Compare commits

...
Author SHA1 Message Date
Lars 58bce0ea19 scripts/import_markdown.py aktualisiert
Deploy mindnet to llm-node / deploy (push) Failing after 2s
2025-09-09 19:57:32 +02:00
Lars 3e888cc669 scripts/import_markdown.py aktualisiert
Deploy mindnet to llm-node / deploy (push) Failing after 2s
2025-09-09 19:47:16 +02:00
Lars 78446c74d3 schemas/note.schema.json aktualisiert
Deploy mindnet to llm-node / deploy (push) Failing after 2s
2025-09-09 19:43:12 +02:00
Lars 51f08f193c scripts/import_markdown.py aktualisiert
Deploy mindnet to llm-node / deploy (push) Failing after 2s
2025-09-09 19:42:35 +02:00
Lars 4872374a6e app/core/note_payload.py aktualisiert
Deploy mindnet to llm-node / deploy (push) Failing after 2s
2025-09-09 19:42:09 +02:00
3 changed files with 277 additions and 427 deletions

No files matched your search

+71 -151
View File
@@ -1,36 +1,8 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
# Modul: app/core/note_payload.py
# Version: 1.6.3
# Version: 1.7.0
# Datum: 2025-09-09
#
# Zweck
# -----
# Erzeugt den Qdrant-Payload für Notes inkl. robuster Hash-Bildung zur
# Änderungserkennung. Der vollständige (parsed) Body wird unter "fulltext"
# persistiert; der Pfad ist relativ (für verlustfreien Export).
#
# Steuerung (CLI/ENV, vom Importer durchgereicht)
# -----------------------------------------------
# - Vergleichsmodus:
# --hash-mode body|frontmatter|full
# ENV: MINDNET_HASH_MODE oder MINDNET_HASH_COMPARE (Body|Frontmatter|Full)
# "full" ist Alias für "body+frontmatter".
# - Hash-Quelle:
# --hash-source parsed|raw (ENV: MINDNET_HASH_SOURCE)
# - Normalisierung:
# --hash-normalize canonical|none (ENV: MINDNET_HASH_NORMALIZE)
#
# Payload-Felder (Auszug)
# -----------------------
# note_id, title, type, status, created, updated, path, tags,
# fulltext, references (Note-Level-Wikilinks),
# hash_fulltext (Primärhash), hash_signature (z. B. "body:raw:none:<hex>")
#
# Hinweise
# --------
# - Keine Abhängigkeit von FS-Zeitstempeln; nur Inhalte fließen in den Hash ein.
# - Abwärtskompatibel: Feldernamen bleiben stabil; zusätzliche Felder stören nicht.
from __future__ import annotations
@@ -45,17 +17,14 @@ try:
except Exception: # pragma: no cover
from .parser import read_markdown, extract_wikilinks, FRONTMATTER_RE # type: ignore
# ---------------------------------------------------------------------------
# Helpers
# ---------------------------------------------------------------------------
def _canon_frontmatter(fm: Dict[str, Any]) -> str:
"""Kanonische JSON-Serialisierung der Frontmatter für Hashbildung."""
return json.dumps(fm or {}, ensure_ascii=False, separators=(",", ":"), sort_keys=True)
def _normalize_body(body: str, mode: str) -> str:
"""Normalisiert den Body für reproduzierbare Hashes (oder nicht)."""
if mode == "none":
return body if body is not None else ""
text = (body or "").replace("\r\n", "\n").replace("\r", "\n")
@@ -63,12 +32,6 @@ def _normalize_body(body: str, mode: str) -> str:
return text
def _resolve_hash_mode(explicit: Optional[str]) -> str:
"""
Normalisiert den Hash-Modus auf:
'body' | 'frontmatter' | 'body+frontmatter'
Akzeptiert 'full' als Alias.
Berücksichtigt ENV: MINDNET_HASH_MODE oder MINDNET_HASH_COMPARE.
"""
if explicit:
val = explicit.strip().lower()
else:
@@ -76,17 +39,12 @@ def _resolve_hash_mode(explicit: Optional[str]) -> str:
or os.environ.get("MINDNET_HASH_COMPARE")
or "body").strip().lower()
if val in ("full", "fulltext", "body+frontmatter", "bodyplusfrontmatter"):
return "body+frontmatter"
return "full"
if val in ("frontmatter", "fm"):
return "frontmatter"
return "body"
def _read_raw_body_from_file(file_path: Optional[str]) -> Tuple[str, Dict[str, Any]]:
"""Liest die Rohdatei und extrahiert Body & Frontmatter ohne Parser-Logik.
Rückgabe:
(body_text, frontmatter_dict)
"""
if not file_path or not os.path.exists(file_path):
return "", {}
try:
@@ -94,7 +52,6 @@ def _read_raw_body_from_file(file_path: Optional[str]) -> Tuple[str, Dict[str, A
raw = f.read()
except Exception:
return "", {}
# Frontmatter per Regex entfernen
m = FRONTMATTER_RE.match(raw)
fm = {}
if m:
@@ -109,55 +66,21 @@ def _read_raw_body_from_file(file_path: Optional[str]) -> Tuple[str, Dict[str, A
body = raw
return body, fm
# ---------------------------------------------------------------------------
# Hashing
# ---------------------------------------------------------------------------
def _sha256(s: str) -> str:
h = hashlib.sha256()
h.update(s.encode("utf-8"))
return h.hexdigest()
def compute_hash(
*,
body: Optional[str],
frontmatter: Optional[Dict[str, Any]],
mode: Optional[str] = None,
normalize: Optional[str] = None,
) -> str:
"""
Berechnet einen Hex-Hash gemäß 'mode' und 'normalize'.
mode: "body" | "frontmatter" | "body+frontmatter"
normalize: "canonical" | "none"
"""
mode = _resolve_hash_mode(mode)
normalize = (normalize or os.environ.get("MINDNET_HASH_NORMALIZE", "canonical")).strip().lower()
def _hash_for(mode: str, *, body: str, fm: Dict[str, Any], normalize: str) -> str:
body_n = _normalize_body(body or "", normalize)
fm_s = _canon_frontmatter(frontmatter or {})
fm_s = _canon_frontmatter(fm or {})
if mode == "frontmatter":
return _sha256(fm_s)
if mode == "body+frontmatter":
if mode == "full":
return _sha256(body_n + "\n--FM--\n" + fm_s)
# default: body
return _sha256(body_n)
def compute_hash_set(*, body_parsed: str, body_raw: str, fm: Dict[str, Any], normalize: str) -> Dict[str, str]:
"""Berechnet ein Set an Hashes für Monitoring/Debug."""
fm_s = _canon_frontmatter(fm or {})
bp = _normalize_body(body_parsed or "", normalize)
br = _normalize_body(body_raw or "", normalize)
return {
"frontmatter": _sha256(fm_s),
"body_parsed": _sha256(bp),
"body_raw": _sha256(br),
"full_parsed": _sha256(bp + "\n--FM--\n" + fm_s),
"full_raw": _sha256(br + "\n--FM--\n" + fm_s),
}
# ---------------------------------------------------------------------------
# Kernfunktion
# ---------------------------------------------------------------------------
@@ -172,27 +95,13 @@ def make_note_payload(
file_path: Optional[str] = None,
) -> Dict[str, Any]:
"""
Erzeugt den Payload für eine geparste Note.
Parameters
----------
parsed : Any
Objekt mit Attributen/Keys 'frontmatter', 'body', 'path'.
vault_root : Optional[str]
Vault-Wurzel (für Pfad-Relativierung).
hash_mode : Optional[str]
"body" | "frontmatter" | "body+frontmatter" | "full" (Alias; überschreibt ENV).
hash_normalize : Optional[str]
"canonical" | "none" (überschreibt ENV).
hash_source : Optional[str]
"parsed" (Default) oder "raw". Wenn "raw", wird der Body aus der Rohdatei gelesen.
file_path : Optional[str]
Pfad zur Markdown-Datei, erforderlich für 'hash_source=raw'.
Returns
-------
Dict[str, Any]
Qdrant-Payload für die Notes-Collection.
Liefert den Note-Payload inkl. Mehrfach-Hashes.
- Es werden IMMER die drei Hashes für (body|frontmatter|full) unter
'parsed:canonical' erzeugt (Schlüssel: z. B. 'body:parsed:canonical').
- Zusätzlich werden – falls die aktuelle Konfig (source/normalize) davon
abweicht – die drei Hashes unter den entsprechenden Schlüsseln erzeugt,
z. B. 'frontmatter:raw:none'.
- 'hash_fulltext' und 'hash_signature' repräsentieren den *aktuellen* Modus.
"""
# dict oder Objekt akzeptieren
if isinstance(parsed, dict):
@@ -204,38 +113,62 @@ def make_note_payload(
body_parsed = getattr(parsed, "body", "") or ""
path = getattr(parsed, "path", "") or ""
# Hash-Quelle bestimmen
src = (hash_source or os.environ.get("MINDNET_HASH_SOURCE", "parsed")).strip().lower()
# Zielpfad relativieren
rel_path = path
try:
if vault_root:
rel = os.path.relpath(path, vault_root)
rel = rel.replace("\\", "/").lstrip("/")
rel_path = rel
except Exception:
pass
# Konfiguration auflösen
mode_resolved = _resolve_hash_mode(hash_mode) # body|frontmatter|full
src = (hash_source or os.environ.get("MINDNET_HASH_SOURCE", "parsed")).strip().lower() # parsed|raw
norm = (hash_normalize or os.environ.get("MINDNET_HASH_NORMALIZE", "canonical")).strip().lower() # canonical|none
# Body-Quelle laden
raw_body, raw_fm = ("", {})
if src == "raw":
raw_body, raw_fm = _read_raw_body_from_file(file_path or path)
# Roh-FM ergänzen (nicht überschreiben)
if isinstance(raw_fm, dict) and raw_fm:
merged_fm = dict(fm)
for k, v in raw_fm.items():
merged_fm.setdefault(k, v)
fm = merged_fm
body_for_hash = raw_body
else:
body_for_hash = body_parsed
normalize = (hash_normalize or os.environ.get("MINDNET_HASH_NORMALIZE", "canonical")).strip().lower()
mode_resolved = _resolve_hash_mode(hash_mode)
# --- 1) Standard-Tripel (parsed:canonical) immer erzeugen ---
std_src = "parsed"
std_norm = "canonical"
std_hashes: Dict[str, str] = {}
for m in ("body", "frontmatter", "full"):
std_hashes[f"{m}:{std_src}:{std_norm}"] = _hash_for(
m, body=body_parsed, fm=fm, normalize=std_norm
)
# Hash gemäß Modus/Quelle bilden
body_for_hash = raw_body if src == "raw" else body_parsed
primary_hash = compute_hash(body=body_for_hash, frontmatter=fm, mode=mode_resolved, normalize=normalize)
hash_signature = f"{'full' if mode_resolved=='body+frontmatter' else mode_resolved}:{src}:{normalize}:{primary_hash}"
# Convenience-Felder (für Tools)
hash_body = std_hashes["body:parsed:canonical"]
hash_frontmatter = std_hashes["frontmatter:parsed:canonical"]
hash_full = std_hashes["full:parsed:canonical"]
# Pfad relativieren
rel_path = path
try:
if vault_root:
rel = os.path.relpath(path, vault_root)
rel = rel.replace("\\", "/").lstrip("/") # normalisieren
rel_path = rel
except Exception:
pass
# --- 2) Hashes für die *aktuelle* Konfiguration (falls abweichend) ---
cur_hashes: Dict[str, str] = {}
if not (src == std_src and norm == std_norm):
for m in ("body", "frontmatter", "full"):
cur_hashes[f"{m}:{src}:{norm}"] = _hash_for(
m, body=body_for_hash, fm=fm, normalize=norm
)
# Note-Level-Wikilinks (Fallback, wenn Chunks nicht geliefert werden)
note_level_refs = list(dict.fromkeys(extract_wikilinks(body_parsed))) if body_parsed else []
# --- 3) Aktueller Modus für Backwards-Compat Felder ---
current_hash = _hash_for(mode_resolved, body=body_for_hash, fm=fm, normalize=norm)
hash_signature = f"{mode_resolved}:{src}:{norm}:{current_hash}"
# Wikilinks (Note-Ebene)
refs = list(dict.fromkeys(extract_wikilinks(body_parsed))) if body_parsed else []
payload: Dict[str, Any] = {
"note_id": fm.get("id") or fm.get("note_id"),
@@ -246,47 +179,36 @@ def make_note_payload(
"updated": fm.get("updated"),
"path": rel_path or fm.get("path"),
"tags": fm.get("tags"),
# Primärer Hash + Signatur (für Vergleich)
"hash_fulltext": primary_hash,
"hash_signature": hash_signature,
# Volltext persistieren (verlustfreie Rekonstruktion) – parsed Body
# Volltext für verlustfreien Export
"fulltext": body_parsed,
# Fallback-Refs auf Note-Ebene
"references": note_level_refs,
# Backwards-Compat:
"hash_fulltext": current_hash,
"hash_signature": hash_signature,
# Option C: Mehrfach-Hashes
"hashes": {**std_hashes, **cur_hashes},
"hash_body": hash_body,
"hash_frontmatter": hash_frontmatter,
"hash_full": hash_full,
# Fallback-Refs
"references": refs,
}
for k in ("area", "project", "source", "lang", "slug", "aliases"):
if k in fm:
payload[k] = fm[k]
# Optional: gesamtes Hash-Set persistieren (Debug/Monitoring)
if os.environ.get("MINDNET_HASH_RECORD_ALL", "false").strip().lower() == "true":
payload["hashes"] = compute_hash_set(
body_parsed=body_parsed, body_raw=raw_body, fm=fm, normalize=normalize
)
# Optional: Roh-Body-Hash separat (historische Kompatibilität)
if os.environ.get("MINDNET_HASH_STORE_RAW", "false").strip().lower() == "true" and src == "raw":
try:
payload["hash_raw_body"] = compute_hash(
body=raw_body, frontmatter=fm, mode="body", normalize="none"
)
except Exception:
pass
return payload
# ---------------------------------------------------------------------------
# CLI – Sichtprüfung
# ---------------------------------------------------------------------------
def _cli() -> None:
ap = argparse.ArgumentParser(description="Note-Payload aus Markdown erzeugen und anzeigen")
ap.add_argument("--from-file", dest="src", required=True, help="Pfad zur Markdown-Datei")
ap.add_argument("--vault-root", dest="vault_root", default=None, help="Vault-Wurzel zur Pfad-Relativierung")
ap.add_argument("--print", dest="do_print", action="store_true", help="Payload auf stdout ausgeben")
ap.add_argument("--hash-mode", choices=["body", "frontmatter", "body+frontmatter", "full"], default=None)
ap.add_argument("--from-file", dest="src", required=True)
ap.add_argument("--vault-root", dest="vault_root", default=None)
ap.add_argument("--print", dest="do_print", action="store_true")
ap.add_argument("--hash-mode", choices=["body", "frontmatter", "full"], default=None)
ap.add_argument("--hash-normalize", choices=["canonical", "none"], default=None)
ap.add_argument("--hash-source", choices=["parsed", "raw"], default=None)
args = ap.parse_args()
@@ -300,10 +222,8 @@ def _cli() -> None:
hash_source=args.hash_source,
file_path=args.src,
)
if args.do_print:
print(json.dumps(payload, ensure_ascii=False, indent=2))
if __name__ == "__main__": # pragma: no cover
_cli()
+35 -29
View File
@@ -1,39 +1,45 @@
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "mindnet_note",
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "mindnet note payload",
"type": "object",
"description": "Note-Payload (Qdrant). Erweitert um fulltext/hash_raw_body für verlustfreien Export.",
"required": ["note_id", "title", "type", "status", "created", "path"],
"properties": {
"note_id": { "type": "string" },
"title": { "type": "string" },
"type": { "type": "string" },
"status": { "type": "string" },
"created": { "type": "string" },
"updated": { "type": "string" },
"note_id": { "type": "string" },
"title": { "type": ["string","null"] },
"type": { "type": ["string","null"] },
"status": { "type": ["string","null"] },
"created": { "type": ["string","null"] },
"updated": { "type": ["string","null"] },
"path": { "type": ["string","null"] },
"tags": { "type": ["array","null"], "items": { "type": "string" } },
"area": { "type": ["string","null"] },
"project": { "type": ["string","null"] },
"source": { "type": ["string","null"] },
"lang": { "type": ["string","null"] },
"slug": { "type": ["string","null"] },
"aliases": { "type": ["array","null"], "items": { "type": "string" } },
"tags": { "type": "array", "items": { "type": "string" } },
"area": { "type": "string" },
"project": { "type": "string" },
"priority": { "type": "number" },
"effort_min": { "type": "number" },
"due": { "type": "string" },
"people": { "type": "array", "items": { "type": "string" } },
"aliases": { "type": "array", "items": { "type": "string" } },
"lang": { "type": "string" },
"fulltext": { "type": ["string","null"] },
"references": { "type": ["array","null"], "items": { "type": "string" } },
"path": { "type": "string" },
"hash_fulltext": { "type": ["string","null"], "pattern": "^[a-f0-9]{64}$" },
"hash_signature": { "type": ["string","null"] },
"references": { "type": "array", "items": { "type": "string" } },
"depends_on": { "type": "array", "items": { "type": "string" } },
"assigned_to": { "type": "array", "items": { "type": "string" } },
"hash_body": { "type": ["string","null"], "pattern": "^[a-f0-9]{64}$" },
"hash_frontmatter": { "type": ["string","null"], "pattern": "^[a-f0-9]{64}$" },
"hash_full": { "type": ["string","null"], "pattern": "^[a-f0-9]{64}$" },
"hash_fulltext":{ "type": "string" },
"hash_raw_body":{ "type": "string" },
"fulltext": { "type": "string" }
"hashes": {
"type": ["object","null"],
"description": "Mapping: <mode>:<source>:<normalize> -> sha256 hex",
"patternProperties": {
"^(body|frontmatter|full):(parsed|raw):(canonical|none)$": {
"type": "string",
"pattern": "^[a-f0-9]{64}$"
}
},
"additionalProperties": false
}
},
"required": ["note_id"],
"additionalProperties": true
}
+171 -247
View File
@@ -2,42 +2,50 @@
# -*- coding: utf-8 -*-
"""
Script: scripts/import_markdown.py — Markdown → Qdrant (Notes, Chunks, Edges)
Version: 3.5.3
Version: 3.6.2
Datum: 2025-09-09
Neu in 3.5.3
------------
- **Fallback**, falls app.core.note_payload.make_note_payload(None) / non-dict zurückgibt:
Der Importer baut einen minimalen, korrekten Note-Payload selbst (inkl. Hash
gemäß --hash-mode/--hash-source/--hash-normalize) und läuft weiter.
- Detaillierte Debug-Ausgaben mit Typ/Preview, falls die Rückgabeform abweicht.
Kurzbeschreibung
----------------
- Liest Markdown-Dateien ein, erzeugt Notes/Chunks/Edges **idempotent**.
- Änderungserkennung (nur Inhalte, keine FS-Zeitstempel) konfigurierbar:
* --hash-mode: body | frontmatter | body+frontmatter | full (Alias)
- Env: MINDNET_HASH_MODE oder MINDNET_HASH_COMPARE (Body/Frontmatter/Full)
* --hash-normalize: canonical | none (Default: canonical)
* --hash-source: parsed (Default) | raw
* Optional: --compare-text (oder ENV MINDNET_COMPARE_TEXT=true)
* Signaturabgleich: Wechselt die Signatur (z. B. body→full, parsed→raw, canonical→none),
gilt die Note einmalig als geändert.
- Liest Markdown-Dateien ein und erzeugt Notes/Chunks/Edges **idempotent**.
- Robuste Änderungserkennung: Mehrfach-Hashes werden parallel in der Note gespeichert
(Option C). Vergleich erfolgt **modusgenau** anhand von `hashes[<mode>:<source>:<normalize>]`.
Ein Wechsel des Vergleichsmodus führt so **nicht** zu Massenänderungen.
- **Fix (v3.6.2):** Bei **erstem Import** (kein Alt-Payload) wird die Note als **geändert**
behandelt → Create (Notes/Chunks/Edges) findet zuverlässig statt.
- Baseline-Modus: Mit `--baseline-modes` werden **fehlende** Hash-Varianten
im Feld `hashes` „still“ nachgetragen (Upsert NUR Notes; Legacy-Hashfelder bleiben unangetastet).
ENV / Qdrant
------------
Konfiguration Hash/Compare
--------------------------
- Vergleichsmodus: `--hash-mode body|frontmatter|full`
- oder ENV: `MINDNET_HASH_MODE` / `MINDNET_HASH_COMPARE` (Body|Frontmatter|Full)
- Quelle: `--hash-source parsed|raw` (ENV: `MINDNET_HASH_SOURCE`, Default parsed)
- Normalisierung: `--hash-normalize canonical|none` (ENV: `MINDNET_HASH_NORMALIZE`, Default canonical)
- Optional: `--compare-text` (oder `MINDNET_COMPARE_TEXT=true`) vergleicht zusätzlich den parsed Body-Text direkt.
Weitere ENV / Qdrant
--------------------
- QDRANT_URL | QDRANT_HOST/QDRANT_PORT | QDRANT_API_KEY
- COLLECTION_PREFIX (Default: mindnet)
- VECTOR_DIM (Default: 384)
- MINDNET_NOTE_SCOPE_REFS: true|false (Default: false)
- MINDNET_COMPARE_TEXT: true|false (Default: false)
Aufruf-Beispiele
----------------
# Standard (Body, parsed, canonical)
python3 -m scripts.import_markdown --vault ./vault
python3 -m scripts.import_markdown --vault ./vault --apply --hash-source raw --hash-normalize none
MINDNET_HASH_COMPARE=Full python3 -m scripts.import_markdown --vault ./vault --apply
python3 -m scripts.import_markdown --vault ./vault --apply --compare-text
# Baseline (füllt hashes für parsed:canonical Tripel „still“ auf)
MINDNET_HASH_SOURCE=parsed MINDNET_HASH_NORMALIZE=canonical \
python3 -m scripts.import_markdown --vault ./vault --apply --baseline-modes
# Frontmatter-Vergleich ohne Massenänderungen (nach Baseline)
MINDNET_HASH_COMPARE=Frontmatter \
python3 -m scripts.import_markdown --vault ./vault
# Sehr sensibel (raw + none) und direkten Textvergleich
python3 -m scripts.import_markdown --vault ./vault --apply --hash-source raw --hash-normalize none --compare-text
"""
from __future__ import annotations
@@ -56,8 +64,6 @@ from app.core.parser import (
read_markdown,
normalize_frontmatter,
validate_required_frontmatter,
extract_wikilinks,
FRONTMATTER_RE,
)
from app.core.note_payload import make_note_payload
from app.core.chunker import assemble_chunks
@@ -117,11 +123,29 @@ def fetch_existing_note_payload(client, prefix: str, note_id: str) -> Optional[D
return points[0].payload or {}
def purge_note_artifacts(client, prefix: str, note_id: str) -> None:
"""
Löscht alle Chunks & Edges zu einer Note mittels Filter-Selector (kompatibel mit aktuellen Qdrant-Clients).
"""
_, chunks_col, edges_col = collections(prefix)
f_chunks = rest.Filter(must=[rest.FieldCondition(key="note_id", match=rest.MatchValue(value=note_id))])
client.delete(collection_name=chunks_col, points_selector=f_chunks, wait=True)
f_edges = rest.Filter(must=[rest.FieldCondition(key="note_id", match=rest.MatchValue(value=note_id))])
client.delete(collection_name=edges_col, points_selector=f_edges, wait=True)
filt = rest.Filter(must=[rest.FieldCondition(key="note_id", match=rest.MatchValue(value=note_id))])
try:
client.delete(
collection_name=chunks_col,
points_selector=rest.FilterSelector(filter=filt),
wait=True
)
except Exception as e:
print(json.dumps({"note_id": note_id, "warn": f"delete chunks via filter failed: {e}"}))
try:
client.delete(
collection_name=edges_col,
points_selector=rest.FilterSelector(filter=filt),
wait=True
)
except Exception as e:
print(json.dumps({"note_id": note_id, "warn": f"delete edges via filter failed: {e}"}))
def _normalize_rel_path(abs_path: str, vault_root: str) -> str:
try:
@@ -130,127 +154,16 @@ def _normalize_rel_path(abs_path: str, vault_root: str) -> str:
rel = abs_path
return rel.replace("\\", "/").lstrip("/")
def _resolve_hash_mode(val: Optional[str]) -> str:
def _resolve_mode(val: Optional[str]) -> str:
v = (val or os.environ.get("MINDNET_HASH_MODE") or os.environ.get("MINDNET_HASH_COMPARE") or "body").strip().lower()
if v in ("full", "fulltext", "body+frontmatter", "bodyplusfrontmatter"):
return "body+frontmatter"
return "full"
if v in ("frontmatter", "fm"):
return "frontmatter"
return "body"
def _normalize_body(body: str, mode: str) -> str:
if mode == "none":
return body if body is not None else ""
text = (body or "").replace("\r\n", "\n").replace("\r", "\n")
text = "\n".join(line.rstrip() for line in text.split("\n"))
return text
def _canon_fm(fm: Dict[str, Any]) -> str:
return json.dumps(fm or {}, ensure_ascii=False, separators=(",", ":"), sort_keys=True)
def _read_raw_body(file_path: str) -> tuple[str, Dict[str, Any]]:
if not os.path.exists(file_path):
return "", {}
with open(file_path, "r", encoding="utf-8") as f:
raw = f.read()
m = FRONTMATTER_RE.match(raw)
fm = {}
if m:
import yaml
try:
fm = yaml.safe_load(m.group(1)) or {}
except Exception:
fm = {}
body = raw[m.end():]
else:
body = raw
return body, fm
def _fallback_note_payload(parsed: Any, vault_root: str, *, hash_mode: Optional[str], hash_normalize: Optional[str],
hash_source: Optional[str], file_path: str) -> Dict[str, Any]:
"""Baut einen minimalen Note-Payload, falls make_note_payload None liefert."""
fm = normalize_frontmatter(parsed.frontmatter)
path = getattr(parsed, "path", file_path)
rel_path = _normalize_rel_path(path, vault_root)
src = (hash_source or os.environ.get("MINDNET_HASH_SOURCE", "parsed")).strip().lower()
norm = (hash_normalize or os.environ.get("MINDNET_HASH_NORMALIZE", "canonical")).strip().lower()
mode = _resolve_hash_mode(hash_mode)
if src == "raw":
body_raw, fm_raw = _read_raw_body(file_path)
# Roh-FM ergänzen (nicht überschreiben)
if fm_raw:
merged = dict(fm)
for k, v in fm_raw.items():
merged.setdefault(k, v)
fm = merged
body_for_hash = body_raw
else:
body_for_hash = getattr(parsed, "body", "") or ""
body_n = _normalize_body(body_for_hash, norm)
fm_s = _canon_fm(fm)
import hashlib
def h(s: str) -> str:
x = hashlib.sha256()
x.update(s.encode("utf-8"))
return x.hexdigest()
if mode == "frontmatter":
primary_hash = h(fm_s)
elif mode == "body+frontmatter":
primary_hash = h(body_n + "\n--FM--\n" + fm_s)
else:
primary_hash = h(body_n)
sig = f"{'full' if mode=='body+frontmatter' else mode}:{src}:{norm}:{primary_hash}"
refs = extract_wikilinks(getattr(parsed, "body", "") or "")
return {
"note_id": fm.get("id") or fm.get("note_id"),
"title": fm.get("title"),
"type": fm.get("type"),
"status": fm.get("status"),
"created": fm.get("created"),
"updated": fm.get("updated"),
"path": rel_path or fm.get("path"),
"tags": fm.get("tags"),
"hash_fulltext": primary_hash,
"hash_signature": sig,
"fulltext": getattr(parsed, "body", "") or "",
"references": list(dict.fromkeys(refs)),
}
def _coerce_to_dict(obj: Any) -> Optional[Dict[str, Any]]:
if obj is None:
return None
if isinstance(obj, dict):
return obj
if isinstance(obj, Mapping):
try:
return dict(obj)
except Exception:
pass
if isinstance(obj, (list, tuple)):
for it in obj:
d = _coerce_to_dict(it)
if isinstance(d, dict):
return d
return None
md = getattr(obj, "model_dump", None)
if callable(md):
try: return md()
except Exception: pass
dd = getattr(obj, "dict", None)
if callable(dd):
try: return dd()
except Exception: pass
dct = getattr(obj, "__dict__", None)
if isinstance(dct, dict):
return dict(dct)
return None
def _env(key: str, default: str) -> str:
return (os.environ.get(key) or default).strip().lower()
# ---------------------------------------------------------------------
@@ -268,17 +181,27 @@ def main() -> None:
ap.add_argument("--embed-note", action="store_true", help="Optional: Note-Volltext einbetten")
ap.add_argument("--force-replace", action="store_true",
help="Änderungserkennung ignorieren und immer upserten (+ optional Purge)")
ap.add_argument("--hash-mode", choices=["body", "frontmatter", "body+frontmatter", "full"], default=None)
ap.add_argument("--hash-mode", choices=["body", "frontmatter", "full"], default=None,
help="Vergleichsmodus (Body | Frontmatter | Full)")
ap.add_argument("--hash-normalize", choices=["canonical", "none"], default=None)
ap.add_argument("--hash-source", choices=["parsed", "raw"], default=None)
ap.add_argument("--note-scope-refs", action="store_true")
ap.add_argument("--debug-hash-diff", action="store_true")
ap.add_argument("--compare-text", action="store_true")
ap.add_argument("--hash-source", choices=["parsed", "raw"], default=None,
help="Quelle für die Hash-Berechnung (Default: parsed)")
ap.add_argument("--note-scope-refs", action="store_true",
help="(Optional) erzeugt zusätzlich references:note (Default: aus)")
ap.add_argument("--debug-hash-diff", action="store_true",
help="Zeigt einen kurzen Diff zwischen altem und neuem Body")
ap.add_argument("--compare-text", action="store_true",
help="Parsed fulltext zusätzlich direkt vergleichen (über Hash hinaus)")
ap.add_argument("--baseline-modes", action="store_true",
help="Fehlende Hash-Varianten im Feld 'hashes' still nachtragen (Upsert NUR Notes)")
args = ap.parse_args()
note_scope_refs_env = (os.environ.get("MINDNET_NOTE_SCOPE_REFS", "false").strip().lower() == "true")
mode = _resolve_mode(args.hash_mode) # body|frontmatter|full
src = _env("MINDNET_HASH_SOURCE", args.hash_source or "parsed") # parsed|raw
norm = _env("MINDNET_HASH_NORMALIZE", args.hash_normalize or "canonical") # canonical|none
note_scope_refs_env = (_env("MINDNET_NOTE_SCOPE_REFS", "false") == "true")
note_scope_refs = args.note_scope_refs or note_scope_refs_env
compare_text = args.compare_text or (os.environ.get("MINDNET_COMPARE_TEXT", "false").strip().lower() == "true")
compare_text = args.compare_text or (_env("MINDNET_COMPARE_TEXT", "false") == "true")
cfg = QdrantConfig.from_env()
client = get_client(cfg)
@@ -291,9 +214,11 @@ def main() -> None:
print("Keine Markdown-Dateien gefunden.", file=sys.stderr)
sys.exit(2)
key_current = f"{mode}:{src}:{norm}"
processed = 0
for path in files:
# ------------- Parsing -------------
# -------- Parse & Validate --------
try:
parsed = read_markdown(path)
except Exception as e:
@@ -315,63 +240,40 @@ def main() -> None:
processed += 1
# ------------- Note-Payload -------------
try:
note_pl_raw = make_note_payload(
parsed,
vault_root=root,
hash_mode=args.hash_mode,
hash_normalize=args.hash_normalize,
hash_source=args.hash_source,
file_path=path,
)
except Exception as e:
print(json.dumps({"path": path, "note_id": fm.get("id"), "error": f"make_note_payload failed: {e}"}))
note_pl_raw = None
note_pl = _coerce_to_dict(note_pl_raw)
if not isinstance(note_pl, dict):
# Fallback: baue minimalen Payload
note_pl = _fallback_note_payload(
parsed,
root,
hash_mode=args.hash_mode,
hash_normalize=args.hash_normalize,
hash_source=args.hash_source,
file_path=path,
)
print(json.dumps({
"path": path,
"note_id": fm.get("id"),
"warn": "make_note_payload returned non-dict; used fallback",
"returned_type": type(note_pl_raw).__name__ if note_pl_raw is not None else "NoneType"
}))
# fulltext + path Sicherheit
# -------- Build new payload (includes 'hashes') --------
note_pl = make_note_payload(
parsed,
vault_root=root,
hash_mode=mode,
hash_normalize=norm,
hash_source=src,
file_path=path,
)
if not note_pl.get("fulltext"):
note_pl["fulltext"] = getattr(parsed, "body", "") or ""
if note_pl.get("path"):
note_pl["path"] = _normalize_rel_path(
os.path.join(root, note_pl["path"]) if not os.path.isabs(note_pl["path"]) else note_pl["path"], root
)
else:
p_path = getattr(parsed, "path", None) or path
note_pl["path"] = _normalize_rel_path(p_path, root)
note_id = note_pl.get("note_id") or fm.get("id")
if not note_id:
print(json.dumps({"path": path, "error": "Missing note_id after payload build (even in fallback)"}))
print(json.dumps({"path": path, "error": "Missing note_id after payload build"}))
continue
# ------------- Change-Detection -------------
# -------- Fetch old payload --------
old_payload = None if args.force_replace else fetch_existing_note_payload(client, cfg.prefix, note_id)
old_hash = None if not old_payload else old_payload.get("hash_fulltext")
old_sig = (old_payload or {}).get("hash_signature")
new_hash = note_pl.get("hash_fulltext")
new_sig = note_pl.get("hash_signature")
has_old = old_payload is not None
sig_changed = bool(old_sig) and bool(new_sig) and (old_sig.split(":")[:3] != new_sig.split(":")[:3])
hash_changed = (old_hash != new_hash)
old_hashes = (old_payload or {}).get("hashes") or {}
old_hash_exact = old_hashes.get(key_current)
# Neu-Hash (aktueller Modus) aus neuem Payload
new_hash_exact = (note_pl.get("hashes") or {}).get(key_current)
needs_baseline = (old_hash_exact is None)
# Change-Detection:
# - CREATE: wenn es KEIN Alt-Payload gibt -> changed=True
# - UPDATE: baseline existiert UND Hash differiert
# - force/text_changed wie gehabt
hash_changed = (old_hash_exact is not None and new_hash_exact is not None and old_hash_exact != new_hash_exact)
text_changed = False
if compare_text:
@@ -379,77 +281,99 @@ def main() -> None:
new_text = note_pl.get("fulltext") or ""
text_changed = (old_text != new_text)
changed = args.force_replace or sig_changed or hash_changed or text_changed
changed = args.force_replace or (not has_old) or hash_changed or text_changed
# ------------- Chunks / Embeddings / Edges -------------
try:
chunks = assemble_chunks(fm["id"], getattr(parsed, "body", "") or "", fm.get("type", "concept"))
chunk_pls = make_chunk_payloads(fm, note_pl["path"], chunks)
except Exception as e:
print(json.dumps({"path": path, "note_id": note_id, "error": f"chunk build failed: {e}"}))
continue
# Baseline-only nur, wenn Alt-Payload existiert UND Key fehlt UND keine sonstige Änderung
do_baseline_only = (args.baseline_modes and has_old and needs_baseline and not changed)
if embed_texts:
# -------- Optional: Chunks / Embeddings / Edges vorbereiten --------
# CREATE/UPDATE: wir brauchen Chunks/Edges; Baseline-only: nein
chunks = []
chunk_pls = []
edges = []
vecs = []
if (args.apply and (changed and (not do_baseline_only))):
try:
vecs = embed_texts([getattr(c, "text", "") for c in chunks]) # type: ignore[attr-defined]
chunks = assemble_chunks(fm["id"], getattr(parsed, "body", "") or "", fm.get("type", "concept"))
chunk_pls = make_chunk_payloads(fm, note_pl["path"], chunks)
except Exception as e:
print(json.dumps({"path": path, "note_id": note_id, "warn": f"embed_texts failed, using zeros: {e}"}))
print(json.dumps({"path": path, "note_id": note_id, "error": f"chunk build failed: {e}"}))
continue
if embed_texts:
try:
vecs = embed_texts([getattr(c, "text", "") for c in chunks]) # type: ignore[attr-defined]
except Exception as e:
print(json.dumps({"path": path, "note_id": note_id, "warn": f"embed_texts failed, using zeros: {e}"}))
vecs = [[0.0] * cfg.dim for _ in chunks]
else:
vecs = [[0.0] * cfg.dim for _ in chunks]
else:
vecs = [[0.0] * cfg.dim for _ in chunks]
try:
note_refs = note_pl.get("references") or []
edges = build_edges_for_note(
note_id,
chunk_pls,
note_refs,
include_note_scope_refs=note_scope_refs,
)
except Exception as e:
print(json.dumps({"path": path, "note_id": note_id, "error": f"build_edges_for_note failed: {e}"}))
continue
try:
note_refs = note_pl.get("references") or []
edges = build_edges_for_note(
note_id,
chunk_pls,
note_refs,
include_note_scope_refs=note_scope_refs,
)
except Exception as e:
print(json.dumps({"path": path, "note_id": note_id, "error": f"build_edges_for_note failed: {e}"}))
continue
# ------------- Summary -------------
# -------- Summary --------
summary = {
"note_id": note_id,
"title": fm.get("title"),
"chunks": len(chunk_pls),
"edges": len(edges),
"changed": changed,
"decision": ("apply" if args.apply and changed else
"needs_baseline_for_mode": needs_baseline,
"decision": ("baseline-only" if args.apply and do_baseline_only else
"apply" if args.apply and changed else
"apply-skip-unchanged" if args.apply and not changed else
"dry-run"),
"path": note_pl["path"],
"hash_mode": args.hash_mode or os.environ.get("MINDNET_HASH_MODE") or os.environ.get("MINDNET_HASH_COMPARE", "body"),
"hash_normalize": args.hash_normalize or os.environ.get("MINDNET_HASH_NORMALIZE", "canonical"),
"hash_source": args.hash_source or os.environ.get("MINDNET_HASH_SOURCE", "parsed"),
"hash_signature": note_pl.get("hash_signature"),
"sig_changed": sig_changed,
"hash_changed": hash_changed,
"text_changed": text_changed,
"hash_mode": mode,
"hash_normalize": norm,
"hash_source": src,
}
print(json.dumps(summary, ensure_ascii=False))
# ------------- Upserts -------------
# -------- Writes --------
if not args.apply:
continue
try:
if changed and args.purge_before_upsert:
purge_note_artifacts(client, cfg.prefix, note_id)
except Exception as e:
print(json.dumps({"path": path, "note_id": note_id, "warn": f"purge failed: {e}"}))
try:
# BASELINE-ONLY: fehlenden Key nachtragen, ohne legacy Felder anzutasten
if do_baseline_only:
merged_hashes = {}
merged_hashes.update(old_hashes)
merged_hashes.update(note_pl.get("hashes") or {})
# Legacy-Hashfelder unverändert lassen, falls vorhanden
if old_payload:
note_pl["hash_fulltext"] = old_payload.get("hash_fulltext", note_pl.get("hash_fulltext"))
note_pl["hash_signature"] = old_payload.get("hash_signature", note_pl.get("hash_signature"))
note_pl["hashes"] = merged_hashes
notes_name, note_pts = points_for_note(cfg.prefix, note_pl, None, cfg.dim)
upsert_batch(client, notes_name, note_pts)
chunks_name, chunk_pts = points_for_chunks(cfg.prefix, chunk_pls, vecs)
upsert_batch(client, chunks_name, chunk_pts)
edges_name, edge_pts = points_for_edges(cfg.prefix, edges)
upsert_batch(client, edges_name, edge_pts)
except Exception as e:
print(json.dumps({"path": path, "note_id": note_id, "error": f"upsert failed: {e}"}))
continue
# Normale CREATE/UPDATE
if not changed:
continue
if args.purge_before_upsert and has_old:
try:
purge_note_artifacts(client, cfg.prefix, note_id)
except Exception as e:
print(json.dumps({"path": path, "note_id": note_id, "warn": f"purge failed: {e}"}))
notes_name, note_pts = points_for_note(cfg.prefix, note_pl, None, cfg.dim)
upsert_batch(client, notes_name, note_pts)
chunks_name, chunk_pts = points_for_chunks(cfg.prefix, chunk_pls, vecs)
upsert_batch(client, chunks_name, chunk_pts)
edges_name, edge_pts = points_for_edges(cfg.prefix, edges)
upsert_batch(client, edges_name, edge_pts)
print(f"Done. Processed notes: {processed}")