batchCooking/services/tech-step-intent-service/tests/test_locale_pipeline_entities.py

"""Rejoue les cas d'offsets caractère exacts et d'insensibilité accents/casse
de `tech-step-matcher.test.ts` (`apps/api/test/recipe-matching/tech-step-matcher.test.ts`)
contre le `PhraseMatcher`/`diacritics_normalizer` de `LocalePipeline` — le
point de fidélité le plus critique de cette migration (voir le plan). Doit
être vert *avant* de brancher `apps/api` dessus.

Ces tests entraînent un pipeline minimal (pas le corpus complet
`TECH_STEP_TRAINING_DATA`, propriété de `apps/api`) avec juste assez de
`synonyms`/`utterances` pour reproduire chaque cas — le textcat n'est pas ce
qui est vérifié ici (voir `test_locale_pipeline_intent.py`).
"""

import pytest

from intent_service.locale_pipeline import LocalePipeline, TrainEntry

# Un jeu d'entrées minimal mais réaliste, reprenant les synonymes réels de
# `tech-step-training-data.ts` pour "preheat"/"melt" qui rendent les cas
# `tech-step-matcher.test.ts` exacts (voir ce fichier, lignes 155/787).
_FR_ENTRIES = [
    TrainEntry(
        uid="preheat",
        synonyms=["préchauffer", "poêle chaude"],
        utterances=["préchauffer le four à 180 degrés", "mettre la poêle sur feu vif"],
    ),
    TrainEntry(
        # `synonyms` deliberately includes both "fondre" (standalone) and
        # "faire fondre" (containing it) — mirrors the real corpus
        # (`tech-step-training-data.ts`) exactly, and is what
        # `test_does_not_double_match_a_synonym_nested_in_a_longer_one`
        # below exists to guard: the `PhraseMatcher` reports both as
        # separate overlapping matches, `LocalePipeline.process` must
        # collapse them into one.
        uid="melt",
        synonyms=["fondre", "fondu", "faire fondre", "faire chauffer"],
        utterances=["faire fondre le beurre", "faire chauffer une noix de beurre"],
    ),
    TrainEntry(
        uid="simmer",
        synonyms=["mijoter"],
        utterances=["faire mijoter à feu doux", "laisser mijoter à couvert"],
    ),
]


@pytest.fixture(scope="module")
def fr_pipeline() -> LocalePipeline:
    pipeline = LocalePipeline("fr")
    pipeline.train(_FR_ENTRIES)
    return pipeline


def test_matches_an_exact_expression(fr_pipeline: LocalePipeline):
    result = fr_pipeline.process("Faire mijoter à feu doux")
    assert [entity.uid for entity in result.entities] == ["simmer"]
    entity = result.entities[0]
    text = "Faire mijoter à feu doux"
    assert text[entity.start : entity.end].lower() == "mijoter"


def test_is_case_and_accent_insensitive(fr_pipeline: LocalePipeline):
    result = fr_pipeline.process("FAIRE MIJOTER")
    assert [entity.uid for entity in result.entities] == ["simmer"]


def test_returns_no_entities_when_nothing_matches(fr_pipeline: LocalePipeline):
    result = fr_pipeline.process("Ranger les couverts dans le tiroir")
    assert result.entities == []


def test_returns_empty_for_an_empty_text(fr_pipeline: LocalePipeline):
    result = fr_pipeline.process("")
    assert result.entities == []
    assert result.intent is None
    assert result.score == 0.0


def test_untrained_locale_returns_empty_without_error():
    pipeline = LocalePipeline("en")
    result = pipeline.process("melt the butter")
    assert result.entities == []
    assert result.intent is None
    assert result.score == 0.0


def test_detects_two_techniques_with_exact_tight_spans_reading_order(fr_pipeline: LocalePipeline):
    # This text's "poêle" is now *also* a real utensil match ("pan", see
    # `utensil_vocabulary.py`) — filtered out here by `kind` since this test
    # is specifically about technique-candidate ordering, not the full
    # mixed entity list (see `test_utensil_matching.py` for the utensil
    # matcher's own coverage).
    text = "Préchauffer la poêle, puis faire fondre le beurre"
    result = fr_pipeline.process(text)

    technique_entities = [entity for entity in result.entities if entity.kind == "technique"]
    uids_by_start = sorted(((entity.start, entity.uid) for entity in technique_entities))
    assert [uid for _, uid in uids_by_start] == ["preheat", "melt"]

    preheat_entity = next(e for e in result.entities if e.uid == "preheat")
    melt_entity = next(e for e in result.entities if e.uid == "melt")
    assert text[preheat_entity.start : preheat_entity.end].lower() == "préchauffer"
    assert text[melt_entity.start : melt_entity.end].lower() == "faire fondre"


def test_does_not_double_match_a_synonym_nested_in_a_longer_one(fr_pipeline: LocalePipeline):
    # Regression: "fondre" is itself a substring of "faire fondre" — both
    # are registered as `melt` synonyms (like the real corpus). Without
    # `filter_spans` in `LocalePipeline.process`, the `PhraseMatcher`
    # reports *both* overlapping matches, producing `melt` twice in
    # apps/api's final `matchTechSteps` output instead of once (caught by a
    # real CI failure in `tech-step-matcher.test.ts` once this service
    # replaced node-nlp).
    text = "faire fondre le beurre"
    result = fr_pipeline.process(text)
    assert [entity.uid for entity in result.entities] == ["melt"]
    entity = result.entities[0]
    assert text[entity.start : entity.end] == "faire fondre"


def test_matches_the_classic_poele_chaude_example_with_exact_offsets(fr_pipeline: LocalePipeline):
    # Le cas motivant les context spans côté apps/api (tech-step-matcher.test.ts) :
    # le mot-clé de `preheat` est un groupe nominal ("poêle chaude"), pas un
    # verbe. Offsets attendus IDENTIQUES à ceux du test TS d'origine :
    # preheat -> [9, 21) ("poêle chaude"), melt -> [23, 37) ("faire chauffer").
    text = "Dans une poêle chaude, faire chauffer une noix de beurre"
    result = fr_pipeline.process(text)

    preheat_entity = next(e for e in result.entities if e.uid == "preheat")
    melt_entity = next(e for e in result.entities if e.uid == "melt")

    assert (preheat_entity.start, preheat_entity.end) == (9, 21)
    assert text[preheat_entity.start : preheat_entity.end] == "poêle chaude"

    assert (melt_entity.start, melt_entity.end) == (23, 37)
    assert text[melt_entity.start : melt_entity.end] == "faire chauffer"


def test_chop_matches_english_text_tight_span():
    pipeline = LocalePipeline("en")
    pipeline.train(
        [
            TrainEntry(
                uid="chop",
                synonyms=["chop"],
                utterances=["chop the onions finely", "finely chop the garlic"],
            ),
            TrainEntry(uid="boil", synonyms=["boil"], utterances=["bring to the boil", "boil the water"]),
        ]
    )
    text = "Chop the onions finely"
    result = pipeline.process(text)
    chop_entity = next(e for e in result.entities if e.uid == "chop")
    assert (chop_entity.start, chop_entity.end) == (0, 4)
    assert text[chop_entity.start : chop_entity.end] == "Chop"