14b1bf844a
Le VLM ne fournit que des value_ids ; la value est reconstruite côté Python depuis l'OCR (le texte VLM est ignoré) -> 0 hallucination par construction. 9 tests unitaires : ancrage, ids hors plage, dédup ordonnée, value_ids vide, confidence min, bbox englobante, anti-injection. Module pur, non branché runtime. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
94 lines
3.3 KiB
Python
94 lines
3.3 KiB
Python
"""Tests du role_mapper : reconstruction de champs ANCRÉS sur l'OCR.
|
|
|
|
Principe cardinal (cf. gate vert 30/06) : le VLM ne fournit QUE des ids de tokens OCR
|
|
(value_ids) ; la valeur est reconstruite côté Python depuis l'OCR. Aucun texte produit
|
|
par le VLM ne doit pouvoir entrer dans une valeur -> 0 hallucination par construction.
|
|
"""
|
|
import pytest
|
|
|
|
from core.extraction.role_mapper import (
|
|
OcrToken,
|
|
reconstruct_fields,
|
|
tokens_from_grid,
|
|
)
|
|
|
|
|
|
def _tok(tid, text, conf=0.9, bbox=(0, 0, 10, 10)):
|
|
return OcrToken(id=tid, text=text, confidence=conf, bbox=bbox)
|
|
|
|
|
|
def test_reconstruit_value_concatene_tokens_dans_lordre():
|
|
tokens = [_tok(0, "DUPONT"), _tok(1, "Jean")]
|
|
fields = reconstruct_fields(tokens, [{"label": "Nom complet", "value_ids": [0, 1]}])
|
|
assert len(fields) == 1
|
|
assert fields[0].label == "Nom complet"
|
|
assert fields[0].value == "DUPONT Jean"
|
|
assert fields[0].anchored is True
|
|
|
|
|
|
def test_ignore_les_ids_hors_plage_et_les_liste():
|
|
tokens = [_tok(0, "DUPONT")]
|
|
fields = reconstruct_fields(tokens, [{"label": "Nom", "value_ids": [0, 99]}])
|
|
assert fields[0].value == "DUPONT"
|
|
assert fields[0].invalid_ids == [99]
|
|
assert fields[0].anchored is True
|
|
|
|
|
|
def test_value_ids_vide_donne_champ_non_ancre():
|
|
tokens = [_tok(0, "DUPONT")]
|
|
fields = reconstruct_fields(tokens, [{"label": "Poids", "value_ids": []}])
|
|
assert fields[0].value == ""
|
|
assert fields[0].anchored is False
|
|
|
|
|
|
def test_aucun_id_valide_donne_champ_non_ancre():
|
|
tokens = [_tok(0, "DUPONT")]
|
|
fields = reconstruct_fields(tokens, [{"label": "Poids", "value_ids": [7, 8]}])
|
|
assert fields[0].anchored is False
|
|
assert fields[0].value == ""
|
|
assert fields[0].invalid_ids == [7, 8]
|
|
|
|
|
|
def test_dedup_ids_en_preservant_lordre():
|
|
tokens = [_tok(0, "DUPONT"), _tok(1, "Jean")]
|
|
fields = reconstruct_fields(tokens, [{"label": "X", "value_ids": [1, 1, 0]}])
|
|
assert fields[0].value == "Jean DUPONT"
|
|
assert fields[0].value_ids == [1, 0]
|
|
|
|
|
|
def test_confidence_est_le_min_des_tokens_ancres():
|
|
tokens = [_tok(0, "A", conf=0.95), _tok(1, "B", conf=0.70)]
|
|
fields = reconstruct_fields(tokens, [{"label": "X", "value_ids": [0, 1]}])
|
|
assert fields[0].confidence == pytest.approx(0.70)
|
|
|
|
|
|
def test_bbox_englobante_des_tokens_ancres():
|
|
tokens = [_tok(0, "A", bbox=(0, 0, 10, 10)), _tok(1, "B", bbox=(20, 5, 40, 15))]
|
|
fields = reconstruct_fields(tokens, [{"label": "X", "value_ids": [0, 1]}])
|
|
assert fields[0].bbox == (0, 0, 40, 15)
|
|
|
|
|
|
def test_invariant_aucun_texte_hors_ocr():
|
|
# 'value' fournie par le VLM est ignorée : seul value_ids compte.
|
|
tokens = [_tok(0, "DUPONT")]
|
|
fields = reconstruct_fields(
|
|
tokens, [{"label": "Nom", "value_ids": [0], "value": "HALLUCINATION"}]
|
|
)
|
|
assert fields[0].value == "DUPONT"
|
|
|
|
|
|
def test_tokens_from_grid_indexe_et_normalise_bbox():
|
|
# grille extract_grid_from_image : bbox = 4 points EasyOCR
|
|
grid = [
|
|
[
|
|
{"text": "Nom", "bbox": [[0, 0], [10, 0], [10, 8], [0, 8]],
|
|
"confidence": 0.9, "row": 0, "col": 0},
|
|
{"text": "DUPONT", "bbox": [[20, 0], [60, 0], [60, 8], [20, 8]],
|
|
"confidence": 0.95, "row": 0, "col": 1},
|
|
],
|
|
]
|
|
tokens = tokens_from_grid(grid)
|
|
assert [t.id for t in tokens] == [0, 1]
|
|
assert tokens[0].text == "Nom"
|
|
assert tokens[1].bbox == (20, 0, 60, 8)
|