Domi31tls
1c44a26eb3
Anonymise toutes les références à des entités réelles (CHCB, Bayonne, Saint-Denis, Réunion, etc.) dans le code source, les configurations YAML, les scripts/outils, et les tests unitaires. Conserve les tests synthétiques (cases) intentionnels. - profile key chcb_strict → chuxx_strict - CHCB → CHUXX, Bayonne → Chicago, Saint-Denis → Springfield, Réunion → Province Bêta, 64100/97400 → 12345, FINESS → 999999999, préfixe tél 05.59.44 → 0X.XX.XX - renomme tools/test_chcb_leak.py → tools/test_force_term_leak.py Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
105 lines
3.1 KiB
Python
105 lines
3.1 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
Tests de non-régression pour la config externalisée.
|
|
"""
|
|
from pathlib import Path
|
|
|
|
import anonymizer_core_refactored_onnx as core
|
|
from config_defaults import (
|
|
deep_merge_dict,
|
|
ensure_runtime_dictionaries_config,
|
|
load_effective_dictionaries_dict,
|
|
load_effective_param_lists,
|
|
read_default_dictionaries_text,
|
|
read_runtime_dictionaries_overlay_text,
|
|
)
|
|
|
|
|
|
def test_default_config_template_is_externalized():
|
|
text = read_default_dictionaries_text()
|
|
|
|
assert "blacklist:" in text
|
|
assert "whitelist_phrases:" in text
|
|
|
|
cfg = core.load_dictionaries(None)
|
|
assert "CHUXX" in cfg["blacklist"]["force_mask_terms"]
|
|
|
|
|
|
def test_runtime_overlay_template_is_minimal():
|
|
text = read_runtime_dictionaries_overlay_text()
|
|
|
|
assert "dictionnaires.default.yml" in text
|
|
assert "{}" in text
|
|
|
|
|
|
def test_deep_merge_dict_preserves_nested_defaults():
|
|
base = {
|
|
"whitelist": {
|
|
"sections_titres": ["DIM"],
|
|
"org_gpe_keep": False,
|
|
},
|
|
"flags": {
|
|
"case_insensitive": True,
|
|
"regex_engine": "python",
|
|
},
|
|
}
|
|
override = {
|
|
"whitelist": {
|
|
"sections_titres": ["GHM"],
|
|
"org_gpe_keep": True,
|
|
},
|
|
"flags": {
|
|
"regex_engine": "re2",
|
|
},
|
|
}
|
|
|
|
merged = deep_merge_dict(base, override)
|
|
|
|
assert merged["whitelist"]["sections_titres"] == ["DIM", "GHM"]
|
|
assert merged["whitelist"]["org_gpe_keep"] is True
|
|
assert merged["flags"]["case_insensitive"] is True
|
|
assert merged["flags"]["regex_engine"] == "re2"
|
|
|
|
|
|
def test_additional_stopwords_refresh_and_reset(tmp_path: Path):
|
|
cfg_path = tmp_path / "cfg.yml"
|
|
cfg_path.write_text("additional_stopwords:\n - xyzzymed\n", encoding="utf-8")
|
|
|
|
core.load_dictionaries(cfg_path)
|
|
assert "xyzzymed" in core._MEDICAL_STOP_WORDS_SET
|
|
assert "xyzzymed" in core._MEDICAL_STOP_WORDS
|
|
|
|
core.load_dictionaries(None)
|
|
assert "xyzzymed" not in core._MEDICAL_STOP_WORDS_SET
|
|
assert "xyzzymed" not in core._MEDICAL_STOP_WORDS
|
|
|
|
|
|
def test_runtime_overlay_is_created_and_effective_merge_works(tmp_path: Path):
|
|
cfg_path = tmp_path / "dictionnaires.yml"
|
|
|
|
created = ensure_runtime_dictionaries_config(cfg_path)
|
|
assert created == cfg_path
|
|
assert cfg_path.exists()
|
|
|
|
effective = load_effective_dictionaries_dict(cfg_path)
|
|
assert "CHUXX" in effective["blacklist"]["force_mask_terms"]
|
|
|
|
cfg_path.write_text(
|
|
"blacklist:\n force_mask_terms:\n - LOCAL_SIGLE\n",
|
|
encoding="utf-8",
|
|
)
|
|
effective = load_effective_dictionaries_dict(cfg_path)
|
|
assert "CHUXX" in effective["blacklist"]["force_mask_terms"]
|
|
assert "LOCAL_SIGLE" in effective["blacklist"]["force_mask_terms"]
|
|
|
|
|
|
def test_effective_param_lists_include_defaults_when_overlay_is_empty(tmp_path: Path):
|
|
cfg_path = tmp_path / "dictionnaires.yml"
|
|
cfg_path.write_text("{}\n", encoding="utf-8")
|
|
|
|
params = load_effective_param_lists(cfg_path)
|
|
|
|
assert "classification internationale" in params["whitelist_phrases"]
|
|
assert "CHUXX" in params["blacklist_force_mask_terms"]
|
|
assert params["additional_stopwords"] == []
|