lifetrack/apps/api/app/tests/modules/test_health_importers.py

"""File importers of the health module: sniffing, parsing tolerance, and
idempotent deduplication (re-importing the same file changes nothing)."""

import datetime as dt
from pathlib import Path

import pytest
from sqlalchemy import select
from sqlalchemy.orm import Session

from app.core.importing.registry import IMPORTER_REGISTRY, detect_importer
from app.modules.auth.models import User
from app.modules.health import importers as health_importers
from app.modules.health.models import DailyActivity, FoodEntry, WeightEntry
from app.modules.imports import service as imports_service
from app.modules.imports.models import ImportRun

FIXTURES = Path(__file__).resolve().parents[1] / "fixtures" / "health"


def fixture_bytes(name: str) -> bytes:
    return (FIXTURES / name).read_bytes()


def run(db: Session, user: User, importer_id: str, name: str) -> ImportRun:
    return imports_service.run_import(db, user, importer_id, name, fixture_bytes(name))


# --- Registration & sniffing ---------------------------------------------------


def test_the_three_importers_are_registered() -> None:
    for importer_id in ("foodvisor_csv", "health_sync_csv", "weight_generic_csv"):
        assert importer_id in IMPORTER_REGISTRY
        assert IMPORTER_REGISTRY[importer_id].domain == "health"
        assert IMPORTER_REGISTRY[importer_id].accepted_extensions == (".csv",)
        # French label, shown as-is in the source picker
        assert IMPORTER_REGISTRY[importer_id].label


@pytest.mark.parametrize(
    ("filename", "expected"),
    [
        ("foodvisor_export.csv", "foodvisor_csv"),
        ("health_sync.csv", "health_sync_csv"),
        ("weight_history.csv", "weight_generic_csv"),
    ],
)
def test_sniffing_is_unambiguous(filename: str, expected: str) -> None:
    detected = detect_importer(filename, fixture_bytes(filename)[:4096])
    assert detected is not None, f"{filename} not detected"
    assert detected.id == expected


def test_sniff_never_raises_on_garbage() -> None:
    for cls in (
        health_importers.FoodvisorCsvImporter,
        health_importers.HealthSyncCsvImporter,
        health_importers.WeightGenericCsvImporter,
    ):
        assert cls.sniff("x.pdf", b"%PDF-1.7") is False
        assert cls.sniff("x.csv", b"\xff\xfe\x00binary") is False
        assert cls.sniff("x.csv", b"") is False


# --- Parsing helpers -----------------------------------------------------------


def test_decoding_falls_back_to_cp1252() -> None:
    assert health_importers.decode_bytes("Protéines".encode()) == "Protéines"
    assert health_importers.decode_bytes("Protéines".encode("cp1252")) == "Protéines"


def test_number_parsing_is_tolerant() -> None:
    to_decimal = health_importers.to_decimal
    assert float(to_decimal("1 234,5")) == 1234.5
    assert float(to_decimal("< 0,5")) == 0.5
    assert float(to_decimal("traces")) == 0.0
    assert to_decimal("-") is None
    assert to_decimal("") is None
    assert float(to_decimal("228.0")) == 228.0


def test_naive_timestamps_are_read_as_paris_time() -> None:
    parsed = health_importers.parse_datetime("2026-08-10 08:15")
    assert parsed == dt.datetime(2026, 8, 10, 6, 15, tzinfo=dt.UTC)  # CEST = UTC+2
    assert health_importers.parse_datetime("10/08/2026") is not None
    assert health_importers.parse_datetime("2026-08-10T08:15:00Z") == dt.datetime(
        2026, 8, 10, 8, 15, tzinfo=dt.UTC
    )
    assert health_importers.parse_datetime("n'importe quoi") is None


def test_meal_mapping_fr_en() -> None:
    assert health_importers.map_meal("Petit-déjeuner").value == "breakfast"
    assert health_importers.map_meal("Déjeuner").value == "lunch"
    assert health_importers.map_meal("Dîner").value == "dinner"
    assert health_importers.map_meal("Collation").value == "snack"
    assert health_importers.map_meal("Breakfast").value == "breakfast"
    assert health_importers.map_meal("inconnu").value == "snack"


# --- Foodvisor -----------------------------------------------------------------


def test_foodvisor_import_maps_meals_and_macros(db: Session, user: User) -> None:
    result = run(db, user, "foodvisor_csv", "foodvisor_export.csv")
    assert result.status == "completed"
    assert (result.rows_total, result.rows_inserted, result.rows_errors) == (4, 4, 0)

    entries = db.scalars(select(FoodEntry).order_by(FoodEntry.eaten_at.asc())).all()
    assert [entry.meal.value for entry in entries] == [
        "breakfast",
        "lunch",
        "dinner",
        "snack",
    ]
    first = entries[0]
    assert first.name == "Flocons d'avoine"
    assert first.brand == "Quaker"
    assert float(first.kcal) == 228.0
    assert float(first.protein_g) == 8.1
    assert float(first.quantity) == 60.0
    assert first.source == "foodvisor"
    assert first.external_id is not None
    assert first.import_run_id == result.id
    assert first.raw["aliment"] == "Flocons d'avoine"
    # 2026-08-10 08:15 Paris -> 06:15 UTC
    assert first.eaten_at == dt.datetime(2026, 8, 10, 6, 15, tzinfo=dt.UTC)
    assert entries[1].brand is None


def test_foodvisor_reimport_is_fully_duplicate(db: Session, user: User) -> None:
    run(db, user, "foodvisor_csv", "foodvisor_export.csv")
    second = run(db, user, "foodvisor_csv", "foodvisor_export.csv")
    assert second.rows_total == 4
    assert second.rows_duplicates == 4
    assert second.rows_inserted == 0
    assert db.scalar(select(FoodEntry).where(FoodEntry.user_id == user.id)) is not None
    assert len(db.scalars(select(FoodEntry)).all()) == 4


def test_foodvisor_rejects_incomplete_rows(db: Session, user: User) -> None:
    data = b"Date;Repas;Aliment;Calories (kcal)\n;Dejeuner;;\n"
    result = imports_service.run_import(db, user, "foodvisor_csv", "x.csv", data)
    assert result.rows_errors == 1
    assert "requis" in result.error_details[0]["message"]


# --- Health Sync ---------------------------------------------------------------


def test_health_sync_import_splits_weights_and_activity(
    db: Session, user: User
) -> None:
    result = run(db, user, "health_sync_csv", "health_sync.csv")
    assert result.status == "completed"
    # 3 rows -> 3 activity records + 2 weights (one row has no weight)
    assert result.rows_total == 5
    assert result.rows_inserted == 5

    activities = db.scalars(
        select(DailyActivity).order_by(DailyActivity.date.asc())
    ).all()
    assert [row.date for row in activities] == [
        dt.date(2026, 8, 10),
        dt.date(2026, 8, 11),
        dt.date(2026, 8, 12),
    ]
    assert activities[0].steps == 9421
    assert activities[0].distance_m == 6800  # 6,80 km -> metres
    assert float(activities[0].active_kcal) == 520.0
    assert activities[0].source == "csv_import"
    assert activities[0].import_run_id == result.id

    weights = db.scalars(
        select(WeightEntry).order_by(WeightEntry.measured_at.asc())
    ).all()
    assert [float(row.weight_kg) for row in weights] == [92.4, 92.1]


def test_health_sync_reimport_is_fully_duplicate(db: Session, user: User) -> None:
    run(db, user, "health_sync_csv", "health_sync.csv")
    second = run(db, user, "health_sync_csv", "health_sync.csv")
    assert second.rows_total == 5
    assert second.rows_duplicates == 5
    assert second.rows_inserted == 0
    assert second.rows_updated == 0


def test_health_sync_updated_values_replace_the_day(db: Session, user: User) -> None:
    run(db, user, "health_sync_csv", "health_sync.csv")
    later = b"Date;Pas;Distance (km);Calories actives\n2026-08-10;11000;7,50;600\n"
    result = imports_service.run_import(db, user, "health_sync_csv", "hs.csv", later)
    assert result.rows_updated == 1
    assert result.rows_inserted == 0
    row = db.scalar(
        select(DailyActivity).where(DailyActivity.date == dt.date(2026, 8, 10))
    )
    assert row.steps == 11000
    assert row.distance_m == 7500


# --- Generic weight history ----------------------------------------------------


def test_weight_generic_import_and_reimport(db: Session, user: User) -> None:
    result = run(db, user, "weight_generic_csv", "weight_history.csv")
    assert (result.rows_total, result.rows_inserted) == (3, 3)
    weights = db.scalars(
        select(WeightEntry).order_by(WeightEntry.measured_at.asc())
    ).all()
    assert [float(row.weight_kg) for row in weights] == [95.2, 94.1, 93.4]
    assert weights[0].source == "csv_import"
    assert weights[0].measured_at == dt.datetime(2026, 6, 30, 22, 0, tzinfo=dt.UTC)

    second = run(db, user, "weight_generic_csv", "weight_history.csv")
    assert second.rows_duplicates == 3
    assert len(db.scalars(select(WeightEntry)).all()) == 3


def test_weight_generic_rejects_out_of_range(db: Session, user: User) -> None:
    data = b"date;poids\n2026-07-01;950,0\n"
    result = imports_service.run_import(db, user, "weight_generic_csv", "w.csv", data)
    assert result.rows_errors == 1
    assert "bornes" in result.error_details[0]["message"]


# --- Central rollback ----------------------------------------------------------


def test_deleting_an_import_run_removes_its_rows(db: Session, user: User) -> None:
    result = run(db, user, "foodvisor_csv", "foodvisor_export.csv")
    assert len(db.scalars(select(FoodEntry)).all()) == 4
    imports_service.rollback_run(db, user.id, result.id)
    assert db.scalars(select(FoodEntry)).all() == []