Spaces:
Build error
Build error
File size: 15,929 Bytes
0341500 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 | """
Tests pour le service d'indexation et de recherche (page_search + indexer).
"""
import json
from pathlib import Path
from unittest.mock import patch
import pytest
import pytest_asyncio
from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_async_engine
import app.models # noqa: F401 β enregistrement des modeles
from app.models.database import Base
from app.schemas.page_master import PageMaster
from app.services.search.indexer import (
_extract_tags,
_normalize,
index_page,
reindex_all,
search_pages,
)
# ββ Fixtures ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
_TEST_DB_URL = "sqlite+aiosqlite:///:memory:"
@pytest_asyncio.fixture
async def db():
"""Session AsyncSession sur une BDD SQLite en memoire."""
engine = create_async_engine(_TEST_DB_URL, echo=False)
async with engine.begin() as conn:
await conn.run_sync(Base.metadata.create_all)
factory = async_sessionmaker(engine, expire_on_commit=False)
async with factory() as session:
yield session
async with engine.begin() as conn:
await conn.run_sync(Base.metadata.drop_all)
await engine.dispose()
def _make_master(
page_id: str = "test-ms-001r",
corpus_profile: str = "medieval-illuminated",
manuscript_id: str = "test-ms",
folio_label: str = "001r",
diplomatic_text: str = "Explicit liber primus",
translation_fr: str = "Fin du premier livre",
tags: list[str] | None = None,
) -> PageMaster:
"""Construit un PageMaster minimal valide pour les tests."""
extensions: dict = {}
if tags:
extensions["iconography"] = [{"region_id": "r1", "tags": tags}]
data = {
"schema_version": "1.0",
"page_id": page_id,
"corpus_profile": corpus_profile,
"manuscript_id": manuscript_id,
"folio_label": folio_label,
"sequence": 1,
"image": {
"master": "https://example.com/image.jpg",
"width": 3000,
"height": 4000,
},
"layout": {
"regions": [
{
"id": "r1",
"type": "text_block",
"bbox": [100, 100, 500, 500],
"confidence": 0.9,
}
]
},
"ocr": {
"diplomatic_text": diplomatic_text,
"language": "la",
"confidence": 0.8,
},
"translation": {"fr": translation_fr, "en": ""},
"extensions": extensions,
}
return PageMaster.model_validate(data)
# ββ Tests _normalize ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
class TestNormalize:
def test_lowercase(self):
assert _normalize("HELLO") == "hello"
def test_accent_removal(self):
assert _normalize("éà ü") == "eau"
def test_combined(self):
assert _normalize("DΓ©but du RΓ©cit") == "debut du recit"
def test_empty(self):
assert _normalize("") == ""
# ββ Tests _extract_tags βββββββββββββββββββββββββββββββββββββββββββββββββββββββ
class TestExtractTags:
def test_with_tags(self):
master = _make_master(tags=["apocalypse", "martyrs", "autel"])
result = _extract_tags(master)
assert "apocalypse" in result
assert "martyrs" in result
assert "autel" in result
def test_no_tags(self):
master = _make_master(tags=None)
result = _extract_tags(master)
assert result == ""
def test_empty_extensions(self):
master = _make_master()
# Force extensions to empty dict
data = master.model_dump(mode="json")
data["extensions"] = {}
m = PageMaster.model_validate(data)
assert _extract_tags(m) == ""
# ββ Tests index_page βββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
class TestIndexPage:
@pytest.mark.asyncio
async def test_index_new_page(self, db: AsyncSession):
master = _make_master()
await index_page(db, master)
await db.commit()
# Verify it was inserted
from app.models.page_search import PageSearchIndex
row = await db.get(PageSearchIndex, master.page_id)
assert row is not None
assert row.page_id == "test-ms-001r"
assert row.diplomatic_text == "Explicit liber primus"
assert row.translation_fr == "Fin du premier livre"
assert row.manuscript_id == "test-ms"
@pytest.mark.asyncio
async def test_index_update_existing(self, db: AsyncSession):
master = _make_master(diplomatic_text="version 1")
await index_page(db, master)
await db.commit()
# Update with new content
master2 = _make_master(diplomatic_text="version 2")
await index_page(db, master2)
await db.commit()
from app.models.page_search import PageSearchIndex
row = await db.get(PageSearchIndex, master.page_id)
assert row is not None
assert row.diplomatic_text == "version 2"
@pytest.mark.asyncio
async def test_index_page_without_ocr(self, db: AsyncSession):
data = {
"schema_version": "1.0",
"page_id": "no-ocr-page",
"corpus_profile": "medieval-illuminated",
"manuscript_id": "test-ms",
"folio_label": "001r",
"sequence": 1,
"image": {
"master": "https://example.com/image.jpg",
"width": 3000,
"height": 4000,
},
"layout": {"regions": []},
"ocr": None,
"translation": None,
}
master = PageMaster.model_validate(data)
await index_page(db, master)
await db.commit()
from app.models.page_search import PageSearchIndex
row = await db.get(PageSearchIndex, "no-ocr-page")
assert row is not None
assert row.diplomatic_text == ""
assert row.translation_fr == ""
@pytest.mark.asyncio
async def test_index_page_with_tags(self, db: AsyncSession):
master = _make_master(tags=["sceau", "martyrs"])
await index_page(db, master)
await db.commit()
from app.models.page_search import PageSearchIndex
row = await db.get(PageSearchIndex, master.page_id)
assert row is not None
assert "sceau" in row.tags
assert "martyrs" in row.tags
# ββ Tests search_pages ββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
class TestSearchPages:
@pytest.mark.asyncio
async def test_search_finds_diplomatic_text(self, db: AsyncSession):
master = _make_master(diplomatic_text="Explicit liber primus incipit")
await index_page(db, master)
await db.commit()
hits = await search_pages(db, "liber")
assert len(hits) == 1
assert hits[0]["page_id"] == "test-ms-001r"
assert hits[0]["score"] >= 1
@pytest.mark.asyncio
async def test_search_finds_translation(self, db: AsyncSession):
master = _make_master(translation_fr="Fin du premier livre")
await index_page(db, master)
await db.commit()
hits = await search_pages(db, "premier")
assert len(hits) == 1
assert hits[0]["page_id"] == "test-ms-001r"
@pytest.mark.asyncio
async def test_search_finds_tags(self, db: AsyncSession):
master = _make_master(tags=["apocalypse", "martyrs"])
await index_page(db, master)
await db.commit()
hits = await search_pages(db, "apocalypse")
assert len(hits) == 1
@pytest.mark.asyncio
async def test_accent_insensitive_search(self, db: AsyncSession):
master = _make_master(translation_fr="DΓ©but du rΓ©cit apocalyptique")
await index_page(db, master)
await db.commit()
# Search without accents
hits = await search_pages(db, "debut")
assert len(hits) == 1
# Search with accents
hits = await search_pages(db, "dΓ©but")
assert len(hits) == 1
# Search with wrong accents
hits = await search_pages(db, "recit")
assert len(hits) == 1
@pytest.mark.asyncio
async def test_case_insensitive_search(self, db: AsyncSession):
master = _make_master(diplomatic_text="Explicit Liber Primus")
await index_page(db, master)
await db.commit()
hits = await search_pages(db, "EXPLICIT")
assert len(hits) == 1
hits = await search_pages(db, "explicit")
assert len(hits) == 1
@pytest.mark.asyncio
async def test_empty_query_returns_nothing(self, db: AsyncSession):
master = _make_master()
await index_page(db, master)
await db.commit()
hits = await search_pages(db, "")
assert hits == []
hits = await search_pages(db, " ")
assert hits == []
@pytest.mark.asyncio
async def test_no_match_returns_empty(self, db: AsyncSession):
master = _make_master(diplomatic_text="Explicit liber primus")
await index_page(db, master)
await db.commit()
hits = await search_pages(db, "zzzznonexistent")
assert hits == []
@pytest.mark.asyncio
async def test_results_sorted_by_score(self, db: AsyncSession):
# Page with many occurrences
master1 = _make_master(
page_id="ms-high",
folio_label="001r",
diplomatic_text="liber liber liber liber liber",
)
# Page with fewer occurrences
master2 = _make_master(
page_id="ms-low",
folio_label="002r",
diplomatic_text="liber primus",
)
await index_page(db, master1)
await index_page(db, master2)
await db.commit()
hits = await search_pages(db, "liber")
assert len(hits) == 2
assert hits[0]["page_id"] == "ms-high"
assert hits[0]["score"] > hits[1]["score"]
@pytest.mark.asyncio
async def test_limit_parameter(self, db: AsyncSession):
# Index 5 pages
for i in range(5):
master = _make_master(
page_id=f"ms-{i:03d}r",
folio_label=f"{i:03d}r",
diplomatic_text="common text shared across all pages",
)
await index_page(db, master)
await db.commit()
hits = await search_pages(db, "common", limit=3)
assert len(hits) == 3
@pytest.mark.asyncio
async def test_excerpt_is_populated(self, db: AsyncSession):
master = _make_master(diplomatic_text="Before context Explicit liber primus after context")
await index_page(db, master)
await db.commit()
hits = await search_pages(db, "liber")
assert len(hits) == 1
assert "liber" in hits[0]["excerpt"].lower()
@pytest.mark.asyncio
async def test_search_across_multiple_fields(self, db: AsyncSession):
"""A page matching in multiple fields should have a higher score."""
# Page matching in both diplomatic and translation
master1 = _make_master(
page_id="ms-multi",
diplomatic_text="liber primus",
translation_fr="liber premier",
)
# Page matching in diplomatic only
master2 = _make_master(
page_id="ms-single",
diplomatic_text="liber primus",
translation_fr="rien a voir",
)
await index_page(db, master1)
await index_page(db, master2)
await db.commit()
hits = await search_pages(db, "liber")
assert len(hits) == 2
assert hits[0]["page_id"] == "ms-multi"
assert hits[0]["score"] > hits[1]["score"]
# ββ Tests reindex_all βββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
class TestReindexAll:
@pytest.mark.asyncio
async def test_reindex_from_filesystem(self, db: AsyncSession, tmp_path: Path):
"""reindex_all should read master.json files and populate the index."""
# Create a fake corpus directory structure
corpus_dir = tmp_path / "corpora" / "test-ms" / "pages" / "001r"
corpus_dir.mkdir(parents=True)
master_data = {
"schema_version": "1.0",
"page_id": "test-ms-001r",
"corpus_profile": "medieval-illuminated",
"manuscript_id": "test-ms",
"folio_label": "001r",
"sequence": 1,
"image": {
"master": "https://example.com/image.jpg",
"width": 3000,
"height": 4000,
},
"layout": {"regions": []},
"ocr": {
"diplomatic_text": "Explicit liber primus",
"language": "la",
"confidence": 0.8,
},
"translation": {"fr": "Fin du premier livre", "en": ""},
}
(corpus_dir / "master.json").write_text(
json.dumps(master_data), encoding="utf-8"
)
count = await reindex_all(db, tmp_path)
assert count == 1
# Verify the page was indexed
hits = await search_pages(db, "liber")
assert len(hits) == 1
assert hits[0]["page_id"] == "test-ms-001r"
@pytest.mark.asyncio
async def test_reindex_skips_invalid_files(self, db: AsyncSession, tmp_path: Path):
"""reindex_all should skip invalid master.json files gracefully."""
corpus_dir = tmp_path / "corpora" / "test-ms" / "pages" / "bad"
corpus_dir.mkdir(parents=True)
# Write invalid JSON
(corpus_dir / "master.json").write_text("not valid json", encoding="utf-8")
count = await reindex_all(db, tmp_path)
assert count == 0
@pytest.mark.asyncio
async def test_reindex_empty_dir(self, db: AsyncSession, tmp_path: Path):
"""reindex_all on an empty data dir should return 0."""
count = await reindex_all(db, tmp_path)
assert count == 0
@pytest.mark.asyncio
async def test_reindex_multiple_pages(self, db: AsyncSession, tmp_path: Path):
"""reindex_all with multiple valid master.json files."""
for folio in ["001r", "002r", "003r"]:
page_dir = tmp_path / "corpora" / "test-ms" / "pages" / folio
page_dir.mkdir(parents=True)
data = {
"schema_version": "1.0",
"page_id": f"test-ms-{folio}",
"corpus_profile": "medieval-illuminated",
"manuscript_id": "test-ms",
"folio_label": folio,
"sequence": int(folio[:3]),
"image": {
"master": "https://example.com/image.jpg",
"width": 3000,
"height": 4000,
},
"layout": {"regions": []},
"ocr": {
"diplomatic_text": f"Text for folio {folio}",
"language": "la",
"confidence": 0.8,
},
}
(page_dir / "master.json").write_text(
json.dumps(data), encoding="utf-8"
)
count = await reindex_all(db, tmp_path)
assert count == 3
|