feat(csv-import): Add CSV import diagnosis endpoint and related functionality
Deploy Development / deploy (push) Successful in 50s
Build Test / pytest-backend (push) Successful in 4s
Build Test / lint-backend (push) Successful in 0s
Build Test / build-frontend (push) Successful in 17s

- Implemented a new endpoint for diagnosing CSV imports without writing to the database, allowing users to validate mappings and type conversions.
- Introduced the `diagnose_vitals_row` function to analyze vital metrics and provide detailed feedback on data validity.
- Enhanced the CSV import logic to include alias handling for vital fields, improving compatibility with different CSV formats.
- Updated the frontend to support the new diagnosis feature, including UI elements for displaying diagnosis results and error details.
- Added tests to ensure the correctness of the new diagnosis functionality and its integration with existing import processes.
This commit is contained in:
Lars committed 2026-04-10 16:35:31 +02:00
1 parent 1855f6e57a
commit c5b0540b11
6 files changed
+394 -18

No files matched your search

+30
View File
@@ -524,6 +524,36 @@ def _v_safe_float(value: Any) -> float | None:
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,
+101
View File
@@ -402,6 +402,29 @@ def _lookup_db_field(csv_col: str, field_mappings: Mapping[str, str]) -> str | N
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 build_row_after_mapping(
csv_row: Mapping[str, str],
field_mappings: Mapping[str, str],
@@ -416,6 +439,8 @@ def build_row_after_mapping(
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)
if not db_field:
continue
spec = tc.get(db_field)
@@ -426,3 +451,79 @@ def build_row_after_mapping(
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 = 96,
) -> dict[str, Any]:
"""
Nur für Diagnose-Endpunkt: Quelle (Vorlage vs. Vital-Alias), Konvertierung pro Spalte,
Ergebnis wie build_row_after_mapping (json-freundliche Vorschau).
"""
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)
target = via_t or via_a
src = "template" if via_t else ("alias" if via_a else "none")
spec = tc.get(target) 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,
}