows_in_group", 0) for n in (agg_notes or []) if n.get("error") == "mehrere_zeilen_pro_schluessel")
|
||||
|
||||
inserted = 0
|
||||
updated = 0
|
||||
new_entries = 0
|
||||
for merged in merged_rows:
|
||||
d = coerce_date(merged.get("date"))
|
||||
if d is None:
|
||||
continue
|
||||
iso = d.isoformat()
|
||||
|
||||
def _sf_macro(x: Any) -> float:
|
||||
if x is None or x == "":
|
||||
return 0.0
|
||||
try:
|
||||
return float(x)
|
||||
except (TypeError, ValueError):
|
||||
return 0.0
|
||||
|
||||
kcal = round(_sf_macro(merged.get("kcal")), 1)
|
||||
fat = round(_sf_macro(merged.get("fat_g")), 1)
|
||||
carbs = round(_sf_macro(merged.get("carbs_g")), 1)
|
||||
prot = round(_sf_macro(merged.get("protein_g")), 1)
|
||||
if kcal == 0 and fat == 0 and carbs == 0 and prot == 0:
|
||||
continue
|
||||
|
||||
cur.execute(
|
||||
"SELECT id FROM nutrition_log WHERE profile_id=%s AND date=%s",
|
||||
(profile_id, iso),
|
||||
)
|
||||
existing = cur.fetchone()
|
||||
if existing:
|
||||
cur.execute(
|
||||
"""
|
||||
UPDATE nutrition_log
|
||||
SET kcal=%s, protein_g=%s, fat_g=%s, carbs_g=%s, source='csv'
|
||||
WHERE profile_id=%s AND date=%s
|
||||
RETURNING id
|
||||
""",
|
||||
(kcal, prot, fat, carbs, profile_id, iso),
|
||||
)
|
||||
row = cur.fetchone()
|
||||
updated += 1
|
||||
if row and row.get("id"):
|
||||
affected_ids["nutrition_log"].append(str(row["id"]))
|
||||
else:
|
||||
eid = str(uuid.uuid4())
|
||||
cur.execute(
|
||||
"""
|
||||
INSERT INTO nutrition_log (id, profile_id, date, kcal, protein_g, fat_g, carbs_g, source, created)
|
||||
VALUES (%s,%s,%s,%s,%s,%s,%s,'csv',CURRENT_TIMESTAMP)
|
||||
""",
|
||||
(eid, profile_id, iso, kcal, prot, fat, carbs),
|
||||
)
|
||||
inserted += 1
|
||||
new_entries += 1
|
||||
affected_ids["nutrition_log"].append(eid)
|
||||
|
||||
return {
|
||||
"rows_total": rows_total,
|
||||
"inserted": inserted,
|
||||
"updated": updated,
|
||||
"skipped": skipped_groups,
|
||||
"new_entries": new_entries,
|
||||
}
|
||||
|
||||
|
||||
def _import_weight(
|
||||
cur,
|
||||
profile_id: str,
|
||||
text: str,
|
||||
delim: str,
|
||||
has_header: bool,
|
||||
fm: dict,
|
||||
tc: dict | None,
|
||||
mapping: dict[str, Any],
|
||||
error_details: list,
|
||||
affected_ids: dict,
|
||||
) -> dict[str, int]:
|
||||
spec = resolve_import_row_processing("weight", mapping)
|
||||
mapped_rows: list[dict[str, Any]] = []
|
||||
rows_total = 0
|
||||
for csv_row in iter_csv_dict_rows(text, delim, has_header=has_header):
|
||||
rows_total += 1
|
||||
mapped = build_row_after_mapping(csv_row, fm, tc, module="weight")
|
||||
d = coerce_date(mapped.get("date"))
|
||||
w = mapped.get("weight")
|
||||
if d is None:
|
||||
error_details.append({"row": rows_total, "error": "Datum fehlt"})
|
||||
continue
|
||||
if w is None:
|
||||
error_details.append({"row": rows_total, "error": "Gewicht fehlt"})
|
||||
continue
|
||||
try:
|
||||
float(w)
|
||||
except (TypeError, ValueError):
|
||||
error_details.append({"row": rows_total, "error": "Gewicht ungültig"})
|
||||
continue
|
||||
mapped["date"] = d
|
||||
mapped_rows.append(mapped)
|
||||
|
||||
if spec:
|
||||
try:
|
||||
validate_import_row_processing("weight", spec, fm)
|
||||
except ValueError as e:
|
||||
raise ValueError(str(e)) from e
|
||||
merged_rows, agg_notes = aggregate_mapped_rows(mapped_rows, spec)
|
||||
error_details.extend(agg_notes)
|
||||
else:
|
||||
merged_rows = list(mapped_rows)
|
||||
agg_notes = []
|
||||
|
||||
skipped_groups = sum(n.get("rows_in_group", 0) for n in (agg_notes or []) if n.get("error") == "mehrere_zeilen_pro_schluessel")
|
||||
|
||||
inserted = 0
|
||||
updated = 0
|
||||
new_entries = 0
|
||||
for merged in merged_rows:
|
||||
d = coerce_date(merged.get("date"))
|
||||
w = merged.get("weight")
|
||||
note = merged.get("note")
|
||||
if d is None:
|
||||
continue
|
||||
if w is None:
|
||||
continue
|
||||
try:
|
||||
w = float(w)
|
||||
except (TypeError, ValueError):
|
||||
continue
|
||||
iso = d.isoformat()
|
||||
cur.execute(
|
||||
"SELECT id FROM weight_log WHERE profile_id=%s AND date=%s",
|
||||
(profile_id, iso),
|
||||
)
|
||||
existing = cur.fetchone()
|
||||
if existing:
|
||||
cur.execute(
|
||||
"""
|
||||
UPDATE weight_log SET weight=%s, note=COALESCE(%s, note), source='csv'
|
||||
WHERE profile_id=%s AND date=%s
|
||||
RETURNING id
|
||||
""",
|
||||
(w, note, profile_id, iso),
|
||||
)
|
||||
row = cur.fetchone()
|
||||
updated += 1
|
||||
if row and row.get("id"):
|
||||
affected_ids["weight_log"].append(str(row["id"]))
|
||||
else:
|
||||
eid = str(uuid.uuid4())
|
||||
cur.execute(
|
||||
"""
|
||||
INSERT INTO weight_log (id, profile_id, date, weight, note, source, created)
|
||||
VALUES (%s,%s,%s,%s,%s,'csv',CURRENT_TIMESTAMP)
|
||||
""",
|
||||
(eid, profile_id, iso, w, note),
|
||||
)
|
||||
inserted += 1
|
||||
new_entries += 1
|
||||
affected_ids["weight_log"].append(eid)
|
||||
|
||||
return {
|
||||
"rows_total": rows_total,
|
||||
"inserted": inserted,
|
||||
"updated": updated,
|
||||
"skipped": skipped_groups,
|
||||
"new_entries": new_entries,
|
||||
}
|
||||
|
||||
|
||||
def diagnose_blood_pressure_row(mapped_typed: dict[str, Any]) -> dict[str, Any]:
|
||||
"""Zeigt, ob Datum/Zeit nach Vorlage + Alias + Apple-Start-Spalte erkannt werden."""
|
||||
md = coerce_date(mapped_typed.get("measured_date"))
|
||||
mt = mapped_typed.get("measured_time")
|
||||
st_combined = mapped_typed.get("start_time")
|
||||
if isinstance(st_combined, dt.datetime):
|
||||
if md is None:
|
||||
md = st_combined.date()
|
||||
if mt is None:
|
||||
mt = st_combined.time()
|
||||
elif isinstance(st_combined, str) and st_combined.strip() and (md is None or mt is None):
|
||||
try:
|
||||
from dateutil import parser as du_parser
|
||||
|
||||
dtp = du_parser.parse(st_combined.strip())
|
||||
if md is None:
|
||||
md = dtp.date()
|
||||
if mt is None:
|
||||
mt = dtp.time()
|
||||
except (ValueError, TypeError, OverflowError):
|
||||
pass
|
||||
sys_v = mapped_typed.get("systolic")
|
||||
dia_v = mapped_typed.get("diastolic")
|
||||
try:
|
||||
int(sys_v)
|
||||
int(dia_v)
|
||||
ok_bp = True
|
||||
except (TypeError, ValueError):
|
||||
ok_bp = False
|
||||
return {
|
||||
"measured_date_iso": md.isoformat() if md else None,
|
||||
"has_measured_time": mt is not None,
|
||||
"start_time_raw_type": type(st_combined).__name__ if st_combined is not None else None,
|
||||
"systolic_ok": ok_bp,
|
||||
"would_reach_insert_check": md is not None and mt is not None,
|
||||
}
|
||||
|
||||
|
||||
def diagnose_activity_row(mapped_typed: dict[str, Any]) -> dict[str, Any]:
|
||||
activity_type = mapped_typed.get("activity_type")
|
||||
start_raw = mapped_typed.get("start_time")
|
||||
date_d = coerce_date(mapped_typed.get("date"))
|
||||
start_key: str | None = None
|
||||
fail_hint: str | None = None
|
||||
if isinstance(start_raw, dt.datetime):
|
||||
start_key = start_raw.strftime("%Y-%m-%d %H:%M:%S")
|
||||
if date_d is None:
|
||||
date_d = start_raw.date()
|
||||
elif isinstance(start_raw, dt.time):
|
||||
if date_d is None:
|
||||
fail_hint = "startzeit_ohne_datum"
|
||||
else:
|
||||
start_key = f"{date_d.isoformat()} {start_raw.strftime('%H:%M:%S')}"
|
||||
elif isinstance(start_raw, str) and start_raw.strip():
|
||||
s = start_raw.strip()
|
||||
if date_d is not None and _looks_like_time_only(s):
|
||||
start_key = f"{date_d.isoformat()} {s}"
|
||||
else:
|
||||
start_key = s
|
||||
if date_d is None and len(start_key) >= 10:
|
||||
for fmt in ("%Y-%m-%d", "%d.%m.%Y"):
|
||||
try:
|
||||
date_d = dt.datetime.strptime(start_key[:10], fmt).date()
|
||||
break
|
||||
except ValueError:
|
||||
continue
|
||||
has_type = bool(activity_type and str(activity_type).strip())
|
||||
ok = has_type and date_d is not None and bool(start_key)
|
||||
if fail_hint is None and not has_type:
|
||||
fail_hint = "trainingsart_fehlt"
|
||||
elif fail_hint is None and not ok:
|
||||
fail_hint = "datum_start_fehlt"
|
||||
return {
|
||||
"activity_type_preview": (str(activity_type).strip()[:80] if activity_type else None),
|
||||
"date_iso": date_d.isoformat() if date_d else None,
|
||||
"start_key_preview": (start_key[:80] if start_key else None),
|
||||
"would_pass_row_gate": ok,
|
||||
"fail_hint": fail_hint,
|
||||
}
|
||||
|
||||
|
||||
def _import_blood_pressure(
|
||||
cur,
|
||||
profile_id: str,
|
||||
text: str,
|
||||
delim: str,
|
||||
has_header: bool,
|
||||
fm: dict,
|
||||
tc: dict | None,
|
||||
error_details: list,
|
||||
affected_ids: dict,
|
||||
) -> dict[str, int]:
|
||||
rows_total = 0
|
||||
inserted = 0
|
||||
updated = 0
|
||||
skipped = 0
|
||||
for csv_row in iter_csv_dict_rows(text, delim, has_header=has_header):
|
||||
rows_total += 1
|
||||
mapped = build_row_after_mapping(csv_row, fm, tc, module="blood_pressure")
|
||||
md = coerce_date(mapped.get("measured_date"))
|
||||
mt = mapped.get("measured_time")
|
||||
st_combined = mapped.get("start_time")
|
||||
if isinstance(st_combined, dt.datetime):
|
||||
if md is None:
|
||||
md = st_combined.date()
|
||||
if mt is None:
|
||||
mt = st_combined.time()
|
||||
elif isinstance(st_combined, str) and st_combined.strip() and (md is None or mt is None):
|
||||
try:
|
||||
from dateutil import parser as du_parser
|
||||
|
||||
dtp = du_parser.parse(st_combined.strip())
|
||||
if md is None:
|
||||
md = dtp.date()
|
||||
if mt is None:
|
||||
mt = dtp.time()
|
||||
except (ValueError, TypeError, OverflowError):
|
||||
pass
|
||||
if md is None:
|
||||
error_details.append({"row": rows_total, "error": "Datum fehlt"})
|
||||
continue
|
||||
if mt is None:
|
||||
error_details.append({"row": rows_total, "error": "Zeit fehlt"})
|
||||
continue
|
||||
if isinstance(mt, str):
|
||||
try:
|
||||
parts = mt.replace(".", ":").split(":")
|
||||
if len(parts) >= 2:
|
||||
mt = dt.time(int(parts[0]), int(parts[1]), int(parts[2]) if len(parts) > 2 else 0)
|
||||
else:
|
||||
raise ValueError()
|
||||
except Exception:
|
||||
error_details.append({"row": rows_total, "error": "Zeit ungültig"})
|
||||
continue
|
||||
if not isinstance(mt, dt.time):
|
||||
error_details.append({"row": rows_total, "error": "Zeitformat wird nicht unterstützt"})
|
||||
continue
|
||||
|
||||
systolic = mapped.get("systolic")
|
||||
diastolic = mapped.get("diastolic")
|
||||
pulse = mapped.get("pulse")
|
||||
try:
|
||||
sys_i = int(systolic)
|
||||
dia_i = int(diastolic)
|
||||
except (TypeError, ValueError):
|
||||
error_details.append({"row": rows_total, "error": "Blutdruckwerte fehlen oder ungültig"})
|
||||
continue
|
||||
pulse_i = int(pulse) if pulse is not None else None
|
||||
|
||||
measured_at = dt.datetime.combine(md, mt)
|
||||
hour = mt.hour
|
||||
context = _derive_bp_context(hour)
|
||||
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT id FROM blood_pressure_log
|
||||
WHERE profile_id = %s AND measured_at = %s
|
||||
""",
|
||||
(profile_id, measured_at),
|
||||
)
|
||||
existing_bp = cur.fetchone()
|
||||
if existing_bp:
|
||||
cur.execute(
|
||||
"""
|
||||
UPDATE blood_pressure_log SET
|
||||
systolic = %s, diastolic = %s, pulse = %s,
|
||||
context = %s, source = 'csv'
|
||||
WHERE profile_id = %s AND measured_at = %s
|
||||
RETURNING id
|
||||
""",
|
||||
(sys_i, dia_i, pulse_i, context, profile_id, measured_at),
|
||||
)
|
||||
row = cur.fetchone()
|
||||
updated += 1
|
||||
if row and row.get("id"):
|
||||
affected_ids["blood_pressure_log"].append(str(row["id"]))
|
||||
else:
|
||||
cur.execute(
|
||||
"""
|
||||
INSERT INTO blood_pressure_log (
|
||||
profile_id, measured_at,
|
||||
systolic, diastolic, pulse,
|
||||
context, source
|
||||
) VALUES (%s, %s, %s, %s, %s, %s, 'csv')
|
||||
RETURNING id
|
||||
""",
|
||||
(profile_id, measured_at, sys_i, dia_i, pulse_i, context),
|
||||
)
|
||||
row = cur.fetchone()
|
||||
inserted += 1
|
||||
if row and row.get("id"):
|
||||
affected_ids["blood_pressure_log"].append(str(row["id"]))
|
||||
|
||||
return {
|
||||
"rows_total": rows_total,
|
||||
"inserted": inserted,
|
||||
"updated": updated,
|
||||
"skipped": skipped,
|
||||
"new_entries": inserted,
|
||||
}
|
||||
|
||||
|
||||
def _v_safe_int(value: Any) -> int | None:
|
||||
if value is None or value == "":
|
||||
return None
|
||||
try:
|
||||
if isinstance(value, float):
|
||||
return int(value)
|
||||
s = str(value).strip()
|
||||
if "." in s:
|
||||
return int(float(s))
|
||||
return int(s)
|
||||
except (ValueError, TypeError):
|
||||
return None
|
||||
|
||||
|
||||
def _v_safe_float(value: Any) -> float | None:
|
||||
if value is None or value == "":
|
||||
return None
|
||||
try:
|
||||
return float(value)
|
||||
except (ValueError, TypeError):
|
||||
return None
|
||||
|
||||
|
||||
def diagnose_vitals_row(mapped_typed: dict[str, Any]) -> dict[str, Any]:
|
||||
"""Erklärt Vital-Baseline-Zeile nach Typkonvertierung (ohne DB)."""
|
||||
d = coerce_date(mapped_typed.get("date"))
|
||||
rhr = _v_safe_int(mapped_typed.get("resting_hr"))
|
||||
hrv = _v_safe_int(mapped_typed.get("hrv"))
|
||||
vo2 = _v_safe_float(mapped_typed.get("vo2_max"))
|
||||
spo2 = _v_safe_int(mapped_typed.get("spo2"))
|
||||
resp = _v_safe_float(mapped_typed.get("respiratory_rate"))
|
||||
has_metric = any(x is not None for x in (rhr, hrv, vo2, spo2, resp))
|
||||
date_raw = mapped_typed.get("date")
|
||||
return {
|
||||
"date_coerced_iso": d.isoformat() if d else None,
|
||||
"date_after_convert_repr": repr(date_raw),
|
||||
"date_after_convert_type": type(date_raw).__name__,
|
||||
"metrics": {
|
||||
"resting_hr": rhr,
|
||||
"hrv": hrv,
|
||||
"vo2_max": vo2,
|
||||
"spo2": spo2,
|
||||
"respiratory_rate": resp,
|
||||
},
|
||||
"would_pass_prefilter": d is not None and has_metric,
|
||||
"prefilter_fail_reason": (
|
||||
"datum_fehlt"
|
||||
if d is None
|
||||
else ("keine_baseline_metrik" if not has_metric else None)
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
def _import_vitals_baseline(
|
||||
cur,
|
||||
profile_id: str,
|
||||
text: str,
|
||||
delim: str,
|
||||
has_header: bool,
|
||||
fm: dict,
|
||||
tc: dict | None,
|
||||
mapping: dict[str, Any],
|
||||
error_details: list,
|
||||
affected_ids: dict,
|
||||
) -> dict[str, int]:
|
||||
spec = resolve_import_row_processing("vitals_baseline", mapping)
|
||||
mapped_rows: list[dict[str, Any]] = []
|
||||
rows_total = 0
|
||||
skipped_prefilter = 0
|
||||
for csv_row in iter_csv_dict_rows(text, delim, has_header=has_header):
|
||||
rows_total += 1
|
||||
mapped = build_row_after_mapping(csv_row, fm, tc, module="vitals_baseline")
|
||||
d = coerce_date(mapped.get("date"))
|
||||
if d is None:
|
||||
error_details.append({"row": rows_total, "error": "Datum fehlt"})
|
||||
continue
|
||||
rhr = _v_safe_int(mapped.get("resting_hr"))
|
||||
hrv = _v_safe_int(mapped.get("hrv"))
|
||||
vo2 = _v_safe_float(mapped.get("vo2_max"))
|
||||
spo2 = _v_safe_int(mapped.get("spo2"))
|
||||
resp = _v_safe_float(mapped.get("respiratory_rate"))
|
||||
if not any(x is not None for x in (rhr, hrv, vo2, spo2, resp)):
|
||||
skipped_prefilter += 1
|
||||
continue
|
||||
mapped["date"] = d
|
||||
mapped_rows.append(mapped)
|
||||
|
||||
if spec:
|
||||
try:
|
||||
validate_import_row_processing("vitals_baseline", spec, fm)
|
||||
except ValueError as e:
|
||||
raise ValueError(str(e)) from e
|
||||
merged_rows, agg_notes = aggregate_mapped_rows(mapped_rows, spec)
|
||||
error_details.extend(agg_notes)
|
||||
else:
|
||||
merged_rows = list(mapped_rows)
|
||||
agg_notes = []
|
||||
|
||||
skipped_merge = sum(n.get("rows_in_group", 0) for n in (agg_notes or []) if n.get("error") == "mehrere_zeilen_pro_schluessel")
|
||||
|
||||
inserted = 0
|
||||
updated = 0
|
||||
skipped = skipped_prefilter + skipped_merge
|
||||
for merged in merged_rows:
|
||||
d = coerce_date(merged.get("date"))
|
||||
if d is None:
|
||||
continue
|
||||
rhr = _v_safe_int(merged.get("resting_hr"))
|
||||
hrv = _v_safe_int(merged.get("hrv"))
|
||||
vo2 = _v_safe_float(merged.get("vo2_max"))
|
||||
spo2 = _v_safe_int(merged.get("spo2"))
|
||||
resp = _v_safe_float(merged.get("respiratory_rate"))
|
||||
if not any(x is not None for x in (rhr, hrv, vo2, spo2, resp)):
|
||||
skipped += 1
|
||||
continue
|
||||
iso = d.isoformat()
|
||||
try:
|
||||
# Ohne SAVEPOINT: erster fehlgeschlagener INSERT setzt die Xact auf „aborted“,
|
||||
# alle folgenden Queries + commit() schlagen fehl → generischer 500.
|
||||
cur.execute("SAVEPOINT vitals_csv_row")
|
||||
cur.execute(
|
||||
"""
|
||||
INSERT INTO vitals_baseline (
|
||||
profile_id, date,
|
||||
resting_hr, hrv, vo2_max, spo2, respiratory_rate,
|
||||
source
|
||||
) VALUES (%s, %s, %s, %s, %s, %s, %s, 'csv')
|
||||
ON CONFLICT (profile_id, date)
|
||||
DO UPDATE SET
|
||||
resting_hr = COALESCE(EXCLUDED.resting_hr, vitals_baseline.resting_hr),
|
||||
hrv = COALESCE(EXCLUDED.hrv, vitals_baseline.hrv),
|
||||
vo2_max = COALESCE(EXCLUDED.vo2_max, vitals_baseline.vo2_max),
|
||||
spo2 = COALESCE(EXCLUDED.spo2, vitals_baseline.spo2),
|
||||
respiratory_rate = COALESCE(EXCLUDED.respiratory_rate, vitals_baseline.respiratory_rate),
|
||||
updated_at = NOW()
|
||||
WHERE vitals_baseline.source != 'manual'
|
||||
RETURNING (xmax = 0) AS inserted, id
|
||||
""",
|
||||
(profile_id, iso, rhr, hrv, vo2, spo2, resp),
|
||||
)
|
||||
result = cur.fetchone()
|
||||
if result is None:
|
||||
skipped += 1
|
||||
elif result.get("inserted"):
|
||||
inserted += 1
|
||||
if result.get("id"):
|
||||
affected_ids["vitals_baseline"].append(str(result["id"]))
|
||||
else:
|
||||
updated += 1
|
||||
if result.get("id"):
|
||||
affected_ids["vitals_baseline"].append(str(result["id"]))
|
||||
cur.execute("RELEASE SAVEPOINT vitals_csv_row")
|
||||
except Exception as e:
|
||||
try:
|
||||
cur.execute("ROLLBACK TO SAVEPOINT vitals_csv_row")
|
||||
except Exception:
|
||||
pass
|
||||
err = enrich_row_error(str(e), module="vitals_baseline")
|
||||
error_details.append(
|
||||
{"row": rows_total, "context": "vitals_baseline upsert", **err},
|
||||
)
|
||||
|
||||
return {
|
||||
"rows_total": rows_total,
|
||||
"inserted": inserted,
|
||||
"updated": updated,
|
||||
"skipped": skipped,
|
||||
"new_entries": inserted,
|
||||
}
|
||||
|
||||
|
||||
def _sf_act(val: Any) -> float | None:
|
||||
try:
|
||||
return round(float(val), 1) if val is not None else None
|
||||
except (TypeError, ValueError):
|
||||
return None
|
||||
|
||||
|
||||
def _activity_hr_bpm(val: Any) -> float | None:
|
||||
"""Plausible Herzfrequenz (Import); größere Werte oft Fehlzuordnung (z. B. Schrittzahl) → NUMERIC-Overflow."""
|
||||
v = _sf_act(val)
|
||||
if v is None:
|
||||
return None
|
||||
if v < 20 or v > 280:
|
||||
return None
|
||||
return v
|
||||
|
||||
|
||||
def _looks_like_time_only(s: str) -> bool:
|
||||
t = s.strip()
|
||||
if not t or " " in t:
|
||||
return False
|
||||
parts = t.split(":")
|
||||
if len(parts) < 2 or len(parts) > 3:
|
||||
return False
|
||||
try:
|
||||
for p in parts:
|
||||
int(p)
|
||||
return True
|
||||
except ValueError:
|
||||
return False
|
||||
|
||||
|
||||
def _import_activity(
|
||||
cur,
|
||||
profile_id: str,
|
||||
text: str,
|
||||
delim: str,
|
||||
has_header: bool,
|
||||
fm: dict,
|
||||
tc: dict | None,
|
||||
error_details: list,
|
||||
affected_ids: dict,
|
||||
) -> dict[str, int]:
|
||||
from data_layer.activity_time_normalize import normalize_activity_start
|
||||
from data_layer.activity_persistence_orchestrator import (
|
||||
activity_csv_registry_updates_from_mapped,
|
||||
find_activity_duplicate_id,
|
||||
insert_activity_csv_minimal,
|
||||
new_activity_id,
|
||||
run_activity_post_write_hooks_import,
|
||||
update_activity_columns,
|
||||
)
|
||||
from data_layer.activity_session_metrics import upsert_session_metrics_from_csv_mapped
|
||||
|
||||
rows_total = 0
|
||||
inserted = 0
|
||||
updated = 0
|
||||
new_entries = 0
|
||||
|
||||
for csv_row in iter_csv_dict_rows(text, delim, has_header=has_header):
|
||||
rows_total += 1
|
||||
mapped = build_row_after_mapping(csv_row, fm, tc, module="activity")
|
||||
activity_type = mapped.get("activity_type")
|
||||
if not activity_type or not str(activity_type).strip():
|
||||
error_details.append({"row": rows_total, "error": "Trainingsart fehlt"})
|
||||
continue
|
||||
|
||||
start_raw = mapped.get("start_time")
|
||||
date_d = coerce_date(mapped.get("date"))
|
||||
start_key: str | None = None
|
||||
if isinstance(start_raw, dt.datetime):
|
||||
start_key = start_raw.strftime("%Y-%m-%d %H:%M:%S")
|
||||
if date_d is None:
|
||||
date_d = start_raw.date()
|
||||
elif isinstance(start_raw, dt.date):
|
||||
date_d = start_raw
|
||||
start_key = f"{start_raw.isoformat()} 00:00:00"
|
||||
elif isinstance(start_raw, dt.time):
|
||||
if date_d is None:
|
||||
error_details.append(
|
||||
{"row": rows_total, "error": "Startzeit (Uhrzeit) ohne Datumsspalte"}
|
||||
)
|
||||
continue
|
||||
start_key = f"{date_d.isoformat()} {start_raw.strftime('%H:%M:%S')}"
|
||||
elif isinstance(start_raw, str) and start_raw.strip():
|
||||
s = start_raw.strip()
|
||||
if date_d is not None and _looks_like_time_only(s):
|
||||
start_key = f"{date_d.isoformat()} {s}"
|
||||
else:
|
||||
start_key = s
|
||||
if date_d is None and len(start_key) >= 10:
|
||||
for fmt in ("%Y-%m-%d", "%d.%m.%Y"):
|
||||
try:
|
||||
date_d = dt.datetime.strptime(start_key[:10], fmt).date()
|
||||
break
|
||||
except ValueError:
|
||||
continue
|
||||
|
||||
if date_d is None or not start_key:
|
||||
error_details.append({"row": rows_total, "error": "Datum/Startzeit fehlt oder ungültig"})
|
||||
continue
|
||||
|
||||
end_raw = mapped.get("end_time")
|
||||
if isinstance(end_raw, dt.datetime):
|
||||
end_str = end_raw.strftime("%Y-%m-%d %H:%M:%S")
|
||||
elif isinstance(end_raw, str):
|
||||
end_str = end_raw.strip()
|
||||
else:
|
||||
end_str = ""
|
||||
|
||||
duration_min = mapped.get("duration_min")
|
||||
if duration_min is not None:
|
||||
try:
|
||||
duration_min = round(float(duration_min), 1)
|
||||
except (TypeError, ValueError):
|
||||
duration_min = None
|
||||
|
||||
kcal_a = _sf_act(mapped.get("kcal_active"))
|
||||
kcal_r = _sf_act(mapped.get("kcal_resting"))
|
||||
hr_a = _activity_hr_bpm(mapped.get("hr_avg"))
|
||||
hr_m = _activity_hr_bpm(mapped.get("hr_max"))
|
||||
dist = _sf_act(mapped.get("distance_km"))
|
||||
|
||||
wtype = str(activity_type).strip()
|
||||
iso = date_d.isoformat()
|
||||
_, workout_start_t = normalize_activity_start(start_key)
|
||||
|
||||
# Pro Zeile: bei SQL-Fehler sonst „current transaction is aborted“ bis Xact-Ende.
|
||||
cur.execute("SAVEPOINT csv_activity_row")
|
||||
try:
|
||||
training_type_id, training_category, training_subcategory = _resolve_training_type_for_activity(
|
||||
cur, wtype, profile_id
|
||||
)
|
||||
registry_updates = activity_csv_registry_updates_from_mapped(mapped)
|
||||
existing_id = find_activity_duplicate_id(cur, profile_id, iso, workout_start_t)
|
||||
|
||||
if existing_id:
|
||||
upd = {
|
||||
"start_time": workout_start_t,
|
||||
"end_time": end_str or None,
|
||||
"activity_type": wtype,
|
||||
"duration_min": duration_min,
|
||||
"kcal_active": kcal_a,
|
||||
"kcal_resting": kcal_r,
|
||||
"hr_avg": hr_a,
|
||||
"hr_max": hr_m,
|
||||
"distance_km": dist,
|
||||
"training_type_id": training_type_id,
|
||||
"training_category": training_category,
|
||||
"training_subcategory": training_subcategory,
|
||||
"source": "csv",
|
||||
}
|
||||
upd.update(registry_updates)
|
||||
update_activity_columns(cur, profile_id, existing_id, upd)
|
||||
updated += 1
|
||||
affected_ids["activity_log"].append(str(existing_id))
|
||||
aid = existing_id
|
||||
else:
|
||||
eid = new_activity_id()
|
||||
insert_activity_csv_minimal(
|
||||
cur,
|
||||
profile_id,
|
||||
eid,
|
||||
date_iso=iso,
|
||||
start_time=workout_start_t,
|
||||
end_time=end_str or None,
|
||||
activity_type=wtype,
|
||||
duration_min=duration_min,
|
||||
kcal_active=kcal_a,
|
||||
kcal_resting=kcal_r,
|
||||
hr_avg=hr_a,
|
||||
hr_max=hr_m,
|
||||
distance_km=dist,
|
||||
training_type_id=training_type_id,
|
||||
training_category=training_category,
|
||||
training_subcategory=training_subcategory,
|
||||
source="csv",
|
||||
)
|
||||
inserted += 1
|
||||
new_entries += 1
|
||||
affected_ids["activity_log"].append(str(eid))
|
||||
aid = eid
|
||||
if registry_updates:
|
||||
update_activity_columns(cur, profile_id, aid, registry_updates)
|
||||
|
||||
run_activity_post_write_hooks_import(
|
||||
cur,
|
||||
profile_id,
|
||||
str(aid),
|
||||
workout_date=iso,
|
||||
training_type_id=training_type_id,
|
||||
duration_min=duration_min,
|
||||
hr_avg=hr_a,
|
||||
hr_max=hr_m,
|
||||
distance_km=dist,
|
||||
kcal_active=kcal_a,
|
||||
kcal_resting=kcal_r,
|
||||
)
|
||||
upsert_session_metrics_from_csv_mapped(
|
||||
cur,
|
||||
profile_id,
|
||||
str(aid),
|
||||
mapped,
|
||||
training_category,
|
||||
training_type_id,
|
||||
)
|
||||
cur.execute("RELEASE SAVEPOINT csv_activity_row")
|
||||
except Exception as e:
|
||||
try:
|
||||
cur.execute("ROLLBACK TO SAVEPOINT csv_activity_row")
|
||||
except Exception:
|
||||
pass
|
||||
err = enrich_row_error(str(e), module="activity")
|
||||
error_details.append({"row": rows_total, **err})
|
||||
|
||||
return {
|
||||
"rows_total": rows_total,
|
||||
"inserted": inserted,
|
||||
"updated": updated,
|
||||
"skipped": 0,
|
||||
"new_entries": new_entries,
|
||||
}
|
||||
@@ -0,0 +1,115 @@
|
||||
"""
|
||||
Kanonische Speichereinheiten pro CSV-Zielfeld (module_registry: field.unit) und
|
||||
abwählbare Quelleinheiten → Faktor für type_conversions.source_unit.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any
|
||||
|
||||
from csv_parser.module_registry import get_module_definition
|
||||
|
||||
# 1 kcal = 4.184 kJ (IEC/ISO 80000)
|
||||
_KJ_TO_KCAL = 1.0 / 4.184
|
||||
|
||||
# — Energie (Ziel kcal) —
|
||||
_ENERGY: list[dict[str, Any]] = [
|
||||
{"id": "kcal", "label": "Kilokalorien (kcal), wie in DB", "factor": 1.0},
|
||||
{"id": "kj", "label": "Kilojoule (kJ) → kcal", "factor": _KJ_TO_KCAL},
|
||||
{"id": "j", "label": "Joule (J) → kcal", "factor": _KJ_TO_KCAL / 1000.0},
|
||||
]
|
||||
|
||||
# — Masse klein (Ziel g): Makronährstoffe —
|
||||
_GRAM: list[dict[str, Any]] = [
|
||||
{"id": "g", "label": "Gramm (g), wie in DB", "factor": 1.0},
|
||||
{"id": "kg", "label": "Kilogramm (kg) → g", "factor": 1000.0},
|
||||
{"id": "mg", "label": "Milligramm (mg) → g", "factor": 0.001},
|
||||
]
|
||||
|
||||
# — Körpergewicht (Ziel kg) —
|
||||
_KG: list[dict[str, Any]] = [
|
||||
{"id": "kg", "label": "Kilogramm (kg), wie in DB", "factor": 1.0},
|
||||
{"id": "g", "label": "Gramm (g) → kg", "factor": 0.001},
|
||||
{"id": "lb", "label": "Pfund / lb → kg", "factor": 0.45359237},
|
||||
{"id": "oz", "label": "Unze / oz → kg", "factor": 0.028349523125},
|
||||
]
|
||||
|
||||
# — Strecke (Ziel km) —
|
||||
_KM: list[dict[str, Any]] = [
|
||||
{"id": "km", "label": "Kilometer (km), wie in DB", "factor": 1.0},
|
||||
{"id": "m", "label": "Meter (m) → km", "factor": 0.001},
|
||||
{"id": "mi", "label": "Meilen (mi) → km", "factor": 1.609344},
|
||||
]
|
||||
|
||||
_UNIT_FAMILY: dict[str, list[dict[str, Any]]] = {
|
||||
"kcal": _ENERGY,
|
||||
"g": _GRAM,
|
||||
"kg": _KG,
|
||||
"km": _KM,
|
||||
}
|
||||
|
||||
|
||||
def get_canonical_unit(module: str, db_field: str) -> str | None:
|
||||
mod = get_module_definition(module)
|
||||
if not mod:
|
||||
return None
|
||||
finfo: dict[str, Any] | None = mod.get("fields", {}).get(db_field)
|
||||
if not finfo:
|
||||
return None
|
||||
u = finfo.get("unit")
|
||||
return str(u) if u else None
|
||||
|
||||
|
||||
def source_unit_choices_for_field(module: str, db_field: str) -> list[dict[str, Any]]:
|
||||
"""Optionen für GUI: id, label, canonical_unit, is_canonical (Umrechnung serverseitig)."""
|
||||
cu = get_canonical_unit(module, db_field)
|
||||
if not cu:
|
||||
return []
|
||||
choices = _UNIT_FAMILY.get(cu)
|
||||
if not choices:
|
||||
return []
|
||||
out: list[dict[str, Any]] = [
|
||||
{
|
||||
"id": c["id"],
|
||||
"label": c["label"],
|
||||
"canonical_unit": cu,
|
||||
"is_canonical": c["id"] == cu,
|
||||
}
|
||||
for c in choices
|
||||
]
|
||||
out.append(
|
||||
{
|
||||
"id": "custom",
|
||||
"label": "Benutzerdefiniert (Konvertierungsfaktor, z. B. ml→g je nach Dichte)",
|
||||
"canonical_unit": cu,
|
||||
"is_canonical": False,
|
||||
}
|
||||
)
|
||||
return out
|
||||
|
||||
|
||||
def factor_source_to_canonical(module: str, db_field: str, source_unit: str | None) -> float:
|
||||
"""
|
||||
Multiplikator: CSV-Zahl * Faktor → Wert in kanonischer DB-Einheit.
|
||||
Unbekannte/None/leer/Passthrough → 1.0
|
||||
|
||||
``source_unit`` ``custom`` / ``none``: kein Registry-Faktor (1.0); freie Skalierung nur über
|
||||
``conversion_factor`` in type_conversions (JSON).
|
||||
"""
|
||||
if source_unit is None:
|
||||
return 1.0
|
||||
su = str(source_unit).strip().lower()
|
||||
if not su:
|
||||
return 1.0
|
||||
if su in ("custom", "none"):
|
||||
return 1.0
|
||||
cu = get_canonical_unit(module, db_field)
|
||||
if not cu:
|
||||
return 1.0
|
||||
choices = _UNIT_FAMILY.get(cu)
|
||||
if not choices:
|
||||
return 1.0
|
||||
for c in choices:
|
||||
if str(c["id"]).lower() == su:
|
||||
return float(c["factor"])
|
||||
return 1.0
|
||||
@@ -0,0 +1,53 @@
|
||||
"""
|
||||
Menschenlesbare Hinweise zu typischen Import-/DB-Fehlern (Universal-CSV).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
|
||||
def enrich_row_error(message: str, module: str | None = None) -> dict[str, str | None]:
|
||||
"""
|
||||
Ergänzt eine Rohexception-Zeichenkette um ``code`` und ``hint`` für die Fehlerliste im Import.
|
||||
"""
|
||||
low = (message or "").lower()
|
||||
out: dict[str, str | None] = {"error": message, "code": None, "hint": None}
|
||||
|
||||
if "numeric field overflow" in low or "numeric value out of range" in low:
|
||||
out["code"] = "db_numeric_overflow"
|
||||
out["hint"] = (
|
||||
"Wert passt nicht in die Datenbank-Spalte (z. B. NUMERIC mit begrenzter Größe). "
|
||||
"Häufig: Kilojoule aus dem Export landen im Kalorien-Feld – in der Vorlage für kcal_active/kcal_resting "
|
||||
'"source_unit": "kj" setzen. Oder eine falsche CSV-Spalte ist einem kleinen Zielfeld zugeordnet '
|
||||
"(z. B. große Zahl in einem HF-Feld)."
|
||||
)
|
||||
return out
|
||||
|
||||
if "violates check constraint" in low and "source" in low:
|
||||
out["code"] = "db_check_constraint_source"
|
||||
out["hint"] = (
|
||||
"Die Tabelle erlaubt den gesetzten «source»-Wert nicht. "
|
||||
"System-Vorlage / Migration zur erlaubten Quelle prüfen (z. B. csv für Universal-Import)."
|
||||
)
|
||||
return out
|
||||
|
||||
if "current transaction is aborted" in low:
|
||||
out["code"] = "transaction_aborted"
|
||||
out["hint"] = (
|
||||
"Eine frühere Zeile hat einen Datenbankfehler ausgelöst. "
|
||||
"Zuerst die niedrigste Zeilennummer in error_details beheben (Vorlage/Daten prüfen)."
|
||||
)
|
||||
return out
|
||||
|
||||
if "invalid input syntax" in low and "time" in low:
|
||||
out["code"] = "db_time_cast"
|
||||
out["hint"] = (
|
||||
"start_time/end_time passen nicht zum erwarteten Zeitformat in der Datenbank. "
|
||||
"Vorlage: Datums- und Zeitanteil konsistent (oft nur Uhrzeit, wenn date separat)."
|
||||
)
|
||||
return out
|
||||
|
||||
if module == "activity" and "foreign key" in low:
|
||||
out["code"] = "db_foreign_key"
|
||||
out["hint"] = "Verknüpfung zur Datenbank verletzt (z. B. training_type). Support kontaktieren."
|
||||
|
||||
return out
|
||||
@@ -0,0 +1,217 @@
|
||||
"""
|
||||
Zeilenaggregation nach CSV-Mapping (group_by + aggregates), vor dem DB-Upsert.
|
||||
|
||||
Spezifikation in der Vorlage (import_row_processing JSONB). Optional: Modul-Default
|
||||
(import_row_processing_default in module_registry) nur als **Legacy-Fallback**, wenn
|
||||
die Vorlage nichts speichert — mittelfristig sollen Vorlagen explizit sein.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import datetime as dt
|
||||
import statistics
|
||||
from typing import Any, Mapping
|
||||
|
||||
from csv_parser.module_registry import get_module_definition
|
||||
|
||||
ALLOWED_AGGREGATES = frozenset({"sum", "mean", "min", "max", "median", "first", "last"})
|
||||
# Mehr als eine CSV-Zeile pro group_by-Schlüssel
|
||||
ALLOWED_MULTI_ROW_POLICIES = frozenset({"aggregate", "reject", "first_row", "last_row"})
|
||||
|
||||
|
||||
def resolve_import_row_processing(module: str, mapping_row: Mapping[str, Any]) -> dict[str, Any] | None:
|
||||
"""Explizite Vorlage hat Vorrang; sonst Modul-Default; leeres Dict zählt wie „nicht gesetzt“."""
|
||||
raw = mapping_row.get("import_row_processing")
|
||||
if isinstance(raw, dict) and raw:
|
||||
return dict(raw)
|
||||
mod = get_module_definition(module)
|
||||
if not mod:
|
||||
return None
|
||||
default = mod.get("import_row_processing_default")
|
||||
if isinstance(default, dict) and default:
|
||||
return dict(default)
|
||||
return None
|
||||
|
||||
|
||||
def validate_import_row_processing(
|
||||
module: str,
|
||||
spec: Mapping[str, Any],
|
||||
field_mappings: Mapping[str, Any],
|
||||
cur=None,
|
||||
) -> None:
|
||||
"""Wirft ValueError bei ungültiger Konfiguration."""
|
||||
mod = get_module_definition(module)
|
||||
if not mod:
|
||||
raise ValueError(f"Unbekanntes Modul: {module}")
|
||||
allowed = set(mod.get("fields") or [])
|
||||
if module == "activity" and cur is not None:
|
||||
cur.execute("SELECT key FROM training_parameters WHERE is_active = true")
|
||||
allowed.update(str(r["key"]) for r in cur.fetchall())
|
||||
fm_targets = {str(v) for v in field_mappings.values() if v and v not in ("-", "_skip")}
|
||||
|
||||
group_by = spec.get("group_by") or []
|
||||
if not isinstance(group_by, list) or not all(isinstance(x, str) for x in group_by):
|
||||
raise ValueError("import_row_processing.group_by muss eine Liste von Feldnamen sein")
|
||||
aggregates = spec.get("aggregates") or {}
|
||||
if not isinstance(aggregates, dict):
|
||||
raise ValueError("import_row_processing.aggregates muss ein Objekt sein")
|
||||
|
||||
for g in group_by:
|
||||
if g not in allowed:
|
||||
raise ValueError(f"group_by: unbekanntes Feld '{g}' für Modul '{module}'")
|
||||
if g not in fm_targets:
|
||||
raise ValueError(
|
||||
f"group_by: Zielfeld '{g}' ist keiner CSV-Spalte zugeordnet — Aggregation nicht möglich."
|
||||
)
|
||||
|
||||
for field, op in aggregates.items():
|
||||
if field not in allowed:
|
||||
raise ValueError(f"aggregates: unbekanntes Feld '{field}' für Modul '{module}'")
|
||||
if str(op) not in ALLOWED_AGGREGATES:
|
||||
raise ValueError(
|
||||
f"aggregates['{field}']: ungültige Operation '{op}'. "
|
||||
f"Erlaubt: {', '.join(sorted(ALLOWED_AGGREGATES))}"
|
||||
)
|
||||
|
||||
mrp = spec.get("multi_row_policy")
|
||||
if mrp is not None and str(mrp) not in ALLOWED_MULTI_ROW_POLICIES:
|
||||
raise ValueError(
|
||||
f"multi_row_policy: ungültiger Wert '{mrp}'. "
|
||||
f"Erlaubt: {', '.join(sorted(ALLOWED_MULTI_ROW_POLICIES))}"
|
||||
)
|
||||
|
||||
dedupe = spec.get("dedupe_identical_rows")
|
||||
if dedupe is not None and not isinstance(dedupe, bool):
|
||||
raise ValueError("dedupe_identical_rows muss ein Boolean sein")
|
||||
|
||||
|
||||
def _sort_key_for_group(v: Any) -> Any:
|
||||
if isinstance(v, dt.datetime):
|
||||
return v.isoformat()
|
||||
if isinstance(v, dt.date):
|
||||
return v.isoformat()
|
||||
if isinstance(v, dt.time):
|
||||
return v.isoformat()
|
||||
return v
|
||||
|
||||
|
||||
def _apply_aggregate(op: str, values: list[Any]) -> Any:
|
||||
nums: list[float] = []
|
||||
for x in values:
|
||||
if x is None or x == "":
|
||||
continue
|
||||
try:
|
||||
nums.append(float(x))
|
||||
except (TypeError, ValueError):
|
||||
continue
|
||||
|
||||
if op == "sum":
|
||||
return sum(nums) if nums else None
|
||||
if op == "mean":
|
||||
return statistics.mean(nums) if nums else None
|
||||
if op == "median":
|
||||
return float(statistics.median(nums)) if nums else None
|
||||
if op == "min":
|
||||
return min(nums) if nums else None
|
||||
if op == "max":
|
||||
return max(nums) if nums else None
|
||||
if op == "first":
|
||||
for x in values:
|
||||
if x is not None and x != "":
|
||||
return x
|
||||
return None
|
||||
if op == "last":
|
||||
for x in reversed(values):
|
||||
if x is not None and x != "":
|
||||
return x
|
||||
return None
|
||||
raise ValueError(f"Unbekannte Aggregations-Operation: {op}")
|
||||
|
||||
|
||||
def _row_identity_signature(r: dict[str, Any]) -> tuple[Any, ...]:
|
||||
return tuple(sorted((k, _sort_key_for_group(r.get(k))) for k in sorted(r.keys())))
|
||||
|
||||
|
||||
def _dedupe_identical_mapped_rows(rows: list[dict[str, Any]]) -> list[dict[str, Any]]:
|
||||
"""Exakt gleiche gemappte Zeilen (alle Keys/Werte) — erste behalten."""
|
||||
seen: set[tuple[Any, ...]] = set()
|
||||
out: list[dict[str, Any]] = []
|
||||
for r in rows:
|
||||
sig = _row_identity_signature(r)
|
||||
if sig in seen:
|
||||
continue
|
||||
seen.add(sig)
|
||||
out.append(r)
|
||||
return out
|
||||
|
||||
|
||||
def aggregate_mapped_rows(
|
||||
rows: list[dict[str, Any]],
|
||||
spec: Mapping[str, Any],
|
||||
) -> tuple[list[dict[str, Any]], list[dict[str, Any]]]:
|
||||
"""
|
||||
Gruppiert gemappte Zeilen-Dicts nach group_by und wendet aggregates an.
|
||||
Felder, die weder in group_by noch in aggregates vorkommen: Wert aus der ersten Zeile der Gruppe.
|
||||
|
||||
Rückgabe: (merged_rows, strukturelle Fehler / Hinweise, z. B. abgelehnte Schlüsselgruppen).
|
||||
"""
|
||||
errors: list[dict[str, Any]] = []
|
||||
rows = list(rows)
|
||||
if spec.get("dedupe_identical_rows"):
|
||||
rows = _dedupe_identical_mapped_rows(rows)
|
||||
|
||||
group_by = spec.get("group_by") or []
|
||||
aggregates = spec.get("aggregates") or {}
|
||||
policy = str(spec.get("multi_row_policy") or "aggregate")
|
||||
if policy not in ALLOWED_MULTI_ROW_POLICIES:
|
||||
policy = "aggregate"
|
||||
|
||||
if not group_by:
|
||||
return rows, errors
|
||||
|
||||
buckets: dict[tuple[Any, ...], list[dict[str, Any]]] = {}
|
||||
order: list[tuple[Any, ...]] = []
|
||||
for r in rows:
|
||||
key = tuple(_sort_key_for_group(r.get(g)) for g in group_by)
|
||||
if key not in buckets:
|
||||
buckets[key] = []
|
||||
order.append(key)
|
||||
buckets[key].append(r)
|
||||
|
||||
gb_label = ", ".join(group_by)
|
||||
out: list[dict[str, Any]] = []
|
||||
for key in order:
|
||||
group_rows = buckets[key]
|
||||
if len(group_rows) > 1:
|
||||
if policy == "reject":
|
||||
errors.append(
|
||||
{
|
||||
"error": "mehrere_zeilen_pro_schluessel",
|
||||
"message": (
|
||||
f"{len(group_rows)} CSV-Zeilen mit gleichem Schlüssel ({gb_label}); "
|
||||
"laut Vorlage abgelehnt (multi_row_policy=reject)."
|
||||
),
|
||||
"rows_in_group": len(group_rows),
|
||||
}
|
||||
)
|
||||
continue
|
||||
if policy == "first_row":
|
||||
group_rows = [group_rows[0]]
|
||||
elif policy == "last_row":
|
||||
group_rows = [group_rows[-1]]
|
||||
|
||||
first = group_rows[0]
|
||||
merged: dict[str, Any] = {}
|
||||
for g in group_by:
|
||||
merged[g] = first.get(g)
|
||||
for field, op in aggregates.items():
|
||||
merged[field] = _apply_aggregate(str(op), [row.get(field) for row in group_rows])
|
||||
for row in group_rows:
|
||||
for k, v in row.items():
|
||||
if k in merged:
|
||||
continue
|
||||
if k in group_by or k in aggregates:
|
||||
continue
|
||||
merged[k] = v
|
||||
out.append(merged)
|
||||
return out, errors
|
||||
@@ -0,0 +1,268 @@
|
||||
"""
|
||||
Heuristische Vorschläge für CSV field_mappings / type_conversions (Admin-Editor, Issue #21).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from copy import deepcopy
|
||||
from typing import Any, Mapping
|
||||
|
||||
from csv_parser.core import normalize_header_for_signature
|
||||
from csv_parser.module_registry import get_module_definition
|
||||
|
||||
# Normalisierte Header-Fragmente → DB-Feld (Substring- oder exakter Norm-Vergleich)
|
||||
_MODULE_HEADER_ALIASES: dict[str, dict[str, frozenset[str]]] = {
|
||||
"nutrition": {
|
||||
"date": frozenset(
|
||||
{"datum", "date", "tag", "day", "zeit", "timestamp", "uhrzeit", "monat", "jahr"}
|
||||
),
|
||||
"kcal": frozenset({"kcal", "kalorie", "calorie", "energie", "energy", "kj", "joule"}),
|
||||
"protein_g": frozenset({"protein", "eiwei", "eiweiss"}),
|
||||
"fat_g": frozenset({"fett", "fat", "lipid"}),
|
||||
"carbs_g": frozenset({"kh", "carb", "kohlenhydr", "carbs", "sugar", "zucker"}),
|
||||
},
|
||||
"weight": {
|
||||
"date": frozenset({"datum", "date", "tag", "day", "zeit"}),
|
||||
"weight": frozenset({"gewicht", "weight", "masse", "kg", "kilo"}),
|
||||
"note": frozenset({"notiz", "note", "comment", "kommentar"}),
|
||||
},
|
||||
"blood_pressure": {
|
||||
"measured_date": frozenset({"datum", "date", "tag", "day", "messdatum"}),
|
||||
"measured_time": frozenset({"zeit", "time", "uhr", "uhrzeit"}),
|
||||
"systolic": frozenset({"systol", "sys", "sbp", "oberdruck"}),
|
||||
"diastolic": frozenset({"diastol", "dia", "dbp", "unterdruck"}),
|
||||
"pulse": frozenset({"puls", "pulse", "hr", "herz", "bpm"}),
|
||||
},
|
||||
"activity": {
|
||||
"date": frozenset({"datum", "date", "tag", "day"}),
|
||||
"start_time": frozenset({"start", "beginn", "von"}),
|
||||
"end_time": frozenset({"end", "ende", "bis", "stop"}),
|
||||
"activity_type": frozenset({"workout", "training", "typ", "type", "art", "aktiv"}),
|
||||
"duration_min": frozenset({"dauer", "duration", "min"}),
|
||||
"distance_km": frozenset({"strecke", "distance", "km", "distanz"}),
|
||||
"kcal_active": frozenset({"kcal", "kalorie", "energie", "active"}),
|
||||
"kcal_resting": frozenset({"ruhe", "resting"}),
|
||||
"hr_avg": frozenset({"puls", "heart", "hr", "bpm", "herzfrequenz", "durchschn"}),
|
||||
"hr_max": frozenset({"max", "peak"}),
|
||||
},
|
||||
"vitals_baseline": {
|
||||
"date": frozenset({"datum", "date", "tag", "start", "zeit"}),
|
||||
"resting_hr": frozenset({"ruhepuls", "resting", "rhr"}),
|
||||
"hrv": frozenset({"hrv", "variabilit", "vfc"}),
|
||||
"vo2_max": frozenset({"vo2"}),
|
||||
"spo2": frozenset({"sauerstoff", "spo2", "oxygen"}),
|
||||
"respiratory_rate": frozenset({"atem", "respiratory"}),
|
||||
},
|
||||
}
|
||||
|
||||
_DEFAULT_TYPE_CONVERSIONS: dict[str, dict[str, dict[str, Any]]] = {
|
||||
"nutrition": {
|
||||
"date": {"type": "date", "format": "dd.mm.yyyy HH:MM", "extract": "date_only", "flexible": True},
|
||||
"kcal": {"type": "float", "decimal_separator": "auto", "flexible": True},
|
||||
"protein_g": {"type": "float", "decimal_separator": "auto", "flexible": True},
|
||||
"fat_g": {"type": "float", "decimal_separator": "auto", "flexible": True},
|
||||
"carbs_g": {"type": "float", "decimal_separator": "auto", "flexible": True},
|
||||
},
|
||||
"weight": {
|
||||
"date": {"type": "date", "format": "dd.mm.yyyy", "flexible": True},
|
||||
"weight": {"type": "float", "decimal_separator": "auto", "flexible": True},
|
||||
"note": {"type": "string"},
|
||||
},
|
||||
"blood_pressure": {
|
||||
"measured_date": {"type": "date", "format": "dd.mm.yyyy", "flexible": True},
|
||||
"measured_time": {"type": "time", "format": "HH:MM", "flexible": True},
|
||||
"start_time": {"type": "datetime", "format": "yyyy-mm-dd HH:MM:SS", "flexible": True},
|
||||
"systolic": {"type": "int", "flexible": True},
|
||||
"diastolic": {"type": "int", "flexible": True},
|
||||
"pulse": {"type": "int", "flexible": True},
|
||||
},
|
||||
"activity": {
|
||||
"date": {"type": "date", "format": "yyyy-mm-dd", "flexible": True},
|
||||
"start_time": {"type": "datetime", "format": "yyyy-mm-dd HH:MM:SS", "flexible": True},
|
||||
"end_time": {"type": "datetime", "format": "yyyy-mm-dd HH:MM:SS", "flexible": True},
|
||||
"activity_type": {"type": "string"},
|
||||
"duration_min": {"type": "duration", "format": "HH:MM:SS", "target_unit": "minutes", "flexible": True},
|
||||
"distance_km": {"type": "float", "decimal_separator": "auto", "flexible": True},
|
||||
"kcal_active": {"type": "float", "decimal_separator": "auto", "flexible": True},
|
||||
"kcal_resting": {"type": "float", "decimal_separator": "auto", "flexible": True},
|
||||
"hr_avg": {"type": "int", "flexible": True},
|
||||
"hr_max": {"type": "int", "flexible": True},
|
||||
},
|
||||
"vitals_baseline": {
|
||||
"date": {
|
||||
"type": "datetime",
|
||||
"format": "yyyy-mm-dd HH:MM:SS",
|
||||
"extract": "date_only",
|
||||
"flexible": True,
|
||||
},
|
||||
"resting_hr": {"type": "int", "flexible": True},
|
||||
"hrv": {"type": "int", "flexible": True},
|
||||
"vo2_max": {"type": "float", "decimal_separator": "auto", "flexible": True},
|
||||
"spo2": {"type": "int", "flexible": True},
|
||||
"respiratory_rate": {"type": "float", "decimal_separator": "auto", "flexible": True},
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
def _norm_key(header: str) -> str:
|
||||
return normalize_header_for_signature(header)
|
||||
|
||||
|
||||
def _match_seed_to_db_field(header: str, seed_fm: Mapping[str, str]) -> str | None:
|
||||
"""Findet Ziel-Feld, wenn Seed-Key zu diesem Header passt (exakt oder normalisiert)."""
|
||||
if header in seed_fm:
|
||||
v = seed_fm[header]
|
||||
if v and v not in ("-", "_skip"):
|
||||
return v
|
||||
nh = _norm_key(header)
|
||||
if nh in seed_fm:
|
||||
v = seed_fm[nh]
|
||||
if v and v not in ("-", "_skip"):
|
||||
return v
|
||||
for sk, sv in seed_fm.items():
|
||||
if not sv or sv in ("-", "_skip"):
|
||||
continue
|
||||
if _norm_key(str(sk)) == nh:
|
||||
return sv
|
||||
return None
|
||||
|
||||
|
||||
def _alias_suggest(
|
||||
norm: str,
|
||||
module: str,
|
||||
used: set[str],
|
||||
*,
|
||||
field_order: list[str] | None = None,
|
||||
) -> str | None:
|
||||
aliases = _MODULE_HEADER_ALIASES.get(module, {})
|
||||
mod = get_module_definition(module)
|
||||
if not mod:
|
||||
return None
|
||||
order = field_order if field_order is not None else list(mod["fields"].keys())
|
||||
for db_field in order:
|
||||
if db_field in used:
|
||||
continue
|
||||
tokens = aliases.get(db_field, frozenset())
|
||||
nlow = norm.lower()
|
||||
if nlow == db_field or nlow.replace("_", "") == db_field.replace("_", ""):
|
||||
return db_field
|
||||
for tok in tokens:
|
||||
if len(tok) >= 2 and tok in nlow:
|
||||
return db_field
|
||||
if len(tok) >= 4 and tok in norm:
|
||||
return db_field
|
||||
return None
|
||||
|
||||
|
||||
def suggest_field_mappings(
|
||||
headers: list[str],
|
||||
module: str,
|
||||
seed_fm: Mapping[str, str] | None = None,
|
||||
*,
|
||||
effective_fields: Mapping[str, Any] | None = None,
|
||||
) -> dict[str, str]:
|
||||
"""
|
||||
Mappt jede CSV-Spalte (Roh-Header als Key) auf DB-Feld oder '-'.
|
||||
Nutzt zuerst eine passende Seed-Vorlage, dann Alias-Heuristik.
|
||||
"""
|
||||
if module == "sleep":
|
||||
return {h: "-" for h in headers}
|
||||
|
||||
mod = get_module_definition(module)
|
||||
if not mod:
|
||||
return {h: "-" for h in headers}
|
||||
|
||||
fields_map = dict(effective_fields) if effective_fields is not None else dict(mod["fields"])
|
||||
field_order = list(fields_map.keys())
|
||||
|
||||
fm: dict[str, str] = {h: "-" for h in headers}
|
||||
used: set[str] = set()
|
||||
|
||||
if seed_fm:
|
||||
for h in headers:
|
||||
db = _match_seed_to_db_field(h, seed_fm)
|
||||
if db and db not in used and db in fields_map:
|
||||
fm[h] = db
|
||||
used.add(db)
|
||||
|
||||
for h in headers:
|
||||
if fm[h] != "-":
|
||||
continue
|
||||
norm = _norm_key(h)
|
||||
db = _alias_suggest(norm, module, used, field_order=field_order)
|
||||
if db:
|
||||
fm[h] = db
|
||||
used.add(db)
|
||||
|
||||
return fm
|
||||
|
||||
|
||||
def build_type_conversions_for_mapping(
|
||||
module: str,
|
||||
field_mappings: Mapping[str, str],
|
||||
seed_tc: Mapping[str, Any] | None = None,
|
||||
*,
|
||||
effective_fields: Mapping[str, Any] | None = None,
|
||||
) -> dict[str, Any]:
|
||||
"""type_conversions nur für zugewiesene Zielfelder; Seed überschreibt Defaults."""
|
||||
if module == "sleep":
|
||||
return {}
|
||||
|
||||
defaults = _DEFAULT_TYPE_CONVERSIONS.get(module, {})
|
||||
out: dict[str, Any] = {}
|
||||
targets = {v for v in field_mappings.values() if v and v not in ("-", "_skip")}
|
||||
field_meta = dict(effective_fields) if effective_fields is not None else None
|
||||
|
||||
if seed_tc:
|
||||
for k, v in seed_tc.items():
|
||||
if k in targets and isinstance(v, dict):
|
||||
out[k] = deepcopy(v)
|
||||
|
||||
for t in targets:
|
||||
if t not in out and t in defaults:
|
||||
out[t] = deepcopy(defaults[t])
|
||||
|
||||
for t in sorted(targets):
|
||||
if t in out:
|
||||
continue
|
||||
finfo = (field_meta or {}).get(t) if field_meta else None
|
||||
if not finfo:
|
||||
continue
|
||||
typ = finfo.get("type")
|
||||
if typ == "int":
|
||||
out[t] = {"type": "int", "flexible": True}
|
||||
elif typ == "float":
|
||||
out[t] = {"type": "float", "decimal_separator": "auto", "flexible": True}
|
||||
else:
|
||||
out[t] = {"type": "string"}
|
||||
|
||||
_apply_energy_kj_hint_from_headers(module, field_mappings, out)
|
||||
return out
|
||||
|
||||
|
||||
_ENERGY_FIELDS = frozenset({"kcal", "kcal_active", "kcal_resting"})
|
||||
|
||||
|
||||
def _apply_energy_kj_hint_from_headers(
|
||||
module: str,
|
||||
field_mappings: Mapping[str, str],
|
||||
out: dict[str, Any],
|
||||
) -> None:
|
||||
"""Wenn Überschrift kJ/Kilojoule nahelegt (nicht kcal), source_unit kj setzen (FDDB & Co.)."""
|
||||
if module not in ("nutrition", "activity"):
|
||||
return
|
||||
for csv_col, db_field in field_mappings.items():
|
||||
if db_field not in _ENERGY_FIELDS:
|
||||
continue
|
||||
spec = out.get(db_field)
|
||||
if not isinstance(spec, dict):
|
||||
continue
|
||||
if spec.get("source_unit"):
|
||||
continue
|
||||
norm = normalize_header_for_signature(str(csv_col)).lower()
|
||||
if "kcal" in norm:
|
||||
continue
|
||||
if "kj" in norm or "kilojoule" in norm:
|
||||
spec2 = deepcopy(spec)
|
||||
spec2["source_unit"] = "kj"
|
||||
out[db_field] = spec2
|
||||
@@ -0,0 +1,184 @@
|
||||
"""
|
||||
Ziel-Module für CSV-Import: Tabellen-Felder, Pflichtfelder, Duplikat-Strategie (Issue #21).
|
||||
|
||||
Hinweis: blood_pressure nutzt in der DB measured_at; Logik-Felder measured_date + measured_time
|
||||
werden im Executor zu measured_at zusammengefügt (Phase Import-Executor).
|
||||
|
||||
Activity: date kann aus start_time (ISO-Datetime) abgeleitet werden, wenn nur start_time gesetzt ist.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any, Dict, cast
|
||||
|
||||
MODULE_DEFINITIONS: Dict[str, Dict[str, Any]] = {
|
||||
"nutrition": {
|
||||
"table": "nutrition_log",
|
||||
"fields": {
|
||||
"date": {"type": "date", "required": True},
|
||||
"kcal": {"type": "float", "required": False, "unit": "kcal"},
|
||||
"protein_g": {"type": "float", "required": False, "min": 0, "unit": "g"},
|
||||
"fat_g": {"type": "float", "required": False, "min": 0, "unit": "g"},
|
||||
"carbs_g": {"type": "float", "required": False, "min": 0, "unit": "g"},
|
||||
},
|
||||
"duplicate_key": ["profile_id", "date"],
|
||||
"duplicate_strategy": "update",
|
||||
# Legacy-Fallback wenn die Vorlage kein import_row_processing speichert — Vorlagen mittelfristig explizit.
|
||||
"import_row_processing_default": {
|
||||
"group_by": ["date"],
|
||||
"aggregates": {
|
||||
"kcal": "sum",
|
||||
"protein_g": "sum",
|
||||
"fat_g": "sum",
|
||||
"carbs_g": "sum",
|
||||
},
|
||||
},
|
||||
},
|
||||
# Kanon: nur Kern/spine + „heiße“ Metriken → activity_log. Erweiterte Parameter → training_parameters / EAV
|
||||
# (siehe backend/data_layer/activity_data_canon.py).
|
||||
"activity": {
|
||||
"table": "activity_log",
|
||||
"fields": {
|
||||
"date": {"type": "date", "required": False, "label_de": "Datum"},
|
||||
"start_time": {
|
||||
"type": "datetime",
|
||||
"required": False,
|
||||
"label_de": "Start (Datum/Uhrzeit)",
|
||||
},
|
||||
"end_time": {"type": "datetime", "required": False, "label_de": "Ende (Datum/Uhrzeit)"},
|
||||
"activity_type": {"type": "string", "required": True, "label_de": "Trainingsart / Workout-Typ"},
|
||||
"duration_min": {"type": "float", "required": False, "min": 0, "label_de": "Dauer (Minuten)"},
|
||||
"kcal_active": {"type": "float", "required": False, "unit": "kcal", "label_de": "Kalorien aktiv"},
|
||||
"kcal_resting": {"type": "float", "required": False, "unit": "kcal", "label_de": "Kalorien Ruhe"},
|
||||
"distance_km": {"type": "float", "required": False, "unit": "km", "label_de": "Distanz (km)"},
|
||||
"hr_avg": {
|
||||
"type": "float",
|
||||
"required": False,
|
||||
"min": 30,
|
||||
"max": 220,
|
||||
"label_de": "Herzfrequenz Ø (bpm)",
|
||||
},
|
||||
"hr_max": {
|
||||
"type": "float",
|
||||
"required": False,
|
||||
"min": 30,
|
||||
"max": 220,
|
||||
"label_de": "Herzfrequenz max (bpm)",
|
||||
},
|
||||
"rpe": {"type": "int", "required": False, "label_de": "RPE (1–10)"},
|
||||
"notes": {"type": "string", "required": False, "label_de": "Notiz"},
|
||||
},
|
||||
"derive_date_from_datetime_field": "start_time",
|
||||
"duplicate_key": ["profile_id", "date", "start_time"],
|
||||
"duplicate_strategy": "update",
|
||||
},
|
||||
"sleep": {
|
||||
"table": "sleep_log",
|
||||
"fields": {},
|
||||
"import_mode": "apple_sleep_aggregate",
|
||||
},
|
||||
"vitals_baseline": {
|
||||
"table": "vitals_baseline",
|
||||
"fields": {
|
||||
"date": {"type": "date", "required": True},
|
||||
"resting_hr": {"type": "int", "required": False},
|
||||
"hrv": {"type": "int", "required": False},
|
||||
"vo2_max": {"type": "float", "required": False},
|
||||
"spo2": {"type": "int", "required": False},
|
||||
"respiratory_rate": {"type": "float", "required": False},
|
||||
},
|
||||
"duplicate_key": ["profile_id", "date"],
|
||||
"duplicate_strategy": "update",
|
||||
# Legacy-Fallback — Vorlagen mittelfristig explizit setzen.
|
||||
"import_row_processing_default": {
|
||||
"group_by": ["date"],
|
||||
"aggregates": {
|
||||
"resting_hr": "mean",
|
||||
"hrv": "mean",
|
||||
"vo2_max": "mean",
|
||||
"spo2": "mean",
|
||||
"respiratory_rate": "mean",
|
||||
},
|
||||
},
|
||||
},
|
||||
"blood_pressure": {
|
||||
"table": "blood_pressure_log",
|
||||
"fields": {
|
||||
"measured_date": {"type": "date", "required": True},
|
||||
"measured_time": {"type": "time", "required": True},
|
||||
# Apple Health: eine Spalte „Start“ / „Datum/Uhrzeit“ (Datetime); Executor splittet.
|
||||
"start_time": {"type": "datetime", "required": False},
|
||||
"systolic": {"type": "int", "required": True},
|
||||
"diastolic": {"type": "int", "required": True},
|
||||
"pulse": {"type": "int", "required": False},
|
||||
},
|
||||
"logical_to_db": "blood_pressure_composite_measured_at",
|
||||
"duplicate_key": ["profile_id", "measured_at"],
|
||||
"duplicate_strategy": "update",
|
||||
},
|
||||
"weight": {
|
||||
"table": "weight_log",
|
||||
"fields": {
|
||||
"date": {"type": "date", "required": True},
|
||||
"weight": {"type": "float", "required": True, "min": 20, "max": 400, "unit": "kg"},
|
||||
"note": {"type": "string", "required": False, "max_length": 2000},
|
||||
},
|
||||
"duplicate_key": ["profile_id", "date"],
|
||||
"duplicate_strategy": "update",
|
||||
# Legacy-Fallback — Vorlagen mittelfristig explizit setzen.
|
||||
"import_row_processing_default": {
|
||||
"group_by": ["date"],
|
||||
"aggregates": {
|
||||
"weight": "last",
|
||||
"note": "last",
|
||||
},
|
||||
},
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
def get_module_definition(module: str) -> Dict[str, Any] | None:
|
||||
return MODULE_DEFINITIONS.get(module)
|
||||
|
||||
|
||||
def list_modules() -> list[str]:
|
||||
return sorted(MODULE_DEFINITIONS.keys())
|
||||
|
||||
|
||||
def validate_field_mappings(module: str, field_mappings: dict, cur=None) -> None:
|
||||
"""Wirft ValueError bei unbekanntem Modul oder unbekanntem DB-Feld."""
|
||||
mod = get_module_definition(module)
|
||||
if not mod:
|
||||
raise ValueError(f"Unbekanntes Modul: {module}")
|
||||
fields = cast(dict, mod["fields"])
|
||||
allowed = set(fields.keys())
|
||||
if module == "activity" and cur is not None:
|
||||
cur.execute("SELECT key FROM training_parameters WHERE is_active = true")
|
||||
allowed.update(str(r["key"]) for r in cur.fetchall())
|
||||
if not allowed:
|
||||
for _csv_col, db_field in field_mappings.items():
|
||||
if db_field not in ("", None, "-", "_skip"):
|
||||
raise ValueError(
|
||||
f"Modul '{module}' nutzt einen Aggregat-Import ohne Spalten-Mapping; "
|
||||
f"alle Spalten müssen „ignorieren“ sein."
|
||||
)
|
||||
return
|
||||
for _csv_col, db_field in field_mappings.items():
|
||||
if db_field in ("", None, "-", "_skip"):
|
||||
continue
|
||||
if db_field not in allowed:
|
||||
raise ValueError(f"Ungültiges Zielfeld '{db_field}' für Modul '{module}'")
|
||||
|
||||
|
||||
def validate_required_field_targets(module: str, field_mappings: dict) -> None:
|
||||
"""Stellt sicher, dass jedes als required markierte Zielfeld mindestens einer Spalte zugeordnet ist."""
|
||||
mod = get_module_definition(module)
|
||||
if not mod:
|
||||
raise ValueError(f"Unbekanntes Modul: {module}")
|
||||
field_defs = cast(dict, mod["fields"])
|
||||
targets = {v for v in field_mappings.values() if v and v not in ("-", "_skip")}
|
||||
if module == "blood_pressure" and "start_time" in targets:
|
||||
targets = set(targets) | {"measured_date", "measured_time"}
|
||||
for fname, finfo in field_defs.items():
|
||||
if finfo.get("required") and fname not in targets:
|
||||
raise ValueError(f"Pflicht-Zielfeld nicht zugeordnet: {fname}")
|
||||
@@ -0,0 +1,19 @@
|
||||
"""Zugriffsregeln für csv_field_mappings (Issue #21)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any, Mapping
|
||||
|
||||
|
||||
def user_may_edit_mapping_row(row: Mapping[str, Any], session: Mapping[str, Any]) -> bool:
|
||||
if session.get("role") == "admin":
|
||||
return True
|
||||
if row.get("is_system"):
|
||||
return False
|
||||
return str(row.get("profile_id")) == str(session.get("profile_id"))
|
||||
|
||||
|
||||
def user_may_delete_mapping(row: Mapping[str, Any], session: Mapping[str, Any]) -> bool:
|
||||
if row.get("is_system"):
|
||||
return False
|
||||
return str(row.get("profile_id")) == str(session.get("profile_id"))
|
||||
@@ -0,0 +1,350 @@
|
||||
"""
|
||||
Apple-Health-Schlaf-CSV → sleep_log (für Universal-Import und /api/sleep/import).
|
||||
Nutzt dieselbe Logik wie der Sleep-Router, ohne HTTPException — arbeitet auf einem übergebenen Cursor.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import csv
|
||||
import io
|
||||
import json
|
||||
import logging
|
||||
from datetime import date, datetime
|
||||
from decimal import Decimal, InvalidOperation
|
||||
from typing import Any, Literal
|
||||
|
||||
from dateutil import parser as dateutil_parser
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def _strip_row_keys(row: dict) -> dict:
|
||||
return {(k or "").strip(): (v.strip() if isinstance(v, str) else v) for k, v in row.items()}
|
||||
|
||||
|
||||
def _safe_float(value: Any) -> float | None:
|
||||
if value is None or value == "":
|
||||
return None
|
||||
if isinstance(value, (int, float)):
|
||||
return float(value)
|
||||
if isinstance(value, Decimal):
|
||||
return float(value)
|
||||
try:
|
||||
s = str(value).strip().replace(",", ".")
|
||||
return float(s)
|
||||
except (ValueError, InvalidOperation):
|
||||
return None
|
||||
|
||||
|
||||
def _parse_apple_sleep_datetime(value: str) -> datetime:
|
||||
raw = (value or "").strip()
|
||||
if not raw:
|
||||
raise ValueError("empty datetime")
|
||||
fmts = (
|
||||
"%Y-%m-%d %H:%M:%S %z",
|
||||
"%d.%m.%y %H:%M:%S",
|
||||
"%d.%m.%Y %H:%M:%S",
|
||||
"%Y-%m-%d %H:%M:%S",
|
||||
)
|
||||
for fmt in fmts:
|
||||
try:
|
||||
return datetime.strptime(raw, fmt)
|
||||
except ValueError:
|
||||
continue
|
||||
try:
|
||||
return dateutil_parser.parse(raw, dayfirst=False)
|
||||
except (ValueError, TypeError, OverflowError) as e:
|
||||
raise ValueError(f"Unbekanntes Datumsformat: {raw!r}") from e
|
||||
|
||||
|
||||
def _hr_to_minutes(hours: float | None) -> int:
|
||||
if hours is None:
|
||||
return 0
|
||||
return int(round(float(hours) * 60))
|
||||
|
||||
|
||||
def detect_apple_sleep_csv_format(fieldnames: list[str] | None) -> Literal["segments", "summary"]:
|
||||
if not fieldnames:
|
||||
raise ValueError("CSV enthält keine Spaltenüberschriften.")
|
||||
fn = {(f or "").strip() for f in fieldnames}
|
||||
if {"Start", "End", "Duration (hr)", "Value"}.issubset(fn):
|
||||
return "segments"
|
||||
if "Start" in fn and "End" in fn and "Total Sleep (hr)" in fn:
|
||||
return "summary"
|
||||
raise ValueError(
|
||||
"Unbekanntes Apple-Health-Schlaf-CSV. Erwartet: Segment-Export oder Schlafanalyse-Zusammenfassung."
|
||||
)
|
||||
|
||||
|
||||
def _build_nights_from_apple_summary(reader: csv.DictReader) -> dict[date, dict]:
|
||||
nights_dict: dict[date, dict] = {}
|
||||
for raw in reader:
|
||||
row = _strip_row_keys(raw)
|
||||
start_s = row.get("Start") or ""
|
||||
end_s = row.get("End") or ""
|
||||
if not start_s or not end_s:
|
||||
continue
|
||||
try:
|
||||
start_dt = _parse_apple_sleep_datetime(start_s)
|
||||
end_dt = _parse_apple_sleep_datetime(end_s)
|
||||
except ValueError:
|
||||
continue
|
||||
|
||||
dt_key = (row.get("Date/Time") or row.get("Datum/Uhrzeit") or "").strip()
|
||||
if dt_key:
|
||||
try:
|
||||
wake_d = datetime.strptime(dt_key[:10], "%Y-%m-%d").date()
|
||||
except ValueError:
|
||||
wake_d = end_dt.date()
|
||||
else:
|
||||
wake_d = end_dt.date()
|
||||
|
||||
core_hr = _safe_float(row.get("Core (hr)"))
|
||||
if core_hr is None:
|
||||
core_hr = _safe_float(row.get("Light (hr)")) or 0.0
|
||||
deep_min = _hr_to_minutes(_safe_float(row.get("Deep (hr)")))
|
||||
rem_min = _hr_to_minutes(_safe_float(row.get("REM (hr)")))
|
||||
light_min = _hr_to_minutes(core_hr)
|
||||
awake_min = _hr_to_minutes(_safe_float(row.get("Awake (hr)")))
|
||||
total_sleep_hr = _safe_float(row.get("Total Sleep (hr)"))
|
||||
nights_dict[wake_d] = {
|
||||
"bedtime": start_dt,
|
||||
"wake_time": end_dt,
|
||||
"segments": [],
|
||||
"deep_minutes": deep_min,
|
||||
"rem_minutes": rem_min,
|
||||
"light_minutes": light_min,
|
||||
"awake_minutes": awake_min,
|
||||
"total_sleep_hr": total_sleep_hr,
|
||||
}
|
||||
return nights_dict
|
||||
|
||||
|
||||
def _build_nights_from_apple_segments(reader: csv.DictReader, phase_map: dict) -> dict[date, dict]:
|
||||
segments = []
|
||||
for raw in reader:
|
||||
row = _strip_row_keys(raw)
|
||||
phase_key = (row.get("Value") or "").strip()
|
||||
phase_en = phase_map.get(phase_key)
|
||||
if phase_en is None:
|
||||
continue
|
||||
try:
|
||||
start_dt = _parse_apple_sleep_datetime(row.get("Start") or "")
|
||||
end_dt = _parse_apple_sleep_datetime(row.get("End") or "")
|
||||
duration_hr = _safe_float(row.get("Duration (hr)"))
|
||||
if duration_hr is None:
|
||||
continue
|
||||
except (ValueError, TypeError):
|
||||
continue
|
||||
duration_min = int(duration_hr * 60)
|
||||
segments.append({
|
||||
"start": start_dt,
|
||||
"end": end_dt,
|
||||
"duration_min": duration_min,
|
||||
"phase": phase_en,
|
||||
})
|
||||
|
||||
segments.sort(key=lambda s: s["start"])
|
||||
nights = []
|
||||
current_night = None
|
||||
|
||||
for seg in segments:
|
||||
if current_night is None or (seg["start"] - current_night["wake_time"]).total_seconds() > 7200:
|
||||
current_night = {
|
||||
"bedtime": seg["start"],
|
||||
"wake_time": seg["end"],
|
||||
"segments": [],
|
||||
"deep_minutes": 0,
|
||||
"rem_minutes": 0,
|
||||
"light_minutes": 0,
|
||||
"awake_minutes": 0,
|
||||
}
|
||||
nights.append(current_night)
|
||||
|
||||
current_night["segments"].append(seg)
|
||||
current_night["wake_time"] = max(current_night["wake_time"], seg["end"])
|
||||
current_night["bedtime"] = min(current_night["bedtime"], seg["start"])
|
||||
|
||||
if seg["phase"] == "deep":
|
||||
current_night["deep_minutes"] += seg["duration_min"]
|
||||
elif seg["phase"] == "rem":
|
||||
current_night["rem_minutes"] += seg["duration_min"]
|
||||
elif seg["phase"] == "light":
|
||||
current_night["light_minutes"] += seg["duration_min"]
|
||||
elif seg["phase"] == "awake":
|
||||
current_night["awake_minutes"] += seg["duration_min"]
|
||||
|
||||
nights_dict: dict[date, dict] = {}
|
||||
for night in nights:
|
||||
wake_date = night["wake_time"].date()
|
||||
nights_dict[wake_date] = night
|
||||
return nights_dict
|
||||
|
||||
|
||||
def import_apple_sleep_nights(cur, profile_id: str, text: str) -> dict[str, Any]:
|
||||
"""
|
||||
Schreibt in sleep_log. Kein conn.commit — Aufrufer rollt Transaktion.
|
||||
Gibt Statistik im Executor-Format zurück.
|
||||
"""
|
||||
csv_text = text.replace("\r\n", "\n").replace("\r", "\n")
|
||||
if csv_text.startswith("\ufeff"):
|
||||
csv_text = csv_text[1:]
|
||||
reader = csv.DictReader(io.StringIO(csv_text))
|
||||
fmt = detect_apple_sleep_csv_format(reader.fieldnames)
|
||||
|
||||
phase_map = {
|
||||
"Kern": "light",
|
||||
"Core": "light",
|
||||
"Light": "light",
|
||||
"REM": "rem",
|
||||
"Tief": "deep",
|
||||
"Deep": "deep",
|
||||
"Wach": "awake",
|
||||
"Awake": "awake",
|
||||
"Schlafend": None,
|
||||
"Asleep": None,
|
||||
"In Bed": None,
|
||||
}
|
||||
|
||||
if fmt == "summary":
|
||||
nights_dict = _build_nights_from_apple_summary(reader)
|
||||
else:
|
||||
nights_dict = _build_nights_from_apple_segments(reader, phase_map)
|
||||
|
||||
if not nights_dict:
|
||||
raise ValueError(
|
||||
"Keine importierbaren Schlafzeilen gefunden (prüfe Start/Ende und Format)."
|
||||
)
|
||||
|
||||
inserted = 0
|
||||
updated = 0
|
||||
skipped = 0
|
||||
error_details: list[dict[str, Any]] = []
|
||||
affected_ids: list[str] = []
|
||||
|
||||
row_hint = 0
|
||||
for wake_date, night in nights_dict.items():
|
||||
row_hint += 1
|
||||
phase_sum = (
|
||||
night["deep_minutes"] + night["rem_minutes"] + night["light_minutes"]
|
||||
)
|
||||
total_hr = night.get("total_sleep_hr")
|
||||
fallback_min = int(round(float(total_hr) * 60)) if total_hr is not None else 0
|
||||
duration_minutes = phase_sum if phase_sum > 0 else fallback_min
|
||||
if duration_minutes <= 0:
|
||||
logger.warning(
|
||||
"Sleep import: überspringe %s — Dauer 0 (Phasen-Summe und Total Sleep (hr) leer/0).",
|
||||
wake_date,
|
||||
)
|
||||
error_details.append(
|
||||
{
|
||||
"row": row_hint,
|
||||
"error": f"Schlafdauer für {wake_date} ist 0 — Phasen oder Total Sleep (hr) fehlen.",
|
||||
}
|
||||
)
|
||||
continue
|
||||
wake_count = sum(1 for seg in night["segments"] if seg["phase"] == "awake")
|
||||
|
||||
sleep_segments = [
|
||||
{
|
||||
"phase": seg["phase"],
|
||||
"start": seg["start"].isoformat(),
|
||||
"end": seg["end"].isoformat(),
|
||||
"duration_min": seg["duration_min"],
|
||||
}
|
||||
for seg in night["segments"]
|
||||
]
|
||||
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT id, source FROM sleep_log
|
||||
WHERE profile_id = %s AND date = %s
|
||||
""",
|
||||
(profile_id, wake_date),
|
||||
)
|
||||
existing = cur.fetchone()
|
||||
|
||||
if existing and existing["source"] == "manual":
|
||||
skipped += 1
|
||||
continue
|
||||
|
||||
try:
|
||||
if existing:
|
||||
cur.execute(
|
||||
"""
|
||||
UPDATE sleep_log SET
|
||||
bedtime = %s,
|
||||
wake_time = %s,
|
||||
duration_minutes = %s,
|
||||
wake_count = %s,
|
||||
deep_minutes = %s,
|
||||
rem_minutes = %s,
|
||||
light_minutes = %s,
|
||||
awake_minutes = %s,
|
||||
sleep_segments = %s,
|
||||
source = 'apple_health',
|
||||
updated_at = CURRENT_TIMESTAMP
|
||||
WHERE id = %s AND profile_id = %s
|
||||
RETURNING id
|
||||
""",
|
||||
(
|
||||
night["bedtime"].time(),
|
||||
night["wake_time"].time(),
|
||||
duration_minutes,
|
||||
wake_count,
|
||||
night["deep_minutes"],
|
||||
night["rem_minutes"],
|
||||
night["light_minutes"],
|
||||
night["awake_minutes"],
|
||||
json.dumps(sleep_segments),
|
||||
existing["id"],
|
||||
profile_id,
|
||||
),
|
||||
)
|
||||
row = cur.fetchone()
|
||||
updated += 1
|
||||
if row and row.get("id"):
|
||||
affected_ids.append(str(row["id"]))
|
||||
else:
|
||||
cur.execute(
|
||||
"""
|
||||
INSERT INTO sleep_log (
|
||||
profile_id, date, bedtime, wake_time, duration_minutes,
|
||||
wake_count, deep_minutes, rem_minutes, light_minutes, awake_minutes,
|
||||
sleep_segments, source, created_at, updated_at
|
||||
) VALUES (
|
||||
%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, 'apple_health', CURRENT_TIMESTAMP, CURRENT_TIMESTAMP
|
||||
)
|
||||
RETURNING id
|
||||
""",
|
||||
(
|
||||
profile_id,
|
||||
wake_date,
|
||||
night["bedtime"].time(),
|
||||
night["wake_time"].time(),
|
||||
duration_minutes,
|
||||
wake_count,
|
||||
night["deep_minutes"],
|
||||
night["rem_minutes"],
|
||||
night["light_minutes"],
|
||||
night["awake_minutes"],
|
||||
json.dumps(sleep_segments),
|
||||
),
|
||||
)
|
||||
row = cur.fetchone()
|
||||
inserted += 1
|
||||
if row and row.get("id"):
|
||||
affected_ids.append(str(row["id"]))
|
||||
except Exception as e:
|
||||
logger.warning("Sleep import row failed: %s", e)
|
||||
error_details.append({"row": row_hint, "error": str(e)})
|
||||
|
||||
return {
|
||||
"rows_total": len(nights_dict),
|
||||
"inserted": inserted,
|
||||
"updated": updated,
|
||||
"skipped": skipped,
|
||||
"new_entries": inserted,
|
||||
"error_details": error_details,
|
||||
"affected_ids": affected_ids,
|
||||
}
|
||||
@@ -0,0 +1,241 @@
|
||||
"""
|
||||
Formatprüfung für CSV-Import-Vorlagen (field_mappings, type_conversions).
|
||||
|
||||
Liefert strukturierte Fehler/Warnungen für Admin-UI und Speicher-Guards.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any, Mapping
|
||||
|
||||
from csv_parser.core import normalize_header_for_signature
|
||||
from csv_parser.import_row_processing import validate_import_row_processing as validate_import_row_processing_spec
|
||||
from csv_parser.module_registry import (
|
||||
get_module_definition,
|
||||
validate_field_mappings,
|
||||
validate_required_field_targets,
|
||||
)
|
||||
from data_layer.activity_persistence_orchestrator import merge_activity_csv_module_fields
|
||||
|
||||
ALLOWED_SPEC_TYPES = frozenset(
|
||||
{"string", "float", "number", "int", "date", "time", "datetime", "duration"}
|
||||
)
|
||||
|
||||
|
||||
def _issue(
|
||||
severity: str,
|
||||
code: str,
|
||||
message: str,
|
||||
*,
|
||||
hint: str | None = None,
|
||||
field: str | None = None,
|
||||
csv_columns: list[str] | None = None,
|
||||
) -> dict[str, Any]:
|
||||
out: dict[str, Any] = {
|
||||
"severity": severity,
|
||||
"code": code,
|
||||
"message": message,
|
||||
}
|
||||
if hint:
|
||||
out["hint"] = hint
|
||||
if field:
|
||||
out["field"] = field
|
||||
if csv_columns:
|
||||
out["csv_columns"] = csv_columns
|
||||
return out
|
||||
|
||||
|
||||
def validate_csv_template(
|
||||
module: str,
|
||||
field_mappings: Mapping[str, Any] | None,
|
||||
type_conversions: Mapping[str, Any] | None = None,
|
||||
import_row_processing: Mapping[str, Any] | None = None,
|
||||
column_signature: list[str] | None = None,
|
||||
*,
|
||||
cur=None,
|
||||
) -> dict[str, Any]:
|
||||
"""
|
||||
Prüft eine Vorlage ohne Datei-Upload.
|
||||
|
||||
Returns:
|
||||
``{"valid": bool, "errors": [...], "warnings": [...]}``
|
||||
"""
|
||||
errors: list[dict[str, Any]] = []
|
||||
warnings: list[dict[str, Any]] = []
|
||||
|
||||
fm = dict(field_mappings or {})
|
||||
tc: dict[str, Any] = dict(type_conversions or {}) if type_conversions else {}
|
||||
mod = get_module_definition(module)
|
||||
if not mod:
|
||||
errors.append(
|
||||
_issue(
|
||||
"error",
|
||||
"unknown_module",
|
||||
f"Unbekanntes Modul «{module}».",
|
||||
hint="Nur registrierte Module in module_registry sind erlaubt.",
|
||||
)
|
||||
)
|
||||
return {"valid": False, "errors": errors, "warnings": warnings}
|
||||
|
||||
field_defs = dict(mod.get("fields") or {})
|
||||
if module == "activity" and cur is not None:
|
||||
field_defs = merge_activity_csv_module_fields(cur, field_defs)
|
||||
|
||||
try:
|
||||
validate_field_mappings(module, fm, cur=cur)
|
||||
except ValueError as e:
|
||||
errors.append(
|
||||
_issue(
|
||||
"error",
|
||||
"invalid_field_mapping",
|
||||
str(e),
|
||||
hint="Jede Zuordnung muss auf ein bekanntes Zielfeld des Moduls zeigen (oder „–“ / ignorieren).",
|
||||
)
|
||||
)
|
||||
|
||||
try:
|
||||
validate_required_field_targets(module, fm)
|
||||
except ValueError as e:
|
||||
errors.append(
|
||||
_issue(
|
||||
"error",
|
||||
"missing_required_target",
|
||||
str(e),
|
||||
hint="Pflichtfelder des Moduls müssen mindestens einer CSV-Spalte zugeordnet sein.",
|
||||
)
|
||||
)
|
||||
|
||||
if import_row_processing:
|
||||
try:
|
||||
validate_import_row_processing_spec(module, import_row_processing, fm, cur=cur)
|
||||
except ValueError as e:
|
||||
errors.append(
|
||||
_issue(
|
||||
"error",
|
||||
"invalid_import_row_processing",
|
||||
str(e),
|
||||
hint="import_row_processing: group_by und aggregates prüfen (siehe Doku Issue #21).",
|
||||
)
|
||||
)
|
||||
|
||||
for db_field, spec in tc.items():
|
||||
if db_field not in field_defs:
|
||||
errors.append(
|
||||
_issue(
|
||||
"error",
|
||||
"unknown_type_conversion_field",
|
||||
f"type_conversions enthält unbekanntes Zielfeld «{db_field}».",
|
||||
hint="Nur Felder aus der Moduldefinition sind erlaubt.",
|
||||
field=db_field,
|
||||
)
|
||||
)
|
||||
continue
|
||||
if not isinstance(spec, Mapping):
|
||||
errors.append(
|
||||
_issue(
|
||||
"error",
|
||||
"type_conversion_not_object",
|
||||
f"type_conversions[\"{db_field}\"] muss ein JSON-Objekt sein.",
|
||||
field=db_field,
|
||||
)
|
||||
)
|
||||
continue
|
||||
stype = spec.get("type", "string")
|
||||
if stype not in ALLOWED_SPEC_TYPES:
|
||||
warnings.append(
|
||||
_issue(
|
||||
"warning",
|
||||
"unusual_conversion_type",
|
||||
f"Ungewöhnlicher Typ «{stype}» für «{db_field}» (erwartet u. a. string, float, date, datetime).",
|
||||
field=db_field,
|
||||
)
|
||||
)
|
||||
|
||||
finfo = field_defs.get(db_field) or {}
|
||||
expected = finfo.get("type")
|
||||
if expected == "date" and stype not in ("date", "datetime"):
|
||||
warnings.append(
|
||||
_issue(
|
||||
"warning",
|
||||
"date_field_conversion",
|
||||
f"Zielfeld «{db_field}» ist ein Datum; der Konvertierungstyp ist «{stype}».",
|
||||
hint="Meist «date» oder «datetime» mit passendem format.",
|
||||
field=db_field,
|
||||
)
|
||||
)
|
||||
if expected == "float" and stype == "int" and db_field in ("hr_avg", "hr_max"):
|
||||
warnings.append(
|
||||
_issue(
|
||||
"warning",
|
||||
"hr_as_int",
|
||||
"Herzfrequenz als «int» konvertiert; Nachkommastellen aus Apple-Export gehen verloren.",
|
||||
hint="Optional «float» mit flexible: true verwenden.",
|
||||
field=db_field,
|
||||
)
|
||||
)
|
||||
|
||||
# Mehrere CSV-Spalten → dasselbe Zielfeld
|
||||
by_target: dict[str, list[str]] = {}
|
||||
for csv_col, dbf in fm.items():
|
||||
if dbf in (None, "", "-", "_skip"):
|
||||
continue
|
||||
by_target.setdefault(str(dbf), []).append(str(csv_col))
|
||||
for dbf, cols in by_target.items():
|
||||
if len(cols) > 1:
|
||||
warnings.append(
|
||||
_issue(
|
||||
"warning",
|
||||
"duplicate_target_columns",
|
||||
f"Mehrere Spalten mappen auf «{dbf}»: {', '.join(cols)}.",
|
||||
hint="Beim Import gewinnt die letzte Spalte in der CSV-Kopfzeilen-Reihenfolge.",
|
||||
field=dbf,
|
||||
csv_columns=cols,
|
||||
)
|
||||
)
|
||||
|
||||
# Kilojoule in kcal-Feldern (häufiger Apple-DE-Fehler)
|
||||
for csv_col, dbf in fm.items():
|
||||
if dbf not in ("kcal_active", "kcal_resting"):
|
||||
continue
|
||||
col_l = str(csv_col).lower()
|
||||
if "kj" in col_l or "kilojoule" in col_l:
|
||||
sub = tc.get(dbf)
|
||||
su = (sub or {}).get("source_unit") if isinstance(sub, Mapping) else None
|
||||
if str(su or "").strip().lower() != "kj":
|
||||
warnings.append(
|
||||
_issue(
|
||||
"warning",
|
||||
"energy_kj_without_source_unit",
|
||||
f"Spalte «{csv_col}» deutet auf Kilojoule, Zielfeld «{dbf}» speichert kcal.",
|
||||
hint='In type_conversions für dieses Feld "source_unit": "kj" setzen (Faktor 1/4.184).',
|
||||
field=str(dbf),
|
||||
csv_columns=[str(csv_col)],
|
||||
)
|
||||
)
|
||||
|
||||
# Signatur vs. gemappte Spalten: beide Seiten wie beim Import normalisieren
|
||||
# (column_signature kann sortierte Normalform aus Analyse sein, field_mappings rohe Header).
|
||||
if column_signature:
|
||||
sig_forms = {
|
||||
normalize_header_for_signature(str(c))
|
||||
for c in column_signature
|
||||
if str(c).strip()
|
||||
}
|
||||
sig_forms.discard("")
|
||||
mapped_forms = {
|
||||
normalize_header_for_signature(str(k))
|
||||
for k in fm.keys()
|
||||
if str(k).strip()
|
||||
}
|
||||
mapped_forms.discard("")
|
||||
if sig_forms and mapped_forms and not sig_forms.intersection(mapped_forms):
|
||||
warnings.append(
|
||||
_issue(
|
||||
"warning",
|
||||
"signature_vs_mappings_mismatch",
|
||||
"column_signature und field_mappings (Schlüssel) haben nach Normalisierung keine gemeinsame Spalte.",
|
||||
hint="Prüfen Sie, ob die gespeicherte Signatur zur CSV passt; Zuordnungen nutzen rohe Kopfzeilen, die Signatur oft die gleiche Normalform wie in der Analyse.",
|
||||
)
|
||||
)
|
||||
|
||||
return {"valid": len(errors) == 0, "errors": errors, "warnings": warnings}
|
||||
@@ -0,0 +1,736 @@
|
||||
"""
|
||||
Typkonvertierung für CSV-Zellen gemäß type_conversions-JSON (Issue #21).
|
||||
|
||||
Locale-robust: dieselbe Vorlage kann Exporte mit wechselndem Datumsformat oder
|
||||
Dezimaltrenner verarbeiten, wenn flexible oder auto-Optionen gesetzt sind.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import datetime as dt
|
||||
import re
|
||||
from decimal import Decimal, InvalidOperation
|
||||
from typing import Any, Mapping, Sequence
|
||||
|
||||
from dateutil import parser as dateutil_parser
|
||||
|
||||
from csv_parser.core import canonical_csv_header_label, normalize_header_for_signature
|
||||
from csv_parser.field_units import factor_source_to_canonical
|
||||
|
||||
# Alias → strptime (JSON in Kleinbuchstaben)
|
||||
DATE_FORMAT_STRPTIME: dict[str, str] = {
|
||||
"yyyy-mm-dd": "%Y-%m-%d",
|
||||
"mm/dd/yyyy": "%m/%d/%Y",
|
||||
"dd/mm/yyyy": "%d/%m/%Y",
|
||||
"dd.mm.yyyy": "%d.%m.%Y",
|
||||
"dd.mm.yyyy hh:mm": "%d.%m.%Y %H:%M",
|
||||
"dd.mm.yyyy HH:MM": "%d.%m.%Y %H:%M",
|
||||
"yyyy-mm-dd hh:mm:ss": "%Y-%m-%d %H:%M:%S",
|
||||
"yyyy-mm-dd HH:MM:SS": "%Y-%m-%d %H:%M:%S",
|
||||
}
|
||||
|
||||
TIME_FORMAT_STRPTIME: dict[str, str] = {
|
||||
"HH:MM": "%H:%M",
|
||||
"HH:MM:SS": "%H:%M:%S",
|
||||
}
|
||||
|
||||
# Wenn flexible: zusätzliche strptime-Versuche (ungefähr häufig → seltener)
|
||||
_STRPTIME_FALLBACK_DATES: list[str] = [
|
||||
"%Y-%m-%d",
|
||||
"%d.%m.%Y",
|
||||
"%d.%m.%y",
|
||||
"%d/%m/%Y",
|
||||
"%m/%d/%Y",
|
||||
"%Y/%m/%d",
|
||||
"%Y%m%d",
|
||||
]
|
||||
_STRPTIME_FALLBACK_DATETIME: list[str] = [
|
||||
"%Y-%m-%d",
|
||||
"%Y-%m-%d %H:%M:%S",
|
||||
"%Y-%m-%d %H:%M",
|
||||
"%d.%m.%Y %H:%M:%S",
|
||||
"%d.%m.%Y %H:%M",
|
||||
"%d.%m.%y %H:%M:%S",
|
||||
"%d.%m.%y %H:%M",
|
||||
"%Y-%m-%dT%H:%M:%S",
|
||||
"%Y-%m-%dT%H:%M:%SZ",
|
||||
"%Y-%m-%dT%H:%M:%S%z",
|
||||
]
|
||||
|
||||
|
||||
def _normalize_num_token(raw: str) -> str:
|
||||
return re.sub(r"[\s\u00a0\u202f]", "", raw.strip())
|
||||
|
||||
|
||||
def _parse_float_auto(s: str) -> float:
|
||||
"""
|
||||
Heuristik ohne festes Locale: Punkt/Komma als Tausender vs. Dezimal,
|
||||
basierend auf der letzten erkannten Trennstelle und Gruppierung.
|
||||
|
||||
Apple Health u. a. liefern berechnete Mittelwerte mit vielen Nachkommastellen
|
||||
(z. B. «96.874937…») und Energie als «596.668904…» — dabei ist der Punkt
|
||||
immer Dezimaltrenner. Früher wurden lange Nachkommateile fälschlich so
|
||||
behandelt, dass der Punkt entfernt wurde (Tausender-Heuristik).
|
||||
"""
|
||||
raw = s
|
||||
s = _normalize_num_token(s)
|
||||
if not s or s in ("-", "—", "–"):
|
||||
raise ValueError("leer")
|
||||
neg = False
|
||||
if s.startswith("(") and s.endswith(")"):
|
||||
neg = True
|
||||
s = s[1:-1].strip()
|
||||
if s.startswith("-"):
|
||||
neg = not neg
|
||||
s = s[1:]
|
||||
elif s.startswith("+"):
|
||||
s = s[1:]
|
||||
|
||||
last_comma = s.rfind(",")
|
||||
last_dot = s.rfind(".")
|
||||
|
||||
if last_comma >= 0 and last_dot >= 0:
|
||||
if last_comma > last_dot:
|
||||
s = s.replace(".", "").replace(",", ".")
|
||||
else:
|
||||
s = s.replace(",", "")
|
||||
elif last_comma >= 0:
|
||||
parts = s.split(",")
|
||||
if len(parts) == 2:
|
||||
left, right = parts[0], parts[1]
|
||||
if not right:
|
||||
raise ValueError("leer")
|
||||
left_digits = left.replace(".", "")
|
||||
# Langer Nachkommateil → Dezimalkomma; «1.234,56»-Fälle oben mit Punkt+Komma
|
||||
if len(right) > 3 or len(right) <= 2:
|
||||
s = left_digits + "." + right.replace(".", "")
|
||||
elif len(right) == 3 and len(left_digits) <= 3:
|
||||
s = left_digits + right
|
||||
else:
|
||||
s = left_digits + "." + right.replace(".", "")
|
||||
else:
|
||||
s = s.replace(",", "")
|
||||
elif last_dot >= 0:
|
||||
parts = s.split(".")
|
||||
if len(parts) == 2:
|
||||
left, right = parts[0], parts[1]
|
||||
if not right:
|
||||
raise ValueError("leer")
|
||||
left_digits = left.replace(",", "")
|
||||
# Genau ein Punkt: viele Nachkommastellen → Apple/US-Dezimalpunkt (nicht „.“ streichen)
|
||||
if len(right) > 3 or len(right) <= 2:
|
||||
s = left_digits + "." + right
|
||||
elif len(right) == 3:
|
||||
if len(left_digits) == 1 and left_digits != "0" and left_digits.isdigit():
|
||||
s = left_digits + right
|
||||
else:
|
||||
s = left_digits + "." + right
|
||||
elif len(parts) > 2:
|
||||
if len(parts[-1]) <= 2:
|
||||
s = "".join(parts[:-1]) + "." + parts[-1]
|
||||
else:
|
||||
s = "".join(parts)
|
||||
else:
|
||||
s = s.replace(".", "")
|
||||
|
||||
try:
|
||||
v = float(Decimal(s))
|
||||
except (InvalidOperation, ValueError) as e:
|
||||
raise ValueError(f"Zahl nicht parsbar: {raw!r}") from e
|
||||
return -v if neg else v
|
||||
|
||||
|
||||
def _parse_float(raw: str, decimal_sep: str) -> float:
|
||||
s = _normalize_num_token(raw)
|
||||
if not s:
|
||||
raise ValueError("leer")
|
||||
if "." in s and "," in s:
|
||||
return _parse_float_auto(s)
|
||||
if decimal_sep == ",":
|
||||
if "," not in s and "." in s:
|
||||
return _parse_float_auto(s)
|
||||
s = s.replace(".", "").replace(",", ".")
|
||||
else:
|
||||
if "," in s and "." not in s:
|
||||
return _parse_float_auto(s)
|
||||
s = s.replace(",", "")
|
||||
return float(Decimal(s))
|
||||
|
||||
|
||||
def _float_from_spec(raw: str, spec: Mapping[str, Any]) -> float:
|
||||
dec = spec.get("decimal_separator", ".")
|
||||
flexible = bool(spec.get("flexible"))
|
||||
if dec in (None, "auto"):
|
||||
return _parse_float_auto(raw)
|
||||
try:
|
||||
return _parse_float(raw, str(dec))
|
||||
except (InvalidOperation, ValueError):
|
||||
if flexible:
|
||||
return _parse_float_auto(raw)
|
||||
raise
|
||||
|
||||
|
||||
def _resolve_strptime_pattern(fmt_key: str) -> str | None:
|
||||
k = fmt_key.strip()
|
||||
if k.startswith("%"):
|
||||
return k
|
||||
return DATE_FORMAT_STRPTIME.get(k.lower())
|
||||
|
||||
|
||||
def _collect_strptime_date_formats(spec: Mapping[str, Any], *, for_datetime: bool) -> list[str]:
|
||||
seen: set[str] = set()
|
||||
out: list[str] = []
|
||||
|
||||
def add(fmt_key: str) -> None:
|
||||
p = _resolve_strptime_pattern(fmt_key)
|
||||
if p and p not in seen:
|
||||
seen.add(p)
|
||||
out.append(p)
|
||||
if not for_datetime and p.endswith(" %H:%M") and "%H:%M:%S" not in p:
|
||||
p2 = p + ":%S"
|
||||
if p2 not in seen:
|
||||
seen.add(p2)
|
||||
out.append(p2)
|
||||
elif for_datetime and p.endswith(":%S"):
|
||||
# z. B. Apple Health „2026-04-09 16:48“ ohne Sekunden
|
||||
p_short = p[:-3]
|
||||
if p_short not in seen:
|
||||
seen.add(p_short)
|
||||
out.append(p_short)
|
||||
|
||||
primary = spec.get("format")
|
||||
if primary:
|
||||
add(str(primary))
|
||||
extra = spec.get("formats")
|
||||
if isinstance(extra, Sequence) and not isinstance(extra, (str, bytes)):
|
||||
for item in extra:
|
||||
if item:
|
||||
add(str(item))
|
||||
|
||||
if bool(spec.get("flexible")):
|
||||
for p in _STRPTIME_FALLBACK_DATETIME if for_datetime else _STRPTIME_FALLBACK_DATES:
|
||||
if p not in seen:
|
||||
seen.add(p)
|
||||
out.append(p)
|
||||
return out
|
||||
|
||||
|
||||
def _try_strptime(s: str, patterns: Sequence[str]) -> dt.datetime | None:
|
||||
for pat in patterns:
|
||||
try:
|
||||
return dt.datetime.strptime(s, pat)
|
||||
except ValueError:
|
||||
continue
|
||||
return None
|
||||
|
||||
|
||||
def _try_strptime_trim_time(s: str, patterns: Sequence[str]) -> dt.datetime | None:
|
||||
head = s.split(maxsplit=1)[0].strip() if s else ""
|
||||
if head and head != s:
|
||||
hit = _try_strptime(head, patterns)
|
||||
if hit:
|
||||
return hit
|
||||
return _try_strptime(s, patterns)
|
||||
|
||||
|
||||
def _normalize_locale_date_months(s: str) -> str:
|
||||
"""
|
||||
Omron Connect / Berichte: «10 Apr. 2026», «31 März 2026» — ohne DE→EN scheitert dateutil.
|
||||
"""
|
||||
if not s:
|
||||
return s
|
||||
out = s
|
||||
for pat, rep in (
|
||||
(r"März", "March"),
|
||||
(r"Maerz", "March"),
|
||||
(r"Januar", "January"),
|
||||
(r"Februar", "February"),
|
||||
(r"Oktober", "October"),
|
||||
(r"Dezember", "December"),
|
||||
(r"Juni", "June"),
|
||||
(r"Juli", "July"),
|
||||
(r"\bMai\b", "May"),
|
||||
):
|
||||
out = re.sub(pat, rep, out, flags=re.IGNORECASE)
|
||||
return out
|
||||
|
||||
|
||||
def _dateutil_parse(s: str, spec: Mapping[str, Any]) -> dt.datetime | None:
|
||||
s_trim = s.strip()
|
||||
dayfirst_opt = spec.get("dayfirst")
|
||||
# ISO YYYY-MM-DD: dayfirst=True vertauscht Monat/Tag (09.04. → 04.09.)
|
||||
iso_ymd_prefix = bool(re.match(r"^\d{4}-\d{2}-\d{2}(\D|$)", s_trim))
|
||||
tries: list[bool | None]
|
||||
if dayfirst_opt is True:
|
||||
tries = [True]
|
||||
elif dayfirst_opt is False:
|
||||
tries = [False]
|
||||
else:
|
||||
tries = [False, True] if iso_ymd_prefix else [True, False]
|
||||
for df in tries:
|
||||
try:
|
||||
return dateutil_parser.parse(s_trim, dayfirst=df)
|
||||
except (ValueError, TypeError, OverflowError):
|
||||
continue
|
||||
return None
|
||||
|
||||
|
||||
def _parse_date_typed(s: str, spec: Mapping[str, Any]) -> dt.date | dt.datetime:
|
||||
extract = spec.get("extract", "date_only")
|
||||
s0 = _normalize_locale_date_months(s.strip())
|
||||
patterns = _collect_strptime_date_formats(spec, for_datetime=False)
|
||||
part = _try_strptime_trim_time(s0, patterns) if patterns else None
|
||||
if part is None:
|
||||
part = _try_strptime(s0, _collect_strptime_date_formats(spec, for_datetime=True))
|
||||
if part is None and (bool(spec.get("flexible")) or spec.get("formats")):
|
||||
part = _dateutil_parse(s0, spec)
|
||||
if part is None:
|
||||
merged: dict[str, Any] = {**dict(spec), "flexible": True}
|
||||
if "dayfirst" not in merged:
|
||||
merged["dayfirst"] = True
|
||||
part = _dateutil_parse(s0, merged)
|
||||
if part is None:
|
||||
fmt_key = str(spec.get("format", ""))
|
||||
raise ValueError(f"Datum nicht parsbar: {fmt_key} / {s!r}")
|
||||
if extract == "date_only":
|
||||
return part.date()
|
||||
return part
|
||||
|
||||
|
||||
def _parse_datetime_typed(s: str, spec: Mapping[str, Any]) -> dt.datetime:
|
||||
s0 = _normalize_locale_date_months(s.strip())
|
||||
patterns = _collect_strptime_date_formats(spec, for_datetime=True)
|
||||
part = _try_strptime(s0, patterns)
|
||||
if part is None and (bool(spec.get("flexible")) or spec.get("formats")):
|
||||
du = _dateutil_parse(s0, spec)
|
||||
if du:
|
||||
part = du
|
||||
if part is None:
|
||||
merged: dict[str, Any] = {**dict(spec), "flexible": True}
|
||||
if "dayfirst" not in merged:
|
||||
merged["dayfirst"] = True
|
||||
du = _dateutil_parse(s0, merged)
|
||||
if du:
|
||||
part = du
|
||||
if part is None:
|
||||
fmt_key = str(spec.get("format", ""))
|
||||
raise ValueError(f"Datetime nicht parsbar: {fmt_key} / {s!r}")
|
||||
return part
|
||||
|
||||
|
||||
def _parse_time_typed(s: str, spec: Mapping[str, Any]) -> dt.time:
|
||||
patterns: list[str] = []
|
||||
seen: set[str] = set()
|
||||
primary = spec.get("format")
|
||||
if primary:
|
||||
fk = str(primary)
|
||||
p = TIME_FORMAT_STRPTIME.get(fk, _resolve_strptime_pattern(fk) or fk)
|
||||
if p not in seen:
|
||||
seen.add(p)
|
||||
patterns.append(p)
|
||||
extra = spec.get("formats")
|
||||
if isinstance(extra, Sequence) and not isinstance(extra, (str, bytes)):
|
||||
for item in extra:
|
||||
if not item:
|
||||
continue
|
||||
p = TIME_FORMAT_STRPTIME.get(str(item), str(item))
|
||||
if p not in seen:
|
||||
seen.add(p)
|
||||
patterns.append(p)
|
||||
if bool(spec.get("flexible")):
|
||||
for p in ("%H:%M:%S", "%H:%M"):
|
||||
if p not in seen:
|
||||
seen.add(p)
|
||||
patterns.append(p)
|
||||
part = _try_strptime(s.strip(), patterns)
|
||||
if part is None:
|
||||
raise ValueError(f"Zeit nicht parsbar: {s!r}")
|
||||
return part.time()
|
||||
|
||||
|
||||
def _parse_int(raw: str, spec: Mapping[str, Any]) -> int:
|
||||
s = raw.strip()
|
||||
if bool(spec.get("flexible")) or spec.get("thousands_separator") == "auto":
|
||||
s2 = _normalize_num_token(s)
|
||||
if not s2 or s2 in ("-", "—", "–"):
|
||||
raise ValueError("leer")
|
||||
# EU-Dezimal (z. B. Apple DE «37,26» für HRV) — nicht alle Ziffern konkatenieren (würde 3726 → CHECK).
|
||||
if "," in s2 or "." in s2:
|
||||
try:
|
||||
fv = _parse_float_auto(s2)
|
||||
return int(round(fv))
|
||||
except (ValueError, InvalidOperation):
|
||||
pass
|
||||
neg = s2.startswith("-")
|
||||
body = s2[1:] if neg else s2
|
||||
digits = re.sub(r"\D", "", body)
|
||||
if not digits:
|
||||
raise ValueError("leer")
|
||||
v = int(digits)
|
||||
return -v if neg else v
|
||||
# Ohne flexible: «108.0» / «96,8» trotzdem als Zahl mit Nachkommastellen
|
||||
s2 = _normalize_num_token(s)
|
||||
if "," in s2 or "." in s2:
|
||||
dec = spec.get("decimal_separator", ".")
|
||||
try:
|
||||
if dec in (None, "auto"):
|
||||
fv = _parse_float_auto(s2)
|
||||
else:
|
||||
fv = _parse_float(raw, str(dec))
|
||||
return int(round(fv))
|
||||
except (ValueError, InvalidOperation):
|
||||
pass
|
||||
s = re.sub(r"[^\d-]", "", s)
|
||||
if not s:
|
||||
raise ValueError("leer")
|
||||
return int(s)
|
||||
|
||||
|
||||
def convert_value(
|
||||
raw: str,
|
||||
db_field: str,
|
||||
spec: Mapping[str, Any] | None,
|
||||
module: str | None = None,
|
||||
) -> Any:
|
||||
"""
|
||||
Konvertiert eine Roh-Zelle in einen Python-Wert.
|
||||
spec kommt aus type_conversions[db_field].
|
||||
|
||||
Optionen (JSON):
|
||||
- flexible: true — nach Primärformat Fallbacks (Datum/Zahl/Zeit/Duration).
|
||||
- decimal_separator: ".", ",", "auto" — bei auto Heuristik EU/US-Mischformen.
|
||||
- formats: [ "yyyy-mm-dd", "%d.%m.%y", ... ] — weitere strptime-/Alias-Ketten.
|
||||
- dayfirst: true|false — nur für dateutil-Fallback; Standard: true dann false.
|
||||
- source_unit: Registry-IDs (z. B. "kj", "kg") oder "custom"/"none" — letztere ohne
|
||||
vordefinierten Faktor; beliebige Skalierung dann nur über conversion_factor.
|
||||
- conversion_factor: Zusätzlicher Multiplikator nach dem Parsen (und nach source_unit);
|
||||
für nicht vordefinierte Umrechnungen source_unit weglassen oder "custom" setzen und
|
||||
hier den Faktor angeben.
|
||||
"""
|
||||
if spec is None:
|
||||
return raw.strip() if raw else None
|
||||
if raw is None:
|
||||
return None
|
||||
s = raw.strip()
|
||||
if s == "":
|
||||
return None
|
||||
|
||||
t = spec.get("type", "string")
|
||||
if t == "string":
|
||||
return s
|
||||
|
||||
if t in ("float", "number"):
|
||||
v = _float_from_spec(raw, spec)
|
||||
if module:
|
||||
su = spec.get("source_unit")
|
||||
if su is not None and str(su).strip() != "":
|
||||
v = float(v) * factor_source_to_canonical(module, db_field, str(su))
|
||||
factor = spec.get("conversion_factor")
|
||||
if factor is not None:
|
||||
v = float(v) * float(factor)
|
||||
return v
|
||||
|
||||
if t == "int":
|
||||
return _parse_int(raw, spec)
|
||||
|
||||
if t == "date":
|
||||
return _parse_date_typed(s, spec)
|
||||
|
||||
if t == "time":
|
||||
return _parse_time_typed(s, spec)
|
||||
|
||||
if t == "datetime":
|
||||
return _parse_datetime_typed(s, spec)
|
||||
|
||||
if t == "duration":
|
||||
target = spec.get("target_unit", "minutes")
|
||||
parts = [p.strip() for p in s.split(":")]
|
||||
flexible = bool(spec.get("flexible"))
|
||||
if len(parts) == 3:
|
||||
try:
|
||||
h, m, sec = int(parts[0]), int(parts[1]), int(parts[2])
|
||||
if target == "minutes":
|
||||
return round(h * 60 + m + sec / 60.0, 4)
|
||||
except ValueError:
|
||||
if not flexible:
|
||||
raise ValueError(f"Duration nicht parsbar: {s!r}") from None
|
||||
if flexible:
|
||||
try:
|
||||
h, m, sec = int(parts[0]), int(parts[1]), float(parts[2])
|
||||
if target == "minutes":
|
||||
return round(h * 60 + m + sec / 60.0, 4)
|
||||
except ValueError:
|
||||
pass
|
||||
if len(parts) == 2:
|
||||
try:
|
||||
h, m = int(parts[0]), int(parts[1])
|
||||
return h * 60 + m
|
||||
except ValueError:
|
||||
pass
|
||||
raise ValueError(f"Duration nicht parsbar: {s!r}")
|
||||
|
||||
return s
|
||||
|
||||
|
||||
def _lookup_db_field(csv_col: str, field_mappings: Mapping[str, str]) -> str | None:
|
||||
"""
|
||||
CSV-Spaltennamen können Roh-Header sein; Vorlagen-Schlüssel oft normalisiert
|
||||
(wie column_signature). Exakter Treffer, dann Schlüssel nach Normalisierung,
|
||||
dann Abgleich aller Vorlagen-Keys über deren Normalform.
|
||||
|
||||
Zusätzlich: Präfix-Treffer für lange manuelle Keys (z. B. Apple
|
||||
„Aufgestiegene Höhe (m)“ → ``aufgestiegene_höhe_(m)`` vs. Mapping
|
||||
„aufgestiegene Höhe“ → ``aufgestiegene_höhe``) — gewinnt der längste passende Key.
|
||||
"""
|
||||
csv_col = canonical_csv_header_label(csv_col)
|
||||
v = field_mappings.get(csv_col)
|
||||
if v:
|
||||
return v if v not in ("-", "_skip") else None
|
||||
norm = normalize_header_for_signature(csv_col)
|
||||
v = field_mappings.get(norm)
|
||||
if v:
|
||||
return v if v not in ("-", "_skip") else None
|
||||
for k, fv in field_mappings.items():
|
||||
if normalize_header_for_signature(str(k)) == norm:
|
||||
return fv if fv not in ("-", "_skip") else None
|
||||
|
||||
# Präfix-Match (min. Länge gegen false positives wie „datum“ → „datum_xyz“)
|
||||
best_fv: str | None = None
|
||||
best_nk_len = 0
|
||||
min_prefix = 10
|
||||
for k, fv in field_mappings.items():
|
||||
if not fv or fv in ("-", "_skip"):
|
||||
continue
|
||||
nk = normalize_header_for_signature(str(k))
|
||||
if len(nk) < min_prefix or len(nk) >= len(norm):
|
||||
continue
|
||||
if not norm.startswith(nk):
|
||||
continue
|
||||
boundary = norm[len(nk) : len(nk) + 1]
|
||||
if boundary not in ("", "_", "("):
|
||||
continue
|
||||
if len(nk) > best_nk_len:
|
||||
best_nk_len = len(nk)
|
||||
best_fv = fv
|
||||
if best_fv:
|
||||
return best_fv
|
||||
return None
|
||||
|
||||
|
||||
def _vitals_baseline_alias_db_field(csv_col: str) -> str | None:
|
||||
"""
|
||||
Apple Health: deutsch „Vitalwerte.csv“ (Breitexport) vs. schmale Vorlage
|
||||
(Start / Resting Heart Rate …). Ohne Alias wählt die Analyse oft die
|
||||
englische Vorlage → jede Zeile „Datum fehlt“.
|
||||
Abgleich über normalisierten Header (normalize_header_for_signature).
|
||||
"""
|
||||
n = normalize_header_for_signature(str(csv_col))
|
||||
if n in ("datum_uhrzeit", "start", "date_time", "datetime"):
|
||||
return "date"
|
||||
if "ruhepuls" in n or n.startswith("resting_heart_rate"):
|
||||
return "resting_hr"
|
||||
if "herzfrequenzvariabilit" in n or "heart_rate_variability" in n:
|
||||
return "hrv"
|
||||
if "vo2" in n and "max" in n:
|
||||
return "vo2_max"
|
||||
if "blutsauerstoff" in n or "oxygen_saturation" in n:
|
||||
return "spo2"
|
||||
if "atemfrequenz" in n or "respiratory_rate" in n:
|
||||
return "respiratory_rate"
|
||||
return None
|
||||
|
||||
|
||||
def _blood_pressure_alias_db_field(csv_col: str) -> str | None:
|
||||
"""
|
||||
Omron (schmal) vs. Apple-Gesundheit (Breitexport): unterschiedliche Spaltennamen;
|
||||
kombinierte Messzeit oft als „Start“ oder „Datum/Uhrzeit“.
|
||||
"""
|
||||
n = normalize_header_for_signature(str(csv_col))
|
||||
low = str(csv_col).lower()
|
||||
if n in ("datum_uhrzeit", "datetime", "date_time", "messzeitpunkt"):
|
||||
return "start_time"
|
||||
if n in ("start", "beginn"):
|
||||
return "start_time"
|
||||
if n in ("datum", "date", "messdatum"):
|
||||
return "measured_date"
|
||||
if n in ("zeit", "time", "uhrzeit"):
|
||||
return "measured_time"
|
||||
if "systolisch" in n or ("blutdruck" in n and "systol" in low) or n.startswith("systolic"):
|
||||
return "systolic"
|
||||
if "diastolisch" in n or ("blutdruck" in n and "diastol" in low) or n.startswith("diastolic"):
|
||||
return "diastolic"
|
||||
if n.startswith("puls") or n.startswith("pulse") or "puls_" in n:
|
||||
return "pulse"
|
||||
return None
|
||||
|
||||
|
||||
def _activity_alias_db_field(csv_col: str) -> str | None:
|
||||
"""
|
||||
Apple-Workout schmal vs. Breitexport (viele Spalten): Trainingsart/Dauer/Strecke
|
||||
trotzdem zuverlässig erkennen.
|
||||
"""
|
||||
n = normalize_header_for_signature(str(csv_col))
|
||||
low = str(csv_col).lower()
|
||||
if n in ("trainingsart", "workout_type", "activity_type", "workouttype"):
|
||||
return "activity_type"
|
||||
if ("trainings" in n and "art" in n) or ("workout" in low and "type" in low):
|
||||
return "activity_type"
|
||||
if n in ("datum_uhrzeit", "start", "beginn", "startzeit", "von"):
|
||||
return "start_time"
|
||||
if n in ("ende", "end", "endzeit", "bis"):
|
||||
return "end_time"
|
||||
if n in ("date", "datum"):
|
||||
return "date"
|
||||
if "dauer" in n or n == "duration" or n.startswith("duration_"):
|
||||
return "duration_min"
|
||||
if ("strecke" in n or "distance" in low) and ("km" in low or "(km" in low or " km" in low):
|
||||
return "distance_km"
|
||||
if "aktive_energie" in n or "active_energy" in n:
|
||||
return "kcal_active"
|
||||
if "ruheeintr" in n or "ruheenergie" in n or "resting_energy" in n:
|
||||
return "kcal_resting"
|
||||
if ("herzfrequenz" in n or "heart_rate" in n) and ("max" in low or "max" in n):
|
||||
return "hr_max"
|
||||
if (
|
||||
"durchschnittliche_herzfrequenz" in n
|
||||
or "heart_rate_average" in n
|
||||
or ("herzfrequenz" in n and ("durchschn" in n or "avg" in low or "average" in low))
|
||||
or ("heart_rate" in n and ("avg" in low or "average" in low))
|
||||
):
|
||||
return "hr_avg"
|
||||
return None
|
||||
|
||||
|
||||
def _effective_conversion_spec(
|
||||
db_field: str,
|
||||
spec: Mapping[str, Any] | None,
|
||||
module: str | None,
|
||||
) -> Mapping[str, Any] | None:
|
||||
if spec is not None:
|
||||
return spec
|
||||
if module == "blood_pressure" and db_field == "start_time":
|
||||
return {"type": "datetime", "format": "yyyy-mm-dd HH:MM:SS", "flexible": True}
|
||||
return None
|
||||
|
||||
|
||||
def build_row_after_mapping(
|
||||
csv_row: Mapping[str, str],
|
||||
field_mappings: Mapping[str, str],
|
||||
type_conversions: Mapping[str, Any] | None,
|
||||
module: str | None = None,
|
||||
) -> dict[str, Any]:
|
||||
"""
|
||||
Wendet Zuordnung csv_spalte → db_feld und Typkonvertierung an.
|
||||
Unzugeordnete oder „—“ werden übersprungen.
|
||||
Die Reihenfolge der Spalten in der CSV spielt keine Rolle (Dict-Zugriff nach Name).
|
||||
Falls mehrere Spalten auf dasselbe db_field abbilden, gewinnt die zuletzt verarbeitete
|
||||
(iterreihenfolge = Kopfzeilen-Reihenfolge in der Datei) — in der Praxis selten.
|
||||
"""
|
||||
out: dict[str, Any] = {}
|
||||
tc = type_conversions or {}
|
||||
for csv_col, raw in csv_row.items():
|
||||
db_field = _lookup_db_field(str(csv_col), field_mappings)
|
||||
if not db_field and module == "vitals_baseline":
|
||||
db_field = _vitals_baseline_alias_db_field(csv_col)
|
||||
elif not db_field and module == "blood_pressure":
|
||||
db_field = _blood_pressure_alias_db_field(csv_col)
|
||||
elif not db_field and module == "activity":
|
||||
db_field = _activity_alias_db_field(csv_col)
|
||||
if not db_field:
|
||||
continue
|
||||
raw_spec = tc.get(db_field) if isinstance(tc, dict) else None
|
||||
if not isinstance(raw_spec, dict):
|
||||
raw_spec = None
|
||||
spec = _effective_conversion_spec(db_field, raw_spec, module)
|
||||
try:
|
||||
out[db_field] = convert_value(
|
||||
raw, db_field, spec if isinstance(spec, dict) else None, module=module
|
||||
)
|
||||
except Exception:
|
||||
out[db_field] = None
|
||||
return out
|
||||
|
||||
|
||||
def diagnose_row_mapping(
|
||||
csv_row: Mapping[str, str],
|
||||
field_mappings: Mapping[str, str],
|
||||
type_conversions: Mapping[str, Any] | None,
|
||||
module: str | None = None,
|
||||
*,
|
||||
mapped_typed: Mapping[str, Any] | None = None,
|
||||
max_columns: int = 512,
|
||||
) -> dict[str, Any]:
|
||||
"""
|
||||
Nur für Diagnose-Endpunkt: Quelle (Vorlage vs. Alias), Konvertierung pro Spalte,
|
||||
Ergebnis wie build_row_after_mapping (json-freundliche Vorschau).
|
||||
max_columns begrenzt nur die Länge der Liste „per_column“ in der Antwort — der echte
|
||||
Import verarbeitet alle Spalten (siehe iter_csv_dict_rows / build_row_after_mapping).
|
||||
"""
|
||||
tc = type_conversions or {}
|
||||
per_column: list[dict[str, Any]] = []
|
||||
n = 0
|
||||
for csv_col, raw in csv_row.items():
|
||||
if n >= max_columns:
|
||||
break
|
||||
n += 1
|
||||
sc = str(csv_col)
|
||||
via_t = _lookup_db_field(sc, field_mappings)
|
||||
via_a = None
|
||||
if not via_t and module == "vitals_baseline":
|
||||
via_a = _vitals_baseline_alias_db_field(sc)
|
||||
elif not via_t and module == "blood_pressure":
|
||||
via_a = _blood_pressure_alias_db_field(sc)
|
||||
elif not via_t and module == "activity":
|
||||
via_a = _activity_alias_db_field(sc)
|
||||
target = via_t or via_a
|
||||
src = "template" if via_t else ("alias" if via_a else "none")
|
||||
raw_spec = tc.get(target) if isinstance(tc, dict) and target else None
|
||||
if not isinstance(raw_spec, dict):
|
||||
raw_spec = None
|
||||
spec = _effective_conversion_spec(target, raw_spec, module) if target else None
|
||||
conv_err: str | None = None
|
||||
conv_preview: Any = None
|
||||
if target:
|
||||
try:
|
||||
conv_val = convert_value(
|
||||
(raw or "").strip(),
|
||||
target,
|
||||
spec if isinstance(spec, dict) else None,
|
||||
module=module,
|
||||
)
|
||||
conv_preview = conv_val.isoformat() if hasattr(conv_val, "isoformat") else conv_val
|
||||
except Exception as e:
|
||||
conv_err = str(e)
|
||||
per_column.append(
|
||||
{
|
||||
"csv_column": sc,
|
||||
"raw_preview": ((raw or "")[:120]),
|
||||
"db_field": target,
|
||||
"source": src,
|
||||
"convert_error": conv_err,
|
||||
"converted_preview": conv_preview,
|
||||
}
|
||||
)
|
||||
|
||||
src_map = (
|
||||
build_row_after_mapping(csv_row, field_mappings, type_conversions, module=module)
|
||||
if mapped_typed is None
|
||||
else mapped_typed
|
||||
)
|
||||
mapped_preview: dict[str, Any] = {}
|
||||
for k, v in src_map.items():
|
||||
mapped_preview[k] = v.isoformat() if hasattr(v, "isoformat") else v
|
||||
|
||||
tmpl_keys = [
|
||||
str(k)
|
||||
for k, v in field_mappings.items()
|
||||
if v not in (None, "-", "_skip")
|
||||
]
|
||||
|
||||
return {
|
||||
"per_column": per_column,
|
||||
"columns_truncated": len(csv_row) > max_columns,
|
||||
"template_mapped_keys": tmpl_keys[:40],
|
||||
"template_mapped_keys_truncated": len(tmpl_keys) > 40,
|
||||
"mapped": mapped_preview,
|
||||
}
|
||||
@@ -51,6 +51,9 @@ __all__ = [
|
||||
|
||||
# Body Metrics (Basic)
|
||||
'get_latest_weight_data',
|
||||
'get_bmi_data',
|
||||
'get_profile_goal_weight_data',
|
||||
'get_profile_goal_bf_pct_data',
|
||||
'get_weight_trend_data',
|
||||
'get_body_composition_data',
|
||||
'get_circumference_summary_data',
|
||||
@@ -99,6 +102,9 @@ __all__ = [
|
||||
'get_activity_summary_data',
|
||||
'get_activity_detail_data',
|
||||
'get_training_type_distribution_data',
|
||||
'get_training_frequency_by_type_data',
|
||||
'get_training_inter_session_gap_data',
|
||||
'get_training_sessions_recent_weeks_data',
|
||||
|
||||
# Activity Metrics (Calculated)
|
||||
'calculate_training_minutes_week',
|
||||
|
||||
@@ -0,0 +1,61 @@
|
||||
"""
|
||||
Kanonische Aufteilung activity_log vs. EAV für Aktivitätssessions.
|
||||
|
||||
- **Kern / Mapping-Ziele für activity_log:** ausschließlich die Keys aus
|
||||
``csv_parser.module_registry.MODULE_DEFINITIONS["activity"].fields`` (keine zweite hartcodierte Liste).
|
||||
- **Alle anderen Attribute:** ``training_parameters`` + Attributprofil (Kategorie/Typ) → EAV;
|
||||
Lesefallback für bekannte Legacy-Spalten siehe unten.
|
||||
|
||||
Normative Doku: .claude/docs/technical/ACTIVITY_PRODUCTION_ARCHITECTURE_AND_PHASES.md,
|
||||
ACTIVITY_SCALAR_KANON_TABLE.md
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Dict, Final
|
||||
|
||||
from csv_parser.module_registry import get_module_definition
|
||||
|
||||
|
||||
def get_activity_module_registry_field_keys() -> frozenset[str]:
|
||||
"""Keys des Universal-CSV-Moduls ``activity`` (= feste activity_log-Kernfelder / Mapping-Ziele)."""
|
||||
mod = get_module_definition("activity")
|
||||
if not mod:
|
||||
return frozenset()
|
||||
return frozenset((mod.get("fields") or {}).keys())
|
||||
|
||||
|
||||
# Gleiche Menge wie ``MODULE_DEFINITIONS["activity"].fields`` — zur Laufzeit aus der Registry abgeleitet.
|
||||
ACTIVITY_MODULE_REGISTRY_FIELD_KEYS: Final[frozenset[str]] = get_activity_module_registry_field_keys()
|
||||
|
||||
# Teil-UPDATEs (Import): alle Kernfelder außer ``date`` (Identität / Duplikat-Key).
|
||||
ACTIVITY_LOG_PATCHABLE_COLUMNS: Final[frozenset[str]] = ACTIVITY_MODULE_REGISTRY_FIELD_KEYS - {"date"}
|
||||
|
||||
# Parameter-Keys (training_parameters.key), die primär in EAV geführt werden; source_field nach Migration 057 NULL.
|
||||
# Lesen (Merge): activity_log-Legacy-Spalte schlägt EAV, wenn beide befüllt; sonst EAV.
|
||||
ACTIVITY_EAV_PRIMARY_PARAMETER_KEYS: Final[frozenset[str]] = frozenset(
|
||||
{
|
||||
"min_hr",
|
||||
"pace_min_per_km",
|
||||
"cadence",
|
||||
"avg_power",
|
||||
"elevation_gain",
|
||||
"temperature_celsius",
|
||||
"humidity_percent",
|
||||
"avg_hr_percent",
|
||||
"kcal_per_km",
|
||||
}
|
||||
)
|
||||
|
||||
# Spaltenname activity_log für Legacy-Merge (Vorrang vor EAV bei gesetztem Spaltenwert).
|
||||
ACTIVITY_LOG_LEGACY_COLUMN_FOR_EAV_PRIMARY_PARAM: Final[Dict[str, str]] = {
|
||||
"min_hr": "hr_min",
|
||||
"pace_min_per_km": "pace_min_per_km",
|
||||
"cadence": "cadence",
|
||||
"avg_power": "avg_power",
|
||||
"elevation_gain": "elevation_gain",
|
||||
"temperature_celsius": "temperature_celsius",
|
||||
"humidity_percent": "humidity_percent",
|
||||
"avg_hr_percent": "avg_hr_percent",
|
||||
"kcal_per_km": "kcal_per_km",
|
||||
}
|
||||
|
||||
@@ -7,6 +7,10 @@ Functions:
|
||||
- get_activity_summary_data(): Count, total duration, calories, averages
|
||||
- get_activity_detail_data(): Detailed activity log entries
|
||||
- get_training_type_distribution_data(): Training category percentages
|
||||
- get_training_frequency_by_type_data(): Häufigkeit & Intensität pro activity_type
|
||||
- get_training_inter_session_gap_data(): Pausen zwischen Einheiten (Stunden)
|
||||
- get_training_sessions_recent_weeks_data(): Wochen-JSON für KI-Kontext
|
||||
- get_training_parameters_ki_glossary_data(): Parameter-Katalog (Feld, Namen, Beschreibungen) für KI
|
||||
|
||||
All functions return structured data (dict) without formatting.
|
||||
Use placeholder_resolver.py for formatted strings for AI.
|
||||
@@ -15,11 +19,12 @@ Phase 0c: Multi-Layer Architecture
|
||||
Version: 1.0
|
||||
"""
|
||||
|
||||
from typing import Dict, List, Optional
|
||||
from datetime import datetime, timedelta, date
|
||||
from typing import Dict, List, Optional, Any
|
||||
from datetime import datetime, timedelta, date, time
|
||||
import statistics
|
||||
from db import get_db, get_cursor, r2d
|
||||
from data_layer.utils import calculate_confidence, safe_float, safe_int
|
||||
from data_layer.activity_session_metrics import enrich_sessions_with_metrics
|
||||
from data_layer.utils import calculate_confidence, safe_float, safe_int, serialize_dates
|
||||
|
||||
|
||||
def get_activity_summary_data(
|
||||
@@ -120,7 +125,8 @@ def get_activity_detail_data(
|
||||
"duration_min": int,
|
||||
"kcal_active": int,
|
||||
"hr_avg": int | None,
|
||||
"training_category": str | None
|
||||
"training_category": str | None,
|
||||
"session_metrics": list | None, # EAV (enrich_sessions_with_metrics)
|
||||
},
|
||||
...
|
||||
],
|
||||
@@ -139,6 +145,7 @@ def get_activity_detail_data(
|
||||
|
||||
cur.execute(
|
||||
"""SELECT
|
||||
id,
|
||||
date,
|
||||
activity_type,
|
||||
duration_min,
|
||||
@@ -149,7 +156,7 @@ def get_activity_detail_data(
|
||||
WHERE profile_id=%s AND date >= %s
|
||||
ORDER BY date DESC
|
||||
LIMIT %s""",
|
||||
(profile_id, cutoff, limit)
|
||||
(profile_id, cutoff, limit),
|
||||
)
|
||||
rows = cur.fetchall()
|
||||
|
||||
@@ -158,19 +165,24 @@ def get_activity_detail_data(
|
||||
"activities": [],
|
||||
"total_count": 0,
|
||||
"confidence": "insufficient",
|
||||
"days_analyzed": days
|
||||
"days_analyzed": days,
|
||||
}
|
||||
|
||||
activities = []
|
||||
for row in rows:
|
||||
activities.append({
|
||||
"date": row['date'],
|
||||
"activity_type": row['activity_type'],
|
||||
"duration_min": safe_int(row['duration_min']),
|
||||
"kcal_active": safe_int(row['kcal_active']),
|
||||
"hr_avg": safe_int(row['hr_avg']) if row.get('hr_avg') else None,
|
||||
"training_category": row.get('training_category')
|
||||
})
|
||||
activities.append(
|
||||
{
|
||||
"id": str(row["id"]),
|
||||
"date": row["date"],
|
||||
"activity_type": row["activity_type"],
|
||||
"duration_min": safe_int(row["duration_min"]),
|
||||
"kcal_active": safe_int(row["kcal_active"]),
|
||||
"hr_avg": safe_int(row["hr_avg"]) if row.get("hr_avg") else None,
|
||||
"training_category": row.get("training_category"),
|
||||
}
|
||||
)
|
||||
|
||||
enrich_sessions_with_metrics(cur, activities)
|
||||
|
||||
confidence = calculate_confidence(len(activities), days, "general")
|
||||
|
||||
@@ -178,7 +190,7 @@ def get_activity_detail_data(
|
||||
"activities": activities,
|
||||
"total_count": len(activities),
|
||||
"confidence": confidence,
|
||||
"days_analyzed": days
|
||||
"days_analyzed": days,
|
||||
}
|
||||
|
||||
|
||||
@@ -601,26 +613,23 @@ def calculate_activity_score(profile_id: str, focus_weights: Optional[Dict] = No
|
||||
from data_layer.scores import get_user_focus_weights
|
||||
focus_weights = get_user_focus_weights(profile_id)
|
||||
|
||||
# Activity-related focus areas (English keys from DB)
|
||||
# Strength training
|
||||
strength = focus_weights.get('strength', 0)
|
||||
strength_endurance = focus_weights.get('strength_endurance', 0)
|
||||
power = focus_weights.get('power', 0)
|
||||
# Activity-related focus areas (English keys from DB); Gewichte float (kein Decimal×float)
|
||||
strength = float(focus_weights.get('strength', 0) or 0)
|
||||
strength_endurance = float(focus_weights.get('strength_endurance', 0) or 0)
|
||||
power = float(focus_weights.get('power', 0) or 0)
|
||||
total_strength = strength + strength_endurance + power
|
||||
|
||||
# Endurance training
|
||||
aerobic = focus_weights.get('aerobic_endurance', 0)
|
||||
anaerobic = focus_weights.get('anaerobic_endurance', 0)
|
||||
cardiovascular = focus_weights.get('cardiovascular_health', 0)
|
||||
aerobic = float(focus_weights.get('aerobic_endurance', 0) or 0)
|
||||
anaerobic = float(focus_weights.get('anaerobic_endurance', 0) or 0)
|
||||
cardiovascular = float(focus_weights.get('cardiovascular_health', 0) or 0)
|
||||
total_cardio = aerobic + anaerobic + cardiovascular
|
||||
|
||||
# Mobility/Coordination
|
||||
flexibility = focus_weights.get('flexibility', 0)
|
||||
mobility = focus_weights.get('mobility', 0)
|
||||
balance = focus_weights.get('balance', 0)
|
||||
reaction = focus_weights.get('reaction', 0)
|
||||
rhythm = focus_weights.get('rhythm', 0)
|
||||
coordination = focus_weights.get('coordination', 0)
|
||||
flexibility = float(focus_weights.get('flexibility', 0) or 0)
|
||||
mobility = float(focus_weights.get('mobility', 0) or 0)
|
||||
balance = float(focus_weights.get('balance', 0) or 0)
|
||||
reaction = float(focus_weights.get('reaction', 0) or 0)
|
||||
rhythm = float(focus_weights.get('rhythm', 0) or 0)
|
||||
coordination = float(focus_weights.get('coordination', 0) or 0)
|
||||
total_ability = flexibility + mobility + balance + reaction + rhythm + coordination
|
||||
|
||||
total_activity_weight = total_strength + total_cardio + total_ability
|
||||
@@ -671,9 +680,9 @@ def calculate_activity_score(profile_id: str, focus_weights: Optional[Dict] = No
|
||||
if not components:
|
||||
return None
|
||||
|
||||
# Weighted average
|
||||
total_score = sum(score * weight for _, score, weight in components)
|
||||
total_weight = sum(weight for _, _, weight in components)
|
||||
# Weighted average (float: DB-Aggregate können Decimal sein)
|
||||
total_score = sum(float(score) * float(weight) for _, score, weight in components)
|
||||
total_weight = sum(float(weight) for _, _, weight in components)
|
||||
|
||||
return int(total_score / total_weight)
|
||||
|
||||
@@ -725,12 +734,13 @@ def _score_cardio_presence(profile_id: str) -> Optional[int]:
|
||||
if not row:
|
||||
return None
|
||||
|
||||
cardio_days = row['cardio_days']
|
||||
cardio_minutes = row['cardio_minutes'] or 0
|
||||
# psycopg2: SUM() → oft Decimal — vor Mix mit float konvertieren
|
||||
cardio_days = int(row['cardio_days'] or 0)
|
||||
cardio_minutes = float(row['cardio_minutes'] or 0)
|
||||
|
||||
# Target: 3-5 days/week, 150+ minutes
|
||||
day_score = min(100, (cardio_days / 4) * 100)
|
||||
minute_score = min(100, (cardio_minutes / 150) * 100)
|
||||
day_score = min(100.0, (cardio_days / 4) * 100)
|
||||
minute_score = min(100.0, (cardio_minutes / 150) * 100)
|
||||
|
||||
return int((day_score + minute_score) / 2)
|
||||
|
||||
@@ -904,3 +914,298 @@ def calculate_activity_data_quality(profile_id: str) -> Dict[str, any]:
|
||||
"quality": int(quality_score)
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
def _session_sort_ts(row: Dict) -> datetime:
|
||||
"""Einheitlicher Zeitstempel für Sortierung und Pausenberechnung."""
|
||||
d = row["date"]
|
||||
if isinstance(d, str):
|
||||
d = datetime.strptime(d[:10], "%Y-%m-%d").date()
|
||||
st = row.get("start_time")
|
||||
if st is None:
|
||||
t = time(12, 0, 0)
|
||||
else:
|
||||
t = st
|
||||
return datetime.combine(d, t)
|
||||
|
||||
|
||||
def get_training_frequency_by_type_data(
|
||||
profile_id: str,
|
||||
days: int = 28,
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Pro activity_type (Roh-Label aus Import/Anzeige): Häufigkeit & Intensitätskennzahlen.
|
||||
|
||||
Returns:
|
||||
{
|
||||
"days_analyzed": int,
|
||||
"confidence": str,
|
||||
"by_type": [
|
||||
{
|
||||
"activity_type": str,
|
||||
"session_count": int,
|
||||
"sessions_per_week": float,
|
||||
"avg_duration_min": float | None,
|
||||
"avg_kcal_active": float | None,
|
||||
"avg_hr_avg": float | None,
|
||||
"avg_hr_max": float | None,
|
||||
"avg_rpe": float | None,
|
||||
"avg_kcal_per_min": float | None, # grobe Intensität, wenn kcal & Dauer
|
||||
},
|
||||
...
|
||||
],
|
||||
}
|
||||
"""
|
||||
weeks = max(days / 7.0, 0.01)
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cutoff = (datetime.now() - timedelta(days=days)).strftime("%Y-%m-%d")
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT
|
||||
activity_type,
|
||||
COUNT(*)::int AS session_count,
|
||||
AVG(duration_min)::float AS avg_duration_min,
|
||||
AVG(kcal_active)::float AS avg_kcal_active,
|
||||
AVG(hr_avg)::float AS avg_hr_avg,
|
||||
AVG(hr_max)::float AS avg_hr_max,
|
||||
AVG(rpe)::float AS avg_rpe,
|
||||
SUM(COALESCE(duration_min, 0))::float AS sum_duration,
|
||||
SUM(COALESCE(kcal_active, 0))::float AS sum_kcal
|
||||
FROM activity_log
|
||||
WHERE profile_id = %s AND date >= %s
|
||||
GROUP BY activity_type
|
||||
ORDER BY session_count DESC
|
||||
""",
|
||||
(profile_id, cutoff),
|
||||
)
|
||||
rows = [r2d(r) for r in cur.fetchall()]
|
||||
|
||||
if not rows:
|
||||
return {
|
||||
"days_analyzed": days,
|
||||
"confidence": "insufficient",
|
||||
"by_type": [],
|
||||
}
|
||||
|
||||
by_type = []
|
||||
for r in rows:
|
||||
sc = int(r["session_count"])
|
||||
sum_dur = float(r["sum_duration"] or 0)
|
||||
sum_kcal = float(r["sum_kcal"] or 0)
|
||||
kcal_per_min = (sum_kcal / sum_dur) if sum_dur > 0 else None
|
||||
by_type.append(
|
||||
{
|
||||
"activity_type": r["activity_type"],
|
||||
"session_count": sc,
|
||||
"sessions_per_week": round(sc / weeks, 2),
|
||||
"avg_duration_min": r["avg_duration_min"],
|
||||
"avg_kcal_active": r["avg_kcal_active"],
|
||||
"avg_hr_avg": r["avg_hr_avg"],
|
||||
"avg_hr_max": r["avg_hr_max"],
|
||||
"avg_rpe": r["avg_rpe"],
|
||||
"avg_kcal_per_min": round(kcal_per_min, 2) if kcal_per_min is not None else None,
|
||||
}
|
||||
)
|
||||
|
||||
total_sessions = sum(x["session_count"] for x in by_type)
|
||||
confidence = calculate_confidence(total_sessions, days, "general")
|
||||
return {
|
||||
"days_analyzed": days,
|
||||
"confidence": confidence,
|
||||
"by_type": by_type,
|
||||
}
|
||||
|
||||
|
||||
def get_training_inter_session_gap_data(
|
||||
profile_id: str,
|
||||
days: int = 28,
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Mittlere/median Pausen zwischen aufeinanderfolgenden Trainingseinheiten (Stunden).
|
||||
|
||||
Sortierung: Datum + start_time (fehlend → 12:00), dann created.
|
||||
"""
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cutoff = (datetime.now() - timedelta(days=days)).strftime("%Y-%m-%d")
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT date, start_time, created
|
||||
FROM activity_log
|
||||
WHERE profile_id = %s AND date >= %s
|
||||
ORDER BY date ASC, start_time ASC NULLS LAST, created ASC
|
||||
""",
|
||||
(profile_id, cutoff),
|
||||
)
|
||||
rows = [r2d(r) for r in cur.fetchall()]
|
||||
|
||||
if len(rows) < 2:
|
||||
return {
|
||||
"days_analyzed": days,
|
||||
"confidence": "insufficient",
|
||||
"gap_hours_median": None,
|
||||
"gap_hours_mean": None,
|
||||
"gap_hours_min": None,
|
||||
"gaps_count": 0,
|
||||
}
|
||||
|
||||
gaps = []
|
||||
prev_ts = None
|
||||
for r in rows:
|
||||
ts = _session_sort_ts(r)
|
||||
if prev_ts is not None:
|
||||
gaps.append((ts - prev_ts).total_seconds() / 3600.0)
|
||||
prev_ts = ts
|
||||
|
||||
if not gaps:
|
||||
return {
|
||||
"days_analyzed": days,
|
||||
"confidence": "insufficient",
|
||||
"gap_hours_median": None,
|
||||
"gap_hours_mean": None,
|
||||
"gap_hours_min": None,
|
||||
"gaps_count": 0,
|
||||
}
|
||||
|
||||
gaps_sorted = sorted(gaps)
|
||||
mid = len(gaps_sorted) // 2
|
||||
median = (
|
||||
gaps_sorted[mid]
|
||||
if len(gaps_sorted) % 2
|
||||
else (gaps_sorted[mid - 1] + gaps_sorted[mid]) / 2.0
|
||||
)
|
||||
confidence = calculate_confidence(len(rows), days, "general")
|
||||
return {
|
||||
"days_analyzed": days,
|
||||
"confidence": confidence,
|
||||
"gap_hours_median": round(median, 1),
|
||||
"gap_hours_mean": round(statistics.mean(gaps), 1),
|
||||
"gap_hours_min": round(min(gaps), 1),
|
||||
"gaps_count": len(gaps),
|
||||
}
|
||||
|
||||
|
||||
def get_training_sessions_recent_weeks_data(
|
||||
profile_id: str,
|
||||
weeks: int = 4,
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Letzte Wochen mit Einzeltrainings für KI-Kontext (Dauer, kcal, HF, Typ).
|
||||
|
||||
weeks: Anzahl zurückliegender ISO-Kalenderwochen (Default 4).
|
||||
"""
|
||||
days = max(weeks * 7, 7)
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cutoff = (datetime.now() - timedelta(days=days)).strftime("%Y-%m-%d")
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT
|
||||
a.id,
|
||||
a.date,
|
||||
a.start_time,
|
||||
a.activity_type,
|
||||
a.training_category,
|
||||
a.duration_min,
|
||||
a.kcal_active,
|
||||
a.hr_avg,
|
||||
a.hr_max,
|
||||
a.rpe,
|
||||
tt.name_de AS training_type_name
|
||||
FROM activity_log a
|
||||
LEFT JOIN training_types tt ON tt.id = a.training_type_id
|
||||
WHERE a.profile_id = %s AND a.date >= %s
|
||||
ORDER BY a.date ASC, a.start_time ASC NULLS LAST, a.created ASC
|
||||
""",
|
||||
(profile_id, cutoff),
|
||||
)
|
||||
rows = [r2d(r) for r in cur.fetchall()]
|
||||
enrich_sessions_with_metrics(cur, rows)
|
||||
|
||||
if not rows:
|
||||
return {
|
||||
"weeks": [],
|
||||
"meta": {
|
||||
"weeks_requested": weeks,
|
||||
"days_loaded": days,
|
||||
"session_count": 0,
|
||||
"confidence": "insufficient",
|
||||
},
|
||||
}
|
||||
|
||||
by_week: Dict[str, List[Dict]] = {}
|
||||
for r in rows:
|
||||
d = r["date"]
|
||||
if isinstance(d, str):
|
||||
d = datetime.strptime(d[:10], "%Y-%m-%d").date()
|
||||
iso = d.isocalendar()
|
||||
wk = f"{iso.year}-W{iso.week:02d}"
|
||||
if wk not in by_week:
|
||||
by_week[wk] = []
|
||||
dur = r.get("duration_min")
|
||||
dur_f = float(dur) if dur is not None else None
|
||||
kcal = r.get("kcal_active")
|
||||
kcal_f = float(kcal) if kcal is not None else None
|
||||
hr_a = r.get("hr_avg")
|
||||
hr_m = r.get("hr_max")
|
||||
by_week[wk].append(
|
||||
{
|
||||
"id": str(r["id"]),
|
||||
"date": d,
|
||||
"start_time": str(r["start_time"]) if r.get("start_time") is not None else None,
|
||||
"activity_type": r.get("activity_type"),
|
||||
"training_category": r.get("training_category"),
|
||||
"training_type_name": r.get("training_type_name"),
|
||||
"duration_min": dur_f,
|
||||
"kcal_active": kcal_f,
|
||||
"hr_avg": int(hr_a) if hr_a is not None else None,
|
||||
"hr_max": int(hr_m) if hr_m is not None else None,
|
||||
"rpe": int(r["rpe"]) if r.get("rpe") is not None else None,
|
||||
"session_metrics": r.get("session_metrics", []),
|
||||
}
|
||||
)
|
||||
|
||||
week_keys = sorted(by_week.keys())
|
||||
weeks_out = [{"week_iso": wk, "sessions": by_week[wk]} for wk in week_keys]
|
||||
confidence = calculate_confidence(len(rows), days, "general")
|
||||
return serialize_dates(
|
||||
{
|
||||
"weeks": weeks_out,
|
||||
"meta": {
|
||||
"weeks_requested": weeks,
|
||||
"days_loaded": days,
|
||||
"session_count": len(rows),
|
||||
"confidence": confidence,
|
||||
},
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
def get_training_parameters_ki_glossary_data(profile_id: str) -> Dict[str, Any]:
|
||||
"""
|
||||
Alle aktiven ``training_parameters`` für KI-Kontext (z. B. neben ``training_sessions_recent_json``).
|
||||
|
||||
Enthält technischen key, name_de/name_en, description_de/description_en, data_type, unit, category.
|
||||
|
||||
Args:
|
||||
profile_id: Reserviert für spätere Einschränkung (z. B. nur im Profil vorkommende Keys);
|
||||
aktuell ungenutzt, Signatur bleibt für Platzhalter-Resolver.
|
||||
"""
|
||||
_ = profile_id
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT key, name_de, name_en, description_de, description_en,
|
||||
data_type, unit, category
|
||||
FROM training_parameters
|
||||
WHERE is_active = true
|
||||
ORDER BY category, key
|
||||
"""
|
||||
)
|
||||
rows = [r2d(r) for r in cur.fetchall()]
|
||||
return {
|
||||
"parameters": rows,
|
||||
"meta": {"count": len(rows), "scope": "global_active_catalog"},
|
||||
}
|
||||
@@ -0,0 +1,406 @@
|
||||
"""
|
||||
Zentrale Persistenz für activity_log + EAV-Nebenwirkungen (Eval).
|
||||
|
||||
Alle Schreibpfade (REST, Universal-CSV, Legacy-Upload) laufen hier zusammen.
|
||||
|
||||
Feld-Katalog für CSV-Mappings: get_mappable_activity_field_catalog()
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import datetime as dt
|
||||
import logging
|
||||
import uuid
|
||||
from typing import Any, Dict, List, Mapping, Optional
|
||||
|
||||
from models import ActivityEntry
|
||||
|
||||
from csv_parser.module_registry import get_module_definition
|
||||
from data_layer.activity_data_canon import get_activity_module_registry_field_keys
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
try:
|
||||
from evaluation_helper import evaluate_and_save_activity as _evaluate_and_save_activity
|
||||
|
||||
_EVALUATION_AVAILABLE = True
|
||||
except Exception: # pragma: no cover
|
||||
_evaluate_and_save_activity = None
|
||||
_EVALUATION_AVAILABLE = False
|
||||
|
||||
|
||||
def find_activity_duplicate_id(
|
||||
cur,
|
||||
profile_id: str,
|
||||
date_iso: str,
|
||||
start_time: Optional[Any],
|
||||
) -> Optional[str]:
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT id FROM activity_log
|
||||
WHERE profile_id = %s AND date = %s::date
|
||||
AND start_time IS NOT DISTINCT FROM %s::time
|
||||
""",
|
||||
(profile_id, date_iso, start_time),
|
||||
)
|
||||
row = cur.fetchone()
|
||||
return str(row["id"]) if row else None
|
||||
|
||||
|
||||
# Datum/Start/Ende/Typ setzt der CSV-Executor explizit (Normalisierung); nicht aus diesem Patch überschreiben.
|
||||
_ACTIVITY_CSV_REGISTRY_EXCLUDE = frozenset({"date", "start_time", "end_time", "activity_type"})
|
||||
|
||||
|
||||
def activity_registry_field_keys() -> frozenset[str]:
|
||||
"""Gleiche Menge wie ``ACTIVITY_MODULE_REGISTRY_FIELD_KEYS`` (Registry als Single Source)."""
|
||||
return get_activity_module_registry_field_keys()
|
||||
|
||||
|
||||
def activity_csv_registry_updates_from_mapped(mapped: Mapping[str, Any]) -> Dict[str, Any]:
|
||||
"""
|
||||
activity_log-Updates nur aus Modul-Registry-Feldern (Kernspalten).
|
||||
Trainingsparameter-Keys (nur in training_parameters) laufen über EAV, nicht hier.
|
||||
"""
|
||||
mod = get_module_definition("activity")
|
||||
if not mod:
|
||||
return {}
|
||||
fields = mod.get("fields") or {}
|
||||
out: Dict[str, Any] = {}
|
||||
|
||||
def _sf(v: Any) -> float | None:
|
||||
try:
|
||||
if v is None or (isinstance(v, str) and not str(v).strip()):
|
||||
return None
|
||||
return round(float(v), 1)
|
||||
except (TypeError, ValueError):
|
||||
return None
|
||||
|
||||
def _si(v: Any) -> int | None:
|
||||
try:
|
||||
if v is None or (isinstance(v, str) and not str(v).strip()):
|
||||
return None
|
||||
return int(round(float(v)))
|
||||
except (TypeError, ValueError):
|
||||
return None
|
||||
|
||||
def _hr(v: Any) -> float | None:
|
||||
x = _sf(v)
|
||||
if x is None or x < 20 or x > 280:
|
||||
return None
|
||||
return x
|
||||
|
||||
for key, spec in fields.items():
|
||||
if key in _ACTIVITY_CSV_REGISTRY_EXCLUDE:
|
||||
continue
|
||||
if key not in mapped:
|
||||
continue
|
||||
raw = mapped[key]
|
||||
if raw is None or raw == "":
|
||||
continue
|
||||
if isinstance(raw, str) and not raw.strip():
|
||||
continue
|
||||
typ = spec.get("type", "string")
|
||||
if typ == "float":
|
||||
v = _hr(raw) if key in ("hr_avg", "hr_max") else _sf(raw)
|
||||
if v is not None:
|
||||
out[key] = v
|
||||
elif typ == "int":
|
||||
v = _si(raw)
|
||||
if v is not None:
|
||||
out[key] = v
|
||||
elif typ == "datetime":
|
||||
if isinstance(raw, dt.datetime):
|
||||
out[key] = raw.strftime("%Y-%m-%d %H:%M:%S")
|
||||
elif isinstance(raw, dt.date):
|
||||
out[key] = f"{raw.isoformat()} 00:00:00"
|
||||
elif isinstance(raw, str) and raw.strip():
|
||||
out[key] = raw.strip()
|
||||
elif typ == "date":
|
||||
if isinstance(raw, dt.date):
|
||||
out[key] = raw.isoformat()
|
||||
elif isinstance(raw, dt.datetime):
|
||||
out[key] = raw.date().isoformat()
|
||||
elif isinstance(raw, str) and raw.strip():
|
||||
out[key] = raw.strip()
|
||||
else:
|
||||
out[key] = str(raw).strip()
|
||||
|
||||
return out
|
||||
|
||||
|
||||
def insert_activity_from_entry(cur, profile_id: str, eid: str, e: ActivityEntry) -> None:
|
||||
"""INSERT activity_log aus ActivityEntry (manueller API-Pfad)."""
|
||||
d = e.model_dump()
|
||||
cur.execute(
|
||||
"""INSERT INTO activity_log (id,profile_id,date,start_time,end_time,activity_type,duration_min,kcal_active,kcal_resting,
|
||||
hr_avg,hr_max,hr_min,distance_km,pace_min_per_km,cadence,avg_power,elevation_gain,
|
||||
temperature_celsius,humidity_percent,avg_hr_percent,kcal_per_km,rpe,source,notes,
|
||||
training_type_id,training_category,training_subcategory,created)
|
||||
VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,CURRENT_TIMESTAMP)""",
|
||||
(
|
||||
eid,
|
||||
profile_id,
|
||||
d["date"],
|
||||
d["start_time"],
|
||||
d["end_time"],
|
||||
d["activity_type"],
|
||||
d["duration_min"],
|
||||
d["kcal_active"],
|
||||
d["kcal_resting"],
|
||||
d["hr_avg"],
|
||||
d["hr_max"],
|
||||
d.get("hr_min"),
|
||||
d["distance_km"],
|
||||
d.get("pace_min_per_km"),
|
||||
d.get("cadence"),
|
||||
d.get("avg_power"),
|
||||
d.get("elevation_gain"),
|
||||
d.get("temperature_celsius"),
|
||||
d.get("humidity_percent"),
|
||||
d.get("avg_hr_percent"),
|
||||
d.get("kcal_per_km"),
|
||||
d["rpe"],
|
||||
d["source"],
|
||||
d["notes"],
|
||||
d.get("training_type_id"),
|
||||
d.get("training_category"),
|
||||
d.get("training_subcategory"),
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
def update_activity_from_entry(cur, profile_id: str, eid: str, e: ActivityEntry) -> None:
|
||||
"""Volles UPDATE aus ActivityEntry (REST PUT)."""
|
||||
d = e.model_dump()
|
||||
cur.execute(
|
||||
f"UPDATE activity_log SET {', '.join(f'{k}=%s' for k in d)} WHERE id=%s AND profile_id=%s",
|
||||
list(d.values()) + [eid, profile_id],
|
||||
)
|
||||
|
||||
|
||||
def update_activity_columns(
|
||||
cur,
|
||||
profile_id: str,
|
||||
eid: str,
|
||||
updates: Dict[str, Any],
|
||||
) -> None:
|
||||
"""Teil-UPDATE nur für übergebene Spalten (Importe)."""
|
||||
if not updates:
|
||||
return
|
||||
cols = [f"{k} = %s" for k in updates]
|
||||
vals = list(updates.values()) + [eid, profile_id]
|
||||
cur.execute(
|
||||
f"UPDATE activity_log SET {', '.join(cols)} WHERE id = %s AND profile_id = %s",
|
||||
vals,
|
||||
)
|
||||
|
||||
|
||||
def insert_activity_csv_minimal(
|
||||
cur,
|
||||
profile_id: str,
|
||||
eid: str,
|
||||
*,
|
||||
date_iso: str,
|
||||
start_time: Any,
|
||||
end_time: Any,
|
||||
activity_type: str,
|
||||
duration_min: Any,
|
||||
kcal_active: Any,
|
||||
kcal_resting: Any,
|
||||
hr_avg: Any,
|
||||
hr_max: Any,
|
||||
distance_km: Any,
|
||||
training_type_id: Any,
|
||||
training_category: Any,
|
||||
training_subcategory: Any,
|
||||
source: str,
|
||||
) -> None:
|
||||
"""INSERT minimale activity_log-Zeile (Universal-CSV)."""
|
||||
cur.execute(
|
||||
"""
|
||||
INSERT INTO activity_log (
|
||||
id, profile_id, date, start_time, end_time, activity_type, duration_min,
|
||||
kcal_active, kcal_resting, hr_avg, hr_max, distance_km,
|
||||
source, training_type_id, training_category, training_subcategory, created
|
||||
)
|
||||
VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,CURRENT_TIMESTAMP)
|
||||
""",
|
||||
(
|
||||
eid,
|
||||
profile_id,
|
||||
date_iso,
|
||||
start_time,
|
||||
end_time,
|
||||
activity_type,
|
||||
duration_min,
|
||||
kcal_active,
|
||||
kcal_resting,
|
||||
hr_avg,
|
||||
hr_max,
|
||||
distance_km,
|
||||
source,
|
||||
training_type_id,
|
||||
training_category,
|
||||
training_subcategory,
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
def run_activity_post_write_hooks(cur, profile_id: str, eid: str) -> None:
|
||||
"""Auto-Eval (falls aktiv). Kein Spalte→EAV-Sync: Lesepfad merge_column_backed_and_eav_metrics."""
|
||||
if _EVALUATION_AVAILABLE and _evaluate_and_save_activity:
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT id, profile_id, date, training_type_id, duration_min,
|
||||
hr_avg, hr_max, distance_km, kcal_active, kcal_resting,
|
||||
rpe, pace_min_per_km, cadence, elevation_gain
|
||||
FROM activity_log
|
||||
WHERE id = %s
|
||||
""",
|
||||
(eid,),
|
||||
)
|
||||
activity_row = cur.fetchone()
|
||||
if activity_row:
|
||||
activity_dict = dict(activity_row)
|
||||
training_type_id = activity_dict.get("training_type_id")
|
||||
if training_type_id:
|
||||
try:
|
||||
_evaluate_and_save_activity(cur, eid, activity_dict, training_type_id, profile_id)
|
||||
except Exception as eval_error:
|
||||
logger.error("[AUTO-EVAL] activity %s: %s", eid, eval_error)
|
||||
|
||||
|
||||
def run_activity_post_write_hooks_import(
|
||||
cur,
|
||||
profile_id: str,
|
||||
eid: str,
|
||||
*,
|
||||
workout_date: str,
|
||||
training_type_id: Optional[int],
|
||||
duration_min: Any,
|
||||
hr_avg: Any,
|
||||
hr_max: Any,
|
||||
distance_km: Any,
|
||||
kcal_active: Any,
|
||||
kcal_resting: Any,
|
||||
) -> None:
|
||||
"""Auto-Eval nach Import. Kein Spalte→EAV-Sync (siehe run_activity_post_write_hooks)."""
|
||||
if _EVALUATION_AVAILABLE and training_type_id and _evaluate_and_save_activity:
|
||||
try:
|
||||
activity_dict = {
|
||||
"id": eid,
|
||||
"profile_id": profile_id,
|
||||
"date": workout_date,
|
||||
"training_type_id": training_type_id,
|
||||
"duration_min": duration_min,
|
||||
"hr_avg": hr_avg,
|
||||
"hr_max": hr_max,
|
||||
"distance_km": distance_km,
|
||||
"kcal_active": kcal_active,
|
||||
"kcal_resting": kcal_resting,
|
||||
"rpe": None,
|
||||
"pace_min_per_km": None,
|
||||
"cadence": None,
|
||||
"elevation_gain": None,
|
||||
}
|
||||
_evaluate_and_save_activity(cur, eid, activity_dict, training_type_id, profile_id)
|
||||
except Exception as eval_err:
|
||||
logger.warning("[activity import] Auto-Eval fehlgeschlagen: %s", eval_err)
|
||||
|
||||
|
||||
def merge_activity_csv_module_fields(
|
||||
cur,
|
||||
static_fields: Dict[str, Any],
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
activity-Modul für CSV: statische Registry-Felder + alle aktiven training_parameters.
|
||||
|
||||
Gleiche Quelle wie get_mappable_activity_field_catalog.training_parameters — erscheint
|
||||
in Admin-CSV-Ziel-Liste, Validierung und Import-Zeilenaggregation.
|
||||
"""
|
||||
out = dict(static_fields)
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT key, data_type, unit, name_de
|
||||
FROM training_parameters
|
||||
WHERE is_active = true
|
||||
ORDER BY key
|
||||
"""
|
||||
)
|
||||
for row in cur.fetchall():
|
||||
k = row["key"]
|
||||
if k in out:
|
||||
continue
|
||||
dt = row["data_type"] or "float"
|
||||
if dt == "integer":
|
||||
mtype = "int"
|
||||
elif dt == "float":
|
||||
mtype = "float"
|
||||
elif dt == "boolean":
|
||||
mtype = "string"
|
||||
else:
|
||||
mtype = "string"
|
||||
spec: Dict[str, Any] = {
|
||||
"type": mtype,
|
||||
"required": False,
|
||||
"from_training_parameter": True,
|
||||
}
|
||||
if row.get("unit"):
|
||||
spec["unit"] = row["unit"]
|
||||
if row.get("name_de"):
|
||||
spec["label_de"] = row["name_de"]
|
||||
out[k] = spec
|
||||
return out
|
||||
|
||||
|
||||
def get_mappable_activity_field_catalog(cur, profile_id: str) -> Dict[str, Any]:
|
||||
"""
|
||||
Felder für konfigurierbare Import-Mappings.
|
||||
|
||||
core_fields: module_registry „activity“ → activity_log.
|
||||
training_parameters: alle aktiven Parameter (global); bei Anwendung auf eine Session
|
||||
werden Keys verworfen, die nicht in resolve_activity_attribute_schema(Kategorie/Typ) liegen.
|
||||
|
||||
profile_id: reserviert für künftige Profil-Filter.
|
||||
"""
|
||||
_ = profile_id
|
||||
mod = get_module_definition("activity") or {}
|
||||
fields = mod.get("fields") or {}
|
||||
core_fields: List[Dict[str, Any]] = []
|
||||
for key, spec in fields.items():
|
||||
s = spec or {}
|
||||
core_fields.append(
|
||||
{
|
||||
"key": key,
|
||||
"target": "activity_log",
|
||||
"column": key,
|
||||
"data_type": s.get("type", "string"),
|
||||
"required": bool(s.get("required")),
|
||||
"unit": s.get("unit"),
|
||||
"label_de": s.get("label_de") or key,
|
||||
}
|
||||
)
|
||||
core_fields.sort(key=lambda x: x["key"])
|
||||
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT id, key, name_de, name_en, category AS param_category,
|
||||
data_type, unit, source_field
|
||||
FROM training_parameters
|
||||
WHERE is_active = true
|
||||
ORDER BY key
|
||||
"""
|
||||
)
|
||||
parameters = [dict(r) for r in cur.fetchall()]
|
||||
|
||||
return {
|
||||
"core_fields": core_fields,
|
||||
"training_parameters": parameters,
|
||||
"notes": (
|
||||
"training_parameters listet alle aktiven Keys. Pro Session werden Werte ignoriert, "
|
||||
"die für deren training_category/training_type_id nicht im Attribut-Schema vorkommen."
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
def new_activity_id() -> str:
|
||||
return str(uuid.uuid4())
|
||||
@@ -0,0 +1,755 @@
|
||||
"""
|
||||
Activity session metrics (EAV) and resolved attribute schema — Layer 1.
|
||||
|
||||
See: .claude/docs/technical/ACTIVITY_SESSION_METRICS_EAV_AGENT_GUIDE.md
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from decimal import Decimal
|
||||
from typing import Any, Dict, List, Mapping, Optional, Sequence
|
||||
|
||||
from data_layer.activity_data_canon import (
|
||||
ACTIVITY_LOG_LEGACY_COLUMN_FOR_EAV_PRIMARY_PARAM,
|
||||
ACTIVITY_MODULE_REGISTRY_FIELD_KEYS,
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Diese Spalten nicht aus CSV-Parameter-Zuordnung überschreiben (kommen aus Typ-Mapping / System).
|
||||
ACTIVITY_LOG_PATCH_FORBIDDEN = frozenset(
|
||||
{
|
||||
"id",
|
||||
"profile_id",
|
||||
"date",
|
||||
"created",
|
||||
"training_type_id",
|
||||
"training_category",
|
||||
"training_subcategory",
|
||||
"source",
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
class ActivitySessionMetricsError(Exception):
|
||||
"""Raised by Layer 1; routers map to HTTP (404/400)."""
|
||||
|
||||
def __init__(self, status_code: int, detail: str):
|
||||
self.status_code = status_code
|
||||
self.detail = detail
|
||||
super().__init__(detail)
|
||||
|
||||
|
||||
def _effective_training_category(
|
||||
cur, training_category: Optional[str], training_type_id: Optional[int]
|
||||
) -> Optional[str]:
|
||||
if training_category:
|
||||
return training_category.strip() or None
|
||||
if training_type_id is None:
|
||||
return None
|
||||
cur.execute("SELECT category FROM training_types WHERE id = %s", (training_type_id,))
|
||||
row = cur.fetchone()
|
||||
if row and row.get("category"):
|
||||
return row["category"]
|
||||
return None
|
||||
|
||||
|
||||
def merge_parameter_schema_rows(
|
||||
category_rows: Sequence[Dict[str, Any]],
|
||||
type_rows: Sequence[Dict[str, Any]],
|
||||
) -> List[Dict[str, Any]]:
|
||||
"""
|
||||
Pure merge: category assignments + type assignments → sorted schema list.
|
||||
Row shapes match SELECTs in resolve_activity_attribute_schema (cat_sort / typ_* aliases).
|
||||
"""
|
||||
merged: Dict[int, Dict[str, Any]] = {}
|
||||
|
||||
for r in category_rows:
|
||||
pid = r["training_parameter_id"]
|
||||
merged[pid] = {
|
||||
"training_parameter_id": pid,
|
||||
"key": r["key"],
|
||||
"name_de": r["name_de"],
|
||||
"name_en": r["name_en"],
|
||||
"description_de": r.get("description_de"),
|
||||
"description_en": r.get("description_en"),
|
||||
"param_category": r["param_category"],
|
||||
"data_type": r["data_type"],
|
||||
"unit": r["unit"],
|
||||
"validation_rules": r["validation_rules"] or {},
|
||||
"source_field": r["source_field"],
|
||||
"sort_order": r["cat_sort"],
|
||||
"required": bool(r["cat_required"]),
|
||||
"ui_group": r["cat_ui_group"],
|
||||
}
|
||||
|
||||
for r in type_rows:
|
||||
pid = r["training_parameter_id"]
|
||||
base = merged.get(pid)
|
||||
if base is None:
|
||||
merged[pid] = {
|
||||
"training_parameter_id": pid,
|
||||
"key": r["key"],
|
||||
"name_de": r["name_de"],
|
||||
"name_en": r["name_en"],
|
||||
"description_de": r.get("description_de"),
|
||||
"description_en": r.get("description_en"),
|
||||
"param_category": r["param_category"],
|
||||
"data_type": r["data_type"],
|
||||
"unit": r["unit"],
|
||||
"validation_rules": r["validation_rules"] or {},
|
||||
"source_field": r["source_field"],
|
||||
"sort_order": r["typ_sort"] if r["typ_sort"] is not None else 0,
|
||||
"required": bool(r["typ_required"]) if r["typ_required"] is not None else False,
|
||||
"ui_group": r["typ_ui_group"],
|
||||
}
|
||||
else:
|
||||
if r["typ_sort"] is not None:
|
||||
base["sort_order"] = r["typ_sort"]
|
||||
if r["typ_required"] is not None:
|
||||
base["required"] = bool(r["typ_required"])
|
||||
if r["typ_ui_group"] is not None:
|
||||
base["ui_group"] = r["typ_ui_group"]
|
||||
|
||||
out = list(merged.values())
|
||||
out.sort(key=lambda x: (x["sort_order"], x["key"]))
|
||||
return out
|
||||
|
||||
|
||||
def resolve_activity_attribute_schema(
|
||||
cur,
|
||||
training_category: Optional[str],
|
||||
training_type_id: Optional[int],
|
||||
) -> List[Dict[str, Any]]:
|
||||
"""
|
||||
Merged parameter definitions for UI / validation (category base + type overrides/additions).
|
||||
Sorted by sort_order, then key.
|
||||
"""
|
||||
cat = _effective_training_category(cur, training_category, training_type_id)
|
||||
category_rows: List[Dict[str, Any]] = []
|
||||
type_rows: List[Dict[str, Any]] = []
|
||||
|
||||
if cat:
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT
|
||||
tcp.training_parameter_id,
|
||||
tcp.sort_order AS cat_sort,
|
||||
tcp.required AS cat_required,
|
||||
tcp.ui_group AS cat_ui_group,
|
||||
tp.key, tp.name_de, tp.name_en,
|
||||
tp.description_de, tp.description_en,
|
||||
tp.category AS param_category,
|
||||
tp.data_type, tp.unit, tp.validation_rules, tp.source_field
|
||||
FROM training_category_parameter tcp
|
||||
JOIN training_parameters tp ON tp.id = tcp.training_parameter_id
|
||||
WHERE tcp.training_category = %s AND tp.is_active = true
|
||||
""",
|
||||
(cat,),
|
||||
)
|
||||
category_rows = list(cur.fetchall())
|
||||
|
||||
if training_type_id is not None:
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT
|
||||
ttp.training_parameter_id,
|
||||
ttp.sort_order AS typ_sort,
|
||||
ttp.required AS typ_required,
|
||||
ttp.ui_group AS typ_ui_group,
|
||||
tp.key, tp.name_de, tp.name_en,
|
||||
tp.description_de, tp.description_en,
|
||||
tp.category AS param_category,
|
||||
tp.data_type, tp.unit, tp.validation_rules, tp.source_field
|
||||
FROM training_type_parameter ttp
|
||||
JOIN training_parameters tp ON tp.id = ttp.training_parameter_id
|
||||
WHERE ttp.training_type_id = %s AND tp.is_active = true
|
||||
""",
|
||||
(training_type_id,),
|
||||
)
|
||||
type_rows = list(cur.fetchall())
|
||||
|
||||
return merge_parameter_schema_rows(category_rows, type_rows)
|
||||
|
||||
|
||||
def _metric_human_labels(schema_row: Mapping[str, Any]) -> Dict[str, Any]:
|
||||
"""Bezeichnung + Kurzbeschreibung aus training_parameters (KI / Export)."""
|
||||
return {
|
||||
"name_de": schema_row.get("name_de"),
|
||||
"name_en": schema_row.get("name_en"),
|
||||
"description_de": schema_row.get("description_de"),
|
||||
"description_en": schema_row.get("description_en"),
|
||||
}
|
||||
|
||||
|
||||
def _validation_rules_dict(raw: Any) -> Dict[str, Any]:
|
||||
if isinstance(raw, dict):
|
||||
return raw
|
||||
return {}
|
||||
|
||||
|
||||
def _validate_single_value(data_type: str, value: Any, rules: Dict[str, Any]) -> None:
|
||||
if data_type == "integer":
|
||||
if not isinstance(value, int) or isinstance(value, bool):
|
||||
raise ActivitySessionMetricsError(400, f"Erwartet integer, erhalten: {type(value).__name__}")
|
||||
if "min" in rules and value < rules["min"]:
|
||||
raise ActivitySessionMetricsError(400, f"Wert unter min ({rules['min']})")
|
||||
if "max" in rules and value > rules["max"]:
|
||||
raise ActivitySessionMetricsError(400, f"Wert über max ({rules['max']})")
|
||||
elif data_type == "float":
|
||||
if isinstance(value, bool) or not isinstance(value, (int, float, Decimal)):
|
||||
raise ActivitySessionMetricsError(400, f"Erwartet Zahl, erhalten: {type(value).__name__}")
|
||||
v = float(value)
|
||||
if "min" in rules and v < float(rules["min"]):
|
||||
raise ActivitySessionMetricsError(400, f"Wert unter min ({rules['min']})")
|
||||
if "max" in rules and v > float(rules["max"]):
|
||||
raise ActivitySessionMetricsError(400, f"Wert über max ({rules['max']})")
|
||||
elif data_type == "string":
|
||||
if not isinstance(value, str):
|
||||
raise ActivitySessionMetricsError(400, f"Erwartet string, erhalten: {type(value).__name__}")
|
||||
if rules.get("not_empty") and not value.strip():
|
||||
raise ActivitySessionMetricsError(400, "Leerer String nicht erlaubt")
|
||||
if "max_length" in rules and len(value) > int(rules["max_length"]):
|
||||
raise ActivitySessionMetricsError(400, f"String zu lang (max {rules['max_length']})")
|
||||
allowed = rules.get("allowed_values")
|
||||
if allowed and value not in allowed:
|
||||
raise ActivitySessionMetricsError(400, "Wert nicht in erlaubter Menge")
|
||||
elif data_type == "boolean":
|
||||
if not isinstance(value, bool):
|
||||
raise ActivitySessionMetricsError(400, f"Erwartet boolean, erhalten: {type(value).__name__}")
|
||||
else:
|
||||
raise ActivitySessionMetricsError(400, f"Unbekannter data_type: {data_type}")
|
||||
|
||||
|
||||
def _row_value_tuple(data_type: str, value: Any) -> tuple:
|
||||
if data_type == "integer":
|
||||
return (None, int(value), None, None)
|
||||
if data_type == "float":
|
||||
return (float(value), None, None, None)
|
||||
if data_type == "string":
|
||||
return (None, None, str(value), None)
|
||||
if data_type == "boolean":
|
||||
return (None, None, None, bool(value))
|
||||
raise ValueError(data_type)
|
||||
|
||||
|
||||
def _coerce_raw_value_for_parameter(data_type: str, raw: Any) -> Any:
|
||||
"""Wert aus activity_log-Spalte in den Typ bringen, den training_parameters.data_type erwartet."""
|
||||
if data_type == "integer":
|
||||
if isinstance(raw, bool):
|
||||
raise TypeError("boolean nicht als integer erlaubt")
|
||||
if isinstance(raw, str):
|
||||
s = raw.strip().replace(",", ".")
|
||||
return int(round(float(s)))
|
||||
return int(round(float(raw)))
|
||||
if data_type == "float":
|
||||
if isinstance(raw, str):
|
||||
s = raw.strip().replace(",", ".")
|
||||
return float(s)
|
||||
return float(raw)
|
||||
if data_type == "string":
|
||||
return str(raw) if raw is not None else ""
|
||||
if data_type == "boolean":
|
||||
if isinstance(raw, bool):
|
||||
return raw
|
||||
s = str(raw).strip().lower()
|
||||
if s in ("true", "1", "t", "yes"):
|
||||
return True
|
||||
if s in ("false", "0", "f", "no", ""):
|
||||
return False
|
||||
raise TypeError(f"boolean-Koercion nicht möglich: {raw!r}")
|
||||
raise ValueError(data_type)
|
||||
|
||||
|
||||
def upsert_session_metrics_from_csv_mapped(
|
||||
cur,
|
||||
profile_id: str,
|
||||
activity_log_id: str,
|
||||
mapped: Mapping[str, Any],
|
||||
training_category: Optional[str],
|
||||
training_type_id: Optional[int],
|
||||
) -> None:
|
||||
"""
|
||||
EAV für Trainingsparameter aus CSV.
|
||||
|
||||
Es werden nur Parameter geschrieben, die in ``resolve_activity_attribute_schema`` (Kategorie +
|
||||
Trainingstyp) vorkommen. CSV-Spalten-Mappings sind import-spezifisch und definieren **nicht** das
|
||||
UI-/Auswertungs-Schema — fehlende tcp/ttp-Zuordnung bedeutet: kein EAV für diesen Key (Werte ggf.
|
||||
nur in ``activity_log``-Kernfeldern).
|
||||
|
||||
Kernfelder schreibt der Executor nach ``activity_log``; hier keine EAV-Zeilen für Registry-Keys.
|
||||
|
||||
Hat ein Parameter ``source_field`` (Semantik aus ``activity_log``), wird EAV nur dann **nicht**
|
||||
geschrieben, wenn diese Spalte nach dem Import bereits befüllt ist — sonst gäbe es doppelte
|
||||
Speicherung und der Merge würde ohnehin die Spalte bevorzugen. Ist die Spalte leer (z. B. Feld
|
||||
nur noch über EAV / Custom-Mapping, ohne Registry-Patch), schreibt der Import den Wert aus
|
||||
``mapped`` nach EAV — analog zum Lesepfad (Spalte zuerst, sonst EAV).
|
||||
"""
|
||||
cur.execute("SELECT * FROM activity_log WHERE id = %s", (activity_log_id,))
|
||||
row = cur.fetchone()
|
||||
if not row or str(row["profile_id"]) != str(profile_id):
|
||||
return
|
||||
header = dict(row)
|
||||
schema = resolve_activity_attribute_schema(cur, training_category, training_type_id)
|
||||
for spec in schema:
|
||||
pkey = spec["key"]
|
||||
if pkey not in mapped:
|
||||
continue
|
||||
raw = mapped[pkey]
|
||||
if raw is None or raw == "":
|
||||
continue
|
||||
if pkey in ACTIVITY_MODULE_REGISTRY_FIELD_KEYS:
|
||||
continue
|
||||
sf_raw = spec.get("source_field")
|
||||
if sf_raw is not None and str(sf_raw).strip():
|
||||
col = str(sf_raw).strip()
|
||||
if col in header and header[col] is not None:
|
||||
continue
|
||||
tid = spec["training_parameter_id"]
|
||||
dt = spec["data_type"]
|
||||
rules = _validation_rules_dict(spec["validation_rules"])
|
||||
try:
|
||||
coerced = _coerce_raw_value_for_parameter(dt, raw)
|
||||
_validate_single_value(dt, coerced, rules)
|
||||
except (ActivitySessionMetricsError, TypeError, ValueError) as ex:
|
||||
logger.warning("CSV EAV skipped %s: %s", pkey, ex)
|
||||
continue
|
||||
vn, vi, vt, vb = _row_value_tuple(dt, coerced)
|
||||
cur.execute(
|
||||
"""
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
) VALUES (%s, %s, %s, %s, %s, %s, NOW())
|
||||
ON CONFLICT (activity_log_id, training_parameter_id)
|
||||
DO UPDATE SET
|
||||
value_num = EXCLUDED.value_num,
|
||||
value_int = EXCLUDED.value_int,
|
||||
value_text = EXCLUDED.value_text,
|
||||
value_bool = EXCLUDED.value_bool,
|
||||
updated_at = NOW()
|
||||
""",
|
||||
(activity_log_id, tid, vn, vi, vt, vb),
|
||||
)
|
||||
|
||||
|
||||
def merge_column_backed_and_eav_metrics(
|
||||
header: Mapping[str, Any],
|
||||
schema: Sequence[Dict[str, Any]],
|
||||
eav_metrics: Sequence[Dict[str, Any]],
|
||||
) -> List[Dict[str, Any]]:
|
||||
"""
|
||||
Effektive Metrikliste **nur** für Parameter aus ``schema`` (Kategorie + Trainingstyp / tcp+ttp).
|
||||
|
||||
Kanon beim Lesen: **activity_log** schlägt EAV, sobald ein passender Spaltenwert existiert und
|
||||
koerzierbar ist — in dieser Reihenfolge:
|
||||
|
||||
1. ``source_field`` → Spalte
|
||||
2. Parameter-Key = Registry-Kernfeld (``ACTIVITY_MODULE_REGISTRY_FIELD_KEYS``) → gleichnamige Spalte
|
||||
3. EAV-primäre Keys → Legacy-Spalte laut ``ACTIVITY_LOG_LEGACY_COLUMN_FOR_EAV_PRIMARY_PARAM``
|
||||
4. sonst EAV
|
||||
|
||||
EAV-Zeilen zu Parametern, die nicht im Schema sind, werden nicht ausgegeben.
|
||||
"""
|
||||
eav_by_key = {m["key"]: m for m in eav_metrics}
|
||||
merged: List[Dict[str, Any]] = []
|
||||
keys_handled: set[str] = set()
|
||||
|
||||
for s in schema:
|
||||
k = s["key"]
|
||||
tid = s["training_parameter_id"]
|
||||
dt = s["data_type"]
|
||||
unit = s.get("unit")
|
||||
sf = s.get("source_field")
|
||||
|
||||
used_column = False
|
||||
if sf and isinstance(sf, str) and str(sf).strip():
|
||||
col = str(sf).strip()
|
||||
if col in header and header[col] is not None:
|
||||
try:
|
||||
val = _coerce_raw_value_for_parameter(dt, header[col])
|
||||
merged.append(
|
||||
{
|
||||
"training_parameter_id": tid,
|
||||
"key": k,
|
||||
"data_type": dt,
|
||||
"unit": unit,
|
||||
"value": val,
|
||||
**_metric_human_labels(s),
|
||||
}
|
||||
)
|
||||
used_column = True
|
||||
keys_handled.add(k)
|
||||
except (TypeError, ValueError):
|
||||
pass
|
||||
|
||||
if used_column:
|
||||
continue
|
||||
|
||||
if k in ACTIVITY_MODULE_REGISTRY_FIELD_KEYS and k in header and header[k] is not None:
|
||||
try:
|
||||
val = _coerce_raw_value_for_parameter(dt, header[k])
|
||||
merged.append(
|
||||
{
|
||||
"training_parameter_id": tid,
|
||||
"key": k,
|
||||
"data_type": dt,
|
||||
"unit": unit,
|
||||
"value": val,
|
||||
**_metric_human_labels(s),
|
||||
}
|
||||
)
|
||||
keys_handled.add(k)
|
||||
continue
|
||||
except (TypeError, ValueError):
|
||||
pass
|
||||
|
||||
legacy_col = ACTIVITY_LOG_LEGACY_COLUMN_FOR_EAV_PRIMARY_PARAM.get(k)
|
||||
if legacy_col and legacy_col in header and header[legacy_col] is not None:
|
||||
try:
|
||||
val = _coerce_raw_value_for_parameter(dt, header[legacy_col])
|
||||
merged.append(
|
||||
{
|
||||
"training_parameter_id": tid,
|
||||
"key": k,
|
||||
"data_type": dt,
|
||||
"unit": unit,
|
||||
"value": val,
|
||||
**_metric_human_labels(s),
|
||||
}
|
||||
)
|
||||
keys_handled.add(k)
|
||||
continue
|
||||
except (TypeError, ValueError):
|
||||
pass
|
||||
|
||||
if k in eav_by_key:
|
||||
row = dict(eav_by_key[k])
|
||||
row.update(_metric_human_labels(s))
|
||||
merged.append(row)
|
||||
keys_handled.add(k)
|
||||
|
||||
merged.sort(key=lambda x: x["key"])
|
||||
return merged
|
||||
|
||||
|
||||
def sync_column_backed_session_metrics(cur, profile_id: str, activity_log_id: str) -> None:
|
||||
"""
|
||||
[Veraltet / nicht mehr in Schreibpfaden aufgerufen]
|
||||
|
||||
Früher: EAV spiegelte activity_log-Spalten für Parameter mit source_field.
|
||||
Kanon: Spaltenwerte werden bei merge_column_backed_and_eav_metrics beim Lesen berücksichtigt; keine
|
||||
doppelte Speicherung. Funktion bleibt für optionale Admin-/Reparatur-Skripte.
|
||||
"""
|
||||
cur.execute("SELECT * FROM activity_log WHERE id = %s", (activity_log_id,))
|
||||
row = cur.fetchone()
|
||||
if not row or str(row["profile_id"]) != str(profile_id):
|
||||
return
|
||||
header = dict(row)
|
||||
schema = resolve_activity_attribute_schema(
|
||||
cur, header.get("training_category"), header.get("training_type_id")
|
||||
)
|
||||
for spec in schema:
|
||||
sf = spec.get("source_field")
|
||||
if sf is None or (isinstance(sf, str) and not str(sf).strip()):
|
||||
continue
|
||||
col = str(sf).strip()
|
||||
if col not in header:
|
||||
continue
|
||||
raw = header[col]
|
||||
tid = spec["training_parameter_id"]
|
||||
dt = spec["data_type"]
|
||||
rules = _validation_rules_dict(spec["validation_rules"])
|
||||
|
||||
if raw is None:
|
||||
cur.execute(
|
||||
"""
|
||||
DELETE FROM activity_session_metrics
|
||||
WHERE activity_log_id = %s AND training_parameter_id = %s
|
||||
""",
|
||||
(activity_log_id, tid),
|
||||
)
|
||||
continue
|
||||
|
||||
try:
|
||||
coerced = _coerce_raw_value_for_parameter(dt, raw)
|
||||
_validate_single_value(dt, coerced, rules)
|
||||
except (ActivitySessionMetricsError, TypeError, ValueError) as ex:
|
||||
logger.warning(
|
||||
"sync_column_backed_session_metrics: überspringe %s (Spalte %s): %s",
|
||||
spec.get("key"),
|
||||
col,
|
||||
ex,
|
||||
)
|
||||
continue
|
||||
|
||||
vn, vi, vt, vb = _row_value_tuple(dt, coerced)
|
||||
cur.execute(
|
||||
"""
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
) VALUES (%s, %s, %s, %s, %s, %s, NOW())
|
||||
ON CONFLICT (activity_log_id, training_parameter_id)
|
||||
DO UPDATE SET
|
||||
value_num = EXCLUDED.value_num,
|
||||
value_int = EXCLUDED.value_int,
|
||||
value_text = EXCLUDED.value_text,
|
||||
value_bool = EXCLUDED.value_bool,
|
||||
updated_at = NOW()
|
||||
""",
|
||||
(activity_log_id, tid, vn, vi, vt, vb),
|
||||
)
|
||||
|
||||
|
||||
def fetch_activity_session_metrics(cur, activity_log_id: str) -> List[Dict[str, Any]]:
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT
|
||||
m.id,
|
||||
m.activity_log_id,
|
||||
m.training_parameter_id,
|
||||
m.value_num,
|
||||
m.value_int,
|
||||
m.value_text,
|
||||
m.value_bool,
|
||||
tp.key,
|
||||
tp.data_type,
|
||||
tp.unit
|
||||
FROM activity_session_metrics m
|
||||
JOIN training_parameters tp ON tp.id = m.training_parameter_id
|
||||
WHERE m.activity_log_id = %s
|
||||
ORDER BY tp.key
|
||||
""",
|
||||
(activity_log_id,),
|
||||
)
|
||||
rows = cur.fetchall()
|
||||
out: List[Dict[str, Any]] = []
|
||||
for r in rows:
|
||||
dt = r["data_type"]
|
||||
if dt == "integer":
|
||||
val = int(r["value_int"]) if r["value_int"] is not None else None
|
||||
elif dt == "float":
|
||||
val = float(r["value_num"]) if r["value_num"] is not None else None
|
||||
elif dt == "string":
|
||||
val = r["value_text"]
|
||||
else:
|
||||
val = r["value_bool"]
|
||||
out.append(
|
||||
{
|
||||
"training_parameter_id": r["training_parameter_id"],
|
||||
"key": r["key"],
|
||||
"data_type": dt,
|
||||
"unit": r["unit"],
|
||||
"value": val,
|
||||
}
|
||||
)
|
||||
return out
|
||||
|
||||
|
||||
def replace_activity_session_metrics(
|
||||
cur,
|
||||
profile_id: str,
|
||||
activity_log_id: str,
|
||||
metrics: Sequence[Dict[str, Any]],
|
||||
) -> List[Dict[str, Any]]:
|
||||
"""
|
||||
Full replace of EAV rows for this session. metrics: [{ "parameter_key": str, "value": ... }, ...]
|
||||
"""
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT id, profile_id, training_category, training_type_id
|
||||
FROM activity_log WHERE id = %s
|
||||
""",
|
||||
(activity_log_id,),
|
||||
)
|
||||
row = cur.fetchone()
|
||||
if not row or str(row["profile_id"]) != str(profile_id):
|
||||
raise ActivitySessionMetricsError(404, "Aktivität nicht gefunden")
|
||||
|
||||
schema = resolve_activity_attribute_schema(
|
||||
cur, row.get("training_category"), row.get("training_type_id")
|
||||
)
|
||||
by_key = {s["key"]: s for s in schema}
|
||||
payload_by_key: Dict[str, Dict[str, Any]] = {}
|
||||
for item in metrics:
|
||||
raw_k = item.get("parameter_key")
|
||||
if raw_k is None or not str(raw_k).strip():
|
||||
raise ActivitySessionMetricsError(400, "parameter_key fehlt")
|
||||
k = str(raw_k).strip()
|
||||
if k not in by_key:
|
||||
raise ActivitySessionMetricsError(400, f"Unbekannter oder nicht zugewiesener Parameter: {k}")
|
||||
payload_by_key[k] = item
|
||||
|
||||
for s in schema:
|
||||
if not s["required"]:
|
||||
continue
|
||||
itk = s["key"]
|
||||
hit = payload_by_key.get(itk)
|
||||
if hit is None or hit.get("value") is None:
|
||||
raise ActivitySessionMetricsError(400, f"Pflichtfeld fehlt: {itk}")
|
||||
|
||||
cur.execute(
|
||||
"DELETE FROM activity_session_metrics WHERE activity_log_id = %s",
|
||||
(activity_log_id,),
|
||||
)
|
||||
|
||||
for item in metrics:
|
||||
k = str(item["parameter_key"]).strip()
|
||||
spec = by_key[k]
|
||||
val = item.get("value")
|
||||
if val is None:
|
||||
if spec["required"]:
|
||||
raise ActivitySessionMetricsError(400, f"Pflichtfeld fehlt: {k}")
|
||||
continue
|
||||
rules = _validation_rules_dict(spec["validation_rules"])
|
||||
_validate_single_value(spec["data_type"], val, rules)
|
||||
vn, vi, vt, vb = _row_value_tuple(spec["data_type"], val)
|
||||
cur.execute(
|
||||
"""
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
) VALUES (%s, %s, %s, %s, %s, %s, NOW())
|
||||
""",
|
||||
(activity_log_id, spec["training_parameter_id"], vn, vi, vt, vb),
|
||||
)
|
||||
|
||||
# Kein sync_column_backed nach PUT /metrics: der Request ist maßgeblich für EAV. Ein Spalten-Sync würde
|
||||
# Werte aus nicht mitgeschriebenen activity_log-Spalten wieder verwerfen.
|
||||
|
||||
return fetch_activity_session_metrics(cur, activity_log_id)
|
||||
|
||||
|
||||
def get_activity_session_logical_unit(
|
||||
cur,
|
||||
profile_id: str,
|
||||
activity_log_id: str,
|
||||
*,
|
||||
use_form_training_context: bool = False,
|
||||
form_training_category: Optional[str] = None,
|
||||
form_training_type_id: Optional[int] = None,
|
||||
) -> Dict[str, Any]:
|
||||
cur.execute("SELECT * FROM activity_log WHERE id = %s", (activity_log_id,))
|
||||
row = cur.fetchone()
|
||||
if not row or str(row["profile_id"]) != str(profile_id):
|
||||
raise ActivitySessionMetricsError(404, "Aktivität nicht gefunden")
|
||||
|
||||
header = dict(row)
|
||||
if use_form_training_context:
|
||||
cat = form_training_category
|
||||
if isinstance(cat, str):
|
||||
cat = cat.strip() or None
|
||||
tid = form_training_type_id
|
||||
else:
|
||||
cat = header.get("training_category")
|
||||
tid = header.get("training_type_id")
|
||||
if tid is not None:
|
||||
try:
|
||||
tid = int(tid)
|
||||
except (TypeError, ValueError):
|
||||
tid = None
|
||||
schema = resolve_activity_attribute_schema(cur, cat, tid)
|
||||
metrics = fetch_activity_session_metrics(cur, activity_log_id)
|
||||
merged_metrics = merge_column_backed_and_eav_metrics(header, schema, metrics)
|
||||
return {
|
||||
"header": header,
|
||||
"schema": schema,
|
||||
"metrics": merged_metrics,
|
||||
}
|
||||
|
||||
|
||||
def enrich_sessions_with_metrics(cur, sessions: List[Dict[str, Any]]) -> None:
|
||||
"""
|
||||
Mutates each session dict: adds key 'session_metrics' (list).
|
||||
|
||||
Kombiniert EAV mit activity_log-Spalten für Parameter mit source_field (kanonisch: Spalte),
|
||||
analog zu get_activity_session_logical_unit – ohne doppelte EAV-Speicherung beim Import.
|
||||
"""
|
||||
if not sessions:
|
||||
return
|
||||
ids = [str(s["id"]) for s in sessions if s.get("id")]
|
||||
if not ids:
|
||||
return
|
||||
ph = ",".join(["%s"] * len(ids))
|
||||
|
||||
cur.execute(
|
||||
f"SELECT * FROM activity_log WHERE id IN ({ph})",
|
||||
ids,
|
||||
)
|
||||
headers_by_id: Dict[str, Dict[str, Any]] = {}
|
||||
for r in cur.fetchall():
|
||||
h = dict(r)
|
||||
headers_by_id[str(h["id"])] = h
|
||||
|
||||
cur.execute(
|
||||
f"""
|
||||
SELECT
|
||||
m.activity_log_id,
|
||||
m.training_parameter_id,
|
||||
tp.key,
|
||||
tp.data_type,
|
||||
tp.unit,
|
||||
m.value_num,
|
||||
m.value_int,
|
||||
m.value_text,
|
||||
m.value_bool
|
||||
FROM activity_session_metrics m
|
||||
JOIN training_parameters tp ON tp.id = m.training_parameter_id
|
||||
WHERE m.activity_log_id IN ({ph})
|
||||
ORDER BY m.activity_log_id, tp.key
|
||||
""",
|
||||
ids,
|
||||
)
|
||||
by_act: Dict[str, List[Dict[str, Any]]] = {}
|
||||
for r in cur.fetchall():
|
||||
aid = str(r["activity_log_id"])
|
||||
dt = r["data_type"]
|
||||
if dt == "integer":
|
||||
val = int(r["value_int"]) if r["value_int"] is not None else None
|
||||
elif dt == "float":
|
||||
val = float(r["value_num"]) if r["value_num"] is not None else None
|
||||
elif dt == "string":
|
||||
val = r["value_text"]
|
||||
else:
|
||||
val = r["value_bool"]
|
||||
by_act.setdefault(aid, []).append(
|
||||
{
|
||||
"training_parameter_id": r["training_parameter_id"],
|
||||
"key": r["key"],
|
||||
"data_type": dt,
|
||||
"unit": r["unit"],
|
||||
"value": val,
|
||||
}
|
||||
)
|
||||
|
||||
schema_cache: Dict[tuple[Any, Any], List[Dict[str, Any]]] = {}
|
||||
|
||||
def _schema(cat: Any, tid: Any) -> List[Dict[str, Any]]:
|
||||
cache_key = (cat, tid)
|
||||
if cache_key not in schema_cache:
|
||||
schema_cache[cache_key] = resolve_activity_attribute_schema(cur, cat, tid)
|
||||
return schema_cache[cache_key]
|
||||
|
||||
for s in sessions:
|
||||
aid = str(s.get("id"))
|
||||
header = headers_by_id.get(aid)
|
||||
if not header:
|
||||
s["session_metrics"] = []
|
||||
continue
|
||||
schema = _schema(header.get("training_category"), header.get("training_type_id"))
|
||||
eav_list = by_act.get(aid, [])
|
||||
merged = merge_column_backed_and_eav_metrics(header, schema, eav_list)
|
||||
s["session_metrics"] = [
|
||||
{
|
||||
"key": m["key"],
|
||||
"data_type": m["data_type"],
|
||||
"unit": m["unit"],
|
||||
"value": m["value"],
|
||||
"name_de": m.get("name_de"),
|
||||
"name_en": m.get("name_en"),
|
||||
"description_de": m.get("description_de"),
|
||||
"description_en": m.get("description_en"),
|
||||
}
|
||||
for m in merged
|
||||
]
|
||||
@@ -0,0 +1,30 @@
|
||||
"""
|
||||
Einheitliche Startzeit-Normalisierung für Aktivität (CSV, Legacy-Import, Dedupe).
|
||||
|
||||
Anbieter-agnostisch: beliebige ISO-/Export-Strings über dateutil.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from datetime import time as dt_time
|
||||
from typing import Optional
|
||||
|
||||
from dateutil import parser as du_parser
|
||||
|
||||
|
||||
def normalize_activity_start(start_raw: str) -> tuple[str, Optional[dt_time]]:
|
||||
"""
|
||||
Roh-String „Start“ aus Exporten → (YYYY-MM-DD, TIME ohne μs) für DB Dedupe/INSERT.
|
||||
|
||||
Leerer Input → ("", None). Fallback bei Parse-Fehler: erstes Datum aus ersten 10 Zeichen.
|
||||
"""
|
||||
s = (start_raw or "").strip()
|
||||
if not s:
|
||||
return "", None
|
||||
try:
|
||||
parsed = du_parser.parse(s, dayfirst=False)
|
||||
t = parsed.time().replace(microsecond=0)
|
||||
return parsed.date().isoformat(), t
|
||||
except (ValueError, TypeError, OverflowError):
|
||||
if len(s) >= 10:
|
||||
return s[:10], None
|
||||
return "", None
|
||||
@@ -5,6 +5,9 @@ Provides structured data for body composition and measurements.
|
||||
|
||||
Functions:
|
||||
- get_latest_weight_data(): Most recent weight entry
|
||||
- get_bmi_data(): BMI from latest weight + profile height
|
||||
- get_profile_goal_weight_data(): Zielgewicht (Profilfeld)
|
||||
- get_profile_goal_bf_pct_data(): Ziel-KFA % (Profilfeld)
|
||||
- get_weight_trend_data(): Weight trend with slope and direction
|
||||
- get_body_composition_data(): Body fat percentage and lean mass
|
||||
- get_circumference_summary_data(): Latest circumference measurements
|
||||
@@ -68,6 +71,105 @@ def get_latest_weight_data(
|
||||
}
|
||||
|
||||
|
||||
def get_bmi_data(profile_id: str) -> Dict:
|
||||
"""
|
||||
BMI from latest weight_log entry and profiles.height (cm).
|
||||
|
||||
Returns:
|
||||
{
|
||||
"bmi": float | None,
|
||||
"weight_kg": float | None,
|
||||
"height_cm": float | None,
|
||||
"confidence": "high" | "insufficient",
|
||||
}
|
||||
"""
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT pr.height,
|
||||
(SELECT wl.weight FROM weight_log wl
|
||||
WHERE wl.profile_id = pr.id
|
||||
ORDER BY wl.date DESC
|
||||
LIMIT 1) AS weight
|
||||
FROM profiles pr
|
||||
WHERE pr.id = %s
|
||||
""",
|
||||
(profile_id,),
|
||||
)
|
||||
row = cur.fetchone()
|
||||
if not row:
|
||||
return {
|
||||
"bmi": None,
|
||||
"weight_kg": None,
|
||||
"height_cm": None,
|
||||
"confidence": "insufficient",
|
||||
}
|
||||
|
||||
height_cm = row["height"]
|
||||
weight = row["weight"]
|
||||
if height_cm is None or weight is None:
|
||||
return {
|
||||
"bmi": None,
|
||||
"weight_kg": safe_float(weight) if weight is not None else None,
|
||||
"height_cm": safe_float(height_cm) if height_cm is not None else None,
|
||||
"confidence": "insufficient",
|
||||
}
|
||||
|
||||
h = safe_float(height_cm)
|
||||
w = safe_float(weight)
|
||||
if h <= 0:
|
||||
return {
|
||||
"bmi": None,
|
||||
"weight_kg": w,
|
||||
"height_cm": h,
|
||||
"confidence": "insufficient",
|
||||
}
|
||||
|
||||
height_m = h / 100.0
|
||||
bmi = w / (height_m ** 2)
|
||||
return {
|
||||
"bmi": bmi,
|
||||
"weight_kg": w,
|
||||
"height_cm": h,
|
||||
"confidence": "high",
|
||||
}
|
||||
|
||||
|
||||
def get_profile_goal_weight_data(profile_id: str) -> Dict:
|
||||
"""Strategisches Zielgewicht aus profiles.goal_weight (kg), nicht goals-Tabelle."""
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute(
|
||||
"SELECT goal_weight FROM profiles WHERE id=%s",
|
||||
(profile_id,),
|
||||
)
|
||||
row = cur.fetchone()
|
||||
if not row or row.get("goal_weight") is None:
|
||||
return {"goal_weight_kg": None, "confidence": "insufficient"}
|
||||
return {
|
||||
"goal_weight_kg": safe_float(row["goal_weight"]),
|
||||
"confidence": "high",
|
||||
}
|
||||
|
||||
|
||||
def get_profile_goal_bf_pct_data(profile_id: str) -> Dict:
|
||||
"""Strategisches Ziel-KFA aus profiles.goal_bf_pct (%), nicht goals-Tabelle."""
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute(
|
||||
"SELECT goal_bf_pct FROM profiles WHERE id=%s",
|
||||
(profile_id,),
|
||||
)
|
||||
row = cur.fetchone()
|
||||
if not row or row.get("goal_bf_pct") is None:
|
||||
return {"goal_bf_pct": None, "confidence": "insufficient"}
|
||||
return {
|
||||
"goal_bf_pct": safe_float(row["goal_bf_pct"]),
|
||||
"confidence": "high",
|
||||
}
|
||||
|
||||
|
||||
def get_weight_trend_data(
|
||||
profile_id: str,
|
||||
days: int = 28
|
||||
@@ -89,7 +191,8 @@ def get_weight_trend_data(
|
||||
"confidence": str,
|
||||
"days_analyzed": int,
|
||||
"first_date": date,
|
||||
"last_date": date
|
||||
"last_date": date,
|
||||
"series": [{"date": date, "weight": float}, ...], # für Charts ohne zweites Query
|
||||
}
|
||||
|
||||
Confidence Rules:
|
||||
@@ -127,7 +230,8 @@ def get_weight_trend_data(
|
||||
"delta": 0.0,
|
||||
"direction": "unknown",
|
||||
"first_date": None,
|
||||
"last_date": None
|
||||
"last_date": None,
|
||||
"series": [],
|
||||
}
|
||||
|
||||
# Extract values
|
||||
@@ -152,7 +256,11 @@ def get_weight_trend_data(
|
||||
"confidence": confidence,
|
||||
"days_analyzed": days,
|
||||
"first_date": rows[0]['date'],
|
||||
"last_date": rows[-1]['date']
|
||||
"last_date": rows[-1]['date'],
|
||||
"series": [
|
||||
{"date": r["date"], "weight": safe_float(r["weight"])}
|
||||
for r in rows
|
||||
],
|
||||
}
|
||||
|
||||
|
||||
@@ -337,12 +445,16 @@ def calculate_weight_7d_median(profile_id: str) -> Optional[float]:
|
||||
ORDER BY date DESC
|
||||
""", (profile_id,))
|
||||
|
||||
weights = [row['weight'] for row in cur.fetchall()]
|
||||
weights = [
|
||||
safe_float(row['weight'])
|
||||
for row in cur.fetchall()
|
||||
if row['weight'] is not None
|
||||
]
|
||||
|
||||
if len(weights) < 4: # Need at least 4 measurements
|
||||
return None
|
||||
|
||||
return round(statistics.median(weights), 1)
|
||||
return round(float(statistics.median(weights)), 1)
|
||||
|
||||
|
||||
def calculate_weight_28d_slope(profile_id: str) -> Optional[float]:
|
||||
@@ -370,7 +482,11 @@ def _calculate_weight_slope(profile_id: str, days: int) -> Optional[float]:
|
||||
ORDER BY date
|
||||
""", (profile_id, days))
|
||||
|
||||
data = [(row['date'], row['weight']) for row in cur.fetchall()]
|
||||
data = [
|
||||
(row['date'], safe_float(row['weight']))
|
||||
for row in cur.fetchall()
|
||||
if row['weight'] is not None
|
||||
]
|
||||
|
||||
# Need minimum data points based on period
|
||||
min_points = max(18, int(days * 0.6)) # 60% coverage
|
||||
@@ -380,21 +496,21 @@ def _calculate_weight_slope(profile_id: str, days: int) -> Optional[float]:
|
||||
# Convert dates to days since start
|
||||
start_date = data[0][0]
|
||||
x_values = [(date - start_date).days for date, _ in data]
|
||||
y_values = [weight for _, weight in data]
|
||||
y_values = [w for _, w in data]
|
||||
|
||||
# Linear regression
|
||||
# Linear regression (alles float: PostgreSQL numeric → Decimal in Python)
|
||||
n = len(data)
|
||||
x_mean = sum(x_values) / n
|
||||
y_mean = sum(y_values) / n
|
||||
x_mean = float(sum(x_values)) / n
|
||||
y_mean = float(sum(y_values)) / n
|
||||
|
||||
numerator = sum((x - x_mean) * (y - y_mean) for x, y in zip(x_values, y_values))
|
||||
denominator = sum((x - x_mean) ** 2 for x in x_values)
|
||||
numerator = sum(float(x - x_mean) * float(y - y_mean) for x, y in zip(x_values, y_values))
|
||||
denominator = float(sum((x - x_mean) ** 2 for x in x_values))
|
||||
|
||||
if denominator == 0:
|
||||
return None
|
||||
|
||||
slope = numerator / denominator
|
||||
return round(slope, 4) # kg/day
|
||||
return round(float(slope), 4) # kg/day
|
||||
|
||||
|
||||
def calculate_goal_projection_date(profile_id: str, goal_id: str) -> Optional[str]:
|
||||
@@ -486,19 +602,24 @@ def _calculate_body_composition_change(profile_id: str, metric: str, days: int)
|
||||
recent = data[0]
|
||||
oldest = data[-1]
|
||||
|
||||
# Calculate FM and LBM
|
||||
recent_fm = recent['weight'] * (recent['bf_pct'] / 100)
|
||||
recent_lbm = recent['weight'] - recent_fm
|
||||
# Calculate FM and LBM (DB numeric → Decimal; für Regression/Scores nur float)
|
||||
rw = float(safe_float(recent['weight']) or 0)
|
||||
ob = float(safe_float(recent['bf_pct']) or 0)
|
||||
ow = float(safe_float(oldest['weight']) or 0)
|
||||
obf = float(safe_float(oldest['bf_pct']) or 0)
|
||||
|
||||
oldest_fm = oldest['weight'] * (oldest['bf_pct'] / 100)
|
||||
oldest_lbm = oldest['weight'] - oldest_fm
|
||||
recent_fm = rw * (ob / 100)
|
||||
recent_lbm = rw - recent_fm
|
||||
|
||||
oldest_fm = ow * (obf / 100)
|
||||
oldest_lbm = ow - oldest_fm
|
||||
|
||||
if metric == 'fm':
|
||||
change = recent_fm - oldest_fm
|
||||
else:
|
||||
change = recent_lbm - oldest_lbm
|
||||
|
||||
return round(change, 2)
|
||||
return round(float(change), 2)
|
||||
|
||||
|
||||
# ── Circumference Calculations ──────────────────────────────────────────────
|
||||
@@ -623,9 +744,9 @@ def calculate_body_progress_score(profile_id: str, focus_weights: Optional[Dict]
|
||||
from data_layer.scores import get_user_focus_weights
|
||||
focus_weights = get_user_focus_weights(profile_id)
|
||||
|
||||
weight_loss = focus_weights.get('weight_loss', 0)
|
||||
muscle_gain = focus_weights.get('muscle_gain', 0)
|
||||
body_recomp = focus_weights.get('body_recomposition', 0)
|
||||
weight_loss = float(focus_weights.get('weight_loss', 0) or 0)
|
||||
muscle_gain = float(focus_weights.get('muscle_gain', 0) or 0)
|
||||
body_recomp = float(focus_weights.get('body_recomposition', 0) or 0)
|
||||
|
||||
total_body_weight = weight_loss + muscle_gain + body_recomp
|
||||
|
||||
@@ -652,8 +773,8 @@ def calculate_body_progress_score(profile_id: str, focus_weights: Optional[Dict]
|
||||
if not components:
|
||||
return None
|
||||
|
||||
total_score = sum(score * weight for _, score, weight in components)
|
||||
total_weight = sum(weight for _, _, weight in components)
|
||||
total_score = sum(float(score) * float(weight) for _, score, weight in components)
|
||||
total_weight = sum(float(weight) for _, _, weight in components)
|
||||
|
||||
return int(total_score / total_weight)
|
||||
|
||||
|
||||
@@ -25,6 +25,88 @@ from datetime import datetime, timedelta, date
|
||||
from db import get_db, get_cursor, r2d
|
||||
from data_layer.utils import calculate_confidence, safe_float, safe_int
|
||||
|
||||
# Fallback TDEE (kcal/day) when demographics for Mifflin–St Jeor are incomplete.
|
||||
TDEE_KCAL_PER_KG_BODYWEIGHT = 32.5
|
||||
# PAL applied to MSJ BMR when height, sex, dob and weight are available (moderate activity).
|
||||
TDEE_PAL_MODERATE = 1.55
|
||||
|
||||
|
||||
def _age_years_from_dob(dob) -> Optional[int]:
|
||||
if dob is None:
|
||||
return None
|
||||
try:
|
||||
if isinstance(dob, str):
|
||||
birth = datetime.strptime(dob[:10], "%Y-%m-%d").date()
|
||||
else:
|
||||
birth = dob
|
||||
today = date.today()
|
||||
return today.year - birth.year - ((today.month, today.day) < (birth.month, birth.day))
|
||||
except Exception:
|
||||
return None
|
||||
|
||||
|
||||
def _mifflin_st_jeor_bmr_kcal(
|
||||
weight_kg: float, height_cm: float, age_years: int, sex_is_male: bool
|
||||
) -> float:
|
||||
if sex_is_male:
|
||||
return 10.0 * weight_kg + 6.25 * height_cm - 5.0 * age_years + 5.0
|
||||
return 10.0 * weight_kg + 6.25 * height_cm - 5.0 * age_years - 161.0
|
||||
|
||||
|
||||
def estimate_tdee_kcal_from_latest_weight(profile_id: str) -> Optional[float]:
|
||||
"""
|
||||
Estimated TDEE (kcal/day).
|
||||
|
||||
Primary: Mifflin–St Jeor BMR × TDEE_PAL_MODERATE when latest weight plus
|
||||
profiles.height, profiles.sex, profiles.dob are usable.
|
||||
|
||||
Fallback: latest weight (kg) × TDEE_KCAL_PER_KG_BODYWEIGHT (legacy heuristic).
|
||||
|
||||
Returns None if no weight on record.
|
||||
"""
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute(
|
||||
"""SELECT weight FROM weight_log
|
||||
WHERE profile_id=%s ORDER BY date DESC LIMIT 1""",
|
||||
(profile_id,),
|
||||
)
|
||||
wrow = cur.fetchone()
|
||||
if not wrow or wrow["weight"] is None:
|
||||
return None
|
||||
weight_kg = float(wrow["weight"])
|
||||
|
||||
cur.execute(
|
||||
"SELECT height, sex, dob FROM profiles WHERE id=%s",
|
||||
(profile_id,),
|
||||
)
|
||||
prow = cur.fetchone()
|
||||
|
||||
if prow and prow.get("height") and prow.get("sex") is not None and prow.get("dob"):
|
||||
height_cm = float(prow["height"])
|
||||
age = _age_years_from_dob(prow["dob"])
|
||||
if age is not None and 10 < age < 120 and height_cm > 50:
|
||||
sex_raw = str(prow["sex"]).strip().lower()
|
||||
sex_is_male = sex_raw in ("m", "male", "männlich", "mann")
|
||||
bmr = _mifflin_st_jeor_bmr_kcal(weight_kg, height_cm, age, sex_is_male)
|
||||
if bmr > 400:
|
||||
return bmr * TDEE_PAL_MODERATE
|
||||
|
||||
return weight_kg * TDEE_KCAL_PER_KG_BODYWEIGHT
|
||||
|
||||
|
||||
def _get_profile_goal_mode(profile_id: str) -> str:
|
||||
"""Strategic goal_mode from profiles (Phase 0a); defaults to health."""
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute("SELECT goal_mode FROM profiles WHERE id=%s", (profile_id,))
|
||||
row = cur.fetchone()
|
||||
if row and row.get("goal_mode"):
|
||||
g = str(row["goal_mode"]).strip().lower()
|
||||
if g:
|
||||
return g
|
||||
return "health"
|
||||
|
||||
|
||||
def get_nutrition_average_data(
|
||||
profile_id: str,
|
||||
@@ -56,20 +138,29 @@ def get_nutrition_average_data(
|
||||
cur = get_cursor(conn)
|
||||
cutoff = (datetime.now() - timedelta(days=days)).strftime('%Y-%m-%d')
|
||||
|
||||
# Mean over calendar days (per-day sums), not over raw log rows.
|
||||
cur.execute(
|
||||
"""SELECT
|
||||
AVG(kcal) as kcal_avg,
|
||||
AVG(protein_g) as protein_avg,
|
||||
AVG(carbs_g) as carbs_avg,
|
||||
AVG(fat_g) as fat_avg,
|
||||
COUNT(*) as data_points
|
||||
FROM nutrition_log
|
||||
WHERE profile_id=%s AND date >= %s""",
|
||||
(profile_id, cutoff)
|
||||
AVG(daily_kcal) AS kcal_avg,
|
||||
AVG(daily_protein) AS protein_avg,
|
||||
AVG(daily_carbs) AS carbs_avg,
|
||||
AVG(daily_fat) AS fat_avg,
|
||||
COUNT(*)::int AS day_count
|
||||
FROM (
|
||||
SELECT date,
|
||||
COALESCE(SUM(kcal), 0)::float AS daily_kcal,
|
||||
COALESCE(SUM(protein_g), 0)::float AS daily_protein,
|
||||
COALESCE(SUM(carbs_g), 0)::float AS daily_carbs,
|
||||
COALESCE(SUM(fat_g), 0)::float AS daily_fat
|
||||
FROM nutrition_log
|
||||
WHERE profile_id=%s AND date >= %s
|
||||
GROUP BY date
|
||||
) AS daily""",
|
||||
(profile_id, cutoff),
|
||||
)
|
||||
row = cur.fetchone()
|
||||
|
||||
if not row or row['data_points'] == 0:
|
||||
if not row or row["day_count"] == 0:
|
||||
return {
|
||||
"kcal_avg": 0.0,
|
||||
"protein_avg": 0.0,
|
||||
@@ -80,7 +171,7 @@ def get_nutrition_average_data(
|
||||
"days_analyzed": days
|
||||
}
|
||||
|
||||
data_points = row['data_points']
|
||||
data_points = row["day_count"]
|
||||
confidence = calculate_confidence(data_points, days, "general")
|
||||
|
||||
return {
|
||||
@@ -190,79 +281,73 @@ def get_energy_balance_data(
|
||||
days: int = 7
|
||||
) -> Dict:
|
||||
"""
|
||||
Calculate energy balance (intake - estimated expenditure).
|
||||
Energy balance (intake - estimated expenditure), kcal/day.
|
||||
|
||||
Note: This is a simplified calculation.
|
||||
For accurate TDEE, use profile-based calculations.
|
||||
|
||||
Args:
|
||||
profile_id: User profile ID
|
||||
days: Analysis window (default 7)
|
||||
|
||||
Returns:
|
||||
{
|
||||
"energy_balance": float, # kcal/day (negative = deficit)
|
||||
"avg_intake": float,
|
||||
"estimated_tdee": float,
|
||||
"status": str, # "deficit" | "surplus" | "maintenance"
|
||||
"confidence": str,
|
||||
"days_analyzed": int,
|
||||
"data_points": int
|
||||
}
|
||||
Intake: mean of daily total kcal (sum per calendar day).
|
||||
TDEE: estimate_tdee_kcal_from_latest_weight (MSJ × PAL oder kg-Fallback).
|
||||
"""
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cutoff = (datetime.now() - timedelta(days=days)).strftime('%Y-%m-%d')
|
||||
|
||||
# Get average intake
|
||||
cur.execute(
|
||||
"""SELECT AVG(kcal) as avg_kcal, COUNT(*) as cnt
|
||||
"""SELECT date, SUM(kcal)::float AS daily_kcal
|
||||
FROM nutrition_log
|
||||
WHERE profile_id=%s AND date >= %s AND kcal IS NOT NULL""",
|
||||
(profile_id, cutoff)
|
||||
WHERE profile_id=%s AND date >= %s AND kcal IS NOT NULL
|
||||
GROUP BY date
|
||||
ORDER BY date""",
|
||||
(profile_id, cutoff),
|
||||
)
|
||||
row = cur.fetchone()
|
||||
|
||||
if not row or row['cnt'] == 0:
|
||||
return {
|
||||
"energy_balance": 0.0,
|
||||
"avg_intake": 0.0,
|
||||
"estimated_tdee": 0.0,
|
||||
"status": "unknown",
|
||||
"confidence": "insufficient",
|
||||
"days_analyzed": days,
|
||||
"data_points": 0
|
||||
}
|
||||
|
||||
avg_intake = safe_float(row['avg_kcal'])
|
||||
data_points = row['cnt']
|
||||
|
||||
# Simple TDEE estimation (this should be improved with profile data)
|
||||
# For now, use a rough estimate: 2500 kcal for average adult
|
||||
estimated_tdee = 2500.0 # TODO: Calculate from profile (weight, height, age, activity)
|
||||
|
||||
energy_balance = avg_intake - estimated_tdee
|
||||
|
||||
# Determine status
|
||||
if energy_balance < -200:
|
||||
status = "deficit"
|
||||
elif energy_balance > 200:
|
||||
status = "surplus"
|
||||
else:
|
||||
status = "maintenance"
|
||||
|
||||
confidence = calculate_confidence(data_points, days, "general")
|
||||
daily_rows = cur.fetchall()
|
||||
|
||||
if not daily_rows:
|
||||
return {
|
||||
"energy_balance": energy_balance,
|
||||
"energy_balance": 0.0,
|
||||
"avg_intake": 0.0,
|
||||
"estimated_tdee": 0.0,
|
||||
"status": "unknown",
|
||||
"confidence": "insufficient",
|
||||
"days_analyzed": days,
|
||||
"data_points": 0,
|
||||
}
|
||||
|
||||
daily_totals = [safe_float(r["daily_kcal"]) for r in daily_rows]
|
||||
avg_intake = sum(daily_totals) / len(daily_totals)
|
||||
data_points = len(daily_totals)
|
||||
|
||||
estimated_tdee = estimate_tdee_kcal_from_latest_weight(profile_id)
|
||||
if estimated_tdee is None:
|
||||
return {
|
||||
"energy_balance": 0.0,
|
||||
"avg_intake": avg_intake,
|
||||
"estimated_tdee": estimated_tdee,
|
||||
"status": status,
|
||||
"confidence": confidence,
|
||||
"estimated_tdee": 0.0,
|
||||
"status": "unknown",
|
||||
"confidence": "insufficient",
|
||||
"days_analyzed": days,
|
||||
"data_points": data_points
|
||||
}
|
||||
|
||||
energy_balance = avg_intake - estimated_tdee
|
||||
|
||||
if energy_balance < -200:
|
||||
status = "deficit"
|
||||
elif energy_balance > 200:
|
||||
status = "surplus"
|
||||
else:
|
||||
status = "maintenance"
|
||||
|
||||
confidence = calculate_confidence(data_points, days, "general")
|
||||
|
||||
return {
|
||||
"energy_balance": energy_balance,
|
||||
"avg_intake": avg_intake,
|
||||
"estimated_tdee": estimated_tdee,
|
||||
"status": status,
|
||||
"confidence": confidence,
|
||||
"days_analyzed": days,
|
||||
"data_points": data_points
|
||||
}
|
||||
|
||||
|
||||
def get_protein_adequacy_data(
|
||||
profile_id: str,
|
||||
@@ -291,7 +376,6 @@ def get_protein_adequacy_data(
|
||||
"confidence": str
|
||||
}
|
||||
"""
|
||||
# Get protein targets
|
||||
targets = get_protein_targets_data(profile_id)
|
||||
|
||||
with get_db() as conn:
|
||||
@@ -299,60 +383,55 @@ def get_protein_adequacy_data(
|
||||
cutoff = (datetime.now() - timedelta(days=days)).strftime('%Y-%m-%d')
|
||||
|
||||
cur.execute(
|
||||
"""SELECT
|
||||
AVG(protein_g) as avg_protein,
|
||||
COUNT(*) as cnt,
|
||||
SUM(CASE WHEN protein_g >= %s AND protein_g <= %s THEN 1 ELSE 0 END) as days_in_target
|
||||
"""SELECT COALESCE(SUM(protein_g), 0)::float AS daily_protein
|
||||
FROM nutrition_log
|
||||
WHERE profile_id=%s AND date >= %s AND protein_g IS NOT NULL""",
|
||||
(targets['protein_target_low'], targets['protein_target_high'], profile_id, cutoff)
|
||||
WHERE profile_id=%s AND date >= %s
|
||||
GROUP BY date""",
|
||||
(profile_id, cutoff),
|
||||
)
|
||||
row = cur.fetchone()
|
||||
|
||||
if not row or row['cnt'] == 0:
|
||||
return {
|
||||
"adequacy_score": 0,
|
||||
"avg_protein_g": 0.0,
|
||||
"target_protein_low": targets['protein_target_low'],
|
||||
"target_protein_high": targets['protein_target_high'],
|
||||
"protein_g_per_kg": 0.0,
|
||||
"days_in_target": 0,
|
||||
"days_with_data": 0,
|
||||
"confidence": "insufficient"
|
||||
}
|
||||
|
||||
avg_protein = safe_float(row['avg_protein'])
|
||||
days_with_data = row['cnt']
|
||||
days_in_target = row['days_in_target']
|
||||
|
||||
protein_g_per_kg = avg_protein / targets['current_weight'] if targets['current_weight'] > 0 else 0.0
|
||||
|
||||
# Calculate adequacy score
|
||||
# 100 = always in target range
|
||||
# Scale based on percentage of days in target + average relative to target
|
||||
target_pct = (days_in_target / days_with_data * 100) if days_with_data > 0 else 0
|
||||
|
||||
# Bonus/penalty for average protein level
|
||||
target_mid = (targets['protein_target_low'] + targets['protein_target_high']) / 2
|
||||
avg_vs_target = (avg_protein / target_mid) if target_mid > 0 else 0
|
||||
|
||||
# Weighted score: 70% target days, 30% average level
|
||||
adequacy_score = int(target_pct * 0.7 + min(avg_vs_target * 100, 100) * 0.3)
|
||||
adequacy_score = max(0, min(100, adequacy_score)) # Clamp to 0-100
|
||||
|
||||
confidence = calculate_confidence(days_with_data, days, "general")
|
||||
rows = cur.fetchall()
|
||||
|
||||
if not rows or targets.get("confidence") == "insufficient" or targets["current_weight"] <= 0:
|
||||
return {
|
||||
"adequacy_score": adequacy_score,
|
||||
"avg_protein_g": avg_protein,
|
||||
"adequacy_score": 0,
|
||||
"avg_protein_g": 0.0,
|
||||
"target_protein_low": targets['protein_target_low'],
|
||||
"target_protein_high": targets['protein_target_high'],
|
||||
"protein_g_per_kg": protein_g_per_kg,
|
||||
"days_in_target": days_in_target,
|
||||
"days_with_data": days_with_data,
|
||||
"confidence": confidence
|
||||
"protein_g_per_kg": 0.0,
|
||||
"days_in_target": 0,
|
||||
"days_with_data": 0,
|
||||
"confidence": "insufficient"
|
||||
}
|
||||
|
||||
daily_totals = [safe_float(r["daily_protein"]) for r in rows]
|
||||
days_with_data = len(daily_totals)
|
||||
low = targets["protein_target_low"]
|
||||
high = targets["protein_target_high"]
|
||||
days_in_target = sum(1 for d in daily_totals if low <= d <= high)
|
||||
|
||||
avg_protein = sum(daily_totals) / days_with_data
|
||||
protein_g_per_kg = avg_protein / targets["current_weight"] if targets["current_weight"] > 0 else 0.0
|
||||
|
||||
target_pct = (days_in_target / days_with_data * 100) if days_with_data > 0 else 0
|
||||
target_mid = (low + high) / 2
|
||||
avg_vs_target = (avg_protein / target_mid) if target_mid > 0 else 0
|
||||
|
||||
adequacy_score = int(target_pct * 0.7 + min(avg_vs_target * 100, 100) * 0.3)
|
||||
adequacy_score = max(0, min(100, adequacy_score))
|
||||
|
||||
confidence = calculate_confidence(days_with_data, days, "general")
|
||||
|
||||
return {
|
||||
"adequacy_score": adequacy_score,
|
||||
"avg_protein_g": avg_protein,
|
||||
"target_protein_low": targets['protein_target_low'],
|
||||
"target_protein_high": targets['protein_target_high'],
|
||||
"protein_g_per_kg": protein_g_per_kg,
|
||||
"days_in_target": days_in_target,
|
||||
"days_with_data": days_with_data,
|
||||
"confidence": confidence
|
||||
}
|
||||
|
||||
|
||||
def get_macro_consistency_data(
|
||||
profile_id: str,
|
||||
@@ -387,16 +466,18 @@ def get_macro_consistency_data(
|
||||
|
||||
cur.execute(
|
||||
"""SELECT
|
||||
protein_g, carbs_g, fat_g, kcal
|
||||
COALESCE(SUM(kcal), 0)::float AS kcal,
|
||||
COALESCE(SUM(protein_g), 0)::float AS protein_g,
|
||||
COALESCE(SUM(carbs_g), 0)::float AS carbs_g,
|
||||
COALESCE(SUM(fat_g), 0)::float AS fat_g
|
||||
FROM nutrition_log
|
||||
WHERE profile_id=%s
|
||||
AND date >= %s
|
||||
AND protein_g IS NOT NULL
|
||||
AND carbs_g IS NOT NULL
|
||||
AND fat_g IS NOT NULL
|
||||
AND kcal > 0
|
||||
ORDER BY date""",
|
||||
(profile_id, cutoff)
|
||||
WHERE profile_id=%s AND date >= %s
|
||||
GROUP BY date
|
||||
HAVING COALESCE(SUM(kcal), 0) > 0
|
||||
AND COALESCE(SUM(protein_g), 0) > 0
|
||||
AND COALESCE(SUM(carbs_g), 0) > 0
|
||||
AND COALESCE(SUM(fat_g), 0) > 0""",
|
||||
(profile_id, cutoff),
|
||||
)
|
||||
rows = cur.fetchall()
|
||||
|
||||
@@ -413,7 +494,6 @@ def get_macro_consistency_data(
|
||||
"data_points": len(rows)
|
||||
}
|
||||
|
||||
# Calculate macro percentages for each day
|
||||
import statistics
|
||||
|
||||
protein_pcts = []
|
||||
@@ -425,7 +505,6 @@ def get_macro_consistency_data(
|
||||
if total_kcal == 0:
|
||||
continue
|
||||
|
||||
# Convert grams to kcal (protein=4, carbs=4, fat=9)
|
||||
protein_kcal = safe_float(row['protein_g']) * 4
|
||||
carbs_kcal = safe_float(row['carbs_g']) * 4
|
||||
fat_kcal = safe_float(row['fat_g']) * 9
|
||||
@@ -491,50 +570,15 @@ def get_macro_consistency_data(
|
||||
|
||||
def calculate_energy_balance_7d(profile_id: str) -> Optional[float]:
|
||||
"""
|
||||
Calculate 7-day average energy balance (kcal/day)
|
||||
Positive = surplus, Negative = deficit
|
||||
|
||||
Migration from Phase 0b:
|
||||
Used by placeholders that need single balance value
|
||||
7-day mean energy balance (kcal/day), same rules as get_energy_balance_data(..., 7).
|
||||
"""
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute("""
|
||||
SELECT kcal
|
||||
FROM nutrition_log
|
||||
WHERE profile_id = %s
|
||||
AND date >= CURRENT_DATE - INTERVAL '7 days'
|
||||
ORDER BY date DESC
|
||||
""", (profile_id,))
|
||||
|
||||
calories = [row['kcal'] for row in cur.fetchall()]
|
||||
|
||||
if len(calories) < 4: # Need at least 4 days
|
||||
return None
|
||||
|
||||
avg_intake = float(sum(calories) / len(calories))
|
||||
|
||||
# Get estimated TDEE (simplified - could use Harris-Benedict)
|
||||
# For now, use weight-based estimate
|
||||
cur.execute("""
|
||||
SELECT weight
|
||||
FROM weight_log
|
||||
WHERE profile_id = %s
|
||||
ORDER BY date DESC
|
||||
LIMIT 1
|
||||
""", (profile_id,))
|
||||
|
||||
weight_row = cur.fetchone()
|
||||
if not weight_row:
|
||||
return None
|
||||
|
||||
# Simple TDEE estimate: bodyweight (kg) × 30-35
|
||||
# TODO: Improve with activity level, age, gender
|
||||
estimated_tdee = float(weight_row['weight']) * 32.5
|
||||
|
||||
balance = avg_intake - estimated_tdee
|
||||
|
||||
return round(balance, 0)
|
||||
data = get_energy_balance_data(profile_id, 7)
|
||||
if data["data_points"] < 4:
|
||||
return None
|
||||
tdee = data.get("estimated_tdee") or 0
|
||||
if tdee <= 0:
|
||||
return None
|
||||
return round(float(data["energy_balance"]), 0)
|
||||
|
||||
|
||||
def calculate_energy_deficit_surplus(profile_id: str, days: int = 7) -> Optional[str]:
|
||||
@@ -654,15 +698,14 @@ def calculate_protein_days_in_target(profile_id: str, target_low: float = 1.6, t
|
||||
|
||||
def calculate_protein_adequacy_28d(profile_id: str) -> Optional[int]:
|
||||
"""
|
||||
Protein adequacy score 0-100 (last 28 days)
|
||||
Based on consistency and target achievement
|
||||
Protein adequacy score 0-100 (last 28 days).
|
||||
Uses per-calendar-day total protein vs. average weight in the window (g/kg per day).
|
||||
"""
|
||||
import statistics
|
||||
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
|
||||
# Get average weight (28d)
|
||||
cur.execute("""
|
||||
SELECT AVG(weight) as avg_weight
|
||||
FROM weight_log
|
||||
@@ -676,38 +719,29 @@ def calculate_protein_adequacy_28d(profile_id: str) -> Optional[int]:
|
||||
|
||||
weight = float(weight_row['avg_weight'])
|
||||
|
||||
# Get protein intake (28d)
|
||||
cur.execute("""
|
||||
SELECT protein_g
|
||||
SELECT COALESCE(SUM(protein_g), 0)::float AS daily_protein
|
||||
FROM nutrition_log
|
||||
WHERE profile_id = %s
|
||||
AND date >= CURRENT_DATE - INTERVAL '28 days'
|
||||
AND protein_g IS NOT NULL
|
||||
GROUP BY date
|
||||
""", (profile_id,))
|
||||
|
||||
protein_values = [float(row['protein_g']) for row in cur.fetchall()]
|
||||
daily_totals = [float(row['daily_protein']) for row in cur.fetchall()]
|
||||
|
||||
if len(protein_values) < 18: # 60% coverage
|
||||
if len(daily_totals) < 18:
|
||||
return None
|
||||
|
||||
# Calculate metrics
|
||||
protein_per_kg_values = [p / weight for p in protein_values]
|
||||
protein_per_kg_values = [p / weight for p in daily_totals]
|
||||
avg_protein_per_kg = sum(protein_per_kg_values) / len(protein_per_kg_values)
|
||||
|
||||
# Target range: 1.6-2.2 g/kg for active individuals
|
||||
target_mid = 1.9
|
||||
|
||||
# Score based on distance from target
|
||||
if 1.6 <= avg_protein_per_kg <= 2.2:
|
||||
base_score = 100
|
||||
elif avg_protein_per_kg < 1.6:
|
||||
# Below target
|
||||
base_score = max(40, 100 - ((1.6 - avg_protein_per_kg) * 40))
|
||||
else:
|
||||
# Above target (less penalty)
|
||||
base_score = max(80, 100 - ((avg_protein_per_kg - 2.2) * 10))
|
||||
|
||||
# Consistency bonus/penalty
|
||||
std_dev = statistics.stdev(protein_per_kg_values)
|
||||
if std_dev < 0.3:
|
||||
consistency_bonus = 10
|
||||
@@ -723,20 +757,24 @@ def calculate_protein_adequacy_28d(profile_id: str) -> Optional[int]:
|
||||
|
||||
def calculate_macro_consistency_score(profile_id: str) -> Optional[int]:
|
||||
"""
|
||||
Macro consistency score 0-100 (last 28 days)
|
||||
Lower variability = higher score
|
||||
Macro consistency score 0-100 (last 28 days).
|
||||
CV of daily totals (kcal and macros), not raw log rows.
|
||||
"""
|
||||
import statistics
|
||||
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute("""
|
||||
SELECT kcal, protein_g, fat_g, carbs_g
|
||||
SELECT
|
||||
COALESCE(SUM(kcal), 0)::float AS dk,
|
||||
COALESCE(SUM(protein_g), 0)::float AS dp,
|
||||
COALESCE(SUM(fat_g), 0)::float AS df,
|
||||
COALESCE(SUM(carbs_g), 0)::float AS dc
|
||||
FROM nutrition_log
|
||||
WHERE profile_id = %s
|
||||
AND date >= CURRENT_DATE - INTERVAL '28 days'
|
||||
AND kcal IS NOT NULL
|
||||
ORDER BY date DESC
|
||||
GROUP BY date
|
||||
HAVING COALESCE(SUM(kcal), 0) > 0
|
||||
""", (profile_id,))
|
||||
|
||||
data = cur.fetchall()
|
||||
@@ -744,9 +782,7 @@ def calculate_macro_consistency_score(profile_id: str) -> Optional[int]:
|
||||
if len(data) < 18:
|
||||
return None
|
||||
|
||||
# Calculate coefficient of variation for each macro
|
||||
def cv(values):
|
||||
"""Coefficient of variation (std_dev / mean)"""
|
||||
if not values or len(values) < 2:
|
||||
return None
|
||||
mean = sum(values) / len(values)
|
||||
@@ -755,10 +791,10 @@ def calculate_macro_consistency_score(profile_id: str) -> Optional[int]:
|
||||
std_dev = statistics.stdev(values)
|
||||
return std_dev / mean
|
||||
|
||||
calories_cv = cv([d['kcal'] for d in data])
|
||||
protein_cv = cv([d['protein_g'] for d in data if d['protein_g']])
|
||||
fat_cv = cv([d['fat_g'] for d in data if d['fat_g']])
|
||||
carbs_cv = cv([d['carbs_g'] for d in data if d['carbs_g']])
|
||||
calories_cv = cv([d['dk'] for d in data])
|
||||
protein_cv = cv([d['dp'] for d in data if d['dp']])
|
||||
fat_cv = cv([d['df'] for d in data if d['df']])
|
||||
carbs_cv = cv([d['dc'] for d in data if d['dc']])
|
||||
|
||||
cv_values = [v for v in [calories_cv, protein_cv, fat_cv, carbs_cv] if v is not None]
|
||||
|
||||
@@ -767,9 +803,6 @@ def calculate_macro_consistency_score(profile_id: str) -> Optional[int]:
|
||||
|
||||
avg_cv = sum(cv_values) / len(cv_values)
|
||||
|
||||
# Score: lower CV = higher score
|
||||
# CV < 0.2 = excellent consistency
|
||||
# CV > 0.5 = poor consistency
|
||||
if avg_cv < 0.2:
|
||||
score = 100
|
||||
elif avg_cv < 0.3:
|
||||
@@ -811,14 +844,16 @@ def calculate_nutrition_score(profile_id: str, focus_weights: Optional[Dict] = N
|
||||
from data_layer.scores import get_user_focus_weights
|
||||
focus_weights = get_user_focus_weights(profile_id)
|
||||
|
||||
# Nutrition-related focus areas (English keys from DB)
|
||||
protein_intake = focus_weights.get('protein_intake', 0)
|
||||
calorie_balance = focus_weights.get('calorie_balance', 0)
|
||||
macro_consistency = focus_weights.get('macro_consistency', 0)
|
||||
meal_timing = focus_weights.get('meal_timing', 0)
|
||||
hydration = focus_weights.get('hydration', 0)
|
||||
# Nutrition-related focus areas (English keys from DB; Gewichte immer float)
|
||||
protein_intake = float(focus_weights.get('protein_intake', 0) or 0)
|
||||
calorie_balance = float(focus_weights.get('calorie_balance', 0) or 0)
|
||||
macro_consistency = float(focus_weights.get('macro_consistency', 0) or 0)
|
||||
meal_timing = float(focus_weights.get('meal_timing', 0) or 0)
|
||||
hydration = float(focus_weights.get('hydration', 0) or 0)
|
||||
|
||||
total_nutrition_weight = protein_intake + calorie_balance + macro_consistency + meal_timing + hydration
|
||||
total_nutrition_weight = (
|
||||
protein_intake + calorie_balance + macro_consistency + meal_timing + hydration
|
||||
)
|
||||
|
||||
if total_nutrition_weight == 0:
|
||||
return None # No nutrition goals
|
||||
@@ -853,40 +888,66 @@ def calculate_nutrition_score(profile_id: str, focus_weights: Optional[Dict] = N
|
||||
if not components:
|
||||
return None
|
||||
|
||||
# Weighted average
|
||||
total_score = sum(score * weight for _, score, weight in components)
|
||||
total_weight = sum(weight for _, _, weight in components)
|
||||
# Weighted average (float: DB-Werte können Decimal sein)
|
||||
total_score = sum(float(score) * float(weight) for _, score, weight in components)
|
||||
total_weight = sum(float(weight) for _, _, weight in components)
|
||||
|
||||
return int(total_score / total_weight)
|
||||
|
||||
|
||||
def _score_calorie_adherence(profile_id: str) -> Optional[int]:
|
||||
"""Score calorie target adherence (0-100)"""
|
||||
# Check for energy balance goal
|
||||
# For now, use energy balance calculation
|
||||
"""Score calorie target adherence (0–100) using 7d balance vs profiles.goal_mode."""
|
||||
balance = calculate_energy_balance_7d(profile_id)
|
||||
|
||||
if balance is None:
|
||||
return None
|
||||
|
||||
# Score based on whether deficit/surplus aligns with goal
|
||||
# Simplified: assume weight loss goal = deficit is good
|
||||
# TODO: Check actual goal type
|
||||
mode = _get_profile_goal_mode(profile_id)
|
||||
b = float(balance)
|
||||
|
||||
abs_balance = abs(balance)
|
||||
def _weight_loss(x: float) -> int:
|
||||
if -550 <= x <= -250:
|
||||
return 100
|
||||
if x > 450:
|
||||
return 38
|
||||
if -750 <= x < -550 or -250 < x <= 120:
|
||||
return 82
|
||||
if x < -1200:
|
||||
return 52
|
||||
if -950 <= x < -750 or 120 < x <= 350:
|
||||
return 68
|
||||
return 58
|
||||
|
||||
# Moderate deficit/surplus = good
|
||||
if 200 <= abs_balance <= 500:
|
||||
return 100
|
||||
elif 100 <= abs_balance <= 700:
|
||||
return 85
|
||||
elif abs_balance <= 900:
|
||||
return 70
|
||||
elif abs_balance <= 1200:
|
||||
return 55
|
||||
else:
|
||||
def _surplus_friendly(x: float) -> int:
|
||||
if 80 <= x <= 480:
|
||||
return 100
|
||||
if -120 <= x < 80 or 480 < x <= 700:
|
||||
return 86
|
||||
if -380 <= x < -120:
|
||||
return 68
|
||||
if x > 850:
|
||||
return 54
|
||||
if x < -650:
|
||||
return 44
|
||||
return 72
|
||||
|
||||
def _maintenance(x: float) -> int:
|
||||
a = abs(x)
|
||||
if a <= 200:
|
||||
return 100
|
||||
if a <= 400:
|
||||
return 84
|
||||
if a <= 650:
|
||||
return 70
|
||||
if a <= 900:
|
||||
return 55
|
||||
return 40
|
||||
|
||||
if mode == "weight_loss":
|
||||
return _weight_loss(b)
|
||||
if mode in ("strength", "recomposition"):
|
||||
return _surplus_friendly(b)
|
||||
return _maintenance(b)
|
||||
|
||||
|
||||
def _score_macro_balance(profile_id: str) -> Optional[int]:
|
||||
"""Score macro balance (0-100)"""
|
||||
|
||||
@@ -15,12 +15,50 @@ Phase 0c: Multi-Layer Architecture
|
||||
Version: 1.0
|
||||
"""
|
||||
|
||||
from typing import Dict, List, Optional
|
||||
import json
|
||||
from typing import Dict, List, Optional, Any
|
||||
from datetime import datetime, timedelta, date
|
||||
from db import get_db, get_cursor, r2d
|
||||
from db import get_db, get_cursor
|
||||
from data_layer.utils import calculate_confidence, safe_float, safe_int
|
||||
|
||||
|
||||
def _parse_sleep_segments(raw: Any) -> Optional[List[dict]]:
|
||||
"""JSONB kann dict/list/str sein; ungültig → None."""
|
||||
if raw is None:
|
||||
return None
|
||||
if isinstance(raw, str):
|
||||
try:
|
||||
raw = json.loads(raw)
|
||||
except (json.JSONDecodeError, TypeError):
|
||||
return None
|
||||
if not isinstance(raw, list):
|
||||
return None
|
||||
return raw
|
||||
|
||||
|
||||
def _segment_minutes(seg: Any) -> int:
|
||||
if not isinstance(seg, dict):
|
||||
return 0
|
||||
for key in ("duration_min", "duration_minutes", "minutes"):
|
||||
v = seg.get(key)
|
||||
if v is not None:
|
||||
return max(0, safe_int(v))
|
||||
return 0
|
||||
|
||||
|
||||
def _normalize_sleep_phase(seg: dict) -> str:
|
||||
"""Kleinbuchstaben; Apple „Core“-Schlaf wird wie light gewertet."""
|
||||
if not isinstance(seg, dict):
|
||||
return ""
|
||||
p = seg.get("phase")
|
||||
if p is None:
|
||||
return ""
|
||||
s = str(p).strip().lower()
|
||||
if s in ("core", "asleep"):
|
||||
return "light"
|
||||
return s
|
||||
|
||||
|
||||
def get_sleep_duration_data(
|
||||
profile_id: str,
|
||||
days: int = 7
|
||||
@@ -51,7 +89,7 @@ def get_sleep_duration_data(
|
||||
cutoff = (datetime.now() - timedelta(days=days)).strftime('%Y-%m-%d')
|
||||
|
||||
cur.execute(
|
||||
"""SELECT sleep_segments FROM sleep_log
|
||||
"""SELECT sleep_segments, duration_minutes FROM sleep_log
|
||||
WHERE profile_id=%s AND date >= %s
|
||||
ORDER BY date DESC""",
|
||||
(profile_id, cutoff)
|
||||
@@ -72,12 +110,17 @@ def get_sleep_duration_data(
|
||||
nights_with_data = 0
|
||||
|
||||
for row in rows:
|
||||
segments = row['sleep_segments']
|
||||
night_minutes = 0
|
||||
segments = _parse_sleep_segments(row.get("sleep_segments"))
|
||||
if segments:
|
||||
night_minutes = sum(seg.get('duration_min', 0) for seg in segments)
|
||||
if night_minutes > 0:
|
||||
total_minutes += night_minutes
|
||||
nights_with_data += 1
|
||||
night_minutes = sum(_segment_minutes(seg) for seg in segments)
|
||||
if night_minutes <= 0:
|
||||
dm = row.get("duration_minutes")
|
||||
if dm is not None:
|
||||
night_minutes = max(0, safe_int(dm))
|
||||
if night_minutes > 0:
|
||||
total_minutes += night_minutes
|
||||
nights_with_data += 1
|
||||
|
||||
if nights_with_data == 0:
|
||||
return {
|
||||
@@ -136,7 +179,9 @@ def get_sleep_quality_data(
|
||||
cutoff = (datetime.now() - timedelta(days=days)).strftime('%Y-%m-%d')
|
||||
|
||||
cur.execute(
|
||||
"""SELECT sleep_segments FROM sleep_log
|
||||
"""SELECT sleep_segments, duration_minutes, deep_minutes, rem_minutes,
|
||||
light_minutes, awake_minutes
|
||||
FROM sleep_log
|
||||
WHERE profile_id=%s AND date >= %s
|
||||
ORDER BY date DESC""",
|
||||
(profile_id, cutoff)
|
||||
@@ -163,15 +208,29 @@ def get_sleep_quality_data(
|
||||
count = 0
|
||||
|
||||
for row in rows:
|
||||
segments = row['sleep_segments']
|
||||
if segments:
|
||||
# Note: segments use 'phase' key, stored lowercase (deep, rem, light, awake)
|
||||
deep_rem_min = sum(s.get('duration_min', 0) for s in segments if s.get('phase') in ['deep', 'rem'])
|
||||
light_min = sum(s.get('duration_min', 0) for s in segments if s.get('phase') == 'light')
|
||||
awake_min = sum(s.get('duration_min', 0) for s in segments if s.get('phase') == 'awake')
|
||||
total_min = sum(s.get('duration_min', 0) for s in segments)
|
||||
deep_rem_min = light_min = awake_min = 0
|
||||
total_min = 0
|
||||
used_segments = False
|
||||
|
||||
segments = _parse_sleep_segments(row.get("sleep_segments"))
|
||||
if segments:
|
||||
total_min = sum(_segment_minutes(s) for s in segments)
|
||||
if total_min > 0:
|
||||
deep_rem_min = sum(
|
||||
_segment_minutes(s)
|
||||
for s in segments
|
||||
if _normalize_sleep_phase(s) in ("deep", "rem")
|
||||
)
|
||||
light_min = sum(
|
||||
_segment_minutes(s)
|
||||
for s in segments
|
||||
if _normalize_sleep_phase(s) == "light"
|
||||
)
|
||||
awake_min = sum(
|
||||
_segment_minutes(s)
|
||||
for s in segments
|
||||
if _normalize_sleep_phase(s) == "awake"
|
||||
)
|
||||
quality_pct = (deep_rem_min / total_min) * 100
|
||||
total_quality += quality_pct
|
||||
total_deep_rem += deep_rem_min
|
||||
@@ -179,6 +238,28 @@ def get_sleep_quality_data(
|
||||
total_awake += awake_min
|
||||
total_all += total_min
|
||||
count += 1
|
||||
used_segments = True
|
||||
|
||||
if not used_segments:
|
||||
d, r, l, a = (
|
||||
row.get("deep_minutes"),
|
||||
row.get("rem_minutes"),
|
||||
row.get("light_minutes"),
|
||||
row.get("awake_minutes"),
|
||||
)
|
||||
if d is not None or r is not None or l is not None:
|
||||
di, ri, li = (d or 0), (r or 0), (l or 0)
|
||||
phase_sum = di + ri + li
|
||||
ai = (a or 0) if a is not None else 0
|
||||
total_min = phase_sum + ai
|
||||
if total_min > 0 and phase_sum > 0:
|
||||
quality_pct = ((di + ri) / total_min) * 100
|
||||
total_quality += quality_pct
|
||||
total_deep_rem += di + ri
|
||||
total_light += li
|
||||
total_awake += ai
|
||||
total_all += total_min
|
||||
count += 1
|
||||
|
||||
if count == 0:
|
||||
return {
|
||||
@@ -351,8 +432,8 @@ def calculate_recovery_score_v2(profile_id: str) -> Optional[int]:
|
||||
return None
|
||||
|
||||
# Weighted average
|
||||
total_score = sum(score * weight for _, score, weight in components)
|
||||
total_weight = sum(weight for _, _, weight in components)
|
||||
total_score = sum(float(score) * float(weight) for _, score, weight in components)
|
||||
total_weight = sum(float(weight) for _, _, weight in components)
|
||||
|
||||
final_score = int(total_score / total_weight)
|
||||
|
||||
@@ -783,17 +864,24 @@ def calculate_sleep_quality_7d(profile_id: str) -> Optional[int]:
|
||||
|
||||
quality_scores = []
|
||||
for s in sleep_data:
|
||||
if s['deep_minutes'] and s['rem_minutes']:
|
||||
quality_pct = ((s['deep_minutes'] + s['rem_minutes']) / s['duration_minutes']) * 100
|
||||
# 40-60% deep+REM is good
|
||||
if quality_pct >= 45:
|
||||
quality_scores.append(100)
|
||||
elif quality_pct >= 35:
|
||||
quality_scores.append(75)
|
||||
elif quality_pct >= 25:
|
||||
quality_scores.append(50)
|
||||
else:
|
||||
quality_scores.append(30)
|
||||
dur = s["duration_minutes"]
|
||||
if not dur or dur <= 0:
|
||||
continue
|
||||
d = s["deep_minutes"]
|
||||
r = s["rem_minutes"]
|
||||
if d is None and r is None:
|
||||
continue
|
||||
di, ri = (d or 0), (r or 0)
|
||||
quality_pct = ((di + ri) / dur) * 100
|
||||
# 40-60% deep+REM is good
|
||||
if quality_pct >= 45:
|
||||
quality_scores.append(100)
|
||||
elif quality_pct >= 35:
|
||||
quality_scores.append(75)
|
||||
elif quality_pct >= 25:
|
||||
quality_scores.append(50)
|
||||
else:
|
||||
quality_scores.append(30)
|
||||
|
||||
if not quality_scores:
|
||||
return None
|
||||
|
||||
@@ -202,29 +202,30 @@ def calculate_goal_progress_score(profile_id: str) -> Optional[int]:
|
||||
total_weight = 0.0
|
||||
|
||||
for focus_area_id, weight in focus_weights.items():
|
||||
w = float(weight)
|
||||
component = focus_to_component.get(focus_area_id)
|
||||
|
||||
if component == 'body' and body_score is not None:
|
||||
total_score += body_score * weight
|
||||
total_weight += weight
|
||||
total_score += float(body_score) * w
|
||||
total_weight += w
|
||||
elif component == 'nutrition' and nutrition_score is not None:
|
||||
total_score += nutrition_score * weight
|
||||
total_weight += weight
|
||||
total_score += float(nutrition_score) * w
|
||||
total_weight += w
|
||||
elif component == 'activity' and activity_score is not None:
|
||||
total_score += activity_score * weight
|
||||
total_weight += weight
|
||||
total_score += float(activity_score) * w
|
||||
total_weight += w
|
||||
elif component == 'recovery' and recovery_score is not None:
|
||||
total_score += recovery_score * weight
|
||||
total_weight += weight
|
||||
total_score += float(recovery_score) * w
|
||||
total_weight += w
|
||||
elif component == 'health' and health_risk_score is not None:
|
||||
total_score += health_risk_score * weight
|
||||
total_weight += weight
|
||||
total_score += float(health_risk_score) * w
|
||||
total_weight += w
|
||||
|
||||
if total_weight == 0:
|
||||
return None
|
||||
|
||||
# Normalize to 0-100
|
||||
final_score = total_score / total_weight
|
||||
# Normalize to 0-100 (Explizit float: Zwischensummen können Decimal aus DB sein)
|
||||
final_score = float(total_score) / float(total_weight)
|
||||
|
||||
return int(final_score)
|
||||
|
||||
@@ -282,9 +283,9 @@ def calculate_health_stability_score(profile_id: str) -> Optional[int]:
|
||||
|
||||
activities = cur.fetchall()
|
||||
if activities:
|
||||
total_minutes = sum(a['duration_min'] for a in activities)
|
||||
total_minutes = float(sum(float(a['duration_min'] or 0) for a in activities))
|
||||
# WHO recommends 150-300 min/week moderate activity
|
||||
movement_score = min(100, (total_minutes / 150) * 100)
|
||||
movement_score = min(100.0, (total_minutes / 150) * 100)
|
||||
components.append(('movement', movement_score, 20))
|
||||
|
||||
# 4. Waist circumference risk (15%)
|
||||
@@ -328,8 +329,8 @@ def calculate_health_stability_score(profile_id: str) -> Optional[int]:
|
||||
return None
|
||||
|
||||
# Weighted average
|
||||
total_score = sum(score * weight for _, score, weight in components)
|
||||
total_weight = sum(weight for _, _, weight in components)
|
||||
total_score = sum(float(score) * float(weight) for _, score, weight in components)
|
||||
total_weight = sum(float(weight) for _, _, weight in components)
|
||||
|
||||
return int(total_score / total_weight)
|
||||
|
||||
@@ -532,9 +533,19 @@ def calculate_focus_area_progress(profile_id: str, focus_area_id: str) -> Option
|
||||
if not goals:
|
||||
return None
|
||||
|
||||
# Weighted average by contribution_weight
|
||||
total_progress = sum(g['progress_pct'] * g['contribution_weight'] for g in goals)
|
||||
total_weight = sum(g['contribution_weight'] for g in goals)
|
||||
# Weighted average; progress_pct darf NULL sein (Ziele ohne quantitative Berechnung)
|
||||
parts: List[tuple] = []
|
||||
for g in goals:
|
||||
pct = g['progress_pct']
|
||||
if pct is None:
|
||||
continue
|
||||
parts.append((float(pct), float(g['contribution_weight'])))
|
||||
|
||||
if not parts:
|
||||
return None
|
||||
|
||||
total_progress = sum(p * w for p, w in parts)
|
||||
total_weight = sum(w for _, w in parts)
|
||||
|
||||
return int(total_progress / total_weight) if total_weight > 0 else None
|
||||
|
||||
|
||||
+6
-4
@@ -29,7 +29,9 @@ def init_pool():
|
||||
user=os.getenv("DB_USER", "mitai"),
|
||||
password=os.getenv("DB_PASSWORD", "")
|
||||
)
|
||||
print(f"✓ PostgreSQL connection pool initialized ({os.getenv('DB_HOST', 'postgres')}:{os.getenv('DB_PORT', '5432')})")
|
||||
print(
|
||||
f"[OK] PostgreSQL connection pool initialized ({os.getenv('DB_HOST', 'postgres')}:{os.getenv('DB_PORT', '5432')})"
|
||||
)
|
||||
|
||||
|
||||
@contextmanager
|
||||
@@ -171,7 +173,7 @@ def init_db():
|
||||
) as table_exists
|
||||
""")
|
||||
if not cur.fetchone()['table_exists']:
|
||||
print("⚠️ ai_prompts table doesn't exist yet - skipping pipeline prompt creation")
|
||||
print("[WARN] ai_prompts table doesn't exist yet - skipping pipeline prompt creation")
|
||||
return
|
||||
|
||||
# Ensure "pipeline" master prompt exists
|
||||
@@ -189,7 +191,7 @@ def init_db():
|
||||
)
|
||||
""")
|
||||
conn.commit()
|
||||
print("✓ Pipeline master prompt created")
|
||||
print("[OK] Pipeline master prompt created")
|
||||
except Exception as e:
|
||||
print(f"⚠️ Could not create pipeline prompt: {e}")
|
||||
print(f"[WARN] Could not create pipeline prompt: {e}")
|
||||
# Don't fail startup - prompt can be created manually
|
||||
+12
-2
@@ -14,6 +14,10 @@ from slowapi.errors import RateLimitExceeded
|
||||
|
||||
from db import init_db
|
||||
|
||||
# Placeholder registry: load all register_placeholder() side-effects before any request
|
||||
# so get_placeholder_catalog() and exports see consistent metadata (see Phase A plan).
|
||||
import placeholder_registrations # noqa: F401
|
||||
|
||||
# Import routers
|
||||
from routers import auth, profiles, weight, circumference, caliper
|
||||
from routers import activity, nutrition, photos, insights, prompts
|
||||
@@ -31,6 +35,8 @@ from routers import workflows # Phase 2 Workflow Engine - Execution
|
||||
from routers import reference_values # Persönliche Referenzwerte (Profil)
|
||||
from routers import admin_reference_value_types # Admin: Referenzwert-Typen
|
||||
from routers import app_dashboard # Geschützter App-Bereich: Dashboard-Lab Layout
|
||||
from routers import csv_import, admin_csv_templates # Issue #21 Universal CSV Parser
|
||||
from routers import admin_training_parameters, admin_activity_attribute_profiles # EAV session metrics
|
||||
|
||||
# ── App Configuration ─────────────────────────────────────────────────────────
|
||||
DATA_DIR = Path(os.getenv("DATA_DIR", "./data"))
|
||||
@@ -61,7 +67,7 @@ async def startup_event():
|
||||
try:
|
||||
init_db()
|
||||
except Exception as e:
|
||||
print(f"⚠️ init_db() failed (non-fatal): {e}")
|
||||
print(f"[WARN] init_db() failed (non-fatal): {e}")
|
||||
# Don't crash on startup - can be created manually
|
||||
|
||||
# Apply v9c migration if needed
|
||||
@@ -69,7 +75,7 @@ async def startup_event():
|
||||
from apply_v9c_migration import apply_migration
|
||||
apply_migration()
|
||||
except Exception as e:
|
||||
print(f"⚠️ v9c migration failed (non-fatal): {e}")
|
||||
print(f"[WARN] v9c migration failed (non-fatal): {e}")
|
||||
|
||||
# ── Register Routers ──────────────────────────────────────────────────────────
|
||||
app.include_router(auth.router) # /api/auth/*
|
||||
@@ -121,6 +127,10 @@ app.include_router(workflows.router) # /api/workflows/* (Phase 2 Exec
|
||||
app.include_router(reference_values.router) # /api/reference-value-types, /api/profile-reference-values
|
||||
app.include_router(admin_reference_value_types.router) # /api/admin/reference-value-types
|
||||
app.include_router(app_dashboard.router) # /api/app/dashboard-layout
|
||||
app.include_router(csv_import.router) # /api/csv/* (Issue #21)
|
||||
app.include_router(admin_csv_templates.router) # /api/admin/csv-templates/* (Issue #21)
|
||||
app.include_router(admin_training_parameters.router) # /api/admin/training-parameters
|
||||
app.include_router(admin_activity_attribute_profiles.router) # /api/admin/training-*-parameters
|
||||
|
||||
# ── Health Check ──────────────────────────────────────────────────────────────
|
||||
@app.get("/")
|
||||
|
||||
@@ -0,0 +1,75 @@
|
||||
-- Migration 042: Universal CSV Parser – Mapping-Registry & Import-Log (Issue #21)
|
||||
-- Tabellen für System-Templates (profile_id NULL, is_system true) und User-Mappings.
|
||||
|
||||
CREATE TABLE IF NOT EXISTS csv_field_mappings (
|
||||
id SERIAL PRIMARY KEY,
|
||||
profile_id UUID REFERENCES profiles(id) ON DELETE CASCADE,
|
||||
is_system BOOLEAN NOT NULL DEFAULT false,
|
||||
module VARCHAR(50) NOT NULL,
|
||||
mapping_name VARCHAR(100) NOT NULL,
|
||||
description TEXT,
|
||||
column_signature TEXT[] NOT NULL DEFAULT '{}',
|
||||
delimiter VARCHAR(10) NOT NULL DEFAULT ',',
|
||||
encoding VARCHAR(20) NOT NULL DEFAULT 'utf-8',
|
||||
has_header BOOLEAN NOT NULL DEFAULT true,
|
||||
field_mappings JSONB NOT NULL DEFAULT '{}',
|
||||
type_conversions JSONB,
|
||||
usage_count INTEGER NOT NULL DEFAULT 0,
|
||||
last_used_at TIMESTAMPTZ,
|
||||
success_rate REAL NOT NULL DEFAULT 1.0,
|
||||
created_at TIMESTAMPTZ NOT NULL DEFAULT CURRENT_TIMESTAMP,
|
||||
updated_at TIMESTAMPTZ NOT NULL DEFAULT CURRENT_TIMESTAMP,
|
||||
CONSTRAINT csv_field_mappings_system_profile CHECK (
|
||||
(is_system = true AND profile_id IS NULL)
|
||||
OR (is_system = false AND profile_id IS NOT NULL)
|
||||
)
|
||||
);
|
||||
|
||||
COMMENT ON TABLE csv_field_mappings IS 'CSV Import: System-Templates + User-Mappings (Issue #21)';
|
||||
COMMENT ON COLUMN csv_field_mappings.is_system IS 'true = globales Template (nur Admin pflegbar), false = User-Mapping';
|
||||
|
||||
CREATE UNIQUE INDEX IF NOT EXISTS idx_csv_field_mappings_system_module_name
|
||||
ON csv_field_mappings (module, mapping_name)
|
||||
WHERE is_system = true AND profile_id IS NULL;
|
||||
|
||||
CREATE UNIQUE INDEX IF NOT EXISTS idx_csv_field_mappings_user_module_name
|
||||
ON csv_field_mappings (profile_id, module, mapping_name)
|
||||
WHERE is_system = false;
|
||||
|
||||
CREATE INDEX IF NOT EXISTS idx_csv_field_mappings_module_profile
|
||||
ON csv_field_mappings (module, profile_id);
|
||||
|
||||
CREATE INDEX IF NOT EXISTS idx_csv_field_mappings_system_module
|
||||
ON csv_field_mappings (module)
|
||||
WHERE is_system = true;
|
||||
|
||||
CREATE TABLE IF NOT EXISTS csv_import_log (
|
||||
id SERIAL PRIMARY KEY,
|
||||
profile_id UUID NOT NULL REFERENCES profiles(id) ON DELETE CASCADE,
|
||||
mapping_id INTEGER REFERENCES csv_field_mappings(id) ON DELETE SET NULL,
|
||||
module VARCHAR(50) NOT NULL,
|
||||
filename VARCHAR(255),
|
||||
rows_total INTEGER,
|
||||
rows_imported INTEGER,
|
||||
rows_updated INTEGER,
|
||||
rows_skipped INTEGER,
|
||||
rows_errors INTEGER,
|
||||
error_details JSONB,
|
||||
started_at TIMESTAMPTZ NOT NULL DEFAULT CURRENT_TIMESTAMP,
|
||||
finished_at TIMESTAMPTZ,
|
||||
status VARCHAR(20) NOT NULL DEFAULT 'running',
|
||||
affected_ids JSONB
|
||||
);
|
||||
|
||||
CREATE INDEX IF NOT EXISTS idx_csv_import_log_profile_module
|
||||
ON csv_import_log (profile_id, module DESC, started_at DESC);
|
||||
|
||||
COMMENT ON COLUMN csv_import_log.affected_ids IS 'Pro Import gesammelte Primärschlüssel je Tabelle (Rollback / Bereinigung)';
|
||||
|
||||
INSERT INTO system_config (key, value, updated_at)
|
||||
VALUES (
|
||||
'csv_import',
|
||||
'{"max_rows_per_file": 50000, "max_file_bytes": 52428800}'::jsonb,
|
||||
CURRENT_TIMESTAMP
|
||||
)
|
||||
ON CONFLICT (key) DO NOTHING;
|
||||
@@ -0,0 +1,315 @@
|
||||
-- Migration 043: CSV Parser – System-Templates (Issue #21)
|
||||
-- Idempotent: pro Template nur einfügen, wenn noch kein System-Eintrag für module+mapping_name existiert.
|
||||
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions
|
||||
)
|
||||
SELECT
|
||||
NULL,
|
||||
true,
|
||||
'nutrition',
|
||||
'FDDB Export (Standard)',
|
||||
'Standard-Format für FDDB.de CSV-Exporte (Deutsch). Delimiter Semikolon, kJ → kcal Konvertierung.',
|
||||
ARRAY['datum_tag_monat_jahr_stunde_minute', 'fett_g', 'kh_g', 'kj', 'protein_g']::TEXT[],
|
||||
';',
|
||||
'utf-8',
|
||||
true,
|
||||
'{
|
||||
"datum_tag_monat_jahr_stunde_minute": "date",
|
||||
"kj": "kcal",
|
||||
"fett_g": "fat_g",
|
||||
"kh_g": "carbs_g",
|
||||
"protein_g": "protein_g"
|
||||
}'::JSONB,
|
||||
'{
|
||||
"date": {
|
||||
"type": "date",
|
||||
"format": "dd.mm.yyyy HH:MM",
|
||||
"extract": "date_only"
|
||||
},
|
||||
"kcal": {
|
||||
"type": "float",
|
||||
"source_unit": "kj",
|
||||
"decimal_separator": ","
|
||||
},
|
||||
"fat_g": {"type": "float", "decimal_separator": ","},
|
||||
"carbs_g": {"type": "float", "decimal_separator": ","},
|
||||
"protein_g": {"type": "float", "decimal_separator": ","}
|
||||
}'::JSONB
|
||||
WHERE NOT EXISTS (
|
||||
SELECT 1 FROM csv_field_mappings f
|
||||
WHERE f.is_system AND f.profile_id IS NULL
|
||||
AND f.module = 'nutrition' AND f.mapping_name = 'FDDB Export (Standard)'
|
||||
);
|
||||
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions
|
||||
)
|
||||
SELECT
|
||||
NULL, true, 'nutrition', 'MyFitnessPal Export',
|
||||
'Standard CSV export from MyFitnessPal (English)',
|
||||
ARRAY['Carbohydrates (g)', 'Calories', 'Date', 'Fat (g)', 'Protein (g)']::TEXT[],
|
||||
',', 'utf-8', true,
|
||||
'{
|
||||
"Date": "date",
|
||||
"Calories": "kcal",
|
||||
"Fat (g)": "fat_g",
|
||||
"Carbohydrates (g)": "carbs_g",
|
||||
"Protein (g)": "protein_g"
|
||||
}'::JSONB,
|
||||
'{
|
||||
"date": {"type": "date", "format": "yyyy-mm-dd"},
|
||||
"kcal": {"type": "float", "decimal_separator": "."},
|
||||
"fat_g": {"type": "float", "decimal_separator": "."},
|
||||
"carbs_g": {"type": "float", "decimal_separator": "."},
|
||||
"protein_g": {"type": "float", "decimal_separator": "."}
|
||||
}'::JSONB
|
||||
WHERE NOT EXISTS (
|
||||
SELECT 1 FROM csv_field_mappings f
|
||||
WHERE f.is_system AND f.profile_id IS NULL
|
||||
AND f.module = 'nutrition' AND f.mapping_name = 'MyFitnessPal Export'
|
||||
);
|
||||
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions
|
||||
)
|
||||
SELECT
|
||||
NULL, true, 'nutrition', 'Cronometer Export',
|
||||
'Cronometer daily nutrition export (English)',
|
||||
ARRAY['Day', 'Energy (kcal)', 'Fat (g)', 'Net Carbs (g)', 'Protein (g)']::TEXT[],
|
||||
',', 'utf-8', true,
|
||||
'{
|
||||
"Day": "date",
|
||||
"Energy (kcal)": "kcal",
|
||||
"Fat (g)": "fat_g",
|
||||
"Net Carbs (g)": "carbs_g",
|
||||
"Protein (g)": "protein_g"
|
||||
}'::JSONB,
|
||||
'{
|
||||
"date": {"type": "date", "format": "yyyy-mm-dd"},
|
||||
"kcal": {"type": "float", "decimal_separator": "."},
|
||||
"fat_g": {"type": "float", "decimal_separator": "."},
|
||||
"carbs_g": {"type": "float", "decimal_separator": "."},
|
||||
"protein_g": {"type": "float", "decimal_separator": "."}
|
||||
}'::JSONB
|
||||
WHERE NOT EXISTS (
|
||||
SELECT 1 FROM csv_field_mappings f
|
||||
WHERE f.is_system AND f.profile_id IS NULL
|
||||
AND f.module = 'nutrition' AND f.mapping_name = 'Cronometer Export'
|
||||
);
|
||||
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions
|
||||
)
|
||||
SELECT
|
||||
NULL, true, 'activity', 'Apple Health Workout Export (English)',
|
||||
'Apple Health CSV-Export für Workouts (English). Automatisches Training-Type-Mapping.',
|
||||
ARRAY['Active Energy (kcal)', 'Distance (km)', 'Duration', 'End', 'Heart Rate Average (bpm)', 'Start', 'Workout Type']::TEXT[],
|
||||
',', 'utf-8', true,
|
||||
'{
|
||||
"Workout Type": "activity_type",
|
||||
"Start": "start_time",
|
||||
"End": "end_time",
|
||||
"Duration": "duration_min",
|
||||
"Distance (km)": "distance_km",
|
||||
"Active Energy (kcal)": "kcal_active",
|
||||
"Heart Rate Average (bpm)": "hr_avg"
|
||||
}'::JSONB,
|
||||
'{
|
||||
"start_time": {"type": "datetime", "format": "yyyy-mm-dd HH:MM:SS", "extract": "date_and_time", "flexible": true},
|
||||
"end_time": {"type": "datetime", "format": "yyyy-mm-dd HH:MM:SS", "flexible": true},
|
||||
"duration_min": {"type": "duration", "format": "HH:MM:SS", "target_unit": "minutes"},
|
||||
"distance_km": {"type": "float", "decimal_separator": "."},
|
||||
"kcal_active": {"type": "float", "decimal_separator": "."},
|
||||
"hr_avg": {"type": "int"}
|
||||
}'::JSONB
|
||||
WHERE NOT EXISTS (
|
||||
SELECT 1 FROM csv_field_mappings f
|
||||
WHERE f.is_system AND f.profile_id IS NULL
|
||||
AND f.module = 'activity' AND f.mapping_name = 'Apple Health Workout Export (English)'
|
||||
);
|
||||
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions
|
||||
)
|
||||
SELECT
|
||||
NULL, true, 'activity', 'Apple Health Workout Export (Deutsch)',
|
||||
'Apple Health CSV-Export für Workouts (Deutsch). Automatisches Training-Type-Mapping.',
|
||||
ARRAY['Aktive Energie (kJ)', 'Aktive Energie (kcal)', 'Dauer', 'Durchschnittliche Herzfrequenz (bpm)', 'Ende', 'Ruheeinträge (kJ)', 'Start', 'Strecke (km)', 'Trainingsart']::TEXT[],
|
||||
',', 'utf-8', true,
|
||||
'{
|
||||
"Trainingsart": "activity_type",
|
||||
"Start": "start_time",
|
||||
"Ende": "end_time",
|
||||
"Dauer": "duration_min",
|
||||
"Strecke (km)": "distance_km",
|
||||
"Aktive Energie (kcal)": "kcal_active",
|
||||
"Aktive Energie (kJ)": "kcal_active",
|
||||
"Ruheeinträge (kJ)": "kcal_resting",
|
||||
"Durchschnittliche Herzfrequenz (bpm)": "hr_avg"
|
||||
}'::JSONB,
|
||||
'{
|
||||
"start_time": {"type": "datetime", "format": "yyyy-mm-dd HH:MM:SS", "extract": "date_and_time", "flexible": true},
|
||||
"end_time": {"type": "datetime", "format": "yyyy-mm-dd HH:MM:SS", "flexible": true},
|
||||
"duration_min": {"type": "duration", "format": "HH:MM:SS", "target_unit": "minutes"},
|
||||
"distance_km": {"type": "float", "decimal_separator": ",", "flexible": true},
|
||||
"kcal_active": {"type": "float", "decimal_separator": ".", "flexible": true, "source_unit": "kj"},
|
||||
"kcal_resting": {"type": "float", "decimal_separator": ".", "flexible": true, "source_unit": "kj"},
|
||||
"hr_avg": {"type": "int", "flexible": true}
|
||||
}'::JSONB
|
||||
WHERE NOT EXISTS (
|
||||
SELECT 1 FROM csv_field_mappings f
|
||||
WHERE f.is_system AND f.profile_id IS NULL
|
||||
AND f.module = 'activity' AND f.mapping_name = 'Apple Health Workout Export (Deutsch)'
|
||||
);
|
||||
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions
|
||||
)
|
||||
SELECT
|
||||
NULL, true, 'activity', 'Garmin Connect Export',
|
||||
'Garmin Connect activity CSV export (English)',
|
||||
ARRAY['Activity Type', 'Avg HR', 'Calories', 'Date', 'Distance', 'Duration', 'Time']::TEXT[],
|
||||
',', 'utf-8', true,
|
||||
'{
|
||||
"Activity Type": "activity_type",
|
||||
"Date": "date",
|
||||
"Time": "start_time",
|
||||
"Duration": "duration_min",
|
||||
"Distance": "distance_km",
|
||||
"Calories": "kcal_active",
|
||||
"Avg HR": "hr_avg"
|
||||
}'::JSONB,
|
||||
'{
|
||||
"date": {"type": "date", "format": "yyyy-mm-dd"},
|
||||
"start_time": {"type": "time", "format": "HH:MM:SS"},
|
||||
"duration_min": {"type": "duration", "format": "HH:MM:SS", "target_unit": "minutes"},
|
||||
"distance_km": {"type": "float", "decimal_separator": "."},
|
||||
"kcal_active": {"type": "float", "decimal_separator": "."},
|
||||
"hr_avg": {"type": "int"}
|
||||
}'::JSONB
|
||||
WHERE NOT EXISTS (
|
||||
SELECT 1 FROM csv_field_mappings f
|
||||
WHERE f.is_system AND f.profile_id IS NULL
|
||||
AND f.module = 'activity' AND f.mapping_name = 'Garmin Connect Export'
|
||||
);
|
||||
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions
|
||||
)
|
||||
SELECT
|
||||
NULL, true, 'blood_pressure', 'Omron Export (Deutsch)',
|
||||
'Omron Blutdruckmessgerät CSV-Export (Deutsch)',
|
||||
ARRAY['Datum', 'Diastolisch (mmHg)', 'Puls (bpm)', 'Systolisch (mmHg)', 'Zeit']::TEXT[],
|
||||
',', 'utf-8', true,
|
||||
'{
|
||||
"Datum": "measured_date",
|
||||
"Zeit": "measured_time",
|
||||
"Systolisch (mmHg)": "systolic",
|
||||
"Diastolisch (mmHg)": "diastolic",
|
||||
"Puls (bpm)": "pulse"
|
||||
}'::JSONB,
|
||||
'{
|
||||
"measured_date": {"type": "date", "format": "dd.mm.yyyy"},
|
||||
"measured_time": {"type": "time", "format": "HH:MM"},
|
||||
"systolic": {"type": "int"},
|
||||
"diastolic": {"type": "int"},
|
||||
"pulse": {"type": "int"}
|
||||
}'::JSONB
|
||||
WHERE NOT EXISTS (
|
||||
SELECT 1 FROM csv_field_mappings f
|
||||
WHERE f.is_system AND f.profile_id IS NULL
|
||||
AND f.module = 'blood_pressure' AND f.mapping_name = 'Omron Export (Deutsch)'
|
||||
);
|
||||
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions
|
||||
)
|
||||
SELECT
|
||||
NULL, true, 'blood_pressure', 'Omron Export (English)',
|
||||
'Omron blood pressure monitor CSV export (English)',
|
||||
ARRAY['Date', 'Diastolic (mmHg)', 'Pulse (bpm)', 'Systolic (mmHg)', 'Time']::TEXT[],
|
||||
',', 'utf-8', true,
|
||||
'{
|
||||
"Date": "measured_date",
|
||||
"Time": "measured_time",
|
||||
"Systolic (mmHg)": "systolic",
|
||||
"Diastolic (mmHg)": "diastolic",
|
||||
"Pulse (bpm)": "pulse"
|
||||
}'::JSONB,
|
||||
'{
|
||||
"measured_date": {"type": "date", "format": "mm/dd/yyyy"},
|
||||
"measured_time": {"type": "time", "format": "HH:MM"},
|
||||
"systolic": {"type": "int"},
|
||||
"diastolic": {"type": "int"},
|
||||
"pulse": {"type": "int"}
|
||||
}'::JSONB
|
||||
WHERE NOT EXISTS (
|
||||
SELECT 1 FROM csv_field_mappings f
|
||||
WHERE f.is_system AND f.profile_id IS NULL
|
||||
AND f.module = 'blood_pressure' AND f.mapping_name = 'Omron Export (English)'
|
||||
);
|
||||
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions
|
||||
)
|
||||
SELECT
|
||||
NULL, true, 'weight', 'Apple Health Weight Export',
|
||||
'Apple Health body mass CSV export',
|
||||
ARRAY['Body Mass (kg)', 'Start']::TEXT[],
|
||||
',', 'utf-8', true,
|
||||
'{
|
||||
"Start": "date",
|
||||
"Body Mass (kg)": "weight"
|
||||
}'::JSONB,
|
||||
'{
|
||||
"date": {"type": "datetime", "format": "yyyy-mm-dd HH:MM:SS", "extract": "date_only"},
|
||||
"weight": {"type": "float", "decimal_separator": "."}
|
||||
}'::JSONB
|
||||
WHERE NOT EXISTS (
|
||||
SELECT 1 FROM csv_field_mappings f
|
||||
WHERE f.is_system AND f.profile_id IS NULL
|
||||
AND f.module = 'weight' AND f.mapping_name = 'Apple Health Weight Export'
|
||||
);
|
||||
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions
|
||||
)
|
||||
SELECT
|
||||
NULL, true, 'weight', 'Withings Export',
|
||||
'Withings smart scale CSV export (weight, body fat, muscle mass)',
|
||||
ARRAY['Body Fat (%)', 'Date', 'Muscle Mass (kg)', 'Weight (kg)']::TEXT[],
|
||||
',', 'utf-8', true,
|
||||
'{
|
||||
"Date": "date",
|
||||
"Weight (kg)": "weight"
|
||||
}'::JSONB,
|
||||
'{
|
||||
"date": {"type": "date", "format": "yyyy-mm-dd"},
|
||||
"weight": {"type": "float", "decimal_separator": "."}
|
||||
}'::JSONB
|
||||
WHERE NOT EXISTS (
|
||||
SELECT 1 FROM csv_field_mappings f
|
||||
WHERE f.is_system AND f.profile_id IS NULL
|
||||
AND f.module = 'weight' AND f.mapping_name = 'Withings Export'
|
||||
);
|
||||
@@ -0,0 +1,155 @@
|
||||
-- Migration 044: CSV Parser — System-Vorlagen Schlaf (Apple) + Vitalwerte Baseline (Issue #21)
|
||||
-- Idempotent wie 043.
|
||||
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions
|
||||
)
|
||||
SELECT
|
||||
NULL,
|
||||
true,
|
||||
'sleep',
|
||||
'Apple Health Schlaf (Segment-Export)',
|
||||
'Apple-Health-Schlaf-CSV mit Phasen-Zeilen (Start, End, Duration (hr), Value). Import läuft aggregiert pro Nacht.',
|
||||
ARRAY['Start', 'End', 'Duration (hr)', 'Value']::TEXT[],
|
||||
',',
|
||||
'utf-8',
|
||||
true,
|
||||
'{
|
||||
"Start": "-",
|
||||
"End": "-",
|
||||
"Duration (hr)": "-",
|
||||
"Value": "-"
|
||||
}'::JSONB,
|
||||
'{}'::JSONB
|
||||
WHERE NOT EXISTS (
|
||||
SELECT 1 FROM csv_field_mappings f
|
||||
WHERE f.is_system AND f.profile_id IS NULL
|
||||
AND f.module = 'sleep' AND f.mapping_name = 'Apple Health Schlaf (Segment-Export)'
|
||||
);
|
||||
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions
|
||||
)
|
||||
SELECT
|
||||
NULL,
|
||||
true,
|
||||
'sleep',
|
||||
'Apple Health Schlaf (Schlafanalyse / Nacht)',
|
||||
'Apple-Health-Schlafanalyse mit Nacht-Zusammenfassung (u. a. Total Sleep (hr), Start, End).',
|
||||
ARRAY['Start', 'End', 'Total Sleep (hr)']::TEXT[],
|
||||
',',
|
||||
'utf-8',
|
||||
true,
|
||||
'{
|
||||
"Start": "-",
|
||||
"End": "-",
|
||||
"Total Sleep (hr)": "-"
|
||||
}'::JSONB,
|
||||
'{}'::JSONB
|
||||
WHERE NOT EXISTS (
|
||||
SELECT 1 FROM csv_field_mappings f
|
||||
WHERE f.is_system AND f.profile_id IS NULL
|
||||
AND f.module = 'sleep' AND f.mapping_name = 'Apple Health Schlaf (Schlafanalyse / Nacht)'
|
||||
);
|
||||
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions
|
||||
)
|
||||
SELECT
|
||||
NULL,
|
||||
true,
|
||||
'vitals_baseline',
|
||||
'Apple Health Baseline Vitals (English)',
|
||||
'Tägliche Baseline-Messungen aus Apple Health (Ruhepuls, HRV, VO2, SpO2, Atemfrequenz).',
|
||||
ARRAY[
|
||||
'Start',
|
||||
'Resting Heart Rate',
|
||||
'Heart Rate Variability',
|
||||
'VO2 Max',
|
||||
'Oxygen Saturation',
|
||||
'Respiratory Rate'
|
||||
]::TEXT[],
|
||||
',',
|
||||
'utf-8',
|
||||
true,
|
||||
'{
|
||||
"Start": "date",
|
||||
"Resting Heart Rate": "resting_hr",
|
||||
"Heart Rate Variability": "hrv",
|
||||
"VO2 Max": "vo2_max",
|
||||
"Oxygen Saturation": "spo2",
|
||||
"Respiratory Rate": "respiratory_rate"
|
||||
}'::JSONB,
|
||||
'{
|
||||
"date": {
|
||||
"type": "datetime",
|
||||
"format": "yyyy-mm-dd HH:MM:SS",
|
||||
"extract": "date_only",
|
||||
"flexible": true
|
||||
},
|
||||
"resting_hr": {"type": "int", "flexible": true},
|
||||
"hrv": {"type": "int", "flexible": true},
|
||||
"vo2_max": {"type": "float", "decimal_separator": "auto", "flexible": true},
|
||||
"spo2": {"type": "int", "flexible": true},
|
||||
"respiratory_rate": {"type": "float", "decimal_separator": "auto", "flexible": true}
|
||||
}'::JSONB
|
||||
WHERE NOT EXISTS (
|
||||
SELECT 1 FROM csv_field_mappings f
|
||||
WHERE f.is_system AND f.profile_id IS NULL
|
||||
AND f.module = 'vitals_baseline' AND f.mapping_name = 'Apple Health Baseline Vitals (English)'
|
||||
);
|
||||
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions
|
||||
)
|
||||
SELECT
|
||||
NULL,
|
||||
true,
|
||||
'vitals_baseline',
|
||||
'Apple Health Baseline Vitals (Deutsch)',
|
||||
'Tägliche Baseline-Messungen aus Apple Health (deutsche Spaltenbezeichnungen).',
|
||||
ARRAY[
|
||||
'Datum/Uhrzeit',
|
||||
'Ruhepuls (count/min)',
|
||||
'Herzfrequenzvariabilität (ms)',
|
||||
'VO2 max (ml/(kg·min))',
|
||||
'Blutsauerstoffsättigung (%)',
|
||||
'Atemfrequenz (count/min)'
|
||||
]::TEXT[],
|
||||
',',
|
||||
'utf-8',
|
||||
true,
|
||||
'{
|
||||
"Datum/Uhrzeit": "date",
|
||||
"Ruhepuls (count/min)": "resting_hr",
|
||||
"Herzfrequenzvariabilität (ms)": "hrv",
|
||||
"VO2 max (ml/(kg·min))": "vo2_max",
|
||||
"Blutsauerstoffsättigung (%)": "spo2",
|
||||
"Atemfrequenz (count/min)": "respiratory_rate"
|
||||
}'::JSONB,
|
||||
'{
|
||||
"date": {
|
||||
"type": "datetime",
|
||||
"format": "yyyy-mm-dd HH:MM:SS",
|
||||
"extract": "date_only",
|
||||
"flexible": true
|
||||
},
|
||||
"resting_hr": {"type": "int", "flexible": true},
|
||||
"hrv": {"type": "int", "flexible": true},
|
||||
"vo2_max": {"type": "float", "decimal_separator": "auto", "flexible": true},
|
||||
"spo2": {"type": "int", "flexible": true},
|
||||
"respiratory_rate": {"type": "float", "decimal_separator": "auto", "flexible": true}
|
||||
}'::JSONB
|
||||
WHERE NOT EXISTS (
|
||||
SELECT 1 FROM csv_field_mappings f
|
||||
WHERE f.is_system AND f.profile_id IS NULL
|
||||
AND f.module = 'vitals_baseline' AND f.mapping_name = 'Apple Health Baseline Vitals (Deutsch)'
|
||||
);
|
||||
@@ -0,0 +1,27 @@
|
||||
-- Migration 045: Schlaf-Systemvorlage — Signatur wie „Schlafanalyse“-Export (Date/Time, Sources, …)
|
||||
-- Ergänzt die Vorlage aus 044 für besseres Matching; Import-Logik unverändert (Apple-Aggregat-Parser).
|
||||
|
||||
UPDATE csv_field_mappings
|
||||
SET
|
||||
column_signature = ARRAY[
|
||||
'Date/Time',
|
||||
'Start',
|
||||
'End',
|
||||
'Total Sleep (hr)',
|
||||
'Asleep (Unspecified) (hr)',
|
||||
'In Bed (hr)',
|
||||
'Core (hr)',
|
||||
'Deep (hr)',
|
||||
'REM (hr)',
|
||||
'Awake (hr)',
|
||||
'Sources'
|
||||
]::TEXT[],
|
||||
description = COALESCE(
|
||||
description,
|
||||
'Apple-Health-Schlafanalyse (Nacht-Zusammenfassung): Spalten wie Date/Time, Start/End mit Zeitzone, Kern/Tief/REM etc.'
|
||||
),
|
||||
updated_at = CURRENT_TIMESTAMP
|
||||
WHERE is_system = true
|
||||
AND profile_id IS NULL
|
||||
AND module = 'sleep'
|
||||
AND mapping_name = 'Apple Health Schlaf (Schlafanalyse / Nacht)';
|
||||
@@ -0,0 +1,19 @@
|
||||
-- Migration 046: FDDB-Systemvorlage — kcal ohne legacy conversion_factor/target_unit (Issue #21, source_unit-Registry)
|
||||
-- Doppelte Umrechnung (kj-Faktor * 0.239) wurde fälschlich gespeichert; target_unit ist nur für duration vorgesehen.
|
||||
|
||||
UPDATE csv_field_mappings
|
||||
SET type_conversions = jsonb_set(
|
||||
type_conversions,
|
||||
'{kcal}',
|
||||
((type_conversions->'kcal') - 'conversion_factor' - 'target_unit')
|
||||
|| jsonb_build_object('source_unit', 'kj')
|
||||
)
|
||||
WHERE is_system = true
|
||||
AND profile_id IS NULL
|
||||
AND module = 'nutrition'
|
||||
AND mapping_name = 'FDDB Export (Standard)'
|
||||
AND (type_conversions->'kcal') IS NOT NULL
|
||||
AND (
|
||||
(type_conversions->'kcal') ? 'conversion_factor'
|
||||
OR (type_conversions->'kcal') ? 'target_unit'
|
||||
);
|
||||
@@ -0,0 +1,7 @@
|
||||
-- Migration 047: CSV-Vorlagen — optionale Zeilenaggregation (group_by + aggregates) vor DB-Schreiben
|
||||
|
||||
ALTER TABLE csv_field_mappings
|
||||
ADD COLUMN IF NOT EXISTS import_row_processing JSONB;
|
||||
|
||||
COMMENT ON COLUMN csv_field_mappings.import_row_processing IS
|
||||
'Optional: { "group_by": ["date"], "aggregates": { "kcal": "sum" } } — siehe csv_parser/import_row_processing.py';
|
||||
@@ -0,0 +1,29 @@
|
||||
-- Universal-CSV-Import setzt source = 'csv'. Alte CHECK-Constraints kennen das nicht.
|
||||
-- Alle passenden CHECKs zu `source` droppen (PG speichert IN oder = ANY (ARRAY[...])).
|
||||
DO $$
|
||||
DECLARE
|
||||
r RECORD;
|
||||
BEGIN
|
||||
FOR r IN
|
||||
SELECT c.conname
|
||||
FROM pg_constraint c
|
||||
JOIN pg_class t ON c.conrelid = t.oid
|
||||
JOIN pg_namespace n ON n.oid = t.relnamespace
|
||||
WHERE n.nspname = 'public'
|
||||
AND t.relname = 'vitals_baseline'
|
||||
AND c.contype = 'c'
|
||||
AND (
|
||||
c.conname = 'vitals_baseline_source_check'
|
||||
OR COALESCE(pg_get_constraintdef(c.oid), '') ILIKE '%source%'
|
||||
)
|
||||
LOOP
|
||||
EXECUTE format('ALTER TABLE public.vitals_baseline DROP CONSTRAINT %I', r.conname);
|
||||
END LOOP;
|
||||
END $$;
|
||||
|
||||
ALTER TABLE public.vitals_baseline DROP CONSTRAINT IF EXISTS vitals_baseline_source_check;
|
||||
|
||||
ALTER TABLE public.vitals_baseline ADD CONSTRAINT vitals_baseline_source_check
|
||||
CHECK (source IN ('manual', 'apple_health', 'garmin', 'withings', 'csv'));
|
||||
|
||||
COMMENT ON COLUMN vitals_baseline.source IS 'manual | apple_health | garmin | withings | csv (Universal-Import)';
|
||||
@@ -0,0 +1,30 @@
|
||||
-- Idempotent: gleicher Zielzustand wie 048, auch wenn die CHECK schon existiert (z. B. 048 DB-seitig
|
||||
-- erfolgreich, aber nicht in schema_migrations). Ein einziges DO vermeidet Mehrfach-Statement-Probleme.
|
||||
DO $$
|
||||
DECLARE
|
||||
r RECORD;
|
||||
BEGIN
|
||||
FOR r IN
|
||||
SELECT c.conname
|
||||
FROM pg_constraint c
|
||||
JOIN pg_class t ON c.conrelid = t.oid
|
||||
JOIN pg_namespace n ON n.oid = t.relnamespace
|
||||
WHERE n.nspname = 'public'
|
||||
AND t.relname = 'vitals_baseline'
|
||||
AND c.contype = 'c'
|
||||
AND (
|
||||
c.conname = 'vitals_baseline_source_check'
|
||||
OR COALESCE(pg_get_constraintdef(c.oid), '') ILIKE '%source%'
|
||||
)
|
||||
LOOP
|
||||
EXECUTE format('ALTER TABLE public.vitals_baseline DROP CONSTRAINT %I', r.conname);
|
||||
END LOOP;
|
||||
|
||||
EXECUTE $ddl$
|
||||
ALTER TABLE public.vitals_baseline ADD CONSTRAINT vitals_baseline_source_check
|
||||
CHECK (source IN ('manual', 'apple_health', 'garmin', 'withings', 'csv'))
|
||||
$ddl$;
|
||||
EXCEPTION
|
||||
WHEN duplicate_object THEN
|
||||
NULL;
|
||||
END $$;
|
||||
@@ -0,0 +1,26 @@
|
||||
-- Apple Health Workout-CSV: Zeit oft ohne Sekunden (HH:MM); dateutil dayfirst bricht ISO YYYY-MM-DD.
|
||||
-- type_converter: zusätzliche Patterns + ISO-reihenfolge in _dateutil_parse.
|
||||
-- Bestehende System-Vorlagen: flexible für Start/End (idempotent).
|
||||
|
||||
UPDATE csv_field_mappings
|
||||
SET type_conversions = jsonb_set(
|
||||
jsonb_set(
|
||||
COALESCE(type_conversions, '{}'::jsonb),
|
||||
'{start_time}',
|
||||
COALESCE(type_conversions->'start_time', '{}'::jsonb) || '{"flexible": true}'::jsonb,
|
||||
true
|
||||
),
|
||||
'{end_time}',
|
||||
COALESCE(type_conversions->'end_time', '{}'::jsonb) || '{"flexible": true}'::jsonb,
|
||||
true
|
||||
)
|
||||
WHERE is_system = true
|
||||
AND profile_id IS NULL
|
||||
AND module = 'activity'
|
||||
AND mapping_name IN (
|
||||
'Apple Health Workout Export (English)',
|
||||
'Apple Health Workout Export (Deutsch)'
|
||||
)
|
||||
AND type_conversions IS NOT NULL
|
||||
AND type_conversions ? 'start_time'
|
||||
AND type_conversions ? 'end_time';
|
||||
@@ -0,0 +1,9 @@
|
||||
-- Universal-CSV-Import schreibt source = 'csv' (siehe csv_parser/executor _import_blood_pressure).
|
||||
|
||||
ALTER TABLE blood_pressure_log DROP CONSTRAINT IF EXISTS blood_pressure_log_source_check;
|
||||
|
||||
ALTER TABLE blood_pressure_log ADD CONSTRAINT blood_pressure_log_source_check
|
||||
CHECK (source IN ('manual', 'omron', 'apple_health', 'withings', 'csv'));
|
||||
|
||||
COMMENT ON COLUMN blood_pressure_log.source IS
|
||||
'manual | omron | apple_health | withings | csv (Universal-CSV-Import)';
|
||||
@@ -0,0 +1,8 @@
|
||||
-- Apple-/Import-Werte: Energie oft >1000 (kJ oder kcal), HR-Felder NUMERIC(5,2) zu eng für Fehlzuordnungen.
|
||||
-- Idempotent: Typ nur anheben, nie verkleinern.
|
||||
|
||||
ALTER TABLE activity_log
|
||||
ALTER COLUMN kcal_active TYPE NUMERIC(12, 2),
|
||||
ALTER COLUMN kcal_resting TYPE NUMERIC(12, 2),
|
||||
ALTER COLUMN hr_avg TYPE NUMERIC(6, 2),
|
||||
ALTER COLUMN hr_max TYPE NUMERIC(6, 2);
|
||||
@@ -0,0 +1,26 @@
|
||||
-- Apple Health Workout (Deutsch): „Aktive Energie (kJ)“ / „Ruheeinträge (kJ)“ → DB speichert kcal.
|
||||
-- type_conversions.source_unit „kj“ nutzt field_units (1/4.184).
|
||||
|
||||
UPDATE csv_field_mappings
|
||||
SET
|
||||
field_mappings = COALESCE(field_mappings, '{}'::jsonb)
|
||||
|| '{"Aktive Energie (kJ)": "kcal_active", "Ruheeinträge (kJ)": "kcal_resting"}'::jsonb,
|
||||
type_conversions = jsonb_set(
|
||||
jsonb_set(
|
||||
COALESCE(type_conversions, '{}'::jsonb),
|
||||
'{kcal_active}',
|
||||
COALESCE(type_conversions->'kcal_active', '{}'::jsonb) || '{"source_unit": "kj"}'::jsonb,
|
||||
true
|
||||
),
|
||||
'{kcal_resting}',
|
||||
COALESCE(
|
||||
type_conversions->'kcal_resting',
|
||||
'{"type": "float", "decimal_separator": ",", "flexible": true}'::jsonb
|
||||
) || '{"source_unit": "kj"}'::jsonb,
|
||||
true
|
||||
)
|
||||
WHERE is_system = true
|
||||
AND profile_id IS NULL
|
||||
AND module = 'activity'
|
||||
AND mapping_name = 'Apple Health Workout Export (Deutsch)'
|
||||
AND type_conversions IS NOT NULL;
|
||||
@@ -0,0 +1,80 @@
|
||||
-- Migration 054: Activity session metrics (EAV) + attribute profiles
|
||||
-- Date: 2026-04-14
|
||||
-- Additive only: safe for production (no data deletion).
|
||||
-- Agent guide: .claude/docs/technical/ACTIVITY_SESSION_METRICS_EAV_AGENT_GUIDE.md
|
||||
|
||||
-- Session interval (nullable; optional backfill later)
|
||||
ALTER TABLE activity_log
|
||||
ADD COLUMN IF NOT EXISTS started_at TIMESTAMPTZ,
|
||||
ADD COLUMN IF NOT EXISTS ended_at TIMESTAMPTZ;
|
||||
|
||||
CREATE INDEX IF NOT EXISTS idx_activity_log_profile_started
|
||||
ON activity_log (profile_id, started_at DESC)
|
||||
WHERE started_at IS NOT NULL;
|
||||
|
||||
COMMENT ON COLUMN activity_log.started_at IS 'Training start (wall clock, TZ-aware); optional; for dedupe/analysis';
|
||||
COMMENT ON COLUMN activity_log.ended_at IS 'Training end (wall clock, TZ-aware); optional';
|
||||
|
||||
-- Which parameters apply to which training category (training_types.category)
|
||||
CREATE TABLE IF NOT EXISTS training_category_parameter (
|
||||
id SERIAL PRIMARY KEY,
|
||||
training_category VARCHAR(50) NOT NULL,
|
||||
training_parameter_id INT NOT NULL REFERENCES training_parameters(id) ON DELETE CASCADE,
|
||||
sort_order INT NOT NULL DEFAULT 0,
|
||||
required BOOLEAN NOT NULL DEFAULT false,
|
||||
ui_group VARCHAR(50),
|
||||
created_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
|
||||
CONSTRAINT uq_training_category_parameter UNIQUE (training_category, training_parameter_id)
|
||||
);
|
||||
|
||||
CREATE INDEX IF NOT EXISTS idx_tcp_category ON training_category_parameter (training_category);
|
||||
|
||||
COMMENT ON TABLE training_category_parameter IS 'EAV schema: parameters enabled per training category';
|
||||
|
||||
-- Per training type: extra parameters or overrides (NULL sort/required/ui = inherit from category row if present)
|
||||
CREATE TABLE IF NOT EXISTS training_type_parameter (
|
||||
id SERIAL PRIMARY KEY,
|
||||
training_type_id INT NOT NULL REFERENCES training_types(id) ON DELETE CASCADE,
|
||||
training_parameter_id INT NOT NULL REFERENCES training_parameters(id) ON DELETE CASCADE,
|
||||
sort_order INT,
|
||||
required BOOLEAN,
|
||||
ui_group VARCHAR(50),
|
||||
created_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
|
||||
CONSTRAINT uq_training_type_parameter UNIQUE (training_type_id, training_parameter_id)
|
||||
);
|
||||
|
||||
CREATE INDEX IF NOT EXISTS idx_ttp_type ON training_type_parameter (training_type_id);
|
||||
|
||||
COMMENT ON TABLE training_type_parameter IS 'EAV schema: add/override parameters for a concrete training_types row';
|
||||
|
||||
-- EAV values per activity session
|
||||
CREATE TABLE IF NOT EXISTS activity_session_metrics (
|
||||
id BIGSERIAL PRIMARY KEY,
|
||||
activity_log_id UUID NOT NULL REFERENCES activity_log(id) ON DELETE CASCADE,
|
||||
training_parameter_id INT NOT NULL REFERENCES training_parameters(id) ON DELETE RESTRICT,
|
||||
value_num DOUBLE PRECISION,
|
||||
value_int BIGINT,
|
||||
value_text TEXT,
|
||||
value_bool BOOLEAN,
|
||||
created_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
|
||||
updated_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
|
||||
CONSTRAINT uq_activity_session_metric UNIQUE (activity_log_id, training_parameter_id),
|
||||
CONSTRAINT chk_activity_session_metric_one_value CHECK (
|
||||
(
|
||||
(value_num IS NOT NULL)::int
|
||||
+ (value_int IS NOT NULL)::int
|
||||
+ (value_text IS NOT NULL)::int
|
||||
+ (value_bool IS NOT NULL)::int
|
||||
) = 1
|
||||
)
|
||||
);
|
||||
|
||||
CREATE INDEX IF NOT EXISTS idx_asm_activity ON activity_session_metrics (activity_log_id);
|
||||
CREATE INDEX IF NOT EXISTS idx_asm_parameter ON activity_session_metrics (training_parameter_id);
|
||||
|
||||
COMMENT ON TABLE activity_session_metrics IS 'EAV: one row per (session, training_parameter); exactly one value_* set';
|
||||
|
||||
DO $$
|
||||
BEGIN
|
||||
RAISE NOTICE 'Migration 054: activity_session_metrics EAV + attribute profile tables + activity_log timestamps';
|
||||
END $$;
|
||||
@@ -0,0 +1,213 @@
|
||||
-- Migration 055: Seed training_category_parameter (all categories × parameters with activity_log source_field)
|
||||
-- + idempotent backfill activity_log → activity_session_metrics (EAV)
|
||||
-- Date: 2026-04-15
|
||||
-- SAFE: INSERT … ON CONFLICT DO NOTHING only; no DELETE/TRUNCATE on activity_log.
|
||||
-- Agent guide: .claude/docs/technical/ACTIVITY_SESSION_METRICS_EAV_AGENT_GUIDE.md
|
||||
|
||||
--1) Jede in training_types vorkommende Kategorie erhält alle aktiven Parameter mit source_field (Spalte in activity_log).
|
||||
INSERT INTO training_category_parameter (
|
||||
training_category,
|
||||
training_parameter_id,
|
||||
sort_order,
|
||||
required,
|
||||
ui_group
|
||||
)
|
||||
SELECT
|
||||
tc.training_category,
|
||||
tp.id,
|
||||
ROW_NUMBER() OVER (
|
||||
PARTITION BY tc.training_category
|
||||
ORDER BY tp.category, tp.id
|
||||
),
|
||||
false,
|
||||
NULL
|
||||
FROM (
|
||||
SELECT DISTINCT category AS training_category
|
||||
FROM training_types
|
||||
WHERE category IS NOT NULL AND trim(category) <> ''
|
||||
) tc
|
||||
CROSS JOIN training_parameters tp
|
||||
WHERE tp.is_active = true
|
||||
AND tp.source_field IS NOT NULL
|
||||
AND trim(tp.source_field) <> ''
|
||||
ON CONFLICT (training_category, training_parameter_id) DO NOTHING;
|
||||
|
||||
-- 2) Backfill: activity_log-Spalten → EAV (nur wenn noch keine Zeile existiert)
|
||||
|
||||
-- duration_min → integer
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT
|
||||
a.id,
|
||||
tp.id,
|
||||
NULL,
|
||||
ROUND(a.duration_min::numeric)::bigint,
|
||||
NULL,
|
||||
NULL,
|
||||
NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'duration_min' AND tp.is_active = true
|
||||
WHERE a.duration_min IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
-- distance_km → float
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT a.id, tp.id, a.distance_km::double precision, NULL, NULL, NULL, NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'distance_km' AND tp.is_active = true
|
||||
WHERE a.distance_km IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
-- kcal_active
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT a.id, tp.id, NULL, ROUND(a.kcal_active::numeric)::bigint, NULL, NULL, NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'kcal_active' AND tp.is_active = true
|
||||
WHERE a.kcal_active IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT a.id, tp.id, NULL, ROUND(a.kcal_resting::numeric)::bigint, NULL, NULL, NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'kcal_resting' AND tp.is_active = true
|
||||
WHERE a.kcal_resting IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
-- hr_avg / hr_max → keys avg_hr, max_hr
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT a.id, tp.id, NULL, ROUND(a.hr_avg::numeric)::bigint, NULL, NULL, NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'avg_hr' AND tp.is_active = true
|
||||
WHERE a.hr_avg IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT a.id, tp.id, NULL, ROUND(a.hr_max::numeric)::bigint, NULL, NULL, NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'max_hr' AND tp.is_active = true
|
||||
WHERE a.hr_max IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
-- rpe
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT a.id, tp.id, NULL, a.rpe::bigint, NULL, NULL, NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'rpe' AND tp.is_active = true
|
||||
WHERE a.rpe IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
-- min_hr (Spalte hr_min nach Migration 014)
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT a.id, tp.id, NULL, a.hr_min, NULL, NULL, NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'min_hr' AND tp.is_active = true
|
||||
WHERE a.hr_min IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT a.id, tp.id, a.pace_min_per_km::double precision, NULL, NULL, NULL, NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'pace_min_per_km' AND tp.is_active = true
|
||||
WHERE a.pace_min_per_km IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT a.id, tp.id, NULL, a.cadence, NULL, NULL, NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'cadence' AND tp.is_active = true
|
||||
WHERE a.cadence IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT a.id, tp.id, NULL, a.avg_power, NULL, NULL, NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'avg_power' AND tp.is_active = true
|
||||
WHERE a.avg_power IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT a.id, tp.id, NULL, a.elevation_gain, NULL, NULL, NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'elevation_gain' AND tp.is_active = true
|
||||
WHERE a.elevation_gain IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT a.id, tp.id, a.temperature_celsius::double precision, NULL, NULL, NULL, NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'temperature_celsius' AND tp.is_active = true
|
||||
WHERE a.temperature_celsius IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT a.id, tp.id, NULL, a.humidity_percent, NULL, NULL, NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'humidity_percent' AND tp.is_active = true
|
||||
WHERE a.humidity_percent IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT a.id, tp.id, a.avg_hr_percent::double precision, NULL, NULL, NULL, NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'avg_hr_percent' AND tp.is_active = true
|
||||
WHERE a.avg_hr_percent IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT a.id, tp.id, a.kcal_per_km::double precision, NULL, NULL, NULL, NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'kcal_per_km' AND tp.is_active = true
|
||||
WHERE a.kcal_per_km IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
DO $$
|
||||
BEGIN
|
||||
RAISE NOTICE 'Migration 055: category parameter seed + EAV backfill from activity_log (no row deletes)';
|
||||
END $$;
|
||||
@@ -0,0 +1,35 @@
|
||||
-- Migration 056: kcal_per_km Trigger — manuelles Leeren bei UPDATE erlauben
|
||||
-- Problem: calculate_avg_hr_percent (014) setzte bei jedem UPDATE kcal_per_km aus
|
||||
-- kcal_active/distance_km, sobald beide gesetzt waren — ein bewusst geleertes Feld
|
||||
-- erschien sofort wieder.
|
||||
-- Lösung: automatische Ableitung nur noch bei INSERT (wenn kcal_per_km noch NULL ist).
|
||||
|
||||
CREATE OR REPLACE FUNCTION calculate_avg_hr_percent()
|
||||
RETURNS TRIGGER AS $$
|
||||
DECLARE
|
||||
user_max_hr INTEGER;
|
||||
BEGIN
|
||||
SELECT hf_max INTO user_max_hr
|
||||
FROM profiles
|
||||
WHERE id = NEW.profile_id;
|
||||
|
||||
IF NEW.hr_avg IS NOT NULL AND user_max_hr IS NOT NULL AND user_max_hr > 0 THEN
|
||||
NEW.avg_hr_percent := (NEW.hr_avg::float / user_max_hr::float) * 100;
|
||||
END IF;
|
||||
|
||||
IF TG_OP = 'INSERT' THEN
|
||||
IF NEW.kcal_active IS NOT NULL AND NEW.distance_km IS NOT NULL AND NEW.distance_km > 0 THEN
|
||||
IF NEW.kcal_per_km IS NULL THEN
|
||||
NEW.kcal_per_km := NEW.kcal_active::float / NEW.distance_km;
|
||||
END IF;
|
||||
END IF;
|
||||
END IF;
|
||||
|
||||
RETURN NEW;
|
||||
END;
|
||||
$$ LANGUAGE plpgsql;
|
||||
|
||||
DO $$
|
||||
BEGIN
|
||||
RAISE NOTICE '✓ Migration 056: kcal_per_km nur noch bei INSERT auto-abgeleitet';
|
||||
END $$;
|
||||
@@ -0,0 +1,115 @@
|
||||
-- Migration 057: Kanon EAV-primär für erweiterte Trainingsmetriken
|
||||
-- Date: 2026-04-15
|
||||
-- activity_log-Spalten bleiben erhalten (Lesefallback / API); training_parameters.source_field
|
||||
-- wird für diese Keys entfernt. Idempotenter EAV-Backfill aus Spalten (wie 055), dann source_field NULL.
|
||||
-- Siehe: backend/data_layer/activity_data_canon.py
|
||||
|
||||
-- min_hr (Spalte hr_min)
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT a.id, tp.id, NULL, a.hr_min, NULL, NULL, NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'min_hr' AND tp.is_active = true
|
||||
WHERE a.hr_min IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT a.id, tp.id, a.pace_min_per_km::double precision, NULL, NULL, NULL, NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'pace_min_per_km' AND tp.is_active = true
|
||||
WHERE a.pace_min_per_km IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT a.id, tp.id, NULL, a.cadence, NULL, NULL, NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'cadence' AND tp.is_active = true
|
||||
WHERE a.cadence IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT a.id, tp.id, NULL, a.avg_power, NULL, NULL, NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'avg_power' AND tp.is_active = true
|
||||
WHERE a.avg_power IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT a.id, tp.id, NULL, a.elevation_gain, NULL, NULL, NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'elevation_gain' AND tp.is_active = true
|
||||
WHERE a.elevation_gain IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT a.id, tp.id, a.temperature_celsius::double precision, NULL, NULL, NULL, NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'temperature_celsius' AND tp.is_active = true
|
||||
WHERE a.temperature_celsius IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT a.id, tp.id, NULL, a.humidity_percent, NULL, NULL, NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'humidity_percent' AND tp.is_active = true
|
||||
WHERE a.humidity_percent IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT a.id, tp.id, a.avg_hr_percent::double precision, NULL, NULL, NULL, NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'avg_hr_percent' AND tp.is_active = true
|
||||
WHERE a.avg_hr_percent IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
INSERT INTO activity_session_metrics (
|
||||
activity_log_id, training_parameter_id,
|
||||
value_num, value_int, value_text, value_bool, updated_at
|
||||
)
|
||||
SELECT a.id, tp.id, a.kcal_per_km::double precision, NULL, NULL, NULL, NOW()
|
||||
FROM activity_log a
|
||||
JOIN training_parameters tp ON tp.key = 'kcal_per_km' AND tp.is_active = true
|
||||
WHERE a.kcal_per_km IS NOT NULL
|
||||
ON CONFLICT (activity_log_id, training_parameter_id) DO NOTHING;
|
||||
|
||||
UPDATE training_parameters
|
||||
SET source_field = NULL
|
||||
WHERE key IN (
|
||||
'min_hr',
|
||||
'pace_min_per_km',
|
||||
'cadence',
|
||||
'avg_power',
|
||||
'elevation_gain',
|
||||
'temperature_celsius',
|
||||
'humidity_percent',
|
||||
'avg_hr_percent',
|
||||
'kcal_per_km'
|
||||
);
|
||||
|
||||
DO $$
|
||||
BEGIN
|
||||
RAISE NOTICE 'Migration 057: EAV-primary canon — backfill + source_field cleared for extended metrics';
|
||||
END $$;
|
||||
@@ -12,30 +12,48 @@
|
||||
-- ============================================================================
|
||||
|
||||
-- ============================================================================
|
||||
-- 1. Rename csv_import to data_import
|
||||
-- 1. csv_import → data_import (FK-sicher)
|
||||
-- ============================================================================
|
||||
UPDATE features
|
||||
SET
|
||||
id = 'data_import',
|
||||
name = 'Daten importieren',
|
||||
description = 'CSV-Import (FDDB, Apple Health) + ZIP-Backup-Import'
|
||||
WHERE id = 'csv_import';
|
||||
-- Zuerst Ziel-Feature-Zeile sichern, dann alle FKs umhängen, dann csv_import
|
||||
-- entfernen. PK direkt per UPDATE ändern scheitert, solange tier_limits noch
|
||||
-- feature_id = 'csv_import' referenziert (tier_limits_feature_id_fkey).
|
||||
|
||||
INSERT INTO features (id, name, description, category, limit_type, reset_period, default_limit, active)
|
||||
VALUES ('data_import', 'Daten importieren', 'CSV-Import (FDDB, Apple Health) + ZIP-Backup-Import', 'import', 'count', 'monthly', 0, true)
|
||||
ON CONFLICT (id) DO UPDATE SET
|
||||
name = EXCLUDED.name,
|
||||
description = EXCLUDED.description,
|
||||
category = EXCLUDED.category,
|
||||
limit_type = EXCLUDED.limit_type,
|
||||
reset_period = EXCLUDED.reset_period;
|
||||
|
||||
-- Update tier_limits references
|
||||
UPDATE tier_limits
|
||||
SET feature_id = 'data_import'
|
||||
WHERE feature_id = 'csv_import';
|
||||
|
||||
-- Update user_feature_restrictions references
|
||||
UPDATE user_feature_restrictions
|
||||
SET feature_id = 'data_import'
|
||||
WHERE feature_id = 'csv_import';
|
||||
|
||||
-- Update user_feature_usage references
|
||||
UPDATE user_feature_usage
|
||||
SET feature_id = 'data_import'
|
||||
WHERE feature_id = 'csv_import';
|
||||
|
||||
-- Widget-Gateway (Migration 041): sonst blockiert FK beim Löschen von csv_import
|
||||
DO $$
|
||||
BEGIN
|
||||
IF EXISTS (
|
||||
SELECT 1 FROM information_schema.tables
|
||||
WHERE table_schema = 'public' AND table_name = 'widget_feature_requirements'
|
||||
) THEN
|
||||
UPDATE widget_feature_requirements
|
||||
SET feature_id = 'data_import'
|
||||
WHERE feature_id = 'csv_import';
|
||||
END IF;
|
||||
END $$;
|
||||
|
||||
DELETE FROM features WHERE id = 'csv_import';
|
||||
|
||||
-- ============================================================================
|
||||
-- 2. Remove old export_csv/json/zip features
|
||||
-- ============================================================================
|
||||
@@ -69,16 +87,8 @@ ON CONFLICT (id) DO UPDATE SET
|
||||
reset_period = EXCLUDED.reset_period;
|
||||
|
||||
-- ============================================================================
|
||||
-- 4. Ensure data_import exists and is properly configured
|
||||
-- 4. data_import: in Schritt 1 angelegt; kein zweites INSERT nötig
|
||||
-- ============================================================================
|
||||
INSERT INTO features (id, name, description, category, limit_type, reset_period, default_limit, active)
|
||||
VALUES ('data_import', 'Daten importieren', 'CSV-Import (FDDB, Apple Health) + ZIP-Backup-Import', 'import', 'count', 'monthly', 0, true)
|
||||
ON CONFLICT (id) DO UPDATE SET
|
||||
name = EXCLUDED.name,
|
||||
description = EXCLUDED.description,
|
||||
category = EXCLUDED.category,
|
||||
limit_type = EXCLUDED.limit_type,
|
||||
reset_period = EXCLUDED.reset_period;
|
||||
|
||||
-- ============================================================================
|
||||
-- 5. Update tier_limits for data_export (consolidate from old features)
|
||||
|
||||
+23
-2
@@ -3,8 +3,9 @@ Pydantic Models for Mitai Jinkendo API
|
||||
|
||||
Data validation schemas for request/response bodies.
|
||||
"""
|
||||
from typing import Optional
|
||||
from pydantic import BaseModel
|
||||
from typing import Any, List, Optional
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
||||
# ── Profile Models ────────────────────────────────────────────────────────────
|
||||
@@ -82,8 +83,17 @@ class ActivityEntry(BaseModel):
|
||||
kcal_resting: Optional[float] = None
|
||||
hr_avg: Optional[float] = None
|
||||
hr_max: Optional[float] = None
|
||||
hr_min: Optional[int] = None # DB-Spalte hr_min (Parameter min_hr)
|
||||
distance_km: Optional[float] = None
|
||||
rpe: Optional[int] = None
|
||||
pace_min_per_km: Optional[float] = None
|
||||
cadence: Optional[int] = None
|
||||
avg_power: Optional[int] = None
|
||||
elevation_gain: Optional[int] = None
|
||||
temperature_celsius: Optional[float] = None
|
||||
humidity_percent: Optional[int] = None
|
||||
avg_hr_percent: Optional[float] = None
|
||||
kcal_per_km: Optional[float] = None
|
||||
source: Optional[str] = 'manual'
|
||||
notes: Optional[str] = None
|
||||
training_type_id: Optional[int] = None # v9d: Training type categorization
|
||||
@@ -91,6 +101,17 @@ class ActivityEntry(BaseModel):
|
||||
training_subcategory: Optional[str] = None # v9d: Denormalized subcategory
|
||||
|
||||
|
||||
class ActivityMetricValue(BaseModel):
|
||||
parameter_key: str
|
||||
value: Any
|
||||
|
||||
|
||||
class ActivityMetricsReplace(BaseModel):
|
||||
"""Voller Ersatz der EAV-Metriken für eine Session (siehe Agent-Guide)."""
|
||||
|
||||
metrics: List[ActivityMetricValue] = Field(default_factory=list)
|
||||
|
||||
|
||||
class NutritionDay(BaseModel):
|
||||
date: str
|
||||
kcal: Optional[float] = None
|
||||
|
||||
@@ -1,11 +1,10 @@
|
||||
"""
|
||||
Complete Placeholder Metadata Definitions
|
||||
Complete Placeholder Metadata Definitions (Legacy / Normativ v1)
|
||||
|
||||
This module contains manually curated, complete metadata for all 116 placeholders.
|
||||
It combines automatic extraction with manual annotation to ensure 100% normative compliance.
|
||||
|
||||
IMPORTANT: This is the authoritative source for placeholder metadata.
|
||||
All new placeholders MUST be added here with complete metadata.
|
||||
Hinweis (2026-04): **Verbindliche Metadaten-Pflege** erfolgt über
|
||||
`backend/placeholder_registrations/` + `placeholder_registry.py` (114 Keys, deckungsgleich
|
||||
mit `PLACEHOLDER_MAP`). Dieses Modul bleibt für ältere Generator-/Export-Pfade und
|
||||
Tests; neue Platzhalter hier nicht mehr duplizieren.
|
||||
"""
|
||||
from placeholder_metadata import (
|
||||
PlaceholderMetadata,
|
||||
@@ -28,7 +27,7 @@ from typing import List
|
||||
|
||||
def get_all_placeholder_metadata() -> List[PlaceholderMetadata]:
|
||||
"""
|
||||
Returns complete metadata for all 116 placeholders.
|
||||
Returns complete metadata for all 114 placeholders (Registry ist maßgeblich).
|
||||
|
||||
This is the authoritative, manually curated source.
|
||||
"""
|
||||
@@ -476,7 +475,7 @@ def get_all_placeholder_metadata() -> List[PlaceholderMetadata]:
|
||||
notes=["Quadrant-Logik basiert auf FM/LBM Delta-Vorzeichen"],
|
||||
),
|
||||
|
||||
# NOTE: Continuing with all 116 placeholders would make this file very long.
|
||||
# NOTE: Continuing with all 114 placeholders would make this file very long.
|
||||
# For brevity, I'll create a separate generator that fills all remaining placeholders.
|
||||
# The pattern is established above - each placeholder gets full metadata.
|
||||
]
|
||||
|
||||
@@ -29,13 +29,22 @@ def extract_value_raw(value_display: str, output_type: OutputType, placeholder_t
|
||||
|
||||
Returns: (raw_value, success)
|
||||
"""
|
||||
if not value_display or value_display in ['nicht verfügbar', 'nicht genug Daten']:
|
||||
return None, True
|
||||
s = (value_display or "").strip()
|
||||
if (
|
||||
not s
|
||||
or s in ['nicht verfügbar', 'nicht genug Daten']
|
||||
or s.startswith('nicht verfügbar —')
|
||||
):
|
||||
# V2 strict mode: missing/unavailable value is not a successful extraction
|
||||
return None, False
|
||||
|
||||
# JSON output type
|
||||
if output_type == OutputType.JSON:
|
||||
try:
|
||||
return json.loads(value_display), True
|
||||
parsed = json.loads(value_display)
|
||||
if isinstance(parsed, dict) and parsed.get('_available') is False:
|
||||
return None, False
|
||||
return parsed, True
|
||||
except (json.JSONDecodeError, TypeError):
|
||||
# Try to find JSON in string
|
||||
json_match = re.search(r'(\{.*\}|\[.*\])', value_display, re.DOTALL)
|
||||
@@ -111,7 +120,8 @@ def infer_unit_strict(key: str, description: str, output_type: OutputType, place
|
||||
return 'kg'
|
||||
|
||||
# Circumferences/lengths
|
||||
if any(x in key_lower for x in ['umfang', 'waist', 'hip', 'chest', 'arm', 'leg', 'delta']) and 'circumference' in desc_lower:
|
||||
circumference_terms = ['umfang', 'waist', 'hip', 'chest', 'arm', 'leg', 'taill', 'hueft', 'brust', 'oberarm', 'oberschenkel']
|
||||
if any(x in key_lower for x in circumference_terms) or any(x in desc_lower for x in ['circumference', 'umfang', 'taill', 'hüft', 'hueft', 'brust', 'oberarm', 'oberschenkel']):
|
||||
return 'cm'
|
||||
|
||||
# Time durations
|
||||
|
||||
@@ -8,7 +8,31 @@ Auto-imports all placeholder registrations to populate the global registry.
|
||||
from . import nutrition_part_a
|
||||
from . import nutrition_part_b
|
||||
from . import nutrition_part_c
|
||||
from . import nutrition_score
|
||||
from . import body_metrics
|
||||
from . import body_extras
|
||||
from . import activity_metrics
|
||||
from . import activity_session_insights
|
||||
from . import schlaf_erholung
|
||||
from . import vitalwerte
|
||||
from . import profil_zeitraum
|
||||
from . import phase_0b_meta_scores
|
||||
from . import phase_0b_ziele_fokus
|
||||
from . import korrelationen
|
||||
|
||||
__all__ = ['nutrition_part_a', 'nutrition_part_b', 'nutrition_part_c', 'body_metrics', 'activity_metrics']
|
||||
__all__ = [
|
||||
'nutrition_part_a',
|
||||
'nutrition_part_b',
|
||||
'nutrition_part_c',
|
||||
'nutrition_score',
|
||||
'body_metrics',
|
||||
'body_extras',
|
||||
'activity_metrics',
|
||||
'activity_session_insights',
|
||||
'schlaf_erholung',
|
||||
'vitalwerte',
|
||||
'profil_zeitraum',
|
||||
'phase_0b_meta_scores',
|
||||
'phase_0b_ziele_fokus',
|
||||
'korrelationen',
|
||||
]
|
||||
@@ -0,0 +1,19 @@
|
||||
"""Gemeinsames Evidence-Tagging für Registry-Einträge."""
|
||||
|
||||
from placeholder_registry import EvidenceType, PlaceholderMetadata
|
||||
|
||||
STANDARD_FIELDS = (
|
||||
"key", "category", "description", "resolver_module", "resolver_function",
|
||||
"data_layer_module", "data_layer_function", "source_tables", "semantic_contract",
|
||||
"unit", "time_window", "output_type", "placeholder_type", "format_hint",
|
||||
"example_output", "minimum_data_requirements", "confidence_logic",
|
||||
"missing_value_policy", "layer_1_decision", "layer_2a_decision",
|
||||
"layer_2b_reuse_possible", "architecture_alignment", "issue_53_alignment",
|
||||
)
|
||||
|
||||
|
||||
def tag_standard_evidence(meta: PlaceholderMetadata) -> None:
|
||||
for field in STANDARD_FIELDS:
|
||||
meta.set_evidence(field, EvidenceType.CODE_DERIVED)
|
||||
meta.set_evidence("business_meaning", EvidenceType.DRAFT_DERIVED)
|
||||
meta.set_evidence("known_limitations", EvidenceType.MIXED)
|
||||
@@ -1,7 +1,7 @@
|
||||
"""
|
||||
Activity Metrics Placeholder Registrations
|
||||
|
||||
Registers all 17 activity-related placeholders in the central placeholder registry.
|
||||
Registers 17 Aktivitäts-Platzhalter hier; 3 weitere Keys in activity_session_insights.py (**20 gesamt** in PLACEHOLDER_MAP).
|
||||
|
||||
Evidence-based metadata with clear tagging of source.
|
||||
|
||||
@@ -10,6 +10,9 @@ Groups:
|
||||
- Basic Metrics (7): training_minutes_week, training_frequency_7d, quality_sessions_pct,
|
||||
proxy_internal_load_7d, monotony_score, strain_score, rest_day_compliance
|
||||
- Advanced Metrics (7): ability_balance_*, vo2max_trend_28d, activity_score
|
||||
|
||||
Resolver: alle Keys gebündelt unter „Training / Aktivität“ in PLACEHOLDER_MAP;
|
||||
activity_score nicht unter „Meta Scores“.
|
||||
"""
|
||||
|
||||
from placeholder_registry import (
|
||||
@@ -40,7 +43,7 @@ def register_activity_group_1():
|
||||
category="Aktivität",
|
||||
description="Zusammenfassung der letzten 14 Tage Aktivität",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="_format_activity_summary",
|
||||
resolver_function="get_activity_summary",
|
||||
data_layer_module=None,
|
||||
data_layer_function=None,
|
||||
source_tables=["activity_log", "training_types"],
|
||||
@@ -124,16 +127,23 @@ def register_activity_group_1():
|
||||
activity_detail_metadata = PlaceholderMetadata(
|
||||
key="activity_detail",
|
||||
category="Aktivität",
|
||||
description="Detaillierte Liste der letzten 14 Tage Aktivität",
|
||||
description=(
|
||||
"Letzte 14 Tage: pro Session Kopfzeile (activity_log) plus gemergte Profil-Metriken "
|
||||
"(dynamische Keys je training_category / training_type_id)"
|
||||
),
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="_format_activity_detail",
|
||||
data_layer_module=None,
|
||||
data_layer_function=None,
|
||||
source_tables=["activity_log", "training_types"],
|
||||
resolver_function="get_activity_detail",
|
||||
data_layer_module="backend/data_layer/activity_metrics.py",
|
||||
data_layer_function="get_activity_detail_data",
|
||||
source_tables=["activity_log", "activity_session_metrics", "training_parameters"],
|
||||
semantic_contract=(
|
||||
"Liefert eine strukturierte Liste aller Trainingseinheiten der letzten 14 Tage. "
|
||||
"Jede Einheit: Datum, Trainingstyp, Dauer (Minuten), optional Notizen. "
|
||||
"Sortiert chronologisch absteigend (neueste zuerst)."
|
||||
"Layer 1: get_activity_detail_data lädt Sessions, enrich_sessions_with_metrics fügt "
|
||||
"session_metrics hinzu — effektive Liste aus merge_column_backed_and_eav_metrics: nur "
|
||||
"Parameter aus dem Attributschema (tcp/ttp), sortiert nach key. "
|
||||
"Leseregel Kanon: activity_log-Spalte (source_field, Registry-Feld, Legacy-Spalte für "
|
||||
"EAV-primäre Keys) schlägt EAV, wenn beide Werte liefern. "
|
||||
"Layer 2a: Zeilen mit „| EAV: key=value; …“ nur für nicht-leere session_metrics; "
|
||||
"die Menge der Keys ist admin-/profilabhängig, kein festes Prompt-Schema."
|
||||
),
|
||||
business_meaning=(
|
||||
"Detaillierte Trainingshistorie für KI-Prompts, die Muster, Progressionen "
|
||||
@@ -144,7 +154,9 @@ def register_activity_group_1():
|
||||
time_window="14d",
|
||||
output_type=OutputType.LIST,
|
||||
placeholder_type=PlaceholderType.RAW_DATA,
|
||||
format_hint="Liste von Strings, eine Zeile pro Einheit: 'YYYY-MM-DD: Typ (Dauer min)'",
|
||||
format_hint=(
|
||||
"Pro Zeile: Datum, Typ, Dauer, kcal, optional HF, optional „| EAV: …“ aus Session-Metriken"
|
||||
),
|
||||
example_output=(
|
||||
"2026-03-28: Krafttraining (45 min)\\n"
|
||||
"2026-03-27: Laufen (30 min)\\n"
|
||||
@@ -160,19 +172,17 @@ def register_activity_group_1():
|
||||
legacy_display="Keine Aktivitätsdaten"
|
||||
),
|
||||
known_limitations=(
|
||||
"OLD RESOLVER PATTERN: Keine Data Layer Funktion. "
|
||||
"Formatierung direkt im Resolver. "
|
||||
"CRITICAL: Keine Qualitätsfilterung - auch ungültige Einheiten (z.B. 0 min) "
|
||||
"werden gelistet. JOIN mit training_types für Typ-Namen."
|
||||
"Keine Profil-Qualitätsfilterung in dieser Liste. Max. 20 Zeilen im Prompt-Output "
|
||||
"(Hard-Limit Resolver). session_metrics kann leer sein (kein Typ, kein Profil, keine EAV-Zeilen). "
|
||||
"Keys und Anzahl Metriken variieren je Instanz/Admin — nicht von festen Platzhaltern in anderen "
|
||||
"Prompts ausgehen. Nur im effektiven Merge erscheinende Parameter; keine verwaisten EAV-Keys "
|
||||
"außerhalb des Schemas."
|
||||
),
|
||||
layer_1_decision="NONE - Old resolver pattern (direct SQL in resolver)",
|
||||
layer_2a_decision="Placeholder Resolver (formatting + SQL query)",
|
||||
layer_2b_reuse_possible=False,
|
||||
architecture_alignment=(
|
||||
"NOT ALIGNED with Phase 0c Multi-Layer Architecture. "
|
||||
"Should be refactored to use data_layer function."
|
||||
),
|
||||
issue_53_alignment="NOT ALIGNED - no layer separation"
|
||||
layer_1_decision="activity_metrics.get_activity_detail_data (+ enrich_sessions_with_metrics)",
|
||||
layer_2a_decision="get_activity_detail (Formatierung)",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment="Phase 0c Layer 1 + EAV-Anreicherung",
|
||||
issue_53_alignment="Layer 1"
|
||||
)
|
||||
|
||||
activity_detail_metadata.set_evidence("key", EvidenceType.CODE_DERIVED)
|
||||
@@ -209,56 +219,47 @@ def register_activity_group_1():
|
||||
trainingstyp_verteilung_metadata = PlaceholderMetadata(
|
||||
key="trainingstyp_verteilung",
|
||||
category="Aktivität",
|
||||
description="Trainingstypen-Verteilung der letzten 14 Tage als JSON",
|
||||
description="Verteilung nach training_category (14 Tage): Top 3 als kompakte Prozent-Textzeile",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="_format_trainingstyp_verteilung",
|
||||
data_layer_module=None,
|
||||
data_layer_function=None,
|
||||
source_tables=["activity_log", "training_types"],
|
||||
resolver_function="get_trainingstyp_verteilung",
|
||||
data_layer_module="backend/data_layer/activity_metrics.py",
|
||||
data_layer_function="get_training_type_distribution_data",
|
||||
source_tables=["activity_log"],
|
||||
semantic_contract=(
|
||||
"Liefert eine JSON-Struktur mit der Verteilung der Trainingstypen über 14 Tage. "
|
||||
"Für jeden Trainingstyp: Anzahl Einheiten, Gesamtdauer (Minuten), "
|
||||
"Prozentanteil an Gesamtdauer. Sortiert nach Dauer absteigend."
|
||||
"Layer 1: get_training_type_distribution_data — Anteil je training_category am "
|
||||
"Gesamt-Session-Count im Fenster (auch unkategorisierte zählen im Nenner). "
|
||||
"Layer 2a: Top 3 Kategorien als „Name: p%“ kommagetrennt; bei fehlenden Daten Kurz-Hinweis."
|
||||
),
|
||||
business_meaning=(
|
||||
"Analyse-Placeholder für Trainingsvielfalt und -schwerpunkte. "
|
||||
"Erlaubt KI-Prompts, Imbalancen zu erkennen (z.B. nur Kraft, keine Ausdauer) "
|
||||
"oder Zielkonformität zu prüfen (z.B. 'zu wenig Mobilität')."
|
||||
),
|
||||
unit="json",
|
||||
unit="text",
|
||||
time_window="14d",
|
||||
output_type=OutputType.JSON,
|
||||
output_type=OutputType.TEXT_SUMMARY,
|
||||
placeholder_type=PlaceholderType.INTERPRETED,
|
||||
format_hint="JSON Object mit Trainingstyp als Key, Value: {count, duration_min, percentage}",
|
||||
example_output=(
|
||||
'{"Krafttraining": {"count": 5, "duration_min": 180, "percentage": 57}, '
|
||||
'"Ausdauer": {"count": 4, "duration_min": 90, "percentage": 29}, '
|
||||
'"Mobilität": {"count": 3, "duration_min": 45, "percentage": 14}}'
|
||||
),
|
||||
format_hint="Eine Zeile: bis zu drei „Kategorie: Prozent%“, durch Komma getrennt",
|
||||
example_output="cardio: 45%, strength: 30%, mobility: 15%",
|
||||
minimum_data_requirements=None,
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="Keine Confidence-Berechnung. Aggregation basiert auf verfügbaren Daten.",
|
||||
confidence_logic="Wie get_training_type_distribution_data (calculate_confidence über categorized_count)",
|
||||
missing_value_policy=MissingValuePolicy(
|
||||
available=False,
|
||||
value_raw=None,
|
||||
missing_reason="no_data",
|
||||
legacy_display="{}"
|
||||
legacy_display="Keine kategorisierten Trainings"
|
||||
),
|
||||
known_limitations=(
|
||||
"OLD RESOLVER PATTERN: Keine Data Layer Funktion. "
|
||||
"Aggregation direkt im Resolver. "
|
||||
"CRITICAL: Keine Qualitätsfilterung - auch ungültige Einheiten werden aggregiert. "
|
||||
"JOIN mit training_types für Typ-Namen. "
|
||||
"EDGE CASE: Einheiten ohne training_type_id werden ignoriert (LEFT JOIN)."
|
||||
"Nur Sessions mit gesetztem training_category fließen in die Verteilungsliste; "
|
||||
"Prozente beziehen sich auf alle Sessions im Fenster (Nenner = total_sessions). "
|
||||
"Keine Qualitätsfilterung der Einheiten. Kein drill-down nach training_type_id in diesem Platzhalter."
|
||||
),
|
||||
layer_1_decision="NONE - Old resolver pattern (direct SQL aggregation in resolver)",
|
||||
layer_2a_decision="Placeholder Resolver (aggregation + JSON formatting)",
|
||||
layer_1_decision="activity_metrics.get_training_type_distribution_data",
|
||||
layer_2a_decision="get_trainingstyp_verteilung (Top 3 als Text)",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment=(
|
||||
"PARTIALLY ALIGNED: JSON output structure suitable for chart endpoints, "
|
||||
"but no data layer separation. Should be refactored."
|
||||
),
|
||||
issue_53_alignment="PARTIALLY ALIGNED - output format good, layer separation missing"
|
||||
architecture_alignment="Phase 0c — Layer 1 + Formatierung",
|
||||
issue_53_alignment="Layer 1"
|
||||
)
|
||||
|
||||
trainingstyp_verteilung_metadata.set_evidence("key", EvidenceType.CODE_DERIVED)
|
||||
@@ -938,9 +939,9 @@ def register_activity_group_3():
|
||||
description="VO2 Max Trend über 28 Tage",
|
||||
category="Aktivität",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="get_vo2max_trend_28d",
|
||||
resolver_function="_safe_float",
|
||||
data_layer_module="backend/data_layer/activity_metrics.py",
|
||||
data_layer_function="calculate_vo2max_trend",
|
||||
data_layer_function="calculate_vo2max_trend_28d",
|
||||
source_tables=["vitals_baseline"],
|
||||
time_window="28d",
|
||||
output_type=OutputType.NUMERIC,
|
||||
@@ -977,8 +978,8 @@ def register_activity_group_3():
|
||||
"EDGE CASE: Nur 1 Messung → kein Trend → missing_value. "
|
||||
"EDGE CASE: Große Zeitlücken zwischen Messungen → Trend nicht aussagekräftig."
|
||||
),
|
||||
layer_1_decision="Data Layer (activity_metrics.calculate_vo2max_trend) - QUESTIONABLE",
|
||||
layer_2a_decision="Placeholder Resolver (formatting only)",
|
||||
layer_1_decision="Data Layer (activity_metrics.calculate_vo2max_trend_28d) — Kategorie diskutierbar",
|
||||
layer_2a_decision="Placeholder Resolver (_safe_float)",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment="Phase 0c Multi-Layer Architecture conform",
|
||||
issue_53_alignment="Layer separation established"
|
||||
@@ -1020,8 +1021,8 @@ def register_activity_group_3():
|
||||
description="Gesamtaktivitäts-Score (gewichtet)",
|
||||
category="Aktivität",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="get_activity_score",
|
||||
data_layer_module="backend/data_layer/scores.py",
|
||||
resolver_function="_safe_int",
|
||||
data_layer_module="backend/data_layer/activity_metrics.py",
|
||||
data_layer_function="calculate_activity_score",
|
||||
source_tables=["activity_log", "training_types", "rest_days", "vitals_baseline", "user_focus_area_weights"],
|
||||
time_window="composite (7d, 14d, 28d mixed)",
|
||||
@@ -1065,8 +1066,8 @@ def register_activity_group_3():
|
||||
"QUESTIONABLE: Vermischt Metriken mit unterschiedlicher Verlässlichkeit "
|
||||
"(z.B. quality_sessions_pct hat TO_VERIFY Issues)."
|
||||
),
|
||||
layer_1_decision="Data Layer (scores.calculate_activity_score)",
|
||||
layer_2a_decision="Placeholder Resolver (formatting only)",
|
||||
layer_1_decision="Data Layer (activity_metrics.calculate_activity_score)",
|
||||
layer_2a_decision="Placeholder Resolver (_safe_int)",
|
||||
layer_2b_reuse_possible=False,
|
||||
architecture_alignment="Phase 0c Multi-Layer Architecture conform",
|
||||
issue_53_alignment="Layer separation established"
|
||||
|
||||
@@ -0,0 +1,254 @@
|
||||
"""
|
||||
Registry: Trainings-Häufigkeit, Pausen zwischen Einheiten, wöchentliche Session-JSON (KI-Rohkontext).
|
||||
"""
|
||||
|
||||
from placeholder_registry import (
|
||||
PlaceholderMetadata,
|
||||
MissingValuePolicy,
|
||||
EvidenceType,
|
||||
OutputType,
|
||||
PlaceholderType,
|
||||
register_placeholder,
|
||||
)
|
||||
|
||||
|
||||
def _ev(meta: PlaceholderMetadata, field: str, et: EvidenceType = EvidenceType.CODE_DERIVED):
|
||||
meta.set_evidence(field, et)
|
||||
|
||||
|
||||
def register_activity_session_insights():
|
||||
md_freq = PlaceholderMetadata(
|
||||
key="training_frequency_by_type_md",
|
||||
category="Aktivität",
|
||||
description=(
|
||||
"Markdown-Tabelle: pro Trainingsart (activity_type) Sessions, Ø/Woche, "
|
||||
"Dauer, kcal, HF, RPE, kcal/min (Intensitätsproxy)"
|
||||
),
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="get_training_frequency_by_type_md",
|
||||
data_layer_module="backend/data_layer/activity_metrics.py",
|
||||
data_layer_function="get_training_frequency_by_type_data",
|
||||
source_tables=["activity_log"],
|
||||
semantic_contract=(
|
||||
"Aggregat über activity_log gruppiert nach activity_type (Roh-Label). "
|
||||
"sessions_per_week = count / (days/7). avg_kcal_per_min = Summe kcal / Summe min."
|
||||
),
|
||||
business_meaning="KI: Häufigkeit & Belastung pro Sportart, Erholungs-/Überlastungs-Kontext",
|
||||
unit="Markdown",
|
||||
time_window="default 28 Tage",
|
||||
output_type=OutputType.TEXT_SUMMARY,
|
||||
placeholder_type=PlaceholderType.INTERPRETED,
|
||||
format_hint="GitHub-Flavored Markdown-Tabelle",
|
||||
example_output="| Art | n | Ø/Woche | … |",
|
||||
minimum_data_requirements="Mindestens eine Session im Fenster",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="Wie calculate_confidence anhand Session-Anzahl",
|
||||
missing_value_policy=MissingValuePolicy(
|
||||
available=False,
|
||||
value_raw=None,
|
||||
missing_reason="no_data",
|
||||
legacy_display="Keine Trainingsdaten",
|
||||
),
|
||||
known_limitations=(
|
||||
"Gruppierung nach activity_type-String (Import-Namen), nicht nur training_type_id. "
|
||||
"HF/RPE oft NULL je nach Quelle. Pausen-Analyse separater Platzhalter."
|
||||
),
|
||||
layer_1_decision="activity_metrics.get_training_frequency_by_type_data",
|
||||
layer_2a_decision="get_training_frequency_by_type_md",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment="Phase 0c",
|
||||
issue_53_alignment="Layer 1",
|
||||
evidence={},
|
||||
)
|
||||
for f in (
|
||||
"key", "category", "description", "resolver_module", "resolver_function",
|
||||
"data_layer_module", "data_layer_function", "source_tables", "semantic_contract",
|
||||
"unit", "time_window", "output_type", "placeholder_type", "format_hint",
|
||||
"example_output", "minimum_data_requirements", "confidence_logic",
|
||||
"missing_value_policy", "layer_1_decision", "layer_2a_decision",
|
||||
"layer_2b_reuse_possible", "architecture_alignment", "issue_53_alignment",
|
||||
):
|
||||
_ev(md_freq, f)
|
||||
_ev(md_freq, "business_meaning", EvidenceType.DRAFT_DERIVED)
|
||||
_ev(md_freq, "known_limitations", EvidenceType.MIXED)
|
||||
register_placeholder(md_freq)
|
||||
|
||||
md_gap = PlaceholderMetadata(
|
||||
key="training_inter_session_gap_md",
|
||||
category="Aktivität",
|
||||
description="Median/Mittel/Min der Stunden zwischen aufeinanderfolgenden Trainingseinheiten",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="get_training_inter_session_gap_md",
|
||||
data_layer_module="backend/data_layer/activity_metrics.py",
|
||||
data_layer_function="get_training_inter_session_gap_data",
|
||||
source_tables=["activity_log"],
|
||||
semantic_contract=(
|
||||
"Sessions chronologisch; Zeitstempel = date + start_time oder 12:00. "
|
||||
"Lücken in Stunden zwischen aufeinanderfolgenden Starts."
|
||||
),
|
||||
business_meaning="KI: ausreichend Erholung zwischen Belastungen? Doppelbelastung?",
|
||||
unit="Markdown",
|
||||
time_window="default 28 Tage",
|
||||
output_type=OutputType.TEXT_SUMMARY,
|
||||
placeholder_type=PlaceholderType.INTERPRETED,
|
||||
format_hint="Kurzer Markdown-Fließtext",
|
||||
example_output="**Pause zwischen Trainings** …",
|
||||
minimum_data_requirements="Mindestens 2 Sessions",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="calculate_confidence über Session-Anzahl",
|
||||
missing_value_policy=MissingValuePolicy(
|
||||
available=False,
|
||||
value_raw=None,
|
||||
missing_reason="insufficient_data",
|
||||
legacy_display="Zu wenige Trainings",
|
||||
),
|
||||
known_limitations=(
|
||||
"Kein Unterscheidung aktiv/passiv außerhalb activity_log. "
|
||||
"Fehlende Uhrzeit verzerrt Reihenfolge am selben Tag nicht (nur ein künstlicher Mittag)."
|
||||
),
|
||||
layer_1_decision="activity_metrics.get_training_inter_session_gap_data",
|
||||
layer_2a_decision="get_training_inter_session_gap_md",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment="Phase 0c",
|
||||
issue_53_alignment="Layer 1",
|
||||
evidence={},
|
||||
)
|
||||
for f in (
|
||||
"key", "category", "description", "resolver_module", "resolver_function",
|
||||
"data_layer_module", "data_layer_function", "source_tables", "semantic_contract",
|
||||
"unit", "time_window", "output_type", "placeholder_type", "format_hint",
|
||||
"example_output", "minimum_data_requirements", "confidence_logic",
|
||||
"missing_value_policy", "layer_1_decision", "layer_2a_decision",
|
||||
"layer_2b_reuse_possible", "architecture_alignment", "issue_53_alignment",
|
||||
):
|
||||
_ev(md_gap, f)
|
||||
_ev(md_gap, "business_meaning", EvidenceType.DRAFT_DERIVED)
|
||||
_ev(md_gap, "known_limitations", EvidenceType.MIXED)
|
||||
register_placeholder(md_gap)
|
||||
|
||||
pj = PlaceholderMetadata(
|
||||
key="training_sessions_recent_json",
|
||||
category="Aktivität",
|
||||
description=(
|
||||
"JSON: ISO-Wochen mit Sessions (activity_log-Kopf) plus session_metrics[] — gemergte Profil-Metriken "
|
||||
"(dynamische Keys)"
|
||||
),
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="_safe_json",
|
||||
data_layer_module="backend/data_layer/activity_metrics.py",
|
||||
data_layer_function="get_training_sessions_recent_weeks_data",
|
||||
source_tables=["activity_log", "training_types", "activity_session_metrics", "training_parameters"],
|
||||
semantic_contract=(
|
||||
"Root: weeks[] mit week_iso; sessions[] pro Einheit u. a. id, date, activity_type, "
|
||||
"duration_min, kcal_active, hr_avg, hr_max, rpe, training_category, training_type_name, "
|
||||
"session_metrics[]. "
|
||||
"session_metrics: effektive Liste nach merge_column_backed_and_eav_metrics — Einträge mit "
|
||||
"training_parameter_id, key, data_type, unit, value, name_de/name_en, description_de/description_en; "
|
||||
"nur Parameter aus Attributschema "
|
||||
"(training_category_parameter + training_type_parameter Overrides), keys sortiert. "
|
||||
"Kanon Lesen: activity_log-Spalte vor EAV bei Konflikt. "
|
||||
"meta: weeks_requested, days_loaded, session_count, confidence. "
|
||||
"Default ca. 4 ISO-Wochen (28 Tage Rohdatenfenster)."
|
||||
),
|
||||
business_meaning="Rohkontext für wochenweise Auswertung (Erholung, Intensität) in der KI",
|
||||
unit="JSON string",
|
||||
time_window="4 ISO-Wochen (28 Tage Datenfenster)",
|
||||
output_type=OutputType.JSON,
|
||||
placeholder_type=PlaceholderType.RAW_DATA,
|
||||
format_hint="JSON-Objekt als String",
|
||||
example_output='{"weeks":[...],"meta":{...}}',
|
||||
minimum_data_requirements="Optional Sessions; meta.confidence bei leer insufficient",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="meta.confidence aus Session-Anzahl",
|
||||
missing_value_policy=MissingValuePolicy(
|
||||
available=False,
|
||||
value_raw=None,
|
||||
missing_reason="no_data",
|
||||
legacy_display="{}",
|
||||
),
|
||||
known_limitations=(
|
||||
"Token-Länge bei vielen Sessions. training_type_name nur bei gesetztem training_type_id. "
|
||||
"session_metrics oft [] (kein Typ, kein Profil, keine gespeicherten Werte). "
|
||||
"Anzahl und Namen der Metrik-Keys sind instanz-/adminabhängig — JSON nicht als festes Schema "
|
||||
"für Downstream-Parsing harter Logik verwenden. "
|
||||
"Für KI-Semantik zusätzlich {{training_parameters_glossary_md}} (gesamter aktiver Katalog) in den Prompt legen. "
|
||||
"Composite-Parameter (JSON in EAV) noch nicht im MVP expandiert; ggf. Roh-value_text in späterer Phase."
|
||||
),
|
||||
layer_1_decision="activity_metrics.get_training_sessions_recent_weeks_data",
|
||||
layer_2a_decision="_safe_json('training_sessions_recent_json')",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment="Phase 0c",
|
||||
issue_53_alignment="Layer 1",
|
||||
evidence={},
|
||||
)
|
||||
for f in (
|
||||
"key", "category", "description", "resolver_module", "resolver_function",
|
||||
"data_layer_module", "data_layer_function", "source_tables", "semantic_contract",
|
||||
"unit", "time_window", "output_type", "placeholder_type", "format_hint",
|
||||
"example_output", "minimum_data_requirements", "confidence_logic",
|
||||
"missing_value_policy", "layer_1_decision", "layer_2a_decision",
|
||||
"layer_2b_reuse_possible", "architecture_alignment", "issue_53_alignment",
|
||||
):
|
||||
_ev(pj, f)
|
||||
_ev(pj, "business_meaning", EvidenceType.DRAFT_DERIVED)
|
||||
_ev(pj, "known_limitations", EvidenceType.MIXED)
|
||||
register_placeholder(pj)
|
||||
|
||||
md_gloss = PlaceholderMetadata(
|
||||
key="training_parameters_glossary_md",
|
||||
category="Aktivität",
|
||||
description=(
|
||||
"Markdown-Tabelle: alle aktiven training_parameters (key, DE/EN, Beschreibungen, Typ, Einheit, Kategorie). "
|
||||
"Ergänzung zu training_sessions_recent_json für KI (Bedeutung dynamischer Metrik-Keys)."
|
||||
),
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="get_training_parameters_glossary_md",
|
||||
data_layer_module="backend/data_layer/activity_metrics.py",
|
||||
data_layer_function="get_training_parameters_ki_glossary_data",
|
||||
source_tables=["training_parameters"],
|
||||
semantic_contract=(
|
||||
"SELECT auf training_parameters WHERE is_active; sortiert category, key. "
|
||||
"profile_id-Parameter im Resolver reserviert, aktuell globaler Katalog."
|
||||
),
|
||||
business_meaning="KI: Legende zu session_metrics-Keys und Custom-Parametern",
|
||||
unit="Markdown",
|
||||
time_window="n/a (Katalog-Snapshot)",
|
||||
output_type=OutputType.TEXT_SUMMARY,
|
||||
placeholder_type=PlaceholderType.INTERPRETED,
|
||||
format_hint="GitHub-Flavored Markdown-Tabelle",
|
||||
example_output="| Feld (key) | DE | EN | Beschreibung DE | … |",
|
||||
minimum_data_requirements="Optional leer → Kurztext statt Tabelle",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="Immer verfügbar wenn DB erreichbar",
|
||||
missing_value_policy=MissingValuePolicy(
|
||||
available=False,
|
||||
value_raw=None,
|
||||
missing_reason="no_data",
|
||||
legacy_display="Keine aktiven Trainingsparameter im Katalog.",
|
||||
),
|
||||
known_limitations=(
|
||||
"Keine profil-spezifische Einschränkung auf tatsächlich genutzte Keys (V2). "
|
||||
"Tabellen können bei großem Katalog lang werden."
|
||||
),
|
||||
layer_1_decision="activity_metrics.get_training_parameters_ki_glossary_data",
|
||||
layer_2a_decision="get_training_parameters_glossary_md",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment="Phase 0c",
|
||||
issue_53_alignment="Layer 2a",
|
||||
evidence={},
|
||||
)
|
||||
for f in (
|
||||
"key", "category", "description", "resolver_module", "resolver_function",
|
||||
"data_layer_module", "data_layer_function", "source_tables", "semantic_contract",
|
||||
"unit", "time_window", "output_type", "placeholder_type", "format_hint",
|
||||
"example_output", "minimum_data_requirements", "confidence_logic",
|
||||
"missing_value_policy", "layer_1_decision", "layer_2a_decision",
|
||||
"layer_2b_reuse_possible", "architecture_alignment", "issue_53_alignment",
|
||||
):
|
||||
_ev(md_gloss, f)
|
||||
_ev(md_gloss, "business_meaning", EvidenceType.DRAFT_DERIVED)
|
||||
_ev(md_gloss, "known_limitations", EvidenceType.MIXED)
|
||||
register_placeholder(md_gloss)
|
||||
|
||||
|
||||
register_activity_session_insights()
|
||||
@@ -0,0 +1,237 @@
|
||||
"""
|
||||
Registry: BMI, Profil-Ziele (goal_weight, goal_bf_pct), body_progress_score.
|
||||
|
||||
Profilfelder sind unabhängig von der goals-Tabelle; operative Ziele über andere Keys.
|
||||
"""
|
||||
|
||||
from placeholder_registry import (
|
||||
PlaceholderMetadata,
|
||||
MissingValuePolicy,
|
||||
EvidenceType,
|
||||
OutputType,
|
||||
PlaceholderType,
|
||||
register_placeholder,
|
||||
)
|
||||
|
||||
|
||||
def register_body_extras():
|
||||
bmi = PlaceholderMetadata(
|
||||
key="bmi",
|
||||
category="Körper",
|
||||
description="Body-Mass-Index aus letztem Gewicht und Profilgröße (cm)",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="calculate_bmi",
|
||||
data_layer_module="backend/data_layer/body_metrics.py",
|
||||
data_layer_function="get_bmi_data",
|
||||
source_tables=["profiles", "weight_log"],
|
||||
semantic_contract=(
|
||||
"BMI = Gewicht_kg / (Größe_m)² mit Größe_m = profiles.height / 100 "
|
||||
"und Gewicht = jüngster Eintrag in weight_log."
|
||||
),
|
||||
business_meaning="Standard-Körpermaß für Coaching und Risiko-Kontext",
|
||||
unit="kg/m²",
|
||||
time_window="latest weight + aktuelle Profilgröße",
|
||||
output_type=OutputType.NUMERIC,
|
||||
placeholder_type=PlaceholderType.RAW_DATA,
|
||||
format_hint="Eine Dezimalstelle, ohne Einheit im String",
|
||||
example_output="24.3",
|
||||
minimum_data_requirements="Profil mit height > 0 und mindestens ein weight_log",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="high nur wenn BMI berechenbar; sonst insufficient / Anzeige nicht verfügbar",
|
||||
missing_value_policy=MissingValuePolicy(
|
||||
available=False,
|
||||
value_raw=None,
|
||||
missing_reason="no_data",
|
||||
legacy_display="nicht verfügbar",
|
||||
),
|
||||
known_limitations=(
|
||||
"Keine ethnischen Referenzkurven; Profilgröße kann veraltet sein. "
|
||||
"Unterscheidet nicht Muskelmasse vs. Fett."
|
||||
),
|
||||
layer_1_decision="body_metrics.get_bmi_data",
|
||||
layer_2a_decision="placeholder_resolver.calculate_bmi (Format)",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment="Phase 0c",
|
||||
issue_53_alignment="Layer 1 als Quelle",
|
||||
evidence={},
|
||||
)
|
||||
for field in (
|
||||
"key", "category", "description", "resolver_module", "resolver_function",
|
||||
"data_layer_module", "data_layer_function", "source_tables",
|
||||
"semantic_contract", "business_meaning", "unit", "time_window",
|
||||
"output_type", "placeholder_type", "format_hint", "example_output",
|
||||
"minimum_data_requirements", "confidence_logic", "missing_value_policy",
|
||||
"known_limitations", "layer_1_decision", "layer_2a_decision",
|
||||
"layer_2b_reuse_possible", "architecture_alignment", "issue_53_alignment",
|
||||
):
|
||||
bmi.set_evidence(field, EvidenceType.CODE_DERIVED)
|
||||
bmi.set_evidence("business_meaning", EvidenceType.DRAFT_DERIVED)
|
||||
bmi.set_evidence("known_limitations", EvidenceType.MIXED)
|
||||
register_placeholder(bmi)
|
||||
|
||||
gw = PlaceholderMetadata(
|
||||
key="goal_weight",
|
||||
category="Körper",
|
||||
description="Zielgewicht aus Profilfeld profiles.goal_weight (kg)",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="get_goal_weight",
|
||||
data_layer_module="backend/data_layer/body_metrics.py",
|
||||
data_layer_function="get_profile_goal_weight_data",
|
||||
source_tables=["profiles"],
|
||||
semantic_contract=(
|
||||
"Strategisches Soll-Gewicht im Profil; unabhängig von der goals-Tabelle "
|
||||
"(dort detaillierte Ziele mit Fortschritt)."
|
||||
),
|
||||
business_meaning="Schneller Abgleich Prompt vs. Profil-Default-Zielgewicht",
|
||||
unit="kg",
|
||||
time_window="Profil-Snapshot",
|
||||
output_type=OutputType.NUMERIC,
|
||||
placeholder_type=PlaceholderType.RAW_DATA,
|
||||
format_hint="Eine Dezimalstelle oder Text „nicht gesetzt“",
|
||||
example_output="82.0",
|
||||
minimum_data_requirements="profiles.goal_weight IS NOT NULL",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="high wenn gesetzt",
|
||||
missing_value_policy=MissingValuePolicy(
|
||||
available=False,
|
||||
value_raw=None,
|
||||
missing_reason="not_set",
|
||||
legacy_display="nicht gesetzt",
|
||||
),
|
||||
known_limitations="Kann von aktiven goals.weight-Zielen abweichen.",
|
||||
layer_1_decision="body_metrics.get_profile_goal_weight_data",
|
||||
layer_2a_decision="placeholder_resolver.get_goal_weight",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment="Phase 0c",
|
||||
issue_53_alignment="Layer 1 als Quelle",
|
||||
evidence={},
|
||||
)
|
||||
for field in (
|
||||
"key", "category", "description", "resolver_module", "resolver_function",
|
||||
"data_layer_module", "data_layer_function", "source_tables",
|
||||
"semantic_contract", "unit", "time_window", "output_type",
|
||||
"placeholder_type", "format_hint", "example_output",
|
||||
"minimum_data_requirements", "confidence_logic", "missing_value_policy",
|
||||
"layer_1_decision", "layer_2a_decision", "layer_2b_reuse_possible",
|
||||
"architecture_alignment", "issue_53_alignment",
|
||||
):
|
||||
gw.set_evidence(field, EvidenceType.CODE_DERIVED)
|
||||
gw.set_evidence("business_meaning", EvidenceType.DRAFT_DERIVED)
|
||||
gw.set_evidence("known_limitations", EvidenceType.MIXED)
|
||||
register_placeholder(gw)
|
||||
|
||||
gbf = PlaceholderMetadata(
|
||||
key="goal_bf_pct",
|
||||
category="Körper",
|
||||
description="Ziel-Körperfettanteil aus Profilfeld profiles.goal_bf_pct (%)",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="get_goal_bf_pct",
|
||||
data_layer_module="backend/data_layer/body_metrics.py",
|
||||
data_layer_function="get_profile_goal_bf_pct_data",
|
||||
source_tables=["profiles"],
|
||||
semantic_contract="Strategisches Ziel-KFA im Profil.",
|
||||
business_meaning="Prompt-Abgleich mit Profil-Ziel-KFA",
|
||||
unit="%",
|
||||
time_window="Profil-Snapshot",
|
||||
output_type=OutputType.NUMERIC,
|
||||
placeholder_type=PlaceholderType.RAW_DATA,
|
||||
format_hint="Eine Dezimalstelle oder Text „nicht gesetzt“",
|
||||
example_output="15.0",
|
||||
minimum_data_requirements="profiles.goal_bf_pct IS NOT NULL",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="high wenn gesetzt",
|
||||
missing_value_policy=MissingValuePolicy(
|
||||
available=False,
|
||||
value_raw=None,
|
||||
missing_reason="not_set",
|
||||
legacy_display="nicht gesetzt",
|
||||
),
|
||||
known_limitations="Kann von goals body_fat abweichen.",
|
||||
layer_1_decision="body_metrics.get_profile_goal_bf_pct_data",
|
||||
layer_2a_decision="placeholder_resolver.get_goal_bf_pct",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment="Phase 0c",
|
||||
issue_53_alignment="Layer 1 als Quelle",
|
||||
evidence={},
|
||||
)
|
||||
for field in (
|
||||
"key", "category", "description", "resolver_module", "resolver_function",
|
||||
"data_layer_module", "data_layer_function", "source_tables",
|
||||
"semantic_contract", "unit", "time_window", "output_type",
|
||||
"placeholder_type", "format_hint", "example_output",
|
||||
"minimum_data_requirements", "confidence_logic", "missing_value_policy",
|
||||
"layer_1_decision", "layer_2a_decision", "layer_2b_reuse_possible",
|
||||
"architecture_alignment", "issue_53_alignment",
|
||||
):
|
||||
gbf.set_evidence(field, EvidenceType.CODE_DERIVED)
|
||||
gbf.set_evidence("business_meaning", EvidenceType.DRAFT_DERIVED)
|
||||
gbf.set_evidence("known_limitations", EvidenceType.MIXED)
|
||||
register_placeholder(gbf)
|
||||
|
||||
bps = PlaceholderMetadata(
|
||||
key="body_progress_score",
|
||||
category="Körper",
|
||||
description="Körper-Fortschritts-Score 0–100, gewichtet nach Focus (Abnehmen, Muskelaufbau, Recomp)",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="_safe_int",
|
||||
data_layer_module="backend/data_layer/body_metrics.py",
|
||||
data_layer_function="calculate_body_progress_score",
|
||||
source_tables=[
|
||||
"user_focus_area_weights",
|
||||
"focus_area_definitions",
|
||||
"goals",
|
||||
"weight_log",
|
||||
"caliper_log",
|
||||
"circumference_log",
|
||||
],
|
||||
semantic_contract=(
|
||||
"Gewichteter Mittelwert aus bis zu drei Komponenten: Trend vs. Gewichtsziel, "
|
||||
"Körperzusammensetzung (FM/LBM/Recomp-Quadrant), Taille-Trend. "
|
||||
"Komponenten nur aktiv, wenn passende Focus-Gewichte > 0."
|
||||
),
|
||||
business_meaning="Meta-KPI: passt dokumentierter Körperfortschritt zur gewichteten Körper-Priorität?",
|
||||
unit="Score (0–100)",
|
||||
time_window="composite (u. a. 28d Deltas, Ziel-Fortschritt)",
|
||||
output_type=OutputType.NUMERIC,
|
||||
placeholder_type=PlaceholderType.SCORE,
|
||||
format_hint="Ganzzahl oder „nicht verfügbar“",
|
||||
example_output="72",
|
||||
minimum_data_requirements=(
|
||||
"Summe der Körper-Focus-Gewichte (weight_loss + muscle_gain + body_recomposition) > 0 "
|
||||
"und mindestens eine bewertbare Komponente mit Daten."
|
||||
),
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="Kein separates Confidence-Feld; None wenn keine Körper-Gewichtung oder keine Teilscores.",
|
||||
missing_value_policy=MissingValuePolicy(
|
||||
available=False,
|
||||
value_raw=None,
|
||||
missing_reason="not_applicable",
|
||||
legacy_display="nicht verfügbar",
|
||||
),
|
||||
known_limitations=(
|
||||
"Abhängig von user_focus_area_weights und aktiven weight-goals für Gewichts-Teilscore. "
|
||||
"Taille-Score wird mit festem Basisgewicht 20+ eingemischt und kann dominieren."
|
||||
),
|
||||
layer_1_decision="body_metrics.calculate_body_progress_score",
|
||||
layer_2a_decision="placeholder_resolver._safe_int('body_progress_score', …)",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment="Phase 0c",
|
||||
issue_53_alignment="Layer 1 als Quelle",
|
||||
evidence={},
|
||||
)
|
||||
for field in (
|
||||
"key", "category", "description", "resolver_module", "resolver_function",
|
||||
"data_layer_module", "data_layer_function", "source_tables",
|
||||
"semantic_contract", "unit", "time_window", "output_type",
|
||||
"placeholder_type", "format_hint", "example_output",
|
||||
"minimum_data_requirements", "confidence_logic", "missing_value_policy",
|
||||
"layer_1_decision", "layer_2a_decision", "layer_2b_reuse_possible",
|
||||
"architecture_alignment", "issue_53_alignment",
|
||||
):
|
||||
bps.set_evidence(field, EvidenceType.CODE_DERIVED)
|
||||
bps.set_evidence("business_meaning", EvidenceType.DRAFT_DERIVED)
|
||||
bps.set_evidence("known_limitations", EvidenceType.MIXED)
|
||||
register_placeholder(bps)
|
||||
|
||||
|
||||
register_body_extras()
|
||||
@@ -1,7 +1,8 @@
|
||||
"""
|
||||
Body Metrics Placeholder Registrations
|
||||
|
||||
Registers 17 body composition and measurement placeholders:
|
||||
Registers 17 Körper-Metriken in diesem Modul; insgesamt 21 Körper-Keys in der Registry
|
||||
(zusätzlich body_extras.py: bmi, goal_weight, goal_bf_pct, body_progress_score).
|
||||
|
||||
Weight & Trends (7):
|
||||
- weight_aktuell
|
||||
@@ -29,7 +30,7 @@ Summaries (2):
|
||||
- circ_summary
|
||||
|
||||
Evidence-based metadata with comprehensive formula documentation.
|
||||
Code inspection: backend/data_layer/body_metrics.py (830 lines)
|
||||
Siehe backend/data_layer/body_metrics.py als Layer-1-Implementierung.
|
||||
"""
|
||||
|
||||
from placeholder_registry import (
|
||||
|
||||
@@ -0,0 +1,96 @@
|
||||
"""Registry: Korrelations- und Treiber-Metriken (Data Layer correlations)."""
|
||||
|
||||
from placeholder_registry import (
|
||||
PlaceholderMetadata,
|
||||
MissingValuePolicy,
|
||||
OutputType,
|
||||
PlaceholderType,
|
||||
register_placeholder,
|
||||
)
|
||||
from ._evidence import tag_standard_evidence
|
||||
|
||||
CAT = "Korrelationen"
|
||||
MVP = lambda reason, disp: MissingValuePolicy(
|
||||
available=False, value_raw=None, missing_reason=reason, legacy_display=disp
|
||||
)
|
||||
|
||||
|
||||
def register_korrelationen():
|
||||
for key, dl_fn, desc, tables, sem in [
|
||||
(
|
||||
"correlation_energy_weight_lag",
|
||||
"calculate_lag_correlation",
|
||||
"JSON: Lag-Korrelation Energiebilanz ↔ Gewicht",
|
||||
["nutrition_log", "weight_log"],
|
||||
"correlations.calculate_lag_correlation(pid, 'energy', 'weight')",
|
||||
),
|
||||
(
|
||||
"correlation_protein_lbm",
|
||||
"calculate_lag_correlation",
|
||||
"JSON: Lag-Korrelation Protein ↔ Magermasse",
|
||||
["nutrition_log", "weight_log", "caliper_log"],
|
||||
"correlations.calculate_lag_correlation(pid, 'protein', 'lbm')",
|
||||
),
|
||||
(
|
||||
"correlation_load_hrv",
|
||||
"calculate_lag_correlation",
|
||||
"JSON: Lag-Korrelation Trainingslast ↔ HRV",
|
||||
["activity_log", "vitals_baseline"],
|
||||
"correlations.calculate_lag_correlation(pid, 'training_load', 'hrv')",
|
||||
),
|
||||
(
|
||||
"correlation_load_rhr",
|
||||
"calculate_lag_correlation",
|
||||
"JSON: Lag-Korrelation Trainingslast ↔ Ruhepuls",
|
||||
["activity_log", "vitals_baseline"],
|
||||
"correlations.calculate_lag_correlation(pid, 'training_load', 'rhr')",
|
||||
),
|
||||
(
|
||||
"plateau_detected",
|
||||
"calculate_plateau_detected",
|
||||
"JSON: Platten-Erkennung (Gewicht/Körper)",
|
||||
["weight_log", "caliper_log"],
|
||||
"correlations.calculate_plateau_detected",
|
||||
),
|
||||
(
|
||||
"top_drivers",
|
||||
"calculate_top_drivers",
|
||||
"JSON: Top Treiber für Ziel-/Score-Variablen",
|
||||
["weight_log", "nutrition_log", "activity_log", "vitals_baseline", "sleep_log"],
|
||||
"correlations.calculate_top_drivers",
|
||||
),
|
||||
]:
|
||||
m = PlaceholderMetadata(
|
||||
key=key,
|
||||
category=CAT,
|
||||
description=desc,
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="_safe_json",
|
||||
data_layer_module="backend/data_layer/correlations.py",
|
||||
data_layer_function=dl_fn,
|
||||
source_tables=tables,
|
||||
semantic_contract=sem,
|
||||
business_meaning="Strukturierte Korrelationsausgabe für KI",
|
||||
unit="JSON",
|
||||
time_window="funktionsintern",
|
||||
output_type=OutputType.JSON,
|
||||
placeholder_type=PlaceholderType.RAW_DATA,
|
||||
format_hint="JSON-String",
|
||||
example_output="{}",
|
||||
minimum_data_requirements="Ausreichend gekoppelte Zeitreihen",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="Wie correlations.*",
|
||||
missing_value_policy=MVP("insufficient_data", "{}"),
|
||||
known_limitations="Bei wenigen Daten leer oder wenig robust",
|
||||
layer_1_decision=f"correlations.{dl_fn}",
|
||||
layer_2a_decision="_safe_json",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment="Phase 0c",
|
||||
issue_53_alignment="Layer 1",
|
||||
evidence={},
|
||||
)
|
||||
tag_standard_evidence(m)
|
||||
register_placeholder(m)
|
||||
|
||||
|
||||
register_korrelationen()
|
||||
@@ -53,6 +53,13 @@ def register_nutrition_part_a():
|
||||
"layer_1_decision": "Data Layer (nutrition_metrics.get_nutrition_average_data)",
|
||||
"layer_2a_decision": "Placeholder Resolver (formatting only)",
|
||||
"architecture_alignment": "Phase 0c Multi-Layer Architecture conform",
|
||||
"minimum_data_requirements": (
|
||||
"Mind. ein Kalendertag mit nutrition_log im Fenster; Mittelwerte aus täglicher Aggregation. "
|
||||
"Confidence über calculate_confidence(day_count, days) in get_nutrition_average_data."
|
||||
),
|
||||
"quality_filter_policy": (
|
||||
"Kein Outlier-Filter auf Tagesaggregaten; leere Tage fehlen in der Aggregation (kein Imputing)."
|
||||
),
|
||||
}
|
||||
|
||||
# Common evidence for shared fields
|
||||
@@ -73,8 +80,8 @@ def register_nutrition_part_a():
|
||||
"layer_2b_reuse_possible": EvidenceType.TO_VERIFY, # not verified in charts
|
||||
"architecture_alignment": EvidenceType.CODE_DERIVED, # imports from data_layer
|
||||
"issue_53_alignment": EvidenceType.MIXED, # layer separation visible, issue conformity derived
|
||||
"minimum_data_requirements": EvidenceType.UNRESOLVED, # not explicit in code
|
||||
"quality_filter_policy": EvidenceType.UNRESOLVED, # not implemented
|
||||
"minimum_data_requirements": EvidenceType.CODE_DERIVED,
|
||||
"quality_filter_policy": EvidenceType.CODE_DERIVED,
|
||||
}
|
||||
|
||||
# ── kcal_avg ──────────────────────────────────────────────────────────────
|
||||
@@ -94,8 +101,6 @@ def register_nutrition_part_a():
|
||||
known_limitations="nur Intake, kein Bedarf; sagt allein nichts über Zielpassung",
|
||||
layer_2b_reuse_possible=None, # to_verify - not checked in chart code
|
||||
issue_53_alignment="Layer separation established",
|
||||
minimum_data_requirements=None, # unresolved
|
||||
quality_filter_policy=None, # unresolved
|
||||
**common_metadata
|
||||
)
|
||||
|
||||
@@ -131,8 +136,6 @@ def register_nutrition_part_a():
|
||||
),
|
||||
layer_2b_reuse_possible=None,
|
||||
issue_53_alignment="Layer separation established",
|
||||
minimum_data_requirements=None,
|
||||
quality_filter_policy=None,
|
||||
**common_metadata
|
||||
)
|
||||
|
||||
@@ -165,8 +168,6 @@ def register_nutrition_part_a():
|
||||
),
|
||||
layer_2b_reuse_possible=None,
|
||||
issue_53_alignment="Layer separation established",
|
||||
minimum_data_requirements=None,
|
||||
quality_filter_policy=None,
|
||||
**common_metadata
|
||||
)
|
||||
|
||||
@@ -196,8 +197,6 @@ def register_nutrition_part_a():
|
||||
known_limitations="meist im Gesamtkontext der Makroverteilung relevant",
|
||||
layer_2b_reuse_possible=None,
|
||||
issue_53_alignment="Layer separation established",
|
||||
minimum_data_requirements=None,
|
||||
quality_filter_policy=None,
|
||||
**common_metadata
|
||||
)
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
"""
|
||||
Placeholder Registrations - Nutrition Part C
|
||||
|
||||
Registers 5 nutrition-related placeholders with complete metadata:
|
||||
Registers 5 nutrition-related placeholders in this file (nutrition_score: siehe nutrition_score.py):
|
||||
- macro_consistency_score
|
||||
- energy_balance_7d
|
||||
- energy_deficit_surplus
|
||||
@@ -113,7 +113,7 @@ energy_balance_metadata = PlaceholderMetadata(
|
||||
resolver_function="_safe_float('energy_balance_7d', pid, decimals=0)",
|
||||
data_layer_module="backend/data_layer/nutrition_metrics.py",
|
||||
data_layer_function="calculate_energy_balance_7d",
|
||||
source_tables=["nutrition_log", "weight_log"],
|
||||
source_tables=["nutrition_log", "weight_log", "profiles"],
|
||||
|
||||
# Semantic
|
||||
semantic_contract="Liefert die geschätzte Energiebilanz über 7 Tage als Differenz zwischen durchschnittlicher Energieaufnahme und geschätztem TDEE (Total Daily Energy Expenditure). Positiver Wert = Überschuss, Negativer Wert = Defizit.",
|
||||
@@ -127,11 +127,14 @@ energy_balance_metadata = PlaceholderMetadata(
|
||||
|
||||
# Quality
|
||||
minimum_data_requirements="Mindestens 4 Tage mit Kalorienerfassung in 7-Tage-Fenster. Aktuelles Gewicht aus weight_log erforderlich.",
|
||||
quality_filter_policy="Unvollständige Intake-Daten und fehlende Gewichtsmessung reduzieren Verlässlichkeit. TDEE-Schätzung ist vereinfacht (weight_kg × 32.5).",
|
||||
quality_filter_policy=(
|
||||
"Unvollständige Intake-Daten und fehlende Gewichtsmessung reduzieren Verlässlichkeit. "
|
||||
"TDEE: Mifflin–St Jeor × PAL 1.55 wenn Höhe, Geschlecht, DOB und Gewicht vorhanden, sonst kg×32.5."
|
||||
),
|
||||
confidence_logic=(
|
||||
"Kombiniert Intake-Abdeckung und Robustheit des Verbrauchsmodells. "
|
||||
"Niedrigere Confidence bei <7 Tagen Daten oder fehlendem Gewicht. "
|
||||
"TDEE-Modell ist vereinfacht → inherent uncertainty."
|
||||
"PAL=1.55 ist ein Festwert (moderate Aktivität), kein individuelles Aktivitätslogging."
|
||||
),
|
||||
missing_value_policy=MissingValuePolicy(
|
||||
available=False,
|
||||
@@ -140,11 +143,10 @@ energy_balance_metadata = PlaceholderMetadata(
|
||||
legacy_display="nicht verfügbar"
|
||||
),
|
||||
known_limitations=(
|
||||
"TDEE-MODELL: Vereinfacht als bodyweight_kg × 32.5 (mittlerer Multiplikator). "
|
||||
"NICHT berücksichtigt: Aktivitätslevel, Alter, Geschlecht, Stoffwechselanpassungen. "
|
||||
"TODO in Code: Harris-Benedict oder Mifflin-St Jeor für präzisere TDEE-Schätzung. "
|
||||
"ACHTUNG: Energiebilanz ist modellbasiert, nicht direkt gemessen. "
|
||||
"Einheit ist kcal/Tag (daily average), NICHT 7d-Total."
|
||||
"TDEE: Bei vollständigem Profil (Größe, Geschlecht, DOB, Gewicht) Mifflin–St Jeor BMR × 1.55; "
|
||||
"sonst Fallback kg×32.5. PAL ist nicht nutzerkonfigurierbar. "
|
||||
"Energiebilanz ist modellbasiert, nicht gemessen. "
|
||||
"Einheit kcal/Tag (Tagesmittel), nicht 7-Tage-Summe."
|
||||
),
|
||||
|
||||
# Architecture
|
||||
@@ -435,8 +437,9 @@ Part C Registration Complete:
|
||||
Total Nutrition Cluster:
|
||||
- Part A: 4 placeholders (kcal_avg, protein_avg, carb_avg, fat_avg)
|
||||
- Part B: 5 placeholders (protein targets + adequacy)
|
||||
- Part C: 5 placeholders (consistency + balance + meta)
|
||||
→ 14 nutrition placeholders total
|
||||
- Part C: 5 placeholders in dieser Datei (consistency + balance + meta)
|
||||
- nutrition_score: eigenes Modul nutrition_score.py
|
||||
→ 15 Ernährungs-Platzhalter gesamt (A+B+C+nutrition_score)
|
||||
|
||||
All registrations follow Phase 0c Multi-Layer Architecture:
|
||||
- Layer 1 (Data Layer): Calculations
|
||||
|
||||
@@ -0,0 +1,102 @@
|
||||
"""
|
||||
Placeholder registration: nutrition_score
|
||||
|
||||
Focus-gewichteter Ernährungs-Meta-Score (separates Modul, um nutrition_part_c schlank zu halten).
|
||||
"""
|
||||
|
||||
from placeholder_registry import (
|
||||
PlaceholderMetadata,
|
||||
MissingValuePolicy,
|
||||
EvidenceType,
|
||||
OutputType,
|
||||
PlaceholderType,
|
||||
register_placeholder,
|
||||
)
|
||||
|
||||
nutrition_score_metadata = PlaceholderMetadata(
|
||||
key="nutrition_score",
|
||||
category="Ernährung",
|
||||
description="Ernährungs-Score (0–100), gewichtet nach Focus Areas",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="_safe_int",
|
||||
data_layer_module="backend/data_layer/nutrition_metrics.py",
|
||||
data_layer_function="calculate_nutrition_score",
|
||||
source_tables=[
|
||||
"nutrition_log",
|
||||
"weight_log",
|
||||
"user_focus_area_weights",
|
||||
"focus_area_definitions",
|
||||
],
|
||||
semantic_contract=(
|
||||
"Gewichteter Score 0–100 aus Komponenten, die nur einfließen, wenn der Nutzer "
|
||||
"passende Ernährungs-Focus-Gewichte gesetzt hat (z. B. protein_intake, "
|
||||
"calorie_balance, macro_consistency). Nutzt u. a. Protein-Adequacy, "
|
||||
"Makro-Konsistenz, Kalorien-Adhärenz (über Energiebilanz) und Makro-Balance."
|
||||
),
|
||||
business_meaning=(
|
||||
"Verdichteter KPI für Prompts: passt die dokumentierte Ernährung zur "
|
||||
"gewichteten strategischen Priorität des Nutzers?"
|
||||
),
|
||||
unit="score (0-100)",
|
||||
time_window="composite (7d / 28d je Komponente)",
|
||||
output_type=OutputType.NUMERIC,
|
||||
placeholder_type=PlaceholderType.SCORE,
|
||||
format_hint="Ganzzahl; bei fehlender Ernährungs-Gewichtung oft nicht verfügbar",
|
||||
example_output="72",
|
||||
minimum_data_requirements=(
|
||||
"Mindestens eine Ernährungs-Focus-Komponente mit Gewicht > 0; "
|
||||
"sowie je nach Komponente ausreichende nutrition_log-/weight_log-Abdeckung."
|
||||
),
|
||||
quality_filter_policy=None,
|
||||
confidence_logic=(
|
||||
"Kein separates Confidence-Feld im Resolver; fehlende Komponenten werden "
|
||||
"aus der Gewichtung ausgeschlossen. total_nutrition_weight == 0 ergibt keinen Score."
|
||||
),
|
||||
missing_value_policy=MissingValuePolicy(
|
||||
available=False,
|
||||
value_raw=None,
|
||||
missing_reason="not_applicable",
|
||||
legacy_display="nicht verfügbar",
|
||||
),
|
||||
known_limitations=(
|
||||
"Abhängig von user_focus_area_weights; ohne Ernährungs-Fokus liefert die "
|
||||
"Funktion None. Kalorien-Adhärenz nutzt 7d-Energiebilanz vs. profiles.goal_mode "
|
||||
"(weight_loss / strength+recomposition / sonst maintenance). "
|
||||
"_score_macro_balance nutzt zeilenbasierte 28d-Abfrage (langfristig an "
|
||||
"Tagesaggregation angleichen)."
|
||||
),
|
||||
layer_1_decision="Data Layer (nutrition_metrics.calculate_nutrition_score)",
|
||||
layer_2a_decision="Placeholder Resolver (_safe_int)",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment="Phase 0c: Berechnung in nutrition_metrics",
|
||||
issue_53_alignment="Layer 1 als Quelle; Komponenten nutzen weitere Layer-1-Funktionen",
|
||||
evidence={},
|
||||
)
|
||||
|
||||
nutrition_score_metadata.set_evidence("key", EvidenceType.CODE_DERIVED)
|
||||
nutrition_score_metadata.set_evidence("category", EvidenceType.CODE_DERIVED)
|
||||
nutrition_score_metadata.set_evidence("description", EvidenceType.MIXED)
|
||||
nutrition_score_metadata.set_evidence("resolver_module", EvidenceType.CODE_DERIVED)
|
||||
nutrition_score_metadata.set_evidence("resolver_function", EvidenceType.CODE_DERIVED)
|
||||
nutrition_score_metadata.set_evidence("data_layer_module", EvidenceType.CODE_DERIVED)
|
||||
nutrition_score_metadata.set_evidence("data_layer_function", EvidenceType.CODE_DERIVED)
|
||||
nutrition_score_metadata.set_evidence("source_tables", EvidenceType.CODE_DERIVED)
|
||||
nutrition_score_metadata.set_evidence("semantic_contract", EvidenceType.CODE_DERIVED)
|
||||
nutrition_score_metadata.set_evidence("business_meaning", EvidenceType.DRAFT_DERIVED)
|
||||
nutrition_score_metadata.set_evidence("unit", EvidenceType.CODE_DERIVED)
|
||||
nutrition_score_metadata.set_evidence("time_window", EvidenceType.CODE_DERIVED)
|
||||
nutrition_score_metadata.set_evidence("output_type", EvidenceType.CODE_DERIVED)
|
||||
nutrition_score_metadata.set_evidence("placeholder_type", EvidenceType.CODE_DERIVED)
|
||||
nutrition_score_metadata.set_evidence("format_hint", EvidenceType.CODE_DERIVED)
|
||||
nutrition_score_metadata.set_evidence("example_output", EvidenceType.CODE_DERIVED)
|
||||
nutrition_score_metadata.set_evidence("minimum_data_requirements", EvidenceType.MIXED)
|
||||
nutrition_score_metadata.set_evidence("confidence_logic", EvidenceType.CODE_DERIVED)
|
||||
nutrition_score_metadata.set_evidence("missing_value_policy", EvidenceType.CODE_DERIVED)
|
||||
nutrition_score_metadata.set_evidence("known_limitations", EvidenceType.MIXED)
|
||||
nutrition_score_metadata.set_evidence("layer_1_decision", EvidenceType.CODE_DERIVED)
|
||||
nutrition_score_metadata.set_evidence("layer_2a_decision", EvidenceType.CODE_DERIVED)
|
||||
nutrition_score_metadata.set_evidence("layer_2b_reuse_possible", EvidenceType.TO_VERIFY)
|
||||
nutrition_score_metadata.set_evidence("architecture_alignment", EvidenceType.CODE_DERIVED)
|
||||
nutrition_score_metadata.set_evidence("issue_53_alignment", EvidenceType.MIXED)
|
||||
|
||||
register_placeholder(nutrition_score_metadata)
|
||||
@@ -0,0 +1,66 @@
|
||||
"""Registry: Meta-Scores (Phase 0b) — Ziel-Fortschritt und Datenqualität."""
|
||||
|
||||
from placeholder_registry import (
|
||||
PlaceholderMetadata,
|
||||
MissingValuePolicy,
|
||||
OutputType,
|
||||
PlaceholderType,
|
||||
register_placeholder,
|
||||
)
|
||||
from ._evidence import tag_standard_evidence
|
||||
|
||||
CAT = "Scores (Phase 0b)"
|
||||
MVP = lambda reason, disp: MissingValuePolicy(
|
||||
available=False, value_raw=None, missing_reason=reason, legacy_display=disp
|
||||
)
|
||||
|
||||
|
||||
def register_phase_0b_meta_scores():
|
||||
for key, dl_fn, desc, unit in [
|
||||
(
|
||||
"goal_progress_score",
|
||||
"calculate_goal_progress_score",
|
||||
"Aggregierter Ziel-Fortschritt 0–100",
|
||||
"0–100",
|
||||
),
|
||||
(
|
||||
"data_quality_score",
|
||||
"calculate_data_quality_score",
|
||||
"Datenqualitäts-Score 0–100",
|
||||
"0–100",
|
||||
),
|
||||
]:
|
||||
m = PlaceholderMetadata(
|
||||
key=key,
|
||||
category=CAT,
|
||||
description=desc,
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="_safe_int",
|
||||
data_layer_module="backend/data_layer/scores.py",
|
||||
data_layer_function=dl_fn,
|
||||
source_tables=["goals", "weight_log", "nutrition_log", "activity_log", "profiles"],
|
||||
semantic_contract=f"scores.{dl_fn} (siehe Data Layer).",
|
||||
business_meaning="Meta-KPI für Prompt-Gewichtung",
|
||||
unit=unit,
|
||||
time_window="composite",
|
||||
output_type=OutputType.NUMERIC,
|
||||
placeholder_type=PlaceholderType.SCORE,
|
||||
format_hint="Ganzzahl als String",
|
||||
example_output="72",
|
||||
minimum_data_requirements="Abhängig von Score-Implementierung",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="Wie calculate_* in scores.py",
|
||||
missing_value_policy=MVP("insufficient_data", "nicht verfügbar"),
|
||||
known_limitations="Bei dünnen Daten weniger aussagekräftig",
|
||||
layer_1_decision=f"scores.{dl_fn}",
|
||||
layer_2a_decision="_safe_int",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment="Phase 0b",
|
||||
issue_53_alignment="Layer 1",
|
||||
evidence={},
|
||||
)
|
||||
tag_standard_evidence(m)
|
||||
register_placeholder(m)
|
||||
|
||||
|
||||
register_phase_0b_meta_scores()
|
||||
@@ -0,0 +1,392 @@
|
||||
"""Registry: Ziele, Fokusbereiche, Kategorie-Scores und formatierte Listen (Phase 0b)."""
|
||||
|
||||
from placeholder_registry import (
|
||||
PlaceholderMetadata,
|
||||
MissingValuePolicy,
|
||||
OutputType,
|
||||
PlaceholderType,
|
||||
register_placeholder,
|
||||
)
|
||||
from ._evidence import tag_standard_evidence
|
||||
|
||||
CAT = "Ziele & Fokus (Phase 0b)"
|
||||
MVP = lambda reason, disp: MissingValuePolicy(
|
||||
available=False, value_raw=None, missing_reason=reason, legacy_display=disp
|
||||
)
|
||||
|
||||
|
||||
def register_phase_0b_ziele_fokus():
|
||||
# Top-Ziel / Top-Fokusbereich
|
||||
m = PlaceholderMetadata(
|
||||
key="top_goal_name",
|
||||
category=CAT,
|
||||
description="Name/Typ des höchstpriorisierten Ziels",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="_safe_str",
|
||||
data_layer_module="backend/data_layer/scores.py",
|
||||
data_layer_function="get_top_priority_goal",
|
||||
source_tables=["goals"],
|
||||
semantic_contract="Feld name oder goal_type aus get_top_priority_goal",
|
||||
business_meaning="Priorisierung für KI-Empfehlungen",
|
||||
unit="text",
|
||||
time_window="aktuell",
|
||||
output_type=OutputType.STRING,
|
||||
placeholder_type=PlaceholderType.INTERPRETED,
|
||||
format_hint="Kurztext",
|
||||
example_output="Gewicht 80kg",
|
||||
minimum_data_requirements="Mindestens ein aktives Ziel",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="scores.get_top_priority_goal",
|
||||
missing_value_policy=MVP("insufficient_data", "nicht verfügbar"),
|
||||
known_limitations=None,
|
||||
layer_1_decision="scores.get_top_priority_goal",
|
||||
layer_2a_decision="_safe_str('top_goal_name')",
|
||||
layer_2b_reuse_possible=False,
|
||||
architecture_alignment="Phase 0b",
|
||||
issue_53_alignment="Layer 1",
|
||||
evidence={},
|
||||
)
|
||||
tag_standard_evidence(m)
|
||||
register_placeholder(m)
|
||||
|
||||
m = PlaceholderMetadata(
|
||||
key="top_goal_progress_pct",
|
||||
category=CAT,
|
||||
description="Fortschritt Top-Ziel (%)",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="_safe_int",
|
||||
data_layer_module="backend/data_layer/scores.py",
|
||||
data_layer_function="get_top_priority_goal",
|
||||
source_tables=["goals"],
|
||||
semantic_contract="progress_pct aus get_top_priority_goal",
|
||||
business_meaning="Priorisierung für KI-Empfehlungen",
|
||||
unit="%",
|
||||
time_window="aktuell",
|
||||
output_type=OutputType.NUMERIC,
|
||||
placeholder_type=PlaceholderType.SCORE,
|
||||
format_hint="Ganzzahl",
|
||||
example_output="65",
|
||||
minimum_data_requirements="Mindestens ein aktives Ziel",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="scores.get_top_priority_goal",
|
||||
missing_value_policy=MVP("insufficient_data", "nicht verfügbar"),
|
||||
known_limitations=None,
|
||||
layer_1_decision="scores.get_top_priority_goal",
|
||||
layer_2a_decision="_safe_int('top_goal_progress_pct')",
|
||||
layer_2b_reuse_possible=False,
|
||||
architecture_alignment="Phase 0b",
|
||||
issue_53_alignment="Layer 1",
|
||||
evidence={},
|
||||
)
|
||||
tag_standard_evidence(m)
|
||||
register_placeholder(m)
|
||||
|
||||
m = PlaceholderMetadata(
|
||||
key="top_goal_status",
|
||||
category=CAT,
|
||||
description="Status-Label Top-Ziel",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="_safe_str",
|
||||
data_layer_module="backend/data_layer/scores.py",
|
||||
data_layer_function="get_top_priority_goal",
|
||||
source_tables=["goals"],
|
||||
semantic_contract="status aus get_top_priority_goal",
|
||||
business_meaning="Priorisierung für KI-Empfehlungen",
|
||||
unit="text",
|
||||
time_window="aktuell",
|
||||
output_type=OutputType.STRING,
|
||||
placeholder_type=PlaceholderType.INTERPRETED,
|
||||
format_hint="Kurztext",
|
||||
example_output="active",
|
||||
minimum_data_requirements="Mindestens ein aktives Ziel",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="scores.get_top_priority_goal",
|
||||
missing_value_policy=MVP("insufficient_data", "nicht verfügbar"),
|
||||
known_limitations=None,
|
||||
layer_1_decision="scores.get_top_priority_goal",
|
||||
layer_2a_decision="_safe_str('top_goal_status')",
|
||||
layer_2b_reuse_possible=False,
|
||||
architecture_alignment="Phase 0b",
|
||||
issue_53_alignment="Layer 1",
|
||||
evidence={},
|
||||
)
|
||||
tag_standard_evidence(m)
|
||||
register_placeholder(m)
|
||||
|
||||
m = PlaceholderMetadata(
|
||||
key="top_focus_area_name",
|
||||
category=CAT,
|
||||
description="Bezeichnung des gewichtet stärksten Fokusbereichs",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="_safe_str",
|
||||
data_layer_module="backend/data_layer/scores.py",
|
||||
data_layer_function="get_top_focus_area",
|
||||
source_tables=["user_focus_area_weights", "focus_area_definitions"],
|
||||
semantic_contract="label aus get_top_focus_area",
|
||||
business_meaning="Priorisierung für KI-Empfehlungen",
|
||||
unit="text",
|
||||
time_window="aktuell",
|
||||
output_type=OutputType.STRING,
|
||||
placeholder_type=PlaceholderType.INTERPRETED,
|
||||
format_hint="Kurztext",
|
||||
example_output="Kraft",
|
||||
minimum_data_requirements="Gewichtete Fokusbereiche",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="scores.get_top_focus_area",
|
||||
missing_value_policy=MVP("insufficient_data", "nicht verfügbar"),
|
||||
known_limitations=None,
|
||||
layer_1_decision="scores.get_top_focus_area",
|
||||
layer_2a_decision="_safe_str('top_focus_area_name')",
|
||||
layer_2b_reuse_possible=False,
|
||||
architecture_alignment="Phase 0b",
|
||||
issue_53_alignment="Layer 1",
|
||||
evidence={},
|
||||
)
|
||||
tag_standard_evidence(m)
|
||||
register_placeholder(m)
|
||||
|
||||
m = PlaceholderMetadata(
|
||||
key="top_focus_area_progress",
|
||||
category=CAT,
|
||||
description="Fortschritt Top-Fokusbereich (%)",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="_safe_int",
|
||||
data_layer_module="backend/data_layer/scores.py",
|
||||
data_layer_function="get_top_focus_area",
|
||||
source_tables=["user_focus_area_weights", "focus_area_definitions", "goals"],
|
||||
semantic_contract="progress aus get_top_focus_area",
|
||||
business_meaning="Priorisierung für KI-Empfehlungen",
|
||||
unit="%",
|
||||
time_window="aktuell",
|
||||
output_type=OutputType.NUMERIC,
|
||||
placeholder_type=PlaceholderType.SCORE,
|
||||
format_hint="Ganzzahl",
|
||||
example_output="58",
|
||||
minimum_data_requirements="Gewichtete Fokusbereiche",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="scores.get_top_focus_area",
|
||||
missing_value_policy=MVP("insufficient_data", "nicht verfügbar"),
|
||||
known_limitations=None,
|
||||
layer_1_decision="scores.get_top_focus_area",
|
||||
layer_2a_decision="_safe_int('top_focus_area_progress')",
|
||||
layer_2b_reuse_possible=False,
|
||||
architecture_alignment="Phase 0b",
|
||||
issue_53_alignment="Layer 1",
|
||||
evidence={},
|
||||
)
|
||||
tag_standard_evidence(m)
|
||||
register_placeholder(m)
|
||||
|
||||
# Kategorie Progress / Weight (7 Kategorien)
|
||||
for slug in (
|
||||
"körper",
|
||||
"ernährung",
|
||||
"aktivität",
|
||||
"recovery",
|
||||
"vitalwerte",
|
||||
"mental",
|
||||
"lebensstil",
|
||||
):
|
||||
key_p = f"focus_cat_{slug}_progress"
|
||||
key_w = f"focus_cat_{slug}_weight"
|
||||
m_p = PlaceholderMetadata(
|
||||
key=key_p,
|
||||
category=CAT,
|
||||
description=f"Aggregierter Fortschritt Kategorie „{slug}“ (%)",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="_safe_int",
|
||||
data_layer_module="backend/data_layer/scores.py",
|
||||
data_layer_function="calculate_category_progress",
|
||||
source_tables=["goals", "focus_area_definitions", "user_focus_area_weights"],
|
||||
semantic_contract=f"scores.calculate_category_progress(pid, '{slug}')",
|
||||
business_meaning="Focus-Area-Kategorie-Score",
|
||||
unit="%",
|
||||
time_window="aktuell",
|
||||
output_type=OutputType.NUMERIC,
|
||||
placeholder_type=PlaceholderType.SCORE,
|
||||
format_hint="Ganzzahl",
|
||||
example_output="55",
|
||||
minimum_data_requirements="Gewichtete Bereiche in Kategorie",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="scores.calculate_category_progress",
|
||||
missing_value_policy=MVP("insufficient_data", "nicht verfügbar"),
|
||||
known_limitations=None,
|
||||
layer_1_decision="scores.calculate_category_progress",
|
||||
layer_2a_decision="_safe_int",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment="Phase 0b",
|
||||
issue_53_alignment="Layer 1",
|
||||
evidence={},
|
||||
)
|
||||
tag_standard_evidence(m_p)
|
||||
register_placeholder(m_p)
|
||||
|
||||
m_w = PlaceholderMetadata(
|
||||
key=key_w,
|
||||
category=CAT,
|
||||
description=f"Nutzer-Gewichtung Kategorie „{slug}“ (Anteil 0–1)",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="_safe_float",
|
||||
data_layer_module="backend/data_layer/scores.py",
|
||||
data_layer_function="calculate_category_weight",
|
||||
source_tables=["user_focus_area_weights", "focus_area_definitions"],
|
||||
semantic_contract=f"scores.calculate_category_weight(pid, '{slug}')",
|
||||
business_meaning="Kategorie-Gewichtung im Fokusmodell",
|
||||
unit="0–1",
|
||||
time_window="aktuell",
|
||||
output_type=OutputType.NUMERIC,
|
||||
placeholder_type=PlaceholderType.INTERPRETED,
|
||||
format_hint="Dezimal",
|
||||
example_output="0.25",
|
||||
minimum_data_requirements="user_focus_area_weights",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="scores.calculate_category_weight",
|
||||
missing_value_policy=MVP("insufficient_data", "nicht verfügbar"),
|
||||
known_limitations=None,
|
||||
layer_1_decision="scores.calculate_category_weight",
|
||||
layer_2a_decision="_safe_float",
|
||||
layer_2b_reuse_possible=False,
|
||||
architecture_alignment="Phase 0b",
|
||||
issue_53_alignment="Layer 1",
|
||||
evidence={},
|
||||
)
|
||||
tag_standard_evidence(m_w)
|
||||
register_placeholder(m_w)
|
||||
|
||||
# Strukturierte Ziele / Fokus
|
||||
for key, res_fn, dl_mod, dl_fn, desc, out, ptype in [
|
||||
(
|
||||
"active_goals_json",
|
||||
"_safe_json",
|
||||
"backend/goal_utils.py",
|
||||
"get_active_goals",
|
||||
"Aktive Ziele als JSON",
|
||||
OutputType.JSON,
|
||||
PlaceholderType.RAW_DATA,
|
||||
),
|
||||
(
|
||||
"active_goals_md",
|
||||
"_safe_str",
|
||||
"backend/placeholder_resolver.py",
|
||||
"_format_goals_as_markdown",
|
||||
"Aktive Ziele als Markdown-Tabelle",
|
||||
OutputType.TEXT_SUMMARY,
|
||||
PlaceholderType.INTERPRETED,
|
||||
),
|
||||
(
|
||||
"focus_areas_weighted_json",
|
||||
"_safe_json",
|
||||
"backend/placeholder_resolver.py",
|
||||
"_get_focus_areas_weighted_json",
|
||||
"Gewichtete Fokusbereiche mit Namen (JSON)",
|
||||
OutputType.JSON,
|
||||
PlaceholderType.RAW_DATA,
|
||||
),
|
||||
(
|
||||
"focus_areas_weighted_md",
|
||||
"_safe_str",
|
||||
"backend/placeholder_resolver.py",
|
||||
"_format_focus_areas_as_markdown",
|
||||
"Gewichtete Fokusbereiche als Markdown",
|
||||
OutputType.TEXT_SUMMARY,
|
||||
PlaceholderType.INTERPRETED,
|
||||
),
|
||||
(
|
||||
"focus_area_weights_json",
|
||||
"_safe_json",
|
||||
"backend/data_layer/scores.py",
|
||||
"get_user_focus_weights",
|
||||
"Rohe Gewichtungen key→Anteil (JSON)",
|
||||
OutputType.JSON,
|
||||
PlaceholderType.RAW_DATA,
|
||||
),
|
||||
]:
|
||||
m = PlaceholderMetadata(
|
||||
key=key,
|
||||
category=CAT,
|
||||
description=desc,
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function=res_fn,
|
||||
data_layer_module=dl_mod,
|
||||
data_layer_function=dl_fn,
|
||||
source_tables=["goals", "focus_area_definitions", "user_focus_area_weights"],
|
||||
semantic_contract=f"{dl_fn} (siehe Modul {dl_mod})",
|
||||
business_meaning="Strukturierte Übersicht für Prompts",
|
||||
unit="JSON" if out == OutputType.JSON else "markdown",
|
||||
time_window="aktuell",
|
||||
output_type=out,
|
||||
placeholder_type=ptype,
|
||||
format_hint="String aus Resolver",
|
||||
example_output="[]" if out == OutputType.JSON else "—",
|
||||
minimum_data_requirements="Ziele bzw. Fokusgewichte",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="Resolver + goal_utils / scores",
|
||||
missing_value_policy=MVP("insufficient_data", "[]" if out == OutputType.JSON else "nicht verfügbar"),
|
||||
known_limitations=None,
|
||||
layer_1_decision=dl_fn,
|
||||
layer_2a_decision=res_fn,
|
||||
layer_2b_reuse_possible=False,
|
||||
architecture_alignment="Phase 0b",
|
||||
issue_53_alignment="Layer 1",
|
||||
evidence={},
|
||||
)
|
||||
tag_standard_evidence(m)
|
||||
register_placeholder(m)
|
||||
|
||||
for key, res_fn, dl_fn, desc, ex in [
|
||||
(
|
||||
"top_3_focus_areas",
|
||||
"_safe_str",
|
||||
"_format_top_focus_areas",
|
||||
"Top-3 Fokusbereiche als formatierter Text",
|
||||
"1. Kraft …",
|
||||
),
|
||||
(
|
||||
"top_3_goals_behind_schedule",
|
||||
"_safe_str",
|
||||
"_format_goals_behind",
|
||||
"Bis zu drei Ziele hinter Zeitplan",
|
||||
"—",
|
||||
),
|
||||
(
|
||||
"top_3_goals_on_track",
|
||||
"_safe_str",
|
||||
"_format_goals_on_track",
|
||||
"Bis zu drei Ziele im Plan",
|
||||
"—",
|
||||
),
|
||||
]:
|
||||
m = PlaceholderMetadata(
|
||||
key=key,
|
||||
category=CAT,
|
||||
description=desc,
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function=res_fn,
|
||||
data_layer_module="backend/goal_utils.py",
|
||||
data_layer_function="get_active_goals",
|
||||
source_tables=["goals", "focus_area_definitions"],
|
||||
semantic_contract=f"Resolver {dl_fn}",
|
||||
business_meaning="Kurzlisten für Coaching-Prompts",
|
||||
unit="text",
|
||||
time_window="aktuell",
|
||||
output_type=OutputType.TEXT_SUMMARY,
|
||||
placeholder_type=PlaceholderType.INTERPRETED,
|
||||
format_hint="Freitext / Aufzählung",
|
||||
example_output=ex,
|
||||
minimum_data_requirements="Ziele / Fokusdaten",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic=dl_fn,
|
||||
missing_value_policy=MVP("insufficient_data", "nicht verfügbar"),
|
||||
known_limitations=None,
|
||||
layer_1_decision="goals + focus aggregation",
|
||||
layer_2a_decision=dl_fn,
|
||||
layer_2b_reuse_possible=False,
|
||||
architecture_alignment="Phase 0b",
|
||||
issue_53_alignment="Layer 2a",
|
||||
evidence={},
|
||||
)
|
||||
tag_standard_evidence(m)
|
||||
register_placeholder(m)
|
||||
|
||||
|
||||
register_phase_0b_ziele_fokus()
|
||||
@@ -0,0 +1,139 @@
|
||||
"""
|
||||
Registry: Profil-Stammdaten und statische Zeitraum-Labels für Prompts.
|
||||
"""
|
||||
|
||||
from placeholder_registry import (
|
||||
PlaceholderMetadata,
|
||||
MissingValuePolicy,
|
||||
OutputType,
|
||||
PlaceholderType,
|
||||
register_placeholder,
|
||||
)
|
||||
from ._evidence import tag_standard_evidence
|
||||
|
||||
MVP = lambda reason, disp: MissingValuePolicy(
|
||||
available=False, value_raw=None, missing_reason=reason, legacy_display=disp
|
||||
)
|
||||
|
||||
|
||||
def register_profil_zeitraum():
|
||||
cat_profil = "Profil"
|
||||
for key, desc, res_fn, unit, ptype, out, hint, ex, sem in [
|
||||
(
|
||||
"name",
|
||||
"Anzeigename aus profiles.name",
|
||||
"get_profile_name",
|
||||
"text",
|
||||
PlaceholderType.ATOMIC,
|
||||
OutputType.STRING,
|
||||
"Kurzname",
|
||||
"Max",
|
||||
"profiles.name, Fallback „Nutzer“.",
|
||||
),
|
||||
(
|
||||
"age",
|
||||
"Alter in Jahren aus profiles.dob",
|
||||
"get_profile_age_display",
|
||||
"Jahre",
|
||||
PlaceholderType.ATOMIC,
|
||||
OutputType.STRING,
|
||||
"Ganzzahl oder unbekannt",
|
||||
"42",
|
||||
"Berechnung aus Geburtsdatum; PostgreSQL date oder ISO-String.",
|
||||
),
|
||||
(
|
||||
"height",
|
||||
"Körpergröße (cm) aus profiles.height",
|
||||
"get_profile_height_display",
|
||||
"cm",
|
||||
PlaceholderType.ATOMIC,
|
||||
OutputType.STRING,
|
||||
"Zahl oder unbekannt",
|
||||
"180",
|
||||
"profiles.height.",
|
||||
),
|
||||
(
|
||||
"geschlecht",
|
||||
"Geschlecht (männlich/weiblich) aus profiles.sex",
|
||||
"get_profile_geschlecht_display",
|
||||
"Kategorie",
|
||||
PlaceholderType.ATOMIC,
|
||||
OutputType.STRING,
|
||||
"m/w-Mapping",
|
||||
"männlich",
|
||||
"sex == 'm' → männlich, sonst weiblich.",
|
||||
),
|
||||
]:
|
||||
m = PlaceholderMetadata(
|
||||
key=key,
|
||||
category=cat_profil,
|
||||
description=desc,
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function=res_fn,
|
||||
data_layer_module=None,
|
||||
data_layer_function=None,
|
||||
source_tables=["profiles"],
|
||||
semantic_contract=sem,
|
||||
business_meaning="Profil-Kontext für KI-Prompts",
|
||||
unit=unit,
|
||||
time_window="latest profile row",
|
||||
output_type=out,
|
||||
placeholder_type=ptype,
|
||||
format_hint=hint,
|
||||
example_output=ex,
|
||||
minimum_data_requirements="Profilzeile",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="Row vorhanden",
|
||||
missing_value_policy=MVP("no_data", "unbekannt" if key != "name" else "Nutzer"),
|
||||
known_limitations="Keine diversen Geschlechtsoptionen im Platzhalter",
|
||||
layer_1_decision="profiles",
|
||||
layer_2a_decision=res_fn,
|
||||
layer_2b_reuse_possible=False,
|
||||
architecture_alignment="Phase 0b",
|
||||
issue_53_alignment="Resolver",
|
||||
evidence={},
|
||||
)
|
||||
tag_standard_evidence(m)
|
||||
register_placeholder(m)
|
||||
|
||||
cat_zeit = "Zeitraum"
|
||||
for key, desc, res_fn, sem, ex_out in [
|
||||
("datum_heute", "Heutiges Datum (lokal)", "get_datum_heute", "datetime.now, Format dd.mm.yyyy", "11.04.2026"),
|
||||
("zeitraum_7d", "Label „letzte 7 Tage“", "get_zeitraum_label_7d", "Statisches UI/Prompt-Label", "letzte 7 Tage"),
|
||||
("zeitraum_30d", "Label „letzte 30 Tage“", "get_zeitraum_label_30d", "Statisches UI/Prompt-Label", "letzte 30 Tage"),
|
||||
("zeitraum_90d", "Label „letzte 90 Tage“", "get_zeitraum_label_90d", "Statisches UI/Prompt-Label", "letzte 90 Tage"),
|
||||
]:
|
||||
m = PlaceholderMetadata(
|
||||
key=key,
|
||||
category=cat_zeit,
|
||||
description=desc,
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function=res_fn,
|
||||
data_layer_module=None,
|
||||
data_layer_function=None,
|
||||
source_tables=[],
|
||||
semantic_contract=sem,
|
||||
business_meaning="Zeitlicher Bezug im Prompt ohne Datenabfrage",
|
||||
unit="label",
|
||||
time_window="n/a",
|
||||
output_type=OutputType.STRING,
|
||||
placeholder_type=PlaceholderType.META,
|
||||
format_hint="Kurzdeutsch",
|
||||
example_output=ex_out,
|
||||
minimum_data_requirements=None,
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="Immer verfügbar",
|
||||
missing_value_policy=None,
|
||||
known_limitations="Kein kalender-basierter Datenfilter allein durch Platzhalter",
|
||||
layer_1_decision="n/a",
|
||||
layer_2a_decision=res_fn,
|
||||
layer_2b_reuse_possible=False,
|
||||
architecture_alignment="Phase 0b",
|
||||
issue_53_alignment="Resolver",
|
||||
evidence={},
|
||||
)
|
||||
tag_standard_evidence(m)
|
||||
register_placeholder(m)
|
||||
|
||||
|
||||
register_profil_zeitraum()
|
||||
@@ -0,0 +1,236 @@
|
||||
"""
|
||||
Registry: Schlaf, Ruhetage, Recovery-Score, Schlaf-Metriken, Schlaf-Erholungs-Korrelation.
|
||||
"""
|
||||
|
||||
from placeholder_registry import (
|
||||
PlaceholderMetadata,
|
||||
MissingValuePolicy,
|
||||
EvidenceType,
|
||||
OutputType,
|
||||
PlaceholderType,
|
||||
register_placeholder,
|
||||
)
|
||||
|
||||
CAT = "Schlaf & Erholung"
|
||||
MVP = lambda reason, disp: MissingValuePolicy(
|
||||
available=False, value_raw=None, missing_reason=reason, legacy_display=disp
|
||||
)
|
||||
|
||||
|
||||
def _tag(m: PlaceholderMetadata):
|
||||
for f in (
|
||||
"key", "category", "description", "resolver_module", "resolver_function",
|
||||
"data_layer_module", "data_layer_function", "source_tables", "semantic_contract",
|
||||
"unit", "time_window", "output_type", "placeholder_type", "format_hint",
|
||||
"example_output", "minimum_data_requirements", "confidence_logic",
|
||||
"missing_value_policy", "layer_1_decision", "layer_2a_decision",
|
||||
"layer_2b_reuse_possible", "architecture_alignment", "issue_53_alignment",
|
||||
):
|
||||
m.set_evidence(f, EvidenceType.CODE_DERIVED)
|
||||
m.set_evidence("business_meaning", EvidenceType.DRAFT_DERIVED)
|
||||
m.set_evidence("known_limitations", EvidenceType.MIXED)
|
||||
|
||||
|
||||
def register_schlaf_erholung():
|
||||
# ── formatierte Schlaf-/Ruhetage-Snapshots ───────────────────────────────
|
||||
m = PlaceholderMetadata(
|
||||
key="sleep_avg_duration",
|
||||
category=CAT,
|
||||
description="Durchschnittliche Schlafdauer (Stunden), formatiert",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="get_sleep_avg_duration",
|
||||
data_layer_module="backend/data_layer/recovery_metrics.py",
|
||||
data_layer_function="get_sleep_duration_data",
|
||||
source_tables=["sleep_log"],
|
||||
semantic_contract="Mittel aus Schlafphasen im Fenster (siehe get_sleep_duration_data).",
|
||||
business_meaning="KI-Kontext Schlafdauer",
|
||||
unit="h (Anzeige mit Einheit)",
|
||||
time_window="7d default im Resolver",
|
||||
output_type=OutputType.STRING,
|
||||
placeholder_type=PlaceholderType.INTERPRETED,
|
||||
format_hint="z. B. 7.2h",
|
||||
example_output="7.2h",
|
||||
minimum_data_requirements="sleep_log im Fenster",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="data['confidence'] im Layer1",
|
||||
missing_value_policy=MVP("no_data", "nicht verfügbar"),
|
||||
known_limitations="Abhängig von Import/Qualität der Phasen",
|
||||
layer_1_decision="recovery_metrics.get_sleep_duration_data",
|
||||
layer_2a_decision="get_sleep_avg_duration",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment="Phase 0c",
|
||||
issue_53_alignment="Layer 1",
|
||||
evidence={},
|
||||
)
|
||||
_tag(m)
|
||||
register_placeholder(m)
|
||||
|
||||
m = PlaceholderMetadata(
|
||||
key="sleep_avg_quality",
|
||||
category=CAT,
|
||||
description="Schlafqualität (Deep+REM %), formatiert",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="get_sleep_avg_quality",
|
||||
data_layer_module="backend/data_layer/recovery_metrics.py",
|
||||
data_layer_function="get_sleep_quality_data",
|
||||
source_tables=["sleep_log"],
|
||||
semantic_contract="Anteil Deep+REM aus Segmenten (siehe get_sleep_quality_data).",
|
||||
business_meaning="KI-Kontext Schlafqualität",
|
||||
unit="%",
|
||||
time_window="7d default",
|
||||
output_type=OutputType.STRING,
|
||||
placeholder_type=PlaceholderType.INTERPRETED,
|
||||
format_hint="Prozent oder nicht verfügbar",
|
||||
example_output="24%",
|
||||
minimum_data_requirements="sleep_log mit Phasen",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="Layer-1-Confidence",
|
||||
missing_value_policy=MVP("no_data", "nicht verfügbar"),
|
||||
known_limitations="Segment-Schreibweise case-sensitiv normalisiert",
|
||||
layer_1_decision="recovery_metrics.get_sleep_quality_data",
|
||||
layer_2a_decision="get_sleep_avg_quality",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment="Phase 0c",
|
||||
issue_53_alignment="Layer 1",
|
||||
evidence={},
|
||||
)
|
||||
_tag(m)
|
||||
register_placeholder(m)
|
||||
|
||||
m = PlaceholderMetadata(
|
||||
key="rest_days_count",
|
||||
category=CAT,
|
||||
description="Anzahl dokumentierter Ruhetage (30d default)",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="get_rest_days_count",
|
||||
data_layer_module="backend/data_layer/recovery_metrics.py",
|
||||
data_layer_function="get_rest_days_data",
|
||||
source_tables=["rest_days"],
|
||||
semantic_contract="Count rest_days im Zeitraum",
|
||||
business_meaning="Aktive/passive Erholungstags-Übersicht",
|
||||
unit="count",
|
||||
time_window="30d default",
|
||||
output_type=OutputType.STRING,
|
||||
placeholder_type=PlaceholderType.RAW_DATA,
|
||||
format_hint="z. B. 2 Ruhetage",
|
||||
example_output="2 Ruhetage",
|
||||
minimum_data_requirements="rest_days",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="Immer Zählung, 0 möglich",
|
||||
missing_value_policy=MVP("no_data", "0 Ruhetage"),
|
||||
known_limitations="Nur explizit erfasste Ruhetage",
|
||||
layer_1_decision="recovery_metrics.get_rest_days_data",
|
||||
layer_2a_decision="get_rest_days_count",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment="Phase 0c",
|
||||
issue_53_alignment="Layer 1",
|
||||
evidence={},
|
||||
)
|
||||
_tag(m)
|
||||
register_placeholder(m)
|
||||
|
||||
m = PlaceholderMetadata(
|
||||
key="recovery_score",
|
||||
category=CAT,
|
||||
description="Recovery-Score 0–100 (v2, komposit)",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="_safe_int",
|
||||
data_layer_module="backend/data_layer/recovery_metrics.py",
|
||||
data_layer_function="calculate_recovery_score_v2",
|
||||
source_tables=["sleep_log", "vitals_baseline", "activity_log"],
|
||||
semantic_contract="Gewichteter Score aus Schlaf, Vitaltrends, optional Load (siehe Implementierung).",
|
||||
business_meaning="Gesamt-Recovery-KPI für Prompts",
|
||||
unit="0–100",
|
||||
time_window="composite",
|
||||
output_type=OutputType.NUMERIC,
|
||||
placeholder_type=PlaceholderType.SCORE,
|
||||
format_hint="Ganzzahl-String",
|
||||
example_output="72",
|
||||
minimum_data_requirements="Teilkomponenten je nach Gewichtung",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="Wie calculate_recovery_score_v2",
|
||||
missing_value_policy=MVP("insufficient_data", "nicht verfügbar"),
|
||||
known_limitations="Abhängig von Datenabdeckung HF/HRV/Schlaf",
|
||||
layer_1_decision="recovery_metrics.calculate_recovery_score_v2",
|
||||
layer_2a_decision="_safe_int('recovery_score_v2')",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment="Phase 0c",
|
||||
issue_53_alignment="Layer 1",
|
||||
evidence={},
|
||||
)
|
||||
_tag(m)
|
||||
register_placeholder(m)
|
||||
|
||||
for key, dl_fn, desc, unit, tbls, res_fn in [
|
||||
("sleep_avg_duration_7d", "calculate_sleep_avg_duration_7d", "Durchschnittliche Schlafdauer 7d (h)", "h", ["sleep_log"], "_safe_float"),
|
||||
("sleep_debt_hours", "calculate_sleep_debt_hours", "Kumulative Schlafschuld (h)", "h", ["sleep_log"], "_safe_float"),
|
||||
("sleep_regularity_proxy", "calculate_sleep_regularity_proxy", "Schlaf-Regularität (Proxy)", "min", ["sleep_log"], "_safe_float"),
|
||||
("recent_load_balance_3d", "calculate_recent_load_balance_3d", "Load-Balance 3d (Score)", "score", ["activity_log"], "_safe_int"),
|
||||
("sleep_quality_7d", "calculate_sleep_quality_7d", "Schlafqualität 7d (0–100)", "0-100", ["sleep_log"], "_safe_int"),
|
||||
]:
|
||||
m = PlaceholderMetadata(
|
||||
key=key,
|
||||
category=CAT,
|
||||
description=desc,
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function=res_fn,
|
||||
data_layer_module="backend/data_layer/recovery_metrics.py",
|
||||
data_layer_function=dl_fn,
|
||||
source_tables=tbls,
|
||||
semantic_contract=f"Berechnung {dl_fn} in recovery_metrics.",
|
||||
business_meaning="Erholungs-Detailmetrik",
|
||||
unit=unit,
|
||||
time_window="siehe Funktion",
|
||||
output_type=OutputType.NUMERIC,
|
||||
placeholder_type=PlaceholderType.INTERPRETED,
|
||||
format_hint="numerischer String",
|
||||
example_output="1.0",
|
||||
minimum_data_requirements="wie Funktion",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="Funktionsintern",
|
||||
missing_value_policy=MVP("insufficient_data", "nicht verfügbar"),
|
||||
known_limitations=None,
|
||||
layer_1_decision=f"recovery_metrics.{dl_fn}",
|
||||
layer_2a_decision="Resolver _safe_float/_safe_int",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment="Phase 0c",
|
||||
issue_53_alignment="Layer 1",
|
||||
evidence={},
|
||||
)
|
||||
_tag(m)
|
||||
register_placeholder(m)
|
||||
|
||||
m = PlaceholderMetadata(
|
||||
key="correlation_sleep_recovery",
|
||||
category=CAT,
|
||||
description="JSON: Korrelation Schlaf ↔ Recovery-Indikatoren",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="_safe_json",
|
||||
data_layer_module="backend/data_layer/correlations.py",
|
||||
data_layer_function="calculate_correlation_sleep_recovery",
|
||||
source_tables=["sleep_log", "vitals_baseline", "activity_log"],
|
||||
semantic_contract="Strukturierte Korrelationsauswertung (siehe correlations).",
|
||||
business_meaning="KI: Zusammenhänge Schlaf und Erholung",
|
||||
unit="JSON",
|
||||
time_window="funktionsabhängig",
|
||||
output_type=OutputType.JSON,
|
||||
placeholder_type=PlaceholderType.RAW_DATA,
|
||||
format_hint="JSON-String",
|
||||
example_output="{}",
|
||||
minimum_data_requirements="Ausreichend gekoppelte Datenpunkte",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="Wie correlation_metrics",
|
||||
missing_value_policy=MVP("insufficient_data", "{}"),
|
||||
known_limitations="Bei wenig Daten leer oder schwach",
|
||||
layer_1_decision="correlations.calculate_correlation_sleep_recovery",
|
||||
layer_2a_decision="_safe_json",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment="Phase 0c",
|
||||
issue_53_alignment="Layer 1",
|
||||
evidence={},
|
||||
)
|
||||
_tag(m)
|
||||
register_placeholder(m)
|
||||
|
||||
|
||||
register_schlaf_erholung()
|
||||
@@ -0,0 +1,180 @@
|
||||
"""
|
||||
Registry: Baseline-Vitals (Ruhepuls, HRV, VO2 Max) und Abweichung vs. persönlicher Baseline.
|
||||
"""
|
||||
|
||||
from placeholder_registry import (
|
||||
PlaceholderMetadata,
|
||||
MissingValuePolicy,
|
||||
EvidenceType,
|
||||
OutputType,
|
||||
PlaceholderType,
|
||||
register_placeholder,
|
||||
)
|
||||
|
||||
CAT = "Vitalwerte"
|
||||
MVP = lambda reason, disp: MissingValuePolicy(
|
||||
available=False, value_raw=None, missing_reason=reason, legacy_display=disp
|
||||
)
|
||||
|
||||
|
||||
def _tag(m: PlaceholderMetadata):
|
||||
for f in (
|
||||
"key", "category", "description", "resolver_module", "resolver_function",
|
||||
"data_layer_module", "data_layer_function", "source_tables", "semantic_contract",
|
||||
"unit", "time_window", "output_type", "placeholder_type", "format_hint",
|
||||
"example_output", "minimum_data_requirements", "confidence_logic",
|
||||
"missing_value_policy", "layer_1_decision", "layer_2a_decision",
|
||||
"layer_2b_reuse_possible", "architecture_alignment", "issue_53_alignment",
|
||||
):
|
||||
m.set_evidence(f, EvidenceType.CODE_DERIVED)
|
||||
m.set_evidence("business_meaning", EvidenceType.DRAFT_DERIVED)
|
||||
m.set_evidence("known_limitations", EvidenceType.MIXED)
|
||||
|
||||
|
||||
def register_vitalwerte():
|
||||
m = PlaceholderMetadata(
|
||||
key="vitals_avg_hr",
|
||||
category=CAT,
|
||||
description="Durchschnittlicher Ruhepuls (7d), formatiert",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="get_vitals_avg_hr",
|
||||
data_layer_module="backend/data_layer/health_metrics.py",
|
||||
data_layer_function="get_resting_heart_rate_data",
|
||||
source_tables=["vitals_baseline"],
|
||||
semantic_contract="Mittel RHR aus vitals_baseline im Fenster (siehe health_metrics).",
|
||||
business_meaning="KI-Kontext kardiovaskuläre Ruhelage",
|
||||
unit="bpm (Anzeige mit Einheit)",
|
||||
time_window="7d default im Resolver",
|
||||
output_type=OutputType.STRING,
|
||||
placeholder_type=PlaceholderType.INTERPRETED,
|
||||
format_hint="z. B. 58 bpm",
|
||||
example_output="58 bpm",
|
||||
minimum_data_requirements="vitals_baseline im Fenster",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="data['confidence'] im Layer1",
|
||||
missing_value_policy=MVP("no_data", "nicht verfügbar"),
|
||||
known_limitations="Nur erfasste Morgen-Baseline-Messungen",
|
||||
layer_1_decision="health_metrics.get_resting_heart_rate_data",
|
||||
layer_2a_decision="get_vitals_avg_hr",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment="Phase 0c",
|
||||
issue_53_alignment="Layer 1",
|
||||
evidence={},
|
||||
)
|
||||
_tag(m)
|
||||
register_placeholder(m)
|
||||
|
||||
m = PlaceholderMetadata(
|
||||
key="vitals_avg_hrv",
|
||||
category=CAT,
|
||||
description="Durchschnittliche HRV (7d), formatiert",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="get_vitals_avg_hrv",
|
||||
data_layer_module="backend/data_layer/health_metrics.py",
|
||||
data_layer_function="get_heart_rate_variability_data",
|
||||
source_tables=["vitals_baseline"],
|
||||
semantic_contract="Mittel HRV aus vitals_baseline im Fenster.",
|
||||
business_meaning="KI-Kontext autonome Regulation / Erholung",
|
||||
unit="ms (Anzeige mit Einheit)",
|
||||
time_window="7d default",
|
||||
output_type=OutputType.STRING,
|
||||
placeholder_type=PlaceholderType.INTERPRETED,
|
||||
format_hint="z. B. 45 ms",
|
||||
example_output="45 ms",
|
||||
minimum_data_requirements="vitals_baseline mit HRV",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="data['confidence'] im Layer1",
|
||||
missing_value_policy=MVP("no_data", "nicht verfügbar"),
|
||||
known_limitations="Geräte-/Messprotokoll kann streuen",
|
||||
layer_1_decision="health_metrics.get_heart_rate_variability_data",
|
||||
layer_2a_decision="get_vitals_avg_hrv",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment="Phase 0c",
|
||||
issue_53_alignment="Layer 1",
|
||||
evidence={},
|
||||
)
|
||||
_tag(m)
|
||||
register_placeholder(m)
|
||||
|
||||
m = PlaceholderMetadata(
|
||||
key="vitals_vo2_max",
|
||||
category=CAT,
|
||||
description="Aktueller VO2 Max (letzte Messung), formatiert",
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function="get_vitals_vo2_max",
|
||||
data_layer_module="backend/data_layer/health_metrics.py",
|
||||
data_layer_function="get_vo2_max_data",
|
||||
source_tables=["vitals_baseline"],
|
||||
semantic_contract="Jüngster vo2_max aus vitals_baseline.",
|
||||
business_meaning="Ausdauer-/Fitness-Kontext",
|
||||
unit="ml/kg/min",
|
||||
time_window="latest",
|
||||
output_type=OutputType.STRING,
|
||||
placeholder_type=PlaceholderType.INTERPRETED,
|
||||
format_hint="eine Dezimalstelle + Einheit",
|
||||
example_output="42.0 ml/kg/min",
|
||||
minimum_data_requirements="mindestens eine VO2-Messung",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="data['confidence'] im Layer1",
|
||||
missing_value_policy=MVP("no_data", "nicht verfügbar"),
|
||||
known_limitations="Schätzung vs. Labortest je nach Quelle",
|
||||
layer_1_decision="health_metrics.get_vo2_max_data",
|
||||
layer_2a_decision="get_vitals_vo2_max",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment="Phase 0c",
|
||||
issue_53_alignment="Layer 1",
|
||||
evidence={},
|
||||
)
|
||||
_tag(m)
|
||||
register_placeholder(m)
|
||||
|
||||
for key, dl_fn, desc, unit, res_fn in [
|
||||
(
|
||||
"hrv_vs_baseline_pct",
|
||||
"calculate_hrv_vs_baseline_pct",
|
||||
"HRV vs. persönlicher Baseline (%)",
|
||||
"%",
|
||||
"_safe_float",
|
||||
),
|
||||
(
|
||||
"rhr_vs_baseline_pct",
|
||||
"calculate_rhr_vs_baseline_pct",
|
||||
"Ruhepuls vs. persönlicher Baseline (%)",
|
||||
"%",
|
||||
"_safe_float",
|
||||
),
|
||||
]:
|
||||
m = PlaceholderMetadata(
|
||||
key=key,
|
||||
category=CAT,
|
||||
description=desc,
|
||||
resolver_module="backend/placeholder_resolver.py",
|
||||
resolver_function=res_fn,
|
||||
data_layer_module="backend/data_layer/recovery_metrics.py",
|
||||
data_layer_function=dl_fn,
|
||||
source_tables=["vitals_baseline"],
|
||||
semantic_contract=f"Vergleich aktueller Wert zu Baseline (siehe {dl_fn}).",
|
||||
business_meaning="Erholungs- und Belastungsindikator relativ zur Norm des Nutzers",
|
||||
unit=unit,
|
||||
time_window="funktionsintern",
|
||||
output_type=OutputType.NUMERIC,
|
||||
placeholder_type=PlaceholderType.INTERPRETED,
|
||||
format_hint="numerischer Prozent-String",
|
||||
example_output="5.2",
|
||||
minimum_data_requirements="Ausreichend Baseline-Historie",
|
||||
quality_filter_policy=None,
|
||||
confidence_logic="Funktionsintern",
|
||||
missing_value_policy=MVP("insufficient_data", "nicht verfügbar"),
|
||||
known_limitations="Baseline braucht ausreichend Vorlauf",
|
||||
layer_1_decision=f"recovery_metrics.{dl_fn}",
|
||||
layer_2a_decision=f"Resolver {res_fn}",
|
||||
layer_2b_reuse_possible=True,
|
||||
architecture_alignment="Phase 0c",
|
||||
issue_53_alignment="Layer 1",
|
||||
evidence={},
|
||||
)
|
||||
_tag(m)
|
||||
register_placeholder(m)
|
||||
|
||||
|
||||
register_vitalwerte()
|
||||
@@ -258,6 +258,42 @@ class PlaceholderRegistry:
|
||||
return metadata._resolver_func(profile_id)
|
||||
|
||||
|
||||
def build_ai_placeholder_caption(metadata: PlaceholderMetadata, max_len: int = 400) -> str:
|
||||
"""
|
||||
Kurzerklärung / Einordnung für {{key|x}} und Exportfeld ``ai_caption`` (ohne Wert, ohne Einheit).
|
||||
|
||||
Inhalt: business_meaning oder gekürzter semantic_contract; bei SCORE-Zeilen die 0–100-Skala.
|
||||
Nicht enthalten: description (die nur bei {{key|d}} angehängt wird) und keine „Technischer Bezug: …“-Zeile.
|
||||
"""
|
||||
desc = (metadata.description or "").strip()
|
||||
bm = (metadata.business_meaning or "").strip()
|
||||
sc = (metadata.semantic_contract or "").strip()
|
||||
|
||||
chunks: List[str] = []
|
||||
|
||||
interpret = bm
|
||||
if not interpret and sc:
|
||||
interpret = sc if len(sc) <= max_len else sc[: max_len - 1] + "…"
|
||||
|
||||
if interpret:
|
||||
il = interpret.lower()
|
||||
redundant = bool(
|
||||
desc
|
||||
and len(desc) >= 10
|
||||
and desc.lower() in il
|
||||
)
|
||||
if not redundant:
|
||||
chunks.append(interpret)
|
||||
|
||||
if metadata.placeholder_type == PlaceholderType.SCORE:
|
||||
chunks.append("Skala 0–100: höher = im Modell günstiger / besser abgestimmt.")
|
||||
|
||||
out = " ".join(c for c in chunks if c).strip()
|
||||
if len(out) > max_len + 120:
|
||||
out = out[: max_len + 60] + "…"
|
||||
return out
|
||||
|
||||
|
||||
# Global registry instance
|
||||
_global_registry = PlaceholderRegistry()
|
||||
|
||||
|
||||
+667
-198
File diff suppressed because it is too large.
Load diff
+78
-44
@@ -12,14 +12,17 @@ import re
|
||||
from typing import Dict, Any, Optional
|
||||
from db import get_db, get_cursor, r2d
|
||||
from fastapi import HTTPException
|
||||
from placeholder_resolver import get_catalog_row_for_key
|
||||
|
||||
|
||||
def resolve_placeholders(template: str, variables: Dict[str, Any], debug_info: Optional[Dict] = None, catalog: Optional[Dict] = None) -> str:
|
||||
"""
|
||||
Replace {{placeholder}} with values from variables dict.
|
||||
|
||||
Supports modifiers:
|
||||
- {{key|d}} - Include description in parentheses (requires catalog)
|
||||
Modifiers (Katalog aus get_placeholder_catalog empfohlen):
|
||||
- {{key|d}} — Wert — description (kurz)
|
||||
- {{key|x}} — nur Erklärung (Katalogfeld ai_caption), ohne Zahlenwert
|
||||
- {{key|d,x}} — Wert — description — Erklärung
|
||||
|
||||
Args:
|
||||
template: String with {{key}} or {{key|modifiers}} placeholders
|
||||
@@ -40,46 +43,66 @@ def resolve_placeholders(template: str, variables: Dict[str, Any], debug_info: O
|
||||
parts = full_placeholder.split('|')
|
||||
key = parts[0].strip()
|
||||
modifiers = parts[1].strip() if len(parts) > 1 else ''
|
||||
mods = {x.strip().lower() for x in modifiers.split(",") if x.strip()}
|
||||
want_d = "d" in mods
|
||||
want_x = "x" in mods
|
||||
|
||||
if key in variables:
|
||||
value = variables[key]
|
||||
# Convert dict/list to JSON string
|
||||
if isinstance(value, (dict, list)):
|
||||
resolved_value = json.dumps(value, ensure_ascii=False)
|
||||
else:
|
||||
resolved_value = str(value)
|
||||
|
||||
# Apply modifiers
|
||||
if 'd' in modifiers:
|
||||
if catalog:
|
||||
# Add description from catalog
|
||||
description = None
|
||||
for cat_items in catalog.values():
|
||||
matching = [item for item in cat_items if item['key'] == key]
|
||||
if matching:
|
||||
description = matching[0].get('description', '')
|
||||
break
|
||||
|
||||
if description:
|
||||
resolved_value = f"{resolved_value} ({description})"
|
||||
else:
|
||||
# Catalog not available - log warning in debug
|
||||
if debug_info is not None:
|
||||
if 'warnings' not in debug_info:
|
||||
debug_info['warnings'] = []
|
||||
debug_info['warnings'].append(f"Modifier |d used but catalog not available for {key}")
|
||||
|
||||
# Track resolution for debug
|
||||
def _warn(msg: str):
|
||||
if debug_info is not None:
|
||||
resolved[key] = resolved_value[:100] + ('...' if len(resolved_value) > 100 else '')
|
||||
debug_info.setdefault("warnings", []).append(msg)
|
||||
|
||||
return resolved_value
|
||||
else:
|
||||
# Keep placeholder if no value found
|
||||
row = get_catalog_row_for_key(catalog, key) if catalog else None
|
||||
|
||||
if want_x and not want_d:
|
||||
if key not in variables:
|
||||
if debug_info is not None:
|
||||
unresolved.append(key)
|
||||
return match.group(0)
|
||||
expl = (row.get("ai_caption") or "").strip() if row else ""
|
||||
if not expl and catalog is None:
|
||||
_warn(f"Modifier |x für {key}: Katalog fehlt (ai_caption).")
|
||||
out = expl
|
||||
if debug_info is not None:
|
||||
resolved[key] = out[:100] + ("..." if len(out) > 100 else "")
|
||||
return out
|
||||
|
||||
if key not in variables:
|
||||
if debug_info is not None:
|
||||
unresolved.append(key)
|
||||
return match.group(0)
|
||||
|
||||
value = variables[key]
|
||||
if isinstance(value, (dict, list)):
|
||||
resolved_value = json.dumps(value, ensure_ascii=False)
|
||||
else:
|
||||
resolved_value = str(value)
|
||||
|
||||
if not want_d and not want_x:
|
||||
out = resolved_value
|
||||
if debug_info is not None:
|
||||
resolved[key] = out[:100] + ("..." if len(out) > 100 else "")
|
||||
return out
|
||||
|
||||
parts = [resolved_value]
|
||||
if want_d:
|
||||
if row:
|
||||
desc = (row.get("description") or "").strip()
|
||||
if desc:
|
||||
parts.append(desc)
|
||||
else:
|
||||
_warn(f"Modifier |d für {key}: Katalog fehlt (description).")
|
||||
if want_x:
|
||||
expl = (row.get("ai_caption") or "").strip() if row else ""
|
||||
if expl:
|
||||
parts.append(expl)
|
||||
elif catalog is not None:
|
||||
_warn(f"Modifier |x (mit |d) für {key}: ai_caption leer.")
|
||||
|
||||
out = " — ".join(parts)
|
||||
if debug_info is not None:
|
||||
resolved[key] = out[:100] + ("..." if len(out) > 100 else "")
|
||||
return out
|
||||
|
||||
result = re.sub(r'\{\{([^}]+)\}\}', replacer, template)
|
||||
|
||||
# Store debug info
|
||||
@@ -144,7 +167,8 @@ async def execute_prompt(
|
||||
prompt_slug: str,
|
||||
variables: Dict[str, Any],
|
||||
openrouter_call_func,
|
||||
enable_debug: bool = False
|
||||
enable_debug: bool = False,
|
||||
progress_callback = None # NEW: Optional callback für SSE Progress-Updates
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Execute a single prompt (base or pipeline type).
|
||||
@@ -194,7 +218,7 @@ async def execute_prompt(
|
||||
|
||||
elif prompt_type == 'workflow':
|
||||
# Workflow prompt: graph-based execution (Phase 0: Foundation)
|
||||
return await execute_workflow_prompt(prompt, variables, openrouter_call_func, enable_debug, catalog)
|
||||
return await execute_workflow_prompt(prompt, variables, openrouter_call_func, enable_debug, catalog, progress_callback)
|
||||
|
||||
else:
|
||||
raise HTTPException(400, f"Unknown prompt type: {prompt_type}")
|
||||
@@ -255,7 +279,11 @@ async def execute_base_prompt(
|
||||
|
||||
if enable_debug:
|
||||
debug_info['template'] = template
|
||||
debug_info['final_prompt'] = prompt_text[:500] + ('...' if len(prompt_text) > 500 else '')
|
||||
# Volltext für Test-UI (Admin); sehr große Prompts nur weich begrenzen
|
||||
_max = 512 * 1024
|
||||
debug_info['final_prompt'] = (
|
||||
prompt_text if len(prompt_text) <= _max else prompt_text[:_max] + "\n… [gekürzt, >512KB]"
|
||||
)
|
||||
debug_info['available_variables'] = list(variables.keys())
|
||||
|
||||
# Call AI
|
||||
@@ -374,7 +402,10 @@ async def execute_pipeline_prompt(
|
||||
if enable_debug:
|
||||
prompt_debug['source'] = 'inline'
|
||||
prompt_debug['template'] = template
|
||||
prompt_debug['final_prompt'] = prompt_text[:500] + ('...' if len(prompt_text) > 500 else '')
|
||||
_max = 512 * 1024
|
||||
prompt_debug['final_prompt'] = (
|
||||
prompt_text if len(prompt_text) <= _max else prompt_text[:_max] + "\n… [gekürzt, >512KB]"
|
||||
)
|
||||
prompt_debug.update(placeholder_debug)
|
||||
|
||||
response = await openrouter_call_func(prompt_text)
|
||||
@@ -439,7 +470,8 @@ async def execute_prompt_with_data(
|
||||
modules: Optional[Dict[str, bool]] = None,
|
||||
timeframes: Optional[Dict[str, int]] = None,
|
||||
openrouter_call_func = None,
|
||||
enable_debug: bool = False
|
||||
enable_debug: bool = False,
|
||||
progress_callback = None # NEW: Optional callback für SSE Progress-Updates
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Execute prompt with data loaded from database.
|
||||
@@ -464,7 +496,7 @@ async def execute_prompt_with_data(
|
||||
'today': datetime.now().strftime('%Y-%m-%d')
|
||||
}
|
||||
|
||||
# Load placeholder catalog for |d modifier support
|
||||
# Load placeholder catalog for |d / |x Modifier
|
||||
try:
|
||||
catalog = get_placeholder_catalog(profile_id)
|
||||
except Exception as e:
|
||||
@@ -575,7 +607,7 @@ async def execute_prompt_with_data(
|
||||
variables['goals_data'] = []
|
||||
|
||||
# Execute prompt
|
||||
return await execute_prompt(prompt_slug, variables, openrouter_call_func, enable_debug)
|
||||
return await execute_prompt(prompt_slug, variables, openrouter_call_func, enable_debug, progress_callback)
|
||||
|
||||
|
||||
async def execute_workflow_prompt(
|
||||
@@ -583,7 +615,8 @@ async def execute_workflow_prompt(
|
||||
variables: Dict[str, Any],
|
||||
openrouter_call_func,
|
||||
enable_debug: bool = False,
|
||||
catalog: Optional[Dict] = None
|
||||
catalog: Optional[Dict] = None,
|
||||
progress_callback = None # NEW: Optional callback für SSE Progress-Updates
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Execute a workflow-type prompt (graph-based execution).
|
||||
@@ -622,7 +655,8 @@ async def execute_workflow_prompt(
|
||||
profile_id=variables.get('profile_id', 'unknown'), # From context
|
||||
variables=variables,
|
||||
openrouter_call_func=openrouter_call_func,
|
||||
enable_debug=enable_debug
|
||||
enable_debug=enable_debug,
|
||||
progress_callback=progress_callback # NEW: Progress-Callbacks durchreichen
|
||||
)
|
||||
|
||||
# Convert ExecutionResult to dict for API response
|
||||
|
||||
@@ -0,0 +1,9 @@
|
||||
[pytest]
|
||||
testpaths = tests
|
||||
python_files = test_*.py
|
||||
python_functions = test_*
|
||||
addopts = -q --tb=short
|
||||
markers =
|
||||
smoke: Fast smoke tests for core regression checks.
|
||||
integration: Integration tests across modules/db/api behavior.
|
||||
slow: Long-running or heavy tests.
|
||||
@@ -0,0 +1,6 @@
|
||||
# Entwicklung / CI: nach requirements.txt installieren
|
||||
# pip install -r requirements.txt -r requirements-dev.txt
|
||||
#
|
||||
# Empfohlene Smoke-Suite (CSV-Import + Parser, ohne DB/Workflow-Integration):
|
||||
# python -m pytest tests/test_csv_parser_core.py tests/test_csv_import_executor.py tests/test_mapping_suggest.py
|
||||
pytest>=8.0
|
||||
@@ -158,7 +158,8 @@ def parse_decision_questions(section_text: str) -> Dict[str, str]:
|
||||
for pattern in patterns:
|
||||
matches = re.finditer(pattern, section_text, re.MULTILINE | re.IGNORECASE)
|
||||
for match in matches:
|
||||
question_type = match.group(1).strip().lower()
|
||||
# Preserve original case for question IDs (e.g., "qAnalyst" not "qanalyst")
|
||||
question_type = match.group(1).strip()
|
||||
answer = match.group(2).strip()
|
||||
|
||||
# Entferne Klammern und Whitespace
|
||||
|
||||
+485
-234
@@ -7,16 +7,76 @@ import csv
|
||||
import io
|
||||
import uuid
|
||||
import logging
|
||||
import re
|
||||
import calendar
|
||||
from datetime import date
|
||||
from typing import Optional
|
||||
|
||||
from fastapi import APIRouter, HTTPException, UploadFile, File, Header, Depends, Query
|
||||
|
||||
from db import get_db, get_cursor, r2d
|
||||
from auth import require_auth, check_feature_access, increment_feature_usage
|
||||
from models import ActivityEntry
|
||||
from models import ActivityEntry, ActivityMetricsReplace
|
||||
from routers.profiles import get_pid
|
||||
from feature_logger import log_feature_usage
|
||||
from quality_filter import get_quality_filter_sql
|
||||
from data_layer.activity_persistence_orchestrator import (
|
||||
get_mappable_activity_field_catalog,
|
||||
insert_activity_from_entry,
|
||||
run_activity_post_write_hooks,
|
||||
update_activity_from_entry,
|
||||
find_activity_duplicate_id,
|
||||
update_activity_columns,
|
||||
insert_activity_csv_minimal,
|
||||
run_activity_post_write_hooks_import,
|
||||
new_activity_id,
|
||||
)
|
||||
from data_layer.activity_time_normalize import normalize_activity_start
|
||||
from data_layer.activity_session_metrics import enrich_sessions_with_metrics
|
||||
|
||||
router = APIRouter(prefix="/api/activity", tags=["activity"])
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_MONTH_RE = re.compile(r"^(\d{4})-(\d{2})$")
|
||||
|
||||
|
||||
def _month_date_bounds(ym: str) -> tuple[date, date]:
|
||||
m = _MONTH_RE.match((ym or "").strip())
|
||||
if not m:
|
||||
raise HTTPException(status_code=400, detail="month muss YYYY-MM sein")
|
||||
y, mo = int(m.group(1)), int(m.group(2))
|
||||
if mo < 1 or mo > 12:
|
||||
raise HTTPException(status_code=400, detail="Ungültiger Monat")
|
||||
last = calendar.monthrange(y, mo)[1]
|
||||
return date(y, mo, 1), date(y, mo, last)
|
||||
|
||||
|
||||
_ACTIVITY_DEDUP_WINDOW = """
|
||||
PARTITION BY al.profile_id, al.date,
|
||||
COALESCE(al.activity_type, ''),
|
||||
COALESCE(al.start_time::text, ''),
|
||||
COALESCE(ROUND(al.duration_min::numeric, 1), '-999999'::numeric),
|
||||
COALESCE(ROUND(al.kcal_active::numeric, 1), '-999999'::numeric)
|
||||
ORDER BY al.created DESC NULLS LAST, al.id DESC
|
||||
"""
|
||||
|
||||
|
||||
def _activity_rows_after_list_query(cur):
|
||||
rows = []
|
||||
for r in cur.fetchall():
|
||||
d = r2d(r)
|
||||
if not d:
|
||||
continue
|
||||
d.pop("_dup_rn", None)
|
||||
rows.append(d)
|
||||
return rows
|
||||
|
||||
|
||||
def _return_activity_list_rows(cur, rows: list) -> list:
|
||||
"""Layer-1: gemergte session_metrics wie Detail-Pfad (Batch)."""
|
||||
enrich_sessions_with_metrics(cur, rows)
|
||||
return rows
|
||||
|
||||
|
||||
# Evaluation import with error handling (Phase 1.2)
|
||||
try:
|
||||
@@ -27,51 +87,143 @@ except Exception as e:
|
||||
EVALUATION_AVAILABLE = False
|
||||
evaluate_and_save_activity = None
|
||||
|
||||
router = APIRouter(prefix="/api/activity", tags=["activity"])
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@router.get("")
|
||||
def list_activity(
|
||||
limit: int = Query(200, ge=1, le=50_000),
|
||||
offset: int = Query(0, ge=0, le=100_000, description="SQL OFFSET für Pagination"),
|
||||
days: Optional[int] = Query(None, ge=1, le=4000, description="Nur Einträge mit date >= HEUTE − days (Kalendertage)"),
|
||||
x_profile_id: Optional[str] = Header(default=None),
|
||||
month: Optional[str] = Query(
|
||||
None,
|
||||
description='Kalendermonat "YYYY-MM" (ganzer Monat; schließt days und offset aus)',
|
||||
),
|
||||
skip_quality_filter: bool = Query(
|
||||
False,
|
||||
description="True = alle Einträge des Profils (ohne quality_label-Filter). Für /activity Erfassung.",
|
||||
),
|
||||
collapse_duplicate_sessions: bool = Query(
|
||||
False,
|
||||
description="True = Sessions mit gleichem Datum/Typ/Startzeit/Dauer/Kcal falten (neueste Zeile behalten).",
|
||||
),
|
||||
session: dict = Depends(require_auth),
|
||||
):
|
||||
"""Get activity entries for current profile. Optional *days* filter by calendar window (not the same as *limit*)."""
|
||||
pid = get_pid(x_profile_id)
|
||||
# Immer das Profil der gültigen Session (X-Profile-Id wird hier nicht verwendet).
|
||||
pid = str(session["profile_id"])
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
|
||||
# Issue #31: Apply global quality filter (profile from DB = saved level)
|
||||
cur.execute("SELECT * FROM profiles WHERE id=%s", (pid,))
|
||||
profile = r2d(cur.fetchone())
|
||||
quality_filter = get_quality_filter_sql(profile)
|
||||
# Issue #31: Qualitätsfilter — auf der Erfassungsseite /activity abschaltbar (skip_quality_filter)
|
||||
if skip_quality_filter:
|
||||
quality_filter = ""
|
||||
quality_filter_al = ""
|
||||
else:
|
||||
cur.execute("SELECT * FROM profiles WHERE id=%s", (pid,))
|
||||
profile = r2d(cur.fetchone())
|
||||
quality_filter = get_quality_filter_sql(profile or {}, "")
|
||||
quality_filter_al = get_quality_filter_sql(profile or {}, "al.")
|
||||
|
||||
if month:
|
||||
if days is not None:
|
||||
raise HTTPException(status_code=400, detail="month und days schließen sich aus")
|
||||
if offset != 0:
|
||||
raise HTTPException(status_code=400, detail="month und offset schließen sich aus")
|
||||
d0, d1 = _month_date_bounds(month)
|
||||
if collapse_duplicate_sessions:
|
||||
cur.execute(
|
||||
f"""
|
||||
SELECT d.* FROM (
|
||||
SELECT al.*, ROW_NUMBER() OVER (
|
||||
{_ACTIVITY_DEDUP_WINDOW}
|
||||
) AS _dup_rn
|
||||
FROM activity_log al
|
||||
WHERE al.profile_id = %s
|
||||
{quality_filter_al}
|
||||
AND al.date >= %s AND al.date <= %s
|
||||
) d
|
||||
WHERE d._dup_rn = 1
|
||||
ORDER BY d.date DESC, d.start_time DESC NULLS LAST, d.id DESC
|
||||
LIMIT %s
|
||||
""",
|
||||
(pid, d0, d1, limit),
|
||||
)
|
||||
return _return_activity_list_rows(cur, _activity_rows_after_list_query(cur))
|
||||
cur.execute(
|
||||
f"""
|
||||
SELECT * FROM activity_log
|
||||
WHERE profile_id=%s
|
||||
{quality_filter}
|
||||
AND date >= %s AND date <= %s
|
||||
ORDER BY date DESC, start_time DESC NULLS LAST, id DESC
|
||||
LIMIT %s
|
||||
""",
|
||||
(pid, d0, d1, limit),
|
||||
)
|
||||
return _return_activity_list_rows(
|
||||
cur, [r2d(r) for r in cur.fetchall()]
|
||||
)
|
||||
|
||||
if days is not None:
|
||||
if collapse_duplicate_sessions:
|
||||
cur.execute(
|
||||
f"""
|
||||
SELECT d.* FROM (
|
||||
SELECT al.*, ROW_NUMBER() OVER (
|
||||
{_ACTIVITY_DEDUP_WINDOW}
|
||||
) AS _dup_rn
|
||||
FROM activity_log al
|
||||
WHERE al.profile_id = %s
|
||||
{quality_filter_al}
|
||||
AND al.date >= (CURRENT_DATE - %s::integer)
|
||||
) d
|
||||
WHERE d._dup_rn = 1
|
||||
ORDER BY d.date DESC, d.start_time DESC NULLS LAST, d.id DESC
|
||||
LIMIT %s OFFSET %s
|
||||
""",
|
||||
(pid, days, limit, offset),
|
||||
)
|
||||
return _return_activity_list_rows(cur, _activity_rows_after_list_query(cur))
|
||||
cur.execute(
|
||||
f"""
|
||||
SELECT * FROM activity_log
|
||||
WHERE profile_id=%s
|
||||
{quality_filter}
|
||||
AND date >= (CURRENT_DATE - %s::integer)
|
||||
ORDER BY date DESC, start_time DESC
|
||||
LIMIT %s
|
||||
ORDER BY date DESC, start_time DESC NULLS LAST, id DESC
|
||||
LIMIT %s OFFSET %s
|
||||
""",
|
||||
(pid, days, limit),
|
||||
(pid, days, limit, offset),
|
||||
)
|
||||
else:
|
||||
if collapse_duplicate_sessions:
|
||||
cur.execute(
|
||||
f"""
|
||||
SELECT d.* FROM (
|
||||
SELECT al.*, ROW_NUMBER() OVER (
|
||||
{_ACTIVITY_DEDUP_WINDOW}
|
||||
) AS _dup_rn
|
||||
FROM activity_log al
|
||||
WHERE al.profile_id = %s
|
||||
{quality_filter_al}
|
||||
) d
|
||||
WHERE d._dup_rn = 1
|
||||
ORDER BY d.date DESC, d.start_time DESC NULLS LAST, d.id DESC
|
||||
LIMIT %s OFFSET %s
|
||||
""",
|
||||
(pid, limit, offset),
|
||||
)
|
||||
return _return_activity_list_rows(cur, _activity_rows_after_list_query(cur))
|
||||
cur.execute(
|
||||
f"""
|
||||
SELECT * FROM activity_log
|
||||
WHERE profile_id=%s
|
||||
{quality_filter}
|
||||
ORDER BY date DESC, start_time DESC
|
||||
LIMIT %s
|
||||
ORDER BY date DESC, start_time DESC NULLS LAST, id DESC
|
||||
LIMIT %s OFFSET %s
|
||||
""",
|
||||
(pid, limit),
|
||||
(pid, limit, offset),
|
||||
)
|
||||
return [r2d(r) for r in cur.fetchall()]
|
||||
return _return_activity_list_rows(cur, [r2d(r) for r in cur.fetchall()])
|
||||
|
||||
|
||||
@router.post("")
|
||||
@@ -95,37 +247,10 @@ def create_activity(e: ActivityEntry, x_profile_id: Optional[str]=Header(default
|
||||
)
|
||||
|
||||
eid = str(uuid.uuid4())
|
||||
d = e.model_dump()
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute("""INSERT INTO activity_log
|
||||
(id,profile_id,date,start_time,end_time,activity_type,duration_min,kcal_active,kcal_resting,
|
||||
hr_avg,hr_max,distance_km,rpe,source,notes,created)
|
||||
VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,CURRENT_TIMESTAMP)""",
|
||||
(eid,pid,d['date'],d['start_time'],d['end_time'],d['activity_type'],d['duration_min'],
|
||||
d['kcal_active'],d['kcal_resting'],d['hr_avg'],d['hr_max'],d['distance_km'],
|
||||
d['rpe'],d['source'],d['notes']))
|
||||
|
||||
# Phase 1.2: Auto-evaluation after INSERT
|
||||
if EVALUATION_AVAILABLE:
|
||||
# Load the activity data to evaluate
|
||||
cur.execute("""
|
||||
SELECT id, profile_id, date, training_type_id, duration_min,
|
||||
hr_avg, hr_max, distance_km, kcal_active, kcal_resting,
|
||||
rpe, pace_min_per_km, cadence, elevation_gain
|
||||
FROM activity_log
|
||||
WHERE id = %s
|
||||
""", (eid,))
|
||||
activity_row = cur.fetchone()
|
||||
if activity_row:
|
||||
activity_dict = dict(activity_row)
|
||||
training_type_id = activity_dict.get("training_type_id")
|
||||
if training_type_id:
|
||||
try:
|
||||
evaluate_and_save_activity(cur, eid, activity_dict, training_type_id, pid)
|
||||
logger.info(f"[AUTO-EVAL] Evaluated activity {eid} on INSERT")
|
||||
except Exception as eval_error:
|
||||
logger.error(f"[AUTO-EVAL] Failed to evaluate activity {eid}: {eval_error}")
|
||||
insert_activity_from_entry(cur, pid, eid, e)
|
||||
run_activity_post_write_hooks(cur, pid, eid)
|
||||
|
||||
# Phase 2: Increment usage counter (always for new entries)
|
||||
increment_feature_usage(pid, 'activity_entries')
|
||||
@@ -133,36 +258,146 @@ def create_activity(e: ActivityEntry, x_profile_id: Optional[str]=Header(default
|
||||
return {"id":eid,"date":e.date}
|
||||
|
||||
|
||||
@router.get("/stats")
|
||||
def activity_stats(
|
||||
skip_quality_filter: bool = Query(
|
||||
False,
|
||||
description="True = Statistik-Kacheln ohne Profil-Qualitätsfilter (passend zur /activity-Liste).",
|
||||
),
|
||||
session: dict = Depends(require_auth),
|
||||
):
|
||||
"""Get activity statistics (last 30 entries)."""
|
||||
pid = str(session["profile_id"])
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
if skip_quality_filter:
|
||||
quality_filter = ""
|
||||
else:
|
||||
cur.execute("SELECT * FROM profiles WHERE id=%s", (pid,))
|
||||
profile = r2d(cur.fetchone())
|
||||
quality_filter = get_quality_filter_sql(profile or {}, "")
|
||||
cur.execute(
|
||||
f"SELECT COUNT(*)::bigint AS c FROM activity_log WHERE profile_id=%s {quality_filter}",
|
||||
(pid,),
|
||||
)
|
||||
total_in_profile = int(cur.fetchone()["c"])
|
||||
if skip_quality_filter:
|
||||
cur.execute(
|
||||
f"""
|
||||
SELECT d.* FROM (
|
||||
SELECT al.*, ROW_NUMBER() OVER (
|
||||
{_ACTIVITY_DEDUP_WINDOW}
|
||||
) AS _dup_rn
|
||||
FROM activity_log al
|
||||
WHERE al.profile_id = %s
|
||||
) d
|
||||
WHERE d._dup_rn = 1
|
||||
ORDER BY d.date DESC, d.start_time DESC NULLS LAST, d.id DESC
|
||||
LIMIT 30
|
||||
""",
|
||||
(pid,),
|
||||
)
|
||||
rows = _activity_rows_after_list_query(cur)
|
||||
else:
|
||||
cur.execute(
|
||||
f"""
|
||||
SELECT * FROM activity_log
|
||||
WHERE profile_id=%s {quality_filter}
|
||||
ORDER BY date DESC, start_time DESC NULLS LAST, id DESC
|
||||
LIMIT 30
|
||||
""",
|
||||
(pid,),
|
||||
)
|
||||
rows = [r2d(r) for r in cur.fetchall()]
|
||||
if not rows:
|
||||
return {
|
||||
"count": 0,
|
||||
"sample_size": 0,
|
||||
"total_in_profile": total_in_profile,
|
||||
"total_kcal": 0,
|
||||
"total_min": 0,
|
||||
"by_type": {},
|
||||
}
|
||||
total_kcal = sum(float(r.get("kcal_active") or 0) for r in rows)
|
||||
total_min = sum(float(r.get("duration_min") or 0) for r in rows)
|
||||
by_type = {}
|
||||
for r in rows:
|
||||
t = r["activity_type"]
|
||||
by_type.setdefault(t, {"count": 0, "kcal": 0, "min": 0})
|
||||
by_type[t]["count"] += 1
|
||||
by_type[t]["kcal"] += float(r.get("kcal_active") or 0)
|
||||
by_type[t]["min"] += float(r.get("duration_min") or 0)
|
||||
return {
|
||||
"count": len(rows),
|
||||
"sample_size": len(rows),
|
||||
"total_in_profile": total_in_profile,
|
||||
"total_kcal": round(total_kcal),
|
||||
"total_min": round(total_min),
|
||||
"by_type": by_type,
|
||||
}
|
||||
|
||||
|
||||
@router.get("/uncategorized")
|
||||
def list_uncategorized_activities(
|
||||
session: dict = Depends(require_auth),
|
||||
):
|
||||
"""Get activities without assigned training type, grouped by activity_type."""
|
||||
pid = str(session["profile_id"])
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT activity_type, COUNT(*) as count,
|
||||
MIN(date) as first_date, MAX(date) as last_date
|
||||
FROM activity_log
|
||||
WHERE profile_id=%s AND training_type_id IS NULL
|
||||
GROUP BY activity_type
|
||||
ORDER BY count DESC
|
||||
""",
|
||||
(pid,),
|
||||
)
|
||||
return [r2d(r) for r in cur.fetchall()]
|
||||
|
||||
|
||||
@router.get("/mappable-fields")
|
||||
def get_activity_mappable_fields(session: dict = Depends(require_auth)):
|
||||
"""
|
||||
Vollständiger Katalog für Import-Mappings (activity_log-Kernfelder + alle aktiven training_parameters).
|
||||
Werte für Keys ohne Schema zur konkreten Session werden beim Import ignoriert.
|
||||
"""
|
||||
pid = str(session["profile_id"])
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
return get_mappable_activity_field_catalog(cur, pid)
|
||||
|
||||
|
||||
@router.get("/attribute-schema")
|
||||
def get_activity_attribute_schema(
|
||||
training_category: Optional[str] = Query(None),
|
||||
training_type_id: Optional[int] = Query(None),
|
||||
session: dict = Depends(require_auth),
|
||||
):
|
||||
"""
|
||||
Aufgelöstes Attributprofil (tcp/ttp) für Erfassung ohne bestehende Session —
|
||||
gleiche Logik wie resolve_activity_attribute_schema.
|
||||
"""
|
||||
from data_layer.activity_session_metrics import resolve_activity_attribute_schema
|
||||
|
||||
cat = (training_category or "").strip() or None
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
schema = resolve_activity_attribute_schema(cur, cat, training_type_id)
|
||||
return {"schema": schema}
|
||||
|
||||
|
||||
@router.put("/{eid}")
|
||||
def update_activity(eid: str, e: ActivityEntry, x_profile_id: Optional[str]=Header(default=None), session: dict=Depends(require_auth)):
|
||||
"""Update existing activity entry."""
|
||||
pid = get_pid(x_profile_id)
|
||||
with get_db() as conn:
|
||||
d = e.model_dump()
|
||||
cur = get_cursor(conn)
|
||||
cur.execute(f"UPDATE activity_log SET {', '.join(f'{k}=%s' for k in d)} WHERE id=%s AND profile_id=%s",
|
||||
list(d.values())+[eid,pid])
|
||||
|
||||
# Phase 1.2: Auto-evaluation after UPDATE
|
||||
if EVALUATION_AVAILABLE:
|
||||
# Load the updated activity data to evaluate
|
||||
cur.execute("""
|
||||
SELECT id, profile_id, date, training_type_id, duration_min,
|
||||
hr_avg, hr_max, distance_km, kcal_active, kcal_resting,
|
||||
rpe, pace_min_per_km, cadence, elevation_gain
|
||||
FROM activity_log
|
||||
WHERE id = %s
|
||||
""", (eid,))
|
||||
activity_row = cur.fetchone()
|
||||
if activity_row:
|
||||
activity_dict = dict(activity_row)
|
||||
training_type_id = activity_dict.get("training_type_id")
|
||||
if training_type_id:
|
||||
try:
|
||||
evaluate_and_save_activity(cur, eid, activity_dict, training_type_id, pid)
|
||||
logger.info(f"[AUTO-EVAL] Re-evaluated activity {eid} on UPDATE")
|
||||
except Exception as eval_error:
|
||||
logger.error(f"[AUTO-EVAL] Failed to re-evaluate activity {eid}: {eval_error}")
|
||||
update_activity_from_entry(cur, pid, eid, e)
|
||||
run_activity_post_write_hooks(cur, pid, eid)
|
||||
|
||||
return {"id":eid}
|
||||
|
||||
@@ -177,25 +412,103 @@ def delete_activity(eid: str, x_profile_id: Optional[str]=Header(default=None),
|
||||
return {"ok":True}
|
||||
|
||||
|
||||
@router.get("/stats")
|
||||
def activity_stats(x_profile_id: Optional[str]=Header(default=None), session: dict=Depends(require_auth)):
|
||||
"""Get activity statistics (last 30 entries)."""
|
||||
pid = get_pid(x_profile_id)
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
@router.put("/{eid}/metrics")
|
||||
def replace_activity_metrics(
|
||||
eid: str,
|
||||
body: ActivityMetricsReplace,
|
||||
session: dict = Depends(require_auth),
|
||||
):
|
||||
"""
|
||||
Voller Ersatz der EAV-Session-Metriken (siehe ACTIVITY_SESSION_METRICS_EAV_AGENT_GUIDE.md).
|
||||
"""
|
||||
from data_layer.activity_session_metrics import (
|
||||
ActivitySessionMetricsError,
|
||||
replace_activity_session_metrics,
|
||||
)
|
||||
|
||||
pid = str(session["profile_id"])
|
||||
payload = [m.model_dump() for m in body.metrics]
|
||||
try:
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
metrics = replace_activity_session_metrics(cur, pid, eid, payload)
|
||||
conn.commit()
|
||||
except ActivitySessionMetricsError as err:
|
||||
raise HTTPException(err.status_code, err.detail) from err
|
||||
return {"id": eid, "metrics": metrics}
|
||||
|
||||
|
||||
@router.get("/{eid}")
|
||||
def get_activity_session(
|
||||
eid: str,
|
||||
use_form_schema: bool = Query(
|
||||
False,
|
||||
description="True: Schema aus Query training_category / training_type_id (Formular), nicht nur DB-Zeile",
|
||||
),
|
||||
training_category: Optional[str] = Query(None),
|
||||
training_type_id: Optional[int] = Query(None),
|
||||
session: dict = Depends(require_auth),
|
||||
):
|
||||
"""Session-Kopf + aufgelöstes Schema + EAV-Metriken (Layer 1)."""
|
||||
from data_layer.activity_session_metrics import (
|
||||
ActivitySessionMetricsError,
|
||||
get_activity_session_logical_unit,
|
||||
)
|
||||
from data_layer.utils import serialize_dates
|
||||
|
||||
pid = str(session["profile_id"])
|
||||
try:
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
unit = get_activity_session_logical_unit(
|
||||
cur,
|
||||
pid,
|
||||
eid,
|
||||
use_form_training_context=use_form_schema,
|
||||
form_training_category=training_category,
|
||||
form_training_type_id=training_type_id,
|
||||
)
|
||||
except ActivitySessionMetricsError as err:
|
||||
raise HTTPException(err.status_code, err.detail) from err
|
||||
unit["header"] = serialize_dates(unit["header"])
|
||||
return unit
|
||||
|
||||
|
||||
def get_training_type_for_activity_with_cursor(cur, activity_type: str, profile_id: str | None = None):
|
||||
"""
|
||||
Wie get_training_type_for_activity, aber mit bestehendem Cursor (z. B. Universal-CSV-Import).
|
||||
Vermeidet verschachteltes get_db() — bei maxconn=1 sonst Deadlock auf dem Connection-Pool.
|
||||
"""
|
||||
if profile_id:
|
||||
cur.execute(
|
||||
"SELECT * FROM activity_log WHERE profile_id=%s ORDER BY date DESC LIMIT 30", (pid,))
|
||||
rows = [r2d(r) for r in cur.fetchall()]
|
||||
if not rows: return {"count":0,"total_kcal":0,"total_min":0,"by_type":{}}
|
||||
total_kcal=sum(float(r.get('kcal_active') or 0) for r in rows)
|
||||
total_min=sum(float(r.get('duration_min') or 0) for r in rows)
|
||||
by_type={}
|
||||
for r in rows:
|
||||
t=r['activity_type']; by_type.setdefault(t,{'count':0,'kcal':0,'min':0})
|
||||
by_type[t]['count']+=1
|
||||
by_type[t]['kcal']+=float(r.get('kcal_active') or 0)
|
||||
by_type[t]['min']+=float(r.get('duration_min') or 0)
|
||||
return {"count":len(rows),"total_kcal":round(total_kcal),"total_min":round(total_min),"by_type":by_type}
|
||||
"""
|
||||
SELECT m.training_type_id, t.category, t.subcategory
|
||||
FROM activity_type_mappings m
|
||||
JOIN training_types t ON m.training_type_id = t.id
|
||||
WHERE m.activity_type = %s AND m.profile_id = %s
|
||||
LIMIT 1
|
||||
""",
|
||||
(activity_type, profile_id),
|
||||
)
|
||||
row = cur.fetchone()
|
||||
if row:
|
||||
return (row["training_type_id"], row["category"], row["subcategory"])
|
||||
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT m.training_type_id, t.category, t.subcategory
|
||||
FROM activity_type_mappings m
|
||||
JOIN training_types t ON m.training_type_id = t.id
|
||||
WHERE m.activity_type = %s AND m.profile_id IS NULL
|
||||
LIMIT 1
|
||||
""",
|
||||
(activity_type,),
|
||||
)
|
||||
row = cur.fetchone()
|
||||
if row:
|
||||
return (row["training_type_id"], row["category"], row["subcategory"])
|
||||
|
||||
return (None, None, None)
|
||||
|
||||
|
||||
def get_training_type_for_activity(activity_type: str, profile_id: str = None):
|
||||
@@ -211,50 +524,7 @@ def get_training_type_for_activity(activity_type: str, profile_id: str = None):
|
||||
"""
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
|
||||
# Try user-specific mapping first
|
||||
if profile_id:
|
||||
cur.execute("""
|
||||
SELECT m.training_type_id, t.category, t.subcategory
|
||||
FROM activity_type_mappings m
|
||||
JOIN training_types t ON m.training_type_id = t.id
|
||||
WHERE m.activity_type = %s AND m.profile_id = %s
|
||||
LIMIT 1
|
||||
""", (activity_type, profile_id))
|
||||
row = cur.fetchone()
|
||||
if row:
|
||||
return (row['training_type_id'], row['category'], row['subcategory'])
|
||||
|
||||
# Try global mapping
|
||||
cur.execute("""
|
||||
SELECT m.training_type_id, t.category, t.subcategory
|
||||
FROM activity_type_mappings m
|
||||
JOIN training_types t ON m.training_type_id = t.id
|
||||
WHERE m.activity_type = %s AND m.profile_id IS NULL
|
||||
LIMIT 1
|
||||
""", (activity_type,))
|
||||
row = cur.fetchone()
|
||||
if row:
|
||||
return (row['training_type_id'], row['category'], row['subcategory'])
|
||||
|
||||
return (None, None, None)
|
||||
|
||||
|
||||
@router.get("/uncategorized")
|
||||
def list_uncategorized_activities(x_profile_id: Optional[str]=Header(default=None), session: dict=Depends(require_auth)):
|
||||
"""Get activities without assigned training type, grouped by activity_type."""
|
||||
pid = get_pid(x_profile_id)
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute("""
|
||||
SELECT activity_type, COUNT(*) as count,
|
||||
MIN(date) as first_date, MAX(date) as last_date
|
||||
FROM activity_log
|
||||
WHERE profile_id=%s AND training_type_id IS NULL
|
||||
GROUP BY activity_type
|
||||
ORDER BY count DESC
|
||||
""", (pid,))
|
||||
return [r2d(r) for r in cur.fetchall()]
|
||||
return get_training_type_for_activity_with_cursor(cur, activity_type, profile_id)
|
||||
|
||||
|
||||
@router.post("/bulk-categorize")
|
||||
@@ -342,7 +612,10 @@ def bulk_categorize_activities(
|
||||
|
||||
@router.post("/import-csv")
|
||||
async def import_activity_csv(file: UploadFile=File(...), x_profile_id: Optional[str]=Header(default=None), session: dict=Depends(require_auth)):
|
||||
"""Import Apple Health workout CSV with automatic training type mapping."""
|
||||
"""
|
||||
Legacy-Upload (Apple Health Workout-CSV-Spaltennamen).
|
||||
Persistenz läuft über activity_persistence_orchestrator — gleiche Schicht wie Universal-CSV.
|
||||
"""
|
||||
pid = get_pid(x_profile_id)
|
||||
raw = await file.read()
|
||||
try: text = raw.decode('utf-8')
|
||||
@@ -356,9 +629,11 @@ async def import_activity_csv(file: UploadFile=File(...), x_profile_id: Optional
|
||||
for row in reader:
|
||||
wtype = row.get('Workout Type','').strip()
|
||||
start = row.get('Start','').strip()
|
||||
if not wtype or not start: continue
|
||||
try: date = start[:10]
|
||||
except: continue
|
||||
if not wtype or not start:
|
||||
continue
|
||||
workout_date, workout_start_t = normalize_activity_start(start)
|
||||
if not workout_date:
|
||||
continue
|
||||
dur = row.get('Duration','').strip()
|
||||
duration_min = None
|
||||
if dur:
|
||||
@@ -375,106 +650,82 @@ async def import_activity_csv(file: UploadFile=File(...), x_profile_id: Optional
|
||||
# Map activity_type to training_type_id using database mappings
|
||||
training_type_id, training_category, training_subcategory = get_training_type_for_activity(wtype, pid)
|
||||
|
||||
kcal_a = kj(row.get("Aktive Energie (kJ)", ""))
|
||||
kcal_r = kj(row.get("Ruheeinträge (kJ)", ""))
|
||||
hr_av = tf(row.get("Durchschn. Herzfrequenz (count/min)", ""))
|
||||
hr_mx = tf(row.get("Max. Herzfrequenz (count/min)", ""))
|
||||
dist_km = tf(row.get("Distanz (km)", ""))
|
||||
try:
|
||||
# Check if entry already exists (duplicate detection by date + start_time)
|
||||
cur.execute("""
|
||||
SELECT id FROM activity_log
|
||||
WHERE profile_id = %s AND date = %s AND start_time = %s
|
||||
""", (pid, date, start))
|
||||
existing = cur.fetchone()
|
||||
|
||||
if existing:
|
||||
# Update existing entry (e.g., to add training type mapping)
|
||||
existing_id = existing['id']
|
||||
cur.execute("""
|
||||
UPDATE activity_log
|
||||
SET end_time = %s,
|
||||
activity_type = %s,
|
||||
duration_min = %s,
|
||||
kcal_active = %s,
|
||||
kcal_resting = %s,
|
||||
hr_avg = %s,
|
||||
hr_max = %s,
|
||||
distance_km = %s,
|
||||
training_type_id = %s,
|
||||
training_category = %s,
|
||||
training_subcategory = %s
|
||||
WHERE id = %s
|
||||
""", (
|
||||
row.get('End',''), wtype, duration_min,
|
||||
kj(row.get('Aktive Energie (kJ)','')),
|
||||
kj(row.get('Ruheeinträge (kJ)','')),
|
||||
tf(row.get('Durchschn. Herzfrequenz (count/min)','')),
|
||||
tf(row.get('Max. Herzfrequenz (count/min)','')),
|
||||
tf(row.get('Distanz (km)','')),
|
||||
training_type_id, training_category, training_subcategory,
|
||||
existing_id
|
||||
))
|
||||
skipped += 1 # Count as skipped (not newly inserted)
|
||||
|
||||
# Phase 1.2: Auto-evaluation after CSV import UPDATE
|
||||
if EVALUATION_AVAILABLE and training_type_id:
|
||||
try:
|
||||
# Build activity dict for evaluation
|
||||
activity_dict = {
|
||||
"id": existing_id,
|
||||
"profile_id": pid,
|
||||
"date": date,
|
||||
"training_type_id": training_type_id,
|
||||
"duration_min": duration_min,
|
||||
"hr_avg": tf(row.get('Durchschn. Herzfrequenz (count/min)','')),
|
||||
"hr_max": tf(row.get('Max. Herzfrequenz (count/min)','')),
|
||||
"distance_km": tf(row.get('Distanz (km)','')),
|
||||
"kcal_active": kj(row.get('Aktive Energie (kJ)','')),
|
||||
"kcal_resting": kj(row.get('Ruheeinträge (kJ)','')),
|
||||
"rpe": None,
|
||||
"pace_min_per_km": None,
|
||||
"cadence": None,
|
||||
"elevation_gain": None
|
||||
}
|
||||
evaluate_and_save_activity(cur, existing_id, activity_dict, training_type_id, pid)
|
||||
logger.debug(f"[AUTO-EVAL] Re-evaluated updated activity {existing_id}")
|
||||
except Exception as eval_error:
|
||||
logger.warning(f"[AUTO-EVAL] Failed to re-evaluate updated activity {existing_id}: {eval_error}")
|
||||
existing_id = find_activity_duplicate_id(cur, pid, workout_date, workout_start_t)
|
||||
if existing_id:
|
||||
update_activity_columns(
|
||||
cur,
|
||||
pid,
|
||||
str(existing_id),
|
||||
{
|
||||
"start_time": workout_start_t,
|
||||
"end_time": row.get("End", "") or None,
|
||||
"activity_type": wtype,
|
||||
"duration_min": duration_min,
|
||||
"kcal_active": kcal_a,
|
||||
"kcal_resting": kcal_r,
|
||||
"hr_avg": hr_av,
|
||||
"hr_max": hr_mx,
|
||||
"distance_km": dist_km,
|
||||
"training_type_id": training_type_id,
|
||||
"training_category": training_category,
|
||||
"training_subcategory": training_subcategory,
|
||||
},
|
||||
)
|
||||
skipped += 1
|
||||
run_activity_post_write_hooks_import(
|
||||
cur,
|
||||
pid,
|
||||
str(existing_id),
|
||||
workout_date=workout_date,
|
||||
training_type_id=training_type_id,
|
||||
duration_min=duration_min,
|
||||
hr_avg=hr_av,
|
||||
hr_max=hr_mx,
|
||||
distance_km=dist_km,
|
||||
kcal_active=kcal_a,
|
||||
kcal_resting=kcal_r,
|
||||
)
|
||||
else:
|
||||
# Insert new entry
|
||||
new_id = str(uuid.uuid4())
|
||||
cur.execute("""INSERT INTO activity_log
|
||||
(id,profile_id,date,start_time,end_time,activity_type,duration_min,kcal_active,kcal_resting,
|
||||
hr_avg,hr_max,distance_km,source,training_type_id,training_category,training_subcategory,created)
|
||||
VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,'apple_health',%s,%s,%s,CURRENT_TIMESTAMP)""",
|
||||
(new_id,pid,date,start,row.get('End',''),wtype,duration_min,
|
||||
kj(row.get('Aktive Energie (kJ)','')),kj(row.get('Ruheeinträge (kJ)','')),
|
||||
tf(row.get('Durchschn. Herzfrequenz (count/min)','')),
|
||||
tf(row.get('Max. Herzfrequenz (count/min)','')),
|
||||
tf(row.get('Distanz (km)','')),
|
||||
training_type_id,training_category,training_subcategory))
|
||||
inserted+=1
|
||||
|
||||
# Phase 1.2: Auto-evaluation after CSV import INSERT
|
||||
if EVALUATION_AVAILABLE and training_type_id:
|
||||
try:
|
||||
# Build activity dict for evaluation
|
||||
activity_dict = {
|
||||
"id": new_id,
|
||||
"profile_id": pid,
|
||||
"date": date,
|
||||
"training_type_id": training_type_id,
|
||||
"duration_min": duration_min,
|
||||
"hr_avg": tf(row.get('Durchschn. Herzfrequenz (count/min)','')),
|
||||
"hr_max": tf(row.get('Max. Herzfrequenz (count/min)','')),
|
||||
"distance_km": tf(row.get('Distanz (km)','')),
|
||||
"kcal_active": kj(row.get('Aktive Energie (kJ)','')),
|
||||
"kcal_resting": kj(row.get('Ruheeinträge (kJ)','')),
|
||||
"rpe": None,
|
||||
"pace_min_per_km": None,
|
||||
"cadence": None,
|
||||
"elevation_gain": None
|
||||
}
|
||||
evaluate_and_save_activity(cur, new_id, activity_dict, training_type_id, pid)
|
||||
logger.debug(f"[AUTO-EVAL] Evaluated imported activity {new_id}")
|
||||
except Exception as eval_error:
|
||||
logger.warning(f"[AUTO-EVAL] Failed to evaluate imported activity {new_id}: {eval_error}")
|
||||
new_id = new_activity_id()
|
||||
insert_activity_csv_minimal(
|
||||
cur,
|
||||
pid,
|
||||
new_id,
|
||||
date_iso=workout_date,
|
||||
start_time=workout_start_t,
|
||||
end_time=row.get("End", "") or None,
|
||||
activity_type=wtype,
|
||||
duration_min=duration_min,
|
||||
kcal_active=kcal_a,
|
||||
kcal_resting=kcal_r,
|
||||
hr_avg=hr_av,
|
||||
hr_max=hr_mx,
|
||||
distance_km=dist_km,
|
||||
training_type_id=training_type_id,
|
||||
training_category=training_category,
|
||||
training_subcategory=training_subcategory,
|
||||
source="apple_health",
|
||||
)
|
||||
inserted += 1
|
||||
run_activity_post_write_hooks_import(
|
||||
cur,
|
||||
pid,
|
||||
new_id,
|
||||
workout_date=workout_date,
|
||||
training_type_id=training_type_id,
|
||||
duration_min=duration_min,
|
||||
hr_avg=hr_av,
|
||||
hr_max=hr_mx,
|
||||
distance_km=dist_km,
|
||||
kcal_active=kcal_a,
|
||||
kcal_resting=kcal_r,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning(f"Import row failed: {e}")
|
||||
skipped+=1
|
||||
|
||||
@@ -0,0 +1,266 @@
|
||||
"""
|
||||
Admin: training_category_parameter + training_type_parameter (attribute profiles).
|
||||
|
||||
Agent guide: .claude/docs/technical/ACTIVITY_SESSION_METRICS_EAV_AGENT_GUIDE.md
|
||||
"""
|
||||
from typing import Optional
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException, Query
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from auth import require_admin
|
||||
from db import get_db, get_cursor, r2d
|
||||
|
||||
router = APIRouter(prefix="/api/admin", tags=["admin", "activity-attribute-profiles"])
|
||||
|
||||
|
||||
class CategoryParameterCreate(BaseModel):
|
||||
training_category: str = Field(..., min_length=1, max_length=50)
|
||||
training_parameter_id: int
|
||||
sort_order: int = 0
|
||||
required: bool = False
|
||||
ui_group: Optional[str] = Field(None, max_length=50)
|
||||
|
||||
|
||||
class TypeParameterCreate(BaseModel):
|
||||
training_type_id: int
|
||||
training_parameter_id: int
|
||||
sort_order: Optional[int] = None
|
||||
required: Optional[bool] = None
|
||||
ui_group: Optional[str] = Field(None, max_length=50)
|
||||
|
||||
|
||||
class CategoryParameterUpdate(BaseModel):
|
||||
sort_order: Optional[int] = None
|
||||
required: Optional[bool] = None
|
||||
ui_group: Optional[str] = Field(None, max_length=50)
|
||||
|
||||
|
||||
class TypeParameterUpdate(BaseModel):
|
||||
sort_order: Optional[int] = None
|
||||
required: Optional[bool] = None
|
||||
ui_group: Optional[str] = Field(None, max_length=50)
|
||||
|
||||
|
||||
@router.get("/training-category-parameters")
|
||||
def admin_list_category_parameters(
|
||||
category: Optional[str] = Query(None, description="Filter: training_types.category"),
|
||||
session: dict = Depends(require_admin),
|
||||
):
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
if category:
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT tcp.*, tp.key AS parameter_key, tp.name_de AS parameter_name_de
|
||||
FROM training_category_parameter tcp
|
||||
JOIN training_parameters tp ON tp.id = tcp.training_parameter_id
|
||||
WHERE tcp.training_category = %s
|
||||
ORDER BY tcp.sort_order, tp.key
|
||||
""",
|
||||
(category.strip(),),
|
||||
)
|
||||
else:
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT tcp.*, tp.key AS parameter_key, tp.name_de AS parameter_name_de
|
||||
FROM training_category_parameter tcp
|
||||
JOIN training_parameters tp ON tp.id = tcp.training_parameter_id
|
||||
ORDER BY tcp.training_category, tcp.sort_order, tp.key
|
||||
"""
|
||||
)
|
||||
return [r2d(r) for r in cur.fetchall()]
|
||||
|
||||
|
||||
@router.post("/training-category-parameters")
|
||||
def admin_add_category_parameter(
|
||||
body: CategoryParameterCreate,
|
||||
session: dict = Depends(require_admin),
|
||||
):
|
||||
cat = body.training_category.strip()
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute("SELECT id FROM training_parameters WHERE id = %s", (body.training_parameter_id,))
|
||||
if not cur.fetchone():
|
||||
raise HTTPException(404, "training_parameter_id unbekannt")
|
||||
try:
|
||||
cur.execute(
|
||||
"""
|
||||
INSERT INTO training_category_parameter (
|
||||
training_category, training_parameter_id, sort_order, required, ui_group
|
||||
) VALUES (%s,%s,%s,%s,%s)
|
||||
RETURNING id
|
||||
""",
|
||||
(cat, body.training_parameter_id, body.sort_order, body.required, body.ui_group),
|
||||
)
|
||||
new_id = cur.fetchone()["id"]
|
||||
conn.commit()
|
||||
except Exception as e:
|
||||
conn.rollback()
|
||||
if "uq_training_category_parameter" in str(e).lower() or "unique" in str(e).lower():
|
||||
raise HTTPException(409, "Zuordnung existiert bereits") from e
|
||||
raise HTTPException(400, str(e)) from e
|
||||
return {"id": new_id}
|
||||
|
||||
|
||||
@router.put("/training-category-parameters/{link_id}")
|
||||
def admin_update_category_parameter(
|
||||
link_id: int,
|
||||
body: CategoryParameterUpdate,
|
||||
session: dict = Depends(require_admin),
|
||||
):
|
||||
patch = body.model_dump(exclude_unset=True)
|
||||
if not patch:
|
||||
raise HTTPException(400, "Keine Felder zum Aktualisieren")
|
||||
cols: list[str] = []
|
||||
vals: list = []
|
||||
if "sort_order" in patch:
|
||||
cols.append("sort_order = %s")
|
||||
vals.append(patch["sort_order"])
|
||||
if "required" in patch:
|
||||
cols.append("required = %s")
|
||||
vals.append(patch["required"])
|
||||
if "ui_group" in patch:
|
||||
cols.append("ui_group = %s")
|
||||
vals.append(patch["ui_group"].strip() if patch["ui_group"] else None)
|
||||
if not cols:
|
||||
raise HTTPException(400, "Keine Felder zum Aktualisieren")
|
||||
vals.append(link_id)
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute(
|
||||
f"UPDATE training_category_parameter SET {', '.join(cols)} WHERE id = %s RETURNING id",
|
||||
vals,
|
||||
)
|
||||
if not cur.fetchone():
|
||||
raise HTTPException(404, "Eintrag nicht gefunden")
|
||||
conn.commit()
|
||||
return {"ok": True, "id": link_id}
|
||||
|
||||
|
||||
@router.delete("/training-category-parameters/{link_id}")
|
||||
def admin_delete_category_parameter(
|
||||
link_id: int,
|
||||
session: dict = Depends(require_admin),
|
||||
):
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute(
|
||||
"DELETE FROM training_category_parameter WHERE id = %s RETURNING id",
|
||||
(link_id,),
|
||||
)
|
||||
if not cur.fetchone():
|
||||
raise HTTPException(404, "Eintrag nicht gefunden")
|
||||
conn.commit()
|
||||
return {"ok": True}
|
||||
|
||||
|
||||
@router.get("/training-type-parameters")
|
||||
def admin_list_type_parameters(
|
||||
training_type_id: int = Query(..., ge=1),
|
||||
session: dict = Depends(require_admin),
|
||||
):
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT ttp.*, tp.key AS parameter_key, tp.name_de AS parameter_name_de
|
||||
FROM training_type_parameter ttp
|
||||
JOIN training_parameters tp ON tp.id = ttp.training_parameter_id
|
||||
WHERE ttp.training_type_id = %s
|
||||
ORDER BY ttp.sort_order NULLS LAST, tp.key
|
||||
""",
|
||||
(training_type_id,),
|
||||
)
|
||||
return [r2d(r) for r in cur.fetchall()]
|
||||
|
||||
|
||||
@router.post("/training-type-parameters")
|
||||
def admin_add_type_parameter(
|
||||
body: TypeParameterCreate,
|
||||
session: dict = Depends(require_admin),
|
||||
):
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute("SELECT id FROM training_types WHERE id = %s", (body.training_type_id,))
|
||||
if not cur.fetchone():
|
||||
raise HTTPException(404, "training_type_id unbekannt")
|
||||
cur.execute("SELECT id FROM training_parameters WHERE id = %s", (body.training_parameter_id,))
|
||||
if not cur.fetchone():
|
||||
raise HTTPException(404, "training_parameter_id unbekannt")
|
||||
try:
|
||||
cur.execute(
|
||||
"""
|
||||
INSERT INTO training_type_parameter (
|
||||
training_type_id, training_parameter_id, sort_order, required, ui_group
|
||||
) VALUES (%s,%s,%s,%s,%s)
|
||||
RETURNING id
|
||||
""",
|
||||
(
|
||||
body.training_type_id,
|
||||
body.training_parameter_id,
|
||||
body.sort_order,
|
||||
body.required,
|
||||
body.ui_group,
|
||||
),
|
||||
)
|
||||
new_id = cur.fetchone()["id"]
|
||||
conn.commit()
|
||||
except Exception as e:
|
||||
conn.rollback()
|
||||
if "uq_training_type_parameter" in str(e).lower() or "unique" in str(e).lower():
|
||||
raise HTTPException(409, "Zuordnung existiert bereits") from e
|
||||
raise HTTPException(400, str(e)) from e
|
||||
return {"id": new_id}
|
||||
|
||||
|
||||
@router.put("/training-type-parameters/{link_id}")
|
||||
def admin_update_type_parameter(
|
||||
link_id: int,
|
||||
body: TypeParameterUpdate,
|
||||
session: dict = Depends(require_admin),
|
||||
):
|
||||
patch = body.model_dump(exclude_unset=True)
|
||||
if not patch:
|
||||
raise HTTPException(400, "Keine Felder zum Aktualisieren")
|
||||
cols: list[str] = []
|
||||
vals: list = []
|
||||
if "sort_order" in patch:
|
||||
cols.append("sort_order = %s")
|
||||
vals.append(patch["sort_order"])
|
||||
if "required" in patch:
|
||||
cols.append("required = %s")
|
||||
vals.append(patch["required"])
|
||||
if "ui_group" in patch:
|
||||
cols.append("ui_group = %s")
|
||||
vals.append(patch["ui_group"].strip() if patch["ui_group"] else None)
|
||||
if not cols:
|
||||
raise HTTPException(400, "Keine Felder zum Aktualisieren")
|
||||
vals.append(link_id)
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute(
|
||||
f"UPDATE training_type_parameter SET {', '.join(cols)} WHERE id = %s RETURNING id",
|
||||
vals,
|
||||
)
|
||||
if not cur.fetchone():
|
||||
raise HTTPException(404, "Eintrag nicht gefunden")
|
||||
conn.commit()
|
||||
return {"ok": True, "id": link_id}
|
||||
|
||||
|
||||
@router.delete("/training-type-parameters/{link_id}")
|
||||
def admin_delete_type_parameter(
|
||||
link_id: int,
|
||||
session: dict = Depends(require_admin),
|
||||
):
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute(
|
||||
"DELETE FROM training_type_parameter WHERE id = %s RETURNING id",
|
||||
(link_id,),
|
||||
)
|
||||
if not cur.fetchone():
|
||||
raise HTTPException(404, "Eintrag nicht gefunden")
|
||||
conn.commit()
|
||||
return {"ok": True}
|
||||
@@ -0,0 +1,453 @@
|
||||
"""
|
||||
Admin: System-CSV-Templates (csv_field_mappings, is_system=true) pflegen (Issue #21).
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any, List, Optional
|
||||
|
||||
from fastapi import APIRouter, Depends, File, Form, HTTPException, UploadFile
|
||||
from pydantic import BaseModel, Field
|
||||
from psycopg2.extras import Json
|
||||
|
||||
from auth import require_admin
|
||||
from db import get_db, get_cursor, r2d
|
||||
from csv_parser.core import (
|
||||
column_signature,
|
||||
decode_raw_bytes,
|
||||
get_csv_import_limits,
|
||||
headers_signature_rank_metrics,
|
||||
normalize_header_for_signature,
|
||||
parse_csv_sample,
|
||||
)
|
||||
from csv_parser.mapping_suggest import build_type_conversions_for_mapping, suggest_field_mappings
|
||||
from csv_parser.import_row_processing import (
|
||||
validate_import_row_processing as validate_import_row_processing_spec,
|
||||
)
|
||||
from csv_parser.module_registry import get_module_definition
|
||||
from csv_parser.template_validator import validate_csv_template
|
||||
from data_layer.activity_persistence_orchestrator import merge_activity_csv_module_fields
|
||||
|
||||
router = APIRouter(prefix="/api/admin/csv-templates", tags=["admin", "csv-import"])
|
||||
|
||||
|
||||
class CsvSystemTemplateCreate(BaseModel):
|
||||
module: str
|
||||
mapping_name: str = Field(..., min_length=1, max_length=100)
|
||||
description: Optional[str] = None
|
||||
column_signature: List[str] = Field(default_factory=list)
|
||||
delimiter: str = ","
|
||||
encoding: str = "utf-8"
|
||||
has_header: bool = True
|
||||
field_mappings: dict = Field(default_factory=dict)
|
||||
type_conversions: Optional[dict] = None
|
||||
import_row_processing: Optional[dict] = None
|
||||
|
||||
|
||||
class CsvSystemTemplateUpdate(BaseModel):
|
||||
mapping_name: Optional[str] = Field(default=None, min_length=1, max_length=100)
|
||||
description: Optional[str] = None
|
||||
column_signature: Optional[List[str]] = None
|
||||
delimiter: Optional[str] = None
|
||||
encoding: Optional[str] = None
|
||||
has_header: Optional[bool] = None
|
||||
field_mappings: Optional[dict] = None
|
||||
type_conversions: Optional[dict] = None
|
||||
import_row_processing: Optional[dict] = None
|
||||
|
||||
|
||||
class CsvImportLimitsBody(BaseModel):
|
||||
max_rows_per_file: int = Field(..., ge=100, le=2_000_000)
|
||||
max_file_bytes: int = Field(..., ge=10_000, le=2_147_483_648)
|
||||
|
||||
|
||||
class CsvTemplateValidateBody(BaseModel):
|
||||
"""Formatprüfung ohne Speichern (field_mappings + type_conversions + optional row_processing)."""
|
||||
|
||||
module: str
|
||||
field_mappings: dict = Field(default_factory=dict)
|
||||
type_conversions: Optional[dict] = None
|
||||
import_row_processing: Optional[dict] = None
|
||||
column_signature: Optional[List[str]] = None
|
||||
|
||||
|
||||
def _row_full(m: dict) -> dict:
|
||||
return {
|
||||
"id": m["id"],
|
||||
"module": m["module"],
|
||||
"mapping_name": m["mapping_name"],
|
||||
"description": m.get("description"),
|
||||
"column_signature": list(m["column_signature"]) if m.get("column_signature") else [],
|
||||
"delimiter": m["delimiter"],
|
||||
"encoding": m["encoding"],
|
||||
"has_header": m["has_header"],
|
||||
"field_mappings": m["field_mappings"],
|
||||
"type_conversions": m.get("type_conversions"),
|
||||
"import_row_processing": m.get("import_row_processing"),
|
||||
"usage_count": m.get("usage_count"),
|
||||
"success_rate": m.get("success_rate"),
|
||||
"last_used_at": m.get("last_used_at"),
|
||||
"created_at": m.get("created_at"),
|
||||
"updated_at": m.get("updated_at"),
|
||||
"is_system": m["is_system"],
|
||||
}
|
||||
|
||||
|
||||
@router.get("/import-limits")
|
||||
def admin_get_csv_import_limits(session: dict = Depends(require_admin)):
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute("SELECT value FROM system_config WHERE key = %s", ("csv_import",))
|
||||
row = cur.fetchone()
|
||||
return get_csv_import_limits(r2d(row) if row else None)
|
||||
|
||||
|
||||
@router.put("/import-limits")
|
||||
def admin_put_csv_import_limits(body: CsvImportLimitsBody, session: dict = Depends(require_admin)):
|
||||
payload = {"max_rows_per_file": body.max_rows_per_file, "max_file_bytes": body.max_file_bytes}
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute(
|
||||
"""
|
||||
INSERT INTO system_config (key, value, updated_at)
|
||||
VALUES ('csv_import', %s, CURRENT_TIMESTAMP)
|
||||
ON CONFLICT (key) DO UPDATE
|
||||
SET value = EXCLUDED.value, updated_at = CURRENT_TIMESTAMP
|
||||
""",
|
||||
(Json(payload),),
|
||||
)
|
||||
return payload
|
||||
|
||||
|
||||
@router.get("")
|
||||
def list_system_templates(
|
||||
module: Optional[str] = None,
|
||||
session: dict = Depends(require_admin),
|
||||
):
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT * FROM csv_field_mappings
|
||||
WHERE is_system = true AND profile_id IS NULL
|
||||
AND (%s::text IS NULL OR module = %s)
|
||||
ORDER BY module, mapping_name
|
||||
""",
|
||||
(module, module),
|
||||
)
|
||||
rows = [r2d(r) for r in cur.fetchall()]
|
||||
return {"templates": [_row_full(m) for m in rows]}
|
||||
|
||||
|
||||
@router.post("/analyze-upload")
|
||||
async def admin_analyze_csv_for_template(
|
||||
file: UploadFile = File(...),
|
||||
module: str = Form(...),
|
||||
delimiter: Optional[str] = Form(default=None),
|
||||
seed_template_id: Optional[int] = Form(default=None),
|
||||
session: dict = Depends(require_admin),
|
||||
):
|
||||
"""
|
||||
CSV hochladen wie im Nutzer-Import: Spalten + Vorschau + Vorschläge für field_mappings
|
||||
und type_conversions. Optional Seed-Vorlage (ID) oder beste Systemvorlage (Abdeckung, dann Jaccard).
|
||||
"""
|
||||
_ = session
|
||||
if not get_module_definition(module):
|
||||
raise HTTPException(400, f"Unbekanntes Modul: {module}")
|
||||
|
||||
raw = await file.read()
|
||||
limits = _admin_csv_limits()
|
||||
max_bytes = limits.get("max_file_bytes", 52_428_800)
|
||||
if len(raw) > max_bytes:
|
||||
raise HTTPException(
|
||||
413,
|
||||
f"Datei zu groß (max. {max_bytes} Bytes laut Systemkonfiguration)",
|
||||
)
|
||||
|
||||
text = decode_raw_bytes(raw)
|
||||
if not text.strip():
|
||||
raise HTTPException(400, "Leere Datei")
|
||||
|
||||
max_rows = limits.get("max_rows_per_file", 50_000)
|
||||
if text.count("\n") > max_rows + 5:
|
||||
raise HTTPException(
|
||||
413,
|
||||
f"Zu viele Zeilen (>{max_rows}) laut Systemkonfiguration",
|
||||
)
|
||||
|
||||
delim = delimiter if delimiter in (",", ";", "\t") else None
|
||||
headers, sample_rows, used_delim = parse_csv_sample(text, delimiter=delim, max_data_rows=5)
|
||||
if not headers:
|
||||
raise HTTPException(400, "Keine Kopfzeile oder leeres CSV")
|
||||
|
||||
sig = column_signature(headers)
|
||||
|
||||
seed_row: dict | None = None
|
||||
field_mappings: dict = {}
|
||||
type_conversions: dict = {}
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
if seed_template_id is not None:
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT * FROM csv_field_mappings
|
||||
WHERE id = %s AND is_system = true AND profile_id IS NULL AND module = %s
|
||||
""",
|
||||
(seed_template_id, module),
|
||||
)
|
||||
seed_row = r2d(cur.fetchone())
|
||||
if not seed_row:
|
||||
raise HTTPException(404, "Seed-Vorlage nicht gefunden oder falsches Modul")
|
||||
else:
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT * FROM csv_field_mappings
|
||||
WHERE is_system = true AND profile_id IS NULL AND module = %s
|
||||
""",
|
||||
(module,),
|
||||
)
|
||||
rows = [r2d(r) for r in cur.fetchall()]
|
||||
best: dict | None = None
|
||||
best_key: tuple[float, int, float] = (-1.0, -1, -1.0)
|
||||
for t in rows:
|
||||
t_sig = list(t.get("column_signature") or [])
|
||||
m = headers_signature_rank_metrics(sig, t_sig)
|
||||
key = (m["confidence"], m["columns_matched"], m["jaccard"])
|
||||
if key > best_key:
|
||||
best_key = key
|
||||
best = t
|
||||
if best and best_key[0] > 0:
|
||||
seed_row = best
|
||||
|
||||
mod_def = get_module_definition(module) or {}
|
||||
eff_fields = dict(mod_def.get("fields") or {})
|
||||
if module == "activity":
|
||||
eff_fields = merge_activity_csv_module_fields(cur, eff_fields)
|
||||
|
||||
seed_fm = (seed_row or {}).get("field_mappings") or {}
|
||||
if isinstance(seed_fm, str):
|
||||
seed_fm = {}
|
||||
seed_tc = (seed_row or {}).get("type_conversions")
|
||||
if not isinstance(seed_tc, dict):
|
||||
seed_tc = {}
|
||||
|
||||
field_mappings = suggest_field_mappings(
|
||||
headers,
|
||||
module,
|
||||
seed_fm if seed_fm else None,
|
||||
effective_fields=eff_fields,
|
||||
)
|
||||
type_conversions = build_type_conversions_for_mapping(
|
||||
module,
|
||||
field_mappings,
|
||||
seed_tc if seed_tc else None,
|
||||
effective_fields=eff_fields,
|
||||
)
|
||||
|
||||
seed_meta = None
|
||||
if seed_row:
|
||||
t_sig = list(seed_row.get("column_signature") or [])
|
||||
sm = headers_signature_rank_metrics(sig, t_sig)
|
||||
seed_meta = {
|
||||
"id": seed_row["id"],
|
||||
"mapping_name": seed_row.get("mapping_name"),
|
||||
"confidence": sm["confidence"],
|
||||
"template_recall": sm["template_recall"],
|
||||
"jaccard": sm["jaccard"],
|
||||
"columns_matched": sm["columns_matched"],
|
||||
"columns_in_template": sm["columns_in_template"],
|
||||
"columns_in_csv": sm["columns_in_csv"],
|
||||
}
|
||||
|
||||
return {
|
||||
"filename": file.filename,
|
||||
"module": module,
|
||||
"delimiter": used_delim,
|
||||
"encoding": "utf-8",
|
||||
"columns": headers,
|
||||
"column_signature_normalized": sig,
|
||||
"sample_rows": sample_rows,
|
||||
"seed_template": seed_meta,
|
||||
"field_mappings": field_mappings,
|
||||
"type_conversions": type_conversions,
|
||||
}
|
||||
|
||||
|
||||
def _admin_csv_limits() -> dict[str, int]:
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute("SELECT value FROM system_config WHERE key = %s", ("csv_import",))
|
||||
row = cur.fetchone()
|
||||
return get_csv_import_limits(r2d(row) if row else None)
|
||||
|
||||
|
||||
@router.post("/validate")
|
||||
def validate_system_template_dry_run(body: CsvTemplateValidateBody, session: dict = Depends(require_admin)):
|
||||
"""
|
||||
Validatorlauf für eine Vorlagen-Konfiguration (ohne DB-Schreiben).
|
||||
Nutzbar aus dem Admin-Editor vor dem Speichern.
|
||||
"""
|
||||
if not get_module_definition(body.module):
|
||||
raise HTTPException(400, f"Unbekanntes Modul: {body.module}")
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
return validate_csv_template(
|
||||
body.module,
|
||||
body.field_mappings,
|
||||
body.type_conversions,
|
||||
body.import_row_processing,
|
||||
body.column_signature,
|
||||
cur=cur,
|
||||
)
|
||||
|
||||
|
||||
@router.get("/{template_id}")
|
||||
def get_system_template(template_id: int, session: dict = Depends(require_admin)):
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute(
|
||||
"SELECT * FROM csv_field_mappings WHERE id = %s AND is_system = true AND profile_id IS NULL",
|
||||
(template_id,),
|
||||
)
|
||||
m = r2d(cur.fetchone())
|
||||
if not m:
|
||||
raise HTTPException(404, "System-Template nicht gefunden")
|
||||
return _row_full(m)
|
||||
|
||||
|
||||
@router.post("")
|
||||
def create_system_template(body: CsvSystemTemplateCreate, session: dict = Depends(require_admin)):
|
||||
if not get_module_definition(body.module):
|
||||
raise HTTPException(400, f"Unbekanntes Modul: {body.module}")
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
report = validate_csv_template(
|
||||
body.module,
|
||||
body.field_mappings,
|
||||
body.type_conversions,
|
||||
body.import_row_processing,
|
||||
body.column_signature,
|
||||
cur=cur,
|
||||
)
|
||||
if not report["valid"]:
|
||||
raise HTTPException(status_code=422, detail=report)
|
||||
|
||||
cur.execute(
|
||||
"""
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions, import_row_processing
|
||||
) VALUES (
|
||||
NULL, true, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s
|
||||
) RETURNING id
|
||||
""",
|
||||
(
|
||||
body.module,
|
||||
body.mapping_name,
|
||||
body.description,
|
||||
body.column_signature,
|
||||
body.delimiter,
|
||||
body.encoding,
|
||||
body.has_header,
|
||||
Json(body.field_mappings),
|
||||
Json(body.type_conversions) if body.type_conversions is not None else None,
|
||||
Json(body.import_row_processing) if body.import_row_processing is not None else None,
|
||||
),
|
||||
)
|
||||
new_id = cur.fetchone()["id"]
|
||||
return {"id": new_id, "validation": report}
|
||||
|
||||
|
||||
@router.put("/{template_id}")
|
||||
def update_system_template(
|
||||
template_id: int,
|
||||
body: CsvSystemTemplateUpdate,
|
||||
session: dict = Depends(require_admin),
|
||||
):
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute(
|
||||
"SELECT * FROM csv_field_mappings WHERE id = %s AND is_system = true AND profile_id IS NULL",
|
||||
(template_id,),
|
||||
)
|
||||
existing = r2d(cur.fetchone())
|
||||
if not existing:
|
||||
raise HTTPException(404, "System-Template nicht gefunden")
|
||||
|
||||
patch: dict[str, Any] = body.model_dump(exclude_unset=True)
|
||||
if not patch:
|
||||
return _row_full(existing)
|
||||
|
||||
fm = patch.get("field_mappings", existing["field_mappings"])
|
||||
tc_eff = patch.get("type_conversions", existing.get("type_conversions"))
|
||||
irp_eff = patch.get("import_row_processing", existing.get("import_row_processing"))
|
||||
col_eff = patch.get("column_signature", existing.get("column_signature"))
|
||||
|
||||
report = validate_csv_template(
|
||||
existing["module"],
|
||||
fm,
|
||||
tc_eff,
|
||||
irp_eff,
|
||||
col_eff if isinstance(col_eff, list) else None,
|
||||
cur=cur,
|
||||
)
|
||||
if not report["valid"]:
|
||||
raise HTTPException(status_code=422, detail=report)
|
||||
|
||||
fields_sql = []
|
||||
vals: list = []
|
||||
if "mapping_name" in patch:
|
||||
fields_sql.append("mapping_name = %s")
|
||||
vals.append(patch["mapping_name"])
|
||||
if "description" in patch:
|
||||
fields_sql.append("description = %s")
|
||||
vals.append(patch["description"])
|
||||
if "column_signature" in patch:
|
||||
fields_sql.append("column_signature = %s")
|
||||
vals.append(patch["column_signature"])
|
||||
if "delimiter" in patch:
|
||||
fields_sql.append("delimiter = %s")
|
||||
vals.append(patch["delimiter"])
|
||||
if "encoding" in patch:
|
||||
fields_sql.append("encoding = %s")
|
||||
vals.append(patch["encoding"])
|
||||
if "has_header" in patch:
|
||||
fields_sql.append("has_header = %s")
|
||||
vals.append(patch["has_header"])
|
||||
if "field_mappings" in patch:
|
||||
fields_sql.append("field_mappings = %s")
|
||||
vals.append(Json(patch["field_mappings"]))
|
||||
if "type_conversions" in patch:
|
||||
fields_sql.append("type_conversions = %s")
|
||||
tc = patch["type_conversions"]
|
||||
vals.append(Json(tc) if tc is not None else None)
|
||||
if "import_row_processing" in patch:
|
||||
irp = patch["import_row_processing"]
|
||||
fields_sql.append("import_row_processing = %s")
|
||||
vals.append(Json(irp) if irp is not None else None)
|
||||
|
||||
fields_sql.append("updated_at = CURRENT_TIMESTAMP")
|
||||
vals.append(template_id)
|
||||
|
||||
cur.execute(
|
||||
f"UPDATE csv_field_mappings SET {', '.join(fields_sql)} WHERE id = %s",
|
||||
tuple(vals),
|
||||
)
|
||||
|
||||
cur.execute("SELECT * FROM csv_field_mappings WHERE id = %s", (template_id,))
|
||||
m = r2d(cur.fetchone())
|
||||
return {**_row_full(m), "validation": report}
|
||||
|
||||
|
||||
@router.delete("/{template_id}")
|
||||
def delete_system_template(template_id: int, session: dict = Depends(require_admin)):
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute(
|
||||
"DELETE FROM csv_field_mappings WHERE id = %s AND is_system = true AND profile_id IS NULL RETURNING id",
|
||||
(template_id,),
|
||||
)
|
||||
row = cur.fetchone()
|
||||
if not row:
|
||||
raise HTTPException(404, "System-Template nicht gefunden")
|
||||
return {"deleted": template_id}
|
||||
@@ -0,0 +1,215 @@
|
||||
"""
|
||||
Admin: training_parameters catalog (EAV keys for activity session metrics).
|
||||
|
||||
Agent guide: .claude/docs/technical/ACTIVITY_SESSION_METRICS_EAV_AGENT_GUIDE.md
|
||||
"""
|
||||
import re
|
||||
from typing import Any, Optional
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException, Query
|
||||
from pydantic import BaseModel, Field
|
||||
from psycopg2 import errors as pg_errors
|
||||
from psycopg2.extras import Json
|
||||
|
||||
from auth import require_admin
|
||||
from db import get_db, get_cursor, r2d
|
||||
|
||||
router = APIRouter(prefix="/api/admin/training-parameters", tags=["admin", "training-parameters"])
|
||||
|
||||
KEY_PATTERN = re.compile(r"^[a-z][a-z0-9_]{0,62}$")
|
||||
|
||||
PARAM_CATEGORY = {"physical", "physiological", "subjective", "environmental", "performance"}
|
||||
DATA_TYPES = {"integer", "float", "string", "boolean"}
|
||||
|
||||
|
||||
class TrainingParameterCreate(BaseModel):
|
||||
key: str = Field(..., min_length=1, max_length=50)
|
||||
name_de: str = Field(..., min_length=1, max_length=100)
|
||||
name_en: str = Field(..., min_length=1, max_length=100)
|
||||
category: str = Field(..., max_length=50)
|
||||
data_type: str = Field(..., max_length=20)
|
||||
unit: Optional[str] = Field(None, max_length=20)
|
||||
description_de: Optional[str] = None
|
||||
description_en: Optional[str] = None
|
||||
source_field: Optional[str] = Field(None, max_length=100)
|
||||
validation_rules: Optional[dict] = None
|
||||
is_active: bool = True
|
||||
|
||||
|
||||
class TrainingParameterUpdate(BaseModel):
|
||||
name_de: Optional[str] = Field(None, min_length=1, max_length=100)
|
||||
name_en: Optional[str] = Field(None, min_length=1, max_length=100)
|
||||
category: Optional[str] = Field(None, max_length=50)
|
||||
data_type: Optional[str] = Field(None, max_length=20)
|
||||
unit: Optional[str] = Field(None, max_length=20)
|
||||
description_de: Optional[str] = None
|
||||
description_en: Optional[str] = None
|
||||
source_field: Optional[str] = Field(None, max_length=100)
|
||||
validation_rules: Optional[dict] = None
|
||||
is_active: Optional[bool] = None
|
||||
|
||||
|
||||
def _norm_key(key: str) -> str:
|
||||
k = key.strip().lower()
|
||||
if not KEY_PATTERN.match(k):
|
||||
raise HTTPException(
|
||||
400,
|
||||
"Ungültiger key: nur Kleinbuchstaben, Ziffern, Unterstriche; muss mit Buchstabe beginnen.",
|
||||
)
|
||||
return k
|
||||
|
||||
|
||||
def _validate_category(cat: str) -> str:
|
||||
c = cat.strip()
|
||||
if c not in PARAM_CATEGORY:
|
||||
raise HTTPException(400, f"category muss einer von {sorted(PARAM_CATEGORY)} sein")
|
||||
return c
|
||||
|
||||
|
||||
def _validate_data_type(dt: str) -> str:
|
||||
d = dt.strip().lower()
|
||||
if d not in DATA_TYPES:
|
||||
raise HTTPException(400, f"data_type muss einer von {sorted(DATA_TYPES)} sein")
|
||||
return d
|
||||
|
||||
|
||||
@router.get("")
|
||||
def admin_list_training_parameters(
|
||||
include_inactive: bool = Query(False),
|
||||
session: dict = Depends(require_admin),
|
||||
):
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
if include_inactive:
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT * FROM training_parameters
|
||||
ORDER BY category, key
|
||||
"""
|
||||
)
|
||||
else:
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT * FROM training_parameters
|
||||
WHERE is_active = true
|
||||
ORDER BY category, key
|
||||
"""
|
||||
)
|
||||
return [r2d(r) for r in cur.fetchall()]
|
||||
|
||||
|
||||
@router.post("")
|
||||
def admin_create_training_parameter(
|
||||
body: TrainingParameterCreate,
|
||||
session: dict = Depends(require_admin),
|
||||
):
|
||||
key = _norm_key(body.key)
|
||||
cat = _validate_category(body.category)
|
||||
dt = _validate_data_type(body.data_type)
|
||||
rules = body.validation_rules if body.validation_rules is not None else {}
|
||||
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
try:
|
||||
cur.execute(
|
||||
"""
|
||||
INSERT INTO training_parameters (
|
||||
key, name_de, name_en, category, data_type, unit,
|
||||
description_de, description_en, source_field, validation_rules, is_active
|
||||
) VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)
|
||||
RETURNING id
|
||||
""",
|
||||
(
|
||||
key,
|
||||
body.name_de.strip(),
|
||||
body.name_en.strip(),
|
||||
cat,
|
||||
dt,
|
||||
body.unit.strip() if body.unit else None,
|
||||
body.description_de,
|
||||
body.description_en,
|
||||
body.source_field.strip() if body.source_field else None,
|
||||
Json(rules),
|
||||
body.is_active,
|
||||
),
|
||||
)
|
||||
new_id = cur.fetchone()["id"]
|
||||
conn.commit()
|
||||
except pg_errors.UniqueViolation:
|
||||
conn.rollback()
|
||||
raise HTTPException(409, "Parameter-key existiert bereits") from None
|
||||
return {"id": new_id, "key": key}
|
||||
|
||||
|
||||
@router.put("/{param_id}")
|
||||
def admin_update_training_parameter(
|
||||
param_id: int,
|
||||
body: TrainingParameterUpdate,
|
||||
session: dict = Depends(require_admin),
|
||||
):
|
||||
cols: list[str] = []
|
||||
vals: list[Any] = []
|
||||
|
||||
if body.name_de is not None:
|
||||
cols.append("name_de = %s")
|
||||
vals.append(body.name_de.strip())
|
||||
if body.name_en is not None:
|
||||
cols.append("name_en = %s")
|
||||
vals.append(body.name_en.strip())
|
||||
if body.category is not None:
|
||||
cols.append("category = %s")
|
||||
vals.append(_validate_category(body.category))
|
||||
if body.data_type is not None:
|
||||
cols.append("data_type = %s")
|
||||
vals.append(_validate_data_type(body.data_type))
|
||||
if body.unit is not None:
|
||||
cols.append("unit = %s")
|
||||
vals.append(body.unit.strip() or None)
|
||||
if body.description_de is not None:
|
||||
cols.append("description_de = %s")
|
||||
vals.append(body.description_de)
|
||||
if body.description_en is not None:
|
||||
cols.append("description_en = %s")
|
||||
vals.append(body.description_en)
|
||||
if body.source_field is not None:
|
||||
cols.append("source_field = %s")
|
||||
vals.append(body.source_field.strip() or None)
|
||||
if body.validation_rules is not None:
|
||||
cols.append("validation_rules = %s")
|
||||
vals.append(Json(body.validation_rules))
|
||||
if body.is_active is not None:
|
||||
cols.append("is_active = %s")
|
||||
vals.append(body.is_active)
|
||||
|
||||
if not cols:
|
||||
raise HTTPException(400, "Keine Felder zum Aktualisieren")
|
||||
|
||||
vals.append(param_id)
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute(
|
||||
f"UPDATE training_parameters SET {', '.join(cols)} WHERE id = %s RETURNING id",
|
||||
vals,
|
||||
)
|
||||
if not cur.fetchone():
|
||||
raise HTTPException(404, "Parameter nicht gefunden")
|
||||
conn.commit()
|
||||
return {"ok": True, "id": param_id}
|
||||
|
||||
|
||||
@router.delete("/{param_id}")
|
||||
def admin_deactivate_training_parameter(
|
||||
param_id: int,
|
||||
session: dict = Depends(require_admin),
|
||||
):
|
||||
"""Soft-delete: is_active = false (FK von session_metrics verhindert hartes Löschen)."""
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute(
|
||||
"UPDATE training_parameters SET is_active = false WHERE id = %s RETURNING id",
|
||||
(param_id,),
|
||||
)
|
||||
if not cur.fetchone():
|
||||
raise HTTPException(404, "Parameter nicht gefunden")
|
||||
conn.commit()
|
||||
return {"ok": True, "id": param_id}
|
||||
+56
-46
@@ -35,7 +35,8 @@ from data_layer.nutrition_metrics import (
|
||||
get_nutrition_average_data,
|
||||
get_protein_targets_data,
|
||||
get_protein_adequacy_data,
|
||||
get_macro_consistency_data
|
||||
get_macro_consistency_data,
|
||||
get_energy_balance_data,
|
||||
)
|
||||
from data_layer.activity_metrics import (
|
||||
get_activity_summary_data,
|
||||
@@ -118,7 +119,7 @@ def get_weight_trend_chart(
|
||||
"""
|
||||
profile_id = session['profile_id']
|
||||
|
||||
# Get structured data from data layer
|
||||
# Get structured data from data layer (includes series — no second weight_log query)
|
||||
trend_data = get_weight_trend_data(profile_id, days)
|
||||
|
||||
# Early return if insufficient data
|
||||
@@ -136,22 +137,12 @@ def get_weight_trend_chart(
|
||||
}
|
||||
}
|
||||
|
||||
# Get raw data points for chart
|
||||
from db import get_db, get_cursor
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cutoff = (datetime.now() - timedelta(days=days)).strftime('%Y-%m-%d')
|
||||
cur.execute(
|
||||
"""SELECT date, weight FROM weight_log
|
||||
WHERE profile_id=%s AND date >= %s
|
||||
ORDER BY date""",
|
||||
(profile_id, cutoff)
|
||||
)
|
||||
rows = cur.fetchall()
|
||||
|
||||
# Format for Chart.js
|
||||
labels = [row['date'].isoformat() for row in rows]
|
||||
values = [float(row['weight']) for row in rows]
|
||||
series = trend_data.get("series") or []
|
||||
labels = [
|
||||
pt["date"].isoformat() if hasattr(pt["date"], "isoformat") else str(pt["date"])
|
||||
for pt in series
|
||||
]
|
||||
values = [pt["weight"] for pt in series]
|
||||
|
||||
return {
|
||||
"chart_type": "line",
|
||||
@@ -346,17 +337,20 @@ def get_energy_balance_chart(
|
||||
"""
|
||||
profile_id = session['profile_id']
|
||||
|
||||
balance_meta = get_energy_balance_data(profile_id, days)
|
||||
|
||||
from db import get_db, get_cursor
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cutoff = (datetime.now() - timedelta(days=days)).strftime('%Y-%m-%d')
|
||||
|
||||
cur.execute(
|
||||
"""SELECT date, kcal
|
||||
"""SELECT date, SUM(kcal)::float AS kcal
|
||||
FROM nutrition_log
|
||||
WHERE profile_id=%s AND date >= %s AND kcal IS NOT NULL
|
||||
GROUP BY date
|
||||
ORDER BY date""",
|
||||
(profile_id, cutoff)
|
||||
(profile_id, cutoff),
|
||||
)
|
||||
rows = cur.fetchall()
|
||||
|
||||
@@ -374,7 +368,21 @@ def get_energy_balance_chart(
|
||||
}
|
||||
}
|
||||
|
||||
# Prepare data
|
||||
estimated_tdee = balance_meta.get("estimated_tdee") or 0
|
||||
if estimated_tdee <= 0:
|
||||
return {
|
||||
"chart_type": "line",
|
||||
"data": {
|
||||
"labels": [],
|
||||
"datasets": []
|
||||
},
|
||||
"metadata": {
|
||||
"confidence": "insufficient",
|
||||
"data_points": len(rows),
|
||||
"message": "Kein Gewicht für TDEE-Schätzung (weight_log erforderlich)"
|
||||
}
|
||||
}
|
||||
|
||||
labels = []
|
||||
daily_values = []
|
||||
avg_7d = []
|
||||
@@ -384,23 +392,19 @@ def get_energy_balance_chart(
|
||||
labels.append(row['date'].isoformat())
|
||||
daily_values.append(safe_float(row['kcal']))
|
||||
|
||||
# 7d rolling average
|
||||
start_7d = max(0, i - 6)
|
||||
window_7d = [safe_float(rows[j]['kcal']) for j in range(start_7d, i + 1)]
|
||||
avg_7d.append(round(sum(window_7d) / len(window_7d), 1) if window_7d else None)
|
||||
|
||||
# 14d rolling average
|
||||
start_14d = max(0, i - 13)
|
||||
window_14d = [safe_float(rows[j]['kcal']) for j in range(start_14d, i + 1)]
|
||||
avg_14d.append(round(sum(window_14d) / len(window_14d), 1) if window_14d else None)
|
||||
|
||||
# Calculate TDEE (estimated, should come from profile)
|
||||
# TODO: Calculate from profile (weight, height, age, activity level)
|
||||
estimated_tdee = 2500.0
|
||||
|
||||
# Calculate deficit/surplus
|
||||
avg_intake = sum(daily_values) / len(daily_values) if daily_values else 0
|
||||
energy_balance = avg_intake - estimated_tdee
|
||||
avg_intake = float(balance_meta.get("avg_intake") or (sum(daily_values) / len(daily_values) if daily_values else 0))
|
||||
energy_balance = float(balance_meta.get("energy_balance") or (avg_intake - estimated_tdee))
|
||||
balance_status = balance_meta.get("status") or (
|
||||
"deficit" if energy_balance < -200 else "surplus" if energy_balance > 200 else "maintenance"
|
||||
)
|
||||
|
||||
datasets = [
|
||||
{
|
||||
@@ -443,8 +447,7 @@ def get_energy_balance_chart(
|
||||
}
|
||||
]
|
||||
|
||||
from data_layer.utils import calculate_confidence
|
||||
confidence = calculate_confidence(len(rows), days, "general")
|
||||
confidence = balance_meta.get("confidence") or "low"
|
||||
|
||||
return {
|
||||
"chart_type": "line",
|
||||
@@ -458,7 +461,7 @@ def get_energy_balance_chart(
|
||||
"avg_kcal": round(avg_intake, 1),
|
||||
"estimated_tdee": estimated_tdee,
|
||||
"energy_balance": round(energy_balance, 1),
|
||||
"balance_status": "deficit" if energy_balance < -200 else "surplus" if energy_balance > 200 else "maintenance",
|
||||
"balance_status": balance_status,
|
||||
"first_date": rows[0]['date'],
|
||||
"last_date": rows[-1]['date']
|
||||
})
|
||||
@@ -587,11 +590,12 @@ def get_protein_adequacy_chart(
|
||||
cutoff = (datetime.now() - timedelta(days=days)).strftime('%Y-%m-%d')
|
||||
|
||||
cur.execute(
|
||||
"""SELECT date, protein_g
|
||||
"""SELECT date, SUM(protein_g)::float AS protein_g
|
||||
FROM nutrition_log
|
||||
WHERE profile_id=%s AND date >= %s AND protein_g IS NOT NULL
|
||||
GROUP BY date
|
||||
ORDER BY date""",
|
||||
(profile_id, cutoff)
|
||||
(profile_id, cutoff),
|
||||
)
|
||||
rows = cur.fetchall()
|
||||
|
||||
@@ -687,7 +691,6 @@ def get_protein_adequacy_chart(
|
||||
from data_layer.utils import calculate_confidence
|
||||
confidence = calculate_confidence(len(rows), days, "general")
|
||||
|
||||
# Count days in target
|
||||
days_in_target = sum(1 for v in daily_values if target_low <= v <= target_high)
|
||||
|
||||
return {
|
||||
@@ -978,16 +981,23 @@ def get_nutrition_adherence_score(
|
||||
|
||||
# Get nutrition data
|
||||
cur.execute(
|
||||
"""SELECT COUNT(*) as cnt,
|
||||
AVG(kcal) as avg_kcal,
|
||||
STDDEV(kcal) as std_kcal,
|
||||
AVG(protein_g) as avg_protein,
|
||||
AVG(carbs_g) as avg_carbs,
|
||||
AVG(fat_g) as avg_fat
|
||||
FROM nutrition_log
|
||||
WHERE profile_id=%s AND date >= %s
|
||||
AND kcal IS NOT NULL""",
|
||||
(profile_id, cutoff)
|
||||
"""WITH daily AS (
|
||||
SELECT date,
|
||||
COALESCE(SUM(kcal), 0)::float AS dk,
|
||||
COALESCE(SUM(protein_g), 0)::float AS dp,
|
||||
COALESCE(SUM(carbs_g), 0)::float AS dc,
|
||||
COALESCE(SUM(fat_g), 0)::float AS df FROM nutrition_log
|
||||
WHERE profile_id=%s AND date >= %s AND kcal IS NOT NULL
|
||||
GROUP BY date
|
||||
)
|
||||
SELECT COUNT(*)::int AS cnt,
|
||||
AVG(dk) AS avg_kcal,
|
||||
STDDEV(dk) AS std_kcal,
|
||||
AVG(dp) AS avg_protein,
|
||||
AVG(dc) AS avg_carbs,
|
||||
AVG(df) AS avg_fat
|
||||
FROM daily""",
|
||||
(profile_id, cutoff),
|
||||
)
|
||||
stats = cur.fetchone()
|
||||
|
||||
|
||||
@@ -0,0 +1,656 @@
|
||||
"""
|
||||
CSV-Import: Nutzer-Endpunkte für Analyse, Mappings, Limits (Issue #21).
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from typing import Any, Optional
|
||||
|
||||
from fastapi import APIRouter, Depends, File, Form, Header, HTTPException, UploadFile
|
||||
from pydantic import BaseModel
|
||||
|
||||
from psycopg2.extras import Json
|
||||
|
||||
from auth import require_auth, check_feature_access, increment_feature_usage
|
||||
from feature_logger import log_feature_usage
|
||||
from db import get_db, get_cursor, r2d
|
||||
from routers.profiles import get_pid
|
||||
from csv_parser.executor import (
|
||||
diagnose_activity_row,
|
||||
diagnose_blood_pressure_row,
|
||||
diagnose_vitals_row,
|
||||
run_universal_csv_import,
|
||||
)
|
||||
from csv_parser.core import (
|
||||
decode_raw_bytes,
|
||||
column_signature,
|
||||
get_csv_import_limits,
|
||||
headers_signature_rank_metrics,
|
||||
iter_csv_dict_rows,
|
||||
normalize_header_for_signature,
|
||||
parse_csv_sample,
|
||||
)
|
||||
from csv_parser.type_converter import build_row_after_mapping, diagnose_row_mapping
|
||||
from csv_parser.field_units import source_unit_choices_for_field
|
||||
from csv_parser.import_errors import enrich_row_error
|
||||
from csv_parser.module_registry import get_module_definition, list_modules, validate_field_mappings
|
||||
from data_layer.activity_persistence_orchestrator import merge_activity_csv_module_fields
|
||||
from csv_parser.sleep_apple_import import detect_apple_sleep_csv_format
|
||||
|
||||
router = APIRouter(prefix="/api/csv", tags=["csv-import"])
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def _load_import_limits() -> dict[str, int]:
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute("SELECT value FROM system_config WHERE key = %s", ("csv_import",))
|
||||
row = cur.fetchone()
|
||||
return get_csv_import_limits(r2d(row) if row else None)
|
||||
|
||||
|
||||
def _mapping_to_summary(m: dict) -> dict:
|
||||
return {
|
||||
"id": m["id"],
|
||||
"module": m["module"],
|
||||
"name": m["mapping_name"],
|
||||
"description": m.get("description"),
|
||||
"is_system": m["is_system"],
|
||||
"usage_count": m.get("usage_count"),
|
||||
"success_rate": m.get("success_rate"),
|
||||
"last_used_at": m.get("last_used_at"),
|
||||
"created_at": m.get("created_at"),
|
||||
}
|
||||
|
||||
|
||||
@router.get("/modules")
|
||||
def csv_modules(session: dict = Depends(require_auth)):
|
||||
"""Unterstützte Import-Module und Felddefinitionen."""
|
||||
out = []
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
for mid in list_modules():
|
||||
d = get_module_definition(mid)
|
||||
if d:
|
||||
field_src = dict(d.get("fields") or {})
|
||||
if mid == "activity":
|
||||
field_src = merge_activity_csv_module_fields(cur, field_src)
|
||||
fields_out = {}
|
||||
for fname, finfo in field_src.items():
|
||||
fd = dict(finfo)
|
||||
opts = source_unit_choices_for_field(mid, fname)
|
||||
if opts:
|
||||
fd["source_unit_options"] = opts
|
||||
fields_out[fname] = fd
|
||||
out.append(
|
||||
{
|
||||
"id": mid,
|
||||
"table": d["table"],
|
||||
"fields": fields_out,
|
||||
"import_mode": d.get("import_mode"),
|
||||
"import_row_processing_default": d.get("import_row_processing_default"),
|
||||
}
|
||||
)
|
||||
return {"modules": out}
|
||||
|
||||
|
||||
@router.get("/limits")
|
||||
def csv_limits(session: dict = Depends(require_auth)):
|
||||
"""Admin-konfigurierbare Import-Limits (system_config.csv_import)."""
|
||||
return _load_import_limits()
|
||||
|
||||
|
||||
@router.get("/mappings")
|
||||
def list_csv_mappings(
|
||||
module: Optional[str] = None,
|
||||
session: dict = Depends(require_auth),
|
||||
):
|
||||
"""System-Templates + eigene User-Mappings."""
|
||||
pid = str(session["profile_id"])
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT id, module, mapping_name, description, is_system, profile_id,
|
||||
usage_count, success_rate, last_used_at, created_at
|
||||
FROM csv_field_mappings
|
||||
WHERE is_system = true
|
||||
AND (%s::text IS NULL OR module = %s)
|
||||
ORDER BY usage_count DESC NULLS LAST, mapping_name
|
||||
""",
|
||||
(module, module),
|
||||
)
|
||||
system_rows = [r2d(r) for r in cur.fetchall()]
|
||||
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT id, module, mapping_name, description, is_system, profile_id,
|
||||
usage_count, success_rate, last_used_at, created_at
|
||||
FROM csv_field_mappings
|
||||
WHERE is_system = false AND profile_id = %s::uuid
|
||||
AND (%s::text IS NULL OR module = %s)
|
||||
ORDER BY last_used_at DESC NULLS LAST, mapping_name
|
||||
""",
|
||||
(pid, module, module),
|
||||
)
|
||||
user_rows = [r2d(r) for r in cur.fetchall()]
|
||||
|
||||
return {
|
||||
"system_templates": [_mapping_to_summary(m) for m in system_rows],
|
||||
"user_mappings": [_mapping_to_summary(m) for m in user_rows],
|
||||
}
|
||||
|
||||
|
||||
class CopyMappingBody(BaseModel):
|
||||
name: Optional[str] = None
|
||||
|
||||
|
||||
@router.post("/mappings/{mapping_id}/copy")
|
||||
def copy_csv_mapping(
|
||||
mapping_id: int,
|
||||
body: CopyMappingBody | None = None,
|
||||
session: dict = Depends(require_auth),
|
||||
):
|
||||
"""System- oder eigenes Mapping als neues User-Mapping kopieren."""
|
||||
pid = str(session["profile_id"])
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT * FROM csv_field_mappings WHERE id = %s
|
||||
""",
|
||||
(mapping_id,),
|
||||
)
|
||||
src = r2d(cur.fetchone())
|
||||
if not src:
|
||||
raise HTTPException(404, "Mapping nicht gefunden")
|
||||
if not src["is_system"] and str(src.get("profile_id")) != pid:
|
||||
raise HTTPException(403, "Kein Zugriff auf dieses Mapping")
|
||||
|
||||
base_name = (body.name if body and body.name else None) or f"{src['mapping_name']} (Kopie)"
|
||||
name = base_name
|
||||
n = 1
|
||||
while True:
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT 1 FROM csv_field_mappings
|
||||
WHERE profile_id = %s::uuid AND module = %s AND mapping_name = %s
|
||||
""",
|
||||
(pid, src["module"], name),
|
||||
)
|
||||
if not cur.fetchone():
|
||||
break
|
||||
n += 1
|
||||
name = f"{base_name} {n}"
|
||||
|
||||
cur.execute(
|
||||
"""
|
||||
INSERT INTO csv_field_mappings (
|
||||
profile_id, is_system, module, mapping_name, description,
|
||||
column_signature, delimiter, encoding, has_header,
|
||||
field_mappings, type_conversions, import_row_processing,
|
||||
usage_count, success_rate
|
||||
) VALUES (
|
||||
%s::uuid, false, %s, %s, %s,
|
||||
%s, %s, %s, %s, %s, %s, %s, 0, 1.0
|
||||
) RETURNING id
|
||||
""",
|
||||
(
|
||||
pid,
|
||||
src["module"],
|
||||
name,
|
||||
src.get("description"),
|
||||
src["column_signature"],
|
||||
src["delimiter"],
|
||||
src["encoding"],
|
||||
src["has_header"],
|
||||
Json(src["field_mappings"]),
|
||||
Json(src["type_conversions"]) if src.get("type_conversions") is not None else None,
|
||||
Json(src["import_row_processing"])
|
||||
if src.get("import_row_processing") is not None
|
||||
else None,
|
||||
),
|
||||
)
|
||||
new_id = cur.fetchone()["id"]
|
||||
return {"new_mapping_id": new_id, "mapping_name": name}
|
||||
|
||||
|
||||
@router.post("/analyze")
|
||||
async def analyze_csv(
|
||||
file: UploadFile = File(...),
|
||||
module: Optional[str] = Form(default=None),
|
||||
delimiter: Optional[str] = Form(default=None),
|
||||
session: dict = Depends(require_auth),
|
||||
):
|
||||
"""
|
||||
Erste Zeilen parsen, Signatur bilden, Vorlagen nach Ähnlichkeit ranken.
|
||||
Ohne `module`: alle System- + eigene User-Vorlagen (echte Format-Erkennung über Spalten-Signatur).
|
||||
Mit `module`: nur Vorlagen dieses Moduls (Abwärtskompatibilität).
|
||||
"""
|
||||
if module and not get_module_definition(module):
|
||||
raise HTTPException(400, f"Unbekanntes Modul: {module}")
|
||||
|
||||
pid = str(session["profile_id"])
|
||||
raw = await file.read()
|
||||
limits = _load_import_limits()
|
||||
max_bytes = limits.get("max_file_bytes", 52_428_800)
|
||||
if len(raw) > max_bytes:
|
||||
raise HTTPException(
|
||||
413,
|
||||
f"Datei zu groß (max. {max_bytes} Bytes laut Systemkonfiguration)",
|
||||
)
|
||||
|
||||
text = decode_raw_bytes(raw)
|
||||
max_rows = limits.get("max_rows_per_file", 50_000)
|
||||
if text.count("\n") > max_rows + 5:
|
||||
raise HTTPException(
|
||||
413,
|
||||
f"Zu viele Zeilen (>{max_rows}) laut Systemkonfiguration csv_import.max_rows_per_file",
|
||||
)
|
||||
delim = delimiter if delimiter in (",", ";", "\t") else None
|
||||
headers, sample_rows, used_delim = parse_csv_sample(text, delimiter=delim, max_data_rows=5)
|
||||
sig = column_signature(headers)
|
||||
|
||||
apple_sleep_csv = False
|
||||
try:
|
||||
detect_apple_sleep_csv_format(headers)
|
||||
apple_sleep_csv = True
|
||||
except ValueError:
|
||||
pass
|
||||
|
||||
mod_def = get_module_definition(module) if module else None
|
||||
available_fields = mod_def["fields"] if mod_def else None
|
||||
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
if module == "activity" and mod_def:
|
||||
available_fields = merge_activity_csv_module_fields(
|
||||
cur, dict(mod_def.get("fields") or {})
|
||||
)
|
||||
if module:
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT id, module, mapping_name, description, column_signature,
|
||||
delimiter, encoding, has_header, field_mappings, type_conversions, is_system
|
||||
FROM csv_field_mappings
|
||||
WHERE module = %s
|
||||
AND (is_system = true OR (is_system = false AND profile_id = %s::uuid))
|
||||
""",
|
||||
(module, pid),
|
||||
)
|
||||
else:
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT id, module, mapping_name, description, column_signature,
|
||||
delimiter, encoding, has_header, field_mappings, type_conversions, is_system
|
||||
FROM csv_field_mappings
|
||||
WHERE is_system = true OR (is_system = false AND profile_id = %s::uuid)
|
||||
""",
|
||||
(pid,),
|
||||
)
|
||||
templates = [r2d(r) for r in cur.fetchall()]
|
||||
|
||||
ranked = []
|
||||
for t in templates:
|
||||
t_sig = list(t["column_signature"]) if t["column_signature"] else []
|
||||
metrics = headers_signature_rank_metrics(sig, t_sig)
|
||||
conf = float(metrics["confidence"] or 0)
|
||||
if apple_sleep_csv and t.get("module") == "sleep":
|
||||
conf = max(conf, 1.0)
|
||||
ranked.append(
|
||||
{
|
||||
"mapping_id": t["id"],
|
||||
"module": t["module"],
|
||||
"mapping_name": t["mapping_name"],
|
||||
"is_system": bool(t.get("is_system")),
|
||||
"confidence": round(conf, 4),
|
||||
"template_recall": metrics["template_recall"],
|
||||
"jaccard": metrics["jaccard"],
|
||||
"columns_matched": metrics["columns_matched"],
|
||||
"columns_in_template": metrics["columns_in_template"],
|
||||
"columns_in_csv": metrics["columns_in_csv"],
|
||||
"match_type": "template_recall",
|
||||
}
|
||||
)
|
||||
ranked.sort(
|
||||
key=lambda x: (
|
||||
-(x.get("confidence") or 0),
|
||||
-(x.get("columns_matched") or 0),
|
||||
-(x.get("jaccard") or 0),
|
||||
),
|
||||
)
|
||||
|
||||
top = ranked[:25]
|
||||
recommended = top[0] if top and (top[0]["confidence"] or 0) > 0 else None
|
||||
|
||||
warnings: list[str] = []
|
||||
if apple_sleep_csv and not any(t.get("module") == "sleep" for t in templates):
|
||||
warnings.append(
|
||||
"Diese Datei ist ein Apple-Schlafexport, aber es fehlt eine Vorlage für das Modul «Schlaf» "
|
||||
"(z. B. Migration 044 / Admin → CSV-Vorlagen)."
|
||||
)
|
||||
if (
|
||||
apple_sleep_csv
|
||||
and recommended
|
||||
and recommended.get("module") != "sleep"
|
||||
and any(t.get("module") == "sleep" for t in templates)
|
||||
):
|
||||
warnings.append(
|
||||
"Apple-Schlaf-CSV erkannt — bitte eine Vorlage unter Modul «Schlaf» wählen, nicht «"
|
||||
+ str(recommended.get("module") or "")
|
||||
+ "».",
|
||||
)
|
||||
|
||||
return {
|
||||
"module_filter": module,
|
||||
"filename": file.filename,
|
||||
"encoding_note": "utf-8/latin-1 mit BOM-Strip",
|
||||
"delimiter": used_delim,
|
||||
"columns": headers,
|
||||
"column_signature_normalized": sig,
|
||||
"sample_rows": sample_rows,
|
||||
"detected_mappings": top,
|
||||
"recommended": recommended,
|
||||
"available_fields": available_fields,
|
||||
"format_detection": {"apple_sleep": apple_sleep_csv},
|
||||
"warnings": warnings,
|
||||
}
|
||||
|
||||
|
||||
@router.post("/import-diagnose")
|
||||
async def csv_import_diagnose(
|
||||
file: UploadFile = File(...),
|
||||
mapping_id: int = Form(...),
|
||||
module: Optional[str] = Form(default=None),
|
||||
x_profile_id: Optional[str] = Header(default=None),
|
||||
session: dict = Depends(require_auth),
|
||||
):
|
||||
"""
|
||||
Kein Import, keine Quota: gleiche Datei + gewählte Vorlage wie beim Import,
|
||||
aber nur die ersten Zeilen durch Mapping/Typkonvertierung (und Vital-Checks).
|
||||
Zum Debugging wenn «Datum fehlt» o. Ä. ohne DB-Zugriff.
|
||||
"""
|
||||
pid = get_pid(x_profile_id)
|
||||
raw = await file.read()
|
||||
limits = _load_import_limits()
|
||||
max_bytes = limits.get("max_file_bytes", 52_428_800)
|
||||
if len(raw) > max_bytes:
|
||||
raise HTTPException(413, f"Datei zu groß (max. {max_bytes} Bytes)")
|
||||
text = decode_raw_bytes(raw)
|
||||
if not text.strip():
|
||||
raise HTTPException(400, "Leere Datei")
|
||||
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
m = _fetch_mapping_row(cur, mapping_id, pid, module)
|
||||
|
||||
if not get_module_definition(m["module"]):
|
||||
raise HTTPException(400, f"Modul nicht unterstützt: {m['module']}")
|
||||
|
||||
fm = m.get("field_mappings") or {}
|
||||
if isinstance(fm, str):
|
||||
fm = {}
|
||||
tc = m.get("type_conversions")
|
||||
if not isinstance(tc, dict):
|
||||
tc = {}
|
||||
delim = str(m.get("delimiter") or ",")
|
||||
exec_module = str(m["module"])
|
||||
|
||||
rows_out: list[dict[str, Any]] = []
|
||||
for i, row in enumerate(iter_csv_dict_rows(text, delim, has_header=True)):
|
||||
if i >= 5:
|
||||
break
|
||||
typed = build_row_after_mapping(row, fm, tc, module=exec_module)
|
||||
dm = diagnose_row_mapping(row, fm, tc, module=exec_module, mapped_typed=typed)
|
||||
entry: dict[str, Any] = {
|
||||
"row_index": i + 1,
|
||||
**dm,
|
||||
}
|
||||
if exec_module == "vitals_baseline":
|
||||
entry["vitals"] = diagnose_vitals_row(typed)
|
||||
elif exec_module == "blood_pressure":
|
||||
entry["blood_pressure"] = diagnose_blood_pressure_row(typed)
|
||||
elif exec_module == "activity":
|
||||
entry["activity"] = diagnose_activity_row(typed)
|
||||
rows_out.append(entry)
|
||||
|
||||
return {
|
||||
"mapping_id": mapping_id,
|
||||
"mapping_name": m.get("mapping_name"),
|
||||
"module": exec_module,
|
||||
"delimiter_used": delim,
|
||||
"has_header": bool(m.get("has_header", True)),
|
||||
"rows_diagnosed": len(rows_out),
|
||||
"rows": rows_out,
|
||||
}
|
||||
|
||||
|
||||
def _fetch_mapping_row(
|
||||
cur,
|
||||
mapping_id: int,
|
||||
profile_id: str,
|
||||
module: Optional[str] = None,
|
||||
) -> dict:
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT * FROM csv_field_mappings WHERE id = %s
|
||||
""",
|
||||
(mapping_id,),
|
||||
)
|
||||
m = r2d(cur.fetchone())
|
||||
if not m:
|
||||
raise HTTPException(404, "Mapping nicht gefunden")
|
||||
if module is not None and m.get("module") != module:
|
||||
raise HTTPException(400, "Mapping gehört zu einem anderen Modul")
|
||||
if not m.get("is_system"):
|
||||
if str(m.get("profile_id") or "") != profile_id:
|
||||
raise HTTPException(403, "Kein Zugriff auf dieses Mapping")
|
||||
return m
|
||||
|
||||
|
||||
def _check_module_feature_access(pid: str, module: str) -> None:
|
||||
if module == "nutrition":
|
||||
access = check_feature_access(pid, "nutrition_entries")
|
||||
log_feature_usage(pid, "nutrition_entries", access, "csv_universal_import")
|
||||
if not access["allowed"]:
|
||||
raise HTTPException(
|
||||
403,
|
||||
f"Limit erreicht (Ernährungseinträge): {access.get('used')}/{access.get('limit')}",
|
||||
)
|
||||
elif module == "weight":
|
||||
access = check_feature_access(pid, "weight_entries")
|
||||
log_feature_usage(pid, "weight_entries", access, "csv_universal_import")
|
||||
if not access["allowed"]:
|
||||
raise HTTPException(
|
||||
403,
|
||||
f"Limit erreicht (Gewichtseinträge): {access.get('used')}/{access.get('limit')}",
|
||||
)
|
||||
elif module == "activity":
|
||||
access = check_feature_access(pid, "activity_entries")
|
||||
log_feature_usage(pid, "activity_entries", access, "csv_universal_import")
|
||||
if not access["allowed"]:
|
||||
raise HTTPException(
|
||||
403,
|
||||
f"Limit erreicht (Aktivitätseinträge): {access.get('used')}/{access.get('limit')}",
|
||||
)
|
||||
|
||||
|
||||
@router.post("/import")
|
||||
async def csv_import_execute(
|
||||
file: UploadFile = File(...),
|
||||
mapping_id: int = Form(...),
|
||||
module: Optional[str] = Form(default=None),
|
||||
x_profile_id: Optional[str] = Header(default=None),
|
||||
session: dict = Depends(require_auth),
|
||||
):
|
||||
"""
|
||||
Universal-CSV-Import: Zielmodul kommt aus der gewählten Vorlage (`mapping_id`).
|
||||
Optional `module` dient nur der Absicherung (muss mit Vorlage übereinstimmen).
|
||||
"""
|
||||
pid = get_pid(x_profile_id)
|
||||
|
||||
access_di = check_feature_access(pid, "data_import")
|
||||
log_feature_usage(pid, "data_import", access_di, "csv_universal_import")
|
||||
if not access_di["allowed"]:
|
||||
raise HTTPException(
|
||||
403,
|
||||
"Limit erreicht (Daten importieren): "
|
||||
f"{access_di.get('used')}/{access_di.get('limit')}",
|
||||
)
|
||||
|
||||
raw = await file.read()
|
||||
limits = _load_import_limits()
|
||||
max_bytes = limits.get("max_file_bytes", 52_428_800)
|
||||
if len(raw) > max_bytes:
|
||||
raise HTTPException(
|
||||
413,
|
||||
f"Datei zu groß (max. {max_bytes} Bytes laut Systemkonfiguration)",
|
||||
)
|
||||
text = decode_raw_bytes(raw)
|
||||
if not text.strip():
|
||||
raise HTTPException(400, "Leere Datei")
|
||||
max_rows = limits.get("max_rows_per_file", 50_000)
|
||||
if text.count("\n") > max_rows + 5:
|
||||
raise HTTPException(
|
||||
413,
|
||||
f"Zu viele Zeilen (>{max_rows}) laut Systemkonfiguration",
|
||||
)
|
||||
|
||||
log_id: int | None = None
|
||||
err_response: HTTPException | None = None
|
||||
result: dict | None = None
|
||||
resolved_module: str | None = None
|
||||
|
||||
try:
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
m = _fetch_mapping_row(cur, mapping_id, pid, module)
|
||||
exec_module = m["module"]
|
||||
resolved_module = exec_module
|
||||
|
||||
if not get_module_definition(exec_module):
|
||||
raise HTTPException(
|
||||
400,
|
||||
f"Modul der Vorlage wird vom Importer noch nicht unterstützt: {exec_module}",
|
||||
)
|
||||
|
||||
_check_module_feature_access(pid, exec_module)
|
||||
|
||||
cur.execute(
|
||||
"""
|
||||
INSERT INTO csv_import_log (
|
||||
profile_id, mapping_id, module, filename,
|
||||
rows_total, rows_imported, rows_updated, rows_skipped, rows_errors,
|
||||
status, error_details, affected_ids
|
||||
) VALUES (
|
||||
%s::uuid, %s, %s, %s,
|
||||
0, 0, 0, 0, 0,
|
||||
'running', NULL, NULL
|
||||
) RETURNING id
|
||||
""",
|
||||
(pid, mapping_id, exec_module, file.filename or "upload.csv"),
|
||||
)
|
||||
log_id = cur.fetchone()["id"]
|
||||
|
||||
cur.execute("SAVEPOINT csv_import_exec")
|
||||
try:
|
||||
result = run_universal_csv_import(
|
||||
cur,
|
||||
pid,
|
||||
exec_module,
|
||||
text,
|
||||
file.filename or "upload.csv",
|
||||
m,
|
||||
)
|
||||
except Exception as exec_err:
|
||||
logger.exception("Universal-CSV-Import fehlgeschlagen: %s", exec_err)
|
||||
cur.execute("ROLLBACK TO SAVEPOINT csv_import_exec")
|
||||
err_payload = {"error": str(exec_err), **enrich_row_error(str(exec_err), exec_module)}
|
||||
cur.execute(
|
||||
"""
|
||||
UPDATE csv_import_log SET
|
||||
finished_at = CURRENT_TIMESTAMP,
|
||||
status = 'failed',
|
||||
error_details = %s
|
||||
WHERE id = %s
|
||||
""",
|
||||
(Json([err_payload]), log_id),
|
||||
)
|
||||
hint = err_payload.get("hint")
|
||||
msg = f"Import fehlgeschlagen: {exec_err}"
|
||||
if hint:
|
||||
msg = f"{msg} ({hint})"
|
||||
err_response = HTTPException(500, msg)
|
||||
else:
|
||||
cur.execute("RELEASE SAVEPOINT csv_import_exec")
|
||||
cur.execute(
|
||||
"""
|
||||
UPDATE csv_import_log SET
|
||||
finished_at = CURRENT_TIMESTAMP,
|
||||
status = 'success',
|
||||
rows_total = %s,
|
||||
rows_imported = %s,
|
||||
rows_updated = %s,
|
||||
rows_skipped = %s,
|
||||
rows_errors = %s,
|
||||
error_details = %s,
|
||||
affected_ids = %s
|
||||
WHERE id = %s
|
||||
""",
|
||||
(
|
||||
result["rows_total"],
|
||||
result["rows_imported"],
|
||||
result["rows_updated"],
|
||||
result["rows_skipped"],
|
||||
result["rows_errors"],
|
||||
Json(result["error_details"]),
|
||||
Json(result["affected_ids"]),
|
||||
log_id,
|
||||
),
|
||||
)
|
||||
|
||||
cur.execute(
|
||||
"""
|
||||
UPDATE csv_field_mappings SET
|
||||
usage_count = usage_count + 1,
|
||||
last_used_at = CURRENT_TIMESTAMP,
|
||||
updated_at = CURRENT_TIMESTAMP
|
||||
WHERE id = %s
|
||||
""",
|
||||
(mapping_id,),
|
||||
)
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
|
||||
if err_response:
|
||||
raise err_response
|
||||
|
||||
assert result is not None
|
||||
|
||||
increment_feature_usage(pid, "data_import")
|
||||
|
||||
ne = result.get("new_entries", result["rows_imported"])
|
||||
if resolved_module == "nutrition":
|
||||
for _ in range(ne):
|
||||
increment_feature_usage(pid, "nutrition_entries")
|
||||
elif resolved_module == "weight":
|
||||
for _ in range(ne):
|
||||
increment_feature_usage(pid, "weight_entries")
|
||||
elif resolved_module == "activity":
|
||||
for _ in range(ne):
|
||||
increment_feature_usage(pid, "activity_entries")
|
||||
|
||||
return {
|
||||
"success": True,
|
||||
"import_log_id": log_id,
|
||||
"module": resolved_module,
|
||||
"stats": {
|
||||
"total_rows": result["rows_total"],
|
||||
"imported": result["rows_imported"],
|
||||
"updated": result["rows_updated"],
|
||||
"skipped": result["rows_skipped"],
|
||||
"errors": result["rows_errors"],
|
||||
},
|
||||
"error_details": result["error_details"],
|
||||
}
|
||||
@@ -22,6 +22,8 @@ from auth import require_auth, check_feature_access, increment_feature_usage
|
||||
from routers.profiles import get_pid
|
||||
from feature_logger import log_feature_usage
|
||||
from caliper_composition import enrich_caliper_row_for_response, load_weight_rows
|
||||
from data_layer.activity_session_metrics import enrich_sessions_with_metrics
|
||||
from data_layer.utils import serialize_dates
|
||||
|
||||
router = APIRouter(prefix="/api/export", tags=["export"])
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -90,10 +92,23 @@ def export_csv(x_profile_id: Optional[str]=Header(default=None), session: dict=D
|
||||
for r in cur.fetchall():
|
||||
writer.writerow(["Ernährung", r['date'], f"{float(r['kcal'])}kcal", f"Protein:{float(r['protein_g'])}g"])
|
||||
|
||||
# Activity
|
||||
cur.execute("SELECT date, activity_type, duration_min, kcal_active FROM activity_log WHERE profile_id=%s ORDER BY date", (pid,))
|
||||
for r in cur.fetchall():
|
||||
writer.writerow(["Training", r['date'], r['activity_type'], f"{float(r['duration_min'])}min {float(r['kcal_active'])}kcal"])
|
||||
# Activity (Layer-1: gemergte session_metrics in Details)
|
||||
cur.execute(
|
||||
"SELECT id, date, activity_type, duration_min, kcal_active FROM activity_log WHERE profile_id=%s ORDER BY date",
|
||||
(pid,),
|
||||
)
|
||||
act_rows = [r2d(r) for r in cur.fetchall()]
|
||||
enrich_sessions_with_metrics(cur, act_rows)
|
||||
for r in act_rows:
|
||||
base = f"{float(r['duration_min'])}min {float(r['kcal_active'])}kcal"
|
||||
eav_parts = []
|
||||
for m in r.get("session_metrics") or []:
|
||||
k, v = m.get("key"), m.get("value")
|
||||
if k is None or v is None:
|
||||
continue
|
||||
eav_parts.append(f"{k}={v}")
|
||||
details = base + (" | " + "; ".join(eav_parts) if eav_parts else "")
|
||||
writer.writerow(["Training", r["date"], r["activity_type"], details])
|
||||
|
||||
output.seek(0)
|
||||
|
||||
@@ -148,7 +163,9 @@ def export_json(x_profile_id: Optional[str]=Header(default=None), session: dict=
|
||||
data['nutrition'] = [r2d(r) for r in cur.fetchall()]
|
||||
|
||||
cur.execute("SELECT * FROM activity_log WHERE profile_id=%s ORDER BY date", (pid,))
|
||||
data['activity'] = [r2d(r) for r in cur.fetchall()]
|
||||
data["activity"] = [r2d(r) for r in cur.fetchall()]
|
||||
enrich_sessions_with_metrics(cur, data["activity"])
|
||||
data["activity"] = serialize_dates(data["activity"])
|
||||
|
||||
cur.execute("SELECT * FROM ai_insights WHERE profile_id=%s ORDER BY created DESC", (pid,))
|
||||
data['insights'] = [r2d(r) for r in cur.fetchall()]
|
||||
@@ -243,6 +260,9 @@ Dieser Export kann in Mitai Jinkendo unter
|
||||
Einstellungen → Import → "Mitai Backup importieren"
|
||||
wieder eingespielt werden.
|
||||
|
||||
activity.csv (optional): Spalte session_metrics_json (JSON-Array, Layer-1-merge)
|
||||
wird beim Standard-Import ignoriert; für Vollständigkeit/externe Tools.
|
||||
|
||||
Format-Version 2 (ab v9b):
|
||||
Alle CSV-Dateien sind UTF-8 mit BOM kodiert.
|
||||
Trennzeichen: Semikolon (;)
|
||||
@@ -318,13 +338,41 @@ Datumsformat: YYYY-MM-DD
|
||||
r['fiber'] = None; r['note'] = ''
|
||||
write_csv(zf, "nutrition.csv", rows, ['id','date','meal_name','kcal','protein','fat','carbs','fiber','note','source','created'])
|
||||
|
||||
cur.execute("SELECT id, date, activity_type, duration_min, kcal_active, hr_avg, hr_max, distance_km, notes, source, created FROM activity_log WHERE profile_id=%s ORDER BY date", (pid,))
|
||||
cur.execute(
|
||||
"SELECT id, date, activity_type, duration_min, kcal_active, hr_avg, hr_max, distance_km, notes, source, created FROM activity_log WHERE profile_id=%s ORDER BY date",
|
||||
(pid,),
|
||||
)
|
||||
rows = [r2d(r) for r in cur.fetchall()]
|
||||
enrich_sessions_with_metrics(cur, rows)
|
||||
for r in rows:
|
||||
r['name'] = r['activity_type']; r['type'] = r.pop('activity_type', None)
|
||||
r['kcal'] = r.pop('kcal_active', None); r['heart_rate_avg'] = r.pop('hr_avg', None)
|
||||
r['heart_rate_max'] = r.pop('hr_max', None); r['note'] = r.pop('notes', None)
|
||||
write_csv(zf, "activity.csv", rows, ['id','date','name','type','duration_min','kcal','heart_rate_avg','heart_rate_max','distance_km','note','source','created'])
|
||||
sm = r.pop("session_metrics", None) or []
|
||||
r["session_metrics_json"] = json.dumps(sm, ensure_ascii=False, default=str)
|
||||
r["name"] = r["activity_type"]
|
||||
r["type"] = r.pop("activity_type", None)
|
||||
r["kcal"] = r.pop("kcal_active", None)
|
||||
r["heart_rate_avg"] = r.pop("hr_avg", None)
|
||||
r["heart_rate_max"] = r.pop("hr_max", None)
|
||||
r["note"] = r.pop("notes", None)
|
||||
write_csv(
|
||||
zf,
|
||||
"activity.csv",
|
||||
rows,
|
||||
[
|
||||
"id",
|
||||
"date",
|
||||
"name",
|
||||
"type",
|
||||
"duration_min",
|
||||
"kcal",
|
||||
"heart_rate_avg",
|
||||
"heart_rate_max",
|
||||
"distance_km",
|
||||
"note",
|
||||
"source",
|
||||
"created",
|
||||
"session_metrics_json",
|
||||
],
|
||||
)
|
||||
|
||||
# 8. insights/ai_insights.json
|
||||
cur.execute("SELECT id, scope, content, created FROM ai_insights WHERE profile_id=%s ORDER BY created DESC", (pid,))
|
||||
|
||||
@@ -699,6 +699,12 @@ def get_goals_grouped(session: dict = Depends(require_auth)):
|
||||
grouped[cat] = []
|
||||
|
||||
goal_dict = r2d(goal)
|
||||
# Keep in sync with GET /goals/list: derive current_value & progress from live data
|
||||
try:
|
||||
_update_goal_progress(conn, pid, goal_dict)
|
||||
except Exception as e:
|
||||
print(f"[ERROR] Failed to update progress for goal {goal_dict.get('id')}: {e}")
|
||||
|
||||
goal_dict['focus_contributions'] = focus_map.get(goal['id'], [])
|
||||
grouped[cat].append(goal_dict)
|
||||
|
||||
|
||||
+474
-172
@@ -12,15 +12,16 @@ from fastapi import APIRouter, Depends, HTTPException, Query, Header
|
||||
from fastapi.responses import StreamingResponse
|
||||
|
||||
from db import get_db, get_cursor, r2d
|
||||
from auth import require_auth, require_admin
|
||||
from auth import require_auth, require_admin, require_auth_flexible
|
||||
from models import (
|
||||
PromptCreate, PromptUpdate, PromptGenerateRequest,
|
||||
PipelineConfigCreate, PipelineConfigUpdate
|
||||
)
|
||||
from prompt_executor import resolve_placeholders as resolve_prompt_placeholders
|
||||
from placeholder_resolver import (
|
||||
resolve_placeholders,
|
||||
get_unknown_placeholders,
|
||||
get_placeholder_example_values,
|
||||
format_value_with_d_modifier,
|
||||
get_available_placeholders,
|
||||
get_placeholder_catalog
|
||||
)
|
||||
@@ -31,6 +32,42 @@ OPENROUTER_MODEL = os.getenv("OPENROUTER_MODEL", "anthropic/claude-sonnet-4")
|
||||
|
||||
router = APIRouter(prefix="/api/prompts", tags=["prompts"])
|
||||
|
||||
# Metadaten-Schlüssel in workflow aggregate_results (nicht als „einziger“ Nutzer-Output)
|
||||
_WORKFLOW_AGG_META_KEYS = frozenset({
|
||||
"combined_analysis",
|
||||
"all_signals",
|
||||
"total_nodes",
|
||||
"executed_nodes",
|
||||
"failed_nodes",
|
||||
"skipped_nodes",
|
||||
})
|
||||
|
||||
|
||||
def _workflow_user_facing_content(agg: object) -> str:
|
||||
"""
|
||||
Nutzer-sichtbarer Text wie im Admin WorkflowResultViewer („Final Output“):
|
||||
primär aggregated_result['analysis_core'], nicht das gesamte JSON.
|
||||
"""
|
||||
if agg is None:
|
||||
return ""
|
||||
if isinstance(agg, str):
|
||||
return agg
|
||||
if not isinstance(agg, dict):
|
||||
return json.dumps(agg, ensure_ascii=False)
|
||||
core = agg.get("analysis_core")
|
||||
if isinstance(core, str) and core.strip():
|
||||
return core
|
||||
combined = agg.get("combined_analysis")
|
||||
if isinstance(combined, str) and combined.strip():
|
||||
return combined
|
||||
non_meta = [k for k in agg.keys() if k not in _WORKFLOW_AGG_META_KEYS]
|
||||
if len(non_meta) == 1:
|
||||
v = agg[non_meta[0]]
|
||||
if isinstance(v, str):
|
||||
return v
|
||||
return json.dumps(v, ensure_ascii=False)
|
||||
return json.dumps(agg, ensure_ascii=False)
|
||||
|
||||
|
||||
@router.get("")
|
||||
def list_prompts(session: dict=Depends(require_auth)):
|
||||
@@ -67,6 +104,328 @@ def list_placeholders_endpoint(session: dict=Depends(require_auth)):
|
||||
return get_placeholder_catalog(profile_id)
|
||||
|
||||
|
||||
@router.get("/export-all")
|
||||
def export_all_prompts(session: dict = Depends(require_admin)):
|
||||
"""
|
||||
Export all prompts as JSON array.
|
||||
Admin only. Used for backup and dev→prod sync.
|
||||
|
||||
IMPORTANT: Must be defined BEFORE /{prompt_id} route to avoid routing conflict.
|
||||
"""
|
||||
from datetime import datetime
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute("SELECT * FROM ai_prompts ORDER BY sort_order, slug")
|
||||
prompts = [r2d(row) for row in cur.fetchall()]
|
||||
|
||||
# Convert to export format (clean up DB-specific fields)
|
||||
export_data = []
|
||||
for p in prompts:
|
||||
export_item = {
|
||||
'slug': p['slug'],
|
||||
'name': p['name'],
|
||||
'display_name': p.get('display_name'),
|
||||
'description': p.get('description'),
|
||||
'type': p.get('type', 'pipeline'),
|
||||
'category': p.get('category', 'ganzheitlich'),
|
||||
'template': p.get('template'),
|
||||
'stages': p.get('stages'),
|
||||
'output_format': p.get('output_format', 'text'),
|
||||
'output_schema': p.get('output_schema'),
|
||||
'question_augmentations': p.get('question_augmentations'),
|
||||
'graph_data': p.get('graph_data'),
|
||||
'active': p.get('active', True),
|
||||
'sort_order': p.get('sort_order', 0)
|
||||
}
|
||||
export_data.append(export_item)
|
||||
|
||||
return {
|
||||
'export_date': datetime.now().isoformat(),
|
||||
'count': len(export_data),
|
||||
'prompts': export_data
|
||||
}
|
||||
|
||||
|
||||
@router.post("/import")
|
||||
def import_prompts(
|
||||
data: dict,
|
||||
overwrite: bool = False,
|
||||
session: dict = Depends(require_admin)
|
||||
):
|
||||
"""
|
||||
Import prompts from JSON export.
|
||||
|
||||
Args:
|
||||
data: Export data from /export-all endpoint
|
||||
overwrite: If true, update existing prompts. If false, skip duplicates.
|
||||
|
||||
Returns:
|
||||
Summary of import results (created, updated, skipped)
|
||||
|
||||
IMPORTANT: Must be defined BEFORE /{prompt_id} route to avoid routing conflict.
|
||||
"""
|
||||
if 'prompts' not in data:
|
||||
raise HTTPException(400, "Invalid import data: missing 'prompts' key")
|
||||
|
||||
prompts = data['prompts']
|
||||
created = 0
|
||||
updated = 0
|
||||
skipped = 0
|
||||
errors = []
|
||||
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
|
||||
for p in prompts:
|
||||
slug = p.get('slug')
|
||||
if not slug:
|
||||
errors.append('Prompt without slug skipped')
|
||||
continue
|
||||
|
||||
# Check if exists
|
||||
cur.execute("SELECT id FROM ai_prompts WHERE slug=%s", (slug,))
|
||||
existing = cur.fetchone()
|
||||
|
||||
if existing and not overwrite:
|
||||
skipped += 1
|
||||
continue
|
||||
|
||||
# Prepare JSON fields if present
|
||||
stages_json = None
|
||||
if p.get('stages'):
|
||||
stages_json = json.dumps(p['stages']) if isinstance(p['stages'], list) else p['stages']
|
||||
|
||||
output_schema_json = None
|
||||
if p.get('output_schema'):
|
||||
output_schema_json = json.dumps(p['output_schema']) if isinstance(p['output_schema'], dict) else p['output_schema']
|
||||
|
||||
question_aug_json = None
|
||||
if p.get('question_augmentations'):
|
||||
question_aug_json = json.dumps(p['question_augmentations']) if isinstance(p['question_augmentations'], (dict, list)) else p['question_augmentations']
|
||||
|
||||
graph_data_json = None
|
||||
if p.get('graph_data'):
|
||||
graph_data_json = json.dumps(p['graph_data']) if isinstance(p['graph_data'], dict) else p['graph_data']
|
||||
|
||||
if existing:
|
||||
# Update existing
|
||||
cur.execute("""
|
||||
UPDATE ai_prompts SET
|
||||
name=%s, display_name=%s, description=%s, type=%s,
|
||||
category=%s, template=%s, stages=%s, output_format=%s,
|
||||
output_schema=%s, question_augmentations=%s, graph_data=%s,
|
||||
active=%s, sort_order=%s,
|
||||
updated=CURRENT_TIMESTAMP
|
||||
WHERE slug=%s
|
||||
""", (
|
||||
p.get('name'), p.get('display_name'), p.get('description'),
|
||||
p.get('type', 'pipeline'), p.get('category', 'ganzheitlich'),
|
||||
p.get('template'), stages_json, p.get('output_format', 'text'),
|
||||
output_schema_json, question_aug_json, graph_data_json,
|
||||
p.get('active', True), p.get('sort_order', 0), slug
|
||||
))
|
||||
updated += 1
|
||||
else:
|
||||
# Create new
|
||||
cur.execute("""
|
||||
INSERT INTO ai_prompts (
|
||||
slug, name, display_name, description, type, category,
|
||||
template, stages, output_format, output_schema,
|
||||
question_augmentations, graph_data,
|
||||
active, sort_order, created, updated
|
||||
) VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,CURRENT_TIMESTAMP,CURRENT_TIMESTAMP)
|
||||
""", (
|
||||
slug, p.get('name'), p.get('display_name'), p.get('description'),
|
||||
p.get('type', 'pipeline'), p.get('category', 'ganzheitlich'),
|
||||
p.get('template'), stages_json, p.get('output_format', 'text'),
|
||||
output_schema_json, question_aug_json, graph_data_json,
|
||||
p.get('active', True), p.get('sort_order', 0)
|
||||
))
|
||||
created += 1
|
||||
|
||||
conn.commit()
|
||||
|
||||
return {
|
||||
'success': True,
|
||||
'created': created,
|
||||
'updated': updated,
|
||||
'skipped': skipped,
|
||||
'errors': errors if errors else None
|
||||
}
|
||||
|
||||
|
||||
# ══════════════════════════════════════════════════════════════════════════════
|
||||
# UNIFIED PROMPT SYSTEM (Issue #28 Phase 2)
|
||||
# ══════════════════════════════════════════════════════════════════════════════
|
||||
|
||||
from prompt_executor import execute_prompt_with_data
|
||||
from models import UnifiedPromptCreate, UnifiedPromptUpdate
|
||||
|
||||
|
||||
@router.get("/execute-stream")
|
||||
async def execute_unified_prompt_stream(
|
||||
prompt_slug: str = Query(..., description="Slug of prompt to execute"),
|
||||
debug: bool = Query(False, description="Include debug information (node_states, etc.)"),
|
||||
save: bool = Query(False, description="Save result to ai_insights"),
|
||||
session: dict = Depends(require_auth_flexible)
|
||||
):
|
||||
"""
|
||||
Execute a unified prompt with Server-Sent Events (SSE) streaming.
|
||||
|
||||
Returns live progress updates during workflow execution:
|
||||
- execution_started: Workflow has begun
|
||||
- node_complete: Each node completes
|
||||
- workflow_graph_finished: Workflow-Graph fertig (Zwischen-Info, kein Endergebnis)
|
||||
- execution_complete: Endergebnis (wie POST /execute, Feld result)
|
||||
- execution_failed: Error occurred
|
||||
|
||||
Use this endpoint for long-running workflows (>30s) to avoid gateway timeouts.
|
||||
"""
|
||||
profile_id = session['profile_id']
|
||||
|
||||
# Use default modules/timeframes (SSE doesn't support complex params)
|
||||
modules = {
|
||||
'körper': True,
|
||||
'ernährung': True,
|
||||
'training': True,
|
||||
'schlaf': True,
|
||||
'vitalwerte': True
|
||||
}
|
||||
|
||||
timeframes = {
|
||||
'körper': 30,
|
||||
'ernährung': 30,
|
||||
'training': 14,
|
||||
'schlaf': 14,
|
||||
'vitalwerte': 7
|
||||
}
|
||||
|
||||
# Wrapper function for OpenRouter calls
|
||||
async def workflow_llm_call(prompt: str, model: str = None) -> str:
|
||||
return await call_openrouter(prompt)
|
||||
|
||||
# SSE Event Generator
|
||||
async def event_stream():
|
||||
"""Generate Server-Sent Events during workflow execution."""
|
||||
import asyncio
|
||||
from asyncio import Queue
|
||||
|
||||
# Event queue for progress updates
|
||||
event_queue = Queue()
|
||||
|
||||
# Flag to track execution completion
|
||||
execution_complete = False
|
||||
|
||||
# Define progress callback for streaming updates
|
||||
async def progress_callback(event_type: str, data: dict):
|
||||
"""Queue SSE event for streaming to client."""
|
||||
event_data = {
|
||||
"type": event_type,
|
||||
**data
|
||||
}
|
||||
await event_queue.put(event_data)
|
||||
|
||||
# Start workflow execution in background task
|
||||
async def execute_workflow_async():
|
||||
nonlocal execution_complete
|
||||
try:
|
||||
# Execute workflow with progress callbacks
|
||||
result = await execute_prompt_with_data(
|
||||
prompt_slug=prompt_slug,
|
||||
profile_id=profile_id,
|
||||
modules=modules,
|
||||
timeframes=timeframes,
|
||||
openrouter_call_func=workflow_llm_call,
|
||||
enable_debug=debug or save,
|
||||
progress_callback=progress_callback
|
||||
)
|
||||
|
||||
# Save to ai_insights if requested (same logic as /execute)
|
||||
if save:
|
||||
if result['type'] == 'pipeline':
|
||||
final_output = result.get('output', {})
|
||||
if isinstance(final_output, dict) and len(final_output) == 1:
|
||||
content = list(final_output.values())[0]
|
||||
else:
|
||||
content = json.dumps(final_output, ensure_ascii=False)
|
||||
elif result['type'] == 'workflow':
|
||||
content = _workflow_user_facing_content(result.get('aggregated_result'))
|
||||
else:
|
||||
content = result.get('output', '')
|
||||
if isinstance(content, dict):
|
||||
content = json.dumps(content, ensure_ascii=False)
|
||||
|
||||
# Save to database (minimal metadata for now)
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute(
|
||||
"""INSERT INTO ai_insights (profile_id, scope, content, metadata, created)
|
||||
VALUES (%s, %s, %s, %s, CURRENT_TIMESTAMP)""",
|
||||
(profile_id, prompt_slug, content, json.dumps({"prompt_type": result['type']}))
|
||||
)
|
||||
conn.commit()
|
||||
|
||||
# Pflicht für alle Prompt-Typen: Pipeline/Base rufen keinen progress_callback
|
||||
# mit Abschluss auf — ohne dieses Event endet SSE ohne resolve → „Connection to server lost“.
|
||||
try:
|
||||
sse_payload = json.loads(json.dumps(result, default=str))
|
||||
except (TypeError, ValueError):
|
||||
sse_payload = {
|
||||
"type": result.get("type", "unknown"),
|
||||
"error": "result_not_serializable",
|
||||
}
|
||||
await event_queue.put({
|
||||
"type": "execution_complete",
|
||||
"result": sse_payload,
|
||||
})
|
||||
|
||||
except Exception as e:
|
||||
# Queue error event
|
||||
await event_queue.put({
|
||||
"type": "execution_failed",
|
||||
"error": str(e)
|
||||
})
|
||||
finally:
|
||||
execution_complete = True
|
||||
|
||||
# Start workflow execution in background
|
||||
import asyncio
|
||||
execution_task = asyncio.create_task(execute_workflow_async())
|
||||
|
||||
# Stream events from queue
|
||||
try:
|
||||
while not execution_complete or not event_queue.empty():
|
||||
try:
|
||||
# Wait for event with timeout
|
||||
event = await asyncio.wait_for(event_queue.get(), timeout=0.5)
|
||||
yield f"data: {json.dumps(event, ensure_ascii=False)}\n\n"
|
||||
except asyncio.TimeoutError:
|
||||
# Send keepalive ping
|
||||
yield f": keepalive\n\n"
|
||||
continue
|
||||
|
||||
# Wait for execution task to complete
|
||||
await execution_task
|
||||
|
||||
except Exception as e:
|
||||
# Send final error event
|
||||
error_event = {
|
||||
"type": "execution_failed",
|
||||
"error": str(e)
|
||||
}
|
||||
yield f"data: {json.dumps(error_event, ensure_ascii=False)}\n\n"
|
||||
|
||||
return StreamingResponse(
|
||||
event_stream(),
|
||||
media_type="text/event-stream",
|
||||
headers={
|
||||
"Cache-Control": "no-cache",
|
||||
"Connection": "keep-alive",
|
||||
"X-Accel-Buffering": "no" # Disable nginx buffering
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
@router.get("/{prompt_id}")
|
||||
def get_prompt(prompt_id: str, session: dict=Depends(require_auth)):
|
||||
"""Get single AI prompt by ID (UUID)."""
|
||||
@@ -178,11 +537,31 @@ def duplicate_prompt(prompt_id: str, session: dict=Depends(require_admin)):
|
||||
|
||||
new_display_name = f"{original.get('display_name') or original['name']} (Kopie)"
|
||||
|
||||
# Prepare JSONB fields (convert dict/list to JSON string if needed)
|
||||
stages_json = json.dumps(original['stages']) if original.get('stages') else None
|
||||
output_schema_json = json.dumps(original['output_schema']) if original.get('output_schema') else None
|
||||
question_aug_json = json.dumps(original['question_augmentations']) if original.get('question_augmentations') else None
|
||||
graph_data_json = json.dumps(original['graph_data']) if original.get('graph_data') else None
|
||||
|
||||
cur.execute(
|
||||
"""INSERT INTO ai_prompts (id, name, slug, display_name, description, template, category, active, sort_order, created, updated)
|
||||
VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, CURRENT_TIMESTAMP, CURRENT_TIMESTAMP)""",
|
||||
(new_id, new_name, new_slug, new_display_name, original['description'], original['template'],
|
||||
original.get('category', 'ganzheitlich'), original['active'], original['sort_order'])
|
||||
"""INSERT INTO ai_prompts (
|
||||
id, name, slug, display_name, description, template, category,
|
||||
type, stages, output_format, output_schema,
|
||||
question_augmentations, graph_data,
|
||||
active, sort_order, created, updated
|
||||
) VALUES (
|
||||
%s, %s, %s, %s, %s, %s, %s,
|
||||
%s, %s, %s, %s,
|
||||
%s, %s,
|
||||
%s, %s, CURRENT_TIMESTAMP, CURRENT_TIMESTAMP
|
||||
)""",
|
||||
(new_id, new_name, new_slug, new_display_name,
|
||||
original.get('description'), original.get('template'),
|
||||
original.get('category', 'ganzheitlich'),
|
||||
original.get('type', 'pipeline'), stages_json,
|
||||
original.get('output_format', 'text'), output_schema_json,
|
||||
question_aug_json, graph_data_json,
|
||||
original.get('active', True), original.get('sort_order', 0))
|
||||
)
|
||||
|
||||
return {"id": new_id, "slug": new_slug, "name": new_name}
|
||||
@@ -225,7 +604,13 @@ def preview_prompt(data: dict, session: dict=Depends(require_auth)):
|
||||
template = data.get('template', '')
|
||||
profile_id = session['profile_id']
|
||||
|
||||
resolved = resolve_placeholders(template, profile_id)
|
||||
catalog = get_placeholder_catalog(profile_id)
|
||||
processed = get_placeholder_example_values(profile_id)
|
||||
variables = {
|
||||
k.replace('{{', '').replace('}}', ''): v
|
||||
for k, v in processed.items()
|
||||
}
|
||||
resolved = resolve_prompt_placeholders(template, variables, None, catalog)
|
||||
unknown = get_unknown_placeholders(template)
|
||||
|
||||
return {
|
||||
@@ -251,8 +636,8 @@ def export_placeholder_values(session: dict = Depends(require_auth)):
|
||||
"""
|
||||
Export all available placeholders with their current resolved values.
|
||||
|
||||
Returns JSON export suitable for download with all placeholders
|
||||
resolved for the current user's profile.
|
||||
Pro Zeile: value = {{key}}, example = Vorschau {{key|d}} (Wert — description),
|
||||
ai_caption = Text für {{key|x}} (Erklärung ohne Wert). JSON für das aktive Profil.
|
||||
"""
|
||||
from datetime import datetime
|
||||
profile_id = session['profile_id']
|
||||
@@ -280,12 +665,16 @@ def export_placeholder_values(session: dict = Depends(require_auth)):
|
||||
export_data['placeholders_by_category'][category] = []
|
||||
for item in items:
|
||||
key = item['key'].replace('{{', '').replace('}}', '')
|
||||
export_data['placeholders_by_category'][category].append({
|
||||
raw_val = cleaned_values.get(key, 'nicht verfügbar')
|
||||
row = {
|
||||
'key': item['key'],
|
||||
'description': item['description'],
|
||||
'value': cleaned_values.get(key, 'nicht verfügbar'),
|
||||
'example': item.get('example')
|
||||
})
|
||||
'value': raw_val,
|
||||
'example': format_value_with_d_modifier(str(raw_val), item),
|
||||
}
|
||||
if item.get('ai_caption'):
|
||||
row['ai_caption'] = item['ai_caption']
|
||||
export_data['placeholders_by_category'][category].append(row)
|
||||
|
||||
# Also include flat list for easy access
|
||||
export_data['all_placeholders'] = cleaned_values
|
||||
@@ -377,8 +766,14 @@ def export_placeholder_values_extended(
|
||||
if 'value_raw' not in metadata.unresolved_fields:
|
||||
metadata.unresolved_fields.append('value_raw')
|
||||
|
||||
# Check availability
|
||||
if value in ['nicht verfügbar', 'nicht genug Daten', '[Fehler:', '[Nicht']:
|
||||
# Check availability (Resolver liefert oft „nicht verfügbar — <Grund>“)
|
||||
sv = str(value)
|
||||
if (
|
||||
sv in ['nicht verfügbar', 'nicht genug Daten']
|
||||
or sv.startswith('nicht verfügbar —')
|
||||
or sv.startswith('[Fehler:')
|
||||
or sv.startswith('[Nicht')
|
||||
):
|
||||
metadata.available = False
|
||||
metadata.missing_reason = value
|
||||
else:
|
||||
@@ -447,11 +842,12 @@ def export_placeholder_values_extended(
|
||||
export_data['legacy']['placeholders_by_category'][category] = []
|
||||
for item in items:
|
||||
key = item['key'].replace('{{', '').replace('}}', '')
|
||||
raw_val = cleaned_values.get(key, 'nicht verfügbar')
|
||||
export_data['legacy']['placeholders_by_category'][category].append({
|
||||
'key': item['key'],
|
||||
'description': item['description'],
|
||||
'value': cleaned_values.get(key, 'nicht verfügbar'),
|
||||
'example': item.get('example')
|
||||
'value': raw_val,
|
||||
'example': format_value_with_d_modifier(str(raw_val), item),
|
||||
})
|
||||
|
||||
# Fill metadata flat
|
||||
@@ -713,27 +1109,60 @@ def export_placeholder_catalog_zip(
|
||||
|
||||
# ── KI-Assisted Prompt Engineering ───────────────────────────────────────────
|
||||
|
||||
async def call_openrouter(prompt: str, max_tokens: int = 1500) -> str:
|
||||
async def call_openrouter(prompt: str, max_tokens: int = 4096) -> str:
|
||||
"""Call OpenRouter API to get AI response."""
|
||||
if not OPENROUTER_KEY:
|
||||
raise HTTPException(status_code=500, detail="OpenRouter API key not configured")
|
||||
|
||||
async with httpx.AsyncClient() as client:
|
||||
resp = await client.post(
|
||||
"https://openrouter.ai/api/v1/chat/completions",
|
||||
headers={"Authorization": f"Bearer {OPENROUTER_KEY}"},
|
||||
json={
|
||||
"model": OPENROUTER_MODEL,
|
||||
"messages": [{"role": "user", "content": prompt}],
|
||||
"max_tokens": max_tokens
|
||||
},
|
||||
timeout=60.0
|
||||
try:
|
||||
async with httpx.AsyncClient() as client:
|
||||
resp = await client.post(
|
||||
"https://openrouter.ai/api/v1/chat/completions",
|
||||
headers={"Authorization": f"Bearer {OPENROUTER_KEY}"},
|
||||
json={
|
||||
"model": OPENROUTER_MODEL,
|
||||
"messages": [{"role": "user", "content": prompt}],
|
||||
"max_tokens": max_tokens
|
||||
},
|
||||
timeout=120.0
|
||||
)
|
||||
except httpx.TimeoutException as e:
|
||||
raise HTTPException(status_code=504, detail=f"OpenRouter-Zeitüberschreitung: {e}") from e
|
||||
except httpx.RequestError as e:
|
||||
raise HTTPException(status_code=502, detail=f"OpenRouter-Verbindungsfehler: {e}") from e
|
||||
|
||||
if resp.status_code != 200:
|
||||
raise HTTPException(
|
||||
status_code=resp.status_code,
|
||||
detail=f"OpenRouter API error ({resp.status_code}): {resp.text[:2000]}",
|
||||
)
|
||||
|
||||
if resp.status_code != 200:
|
||||
raise HTTPException(status_code=resp.status_code, detail=f"OpenRouter API error: {resp.text}")
|
||||
try:
|
||||
data = resp.json()
|
||||
except json.JSONDecodeError:
|
||||
raise HTTPException(
|
||||
status_code=502,
|
||||
detail=f"OpenRouter lieferte kein JSON: {resp.text[:800]}",
|
||||
)
|
||||
|
||||
return resp.json()['choices'][0]['message']['content'].strip()
|
||||
choices = data.get("choices") or []
|
||||
if not choices:
|
||||
err_snip = json.dumps(data.get("error") or data, ensure_ascii=False)[:1200]
|
||||
raise HTTPException(
|
||||
status_code=502,
|
||||
detail=f"OpenRouter ohne choices in der Antwort: {err_snip}",
|
||||
)
|
||||
|
||||
message = choices[0].get("message") or {}
|
||||
content = message.get("content")
|
||||
if content is None:
|
||||
raise HTTPException(
|
||||
status_code=502,
|
||||
detail="OpenRouter-Antwort ohne message.content (z. B. Tool-Calls oder abweichendes Schema).",
|
||||
)
|
||||
if not isinstance(content, str):
|
||||
content = str(content)
|
||||
return content.strip()
|
||||
|
||||
|
||||
def collect_example_data(profile_id: str, data_categories: list[str]) -> dict:
|
||||
@@ -1180,21 +1609,13 @@ def reset_prompt_to_default(prompt_id: str, session: dict=Depends(require_admin)
|
||||
return {"ok": True}
|
||||
|
||||
|
||||
# ══════════════════════════════════════════════════════════════════════════════
|
||||
# UNIFIED PROMPT SYSTEM (Issue #28 Phase 2)
|
||||
# ══════════════════════════════════════════════════════════════════════════════
|
||||
|
||||
from prompt_executor import execute_prompt_with_data
|
||||
from models import UnifiedPromptCreate, UnifiedPromptUpdate
|
||||
|
||||
|
||||
@router.post("/execute")
|
||||
async def execute_unified_prompt(
|
||||
prompt_slug: str,
|
||||
prompt_slug: str = Query(..., description="Slug of prompt to execute"),
|
||||
modules: Optional[dict] = None,
|
||||
timeframes: Optional[dict] = None,
|
||||
debug: bool = False,
|
||||
save: bool = False,
|
||||
debug: bool = Query(False, description="Include debug information (node_states, etc.)"),
|
||||
save: bool = Query(False, description="Save result to ai_insights"),
|
||||
session: dict = Depends(require_auth)
|
||||
):
|
||||
"""
|
||||
@@ -1231,6 +1652,14 @@ async def execute_unified_prompt(
|
||||
'vitalwerte': 7
|
||||
}
|
||||
|
||||
# Wrapper function to match workflow_executor's expected signature: (prompt, model) -> str
|
||||
# workflow_executor calls: openrouter_call_func(prompt, "anthropic/claude-sonnet-4")
|
||||
# but call_openrouter expects: call_openrouter(prompt, max_tokens=4096)
|
||||
async def workflow_llm_call(prompt: str, model: str = None) -> str:
|
||||
# Ignore model parameter (already set in OPENROUTER_MODEL env var)
|
||||
# Use default max_tokens=4096 from call_openrouter
|
||||
return await call_openrouter(prompt)
|
||||
|
||||
# Execute with prompt_executor
|
||||
# Always enable debug when saving to collect metadata for value table
|
||||
result = await execute_prompt_with_data(
|
||||
@@ -1238,7 +1667,7 @@ async def execute_unified_prompt(
|
||||
profile_id=profile_id,
|
||||
modules=modules,
|
||||
timeframes=timeframes,
|
||||
openrouter_call_func=call_openrouter,
|
||||
openrouter_call_func=workflow_llm_call, # Use wrapper with correct signature
|
||||
enable_debug=debug or save # Enable debug if saving for metadata collection
|
||||
)
|
||||
|
||||
@@ -1253,6 +1682,8 @@ async def execute_unified_prompt(
|
||||
content = list(final_output.values())[0]
|
||||
else:
|
||||
content = json.dumps(final_output, ensure_ascii=False)
|
||||
elif result['type'] == 'workflow':
|
||||
content = _workflow_user_facing_content(result.get('aggregated_result'))
|
||||
else:
|
||||
# For base prompts, use output directly
|
||||
content = result.get('output', '')
|
||||
@@ -1569,132 +2000,3 @@ def update_unified_prompt(prompt_id: str, p: UnifiedPromptUpdate, session: dict
|
||||
)
|
||||
|
||||
return {"ok": True}
|
||||
|
||||
|
||||
@router.get("/export-all")
|
||||
def export_all_prompts(session: dict = Depends(require_admin)):
|
||||
"""
|
||||
Export all prompts as JSON array.
|
||||
Admin only. Used for backup and dev→prod sync.
|
||||
"""
|
||||
from datetime import datetime
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
cur.execute("SELECT * FROM ai_prompts ORDER BY sort_order, slug")
|
||||
prompts = [r2d(row) for row in cur.fetchall()]
|
||||
|
||||
# Convert to export format (clean up DB-specific fields)
|
||||
export_data = []
|
||||
for p in prompts:
|
||||
export_item = {
|
||||
'slug': p['slug'],
|
||||
'name': p['name'],
|
||||
'display_name': p.get('display_name'),
|
||||
'description': p.get('description'),
|
||||
'type': p.get('type', 'pipeline'),
|
||||
'category': p.get('category', 'ganzheitlich'),
|
||||
'template': p.get('template'),
|
||||
'stages': p.get('stages'),
|
||||
'output_format': p.get('output_format', 'text'),
|
||||
'output_schema': p.get('output_schema'),
|
||||
'active': p.get('active', True),
|
||||
'sort_order': p.get('sort_order', 0)
|
||||
}
|
||||
export_data.append(export_item)
|
||||
|
||||
return {
|
||||
'export_date': datetime.now().isoformat(),
|
||||
'count': len(export_data),
|
||||
'prompts': export_data
|
||||
}
|
||||
|
||||
|
||||
@router.post("/import")
|
||||
def import_prompts(
|
||||
data: dict,
|
||||
overwrite: bool = False,
|
||||
session: dict = Depends(require_admin)
|
||||
):
|
||||
"""
|
||||
Import prompts from JSON export.
|
||||
|
||||
Args:
|
||||
data: Export data from /export-all endpoint
|
||||
overwrite: If true, update existing prompts. If false, skip duplicates.
|
||||
|
||||
Returns:
|
||||
Summary of import results (created, updated, skipped)
|
||||
"""
|
||||
if 'prompts' not in data:
|
||||
raise HTTPException(400, "Invalid import data: missing 'prompts' key")
|
||||
|
||||
prompts = data['prompts']
|
||||
created = 0
|
||||
updated = 0
|
||||
skipped = 0
|
||||
errors = []
|
||||
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
|
||||
for p in prompts:
|
||||
slug = p.get('slug')
|
||||
if not slug:
|
||||
errors.append('Prompt without slug skipped')
|
||||
continue
|
||||
|
||||
# Check if exists
|
||||
cur.execute("SELECT id FROM ai_prompts WHERE slug=%s", (slug,))
|
||||
existing = cur.fetchone()
|
||||
|
||||
if existing and not overwrite:
|
||||
skipped += 1
|
||||
continue
|
||||
|
||||
# Prepare stages JSON if present
|
||||
stages_json = None
|
||||
if p.get('stages'):
|
||||
stages_json = json.dumps(p['stages']) if isinstance(p['stages'], list) else p['stages']
|
||||
|
||||
if existing:
|
||||
# Update existing
|
||||
cur.execute("""
|
||||
UPDATE ai_prompts SET
|
||||
name=%s, display_name=%s, description=%s, type=%s,
|
||||
category=%s, template=%s, stages=%s, output_format=%s,
|
||||
output_schema=%s, active=%s, sort_order=%s,
|
||||
updated=CURRENT_TIMESTAMP
|
||||
WHERE slug=%s
|
||||
""", (
|
||||
p.get('name'), p.get('display_name'), p.get('description'),
|
||||
p.get('type', 'pipeline'), p.get('category', 'ganzheitlich'),
|
||||
p.get('template'), stages_json, p.get('output_format', 'text'),
|
||||
p.get('output_schema'), p.get('active', True),
|
||||
p.get('sort_order', 0), slug
|
||||
))
|
||||
updated += 1
|
||||
else:
|
||||
# Create new
|
||||
cur.execute("""
|
||||
INSERT INTO ai_prompts (
|
||||
slug, name, display_name, description, type, category,
|
||||
template, stages, output_format, output_schema,
|
||||
active, sort_order, created, updated
|
||||
) VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,CURRENT_TIMESTAMP,CURRENT_TIMESTAMP)
|
||||
""", (
|
||||
slug, p.get('name'), p.get('display_name'), p.get('description'),
|
||||
p.get('type', 'pipeline'), p.get('category', 'ganzheitlich'),
|
||||
p.get('template'), stages_json, p.get('output_format', 'text'),
|
||||
p.get('output_schema'), p.get('active', True), p.get('sort_order', 0)
|
||||
))
|
||||
created += 1
|
||||
|
||||
conn.commit()
|
||||
|
||||
return {
|
||||
'success': True,
|
||||
'created': created,
|
||||
'updated': updated,
|
||||
'skipped': skipped,
|
||||
'errors': errors if errors else None
|
||||
}
|
||||
+15
-299
@@ -8,186 +8,16 @@ Endpoints:
|
||||
"""
|
||||
from fastapi import APIRouter, Depends, HTTPException, UploadFile, File
|
||||
from pydantic import BaseModel
|
||||
from typing import Literal
|
||||
from datetime import datetime, timedelta, date
|
||||
from decimal import Decimal, InvalidOperation
|
||||
import csv
|
||||
import io
|
||||
import json
|
||||
from typing import Literal
|
||||
|
||||
from auth import require_auth
|
||||
from csv_parser.sleep_apple_import import import_apple_sleep_nights
|
||||
from db import get_db, get_cursor
|
||||
|
||||
router = APIRouter(prefix="/api/sleep", tags=["sleep"])
|
||||
|
||||
|
||||
def _strip_row_keys(row: dict) -> dict:
|
||||
return {(k or "").strip(): (v.strip() if isinstance(v, str) else v) for k, v in row.items()}
|
||||
|
||||
|
||||
def _safe_float(value) -> float | None:
|
||||
if value is None or value == "":
|
||||
return None
|
||||
if isinstance(value, (int, float)):
|
||||
return float(value)
|
||||
if isinstance(value, Decimal):
|
||||
return float(value)
|
||||
try:
|
||||
s = str(value).strip().replace(",", ".")
|
||||
return float(s)
|
||||
except (ValueError, InvalidOperation):
|
||||
return None
|
||||
|
||||
|
||||
def _parse_apple_sleep_datetime(value: str) -> datetime:
|
||||
raw = (value or "").strip()
|
||||
if not raw:
|
||||
raise ValueError("empty datetime")
|
||||
fmts = (
|
||||
"%Y-%m-%d %H:%M:%S %z",
|
||||
"%d.%m.%y %H:%M:%S",
|
||||
"%d.%m.%Y %H:%M:%S",
|
||||
"%Y-%m-%d %H:%M:%S",
|
||||
)
|
||||
last_err = None
|
||||
for fmt in fmts:
|
||||
try:
|
||||
return datetime.strptime(raw, fmt)
|
||||
except ValueError as e:
|
||||
last_err = e
|
||||
raise ValueError(f"Unbekanntes Datumsformat: {raw!r}") from last_err
|
||||
|
||||
|
||||
def _hr_to_minutes(hours: float | None) -> int:
|
||||
if hours is None:
|
||||
return 0
|
||||
return int(round(float(hours) * 60))
|
||||
|
||||
|
||||
def _detect_apple_sleep_csv_format(fieldnames: list[str] | None) -> Literal["segments", "summary"]:
|
||||
if not fieldnames:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail="CSV enthält keine Spaltenüberschriften.",
|
||||
)
|
||||
fn = {(f or "").strip() for f in fieldnames}
|
||||
if {"Start", "End", "Duration (hr)", "Value"}.issubset(fn):
|
||||
return "segments"
|
||||
if "Start" in fn and "End" in fn and "Total Sleep (hr)" in fn:
|
||||
return "summary"
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=(
|
||||
"Unbekanntes Apple-Health-Schlaf-CSV. "
|
||||
"Erwartet wird entweder der Segment-Export (Spalten Start, End, Duration (hr), Value) "
|
||||
"oder die Schlafanalyse mit Nacht-Zusammenfassung (u. a. Total Sleep (hr), Core/Light, Deep, REM)."
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
def _build_nights_from_apple_summary(reader: csv.DictReader) -> dict[date, dict]:
|
||||
nights_dict: dict[date, dict] = {}
|
||||
for raw in reader:
|
||||
row = _strip_row_keys(raw)
|
||||
start_s = row.get("Start") or ""
|
||||
end_s = row.get("End") or ""
|
||||
if not start_s or not end_s:
|
||||
continue
|
||||
try:
|
||||
start_dt = _parse_apple_sleep_datetime(start_s)
|
||||
end_dt = _parse_apple_sleep_datetime(end_s)
|
||||
except ValueError:
|
||||
continue
|
||||
|
||||
dt_key = (row.get("Date/Time") or row.get("Datum/Uhrzeit") or "").strip()
|
||||
if dt_key:
|
||||
try:
|
||||
wake_d = datetime.strptime(dt_key[:10], "%Y-%m-%d").date()
|
||||
except ValueError:
|
||||
wake_d = end_dt.date()
|
||||
else:
|
||||
wake_d = end_dt.date()
|
||||
|
||||
core_hr = _safe_float(row.get("Core (hr)"))
|
||||
if core_hr is None:
|
||||
core_hr = _safe_float(row.get("Light (hr)")) or 0.0
|
||||
deep_min = _hr_to_minutes(_safe_float(row.get("Deep (hr)")))
|
||||
rem_min = _hr_to_minutes(_safe_float(row.get("REM (hr)")))
|
||||
light_min = _hr_to_minutes(core_hr)
|
||||
awake_min = _hr_to_minutes(_safe_float(row.get("Awake (hr)")))
|
||||
nights_dict[wake_d] = {
|
||||
"bedtime": start_dt,
|
||||
"wake_time": end_dt,
|
||||
"segments": [],
|
||||
"deep_minutes": deep_min,
|
||||
"rem_minutes": rem_min,
|
||||
"light_minutes": light_min,
|
||||
"awake_minutes": awake_min,
|
||||
}
|
||||
return nights_dict
|
||||
|
||||
|
||||
def _build_nights_from_apple_segments(reader: csv.DictReader, phase_map: dict) -> dict[date, dict]:
|
||||
segments = []
|
||||
for raw in reader:
|
||||
row = _strip_row_keys(raw)
|
||||
phase_key = (row.get("Value") or "").strip()
|
||||
phase_en = phase_map.get(phase_key)
|
||||
if phase_en is None:
|
||||
continue
|
||||
try:
|
||||
start_dt = _parse_apple_sleep_datetime(row.get("Start") or "")
|
||||
end_dt = _parse_apple_sleep_datetime(row.get("End") or "")
|
||||
duration_hr = _safe_float(row.get("Duration (hr)"))
|
||||
if duration_hr is None:
|
||||
continue
|
||||
except (ValueError, TypeError):
|
||||
continue
|
||||
duration_min = int(duration_hr * 60)
|
||||
segments.append({
|
||||
"start": start_dt,
|
||||
"end": end_dt,
|
||||
"duration_min": duration_min,
|
||||
"phase": phase_en,
|
||||
})
|
||||
|
||||
segments.sort(key=lambda s: s["start"])
|
||||
nights = []
|
||||
current_night = None
|
||||
|
||||
for seg in segments:
|
||||
if current_night is None or (seg["start"] - current_night["wake_time"]).total_seconds() > 7200:
|
||||
current_night = {
|
||||
"bedtime": seg["start"],
|
||||
"wake_time": seg["end"],
|
||||
"segments": [],
|
||||
"deep_minutes": 0,
|
||||
"rem_minutes": 0,
|
||||
"light_minutes": 0,
|
||||
"awake_minutes": 0,
|
||||
}
|
||||
nights.append(current_night)
|
||||
|
||||
current_night["segments"].append(seg)
|
||||
current_night["wake_time"] = max(current_night["wake_time"], seg["end"])
|
||||
current_night["bedtime"] = min(current_night["bedtime"], seg["start"])
|
||||
|
||||
if seg["phase"] == "deep":
|
||||
current_night["deep_minutes"] += seg["duration_min"]
|
||||
elif seg["phase"] == "rem":
|
||||
current_night["rem_minutes"] += seg["duration_min"]
|
||||
elif seg["phase"] == "light":
|
||||
current_night["light_minutes"] += seg["duration_min"]
|
||||
elif seg["phase"] == "awake":
|
||||
current_night["awake_minutes"] += seg["duration_min"]
|
||||
|
||||
nights_dict: dict[date, dict] = {}
|
||||
for night in nights:
|
||||
wake_date = night["wake_time"].date()
|
||||
nights_dict[wake_date] = night
|
||||
return nights_dict
|
||||
|
||||
|
||||
# ── Models ────────────────────────────────────────────────────────────────────
|
||||
|
||||
class SleepCreate(BaseModel):
|
||||
@@ -641,139 +471,25 @@ async def import_apple_health_sleep(
|
||||
pid = session['profile_id']
|
||||
|
||||
content = await file.read()
|
||||
csv_text = content.decode('utf-8-sig')
|
||||
reader = csv.DictReader(io.StringIO(csv_text))
|
||||
fmt = _detect_apple_sleep_csv_format(reader.fieldnames)
|
||||
|
||||
phase_map = {
|
||||
"Kern": "light",
|
||||
"Core": "light",
|
||||
"Light": "light",
|
||||
"REM": "rem",
|
||||
"Tief": "deep",
|
||||
"Deep": "deep",
|
||||
"Wach": "awake",
|
||||
"Awake": "awake",
|
||||
"Schlafend": None,
|
||||
"Asleep": None,
|
||||
"In Bed": None,
|
||||
}
|
||||
|
||||
if fmt == "summary":
|
||||
nights_dict = _build_nights_from_apple_summary(reader)
|
||||
else:
|
||||
nights_dict = _build_nights_from_apple_segments(reader, phase_map)
|
||||
|
||||
if not nights_dict:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail="Keine importierbaren Schlafzeilen gefunden (prüfe Start/Ende und Format).",
|
||||
)
|
||||
|
||||
# Insert nights
|
||||
imported = 0
|
||||
skipped = 0
|
||||
try:
|
||||
csv_text = content.decode("utf-8-sig")
|
||||
except UnicodeDecodeError:
|
||||
csv_text = content.decode("latin-1")
|
||||
|
||||
with get_db() as conn:
|
||||
cur = get_cursor(conn)
|
||||
|
||||
for date, night in nights_dict.items():
|
||||
# Calculate sleep duration (deep + rem + light, WITHOUT awake)
|
||||
# Note: awake_minutes tracked separately, not part of sleep duration
|
||||
duration_minutes = (
|
||||
night['deep_minutes'] +
|
||||
night['rem_minutes'] +
|
||||
night['light_minutes']
|
||||
)
|
||||
|
||||
# Calculate wake_count (number of awake segments)
|
||||
wake_count = sum(1 for seg in night['segments'] if seg['phase'] == 'awake')
|
||||
|
||||
# Prepare JSONB segments with full datetime
|
||||
sleep_segments = [
|
||||
{
|
||||
'phase': seg['phase'],
|
||||
'start': seg['start'].isoformat(), # Full datetime: 2026-03-21T22:30:00
|
||||
'end': seg['end'].isoformat(), # Full datetime: 2026-03-21T23:15:00
|
||||
'duration_min': seg['duration_min']
|
||||
}
|
||||
for seg in night['segments']
|
||||
]
|
||||
|
||||
# Check if manual entry exists - do NOT overwrite
|
||||
cur.execute("""
|
||||
SELECT id, source FROM sleep_log
|
||||
WHERE profile_id = %s AND date = %s
|
||||
""", (pid, date))
|
||||
existing = cur.fetchone()
|
||||
|
||||
if existing and existing['source'] == 'manual':
|
||||
skipped += 1
|
||||
continue # Skip - don't overwrite manual entries
|
||||
|
||||
# Upsert (only if not manual)
|
||||
# If entry exists and is NOT manual → update
|
||||
# If entry doesn't exist → insert
|
||||
if existing:
|
||||
# Update existing non-manual entry
|
||||
cur.execute("""
|
||||
UPDATE sleep_log SET
|
||||
bedtime = %s,
|
||||
wake_time = %s,
|
||||
duration_minutes = %s,
|
||||
wake_count = %s,
|
||||
deep_minutes = %s,
|
||||
rem_minutes = %s,
|
||||
light_minutes = %s,
|
||||
awake_minutes = %s,
|
||||
sleep_segments = %s,
|
||||
source = 'apple_health',
|
||||
updated_at = CURRENT_TIMESTAMP
|
||||
WHERE id = %s AND profile_id = %s
|
||||
""", (
|
||||
night['bedtime'].time(),
|
||||
night['wake_time'].time(),
|
||||
duration_minutes,
|
||||
wake_count,
|
||||
night['deep_minutes'],
|
||||
night['rem_minutes'],
|
||||
night['light_minutes'],
|
||||
night['awake_minutes'],
|
||||
json.dumps(sleep_segments),
|
||||
existing['id'],
|
||||
pid
|
||||
))
|
||||
else:
|
||||
# Insert new entry
|
||||
cur.execute("""
|
||||
INSERT INTO sleep_log (
|
||||
profile_id, date, bedtime, wake_time, duration_minutes,
|
||||
wake_count, deep_minutes, rem_minutes, light_minutes, awake_minutes,
|
||||
sleep_segments, source, created_at, updated_at
|
||||
) VALUES (
|
||||
%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, 'apple_health', CURRENT_TIMESTAMP, CURRENT_TIMESTAMP
|
||||
)
|
||||
""", (
|
||||
pid,
|
||||
date,
|
||||
night['bedtime'].time(),
|
||||
night['wake_time'].time(),
|
||||
duration_minutes,
|
||||
wake_count,
|
||||
night['deep_minutes'],
|
||||
night['rem_minutes'],
|
||||
night['light_minutes'],
|
||||
night['awake_minutes'],
|
||||
json.dumps(sleep_segments)
|
||||
))
|
||||
|
||||
imported += 1
|
||||
|
||||
try:
|
||||
r = import_apple_sleep_nights(cur, pid, csv_text)
|
||||
except ValueError as e:
|
||||
raise HTTPException(status_code=400, detail=str(e))
|
||||
conn.commit()
|
||||
|
||||
imported = r["inserted"] + r["updated"]
|
||||
skipped = r["skipped"]
|
||||
total = r["rows_total"]
|
||||
return {
|
||||
"imported": imported,
|
||||
"skipped": skipped,
|
||||
"total_nights": len(nights_dict),
|
||||
"message": f"{imported} Nächte importiert, {skipped} übersprungen (manuelle Einträge)"
|
||||
"total_nights": total,
|
||||
"message": f"{imported} Nächte importiert, {skipped} übersprungen (manuelle Einträge)",
|
||||
}
|
||||
@@ -86,11 +86,19 @@ async def execute_workflow_endpoint(
|
||||
"type": "workflow"
|
||||
}
|
||||
|
||||
# Wrapper function to match workflow_executor's expected signature: (prompt, model) -> str
|
||||
# workflow_executor calls: openrouter_call_func(prompt, "anthropic/claude-sonnet-4")
|
||||
# but call_openrouter expects: call_openrouter(prompt, max_tokens=4096)
|
||||
async def workflow_llm_call(prompt: str, model: str) -> str:
|
||||
# Ignore model parameter (already set in OPENROUTER_MODEL env var)
|
||||
# Use default max_tokens=4096 from call_openrouter
|
||||
return await call_openrouter(prompt)
|
||||
|
||||
try:
|
||||
result = await execute_workflow_prompt(
|
||||
prompt=workflow_prompt,
|
||||
variables=variables,
|
||||
openrouter_call_func=call_openrouter,
|
||||
openrouter_call_func=workflow_llm_call, # Use wrapper with correct signature
|
||||
enable_debug=request.enable_debug
|
||||
)
|
||||
return result
|
||||
|
||||
+4
-4
@@ -160,10 +160,10 @@ CREATE TABLE IF NOT EXISTS activity_log (
|
||||
end_time TIME,
|
||||
activity_type VARCHAR(50) NOT NULL,
|
||||
duration_min NUMERIC(6,2),
|
||||
kcal_active NUMERIC(7,2),
|
||||
kcal_resting NUMERIC(7,2),
|
||||
hr_avg NUMERIC(5,2),
|
||||
hr_max NUMERIC(5,2),
|
||||
kcal_active NUMERIC(12,2),
|
||||
kcal_resting NUMERIC(12,2),
|
||||
hr_avg NUMERIC(6,2),
|
||||
hr_max NUMERIC(6,2),
|
||||
distance_km NUMERIC(7,2),
|
||||
rpe INTEGER CHECK (rpe >= 1 AND rpe <= 10),
|
||||
source VARCHAR(20) DEFAULT 'manual',
|
||||
|
||||
@@ -0,0 +1,179 @@
|
||||
"""
|
||||
Diagnose: Was liegt in activity_session_metrics (EAV) vs. activity_log?
|
||||
|
||||
Ausführung (mit gesetzten DB_*-Variablen wie die App, z. B. aus .env):
|
||||
|
||||
cd backend
|
||||
python scripts/inspect_activity_eav.py
|
||||
|
||||
Lokal ohne Docker-Hostname: z. B. ``set DB_HOST=127.0.0.1`` (Windows) / ``export DB_HOST=127.0.0.1``,
|
||||
Port/User/Pass wie in der laufenden Postgres-Instanz.
|
||||
|
||||
Im Backend-Container (Compose-Service meist ``backend``, Arbeitsverzeichnis ``/app``):
|
||||
|
||||
docker compose exec backend python /app/scripts/inspect_activity_eav.py
|
||||
|
||||
Optional:
|
||||
python scripts/inspect_activity_eav.py --limit 30
|
||||
python scripts/inspect_activity_eav.py --profile <uuid>
|
||||
python scripts/inspect_activity_eav.py --activity <activity_log uuid>
|
||||
|
||||
Keine Schreibzugriffe — nur SELECT.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import os
|
||||
import sys
|
||||
|
||||
# backend/ als Import-Root
|
||||
_BACKEND_ROOT = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
|
||||
if _BACKEND_ROOT not in sys.path:
|
||||
sys.path.insert(0, _BACKEND_ROOT)
|
||||
|
||||
|
||||
def _val_row(r: dict) -> str | None:
|
||||
dt = r.get("data_type")
|
||||
if dt == "integer":
|
||||
v = r.get("value_int")
|
||||
return str(v) if v is not None else None
|
||||
if dt == "float":
|
||||
v = r.get("value_num")
|
||||
return str(v) if v is not None else None
|
||||
if dt == "string":
|
||||
v = r.get("value_text")
|
||||
return repr(v) if v is not None else None
|
||||
if dt == "boolean":
|
||||
v = r.get("value_bool")
|
||||
return str(v) if v is not None else None
|
||||
return None
|
||||
|
||||
|
||||
def main() -> None:
|
||||
parser = argparse.ArgumentParser(description="EAV activity_session_metrics inspizieren")
|
||||
parser.add_argument("--limit", type=int, default=40, help="Zeilen Report A/B")
|
||||
parser.add_argument("--profile", type=str, default=None, help="profile_id filtern")
|
||||
parser.add_argument("--activity", type=str, default=None, help="activity_log.id (einzelne Session)")
|
||||
args = parser.parse_args()
|
||||
|
||||
from db import get_db, get_cursor
|
||||
|
||||
if args.activity:
|
||||
with get_db() as conn:
|
||||
with get_cursor(conn) as cur:
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT al.id, al.profile_id, al.date, al.start_time, al.source,
|
||||
al.training_category, al.training_type_id, al.activity_type,
|
||||
al.duration_min, al.kcal_active, al.hr_avg, al.hr_max, al.distance_km
|
||||
FROM activity_log al
|
||||
WHERE al.id = %s::uuid
|
||||
""",
|
||||
(args.activity,),
|
||||
)
|
||||
h = cur.fetchone()
|
||||
if not h:
|
||||
print("activity_log: keine Zeile für diese id")
|
||||
return
|
||||
print("=== activity_log (Kopfzeile) ===")
|
||||
for k, v in dict(h).items():
|
||||
print(f" {k}: {v}")
|
||||
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT m.id AS metric_id, tp.key, tp.data_type, tp.source_field,
|
||||
m.value_num, m.value_int, m.value_text, m.value_bool, m.updated_at
|
||||
FROM activity_session_metrics m
|
||||
JOIN training_parameters tp ON tp.id = m.training_parameter_id
|
||||
WHERE m.activity_log_id = %s::uuid
|
||||
ORDER BY tp.key
|
||||
""",
|
||||
(args.activity,),
|
||||
)
|
||||
rows = cur.fetchall()
|
||||
print(f"\n=== activity_session_metrics ({len(rows)} Zeilen) ===")
|
||||
for r in rows:
|
||||
d = dict(r)
|
||||
print(
|
||||
f" {d['key']} ({d['data_type']}) "
|
||||
f"value={_val_row(d)!r} source_field={d.get('source_field')!r} "
|
||||
f"updated_at={d.get('updated_at')}"
|
||||
)
|
||||
if not rows:
|
||||
print(" (keine EAV-Zeilen)")
|
||||
return
|
||||
|
||||
prof_filter = ""
|
||||
if args.profile:
|
||||
prof_filter = " AND al.profile_id = %s::uuid "
|
||||
params_a: tuple = (args.profile, args.limit) if args.profile else (args.limit,)
|
||||
params_b: tuple = (args.profile, args.limit) if args.profile else (args.limit,)
|
||||
|
||||
q_recent_eav = f"""
|
||||
SELECT
|
||||
al.id AS activity_id,
|
||||
al.profile_id,
|
||||
al.date,
|
||||
al.start_time,
|
||||
al.source,
|
||||
al.training_type_id,
|
||||
al.training_category,
|
||||
tp.key AS parameter_key,
|
||||
tp.data_type,
|
||||
tp.source_field AS tp_source_field,
|
||||
m.value_num,
|
||||
m.value_int,
|
||||
m.value_text,
|
||||
m.value_bool,
|
||||
m.updated_at
|
||||
FROM activity_session_metrics m
|
||||
JOIN activity_log al ON al.id = m.activity_log_id
|
||||
JOIN training_parameters tp ON tp.id = m.training_parameter_id
|
||||
WHERE 1=1 {prof_filter}
|
||||
ORDER BY m.updated_at DESC NULLS LAST, al.date DESC, al.start_time DESC
|
||||
LIMIT %s
|
||||
"""
|
||||
|
||||
q_csv_no_eav = f"""
|
||||
SELECT
|
||||
al.id AS activity_id,
|
||||
al.profile_id,
|
||||
al.date,
|
||||
al.start_time,
|
||||
al.source,
|
||||
al.training_type_id,
|
||||
al.training_category,
|
||||
(SELECT COUNT(*) FROM activity_session_metrics m WHERE m.activity_log_id = al.id) AS eav_count
|
||||
FROM activity_log al
|
||||
WHERE al.source = 'csv' {prof_filter}
|
||||
ORDER BY al.date DESC, al.start_time DESC
|
||||
LIMIT %s
|
||||
"""
|
||||
|
||||
with get_db() as conn:
|
||||
with get_cursor(conn) as cur:
|
||||
print("=== A) Neueste EAV-Zeilen (join activity_log + training_parameters) ===\n")
|
||||
cur.execute(q_recent_eav, params_a)
|
||||
for r in cur.fetchall():
|
||||
d = dict(r)
|
||||
v = _val_row(d)
|
||||
print(
|
||||
f"{d['date']} {d['start_time']} | {d['activity_id']} | src={d['source']!r} | "
|
||||
f"type={d['training_type_id']} cat={d['training_category']!r} | "
|
||||
f"{d['parameter_key']}={v!r} (tp.source_field={d.get('tp_source_field')!r})"
|
||||
)
|
||||
|
||||
print("\n=== B) Neueste CSV-importierte Sessions: EAV-Anzahl pro Zeile ===\n")
|
||||
cur.execute(q_csv_no_eav, params_b)
|
||||
for r in cur.fetchall():
|
||||
d = dict(r)
|
||||
print(
|
||||
f"{d['date']} {d['start_time']} | {d['activity_id']} | "
|
||||
f"type={d['training_type_id']} | eav_count={d['eav_count']}"
|
||||
)
|
||||
|
||||
print("\nFertig. Für eine Session im Detail: --activity <uuid>")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Loaded 100 of 158 files, more files were not shown because too many files have changed in this diff.
Show more
Reference in new issue
Block a user