feat: Refactor activity import logic and enhance CSV handling
Deploy Development / deploy (push) Successful in 56s
Build Test / pytest-backend (push) Successful in 4s
Build Test / lint-backend (push) Successful in 0s
Build Test / build-frontend (push) Successful in 16s

- Replaced the deprecated `resolve_activity_log_column_patch_from_csv` function with `activity_csv_registry_updates_from_mapped` to streamline updates from CSV mappings.
- Updated the `_import_activity` function to utilize the new registry updates, improving data integrity during activity imports.
- Enhanced the activity module registry by adding German labels for various fields, improving localization support.
- Refactored the session metrics handling to ensure only relevant fields are processed, enhancing the overall robustness of CSV imports.
This commit is contained in:
Lars committed 2026-04-15 10:35:48 +02:00
1 parent 9d47c4ef84
commit 08eae86ddc
6 files changed
+181 -93

No files matched your search

@@ -7,9 +7,10 @@ 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, Optional
from typing import Any, Dict, List, Mapping, Optional
from models import ActivityEntry
@@ -45,6 +46,89 @@ def find_activity_duplicate_id(
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]:
mod = get_module_definition("activity")
if not mod:
return frozenset()
return frozenset((mod.get("fields") or {}).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()
@@ -296,7 +380,7 @@ def get_mappable_activity_field_catalog(cur, profile_id: str) -> Dict[str, Any]:
"data_type": s.get("type", "string"),
"required": bool(s.get("required")),
"unit": s.get("unit"),
"label_de": key,
"label_de": s.get("label_de") or key,
}
)
core_fields.sort(key=lambda x: x["key"])
+8 -50
View File
@@ -9,6 +9,8 @@ import logging
from decimal import Decimal
from typing import Any, Dict, List, Mapping, Optional, Sequence
from csv_parser.module_registry import get_module_definition
logger = logging.getLogger(__name__)
# activity_log-Spalten, die per training_parameters.source_field aus CSV (Parameter-Key) befüllt werden dürfen.
@@ -265,46 +267,6 @@ def _coerce_raw_value_for_parameter(data_type: str, raw: Any) -> Any:
raise ValueError(data_type)
def resolve_activity_log_column_patch_from_csv(
cur,
mapped: Mapping[str, Any],
training_category: Optional[str],
training_type_id: Optional[int],
) -> Dict[str, Any]:
"""
Zusätzliche activity_log-Updates aus CSV: Parameter mit source_field → Spalte.
"""
schema = resolve_activity_attribute_schema(cur, training_category, training_type_id)
patch: Dict[str, Any] = {}
for spec in schema:
src_col = (spec.get("source_field") or "").strip()
if not src_col or src_col in ACTIVITY_LOG_PATCH_FORBIDDEN:
continue
if src_col not in ACTIVITY_LOG_PATCHABLE_COLUMNS:
continue
pkey = spec["key"]
if pkey not in mapped:
continue
raw = mapped[pkey]
if raw is None or raw == "":
continue
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 activity_log patch skipped %s → %s: %s",
pkey,
src_col,
ex,
)
continue
patch[src_col] = coerced
return patch
def upsert_session_metrics_from_csv_mapped(
cur,
profile_id: str,
@@ -314,15 +276,10 @@ def upsert_session_metrics_from_csv_mapped(
training_type_id: Optional[int],
) -> None:
"""
EAV für Schema-Parameter aus CSV-mapped Werten.
EAV für Trainingsparameter aus CSV (nur Keys, die nicht im activity-Modul-Registry liegen).
Spalten-gestützte Parameter (source_field ∈ ACTIVITY_LOG_PATCHABLE_COLUMNS) werden
ausschließlich über resolve_activity_log_column_patch_from_csv → activity_log
geschrieben — hier kein EAV.
Wenn source_field gesetzt ist, aber **kein** patchbarer Spaltenname (z. B. eigener
Key „stola“ wie der Parametername), wäre früher weder Spalten-Update noch EAV erfolgt;
dann EAV wie bei reinen Metriken.
Kernfelder (Datum, Start, Distanz, HF, …) schreibt der Executor nach activity_log;
hier keine doppelten EAV-Zeilen für dieselben Registry-Keys.
"""
cur.execute(
"SELECT profile_id FROM activity_log WHERE id = %s",
@@ -331,6 +288,8 @@ def upsert_session_metrics_from_csv_mapped(
row = cur.fetchone()
if not row or str(row["profile_id"]) != str(profile_id):
return
mod = get_module_definition("activity") or {}
activity_registry_keys = frozenset((mod.get("fields") or {}).keys())
schema = resolve_activity_attribute_schema(cur, training_category, training_type_id)
for spec in schema:
pkey = spec["key"]
@@ -339,8 +298,7 @@ def upsert_session_metrics_from_csv_mapped(
raw = mapped[pkey]
if raw is None or raw == "":
continue
src_col = (spec.get("source_field") or "").strip()
if src_col and src_col in ACTIVITY_LOG_PATCHABLE_COLUMNS:
if pkey in activity_registry_keys:
continue
tid = spec["training_parameter_id"]
dt = spec["data_type"]