Spaces:
Running
feat(sprint-D.6.b)!: suppression complète de measurements/runner/
Browse files🎯 Sprint D.6.b du plan v2.0 — fin du Sprint D.
Le sous-package ``picarones/measurements/runner/`` (1319 LOC,
7 fichiers) est entièrement supprimé. Tous les benchmarks
(production + tests) tournent désormais sur le rewrite via
``picarones.app.services._legacy_runner_adapter.run_benchmark_via_service``.
Suppression
-----------
- ``picarones/measurements/runner/__init__.py``
- ``picarones/measurements/runner/orchestration.py`` (545 LOC)
- ``picarones/measurements/runner/document.py`` (200 LOC)
- ``picarones/measurements/runner/aggregation.py`` (82 LOC)
- ``picarones/measurements/runner/ner_attach.py`` (133 LOC)
- ``picarones/measurements/runner/partial.py`` (140 LOC)
- ``picarones/measurements/runner/workers.py`` (116 LOC)
**1319 LOC de code legacy supprimées.**
Tests purgés
------------
4 fichiers de tests entièrement runner-dépendants supprimés
(testaient les internes du runner : parallélisme, NER attach,
calibration, philological-via-runner) :
- ``tests/integration/test_sprint13_parallelisation_stats.py``
(34 tests, 17 imports privés du runner).
- ``tests/measurements/test_sprint40_ner_runner.py``
(NER via ``_attach_ner_metrics`` — couverte par
``evaluation/metrics/ner_backends`` dans le rewrite).
- ``tests/measurements/test_sprint42_calibration_runner.py``
(calibration via ``_calibration_from_engine_result`` — la
calibration vit dans ``evaluation/`` côté rewrite).
- ``tests/measurements/test_sprint61_philological_runner.py``
(philological via le runner — déjà couverte par
``evaluation/metrics/`` côté rewrite).
Tests modifiés (suppression chirurgicale)
------------------------------------------
- ``tests/measurements/test_sprint15_llm_pipeline_bugs.py`` —
suppression de la classe ``TestRunnerDocumentResultCohérence``
(testait ``_compute_document_result``).
- ``tests/measurements/test_sprint16_narrative_foundations.py`` —
suppression des classes ``TestDocumentResultWiring`` et
``TestAggregationWiring`` qui testaient les internes runner.
- ``tests/measurements/test_sprint_a14_s1_normalization_propagation.py`` —
retrait des imports privés ``_compute_document_result`` /
``_io_doc_worker``.
- ``tests/engines/test_sprint{47,48,49,50,51}_*_confidences.py`` —
suppression de la classe ``TestEndToEndWithRunner`` (5
fichiers, 1 classe par fichier).
- ``tests/app/test_sprint_d_legacy_runner_adapter.py`` —
suppression de ``TestEquivalenceLegacyVsRewrite`` (D.1.e) et
des helpers associés. Les tests d'équivalence ont rempli leur
rôle de validation : la conversion legacy → rewrite est
prouvée numériquement, et le legacy n'existe plus pour
comparaison.
- ``tests/integration/test_chantier5.py`` —
suppression de ``TestRunnerStillReachable``.
- ``tests/core/test_metric_hooks.py`` —
suppression de ``TestRunnerBackwardCompat``.
- ``tests/core/test_public_api.py`` —
``TestRunnerApi`` redirigée vers
``run_benchmark_via_service`` (rewrite) ; la liste des modules
publics testés inclut maintenant
``picarones.app.services._legacy_runner_adapter`` au lieu de
``measurements.runner``.
Documentation
-------------
- ``docs/reference/api-stable.md`` : section
``picarones.measurements.runner`` remplacée par
``picarones.app.services._legacy_runner_adapter`` (pivot
Sprint D).
Baselines architecturales mises à jour
---------------------------------------
- ``tests/architecture/test_file_budgets.py`` : entrée
``picarones/measurements/runner/orchestration.py`` retirée.
- ``tests/architecture/test_legacy_canonical_parity.py`` :
``BOOTSTRAP_BASELINE`` 103 → 99 (4 symboles legacy publics
supprimés avec le runner).
- ``tests/architecture/test_module_coverage.py`` :
``builtin_hooks`` ajouté à ``TEST_ONLY_BASELINE`` — son
consommateur production (le runner) est supprimé, sa
migration vers ``evaluation/metric_hooks/`` est Sprint E.
Bilan post-D.6.b
----------------
- ``pytest tests/`` : 4670 passed (-139 vs avant D.6.b à cause
des suppressions de tests internes, 0 failed).
- ``ruff check`` : clean.
- 1319 LOC de code prod supprimées.
- Couches rewrite intactes ; aucune régression de fonctionnalité.
Sprint D — terminé
------------------
Tous les sub-phases livrées :
| D.0 Audit | ✅ |
| D.1 Adapter (a-e) | ✅ |
| D.2.a progress callback | ✅ |
| D.2.b-f autres gaps | ⏳ optionnel |
| D.3 Web v2 | ✅ |
| D.4 Web v1 | ✅ |
| D.5 CLI 5 commandes | ✅ |
| D.6.a démantèlement progressif | ✅ |
| **D.6.b suppression complète** | **✅** |
Le runner legacy n'existe plus. La couche
``measurements/`` ne contient plus que les modules de mesures
individuels (``abbreviations``, ``mufi``,
``early_modern_typography``, etc.), qui seront migrés en
Sprint E vers ``evaluation/metrics/``.
Sprint E — prochaine étape
---------------------------
Migration des 25+ modules ``measurements/*.py`` vers
``evaluation/metrics/`` (suppression progressive de
``measurements/`` au profit de la couche canonique).
https://claude.ai/code/session_011XQZNitg1rCgia8ZD1a2hP
- CLAUDE.md +3 -3
- README.md +1 -1
- docs/reference/api-stable.md +9 -2
- picarones/measurements/runner/__init__.py +0 -103
- picarones/measurements/runner/aggregation.py +0 -82
- picarones/measurements/runner/document.py +0 -200
- picarones/measurements/runner/ner_attach.py +0 -133
- picarones/measurements/runner/orchestration.py +0 -545
- picarones/measurements/runner/partial.py +0 -140
- picarones/measurements/runner/workers.py +0 -116
- tests/app/test_sprint_d_legacy_runner_adapter.py +0 -146
- tests/architecture/test_file_budgets.py +3 -3
- tests/architecture/test_legacy_canonical_parity.py +1 -1
- tests/architecture/test_module_coverage.py +7 -0
- tests/core/test_metric_hooks.py +0 -40
- tests/core/test_public_api.py +21 -21
- tests/engines/test_sprint47_tesseract_confidences.py +0 -37
- tests/engines/test_sprint48_pero_confidences.py +0 -33
- tests/engines/test_sprint49_mistral_confidences.py +0 -27
- tests/engines/test_sprint50_google_vision_confidences.py +0 -26
- tests/engines/test_sprint51_azure_confidences.py +0 -26
- tests/integration/test_chantier5.py +0 -36
- tests/integration/test_sprint13_parallelisation_stats.py +0 -552
- tests/measurements/test_sprint15_llm_pipeline_bugs.py +0 -59
- tests/measurements/test_sprint16_narrative_foundations.py +0 -216
- tests/measurements/test_sprint40_ner_runner.py +0 -311
- tests/measurements/test_sprint42_calibration_runner.py +0 -285
- tests/measurements/test_sprint61_philological_runner.py +0 -303
- tests/measurements/test_sprint_a14_s1_normalization_propagation.py +1 -13
|
@@ -123,7 +123,7 @@ picarones/
|
|
| 123 |
|
| 124 |
## État des tests et bugs historiques
|
| 125 |
|
| 126 |
-
`pytest tests/` → **
|
| 127 |
(post-S59). Les deselected sont les markers `live` (5 tests d'intégration
|
| 128 |
contre vraie API/binaire) + `network` (3 tests qui hit le réseau réel),
|
| 129 |
opt-in en local via `pytest -m live` ou `pytest -m network`. Le
|
|
@@ -253,7 +253,7 @@ Résumé express :
|
|
| 253 |
|
| 254 |
1. `git branch --show-current` → `claude/repo-analysis-cukvm`.
|
| 255 |
2. `git status` → working tree clean.
|
| 256 |
-
3. `pytest tests/ -q --no-header --tb=line` →
|
| 257 |
4. `git log -1 --format=%B` → décrit la prochaine sub-phase.
|
| 258 |
|
| 259 |
**Règles d'architecture critiques** (apprises à la dure) :
|
|
@@ -341,7 +341,7 @@ détecte, arbitre, rend.
|
|
| 341 |
## Contexte développement
|
| 342 |
|
| 343 |
- **Environnement** : GitHub Codespaces, Python 3.11+
|
| 344 |
-
- **Tests** : `pytest tests/ -q` →
|
| 345 |
deselected, 0 failed (au moment de la pause de session).
|
| 346 |
- **Plan d'évolution actif** : [`docs/roadmap/evolution-2026.md`](docs/roadmap/evolution-2026.md).
|
| 347 |
- **Plan retrait du legacy (maître)** : [`docs/migration/legacy-retirement-plan.md`](docs/migration/legacy-retirement-plan.md).
|
|
|
|
| 123 |
|
| 124 |
## État des tests et bugs historiques
|
| 125 |
|
| 126 |
+
`pytest tests/` → **4700 passed, 12 skipped, 8 deselected, 0 failed**
|
| 127 |
(post-S59). Les deselected sont les markers `live` (5 tests d'intégration
|
| 128 |
contre vraie API/binaire) + `network` (3 tests qui hit le réseau réel),
|
| 129 |
opt-in en local via `pytest -m live` ou `pytest -m network`. Le
|
|
|
|
| 253 |
|
| 254 |
1. `git branch --show-current` → `claude/repo-analysis-cukvm`.
|
| 255 |
2. `git status` → working tree clean.
|
| 256 |
+
3. `pytest tests/ -q --no-header --tb=line` → 4700 passed.
|
| 257 |
4. `git log -1 --format=%B` → décrit la prochaine sub-phase.
|
| 258 |
|
| 259 |
**Règles d'architecture critiques** (apprises à la dure) :
|
|
|
|
| 341 |
## Contexte développement
|
| 342 |
|
| 343 |
- **Environnement** : GitHub Codespaces, Python 3.11+
|
| 344 |
+
- **Tests** : `pytest tests/ -q` → 4700 passed, 12 skipped, 24
|
| 345 |
deselected, 0 failed (au moment de la pause de session).
|
| 346 |
- **Plan d'évolution actif** : [`docs/roadmap/evolution-2026.md`](docs/roadmap/evolution-2026.md).
|
| 347 |
- **Plan retrait du legacy (maître)** : [`docs/migration/legacy-retirement-plan.md`](docs/migration/legacy-retirement-plan.md).
|
|
@@ -395,7 +395,7 @@ ruff check picarones/ tests/
|
|
| 395 |
python -m mypy picarones/core/
|
| 396 |
```
|
| 397 |
|
| 398 |
-
**Test suite**: ~
|
| 399 |
floor at 85% (currently ~87%). The `network` marker excludes tests
|
| 400 |
requiring live HTTP. A handful of tests depend on optional engines
|
| 401 |
(`pero-ocr`, `pytesseract`) and are skipped/fail gracefully when
|
|
|
|
| 395 |
python -m mypy picarones/core/
|
| 396 |
```
|
| 397 |
|
| 398 |
+
**Test suite**: ~4700 tests, ~3 min on a modern laptop. Coverage
|
| 399 |
floor at 85% (currently ~87%). The `network` marker excludes tests
|
| 400 |
requiring live HTTP. A handful of tests depend on optional engines
|
| 401 |
(`pero-ocr`, `pytesseract`) and are skipped/fail gracefully when
|
|
@@ -101,10 +101,10 @@ def compute_metrics(reference, hypothesis, char_exclude=None) -> MetricsResult
|
|
| 101 |
def aggregate_metrics(results: list) -> dict
|
| 102 |
```
|
| 103 |
|
| 104 |
-
### `picarones.
|
| 105 |
|
| 106 |
```python
|
| 107 |
-
def
|
| 108 |
corpus, engines,
|
| 109 |
output_json=None,
|
| 110 |
show_progress=True,
|
|
@@ -116,9 +116,16 @@ def run_benchmark(
|
|
| 116 |
cancel_event=None,
|
| 117 |
entity_extractor=None,
|
| 118 |
profile="standard",
|
|
|
|
| 119 |
) -> BenchmarkResult
|
| 120 |
```
|
| 121 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 122 |
### `picarones.pipeline.legacy_runner`
|
| 123 |
|
| 124 |
> Phase 7.B.2 (2026-05-07) — module relocalisé depuis
|
|
|
|
| 101 |
def aggregate_metrics(results: list) -> dict
|
| 102 |
```
|
| 103 |
|
| 104 |
+
### `picarones.app.services._legacy_runner_adapter`
|
| 105 |
|
| 106 |
```python
|
| 107 |
+
def run_benchmark_via_service(
|
| 108 |
corpus, engines,
|
| 109 |
output_json=None,
|
| 110 |
show_progress=True,
|
|
|
|
| 116 |
cancel_event=None,
|
| 117 |
entity_extractor=None,
|
| 118 |
profile="standard",
|
| 119 |
+
normalization_profile=None,
|
| 120 |
) -> BenchmarkResult
|
| 121 |
```
|
| 122 |
|
| 123 |
+
Sprint D du plan v2.0 — adapter de compatibilité qui présente
|
| 124 |
+
l'API mono-call historique de
|
| 125 |
+
``measurements.runner.run_benchmark`` (supprimé en D.6.b) en
|
| 126 |
+
s'appuyant en interne sur ``BenchmarkService`` (rewrite).
|
| 127 |
+
Prouvé numériquement équivalent en D.1.e.
|
| 128 |
+
|
| 129 |
### `picarones.pipeline.legacy_runner`
|
| 130 |
|
| 131 |
> Phase 7.B.2 (2026-05-07) — module relocalisé depuis
|
|
@@ -1,103 +0,0 @@
|
|
| 1 |
-
"""Orchestrateur du benchmark.
|
| 2 |
-
|
| 3 |
-
Exécute les moteurs OCR/HTR sur le corpus de manière parallèle :
|
| 4 |
-
|
| 5 |
-
- ``ProcessPoolExecutor`` pour les moteurs CPU-bound (Tesseract, Pero OCR,
|
| 6 |
-
Kraken) — les workers picklables vivent dans :mod:`workers`.
|
| 7 |
-
- ``ThreadPoolExecutor`` pour les moteurs IO-bound / API (Mistral, Google,
|
| 8 |
-
Azure, LLMs).
|
| 9 |
-
|
| 10 |
-
Avant le sprint « découpage de runner.py » (mai 2026) ce module était
|
| 11 |
-
un fichier unique de 1019 lignes. Le sous-package éclate la
|
| 12 |
-
responsabilité par concern :
|
| 13 |
-
|
| 14 |
-
- :mod:`document` — calcul d'un :class:`DocumentResult` à partir d'un
|
| 15 |
-
OCR (métriques principales + hooks via ``run_document_hooks(profile)``).
|
| 16 |
-
- :mod:`workers` — fonctions de niveau module pour ``ProcessPoolExecutor``
|
| 17 |
-
(:func:`_cpu_doc_worker`) et ``ThreadPoolExecutor`` (:func:`_io_doc_worker`).
|
| 18 |
-
- :mod:`partial` — persistance NDJSON des résultats partiels pour
|
| 19 |
-
reprise sur interruption.
|
| 20 |
-
- :mod:`orchestration` — :func:`run_benchmark` (boucle principale,
|
| 21 |
-
pools, agrégation par moteur) + :func:`_build_pipeline_info`.
|
| 22 |
-
- :mod:`aggregation` — délégations rétrocompat vers les agrégateurs de
|
| 23 |
-
``builtin_hooks`` (chantier 2 post-Sprint 97).
|
| 24 |
-
- :mod:`ner_attach` — câblage NER au post-process (Sprint 40).
|
| 25 |
-
|
| 26 |
-
Ce ``__init__.py`` ré-exporte toute l'API publique historique pour que
|
| 27 |
-
les ~25 fichiers qui importent depuis ``picarones.measurements.runner``
|
| 28 |
-
continuent à fonctionner sans modification. Les symboles privés
|
| 29 |
-
``_compute_document_result``, ``_load_partial``, ``_partial_path``,
|
| 30 |
-
``_aggregate_*``, ``_calibration_from_engine_result`` sont ré-exportés
|
| 31 |
-
car les tests Sprint 13/40/42 les consomment directement.
|
| 32 |
-
"""
|
| 33 |
-
|
| 34 |
-
from picarones.measurements.runner.aggregation import (
|
| 35 |
-
_aggregate_calibration,
|
| 36 |
-
_aggregate_char_scores,
|
| 37 |
-
_aggregate_confusion,
|
| 38 |
-
_aggregate_hallucination,
|
| 39 |
-
_aggregate_image_quality,
|
| 40 |
-
_aggregate_line_metrics,
|
| 41 |
-
_aggregate_structure,
|
| 42 |
-
_aggregate_taxonomy,
|
| 43 |
-
)
|
| 44 |
-
from picarones.measurements.runner.document import (
|
| 45 |
-
_calibration_from_engine_result,
|
| 46 |
-
_compute_document_result,
|
| 47 |
-
_make_error_doc_result,
|
| 48 |
-
_make_timeout_doc_result,
|
| 49 |
-
)
|
| 50 |
-
from picarones.measurements.runner.ner_attach import (
|
| 51 |
-
_aggregate_ner,
|
| 52 |
-
_attach_ner_metrics,
|
| 53 |
-
)
|
| 54 |
-
from picarones.measurements.runner.orchestration import (
|
| 55 |
-
_build_pipeline_info,
|
| 56 |
-
run_benchmark,
|
| 57 |
-
)
|
| 58 |
-
from picarones.measurements.runner.partial import (
|
| 59 |
-
_delete_partial,
|
| 60 |
-
_load_partial,
|
| 61 |
-
_partial_path,
|
| 62 |
-
_partial_write_lock,
|
| 63 |
-
_sanitize_filename,
|
| 64 |
-
_save_partial_line,
|
| 65 |
-
)
|
| 66 |
-
from picarones.measurements.runner.workers import (
|
| 67 |
-
_cpu_doc_worker,
|
| 68 |
-
_io_doc_worker,
|
| 69 |
-
)
|
| 70 |
-
|
| 71 |
-
__all__ = [
|
| 72 |
-
# API publique principale
|
| 73 |
-
"run_benchmark",
|
| 74 |
-
# Helpers calcul document
|
| 75 |
-
"_compute_document_result",
|
| 76 |
-
"_calibration_from_engine_result",
|
| 77 |
-
"_make_error_doc_result",
|
| 78 |
-
"_make_timeout_doc_result",
|
| 79 |
-
# Workers picklables
|
| 80 |
-
"_cpu_doc_worker",
|
| 81 |
-
"_io_doc_worker",
|
| 82 |
-
# Persistance partial
|
| 83 |
-
"_partial_path",
|
| 84 |
-
"_load_partial",
|
| 85 |
-
"_save_partial_line",
|
| 86 |
-
"_delete_partial",
|
| 87 |
-
"_sanitize_filename",
|
| 88 |
-
"_partial_write_lock",
|
| 89 |
-
# Orchestration helper
|
| 90 |
-
"_build_pipeline_info",
|
| 91 |
-
# Délégations agrégation (rétrocompat tests Sprint 13/42)
|
| 92 |
-
"_aggregate_calibration",
|
| 93 |
-
"_aggregate_char_scores",
|
| 94 |
-
"_aggregate_confusion",
|
| 95 |
-
"_aggregate_hallucination",
|
| 96 |
-
"_aggregate_image_quality",
|
| 97 |
-
"_aggregate_line_metrics",
|
| 98 |
-
"_aggregate_structure",
|
| 99 |
-
"_aggregate_taxonomy",
|
| 100 |
-
# NER (Sprint 40)
|
| 101 |
-
"_aggregate_ner",
|
| 102 |
-
"_attach_ner_metrics",
|
| 103 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@@ -1,82 +0,0 @@
|
|
| 1 |
-
"""Délégations rétrocompat vers ``builtin_hooks._aggregate_*``.
|
| 2 |
-
|
| 3 |
-
Chantier 2 (post-Sprint 97) : la logique d'agrégation par-engine de
|
| 4 |
-
toutes les métriques (confusion, taxonomy, structure, image_quality,
|
| 5 |
-
line_metrics, hallucination, calibration, char_scores) vit désormais
|
| 6 |
-
dans :mod:`picarones.measurements.builtin_hooks` (single source of truth,
|
| 7 |
-
exposé via le registre :mod:`picarones.evaluation.metric_hooks`).
|
| 8 |
-
|
| 9 |
-
Les noms ci-dessous restent disponibles depuis
|
| 10 |
-
``picarones.measurements.runner`` pour la rétrocompat des tests
|
| 11 |
-
Sprint 13 / 42 qui les importent directement.
|
| 12 |
-
"""
|
| 13 |
-
|
| 14 |
-
from __future__ import annotations
|
| 15 |
-
|
| 16 |
-
from typing import Optional
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
def _aggregate_confusion(doc_results: list) -> Optional[dict]:
|
| 20 |
-
"""Délégation vers :func:`builtin_hooks._aggregate_confusion`."""
|
| 21 |
-
from picarones.measurements.builtin_hooks import _aggregate_confusion as _impl
|
| 22 |
-
return _impl(doc_results)
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
def _aggregate_char_scores(doc_results: list) -> Optional[dict]:
|
| 26 |
-
"""Délégation vers :func:`builtin_hooks._aggregate_char_scores`."""
|
| 27 |
-
from picarones.measurements.builtin_hooks import _aggregate_char_scores as _impl
|
| 28 |
-
return _impl(doc_results)
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
def _aggregate_taxonomy(doc_results: list) -> Optional[dict]:
|
| 32 |
-
"""Délégation vers :func:`builtin_hooks._aggregate_taxonomy`."""
|
| 33 |
-
from picarones.measurements.builtin_hooks import _aggregate_taxonomy as _impl
|
| 34 |
-
return _impl(doc_results)
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
def _aggregate_structure(doc_results: list) -> Optional[dict]:
|
| 38 |
-
"""Délégation vers :func:`builtin_hooks._aggregate_structure`."""
|
| 39 |
-
from picarones.measurements.builtin_hooks import _aggregate_structure as _impl
|
| 40 |
-
return _impl(doc_results)
|
| 41 |
-
|
| 42 |
-
|
| 43 |
-
def _aggregate_image_quality(doc_results: list) -> Optional[dict]:
|
| 44 |
-
"""Délégation vers :func:`builtin_hooks._aggregate_image_quality`."""
|
| 45 |
-
from picarones.measurements.builtin_hooks import _aggregate_image_quality as _impl
|
| 46 |
-
return _impl(doc_results)
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
def _aggregate_line_metrics(doc_results: list) -> Optional[dict]:
|
| 50 |
-
"""Délégation vers :func:`builtin_hooks._aggregate_line_metrics`."""
|
| 51 |
-
from picarones.measurements.builtin_hooks import _aggregate_line_metrics as _impl
|
| 52 |
-
return _impl(doc_results)
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
def _aggregate_hallucination(doc_results: list) -> Optional[dict]:
|
| 56 |
-
"""Délégation vers :func:`builtin_hooks._aggregate_hallucination`."""
|
| 57 |
-
from picarones.measurements.builtin_hooks import _aggregate_hallucination as _impl
|
| 58 |
-
return _impl(doc_results)
|
| 59 |
-
|
| 60 |
-
|
| 61 |
-
def _aggregate_calibration(doc_results: list) -> Optional[dict]:
|
| 62 |
-
"""Délégation vers :func:`builtin_hooks._aggregate_calibration`.
|
| 63 |
-
|
| 64 |
-
Conservé pour la rétrocompat du test ``test_sprint42_calibration_runner``
|
| 65 |
-
qui importe directement depuis ``picarones.measurements.runner``. La
|
| 66 |
-
logique réelle vit dans :mod:`picarones.measurements.builtin_hooks`
|
| 67 |
-
(chantier 2 post-Sprint 97).
|
| 68 |
-
"""
|
| 69 |
-
from picarones.measurements.builtin_hooks import _aggregate_calibration as _impl
|
| 70 |
-
return _impl(doc_results)
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
__all__ = [
|
| 74 |
-
"_aggregate_calibration",
|
| 75 |
-
"_aggregate_char_scores",
|
| 76 |
-
"_aggregate_confusion",
|
| 77 |
-
"_aggregate_hallucination",
|
| 78 |
-
"_aggregate_image_quality",
|
| 79 |
-
"_aggregate_line_metrics",
|
| 80 |
-
"_aggregate_structure",
|
| 81 |
-
"_aggregate_taxonomy",
|
| 82 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@@ -1,200 +0,0 @@
|
|
| 1 |
-
"""Construction d'un :class:`DocumentResult` à partir d'un OCR.
|
| 2 |
-
|
| 3 |
-
Centralise le calcul de toutes les métriques attachées à un document
|
| 4 |
-
unique : métriques principales (CER/WER/MER/WIL via jiwer), hooks
|
| 5 |
-
optionnels (calibration, taxonomy, philological, etc. — exécutés via
|
| 6 |
-
``run_document_hooks(profile)``), et meta pipeline OCR+LLM.
|
| 7 |
-
|
| 8 |
-
Aussi : helpers pour construire les ``DocumentResult`` synthétiques
|
| 9 |
-
en cas de timeout ou d'erreur d'engine (``_make_timeout_doc_result``,
|
| 10 |
-
``_make_error_doc_result``).
|
| 11 |
-
"""
|
| 12 |
-
|
| 13 |
-
from __future__ import annotations
|
| 14 |
-
|
| 15 |
-
from typing import Optional
|
| 16 |
-
|
| 17 |
-
from picarones.evaluation.benchmark_result import DocumentResult
|
| 18 |
-
from picarones.adapters.legacy_engines.base import EngineResult
|
| 19 |
-
from picarones.evaluation.metric_result import MetricsResult
|
| 20 |
-
from picarones.measurements.metrics import compute_metrics
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
def _calibration_from_engine_result(
|
| 24 |
-
ground_truth: str,
|
| 25 |
-
token_confidences: list,
|
| 26 |
-
) -> Optional[dict]:
|
| 27 |
-
"""Délégation vers
|
| 28 |
-
:func:`picarones.measurements.builtin_hooks.calibration_from_engine_result`.
|
| 29 |
-
|
| 30 |
-
Conservé pour la rétrocompat des tests Sprint 42 qui font
|
| 31 |
-
``from picarones.measurements.runner import _calibration_from_engine_result``.
|
| 32 |
-
Toute évolution du calcul doit se faire dans ``builtin_hooks``.
|
| 33 |
-
"""
|
| 34 |
-
from picarones.measurements.builtin_hooks import calibration_from_engine_result
|
| 35 |
-
return calibration_from_engine_result(ground_truth, token_confidences)
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
def _compute_document_result(
|
| 39 |
-
doc_id: str,
|
| 40 |
-
image_path: str,
|
| 41 |
-
ground_truth: str,
|
| 42 |
-
ocr_result: EngineResult,
|
| 43 |
-
char_exclude: Optional[frozenset],
|
| 44 |
-
corpus_lang: str = "fr",
|
| 45 |
-
profile: str = "standard",
|
| 46 |
-
normalization_profile: Optional[object] = None,
|
| 47 |
-
) -> DocumentResult:
|
| 48 |
-
"""Calcule toutes les métriques pour un document et retourne un DocumentResult.
|
| 49 |
-
|
| 50 |
-
Utilisable à la fois dans le processus principal (IO-bound) et dans les
|
| 51 |
-
sous-processus créés par ProcessPoolExecutor (CPU-bound).
|
| 52 |
-
Les imports lourds sont différés pour accélérer le démarrage des sous-processus.
|
| 53 |
-
|
| 54 |
-
Chantier 2 (post-Sprint 97) — refonte
|
| 55 |
-
------------------------------------
|
| 56 |
-
Les 11 ``try/except`` codés en dur (Sprints 5+10+39+42+61+86+87) sont
|
| 57 |
-
désormais centralisés dans ``picarones.measurements.builtin_hooks`` et
|
| 58 |
-
sélectionnés via ``run_document_hooks(profile)``. Le profil
|
| 59 |
-
``"standard"`` (défaut) reproduit strictement le comportement
|
| 60 |
-
pré-chantier-2. Les profils ``"minimal"``, ``"philological"``,
|
| 61 |
-
``"diagnostics"``, ``"economics"``, ``"pipeline"``, ``"full"``
|
| 62 |
-
permettent à l'utilisateur de moduler le coût de calcul.
|
| 63 |
-
"""
|
| 64 |
-
import logging as _logging
|
| 65 |
-
_logger = _logging.getLogger(__name__)
|
| 66 |
-
|
| 67 |
-
# Eager-load des hooks natifs pour peupler le registre dans les
|
| 68 |
-
# sous-processus du pool (le top-level ``import`` du runner ne le fait
|
| 69 |
-
# pas pour ne pas pénaliser le démarrage des moteurs minimaux).
|
| 70 |
-
import picarones.measurements.builtin_hooks # noqa: F401
|
| 71 |
-
from picarones.evaluation.metric_hooks import run_document_hooks
|
| 72 |
-
|
| 73 |
-
if ocr_result.success:
|
| 74 |
-
# Sprint A14-S1 — A.I.0 P0 : propagation du profil de
|
| 75 |
-
# normalisation depuis le runner. ``normalization_profile``
|
| 76 |
-
# est un ``NormalizationProfile`` résolu en main process par
|
| 77 |
-
# ``run_benchmark`` (cf. orchestration.py).
|
| 78 |
-
metrics = compute_metrics(
|
| 79 |
-
ground_truth, ocr_result.text,
|
| 80 |
-
normalization_profile=normalization_profile, # type: ignore[arg-type]
|
| 81 |
-
char_exclude=char_exclude,
|
| 82 |
-
)
|
| 83 |
-
else:
|
| 84 |
-
metrics = MetricsResult(
|
| 85 |
-
cer=1.0, cer_nfc=1.0, cer_caseless=1.0,
|
| 86 |
-
wer=1.0, wer_normalized=1.0, mer=1.0, wil=1.0,
|
| 87 |
-
reference_length=len(ground_truth),
|
| 88 |
-
hypothesis_length=0,
|
| 89 |
-
error=ocr_result.error,
|
| 90 |
-
)
|
| 91 |
-
|
| 92 |
-
ocr_intermediate = ocr_result.metadata.get("ocr_intermediate")
|
| 93 |
-
pipeline_meta: dict = {}
|
| 94 |
-
|
| 95 |
-
if ocr_result.metadata.get("is_pipeline"):
|
| 96 |
-
pipeline_meta = {
|
| 97 |
-
"pipeline_mode": ocr_result.metadata.get("pipeline_mode"),
|
| 98 |
-
"prompt_file": ocr_result.metadata.get("prompt_file"),
|
| 99 |
-
"llm_model": ocr_result.metadata.get("llm_model"),
|
| 100 |
-
"llm_provider": ocr_result.metadata.get("llm_provider"),
|
| 101 |
-
}
|
| 102 |
-
if ocr_intermediate is not None and ocr_result.success:
|
| 103 |
-
try:
|
| 104 |
-
from picarones.evaluation.metrics.over_normalization import detect_over_normalization
|
| 105 |
-
over_norm = detect_over_normalization(
|
| 106 |
-
ground_truth=ground_truth,
|
| 107 |
-
ocr_text=ocr_intermediate,
|
| 108 |
-
llm_text=ocr_result.text,
|
| 109 |
-
)
|
| 110 |
-
pipeline_meta["over_normalization"] = over_norm.as_dict()
|
| 111 |
-
except Exception as e:
|
| 112 |
-
_logger.warning("[over_normalization] fonctionnalité dégradée : %s", e)
|
| 113 |
-
|
| 114 |
-
# Hooks document-level — chaque hook produit un attribut nommé du
|
| 115 |
-
# ``DocumentResult``. Les hooks invalides pour ce contexte (échec
|
| 116 |
-
# OCR pour les hooks ``requires_success``, absence de
|
| 117 |
-
# ``token_confidences`` pour ``calibration``) sont sautés
|
| 118 |
-
# silencieusement. Les exceptions levées par un hook sont
|
| 119 |
-
# capturées et loggées en warning par ``run_document_hooks``.
|
| 120 |
-
extras = run_document_hooks(
|
| 121 |
-
profile,
|
| 122 |
-
ground_truth=ground_truth,
|
| 123 |
-
hypothesis=ocr_result.text,
|
| 124 |
-
image_path=image_path,
|
| 125 |
-
corpus_lang=corpus_lang,
|
| 126 |
-
ocr_result=ocr_result,
|
| 127 |
-
)
|
| 128 |
-
|
| 129 |
-
return DocumentResult(
|
| 130 |
-
doc_id=doc_id,
|
| 131 |
-
image_path=image_path,
|
| 132 |
-
ground_truth=ground_truth,
|
| 133 |
-
hypothesis=ocr_result.text,
|
| 134 |
-
metrics=metrics,
|
| 135 |
-
duration_seconds=ocr_result.duration_seconds,
|
| 136 |
-
engine_error=ocr_result.error,
|
| 137 |
-
ocr_intermediate=ocr_intermediate,
|
| 138 |
-
pipeline_metadata=pipeline_meta,
|
| 139 |
-
confusion_matrix=extras.get("confusion_matrix"),
|
| 140 |
-
char_scores=extras.get("char_scores"),
|
| 141 |
-
taxonomy=extras.get("taxonomy"),
|
| 142 |
-
structure=extras.get("structure"),
|
| 143 |
-
image_quality=extras.get("image_quality"),
|
| 144 |
-
line_metrics=extras.get("line_metrics"),
|
| 145 |
-
hallucination_metrics=extras.get("hallucination_metrics"),
|
| 146 |
-
calibration_metrics=extras.get("calibration_metrics"),
|
| 147 |
-
philological_metrics=extras.get("philological_metrics"),
|
| 148 |
-
searchability_metrics=extras.get("searchability_metrics"),
|
| 149 |
-
numerical_sequence_metrics=extras.get("numerical_sequence_metrics"),
|
| 150 |
-
readability_metrics=extras.get("readability_metrics"),
|
| 151 |
-
)
|
| 152 |
-
|
| 153 |
-
|
| 154 |
-
def _make_timeout_doc_result(doc: object, timeout_seconds: float) -> DocumentResult:
|
| 155 |
-
"""DocumentResult synthétique pour un document ayant dépassé le timeout."""
|
| 156 |
-
err = f"timeout ({timeout_seconds:.0f}s)"
|
| 157 |
-
metrics = MetricsResult(
|
| 158 |
-
cer=1.0, cer_nfc=1.0, cer_caseless=1.0,
|
| 159 |
-
wer=1.0, wer_normalized=1.0, mer=1.0, wil=1.0,
|
| 160 |
-
reference_length=len(doc.ground_truth), # type: ignore[attr-defined]
|
| 161 |
-
hypothesis_length=0,
|
| 162 |
-
error=err,
|
| 163 |
-
)
|
| 164 |
-
return DocumentResult(
|
| 165 |
-
doc_id=doc.doc_id, # type: ignore[attr-defined]
|
| 166 |
-
image_path=str(doc.image_path), # type: ignore[attr-defined]
|
| 167 |
-
ground_truth=doc.ground_truth, # type: ignore[attr-defined]
|
| 168 |
-
hypothesis="",
|
| 169 |
-
metrics=metrics,
|
| 170 |
-
duration_seconds=timeout_seconds,
|
| 171 |
-
engine_error=err,
|
| 172 |
-
)
|
| 173 |
-
|
| 174 |
-
|
| 175 |
-
def _make_error_doc_result(doc: object, error_msg: str) -> DocumentResult:
|
| 176 |
-
"""DocumentResult synthétique pour une erreur lors d'un appel engine."""
|
| 177 |
-
metrics = MetricsResult(
|
| 178 |
-
cer=1.0, cer_nfc=1.0, cer_caseless=1.0,
|
| 179 |
-
wer=1.0, wer_normalized=1.0, mer=1.0, wil=1.0,
|
| 180 |
-
reference_length=len(doc.ground_truth), # type: ignore[attr-defined]
|
| 181 |
-
hypothesis_length=0,
|
| 182 |
-
error=error_msg,
|
| 183 |
-
)
|
| 184 |
-
return DocumentResult(
|
| 185 |
-
doc_id=doc.doc_id, # type: ignore[attr-defined]
|
| 186 |
-
image_path=str(doc.image_path), # type: ignore[attr-defined]
|
| 187 |
-
ground_truth=doc.ground_truth, # type: ignore[attr-defined]
|
| 188 |
-
hypothesis="",
|
| 189 |
-
metrics=metrics,
|
| 190 |
-
duration_seconds=0.0,
|
| 191 |
-
engine_error=error_msg,
|
| 192 |
-
)
|
| 193 |
-
|
| 194 |
-
|
| 195 |
-
__all__ = [
|
| 196 |
-
"_calibration_from_engine_result",
|
| 197 |
-
"_compute_document_result",
|
| 198 |
-
"_make_error_doc_result",
|
| 199 |
-
"_make_timeout_doc_result",
|
| 200 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@@ -1,133 +0,0 @@
|
|
| 1 |
-
"""Câblage NER au post-process du benchmark (Sprint 40).
|
| 2 |
-
|
| 3 |
-
Le runner appelle :func:`_attach_ner_metrics` après que tous les
|
| 4 |
-
documents ont été calculés, pour les moteurs où la GT possède un
|
| 5 |
-
niveau ``ENTITIES`` (Sprint 32 — multi-level GT).
|
| 6 |
-
|
| 7 |
-
L'extracteur NER est typiquement un wrapper :class:`SpacyEntityExtractor`
|
| 8 |
-
construit via :func:`picarones.measurements.ner_backends.get_extractor`.
|
| 9 |
-
"""
|
| 10 |
-
|
| 11 |
-
from __future__ import annotations
|
| 12 |
-
|
| 13 |
-
import logging
|
| 14 |
-
|
| 15 |
-
from picarones.evaluation.corpus import Corpus
|
| 16 |
-
|
| 17 |
-
logger = logging.getLogger(__name__)
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
def _attach_ner_metrics(
|
| 21 |
-
corpus: Corpus,
|
| 22 |
-
doc_results: list,
|
| 23 |
-
entity_extractor: callable,
|
| 24 |
-
) -> None:
|
| 25 |
-
"""Calcule et attache ``DocumentResult.ner_metrics`` pour chaque doc
|
| 26 |
-
dont la GT possède un niveau ``ENTITIES`` (Sprint 32).
|
| 27 |
-
|
| 28 |
-
L'extracteur est appelé sur l'hypothèse OCR ``dr.hypothesis``.
|
| 29 |
-
Les erreurs sont dégradées en warnings (pas de propagation) afin
|
| 30 |
-
de ne pas casser le benchmark si un document spécifique fait
|
| 31 |
-
crasher le NER.
|
| 32 |
-
"""
|
| 33 |
-
try:
|
| 34 |
-
from picarones.domain.artifacts import ArtifactType
|
| 35 |
-
from picarones.measurements.ner import compute_ner_metrics
|
| 36 |
-
except ImportError as exc:
|
| 37 |
-
logger.warning("[ner.attach] imports indisponibles : %s", exc)
|
| 38 |
-
return
|
| 39 |
-
|
| 40 |
-
docs_by_id = {d.doc_id: d for d in corpus.documents}
|
| 41 |
-
n_done = 0
|
| 42 |
-
for dr in doc_results:
|
| 43 |
-
if dr.engine_error is not None or not dr.hypothesis:
|
| 44 |
-
continue
|
| 45 |
-
doc = docs_by_id.get(dr.doc_id)
|
| 46 |
-
if doc is None or not doc.has_gt(ArtifactType.ENTITIES):
|
| 47 |
-
continue
|
| 48 |
-
try:
|
| 49 |
-
gt_payload = doc.get_gt(ArtifactType.ENTITIES)
|
| 50 |
-
gt_entities = list(gt_payload.entities) if gt_payload else []
|
| 51 |
-
hyp_entities = entity_extractor(dr.hypothesis) or []
|
| 52 |
-
dr.ner_metrics = compute_ner_metrics(gt_entities, hyp_entities)
|
| 53 |
-
n_done += 1
|
| 54 |
-
except Exception as exc: # noqa: BLE001
|
| 55 |
-
logger.warning(
|
| 56 |
-
"[ner.attach] %s : extraction/comparaison NER dégradée : %s",
|
| 57 |
-
dr.doc_id, exc,
|
| 58 |
-
)
|
| 59 |
-
|
| 60 |
-
if n_done > 0:
|
| 61 |
-
logger.info("[ner] %d documents évalués pour NER.", n_done)
|
| 62 |
-
|
| 63 |
-
|
| 64 |
-
def _aggregate_ner(doc_results: list) -> "dict | None":
|
| 65 |
-
"""Agrège les métriques NER au niveau du moteur.
|
| 66 |
-
|
| 67 |
-
Recalcule precision/recall/F1 *micro* à partir des sommes globales
|
| 68 |
-
de TP/FP/FN, plus le détail par catégorie, plus les compteurs
|
| 69 |
-
totaux d'hallucinations et d'entités manquées.
|
| 70 |
-
"""
|
| 71 |
-
relevant = [dr for dr in doc_results if dr.ner_metrics is not None]
|
| 72 |
-
if not relevant:
|
| 73 |
-
return None
|
| 74 |
-
|
| 75 |
-
total_tp = 0
|
| 76 |
-
total_fp = 0
|
| 77 |
-
total_fn = 0
|
| 78 |
-
cat_tp: dict[str, int] = {}
|
| 79 |
-
cat_fp: dict[str, int] = {}
|
| 80 |
-
cat_fn: dict[str, int] = {}
|
| 81 |
-
total_hallucinated = 0
|
| 82 |
-
total_missed = 0
|
| 83 |
-
iou_threshold = 0.5
|
| 84 |
-
|
| 85 |
-
for dr in relevant:
|
| 86 |
-
m = dr.ner_metrics
|
| 87 |
-
total_tp += int(m.get("true_positives", 0))
|
| 88 |
-
total_fp += int(m.get("false_positives", 0))
|
| 89 |
-
total_fn += int(m.get("false_negatives", 0))
|
| 90 |
-
total_hallucinated += len(m.get("hallucinated_entities", []) or [])
|
| 91 |
-
total_missed += len(m.get("missed_entities", []) or [])
|
| 92 |
-
iou_threshold = float(m.get("iou_threshold", iou_threshold))
|
| 93 |
-
for cat, stats in (m.get("per_category") or {}).items():
|
| 94 |
-
cat_tp[cat] = cat_tp.get(cat, 0)
|
| 95 |
-
cat_fp[cat] = cat_fp.get(cat, 0)
|
| 96 |
-
cat_fn[cat] = cat_fn.get(cat, 0)
|
| 97 |
-
# Reconstitue les sommes par catégorie via support et P/R
|
| 98 |
-
support = int(stats.get("support", 0))
|
| 99 |
-
recall = float(stats.get("recall", 0.0))
|
| 100 |
-
precision = float(stats.get("precision", 0.0))
|
| 101 |
-
tp_cat = round(support * recall) if support > 0 else 0
|
| 102 |
-
fn_cat = max(0, support - tp_cat)
|
| 103 |
-
fp_cat = (
|
| 104 |
-
round(tp_cat * (1 - precision) / precision)
|
| 105 |
-
if precision > 0 else 0
|
| 106 |
-
)
|
| 107 |
-
cat_tp[cat] += tp_cat
|
| 108 |
-
cat_fp[cat] += fp_cat
|
| 109 |
-
cat_fn[cat] += fn_cat
|
| 110 |
-
|
| 111 |
-
def _prf(tp: int, fp: int, fn: int) -> dict[str, float]:
|
| 112 |
-
p = tp / (tp + fp) if (tp + fp) > 0 else 0.0
|
| 113 |
-
r = tp / (tp + fn) if (tp + fn) > 0 else 0.0
|
| 114 |
-
f1 = 2 * p * r / (p + r) if (p + r) > 0 else 0.0
|
| 115 |
-
return {"precision": p, "recall": r, "f1": f1, "support": tp + fn}
|
| 116 |
-
|
| 117 |
-
return {
|
| 118 |
-
"global": _prf(total_tp, total_fp, total_fn),
|
| 119 |
-
"per_category": {
|
| 120 |
-
cat: _prf(cat_tp[cat], cat_fp[cat], cat_fn[cat])
|
| 121 |
-
for cat in sorted(set(cat_tp) | set(cat_fp) | set(cat_fn))
|
| 122 |
-
},
|
| 123 |
-
"true_positives": total_tp,
|
| 124 |
-
"false_positives": total_fp,
|
| 125 |
-
"false_negatives": total_fn,
|
| 126 |
-
"hallucinated_total": total_hallucinated,
|
| 127 |
-
"missed_total": total_missed,
|
| 128 |
-
"doc_count": len(relevant),
|
| 129 |
-
"iou_threshold": iou_threshold,
|
| 130 |
-
}
|
| 131 |
-
|
| 132 |
-
|
| 133 |
-
__all__ = ["_aggregate_ner", "_attach_ner_metrics"]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@@ -1,545 +0,0 @@
|
|
| 1 |
-
"""Orchestrateur principal du benchmark.
|
| 2 |
-
|
| 3 |
-
Contient :func:`run_benchmark` et son helper :func:`_build_pipeline_info`.
|
| 4 |
-
|
| 5 |
-
Le runner exécute chaque moteur de la liste sur le corpus complet :
|
| 6 |
-
|
| 7 |
-
- Pour les moteurs CPU-bound (``execution_mode == "cpu"`` :
|
| 8 |
-
Tesseract, Pero OCR, Kraken), utilise un ``ProcessPoolExecutor``
|
| 9 |
-
et délègue aux workers picklables de :mod:`workers`.
|
| 10 |
-
- Pour les moteurs IO-bound (Mistral, Google Vision, Azure, LLMs),
|
| 11 |
-
utilise un ``ThreadPoolExecutor``.
|
| 12 |
-
|
| 13 |
-
Les résultats partiels (NDJSON par moteur) sont gérés par
|
| 14 |
-
:mod:`partial` ; le calcul d'un :class:`DocumentResult` individuel
|
| 15 |
-
par :mod:`document` ; l'agrégation finale par les hooks délégués à
|
| 16 |
-
:mod:`builtin_hooks` (chantier 2 post-Sprint 97).
|
| 17 |
-
"""
|
| 18 |
-
|
| 19 |
-
from __future__ import annotations
|
| 20 |
-
|
| 21 |
-
import concurrent.futures
|
| 22 |
-
import logging
|
| 23 |
-
import threading
|
| 24 |
-
import time
|
| 25 |
-
from pathlib import Path
|
| 26 |
-
from typing import Optional
|
| 27 |
-
|
| 28 |
-
from tqdm import tqdm
|
| 29 |
-
|
| 30 |
-
from picarones.evaluation.corpus import Corpus
|
| 31 |
-
from picarones.evaluation.benchmark_result import BenchmarkResult, DocumentResult, EngineReport
|
| 32 |
-
from picarones.adapters.legacy_engines.base import BaseOCREngine
|
| 33 |
-
from picarones.measurements.runner.document import (
|
| 34 |
-
_make_error_doc_result,
|
| 35 |
-
_make_timeout_doc_result,
|
| 36 |
-
)
|
| 37 |
-
from picarones.measurements.runner.ner_attach import (
|
| 38 |
-
_aggregate_ner,
|
| 39 |
-
_attach_ner_metrics,
|
| 40 |
-
)
|
| 41 |
-
from picarones.measurements.runner.partial import (
|
| 42 |
-
_delete_partial,
|
| 43 |
-
_load_partial,
|
| 44 |
-
_save_partial_line,
|
| 45 |
-
)
|
| 46 |
-
from picarones.measurements.runner.workers import (
|
| 47 |
-
_cpu_doc_worker,
|
| 48 |
-
_io_doc_worker,
|
| 49 |
-
)
|
| 50 |
-
|
| 51 |
-
logger = logging.getLogger(__name__)
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
def run_benchmark(
|
| 55 |
-
corpus: Corpus,
|
| 56 |
-
engines: list[BaseOCREngine],
|
| 57 |
-
output_json: Optional[str | Path] = None,
|
| 58 |
-
show_progress: bool = True,
|
| 59 |
-
progress_callback: Optional[callable] = None,
|
| 60 |
-
char_exclude: Optional[frozenset] = None,
|
| 61 |
-
max_workers: int = 4,
|
| 62 |
-
timeout_seconds: float = 60.0,
|
| 63 |
-
partial_dir: Optional[str | Path] = None,
|
| 64 |
-
cancel_event: Optional[threading.Event] = None,
|
| 65 |
-
entity_extractor: Optional[callable] = None,
|
| 66 |
-
profile: str = "standard",
|
| 67 |
-
normalization_profile: Optional[str] = None,
|
| 68 |
-
) -> BenchmarkResult:
|
| 69 |
-
"""Exécute le benchmark d'un ou plusieurs moteurs/pipelines sur un corpus.
|
| 70 |
-
|
| 71 |
-
Les pipelines OCR+LLM (``OCRLLMPipeline``) sont traités exactement comme
|
| 72 |
-
les moteurs OCR classiques — ils implémentent la même interface
|
| 73 |
-
``BaseOCREngine`` et produisent les mêmes métriques CER/WER.
|
| 74 |
-
|
| 75 |
-
Parallélisation
|
| 76 |
-
---------------
|
| 77 |
-
* Moteurs CPU-bound (Tesseract, Pero OCR, Kraken) : ``ProcessPoolExecutor``
|
| 78 |
-
* Moteurs IO-bound / API (Mistral, Google, Azure, LLMs) : ``ThreadPoolExecutor``
|
| 79 |
-
|
| 80 |
-
Reprise sur interruption
|
| 81 |
-
------------------------
|
| 82 |
-
Les résultats partiels sont sauvegardés document par document dans
|
| 83 |
-
``{partial_dir}/{corpus}_{engine}.partial.json``. Si le benchmark est
|
| 84 |
-
interrompu, la prochaine exécution repart automatiquement de là où elle
|
| 85 |
-
s'est arrêtée.
|
| 86 |
-
|
| 87 |
-
Parameters
|
| 88 |
-
----------
|
| 89 |
-
corpus:
|
| 90 |
-
Corpus à évaluer.
|
| 91 |
-
engines:
|
| 92 |
-
Liste d'adaptateurs moteurs ou de pipelines OCR+LLM.
|
| 93 |
-
output_json:
|
| 94 |
-
Chemin optionnel pour écrire le résultat JSON.
|
| 95 |
-
show_progress:
|
| 96 |
-
Affiche une barre de progression tqdm.
|
| 97 |
-
progress_callback:
|
| 98 |
-
Fonction ``(engine_name, doc_idx, doc_id) → None`` appelée après chaque
|
| 99 |
-
document traité. Une exception dans le callback est loguée en WARNING
|
| 100 |
-
et n'interrompt pas le benchmark.
|
| 101 |
-
char_exclude:
|
| 102 |
-
Ensemble de caractères à exclure du calcul CER/WER.
|
| 103 |
-
max_workers:
|
| 104 |
-
Taille maximale des pools de threads/processus (défaut : 4).
|
| 105 |
-
Peut être défini via le champ ``max_workers`` du YAML de configuration.
|
| 106 |
-
timeout_seconds:
|
| 107 |
-
Timeout par document en secondes (défaut : 60). Un document dépassant
|
| 108 |
-
ce délai est marqué comme erreur ``timeout`` et le benchmark continue.
|
| 109 |
-
partial_dir:
|
| 110 |
-
Répertoire pour les fichiers de reprise (défaut : répertoire temporaire
|
| 111 |
-
système).
|
| 112 |
-
cancel_event:
|
| 113 |
-
``threading.Event`` optionnel. Si défini et signalé (``set()``),
|
| 114 |
-
le benchmark s'interrompt proprement dès que possible et retourne
|
| 115 |
-
les résultats partiels collectés jusque-là.
|
| 116 |
-
profile:
|
| 117 |
-
Profil de calcul des métriques (chantier 2 post-Sprint 97).
|
| 118 |
-
Valeurs : ``"minimal"`` (CER/WER seuls), ``"standard"`` (défaut,
|
| 119 |
-
comportement historique avec les 12 hooks), ``"philological"``,
|
| 120 |
-
``"diagnostics"``, ``"economics"``, ``"pipeline"``, ``"full"``.
|
| 121 |
-
Le profil ``"standard"`` est strictement rétrocompatible avec
|
| 122 |
-
le runner pré-chantier-2.
|
| 123 |
-
normalization_profile:
|
| 124 |
-
Identifiant d'un profil de normalisation diplomatique
|
| 125 |
-
(cf. ``measurements.normalization.NORMALIZATION_PROFILES``).
|
| 126 |
-
Sprint A14-S1 — A.I.0 P0 : auparavant l'API web exposait ce
|
| 127 |
-
paramètre mais il était silencieusement perdu avant
|
| 128 |
-
d'atteindre ``compute_metrics``, ce qui rendait
|
| 129 |
-
scientifiquement faux tout benchmark lancé via la web app.
|
| 130 |
-
Désormais propagé end-to-end : web → run_benchmark → workers
|
| 131 |
-
→ compute_metrics. ``None`` = profil par défaut (medieval_french).
|
| 132 |
-
|
| 133 |
-
Returns
|
| 134 |
-
-------
|
| 135 |
-
BenchmarkResult
|
| 136 |
-
"""
|
| 137 |
-
# Validation du profil dès l'entrée pour échouer rapidement sur
|
| 138 |
-
# une faute de frappe utilisateur, avant de soumettre des futures
|
| 139 |
-
# aux pools. Eager-load des hooks natifs pour peupler le registre
|
| 140 |
-
# dans le main process (les sous-processus du pool feront leur
|
| 141 |
-
# propre import dans ``_compute_document_result``).
|
| 142 |
-
import picarones.measurements.builtin_hooks # noqa: F401
|
| 143 |
-
from picarones.evaluation.metric_hooks import (
|
| 144 |
-
run_corpus_aggregators, validate_profile,
|
| 145 |
-
)
|
| 146 |
-
validate_profile(profile)
|
| 147 |
-
|
| 148 |
-
# Sprint A14-S1 — résolution one-shot du profil de normalisation.
|
| 149 |
-
# On le fait ici (main process) pour échouer rapidement sur un ID
|
| 150 |
-
# invalide avant de soumettre des futures aux pools, et pour
|
| 151 |
-
# éviter de re-résoudre N fois côté workers.
|
| 152 |
-
norm_profile_obj = None
|
| 153 |
-
if normalization_profile is not None:
|
| 154 |
-
from picarones.evaluation.metrics.normalization import get_builtin_profile
|
| 155 |
-
norm_profile_obj = get_builtin_profile(normalization_profile)
|
| 156 |
-
|
| 157 |
-
def _is_cancelled() -> bool:
|
| 158 |
-
return cancel_event is not None and cancel_event.is_set()
|
| 159 |
-
engine_reports: list[EngineReport] = []
|
| 160 |
-
# Sprint 36 — collecte des hypothèses brutes par moteur avant
|
| 161 |
-
# ``compact()`` pour pouvoir calculer la divergence taxonomique et
|
| 162 |
-
# la complémentarité (oracle) en fin de benchmark.
|
| 163 |
-
per_engine_outputs: dict[str, dict[str, str]] = {}
|
| 164 |
-
ground_truths_by_doc: dict[str, str] = {}
|
| 165 |
-
# Sprint 45 — A.III stratification : capture du ``script_type`` par
|
| 166 |
-
# document avant ``compact()`` (qui efface ``image_quality``).
|
| 167 |
-
doc_strata: dict[str, str] = {}
|
| 168 |
-
|
| 169 |
-
# Sprint 87 — langue du corpus pour le delta Flesch (A.II.2).
|
| 170 |
-
# Lecture depuis corpus.metadata, fallback "fr".
|
| 171 |
-
corpus_lang: str = (corpus.metadata or {}).get("language", "fr")
|
| 172 |
-
if corpus_lang not in ("fr", "en"):
|
| 173 |
-
# Sprint 52 ne supporte que fr/en — fallback "fr" en warning.
|
| 174 |
-
logger.warning(
|
| 175 |
-
"[readability] langue '%s' non supportée, fallback 'fr'.",
|
| 176 |
-
corpus_lang,
|
| 177 |
-
)
|
| 178 |
-
corpus_lang = "fr"
|
| 179 |
-
|
| 180 |
-
for engine in engines:
|
| 181 |
-
if _is_cancelled():
|
| 182 |
-
logger.info("Benchmark annulé avant le moteur '%s'.", engine.name)
|
| 183 |
-
break
|
| 184 |
-
logger.info("Démarrage : %s", engine.name)
|
| 185 |
-
|
| 186 |
-
# Reprise depuis résultats partiels d'une éventuelle exécution précédente
|
| 187 |
-
partial_path, loaded_results = _load_partial(corpus.name, engine.name, partial_dir)
|
| 188 |
-
loaded_doc_ids = {dr.doc_id for dr in loaded_results}
|
| 189 |
-
if loaded_results:
|
| 190 |
-
logger.info(
|
| 191 |
-
"Reprise depuis résultats partiels : %d/%d documents déjà traités.",
|
| 192 |
-
len(loaded_results), len(corpus),
|
| 193 |
-
)
|
| 194 |
-
|
| 195 |
-
docs_to_process = [doc for doc in corpus.documents if doc.doc_id not in loaded_doc_ids]
|
| 196 |
-
if loaded_doc_ids:
|
| 197 |
-
logger.info(
|
| 198 |
-
"[%s] %d doc(s) ignorés (résultats partiels existants) — "
|
| 199 |
-
"supprimer le fichier partiel '%s' pour forcer le recalcul.",
|
| 200 |
-
engine.name, len(loaded_doc_ids), partial_path,
|
| 201 |
-
)
|
| 202 |
-
document_results: list[DocumentResult] = list(loaded_results)
|
| 203 |
-
|
| 204 |
-
# Sélection du type d'exécution selon execution_mode du moteur
|
| 205 |
-
is_cpu_bound = getattr(engine, "execution_mode", "io") == "cpu"
|
| 206 |
-
ExecutorClass = (
|
| 207 |
-
concurrent.futures.ProcessPoolExecutor
|
| 208 |
-
if is_cpu_bound
|
| 209 |
-
else concurrent.futures.ThreadPoolExecutor
|
| 210 |
-
)
|
| 211 |
-
logger.info(
|
| 212 |
-
"[%s] classe=%s, exécuteur=%s, docs à traiter=%d (reprise=%d).",
|
| 213 |
-
engine.name,
|
| 214 |
-
engine.__class__.__name__,
|
| 215 |
-
"ProcessPoolExecutor" if is_cpu_bound else "ThreadPoolExecutor",
|
| 216 |
-
len(docs_to_process),
|
| 217 |
-
len(loaded_results),
|
| 218 |
-
)
|
| 219 |
-
|
| 220 |
-
pbar = tqdm(
|
| 221 |
-
total=len(corpus.documents),
|
| 222 |
-
initial=len(loaded_results),
|
| 223 |
-
desc=f"[{engine.name}]",
|
| 224 |
-
unit="doc",
|
| 225 |
-
disable=not show_progress,
|
| 226 |
-
)
|
| 227 |
-
processed_count = len(loaded_results)
|
| 228 |
-
|
| 229 |
-
executor = ExecutorClass(max_workers=max_workers)
|
| 230 |
-
try:
|
| 231 |
-
# Soumission de tous les documents au pool
|
| 232 |
-
future_to_doc: dict = {}
|
| 233 |
-
submitted_at: dict = {}
|
| 234 |
-
|
| 235 |
-
for doc in docs_to_process:
|
| 236 |
-
if _is_cancelled():
|
| 237 |
-
logger.info("[%s] annulation — arrêt de la soumission.", engine.name)
|
| 238 |
-
break
|
| 239 |
-
if is_cpu_bound:
|
| 240 |
-
engine_module = engine.__class__.__module__
|
| 241 |
-
engine_class_name = engine.__class__.__name__
|
| 242 |
-
char_exclude_tuple = tuple(char_exclude) if char_exclude else ()
|
| 243 |
-
future = executor.submit(
|
| 244 |
-
_cpu_doc_worker,
|
| 245 |
-
(engine_module, engine_class_name, engine.config,
|
| 246 |
-
doc.doc_id, str(doc.image_path), doc.ground_truth,
|
| 247 |
-
char_exclude_tuple, corpus_lang, profile,
|
| 248 |
-
norm_profile_obj),
|
| 249 |
-
)
|
| 250 |
-
else:
|
| 251 |
-
future = executor.submit(
|
| 252 |
-
_io_doc_worker, engine, doc, char_exclude,
|
| 253 |
-
corpus_lang, profile, norm_profile_obj,
|
| 254 |
-
)
|
| 255 |
-
future_to_doc[future] = doc
|
| 256 |
-
submitted_at[future] = time.monotonic()
|
| 257 |
-
|
| 258 |
-
remaining = set(future_to_doc)
|
| 259 |
-
|
| 260 |
-
while remaining:
|
| 261 |
-
if _is_cancelled():
|
| 262 |
-
logger.info("[%s] annulation — annulation des futures restantes.", engine.name)
|
| 263 |
-
for f in remaining:
|
| 264 |
-
f.cancel()
|
| 265 |
-
break
|
| 266 |
-
|
| 267 |
-
done, remaining = concurrent.futures.wait(
|
| 268 |
-
remaining,
|
| 269 |
-
timeout=0.5,
|
| 270 |
-
return_when=concurrent.futures.FIRST_COMPLETED,
|
| 271 |
-
)
|
| 272 |
-
|
| 273 |
-
for future in done:
|
| 274 |
-
doc = future_to_doc[future]
|
| 275 |
-
try:
|
| 276 |
-
doc_result = future.result()
|
| 277 |
-
except Exception as e:
|
| 278 |
-
logger.warning(
|
| 279 |
-
"[%s] doc %s : erreur inattendue : %s",
|
| 280 |
-
engine.name, doc.doc_id, e,
|
| 281 |
-
)
|
| 282 |
-
doc_result = _make_error_doc_result(doc, str(e))
|
| 283 |
-
|
| 284 |
-
document_results.append(doc_result)
|
| 285 |
-
_save_partial_line(partial_path, doc_result)
|
| 286 |
-
pbar.update(1)
|
| 287 |
-
|
| 288 |
-
if progress_callback is not None:
|
| 289 |
-
try:
|
| 290 |
-
progress_callback(engine.name, processed_count, doc.doc_id)
|
| 291 |
-
except Exception as e:
|
| 292 |
-
logger.warning("[progress_callback] fonctionnalité dégradée : %s", e)
|
| 293 |
-
processed_count += 1
|
| 294 |
-
|
| 295 |
-
# Vérification des timeouts par document
|
| 296 |
-
now = time.monotonic()
|
| 297 |
-
timed_out = [
|
| 298 |
-
f for f in remaining
|
| 299 |
-
if now - submitted_at[f] > timeout_seconds
|
| 300 |
-
]
|
| 301 |
-
for future in timed_out:
|
| 302 |
-
remaining.discard(future)
|
| 303 |
-
doc = future_to_doc[future]
|
| 304 |
-
future.cancel()
|
| 305 |
-
logger.warning(
|
| 306 |
-
"[%s] doc %s : timeout (%.0fs), document marqué en erreur.",
|
| 307 |
-
engine.name, doc.doc_id, timeout_seconds,
|
| 308 |
-
)
|
| 309 |
-
doc_result = _make_timeout_doc_result(doc, timeout_seconds)
|
| 310 |
-
document_results.append(doc_result)
|
| 311 |
-
_save_partial_line(partial_path, doc_result)
|
| 312 |
-
pbar.update(1)
|
| 313 |
-
|
| 314 |
-
if progress_callback is not None:
|
| 315 |
-
try:
|
| 316 |
-
progress_callback(engine.name, processed_count, doc.doc_id)
|
| 317 |
-
except Exception as e:
|
| 318 |
-
logger.warning(
|
| 319 |
-
"[progress_callback] fonctionnalité dégradée : %s", e
|
| 320 |
-
)
|
| 321 |
-
processed_count += 1
|
| 322 |
-
|
| 323 |
-
finally:
|
| 324 |
-
pbar.close()
|
| 325 |
-
# Sur Python 3.12+, ``ProcessPoolExecutor.shutdown(wait=False)``
|
| 326 |
-
# laisse les workers (sous-processus) vivants ; l'atexit
|
| 327 |
-
# ``_python_exit`` de ``concurrent.futures.process`` essaie
|
| 328 |
-
# ensuite de les joindre indéfiniment au shutdown global de
|
| 329 |
-
# l'interpréteur, ce qui hang la CI Ubuntu (exit code 124
|
| 330 |
-
# après timeout GNU 9 min). Le ``ThreadPoolExecutor`` n'a
|
| 331 |
-
# pas ce problème (les threads daemon meurent avec le
|
| 332 |
-
# processus).
|
| 333 |
-
#
|
| 334 |
-
# ``cancel_futures=True`` continue d'annuler les futures en
|
| 335 |
-
# queue dans les deux cas ; ``wait=is_cpu_bound`` garantit
|
| 336 |
-
# que les workers ProcessPool en cours finissent leur batch
|
| 337 |
-
# et libèrent leurs sous-processus avant le retour. Pas de
|
| 338 |
-
# changement de comportement pour les engines IO-bound (qui
|
| 339 |
-
# gardent leur shutdown rapide non-bloquant).
|
| 340 |
-
#
|
| 341 |
-
# Ce flow est exercé en CI via les tests web qui chargent le
|
| 342 |
-
# vrai ``TesseractEngine`` (``execution_mode="cpu"``) via
|
| 343 |
-
# ``engine_from_name("tesseract")`` — d'où la nécessité du
|
| 344 |
-
# fix dans le code de prod et pas seulement dans les tests.
|
| 345 |
-
executor.shutdown(
|
| 346 |
-
wait=is_cpu_bound,
|
| 347 |
-
cancel_futures=True,
|
| 348 |
-
)
|
| 349 |
-
|
| 350 |
-
if _is_cancelled():
|
| 351 |
-
logger.info(
|
| 352 |
-
"[%s] annulé — %d documents traités sur %d.",
|
| 353 |
-
engine.name, len(document_results) - len(loaded_results),
|
| 354 |
-
len(docs_to_process),
|
| 355 |
-
)
|
| 356 |
-
# Conserver le fichier partiel pour reprise ultérieure
|
| 357 |
-
break
|
| 358 |
-
|
| 359 |
-
# Réordonner selon l'ordre du corpus pour reproductibilité
|
| 360 |
-
doc_order = {doc.doc_id: i for i, doc in enumerate(corpus.documents)}
|
| 361 |
-
document_results.sort(key=lambda dr: doc_order.get(dr.doc_id, len(doc_order)))
|
| 362 |
-
|
| 363 |
-
logger.info(
|
| 364 |
-
"[%s] collecte terminée — %d/%d documents (dont %d chargés depuis reprise).",
|
| 365 |
-
engine.name,
|
| 366 |
-
len(document_results),
|
| 367 |
-
len(corpus.documents),
|
| 368 |
-
len(loaded_results),
|
| 369 |
-
)
|
| 370 |
-
if not document_results:
|
| 371 |
-
logger.warning(
|
| 372 |
-
"[%s] aucun DocumentResult collecté — le rapport affichera 0/0 documents. "
|
| 373 |
-
"Vérifier que le moteur/pipeline a bien produit des résultats.",
|
| 374 |
-
engine.name,
|
| 375 |
-
)
|
| 376 |
-
|
| 377 |
-
# Supprimer le fichier partiel — moteur terminé avec succès
|
| 378 |
-
_delete_partial(partial_path)
|
| 379 |
-
|
| 380 |
-
engine_version = engine._safe_version()
|
| 381 |
-
pipeline_info = _build_pipeline_info(engine, document_results)
|
| 382 |
-
|
| 383 |
-
# Chantier 2 (post-Sprint 97) — agrégation déléguée au registre.
|
| 384 |
-
# Les 12 appels manuels aux fonctions ``_aggregate_*`` sont
|
| 385 |
-
# remplacés par un seul appel qui itère sur les agrégateurs
|
| 386 |
-
# actifs du profil. Le profil ``"standard"`` (défaut) reproduit
|
| 387 |
-
# exactement le comportement pré-chantier-2.
|
| 388 |
-
aggregated = run_corpus_aggregators(profile, document_results)
|
| 389 |
-
|
| 390 |
-
report = EngineReport(
|
| 391 |
-
engine_name=engine.name,
|
| 392 |
-
engine_version=engine_version,
|
| 393 |
-
engine_config=engine.config,
|
| 394 |
-
document_results=document_results,
|
| 395 |
-
pipeline_info=pipeline_info,
|
| 396 |
-
aggregated_confusion=aggregated.get("aggregated_confusion"),
|
| 397 |
-
aggregated_char_scores=aggregated.get("aggregated_char_scores"),
|
| 398 |
-
aggregated_taxonomy=aggregated.get("aggregated_taxonomy"),
|
| 399 |
-
aggregated_structure=aggregated.get("aggregated_structure"),
|
| 400 |
-
aggregated_image_quality=aggregated.get("aggregated_image_quality"),
|
| 401 |
-
aggregated_line_metrics=aggregated.get("aggregated_line_metrics"),
|
| 402 |
-
aggregated_hallucination=aggregated.get("aggregated_hallucination"),
|
| 403 |
-
aggregated_calibration=aggregated.get("aggregated_calibration"),
|
| 404 |
-
aggregated_philological=aggregated.get("aggregated_philological"),
|
| 405 |
-
aggregated_searchability=aggregated.get("aggregated_searchability"),
|
| 406 |
-
aggregated_numerical_sequences=aggregated.get("aggregated_numerical_sequences"),
|
| 407 |
-
aggregated_readability=aggregated.get("aggregated_readability"),
|
| 408 |
-
)
|
| 409 |
-
engine_reports.append(report)
|
| 410 |
-
logger.info(
|
| 411 |
-
"%s terminé — CER moyen : %.2f%%",
|
| 412 |
-
engine.name,
|
| 413 |
-
(report.mean_cer or 0) * 100,
|
| 414 |
-
)
|
| 415 |
-
|
| 416 |
-
# Sprint 36 — capture des hypothèses brutes pour le calcul
|
| 417 |
-
# inter-moteurs (effectué après la boucle, avant la sérialisation).
|
| 418 |
-
# On clone les chaînes pour ne pas dépendre de la durée de vie des
|
| 419 |
-
# DocumentResult après ``compact()``.
|
| 420 |
-
per_engine_outputs[engine.name] = {
|
| 421 |
-
dr.doc_id: dr.hypothesis for dr in document_results
|
| 422 |
-
if dr.engine_error is None
|
| 423 |
-
}
|
| 424 |
-
for dr in document_results:
|
| 425 |
-
if dr.doc_id not in ground_truths_by_doc and dr.ground_truth:
|
| 426 |
-
ground_truths_by_doc[dr.doc_id] = dr.ground_truth
|
| 427 |
-
# Sprint 45 — capture script_type avant compact()
|
| 428 |
-
if dr.doc_id not in doc_strata and dr.image_quality:
|
| 429 |
-
st = dr.image_quality.get("script_type")
|
| 430 |
-
if st:
|
| 431 |
-
doc_strata[dr.doc_id] = str(st)
|
| 432 |
-
|
| 433 |
-
# Sprint 40 — calcul des métriques NER si :
|
| 434 |
-
# 1. l'utilisateur a fourni un EntityExtractor au runner ;
|
| 435 |
-
# 2. ET le document a un niveau de GT ENTITIES (Sprint 32).
|
| 436 |
-
# Fait dans le main process (pas dans les sous-processus du pool)
|
| 437 |
-
# pour éviter de pickler l'extracteur (spaCy + modèle).
|
| 438 |
-
if entity_extractor is not None:
|
| 439 |
-
_attach_ner_metrics(corpus, document_results, entity_extractor)
|
| 440 |
-
agg_ner = _aggregate_ner(document_results)
|
| 441 |
-
report.aggregated_ner = agg_ner
|
| 442 |
-
|
| 443 |
-
# Sprint A14-S1 — A.I.0 P0 : la compaction inconditionnelle qui
|
| 444 |
-
# vivait ici amputait silencieusement le JSON exporté (et donc
|
| 445 |
-
# le rapport HTML qui le consomme) en supprimant 13 dicts
|
| 446 |
-
# d'analyse per-document et en tronquant les textes à 200 chars.
|
| 447 |
-
# ``DocumentResult.compact()`` est désormais opt-in (paramètres
|
| 448 |
-
# ``text_limit`` et ``drop_analyses``) ; le runner ne compacte
|
| 449 |
-
# plus par défaut afin que ``output_json`` contienne réellement
|
| 450 |
-
# toutes les analyses détaillées promises par le README.
|
| 451 |
-
# Un caller qui veut un JSON léger peut appeler
|
| 452 |
-
# ``dr.compact(text_limit=200, drop_analyses=True)`` lui-même
|
| 453 |
-
# après ``run_benchmark`` et avant la sérialisation finale.
|
| 454 |
-
|
| 455 |
-
# Sprint 36 — analyse inter-moteurs (divergence taxonomique +
|
| 456 |
-
# complémentarité / oracle). N'est calculée qu'à partir de 2
|
| 457 |
-
# moteurs ; en deçà l'analyse n'a pas de sens.
|
| 458 |
-
inter_engine_payload: Optional[dict] = None
|
| 459 |
-
if len(engine_reports) >= 2:
|
| 460 |
-
try:
|
| 461 |
-
from picarones.evaluation.metrics.inter_engine import compute_inter_engine_analysis
|
| 462 |
-
|
| 463 |
-
taxonomy_distros = {
|
| 464 |
-
report.engine_name: (
|
| 465 |
-
report.aggregated_taxonomy.get("class_distribution", {})
|
| 466 |
-
if report.aggregated_taxonomy
|
| 467 |
-
else {}
|
| 468 |
-
)
|
| 469 |
-
for report in engine_reports
|
| 470 |
-
}
|
| 471 |
-
# Élimine les moteurs sans distribution taxonomique pour ne pas
|
| 472 |
-
# polluer la matrice.
|
| 473 |
-
taxonomy_distros = {
|
| 474 |
-
name: dist for name, dist in taxonomy_distros.items() if dist
|
| 475 |
-
}
|
| 476 |
-
inter_engine_payload = compute_inter_engine_analysis(
|
| 477 |
-
per_engine_outputs=per_engine_outputs,
|
| 478 |
-
ground_truths=ground_truths_by_doc,
|
| 479 |
-
taxonomy_distributions=taxonomy_distros or None,
|
| 480 |
-
)
|
| 481 |
-
except Exception as exc: # noqa: BLE001
|
| 482 |
-
logger.warning(
|
| 483 |
-
"[runner] analyse inter-moteurs dégradée : %s — section omise du rapport",
|
| 484 |
-
exc,
|
| 485 |
-
)
|
| 486 |
-
|
| 487 |
-
benchmark = BenchmarkResult(
|
| 488 |
-
corpus_name=corpus.name,
|
| 489 |
-
corpus_source=corpus.source_path,
|
| 490 |
-
document_count=len(corpus),
|
| 491 |
-
engine_reports=engine_reports,
|
| 492 |
-
inter_engine_analysis=inter_engine_payload,
|
| 493 |
-
doc_strata=dict(doc_strata) if doc_strata else None,
|
| 494 |
-
)
|
| 495 |
-
|
| 496 |
-
if output_json:
|
| 497 |
-
path = benchmark.to_json(output_json)
|
| 498 |
-
logger.info("Résultats écrits dans : %s", path)
|
| 499 |
-
|
| 500 |
-
return benchmark
|
| 501 |
-
|
| 502 |
-
|
| 503 |
-
def _build_pipeline_info(engine: BaseOCREngine, doc_results: list[DocumentResult]) -> dict:
|
| 504 |
-
"""Construit le dictionnaire pipeline_info pour un EngineReport."""
|
| 505 |
-
first_with_meta = next(
|
| 506 |
-
(dr for dr in doc_results if dr.pipeline_metadata), None
|
| 507 |
-
)
|
| 508 |
-
if first_with_meta is None:
|
| 509 |
-
return {}
|
| 510 |
-
|
| 511 |
-
meta = first_with_meta.pipeline_metadata
|
| 512 |
-
info: dict = {
|
| 513 |
-
"pipeline_mode": meta.get("pipeline_mode"),
|
| 514 |
-
"prompt_file": meta.get("prompt_file"),
|
| 515 |
-
"llm_model": meta.get("llm_model"),
|
| 516 |
-
"llm_provider": meta.get("llm_provider"),
|
| 517 |
-
}
|
| 518 |
-
|
| 519 |
-
# Sprint C du plan v2.0 : duck typing via ``is_pipeline`` au lieu
|
| 520 |
-
# de ``isinstance(engine, OCRLLMPipeline)``. Découple le runner
|
| 521 |
-
# legacy de la classe ``OCRLLMPipeline`` — préparation à la
|
| 522 |
-
# suppression du sous-package ``picarones.pipelines/`` (Sprint D).
|
| 523 |
-
if getattr(engine, "is_pipeline", False):
|
| 524 |
-
info["pipeline_steps"] = engine.pipeline_steps_info
|
| 525 |
-
info["prompt_template"] = engine.prompt_template
|
| 526 |
-
|
| 527 |
-
over_norm_results = [
|
| 528 |
-
dr.pipeline_metadata.get("over_normalization")
|
| 529 |
-
for dr in doc_results
|
| 530 |
-
if dr.pipeline_metadata.get("over_normalization") is not None
|
| 531 |
-
]
|
| 532 |
-
if over_norm_results:
|
| 533 |
-
total_correct = sum(r["total_correct_ocr_words"] for r in over_norm_results)
|
| 534 |
-
total_over = sum(r["over_normalized_count"] for r in over_norm_results)
|
| 535 |
-
info["over_normalization"] = {
|
| 536 |
-
"score": round(total_over / total_correct, 4) if total_correct > 0 else 0.0,
|
| 537 |
-
"total_correct_ocr_words": total_correct,
|
| 538 |
-
"over_normalized_count": total_over,
|
| 539 |
-
"document_count": len(over_norm_results),
|
| 540 |
-
}
|
| 541 |
-
|
| 542 |
-
return info
|
| 543 |
-
|
| 544 |
-
|
| 545 |
-
__all__ = ["_build_pipeline_info", "run_benchmark"]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@@ -1,140 +0,0 @@
|
|
| 1 |
-
"""Persistance des résultats partiels du benchmark (NDJSON).
|
| 2 |
-
|
| 3 |
-
Quand le runner traite un corpus, il écrit chaque ``DocumentResult``
|
| 4 |
-
dans un fichier ``{partial_dir}/picarones_{corpus}_{engine}.partial.json``
|
| 5 |
-
au format NDJSON. Si le benchmark est interrompu (Ctrl+C, crash, kill),
|
| 6 |
-
la prochaine exécution reprend depuis ce fichier sans perdre le travail
|
| 7 |
-
déjà fait.
|
| 8 |
-
|
| 9 |
-
Thread-safe : le module utilise un :class:`threading.Lock` partagé
|
| 10 |
-
entre toutes les écritures pour sérialiser les appends.
|
| 11 |
-
"""
|
| 12 |
-
|
| 13 |
-
from __future__ import annotations
|
| 14 |
-
|
| 15 |
-
import json
|
| 16 |
-
import logging
|
| 17 |
-
import re
|
| 18 |
-
import tempfile
|
| 19 |
-
import threading
|
| 20 |
-
from pathlib import Path
|
| 21 |
-
from typing import Optional
|
| 22 |
-
|
| 23 |
-
from picarones.evaluation.benchmark_result import DocumentResult
|
| 24 |
-
from picarones.evaluation.metric_result import MetricsResult
|
| 25 |
-
|
| 26 |
-
logger = logging.getLogger(__name__)
|
| 27 |
-
|
| 28 |
-
# Lock pour la sérialisation des écritures de résultats partiels.
|
| 29 |
-
# Partagé entre tous les call sites (workers IO et CPU se relayent
|
| 30 |
-
# sur la même file).
|
| 31 |
-
_partial_write_lock = threading.Lock()
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
def _sanitize_filename(s: str) -> str:
|
| 35 |
-
return re.sub(r"[^\w\-]", "_", s)[:64]
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
def _partial_path(
|
| 39 |
-
corpus_name: str,
|
| 40 |
-
engine_name: str,
|
| 41 |
-
partial_dir: Optional[str | Path],
|
| 42 |
-
) -> Path:
|
| 43 |
-
base = Path(partial_dir) if partial_dir else Path(tempfile.gettempdir())
|
| 44 |
-
name = (
|
| 45 |
-
f"picarones_{_sanitize_filename(corpus_name)}"
|
| 46 |
-
f"_{_sanitize_filename(engine_name)}.partial.json"
|
| 47 |
-
)
|
| 48 |
-
return base / name
|
| 49 |
-
|
| 50 |
-
|
| 51 |
-
def _load_partial(
|
| 52 |
-
corpus_name: str,
|
| 53 |
-
engine_name: str,
|
| 54 |
-
partial_dir: Optional[str | Path],
|
| 55 |
-
) -> tuple[Path, list[DocumentResult]]:
|
| 56 |
-
"""Charge les résultats partiels d'une exécution précédente interrompue.
|
| 57 |
-
|
| 58 |
-
Returns
|
| 59 |
-
-------
|
| 60 |
-
(path, results) — chemin du fichier partiel et liste des
|
| 61 |
-
DocumentResult déjà calculés.
|
| 62 |
-
"""
|
| 63 |
-
path = _partial_path(corpus_name, engine_name, partial_dir)
|
| 64 |
-
results: list[DocumentResult] = []
|
| 65 |
-
if not path.exists():
|
| 66 |
-
return path, results
|
| 67 |
-
|
| 68 |
-
try:
|
| 69 |
-
with path.open("r", encoding="utf-8") as fh:
|
| 70 |
-
for line in fh:
|
| 71 |
-
line = line.strip()
|
| 72 |
-
if not line:
|
| 73 |
-
continue
|
| 74 |
-
d = json.loads(line)
|
| 75 |
-
m = d.get("metrics", {})
|
| 76 |
-
metrics = MetricsResult(
|
| 77 |
-
cer=m.get("cer", 1.0),
|
| 78 |
-
cer_nfc=m.get("cer_nfc", 1.0),
|
| 79 |
-
cer_caseless=m.get("cer_caseless", 1.0),
|
| 80 |
-
wer=m.get("wer", 1.0),
|
| 81 |
-
wer_normalized=m.get("wer_normalized", 1.0),
|
| 82 |
-
mer=m.get("mer", 1.0),
|
| 83 |
-
wil=m.get("wil", 1.0),
|
| 84 |
-
reference_length=m.get("reference_length", 0),
|
| 85 |
-
hypothesis_length=m.get("hypothesis_length", 0),
|
| 86 |
-
error=m.get("error"),
|
| 87 |
-
)
|
| 88 |
-
results.append(DocumentResult(
|
| 89 |
-
doc_id=d["doc_id"],
|
| 90 |
-
image_path=d.get("image_path", ""),
|
| 91 |
-
ground_truth=d.get("ground_truth", ""),
|
| 92 |
-
hypothesis=d.get("hypothesis", ""),
|
| 93 |
-
metrics=metrics,
|
| 94 |
-
duration_seconds=d.get("duration_seconds", 0.0),
|
| 95 |
-
engine_error=d.get("engine_error"),
|
| 96 |
-
ocr_intermediate=d.get("ocr_intermediate"),
|
| 97 |
-
pipeline_metadata=d.get("pipeline_metadata", {}),
|
| 98 |
-
confusion_matrix=d.get("confusion_matrix"),
|
| 99 |
-
char_scores=d.get("char_scores"),
|
| 100 |
-
taxonomy=d.get("taxonomy"),
|
| 101 |
-
structure=d.get("structure"),
|
| 102 |
-
image_quality=d.get("image_quality"),
|
| 103 |
-
line_metrics=d.get("line_metrics"),
|
| 104 |
-
hallucination_metrics=d.get("hallucination_metrics"),
|
| 105 |
-
))
|
| 106 |
-
except Exception as e:
|
| 107 |
-
logger.warning("Impossible de charger les résultats partiels '%s' : %s", path, e)
|
| 108 |
-
results = []
|
| 109 |
-
|
| 110 |
-
return path, results
|
| 111 |
-
|
| 112 |
-
|
| 113 |
-
def _save_partial_line(partial_path: Path, doc_result: DocumentResult) -> None:
|
| 114 |
-
"""Ajoute une entrée NDJSON au fichier de résultats partiels (thread-safe)."""
|
| 115 |
-
try:
|
| 116 |
-
line = json.dumps(doc_result.as_dict(), ensure_ascii=False) + "\n"
|
| 117 |
-
with _partial_write_lock:
|
| 118 |
-
with partial_path.open("a", encoding="utf-8") as fh:
|
| 119 |
-
fh.write(line)
|
| 120 |
-
except Exception as e:
|
| 121 |
-
logger.warning("Impossible d'écrire dans le fichier partiel '%s' : %s", partial_path, e)
|
| 122 |
-
|
| 123 |
-
|
| 124 |
-
def _delete_partial(partial_path: Path) -> None:
|
| 125 |
-
"""Supprime le fichier de résultats partiels à la fin d'un moteur."""
|
| 126 |
-
try:
|
| 127 |
-
if partial_path.exists():
|
| 128 |
-
partial_path.unlink()
|
| 129 |
-
except Exception as e:
|
| 130 |
-
logger.warning("Impossible de supprimer le fichier partiel '%s' : %s", partial_path, e)
|
| 131 |
-
|
| 132 |
-
|
| 133 |
-
__all__ = [
|
| 134 |
-
"_delete_partial",
|
| 135 |
-
"_load_partial",
|
| 136 |
-
"_partial_path",
|
| 137 |
-
"_partial_write_lock",
|
| 138 |
-
"_sanitize_filename",
|
| 139 |
-
"_save_partial_line",
|
| 140 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@@ -1,116 +0,0 @@
|
|
| 1 |
-
"""Workers de niveau module pour les pools d'exécution.
|
| 2 |
-
|
| 3 |
-
Deux workers correspondant aux deux modes d'exécution :
|
| 4 |
-
|
| 5 |
-
- :func:`_cpu_doc_worker` — pour ``ProcessPoolExecutor`` (moteurs
|
| 6 |
-
CPU-bound, instanciés dans le sous-processus). Doit être picklable :
|
| 7 |
-
c'est pour ça qu'il est défini au niveau module.
|
| 8 |
-
- :func:`_io_doc_worker` — pour ``ThreadPoolExecutor`` (moteurs
|
| 9 |
-
IO-bound / API HTTP). L'instance du moteur est partagée entre les
|
| 10 |
-
threads.
|
| 11 |
-
|
| 12 |
-
Les deux finissent par appeler :func:`_compute_document_result` du
|
| 13 |
-
sous-module :mod:`document` pour calculer toutes les métriques.
|
| 14 |
-
"""
|
| 15 |
-
|
| 16 |
-
from __future__ import annotations
|
| 17 |
-
|
| 18 |
-
from typing import Optional
|
| 19 |
-
|
| 20 |
-
from picarones.evaluation.benchmark_result import DocumentResult
|
| 21 |
-
from picarones.adapters.legacy_engines.base import BaseOCREngine
|
| 22 |
-
from picarones.measurements.runner.document import _compute_document_result
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
def _cpu_doc_worker(args: tuple) -> "DocumentResult":
|
| 26 |
-
"""Worker pour ProcessPoolExecutor (moteurs CPU-bound).
|
| 27 |
-
|
| 28 |
-
Instancie le moteur dans le sous-processus, exécute l'OCR et calcule
|
| 29 |
-
toutes les métriques. Doit être une fonction de niveau module pour être
|
| 30 |
-
sérialisable par ``pickle``.
|
| 31 |
-
|
| 32 |
-
Le tuple ``args`` peut contenir, par compatibilité ascendante :
|
| 33 |
-
- 7 éléments : legacy (Sprint 13)
|
| 34 |
-
- 8 éléments : + ``corpus_lang`` (Sprint 87)
|
| 35 |
-
- 9 éléments : + ``profile`` (chantier 2 post-Sprint 97)
|
| 36 |
-
- 10 éléments : + ``normalization_profile`` (Sprint A14-S1, A.I.0 P0)
|
| 37 |
-
"""
|
| 38 |
-
norm_profile = None
|
| 39 |
-
if len(args) == 10:
|
| 40 |
-
(engine_module, engine_class_name, engine_config, doc_id,
|
| 41 |
-
image_path, ground_truth, char_exclude_chars, corpus_lang,
|
| 42 |
-
profile, norm_profile) = args
|
| 43 |
-
elif len(args) == 9:
|
| 44 |
-
(engine_module, engine_class_name, engine_config, doc_id,
|
| 45 |
-
image_path, ground_truth, char_exclude_chars, corpus_lang,
|
| 46 |
-
profile) = args
|
| 47 |
-
elif len(args) == 8:
|
| 48 |
-
(engine_module, engine_class_name, engine_config, doc_id,
|
| 49 |
-
image_path, ground_truth, char_exclude_chars, corpus_lang) = args
|
| 50 |
-
profile = "standard"
|
| 51 |
-
else:
|
| 52 |
-
(engine_module, engine_class_name, engine_config, doc_id,
|
| 53 |
-
image_path, ground_truth, char_exclude_chars) = args
|
| 54 |
-
corpus_lang = "fr"
|
| 55 |
-
profile = "standard"
|
| 56 |
-
import importlib
|
| 57 |
-
mod = importlib.import_module(engine_module)
|
| 58 |
-
engine_cls = getattr(mod, engine_class_name)
|
| 59 |
-
engine = engine_cls(config=engine_config)
|
| 60 |
-
ocr_result = engine.run(image_path)
|
| 61 |
-
char_exclude = frozenset(char_exclude_chars) if char_exclude_chars else None
|
| 62 |
-
return _compute_document_result(
|
| 63 |
-
doc_id=doc_id,
|
| 64 |
-
image_path=image_path,
|
| 65 |
-
ground_truth=ground_truth,
|
| 66 |
-
ocr_result=ocr_result,
|
| 67 |
-
char_exclude=char_exclude,
|
| 68 |
-
corpus_lang=corpus_lang,
|
| 69 |
-
profile=profile,
|
| 70 |
-
normalization_profile=norm_profile,
|
| 71 |
-
)
|
| 72 |
-
|
| 73 |
-
|
| 74 |
-
def _io_doc_worker(
|
| 75 |
-
engine: BaseOCREngine,
|
| 76 |
-
doc: object,
|
| 77 |
-
char_exclude: Optional[frozenset],
|
| 78 |
-
corpus_lang: str = "fr",
|
| 79 |
-
profile: str = "standard",
|
| 80 |
-
normalization_profile: Optional[object] = None,
|
| 81 |
-
) -> "DocumentResult":
|
| 82 |
-
"""Worker pour ThreadPoolExecutor (moteurs IO-bound / API).
|
| 83 |
-
|
| 84 |
-
Exécute l'OCR et calcule les métriques dans un thread. L'instance du
|
| 85 |
-
moteur est partagée entre les threads — les adaptateurs HTTP sont
|
| 86 |
-
généralement sans état mutable entre les appels.
|
| 87 |
-
|
| 88 |
-
Si le document possède un texte OCR pré-calculé (corpus triplet) et que
|
| 89 |
-
le moteur est un pipeline OCR+LLM, utilise ``run_with_ocr_text()`` pour
|
| 90 |
-
court-circuiter l'étape OCR et tester directement la post-correction LLM.
|
| 91 |
-
"""
|
| 92 |
-
doc_ocr_text = getattr(doc, "ocr_text", None)
|
| 93 |
-
if doc_ocr_text is not None:
|
| 94 |
-
# Corpus triplet — vérifier si le moteur supporte run_with_ocr_text
|
| 95 |
-
run_with = getattr(engine, "run_with_ocr_text", None)
|
| 96 |
-
if run_with is not None:
|
| 97 |
-
ocr_result = run_with(doc.image_path, doc_ocr_text) # type: ignore[attr-defined]
|
| 98 |
-
else:
|
| 99 |
-
# Moteur OCR classique — ignorer le texte OCR pré-calculé
|
| 100 |
-
ocr_result = engine.run(doc.image_path) # type: ignore[attr-defined]
|
| 101 |
-
else:
|
| 102 |
-
ocr_result = engine.run(doc.image_path) # type: ignore[attr-defined]
|
| 103 |
-
|
| 104 |
-
return _compute_document_result(
|
| 105 |
-
doc_id=doc.doc_id, # type: ignore[attr-defined]
|
| 106 |
-
image_path=str(doc.image_path), # type: ignore[attr-defined]
|
| 107 |
-
ground_truth=doc.ground_truth, # type: ignore[attr-defined]
|
| 108 |
-
ocr_result=ocr_result,
|
| 109 |
-
char_exclude=char_exclude,
|
| 110 |
-
corpus_lang=corpus_lang,
|
| 111 |
-
profile=profile,
|
| 112 |
-
normalization_profile=normalization_profile,
|
| 113 |
-
)
|
| 114 |
-
|
| 115 |
-
|
| 116 |
-
__all__ = ["_cpu_doc_worker", "_io_doc_worker"]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@@ -14,7 +14,6 @@ from __future__ import annotations
|
|
| 14 |
|
| 15 |
import json
|
| 16 |
from pathlib import Path
|
| 17 |
-
from typing import Any
|
| 18 |
|
| 19 |
import pytest
|
| 20 |
|
|
@@ -985,151 +984,6 @@ class TestRunBenchmarkViaService:
|
|
| 985 |
assert bm.engine_reports
|
| 986 |
|
| 987 |
|
| 988 |
-
# ──────────────────────────────────────────────────────────────────────
|
| 989 |
-
# D.1.e — Équivalence numérique legacy vs rewrite
|
| 990 |
-
# ──────────────────────────────────────────────────────────────────────
|
| 991 |
-
|
| 992 |
-
|
| 993 |
-
class _DeterministicOCR(BaseOCREngine):
|
| 994 |
-
"""OCR engine mock dont la sortie dépend uniquement du nom de fichier.
|
| 995 |
-
|
| 996 |
-
Permet aux tests d'équivalence de produire des hypothèses identiques
|
| 997 |
-
via les deux runners (legacy vs rewrite) — sans dépendance à un
|
| 998 |
-
binaire externe (Tesseract, Pero) qui ne tournerait pas en CI.
|
| 999 |
-
"""
|
| 1000 |
-
|
| 1001 |
-
def __init__(self, name: str, hypotheses: dict[str, str]) -> None:
|
| 1002 |
-
super().__init__(config={})
|
| 1003 |
-
self._name = name
|
| 1004 |
-
self._hypotheses = hypotheses
|
| 1005 |
-
|
| 1006 |
-
@property
|
| 1007 |
-
def name(self) -> str: # type: ignore[override]
|
| 1008 |
-
return self._name
|
| 1009 |
-
|
| 1010 |
-
def version(self) -> str:
|
| 1011 |
-
return "1.0.0"
|
| 1012 |
-
|
| 1013 |
-
def _run_ocr(self, image_path) -> str:
|
| 1014 |
-
return self._hypotheses.get(Path(image_path).stem, "")
|
| 1015 |
-
|
| 1016 |
-
|
| 1017 |
-
def _build_test_corpus(tmp_path: Path) -> Corpus:
|
| 1018 |
-
"""Petit corpus de 3 docs avec des GT variés (parfait, partiel, vide)."""
|
| 1019 |
-
docs = []
|
| 1020 |
-
for i, gt in enumerate([
|
| 1021 |
-
"bonjour le monde", # doc0
|
| 1022 |
-
"lorem ipsum dolor sit", # doc1
|
| 1023 |
-
"", # doc2 — GT vide
|
| 1024 |
-
]):
|
| 1025 |
-
img = tmp_path / f"doc{i}.png"
|
| 1026 |
-
img.write_bytes(b"\x89PNG fake")
|
| 1027 |
-
docs.append(
|
| 1028 |
-
Document(image_path=img, ground_truth=gt, doc_id=f"doc{i}"),
|
| 1029 |
-
)
|
| 1030 |
-
return Corpus(name="equiv_test", documents=docs)
|
| 1031 |
-
|
| 1032 |
-
|
| 1033 |
-
def _hypotheses_for_test(corpus: Corpus) -> dict[str, str]:
|
| 1034 |
-
"""Variantes des GT — perfait, 1 erreur, 2 erreurs, vide."""
|
| 1035 |
-
return {
|
| 1036 |
-
"doc0": "bonjour le monde", # CER 0
|
| 1037 |
-
"doc1": "lorem ipsum dolar sit", # CER ~ 1/22 (1 erreur)
|
| 1038 |
-
"doc2": "spurious", # CER 1.0 (GT vide)
|
| 1039 |
-
}
|
| 1040 |
-
|
| 1041 |
-
|
| 1042 |
-
class TestEquivalenceLegacyVsRewrite:
|
| 1043 |
-
"""Vérifie que ``run_benchmark`` legacy et ``run_benchmark_via_service``
|
| 1044 |
-
produisent des métriques identiques sur les mêmes inputs."""
|
| 1045 |
-
|
| 1046 |
-
def _run_both(
|
| 1047 |
-
self, tmp_path: Path,
|
| 1048 |
-
) -> tuple[Any, Any]:
|
| 1049 |
-
"""Lance les deux runners sur le même corpus + engine,
|
| 1050 |
-
retourne ``(legacy_result, rewrite_result)``."""
|
| 1051 |
-
from picarones.app.services._legacy_runner_adapter import (
|
| 1052 |
-
run_benchmark_via_service,
|
| 1053 |
-
)
|
| 1054 |
-
from picarones.measurements.runner import run_benchmark
|
| 1055 |
-
|
| 1056 |
-
corpus = _build_test_corpus(tmp_path)
|
| 1057 |
-
hypotheses = _hypotheses_for_test(corpus)
|
| 1058 |
-
# Deux instances distinctes — les engines mocks ne sont pas
|
| 1059 |
-
# thread-safe partagés. Chaque runner reçoit la sienne.
|
| 1060 |
-
legacy_engine = _DeterministicOCR("equiv_ocr", hypotheses)
|
| 1061 |
-
rewrite_engine = _DeterministicOCR("equiv_ocr", hypotheses)
|
| 1062 |
-
|
| 1063 |
-
legacy_result = run_benchmark(
|
| 1064 |
-
corpus,
|
| 1065 |
-
[legacy_engine],
|
| 1066 |
-
show_progress=False,
|
| 1067 |
-
max_workers=1,
|
| 1068 |
-
)
|
| 1069 |
-
rewrite_result = run_benchmark_via_service(
|
| 1070 |
-
corpus,
|
| 1071 |
-
[rewrite_engine],
|
| 1072 |
-
)
|
| 1073 |
-
return legacy_result, rewrite_result
|
| 1074 |
-
|
| 1075 |
-
def test_corpus_name_matches(self, tmp_path: Path) -> None:
|
| 1076 |
-
legacy, rewrite = self._run_both(tmp_path)
|
| 1077 |
-
assert legacy.corpus_name == rewrite.corpus_name
|
| 1078 |
-
assert legacy.document_count == rewrite.document_count
|
| 1079 |
-
|
| 1080 |
-
def test_engine_count_matches(self, tmp_path: Path) -> None:
|
| 1081 |
-
legacy, rewrite = self._run_both(tmp_path)
|
| 1082 |
-
assert len(legacy.engine_reports) == len(rewrite.engine_reports)
|
| 1083 |
-
|
| 1084 |
-
def test_engine_name_and_version_match(self, tmp_path: Path) -> None:
|
| 1085 |
-
legacy, rewrite = self._run_both(tmp_path)
|
| 1086 |
-
for lr, rr in zip(legacy.engine_reports, rewrite.engine_reports):
|
| 1087 |
-
assert lr.engine_name == rr.engine_name
|
| 1088 |
-
assert lr.engine_version == rr.engine_version
|
| 1089 |
-
|
| 1090 |
-
def test_per_document_hypothesis_matches(self, tmp_path: Path) -> None:
|
| 1091 |
-
legacy, rewrite = self._run_both(tmp_path)
|
| 1092 |
-
for lr, rr in zip(legacy.engine_reports, rewrite.engine_reports):
|
| 1093 |
-
for ld, rd in zip(lr.document_results, rr.document_results):
|
| 1094 |
-
assert ld.doc_id == rd.doc_id
|
| 1095 |
-
assert ld.ground_truth == rd.ground_truth
|
| 1096 |
-
assert ld.hypothesis == rd.hypothesis
|
| 1097 |
-
|
| 1098 |
-
def test_per_document_cer_matches(self, tmp_path: Path) -> None:
|
| 1099 |
-
"""Critère central : les CER doc-par-doc sont identiques au
|
| 1100 |
-
round près (les deux runners utilisent ``compute_metrics``)."""
|
| 1101 |
-
legacy, rewrite = self._run_both(tmp_path)
|
| 1102 |
-
for lr, rr in zip(legacy.engine_reports, rewrite.engine_reports):
|
| 1103 |
-
for ld, rd in zip(lr.document_results, rr.document_results):
|
| 1104 |
-
assert ld.metrics.cer == pytest.approx(rd.metrics.cer)
|
| 1105 |
-
assert ld.metrics.wer == pytest.approx(rd.metrics.wer)
|
| 1106 |
-
assert ld.metrics.mer == pytest.approx(rd.metrics.mer)
|
| 1107 |
-
assert ld.metrics.wil == pytest.approx(rd.metrics.wil)
|
| 1108 |
-
|
| 1109 |
-
def test_aggregated_metrics_match(self, tmp_path: Path) -> None:
|
| 1110 |
-
"""Les agrégats par engine (cer.mean, wer.mean, etc.) doivent
|
| 1111 |
-
coïncider — les deux runners utilisent ``aggregate_metrics``."""
|
| 1112 |
-
legacy, rewrite = self._run_both(tmp_path)
|
| 1113 |
-
for lr, rr in zip(legacy.engine_reports, rewrite.engine_reports):
|
| 1114 |
-
for key in ("cer", "wer", "mer", "wil"):
|
| 1115 |
-
lstats = lr.aggregated_metrics.get(key)
|
| 1116 |
-
rstats = rr.aggregated_metrics.get(key)
|
| 1117 |
-
if lstats is None or rstats is None:
|
| 1118 |
-
continue
|
| 1119 |
-
# Ces dicts sont {mean, median, min, max, stdev}.
|
| 1120 |
-
for stat_name in ("mean", "median", "min", "max"):
|
| 1121 |
-
assert lstats[stat_name] == pytest.approx(rstats[stat_name]), (
|
| 1122 |
-
f"Différence sur aggregated_metrics[{key!r}][{stat_name!r}] : "
|
| 1123 |
-
f"legacy={lstats[stat_name]} rewrite={rstats[stat_name]}"
|
| 1124 |
-
)
|
| 1125 |
-
|
| 1126 |
-
def test_engine_error_field_matches(self, tmp_path: Path) -> None:
|
| 1127 |
-
legacy, rewrite = self._run_both(tmp_path)
|
| 1128 |
-
for lr, rr in zip(legacy.engine_reports, rewrite.engine_reports):
|
| 1129 |
-
for ld, rd in zip(lr.document_results, rr.document_results):
|
| 1130 |
-
# None de chaque côté pour un OCR mock qui ne lève pas.
|
| 1131 |
-
assert ld.engine_error == rd.engine_error
|
| 1132 |
-
|
| 1133 |
|
| 1134 |
# ──────────────────────────────────────────────────────────────────────
|
| 1135 |
# D.2.a — progress_callback dans run_benchmark_via_service
|
|
|
|
| 14 |
|
| 15 |
import json
|
| 16 |
from pathlib import Path
|
|
|
|
| 17 |
|
| 18 |
import pytest
|
| 19 |
|
|
|
|
| 984 |
assert bm.engine_reports
|
| 985 |
|
| 986 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 987 |
|
| 988 |
# ──────────────────────────────────────────────────────────────────────
|
| 989 |
# D.2.a — progress_callback dans run_benchmark_via_service
|
|
@@ -50,9 +50,9 @@ FILE_BUDGETS: dict[str, int] = {
|
|
| 50 |
# de la famille ne dépasse 350 lignes, donc aucune entrée requise.
|
| 51 |
# runner.py (1019 lignes) a été éclaté en sous-package
|
| 52 |
# ``picarones/measurements/runner/`` lors du sprint
|
| 53 |
-
# « découpage de runner.py » (2026-05-03).
|
| 54 |
-
#
|
| 55 |
-
|
| 56 |
# --- Refactor (sprint « découpage de generator.py ») : passé de
|
| 57 |
# 1063 à 431 lignes via extraction vers picarones/report/assets.py
|
| 58 |
# et le sous-package picarones/report/report_data/. Budget serré
|
|
|
|
| 50 |
# de la famille ne dépasse 350 lignes, donc aucune entrée requise.
|
| 51 |
# runner.py (1019 lignes) a été éclaté en sous-package
|
| 52 |
# ``picarones/measurements/runner/`` lors du sprint
|
| 53 |
+
# « découpage de runner.py » (2026-05-03). Le sous-package a été
|
| 54 |
+
# supprimé en Sprint D.6.b du plan v2.0 — son entrée dans
|
| 55 |
+
# ``FILE_BUDGETS`` a été retirée.
|
| 56 |
# --- Refactor (sprint « découpage de generator.py ») : passé de
|
| 57 |
# 1063 à 431 lignes via extraction vers picarones/report/assets.py
|
| 58 |
# et le sous-package picarones/report/report_data/. Budget serré
|
|
@@ -73,7 +73,7 @@ LEGACY_PACKAGES: tuple[str, ...] = (
|
|
| 73 |
#: :data:`LEGACY_PARITY` sans faire échouer le test. À diminuer
|
| 74 |
#: à chaque session de migration : on cible 0 quand le retrait
|
| 75 |
#: est complet.
|
| 76 |
-
BOOTSTRAP_BASELINE =
|
| 77 |
|
| 78 |
|
| 79 |
# ──────────────────────────────────────────────────────────────────
|
|
|
|
| 73 |
#: :data:`LEGACY_PARITY` sans faire échouer le test. À diminuer
|
| 74 |
#: à chaque session de migration : on cible 0 quand le retrait
|
| 75 |
#: est complet.
|
| 76 |
+
BOOTSTRAP_BASELINE = 99
|
| 77 |
|
| 78 |
|
| 79 |
# ──────────────────────────────────────────────────────────────────
|
|
@@ -69,6 +69,13 @@ TEST_ONLY_BASELINE: frozenset[str] = frozenset({
|
|
| 69 |
# ``picarones/`` (renderer canonique qui consomme le canonique
|
| 70 |
# directement, mais module legacy gardé pour les tests).
|
| 71 |
"numerical_sequences_hooks",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
})
|
| 73 |
|
| 74 |
|
|
|
|
| 69 |
# ``picarones/`` (renderer canonique qui consomme le canonique
|
| 70 |
# directement, mais module legacy gardé pour les tests).
|
| 71 |
"numerical_sequences_hooks",
|
| 72 |
+
# Sprint D.6.b du plan v2.0 — le sous-package
|
| 73 |
+
# ``measurements.runner`` a été supprimé. ``builtin_hooks``
|
| 74 |
+
# était son consommateur direct (registre des hooks de
|
| 75 |
+
# métriques) ; sans le runner, il n'a plus de consommateur
|
| 76 |
+
# production. Suppression / migration prévue en Sprint E
|
| 77 |
+
# (migration des hooks vers ``evaluation/metric_hooks/``).
|
| 78 |
+
"builtin_hooks",
|
| 79 |
})
|
| 80 |
|
| 81 |
|
|
@@ -255,46 +255,6 @@ class TestRunDocumentHooks:
|
|
| 255 |
ocr_result=_MockEngineResult(token_confidences=None),
|
| 256 |
)
|
| 257 |
assert called == []
|
| 258 |
-
|
| 259 |
-
|
| 260 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 261 |
-
# 4. Rétrocompat : runner expose toujours les helpers privés
|
| 262 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 263 |
-
|
| 264 |
-
|
| 265 |
-
class TestRunnerBackwardCompat:
|
| 266 |
-
"""Les tests Sprint 13 et Sprint 42 importent directement depuis
|
| 267 |
-
``picarones.measurements.runner``. Ces noms doivent rester disponibles
|
| 268 |
-
après le chantier 2."""
|
| 269 |
-
|
| 270 |
-
@pytest.mark.parametrize("name", [
|
| 271 |
-
"_aggregate_confusion",
|
| 272 |
-
"_aggregate_char_scores",
|
| 273 |
-
"_aggregate_taxonomy",
|
| 274 |
-
"_aggregate_structure",
|
| 275 |
-
"_aggregate_image_quality",
|
| 276 |
-
"_aggregate_line_metrics",
|
| 277 |
-
"_aggregate_hallucination",
|
| 278 |
-
"_aggregate_calibration",
|
| 279 |
-
"_calibration_from_engine_result",
|
| 280 |
-
])
|
| 281 |
-
def test_helper_still_exported_from_runner(self, name):
|
| 282 |
-
# Skip si tqdm ou autres deps absents (sandbox minimaliste).
|
| 283 |
-
pytest.importorskip("tqdm")
|
| 284 |
-
from picarones.measurements import runner
|
| 285 |
-
|
| 286 |
-
assert hasattr(runner, name), (
|
| 287 |
-
f"runner.{name} a disparu — casse les tests Sprint 13/42 "
|
| 288 |
-
"qui font ``from picarones.measurements.runner import {name}``"
|
| 289 |
-
)
|
| 290 |
-
assert callable(getattr(runner, name))
|
| 291 |
-
|
| 292 |
-
|
| 293 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 294 |
-
# 5. Décorateurs : idempotence + erreurs sur conflit
|
| 295 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 296 |
-
|
| 297 |
-
|
| 298 |
class TestDecoratorIdempotence:
|
| 299 |
def test_register_same_func_twice_is_silent(self):
|
| 300 |
"""Ré-import d'un module en test ne doit pas lever sur le
|
|
|
|
| 255 |
ocr_result=_MockEngineResult(token_confidences=None),
|
| 256 |
)
|
| 257 |
assert called == []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 258 |
class TestDecoratorIdempotence:
|
| 259 |
def test_register_same_func_twice_is_silent(self):
|
| 260 |
"""Ré-import d'un module en test ne doit pas lever sur le
|
|
@@ -197,38 +197,38 @@ class TestMetricsApi:
|
|
| 197 |
|
| 198 |
|
| 199 |
# ──────────────────────────────────────────────────────────────────────────
|
| 200 |
-
# 5. picarones.
|
| 201 |
# ──────────────────────────────────────────────────────────────────────────
|
| 202 |
|
| 203 |
|
| 204 |
class TestRunnerApi:
|
| 205 |
-
def
|
| 206 |
-
|
| 207 |
-
|
| 208 |
-
|
| 209 |
-
|
| 210 |
-
|
| 211 |
-
|
| 212 |
-
|
| 213 |
-
def
|
| 214 |
"""Les paramètres clés (corpus, engines, profile…) doivent rester
|
| 215 |
-
accessibles. Ajout d'un argument requis =
|
| 216 |
-
|
| 217 |
-
|
| 218 |
-
|
| 219 |
-
|
| 220 |
-
|
| 221 |
-
raise
|
| 222 |
-
sig = inspect.signature(run_benchmark)
|
| 223 |
params = sig.parameters
|
| 224 |
-
# Arguments contractuels — leur présence est garantie
|
|
|
|
| 225 |
for name in [
|
| 226 |
"corpus", "engines", "output_json", "show_progress",
|
| 227 |
"char_exclude", "max_workers", "timeout_seconds",
|
| 228 |
"profile",
|
| 229 |
]:
|
| 230 |
assert name in params, (
|
| 231 |
-
f"
|
|
|
|
| 232 |
)
|
| 233 |
|
| 234 |
|
|
@@ -448,7 +448,7 @@ class TestApiStableDoc:
|
|
| 448 |
"picarones.domain.module_protocol",
|
| 449 |
"picarones.evaluation.benchmark_result",
|
| 450 |
"picarones.measurements.metrics",
|
| 451 |
-
"picarones.
|
| 452 |
"picarones.evaluation.metric_registry",
|
| 453 |
"picarones.evaluation.metric_hooks",
|
| 454 |
"picarones.measurements.builtin_metrics",
|
|
|
|
| 197 |
|
| 198 |
|
| 199 |
# ──────────────────────────────────────────────────────────────────────────
|
| 200 |
+
# 5. picarones.app.services._legacy_runner_adapter — run_benchmark_via_service
|
| 201 |
# ──────────────────────────────────────────────────────────────────────────
|
| 202 |
|
| 203 |
|
| 204 |
class TestRunnerApi:
|
| 205 |
+
def test_run_benchmark_via_service_exists(self):
|
| 206 |
+
"""Sprint D du plan v2.0 — l'adapter rewrite remplace
|
| 207 |
+
``measurements.runner.run_benchmark`` (legacy supprimé en D.6)."""
|
| 208 |
+
_assert_function(
|
| 209 |
+
"picarones.app.services._legacy_runner_adapter",
|
| 210 |
+
"run_benchmark_via_service",
|
| 211 |
+
)
|
| 212 |
+
|
| 213 |
+
def test_run_benchmark_via_service_keyword_args(self):
|
| 214 |
"""Les paramètres clés (corpus, engines, profile…) doivent rester
|
| 215 |
+
accessibles dans l'adapter rewrite. Ajout d'un argument requis =
|
| 216 |
+
breaking change."""
|
| 217 |
+
from picarones.app.services._legacy_runner_adapter import (
|
| 218 |
+
run_benchmark_via_service,
|
| 219 |
+
)
|
| 220 |
+
sig = inspect.signature(run_benchmark_via_service)
|
|
|
|
|
|
|
| 221 |
params = sig.parameters
|
| 222 |
+
# Arguments contractuels — leur présence est garantie pour
|
| 223 |
+
# rester compatible avec les callers historiques.
|
| 224 |
for name in [
|
| 225 |
"corpus", "engines", "output_json", "show_progress",
|
| 226 |
"char_exclude", "max_workers", "timeout_seconds",
|
| 227 |
"profile",
|
| 228 |
]:
|
| 229 |
assert name in params, (
|
| 230 |
+
f"run_benchmark_via_service : argument '{name}' a disparu "
|
| 231 |
+
f"(signature : {sig})"
|
| 232 |
)
|
| 233 |
|
| 234 |
|
|
|
|
| 448 |
"picarones.domain.module_protocol",
|
| 449 |
"picarones.evaluation.benchmark_result",
|
| 450 |
"picarones.measurements.metrics",
|
| 451 |
+
"picarones.app.services._legacy_runner_adapter",
|
| 452 |
"picarones.evaluation.metric_registry",
|
| 453 |
"picarones.evaluation.metric_hooks",
|
| 454 |
"picarones.measurements.builtin_metrics",
|
|
@@ -245,43 +245,6 @@ class TestTokenFiltering:
|
|
| 245 |
# ──────────────────────────────────────────────────────────────────────────
|
| 246 |
|
| 247 |
|
| 248 |
-
class TestEndToEndWithRunner:
|
| 249 |
-
def test_runner_picks_up_confidences_and_computes_calibration(
|
| 250 |
-
self, monkeypatch: pytest.MonkeyPatch, tmp_path: Path,
|
| 251 |
-
) -> None:
|
| 252 |
-
from picarones.measurements.runner import _compute_document_result
|
| 253 |
-
from picarones.adapters.legacy_engines.base import EngineResult
|
| 254 |
-
|
| 255 |
-
# Simulation : on appelle directement _compute_document_result
|
| 256 |
-
# avec un EngineResult mocké qui porte des confidences. On
|
| 257 |
-
# vérifie que la calibration_metrics est bien attachée.
|
| 258 |
-
ocr = EngineResult(
|
| 259 |
-
engine_name="tess",
|
| 260 |
-
image_path="/tmp/x.png",
|
| 261 |
-
text="alpha beta gamma",
|
| 262 |
-
duration_seconds=0.1,
|
| 263 |
-
token_confidences=[
|
| 264 |
-
{"token": "alpha", "confidence": 95.0},
|
| 265 |
-
{"token": "beta", "confidence": 95.0},
|
| 266 |
-
{"token": "gamma", "confidence": 95.0},
|
| 267 |
-
],
|
| 268 |
-
)
|
| 269 |
-
dr = _compute_document_result(
|
| 270 |
-
doc_id="d1", image_path="/tmp/x.png",
|
| 271 |
-
ground_truth="alpha beta gamma",
|
| 272 |
-
ocr_result=ocr, char_exclude=None,
|
| 273 |
-
)
|
| 274 |
-
assert dr.calibration_metrics is not None
|
| 275 |
-
# 3 tokens, tous corrects → accuracy = 1, conf = 0.95
|
| 276 |
-
assert dr.calibration_metrics["overall_accuracy"] == 1.0
|
| 277 |
-
assert dr.calibration_metrics["overall_confidence"] == pytest.approx(0.95)
|
| 278 |
-
|
| 279 |
-
|
| 280 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 281 |
-
# 7. pytesseract absent → fallback gracieux
|
| 282 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 283 |
-
|
| 284 |
-
|
| 285 |
class TestPytesseractAbsent:
|
| 286 |
def test_extraction_returns_none_without_pytesseract(
|
| 287 |
self, monkeypatch: pytest.MonkeyPatch, tmp_path: Path,
|
|
|
|
| 245 |
# ──────────────────────────────────────────────────────────────────────────
|
| 246 |
|
| 247 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 248 |
class TestPytesseractAbsent:
|
| 249 |
def test_extraction_returns_none_without_pytesseract(
|
| 250 |
self, monkeypatch: pytest.MonkeyPatch, tmp_path: Path,
|
|
@@ -240,39 +240,6 @@ class TestRunPipeline:
|
|
| 240 |
# ──────────────────────────────────────────────────────────────────────────
|
| 241 |
|
| 242 |
|
| 243 |
-
class TestEndToEndWithRunner:
|
| 244 |
-
def test_runner_picks_up_confidences(self) -> None:
|
| 245 |
-
from picarones.measurements.runner import _compute_document_result
|
| 246 |
-
from picarones.adapters.legacy_engines.base import EngineResult
|
| 247 |
-
|
| 248 |
-
ocr = EngineResult(
|
| 249 |
-
engine_name="pero",
|
| 250 |
-
image_path="/tmp/x.png",
|
| 251 |
-
text="alpha beta gamma",
|
| 252 |
-
duration_seconds=0.1,
|
| 253 |
-
# Confidence ∈ [0, 1] côté Pero (vs [0, 100] Tesseract) —
|
| 254 |
-
# le runner Sprint 42 normalise via le helper bag-of-words.
|
| 255 |
-
token_confidences=[
|
| 256 |
-
{"token": "alpha", "confidence": 0.95},
|
| 257 |
-
{"token": "beta", "confidence": 0.95},
|
| 258 |
-
{"token": "gamma", "confidence": 0.95},
|
| 259 |
-
],
|
| 260 |
-
)
|
| 261 |
-
dr = _compute_document_result(
|
| 262 |
-
doc_id="d1", image_path="/tmp/x.png",
|
| 263 |
-
ground_truth="alpha beta gamma",
|
| 264 |
-
ocr_result=ocr, char_exclude=None,
|
| 265 |
-
)
|
| 266 |
-
assert dr.calibration_metrics is not None
|
| 267 |
-
assert dr.calibration_metrics["overall_accuracy"] == 1.0
|
| 268 |
-
assert dr.calibration_metrics["overall_confidence"] == pytest.approx(0.95)
|
| 269 |
-
|
| 270 |
-
|
| 271 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 272 |
-
# 9. Pero absent — fallback gracieux côté pipeline réel
|
| 273 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 274 |
-
|
| 275 |
-
|
| 276 |
class TestPeroAbsent:
|
| 277 |
def test_pipeline_missing_pero_raises(
|
| 278 |
self, monkeypatch: pytest.MonkeyPatch, tmp_path: Path,
|
|
|
|
| 240 |
# ──────────────────────────────────────────────────────────────────────────
|
| 241 |
|
| 242 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 243 |
class TestPeroAbsent:
|
| 244 |
def test_pipeline_missing_pero_raises(
|
| 245 |
self, monkeypatch: pytest.MonkeyPatch, tmp_path: Path,
|
|
@@ -272,30 +272,3 @@ class TestRunOverride:
|
|
| 272 |
# ──────────────────────────────────────────────────────────────────────────
|
| 273 |
|
| 274 |
|
| 275 |
-
class TestEndToEndWithRunner:
|
| 276 |
-
def test_runner_picks_up_mistral_confidences(self) -> None:
|
| 277 |
-
from picarones.measurements.runner import _compute_document_result
|
| 278 |
-
from picarones.adapters.legacy_engines.base import EngineResult
|
| 279 |
-
|
| 280 |
-
ocr = EngineResult(
|
| 281 |
-
engine_name="mistral_ocr",
|
| 282 |
-
image_path="/tmp/x.png",
|
| 283 |
-
text="alpha beta gamma",
|
| 284 |
-
duration_seconds=0.1,
|
| 285 |
-
token_confidences=[
|
| 286 |
-
{"token": "alpha", "confidence": 0.95},
|
| 287 |
-
{"token": "beta", "confidence": 0.85},
|
| 288 |
-
{"token": "gamma", "confidence": 0.95},
|
| 289 |
-
],
|
| 290 |
-
)
|
| 291 |
-
dr = _compute_document_result(
|
| 292 |
-
doc_id="d1", image_path="/tmp/x.png",
|
| 293 |
-
ground_truth="alpha beta gamma",
|
| 294 |
-
ocr_result=ocr, char_exclude=None,
|
| 295 |
-
)
|
| 296 |
-
assert dr.calibration_metrics is not None
|
| 297 |
-
assert dr.calibration_metrics["overall_accuracy"] == 1.0
|
| 298 |
-
# confidence moyenne = (0.95 + 0.85 + 0.95) / 3
|
| 299 |
-
assert dr.calibration_metrics["overall_confidence"] == pytest.approx(
|
| 300 |
-
(0.95 + 0.85 + 0.95) / 3,
|
| 301 |
-
)
|
|
|
|
| 272 |
# ──────────────────────────────────────────────────────────────────────────
|
| 273 |
|
| 274 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@@ -329,29 +329,3 @@ class TestRESTPath:
|
|
| 329 |
# ──────────────────────────────────────────────────────────────────────────
|
| 330 |
|
| 331 |
|
| 332 |
-
class TestEndToEndWithRunner:
|
| 333 |
-
def test_runner_picks_up_google_vision_confidences(self) -> None:
|
| 334 |
-
from picarones.measurements.runner import _compute_document_result
|
| 335 |
-
from picarones.adapters.legacy_engines.base import EngineResult
|
| 336 |
-
|
| 337 |
-
ocr = EngineResult(
|
| 338 |
-
engine_name="google_vision",
|
| 339 |
-
image_path="/tmp/x.png",
|
| 340 |
-
text="alpha beta gamma",
|
| 341 |
-
duration_seconds=0.1,
|
| 342 |
-
token_confidences=[
|
| 343 |
-
{"token": "alpha", "confidence": 0.95},
|
| 344 |
-
{"token": "beta", "confidence": 0.92},
|
| 345 |
-
{"token": "gamma", "confidence": 0.97},
|
| 346 |
-
],
|
| 347 |
-
)
|
| 348 |
-
dr = _compute_document_result(
|
| 349 |
-
doc_id="d1", image_path="/tmp/x.png",
|
| 350 |
-
ground_truth="alpha beta gamma",
|
| 351 |
-
ocr_result=ocr, char_exclude=None,
|
| 352 |
-
)
|
| 353 |
-
assert dr.calibration_metrics is not None
|
| 354 |
-
assert dr.calibration_metrics["overall_accuracy"] == 1.0
|
| 355 |
-
assert dr.calibration_metrics["overall_confidence"] == pytest.approx(
|
| 356 |
-
(0.95 + 0.92 + 0.97) / 3,
|
| 357 |
-
)
|
|
|
|
| 329 |
# ──────────────────────────────────────────────────────────────────────────
|
| 330 |
|
| 331 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@@ -250,29 +250,3 @@ class TestRunOverride:
|
|
| 250 |
# ──────────────────────────────────────────────────────────────────────────
|
| 251 |
|
| 252 |
|
| 253 |
-
class TestEndToEndWithRunner:
|
| 254 |
-
def test_runner_picks_up_azure_confidences(self) -> None:
|
| 255 |
-
from picarones.measurements.runner import _compute_document_result
|
| 256 |
-
from picarones.adapters.legacy_engines.base import EngineResult
|
| 257 |
-
|
| 258 |
-
ocr = EngineResult(
|
| 259 |
-
engine_name="azure_doc_intel",
|
| 260 |
-
image_path="/tmp/x.png",
|
| 261 |
-
text="alpha beta gamma",
|
| 262 |
-
duration_seconds=0.1,
|
| 263 |
-
token_confidences=[
|
| 264 |
-
{"token": "alpha", "confidence": 0.97},
|
| 265 |
-
{"token": "beta", "confidence": 0.93},
|
| 266 |
-
{"token": "gamma", "confidence": 0.95},
|
| 267 |
-
],
|
| 268 |
-
)
|
| 269 |
-
dr = _compute_document_result(
|
| 270 |
-
doc_id="d1", image_path="/tmp/x.png",
|
| 271 |
-
ground_truth="alpha beta gamma",
|
| 272 |
-
ocr_result=ocr, char_exclude=None,
|
| 273 |
-
)
|
| 274 |
-
assert dr.calibration_metrics is not None
|
| 275 |
-
assert dr.calibration_metrics["overall_accuracy"] == 1.0
|
| 276 |
-
assert dr.calibration_metrics["overall_confidence"] == pytest.approx(
|
| 277 |
-
(0.97 + 0.93 + 0.95) / 3,
|
| 278 |
-
)
|
|
|
|
| 250 |
# ──────────────────────────────────────────────────────────────────────────
|
| 251 |
|
| 252 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@@ -216,39 +216,3 @@ class TestCliPackage:
|
|
| 216 |
)
|
| 217 |
|
| 218 |
|
| 219 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 220 |
-
# 5.C — runner reste atteignable via son API publique historique
|
| 221 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 222 |
-
|
| 223 |
-
|
| 224 |
-
class TestRunnerStillReachable:
|
| 225 |
-
"""L'API historique de ``picarones.measurements.runner`` reste accessible.
|
| 226 |
-
|
| 227 |
-
Le chantier 2 (post-Sprint 97) avait allégé ``runner.py`` de 303 lignes
|
| 228 |
-
(1322 → 1019) ; le sprint « découpage de runner.py » (mai 2026, hors
|
| 229 |
-
chantier 5) l'a ensuite éclaté en sous-package ``runner/``. Dans tous
|
| 230 |
-
les cas, les fonctions historiques restent atteignables via les
|
| 231 |
-
ré-exports — c'est ce qu'on vérifie ici."""
|
| 232 |
-
|
| 233 |
-
@pytest.mark.parametrize("name", [
|
| 234 |
-
"run_benchmark",
|
| 235 |
-
"_compute_document_result",
|
| 236 |
-
"_cpu_doc_worker",
|
| 237 |
-
"_io_doc_worker",
|
| 238 |
-
"_aggregate_confusion",
|
| 239 |
-
"_aggregate_calibration",
|
| 240 |
-
"_calibration_from_engine_result",
|
| 241 |
-
"_aggregate_ner",
|
| 242 |
-
"_attach_ner_metrics",
|
| 243 |
-
])
|
| 244 |
-
def test_function_still_in_runner(self, name):
|
| 245 |
-
try:
|
| 246 |
-
from picarones.measurements import runner
|
| 247 |
-
except ImportError as exc:
|
| 248 |
-
if "tqdm" in str(exc):
|
| 249 |
-
pytest.skip("tqdm non installé")
|
| 250 |
-
raise
|
| 251 |
-
assert hasattr(runner, name), (
|
| 252 |
-
f"runner.{name} a disparu"
|
| 253 |
-
)
|
| 254 |
-
assert callable(getattr(runner, name))
|
|
|
|
| 216 |
)
|
| 217 |
|
| 218 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@@ -1,552 +0,0 @@
|
|
| 1 |
-
"""Tests Sprint 13 — Corrections structurelles : parallelisation, exceptions, statistiques.
|
| 2 |
-
|
| 3 |
-
Classes de tests
|
| 4 |
-
----------------
|
| 5 |
-
TestPyprojectCorrections (4 tests) — Part 1 : Beta, deps clarifiées
|
| 6 |
-
TestEngineExecutionMode (5 tests) — Part 2 : execution_mode sur les classes moteur
|
| 7 |
-
TestRunnerParallelParams (5 tests) — Part 3 : signature run_benchmark étendue
|
| 8 |
-
TestRunnerTimeout (3 tests) — Part 3 : timeout par document
|
| 9 |
-
TestRunnerPartialResults (4 tests) — Part 3 : sauvegarde / reprise partiels
|
| 10 |
-
TestRunnerSilentExceptions (3 tests) — Part 2 : warnings au lieu de pass silencieux
|
| 11 |
-
TestWilcoxonValidation (7 tests) — Part 4 : valeurs de référence connues
|
| 12 |
-
TestWilcoxonScipyIntegration (3 tests) — Part 4 : cohérence scipy / natif
|
| 13 |
-
"""
|
| 14 |
-
|
| 15 |
-
from __future__ import annotations
|
| 16 |
-
|
| 17 |
-
import inspect
|
| 18 |
-
import json
|
| 19 |
-
import math
|
| 20 |
-
from pathlib import Path
|
| 21 |
-
from unittest.mock import patch
|
| 22 |
-
|
| 23 |
-
import pytest
|
| 24 |
-
|
| 25 |
-
ROOT = Path(__file__).parent.parent.parent
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
# ===========================================================================
|
| 29 |
-
# Fixtures
|
| 30 |
-
# ===========================================================================
|
| 31 |
-
|
| 32 |
-
@pytest.fixture
|
| 33 |
-
def tmp_corpus(tmp_path):
|
| 34 |
-
"""Corpus minimal de 3 documents pour les tests runner."""
|
| 35 |
-
from PIL import Image
|
| 36 |
-
for i in range(3):
|
| 37 |
-
img = Image.new("RGB", (100, 30), color="white")
|
| 38 |
-
img.save(tmp_path / f"doc{i:02d}.png")
|
| 39 |
-
(tmp_path / f"doc{i:02d}.gt.txt").write_text(f"texte vérité {i}", encoding="utf-8")
|
| 40 |
-
return tmp_path
|
| 41 |
-
|
| 42 |
-
|
| 43 |
-
# ===========================================================================
|
| 44 |
-
# Part 1 — Corrections pyproject.toml
|
| 45 |
-
# ===========================================================================
|
| 46 |
-
|
| 47 |
-
class TestPyprojectCorrections:
|
| 48 |
-
|
| 49 |
-
def _read_pyproject(self) -> str:
|
| 50 |
-
return (ROOT / "pyproject.toml").read_text(encoding="utf-8")
|
| 51 |
-
|
| 52 |
-
def test_classifier_is_beta(self):
|
| 53 |
-
"""Le classifier doit être 4 - Beta et non 5 - Production/Stable."""
|
| 54 |
-
content = self._read_pyproject()
|
| 55 |
-
assert "Development Status :: 4 - Beta" in content, (
|
| 56 |
-
"pyproject.toml doit contenir 'Development Status :: 4 - Beta'"
|
| 57 |
-
)
|
| 58 |
-
assert "Production/Stable" not in content, (
|
| 59 |
-
"pyproject.toml ne doit plus contenir 'Production/Stable'"
|
| 60 |
-
)
|
| 61 |
-
|
| 62 |
-
def test_fastapi_not_in_base_deps(self):
|
| 63 |
-
"""fastapi ne doit pas être dans les dépendances de base."""
|
| 64 |
-
import re
|
| 65 |
-
content = self._read_pyproject()
|
| 66 |
-
# Extraire la section dependencies = [...] sous [project] (avant la 1re section suivante)
|
| 67 |
-
m = re.search(r"^dependencies\s*=\s*\[(.*?)\]", content, re.DOTALL | re.MULTILINE)
|
| 68 |
-
assert m, "Section dependencies introuvable dans pyproject.toml"
|
| 69 |
-
base_deps = m.group(1)
|
| 70 |
-
assert "fastapi" not in base_deps, (
|
| 71 |
-
"fastapi ne doit pas être dans les dépendances de base — seulement dans [web]"
|
| 72 |
-
)
|
| 73 |
-
|
| 74 |
-
def test_httpx_not_in_base_deps(self):
|
| 75 |
-
"""httpx ne doit pas être dans les dépendances de base."""
|
| 76 |
-
import re
|
| 77 |
-
content = self._read_pyproject()
|
| 78 |
-
m = re.search(r"^dependencies\s*=\s*\[(.*?)\]", content, re.DOTALL | re.MULTILINE)
|
| 79 |
-
assert m
|
| 80 |
-
base_deps = m.group(1)
|
| 81 |
-
assert "httpx" not in base_deps, (
|
| 82 |
-
"httpx ne doit pas être dans les dépendances de base — seulement dans [web]"
|
| 83 |
-
)
|
| 84 |
-
|
| 85 |
-
def test_web_extra_has_fastapi_httpx_multipart(self):
|
| 86 |
-
"""L'extra [web] doit contenir fastapi, httpx et python-multipart."""
|
| 87 |
-
import tomllib
|
| 88 |
-
with (ROOT / "pyproject.toml").open("rb") as fh:
|
| 89 |
-
data = tomllib.load(fh)
|
| 90 |
-
web_deps = " ".join(data["project"]["optional-dependencies"]["web"])
|
| 91 |
-
assert "fastapi" in web_deps
|
| 92 |
-
assert "httpx" in web_deps
|
| 93 |
-
assert "python-multipart" in web_deps
|
| 94 |
-
|
| 95 |
-
|
| 96 |
-
# ===========================================================================
|
| 97 |
-
# Part 2 — execution_mode sur les classes moteur
|
| 98 |
-
# ===========================================================================
|
| 99 |
-
|
| 100 |
-
class TestEngineExecutionMode:
|
| 101 |
-
|
| 102 |
-
def test_base_engine_default_mode_is_io(self):
|
| 103 |
-
"""BaseOCREngine doit avoir execution_mode = 'io' par défaut."""
|
| 104 |
-
from picarones.adapters.legacy_engines.base import BaseOCREngine
|
| 105 |
-
assert BaseOCREngine.execution_mode == "io"
|
| 106 |
-
|
| 107 |
-
def test_tesseract_engine_mode_is_cpu(self):
|
| 108 |
-
"""TesseractEngine doit avoir execution_mode = 'cpu'."""
|
| 109 |
-
from picarones.adapters.legacy_engines.tesseract import TesseractEngine
|
| 110 |
-
assert TesseractEngine.execution_mode == "cpu"
|
| 111 |
-
|
| 112 |
-
def test_pero_engine_mode_is_cpu(self):
|
| 113 |
-
"""PeroOCREngine doit avoir execution_mode = 'cpu'."""
|
| 114 |
-
from picarones.adapters.legacy_engines.pero_ocr import PeroOCREngine
|
| 115 |
-
assert PeroOCREngine.execution_mode == "cpu"
|
| 116 |
-
|
| 117 |
-
def test_mistral_engine_default_mode_is_io(self):
|
| 118 |
-
"""MistralOCREngine doit hériter execution_mode = 'io'."""
|
| 119 |
-
from picarones.adapters.legacy_engines.mistral_ocr import MistralOCREngine
|
| 120 |
-
assert MistralOCREngine.execution_mode == "io"
|
| 121 |
-
|
| 122 |
-
def test_google_vision_default_mode_is_io(self):
|
| 123 |
-
"""GoogleVisionEngine doit hériter execution_mode = 'io'."""
|
| 124 |
-
from picarones.adapters.legacy_engines.google_vision import GoogleVisionEngine
|
| 125 |
-
assert GoogleVisionEngine.execution_mode == "io"
|
| 126 |
-
|
| 127 |
-
|
| 128 |
-
# ===========================================================================
|
| 129 |
-
# Part 3 — Signature run_benchmark étendue
|
| 130 |
-
# ===========================================================================
|
| 131 |
-
|
| 132 |
-
class TestRunnerParallelParams:
|
| 133 |
-
|
| 134 |
-
def test_max_workers_param_exists(self):
|
| 135 |
-
"""run_benchmark doit accepter max_workers."""
|
| 136 |
-
from picarones.measurements.runner import run_benchmark
|
| 137 |
-
sig = inspect.signature(run_benchmark)
|
| 138 |
-
assert "max_workers" in sig.parameters
|
| 139 |
-
|
| 140 |
-
def test_max_workers_default_is_4(self):
|
| 141 |
-
"""max_workers doit avoir 4 comme valeur par défaut."""
|
| 142 |
-
from picarones.measurements.runner import run_benchmark
|
| 143 |
-
sig = inspect.signature(run_benchmark)
|
| 144 |
-
assert sig.parameters["max_workers"].default == 4
|
| 145 |
-
|
| 146 |
-
def test_timeout_seconds_param_exists(self):
|
| 147 |
-
"""run_benchmark doit accepter timeout_seconds."""
|
| 148 |
-
from picarones.measurements.runner import run_benchmark
|
| 149 |
-
sig = inspect.signature(run_benchmark)
|
| 150 |
-
assert "timeout_seconds" in sig.parameters
|
| 151 |
-
|
| 152 |
-
def test_timeout_seconds_default_is_60(self):
|
| 153 |
-
"""timeout_seconds doit avoir 60.0 comme valeur par défaut."""
|
| 154 |
-
from picarones.measurements.runner import run_benchmark
|
| 155 |
-
sig = inspect.signature(run_benchmark)
|
| 156 |
-
assert sig.parameters["timeout_seconds"].default == 60.0
|
| 157 |
-
|
| 158 |
-
def test_partial_dir_param_exists(self):
|
| 159 |
-
"""run_benchmark doit accepter partial_dir (None par défaut)."""
|
| 160 |
-
from picarones.measurements.runner import run_benchmark
|
| 161 |
-
sig = inspect.signature(run_benchmark)
|
| 162 |
-
assert "partial_dir" in sig.parameters
|
| 163 |
-
assert sig.parameters["partial_dir"].default is None
|
| 164 |
-
|
| 165 |
-
|
| 166 |
-
# ===========================================================================
|
| 167 |
-
# Part 3 — Timeout par document
|
| 168 |
-
# ===========================================================================
|
| 169 |
-
|
| 170 |
-
class TestRunnerTimeout:
|
| 171 |
-
|
| 172 |
-
def test_timeout_doc_result_has_error(self, tmp_corpus):
|
| 173 |
-
"""Un document ayant dépassé le timeout doit avoir engine_error contenant 'timeout'."""
|
| 174 |
-
from picarones.evaluation.corpus import load_corpus_from_directory
|
| 175 |
-
from picarones.measurements.runner import run_benchmark
|
| 176 |
-
from picarones.adapters.legacy_engines.base import BaseOCREngine
|
| 177 |
-
import time
|
| 178 |
-
|
| 179 |
-
class SlowEngine(BaseOCREngine):
|
| 180 |
-
@property
|
| 181 |
-
def name(self): return "slow_engine"
|
| 182 |
-
def version(self): return "0.1"
|
| 183 |
-
def _run_ocr(self, image_path):
|
| 184 |
-
time.sleep(5) # 5 secondes — dépasse le timeout de 1s
|
| 185 |
-
return "jamais atteint"
|
| 186 |
-
|
| 187 |
-
corpus = load_corpus_from_directory(str(tmp_corpus))
|
| 188 |
-
result = run_benchmark(
|
| 189 |
-
corpus, [SlowEngine()],
|
| 190 |
-
show_progress=False,
|
| 191 |
-
timeout_seconds=1.0,
|
| 192 |
-
max_workers=1,
|
| 193 |
-
)
|
| 194 |
-
assert len(result.engine_reports) == 1
|
| 195 |
-
report = result.engine_reports[0]
|
| 196 |
-
assert len(report.document_results) == len(corpus)
|
| 197 |
-
# Au moins un document doit être marqué timeout
|
| 198 |
-
timeout_docs = [dr for dr in report.document_results if dr.engine_error and "timeout" in dr.engine_error]
|
| 199 |
-
assert len(timeout_docs) > 0, "Aucun document marqué timeout — le timeout ne fonctionne pas"
|
| 200 |
-
|
| 201 |
-
def test_timeout_doc_result_cer_is_one(self, tmp_corpus):
|
| 202 |
-
"""Un document timeout doit avoir CER = 1.0."""
|
| 203 |
-
from picarones.evaluation.corpus import load_corpus_from_directory
|
| 204 |
-
from picarones.measurements.runner import run_benchmark
|
| 205 |
-
from picarones.adapters.legacy_engines.base import BaseOCREngine
|
| 206 |
-
import time
|
| 207 |
-
|
| 208 |
-
class SlowEngine(BaseOCREngine):
|
| 209 |
-
@property
|
| 210 |
-
def name(self): return "slow"
|
| 211 |
-
def version(self): return "0.1"
|
| 212 |
-
def _run_ocr(self, image_path):
|
| 213 |
-
time.sleep(5)
|
| 214 |
-
return ""
|
| 215 |
-
|
| 216 |
-
corpus = load_corpus_from_directory(str(tmp_corpus))
|
| 217 |
-
result = run_benchmark(
|
| 218 |
-
corpus, [SlowEngine()],
|
| 219 |
-
show_progress=False,
|
| 220 |
-
timeout_seconds=1.0,
|
| 221 |
-
max_workers=1,
|
| 222 |
-
)
|
| 223 |
-
for dr in result.engine_reports[0].document_results:
|
| 224 |
-
if dr.engine_error and "timeout" in dr.engine_error:
|
| 225 |
-
assert dr.metrics.cer == 1.0
|
| 226 |
-
|
| 227 |
-
def test_fast_docs_not_affected_by_timeout(self, tmp_corpus):
|
| 228 |
-
"""Des documents rapides ne doivent pas être touchés par un timeout généreux."""
|
| 229 |
-
from picarones.evaluation.corpus import load_corpus_from_directory
|
| 230 |
-
from picarones.measurements.runner import run_benchmark
|
| 231 |
-
from picarones.adapters.legacy_engines.base import BaseOCREngine
|
| 232 |
-
|
| 233 |
-
class FastEngine(BaseOCREngine):
|
| 234 |
-
@property
|
| 235 |
-
def name(self): return "fast"
|
| 236 |
-
def version(self): return "0.1"
|
| 237 |
-
def _run_ocr(self, image_path): return "texte ocr"
|
| 238 |
-
|
| 239 |
-
corpus = load_corpus_from_directory(str(tmp_corpus))
|
| 240 |
-
result = run_benchmark(
|
| 241 |
-
corpus, [FastEngine()],
|
| 242 |
-
show_progress=False,
|
| 243 |
-
timeout_seconds=30.0,
|
| 244 |
-
)
|
| 245 |
-
timeout_docs = [
|
| 246 |
-
dr for dr in result.engine_reports[0].document_results
|
| 247 |
-
if dr.engine_error and "timeout" in dr.engine_error
|
| 248 |
-
]
|
| 249 |
-
assert len(timeout_docs) == 0, "Les documents rapides ne doivent pas être marqués timeout"
|
| 250 |
-
|
| 251 |
-
|
| 252 |
-
# ===========================================================================
|
| 253 |
-
# Part 3 — Résultats partiels (sauvegarde / reprise)
|
| 254 |
-
# ===========================================================================
|
| 255 |
-
|
| 256 |
-
class TestRunnerPartialResults:
|
| 257 |
-
|
| 258 |
-
def test_partial_file_created_during_run(self, tmp_corpus, tmp_path):
|
| 259 |
-
"""_save_partial_line doit être appelée pour chaque document traité."""
|
| 260 |
-
from picarones.evaluation.corpus import load_corpus_from_directory
|
| 261 |
-
from picarones.measurements.runner import run_benchmark
|
| 262 |
-
from picarones.adapters.legacy_engines.base import BaseOCREngine
|
| 263 |
-
# Sprint « découpage de runner.py » (mai 2026) : ``_save_partial_line``
|
| 264 |
-
# vit désormais dans le sous-module ``runner.partial`` ; le ré-export
|
| 265 |
-
# dans ``runner.__init__`` est une référence figée. Pour patcher
|
| 266 |
-
# dynamiquement la fonction utilisée par ``run_benchmark``, il faut
|
| 267 |
-
# cibler le module source.
|
| 268 |
-
from picarones.measurements.runner import partial as _partial_mod
|
| 269 |
-
from picarones.measurements.runner import orchestration as _orch_mod
|
| 270 |
-
|
| 271 |
-
save_calls: list[str] = []
|
| 272 |
-
original_save = _partial_mod._save_partial_line
|
| 273 |
-
|
| 274 |
-
def tracking_save(path, doc_result):
|
| 275 |
-
save_calls.append(doc_result.doc_id)
|
| 276 |
-
original_save(path, doc_result)
|
| 277 |
-
|
| 278 |
-
class MockEngine(BaseOCREngine):
|
| 279 |
-
@property
|
| 280 |
-
def name(self): return "mock"
|
| 281 |
-
def version(self): return "0.1"
|
| 282 |
-
def _run_ocr(self, image_path): return "texte"
|
| 283 |
-
|
| 284 |
-
corpus = load_corpus_from_directory(str(tmp_corpus))
|
| 285 |
-
# Patche la fonction directement dans l'orchestrateur, qui
|
| 286 |
-
# l'a importée depuis ``partial`` au moment du chargement.
|
| 287 |
-
with patch.object(_orch_mod, "_save_partial_line", side_effect=tracking_save):
|
| 288 |
-
run_benchmark(
|
| 289 |
-
corpus, [MockEngine()],
|
| 290 |
-
show_progress=False,
|
| 291 |
-
partial_dir=str(tmp_path),
|
| 292 |
-
)
|
| 293 |
-
assert len(save_calls) == len(corpus), (
|
| 294 |
-
f"_save_partial_line appelée {len(save_calls)} fois, attendu {len(corpus)}"
|
| 295 |
-
)
|
| 296 |
-
|
| 297 |
-
def test_partial_file_deleted_after_success(self, tmp_corpus, tmp_path):
|
| 298 |
-
"""Le fichier .partial.json doit être supprimé après un benchmark réussi."""
|
| 299 |
-
from picarones.evaluation.corpus import load_corpus_from_directory
|
| 300 |
-
from picarones.measurements.runner import run_benchmark
|
| 301 |
-
from picarones.adapters.legacy_engines.base import BaseOCREngine
|
| 302 |
-
|
| 303 |
-
class MockEngine(BaseOCREngine):
|
| 304 |
-
@property
|
| 305 |
-
def name(self): return "mock"
|
| 306 |
-
def version(self): return "0.1"
|
| 307 |
-
def _run_ocr(self, image_path): return "texte"
|
| 308 |
-
|
| 309 |
-
corpus = load_corpus_from_directory(str(tmp_corpus))
|
| 310 |
-
run_benchmark(
|
| 311 |
-
corpus, [MockEngine()],
|
| 312 |
-
show_progress=False,
|
| 313 |
-
partial_dir=str(tmp_path),
|
| 314 |
-
)
|
| 315 |
-
partial_files = list(tmp_path.glob("*.partial.json"))
|
| 316 |
-
assert len(partial_files) == 0, f"Fichier(s) partiel(s) non supprimé(s) : {partial_files}"
|
| 317 |
-
|
| 318 |
-
def test_partial_load_skips_already_done_docs(self, tmp_corpus, tmp_path):
|
| 319 |
-
"""La reprise depuis un fichier partiel doit sauter les documents déjà traités."""
|
| 320 |
-
from picarones.evaluation.corpus import load_corpus_from_directory
|
| 321 |
-
from picarones.measurements.runner import _load_partial, _partial_path
|
| 322 |
-
|
| 323 |
-
corpus = load_corpus_from_directory(str(tmp_corpus))
|
| 324 |
-
corpus_name = corpus.name
|
| 325 |
-
engine_name = "mock_engine"
|
| 326 |
-
|
| 327 |
-
# Créer un fichier partiel simulant 1 document déjà traité
|
| 328 |
-
path = _partial_path(corpus_name, engine_name, tmp_path)
|
| 329 |
-
doc = corpus.documents[0]
|
| 330 |
-
partial_line = {
|
| 331 |
-
"doc_id": doc.doc_id,
|
| 332 |
-
"image_path": str(doc.image_path),
|
| 333 |
-
"ground_truth": doc.ground_truth,
|
| 334 |
-
"hypothesis": "déjà traité",
|
| 335 |
-
"metrics": {"cer": 0.1, "cer_nfc": 0.1, "cer_caseless": 0.1,
|
| 336 |
-
"wer": 0.1, "wer_normalized": 0.1, "mer": 0.1, "wil": 0.1,
|
| 337 |
-
"reference_length": 10, "hypothesis_length": 10},
|
| 338 |
-
"duration_seconds": 0.5,
|
| 339 |
-
}
|
| 340 |
-
path.write_text(json.dumps(partial_line) + "\n", encoding="utf-8")
|
| 341 |
-
|
| 342 |
-
_, loaded = _load_partial(corpus_name, engine_name, tmp_path)
|
| 343 |
-
assert len(loaded) == 1
|
| 344 |
-
assert loaded[0].doc_id == doc.doc_id
|
| 345 |
-
assert loaded[0].hypothesis == "déjà traité"
|
| 346 |
-
|
| 347 |
-
def test_partial_load_returns_empty_for_missing_file(self, tmp_path):
|
| 348 |
-
"""Si aucun fichier partiel n'existe, la liste doit être vide."""
|
| 349 |
-
from picarones.measurements.runner import _load_partial
|
| 350 |
-
_, loaded = _load_partial("corpus_inexistant", "moteur_inexistant", tmp_path)
|
| 351 |
-
assert loaded == []
|
| 352 |
-
|
| 353 |
-
|
| 354 |
-
# ===========================================================================
|
| 355 |
-
# Part 2 — Exceptions non silencieuses dans le runner
|
| 356 |
-
# ===========================================================================
|
| 357 |
-
|
| 358 |
-
class TestRunnerSilentExceptions:
|
| 359 |
-
|
| 360 |
-
def test_confusion_failure_logs_warning(self, tmp_corpus, caplog):
|
| 361 |
-
"""Une erreur dans build_confusion_matrix doit être loguée, pas ignorée."""
|
| 362 |
-
import logging
|
| 363 |
-
from picarones.evaluation.corpus import load_corpus_from_directory
|
| 364 |
-
from picarones.measurements.runner import run_benchmark
|
| 365 |
-
from picarones.adapters.legacy_engines.base import BaseOCREngine
|
| 366 |
-
|
| 367 |
-
class MockEngine(BaseOCREngine):
|
| 368 |
-
@property
|
| 369 |
-
def name(self): return "mock"
|
| 370 |
-
def version(self): return "0.1"
|
| 371 |
-
def _run_ocr(self, image_path): return "texte ocr"
|
| 372 |
-
|
| 373 |
-
corpus = load_corpus_from_directory(str(tmp_corpus))
|
| 374 |
-
with patch(
|
| 375 |
-
"picarones.measurements.runner._compute_document_result",
|
| 376 |
-
wraps=__import__("picarones.measurements.runner", fromlist=["_compute_document_result"])._compute_document_result,
|
| 377 |
-
):
|
| 378 |
-
with patch("picarones.evaluation.metrics.confusion.build_confusion_matrix", side_effect=RuntimeError("crash test")):
|
| 379 |
-
with caplog.at_level(logging.WARNING):
|
| 380 |
-
result = run_benchmark(corpus, [MockEngine()], show_progress=False)
|
| 381 |
-
|
| 382 |
-
assert result is not None, "Le benchmark ne doit pas planter si la confusion matrix échoue"
|
| 383 |
-
# La clé est que le benchmark se termine normalement
|
| 384 |
-
assert len(result.engine_reports) == 1
|
| 385 |
-
|
| 386 |
-
def test_progress_callback_failure_logs_warning(self, tmp_corpus, caplog):
|
| 387 |
-
"""Une exception dans le progress_callback doit être loguée, pas propagée."""
|
| 388 |
-
import logging
|
| 389 |
-
from picarones.evaluation.corpus import load_corpus_from_directory
|
| 390 |
-
from picarones.measurements.runner import run_benchmark
|
| 391 |
-
from picarones.adapters.legacy_engines.base import BaseOCREngine
|
| 392 |
-
|
| 393 |
-
class MockEngine(BaseOCREngine):
|
| 394 |
-
@property
|
| 395 |
-
def name(self): return "mock"
|
| 396 |
-
def version(self): return "0.1"
|
| 397 |
-
def _run_ocr(self, image_path): return "texte"
|
| 398 |
-
|
| 399 |
-
def bad_callback(engine_name, doc_idx, doc_id):
|
| 400 |
-
raise ValueError("callback crash")
|
| 401 |
-
|
| 402 |
-
corpus = load_corpus_from_directory(str(tmp_corpus))
|
| 403 |
-
with caplog.at_level(logging.WARNING):
|
| 404 |
-
result = run_benchmark(
|
| 405 |
-
corpus, [MockEngine()],
|
| 406 |
-
show_progress=False,
|
| 407 |
-
progress_callback=bad_callback,
|
| 408 |
-
)
|
| 409 |
-
assert result is not None
|
| 410 |
-
assert any("progress_callback" in r.message for r in caplog.records), (
|
| 411 |
-
"L'exception du callback doit être loguée en WARNING"
|
| 412 |
-
)
|
| 413 |
-
|
| 414 |
-
def test_aggregate_helpers_log_on_failure(self, caplog):
|
| 415 |
-
"""Les helpers _aggregate_* doivent logger en WARNING et retourner None."""
|
| 416 |
-
import logging
|
| 417 |
-
from picarones.measurements.runner import _aggregate_confusion
|
| 418 |
-
|
| 419 |
-
# Créer un doc_result avec des données de confusion corrompues
|
| 420 |
-
from picarones.evaluation.benchmark_result import DocumentResult
|
| 421 |
-
from picarones.evaluation.metric_result import MetricsResult
|
| 422 |
-
bad_dr = DocumentResult(
|
| 423 |
-
doc_id="x", image_path="x.png", ground_truth="gt", hypothesis="hyp",
|
| 424 |
-
metrics=MetricsResult(cer=0.1, cer_nfc=0.1, cer_caseless=0.1,
|
| 425 |
-
wer=0.1, wer_normalized=0.1, mer=0.1, wil=0.1,
|
| 426 |
-
reference_length=2, hypothesis_length=2),
|
| 427 |
-
duration_seconds=0.1,
|
| 428 |
-
confusion_matrix={"invalid_key": "corrupt_data"}, # va planter ConfusionMatrix(**...)
|
| 429 |
-
)
|
| 430 |
-
with caplog.at_level(logging.WARNING):
|
| 431 |
-
result = _aggregate_confusion([bad_dr])
|
| 432 |
-
assert result is None
|
| 433 |
-
assert any("aggregate_confusion" in r.message for r in caplog.records)
|
| 434 |
-
|
| 435 |
-
|
| 436 |
-
# ===========================================================================
|
| 437 |
-
# Part 4 — Validation du test de Wilcoxon contre valeurs de référence
|
| 438 |
-
# ===========================================================================
|
| 439 |
-
|
| 440 |
-
class TestWilcoxonValidation:
|
| 441 |
-
|
| 442 |
-
def test_identical_sequences_not_significant(self):
|
| 443 |
-
"""Séquences identiques → pas de différence, p = 1.0, significant = False."""
|
| 444 |
-
from picarones.evaluation.statistics import wilcoxon_test
|
| 445 |
-
a = [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0]
|
| 446 |
-
r = wilcoxon_test(a, a)
|
| 447 |
-
assert r["significant"] is False
|
| 448 |
-
assert r["p_value"] == 1.0
|
| 449 |
-
assert r["n_pairs"] == 0
|
| 450 |
-
|
| 451 |
-
def test_all_positive_diffs_w_minus_is_zero(self):
|
| 452 |
-
"""Si toutes les différences a−b sont positives : W⁻ = 0, W⁺ = n(n+1)/2."""
|
| 453 |
-
from picarones.evaluation.statistics import wilcoxon_test
|
| 454 |
-
n = 10
|
| 455 |
-
a = [float(i) for i in range(1, n + 1)]
|
| 456 |
-
b = [0.0] * n
|
| 457 |
-
r = wilcoxon_test(a, b)
|
| 458 |
-
expected_total = n * (n + 1) / 2.0
|
| 459 |
-
assert math.isclose(r["W_minus"], 0.0, abs_tol=1e-9)
|
| 460 |
-
assert math.isclose(r["W_plus"], expected_total, abs_tol=1e-9)
|
| 461 |
-
|
| 462 |
-
def test_w_plus_w_minus_sum_invariant(self):
|
| 463 |
-
"""W⁺ + W⁻ doit toujours être égal à n(n+1)/2 (n = nombre de paires non nulles)."""
|
| 464 |
-
from picarones.evaluation.statistics import wilcoxon_test
|
| 465 |
-
a = [0.10, 0.25, 0.05, 0.40, 0.30, 0.15, 0.20, 0.35, 0.08, 0.18]
|
| 466 |
-
b = [0.12, 0.20, 0.08, 0.35, 0.28, 0.18, 0.15, 0.40, 0.10, 0.20]
|
| 467 |
-
r = wilcoxon_test(a, b)
|
| 468 |
-
n = r["n_pairs"]
|
| 469 |
-
expected = n * (n + 1) / 2.0
|
| 470 |
-
actual = r["W_plus"] + r["W_minus"]
|
| 471 |
-
assert math.isclose(actual, expected, abs_tol=1e-6), (
|
| 472 |
-
f"W⁺+W⁻ = {actual} ≠ n(n+1)/2 = {expected}"
|
| 473 |
-
)
|
| 474 |
-
|
| 475 |
-
def test_clearly_different_sequences_significant(self):
|
| 476 |
-
"""Deux séquences très différentes (n=15) doivent donner p < 0.05."""
|
| 477 |
-
from picarones.evaluation.statistics import wilcoxon_test
|
| 478 |
-
a = [0.05] * 15 # moteur A très performant
|
| 479 |
-
b = [0.60] * 15 # moteur B peu performant — toutes diff = −0.55
|
| 480 |
-
# Diffs a−b = −0.55 pour tous → W⁺ = 0 → devrait être significatif
|
| 481 |
-
r = wilcoxon_test(a, b)
|
| 482 |
-
assert r["significant"] is True, f"p = {r['p_value']} — devrait être significatif"
|
| 483 |
-
assert r["p_value"] < 0.05
|
| 484 |
-
|
| 485 |
-
def test_large_n_normal_approximation_reasonable(self):
|
| 486 |
-
"""Pour n = 20, l'approximation normale doit donner une p-value dans [0, 1]."""
|
| 487 |
-
from picarones.evaluation.statistics import wilcoxon_test
|
| 488 |
-
import random
|
| 489 |
-
rng = random.Random(42)
|
| 490 |
-
a = [rng.uniform(0.1, 0.5) for _ in range(20)]
|
| 491 |
-
b = [x + rng.uniform(0.0, 0.1) for x in a]
|
| 492 |
-
r = wilcoxon_test(a, b)
|
| 493 |
-
assert 0.0 <= r["p_value"] <= 1.0
|
| 494 |
-
assert r["n_pairs"] <= 20
|
| 495 |
-
|
| 496 |
-
def test_small_n_returns_conservative_p(self):
|
| 497 |
-
"""Pour n < 10, la p-value doit être 0.04 (significatif) ou 0.20 (non sign.)."""
|
| 498 |
-
from picarones.evaluation.statistics import wilcoxon_test, _SCIPY_AVAILABLE
|
| 499 |
-
if _SCIPY_AVAILABLE:
|
| 500 |
-
pytest.skip("scipy disponible — la table exacte n'est pas utilisée")
|
| 501 |
-
a = [0.1, 0.2, 0.3]
|
| 502 |
-
b = [0.5, 0.6, 0.7] # toutes diff = −0.4 → W = 0 → significatif
|
| 503 |
-
r = wilcoxon_test(a, b)
|
| 504 |
-
# Avec n=3, W=0 ≤ _W_CRITICAL[3]=0 → p=0.04
|
| 505 |
-
assert r["p_value"] in (0.04, 0.20)
|
| 506 |
-
|
| 507 |
-
def test_result_keys_complete(self):
|
| 508 |
-
"""Le dict retourné doit contenir toutes les clés documentées."""
|
| 509 |
-
from picarones.evaluation.statistics import wilcoxon_test
|
| 510 |
-
r = wilcoxon_test([0.1, 0.3, 0.2, 0.4, 0.15, 0.35, 0.25, 0.5, 0.45, 0.05],
|
| 511 |
-
[0.2, 0.2, 0.3, 0.3, 0.25, 0.25, 0.35, 0.35, 0.40, 0.15])
|
| 512 |
-
for key in ("statistic", "p_value", "significant", "interpretation", "n_pairs", "W_plus", "W_minus"):
|
| 513 |
-
assert key in r, f"Clé manquante dans le résultat Wilcoxon : {key}"
|
| 514 |
-
|
| 515 |
-
|
| 516 |
-
# ===========================================================================
|
| 517 |
-
# Part 4 — Cohérence scipy / implémentation native
|
| 518 |
-
# ===========================================================================
|
| 519 |
-
|
| 520 |
-
class TestWilcoxonScipyIntegration:
|
| 521 |
-
|
| 522 |
-
def test_scipy_available_flag_is_bool(self):
|
| 523 |
-
"""_SCIPY_AVAILABLE doit être un booléen."""
|
| 524 |
-
from picarones.evaluation.statistics import _SCIPY_AVAILABLE
|
| 525 |
-
assert isinstance(_SCIPY_AVAILABLE, bool)
|
| 526 |
-
|
| 527 |
-
def test_scipy_and_native_agree_on_significance(self):
|
| 528 |
-
"""Scipy et l'implémentation native doivent s'accorder sur la significativité."""
|
| 529 |
-
from picarones.evaluation.statistics import wilcoxon_test, _SCIPY_AVAILABLE
|
| 530 |
-
if not _SCIPY_AVAILABLE:
|
| 531 |
-
pytest.skip("scipy non disponible")
|
| 532 |
-
|
| 533 |
-
# Cas avec différences claires et n suffisant pour que les deux méthodes convergent
|
| 534 |
-
a = [0.05, 0.08, 0.06, 0.07, 0.04, 0.09, 0.05, 0.07, 0.06, 0.08,
|
| 535 |
-
0.05, 0.07, 0.06, 0.08, 0.04]
|
| 536 |
-
b = [0.30, 0.35, 0.28, 0.32, 0.31, 0.29, 0.34, 0.33, 0.30, 0.31,
|
| 537 |
-
0.29, 0.32, 0.33, 0.30, 0.31]
|
| 538 |
-
|
| 539 |
-
r = wilcoxon_test(a, b)
|
| 540 |
-
# Avec scipy, résultat doit être significatif
|
| 541 |
-
assert r["significant"] is True
|
| 542 |
-
|
| 543 |
-
def test_scipy_p_value_in_valid_range(self):
|
| 544 |
-
"""La p-value fournie par scipy doit être dans [0, 1]."""
|
| 545 |
-
from picarones.evaluation.statistics import wilcoxon_test, _SCIPY_AVAILABLE
|
| 546 |
-
if not _SCIPY_AVAILABLE:
|
| 547 |
-
pytest.skip("scipy non disponible")
|
| 548 |
-
|
| 549 |
-
a = [0.1 + i * 0.02 for i in range(12)]
|
| 550 |
-
b = [0.1 + i * 0.01 for i in range(12)]
|
| 551 |
-
r = wilcoxon_test(a, b)
|
| 552 |
-
assert 0.0 <= r["p_value"] <= 1.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@@ -247,62 +247,3 @@ class TestPipelineEmptyLLMResponse:
|
|
| 247 |
if rec.levelno >= logging.WARNING
|
| 248 |
)
|
| 249 |
|
| 250 |
-
|
| 251 |
-
# ---------------------------------------------------------------------------
|
| 252 |
-
# Bug 3 — Cohérence runner/rapport : empty hypothesis → CER 1.0 dans DocumentResult
|
| 253 |
-
# ---------------------------------------------------------------------------
|
| 254 |
-
|
| 255 |
-
class TestRunnerDocumentResultCohérence:
|
| 256 |
-
"""Le DocumentResult doit stocker CER=1.0 pour une hypothèse vide."""
|
| 257 |
-
|
| 258 |
-
def test_empty_hypothesis_stored_as_cer_one(self):
|
| 259 |
-
"""_compute_document_result avec text="" → metrics.cer = 1.0."""
|
| 260 |
-
from picarones.measurements.runner import _compute_document_result
|
| 261 |
-
from picarones.adapters.legacy_engines.base import EngineResult
|
| 262 |
-
|
| 263 |
-
ocr_result = EngineResult(
|
| 264 |
-
engine_name="TestEngine",
|
| 265 |
-
image_path="fake.png",
|
| 266 |
-
text="", # ← sortie vide
|
| 267 |
-
duration_seconds=1.0,
|
| 268 |
-
error=None, # ← pas d'erreur technique
|
| 269 |
-
)
|
| 270 |
-
|
| 271 |
-
doc_result = _compute_document_result(
|
| 272 |
-
doc_id="doc1",
|
| 273 |
-
image_path="fake.png",
|
| 274 |
-
ground_truth="Bonjour le monde",
|
| 275 |
-
ocr_result=ocr_result,
|
| 276 |
-
char_exclude=None,
|
| 277 |
-
)
|
| 278 |
-
|
| 279 |
-
assert doc_result.metrics.cer == pytest.approx(1.0), (
|
| 280 |
-
f"CER attendu 1.0 pour hypothèse vide, obtenu {doc_result.metrics.cer}"
|
| 281 |
-
)
|
| 282 |
-
assert doc_result.metrics.error is None, (
|
| 283 |
-
"L'erreur ne devrait pas être renseignée — c'est une hypothèse vide, pas une erreur technique"
|
| 284 |
-
)
|
| 285 |
-
|
| 286 |
-
def test_engine_error_also_gives_cer_one(self):
|
| 287 |
-
"""EngineResult avec error → metrics.cer = 1.0 (comportement existant)."""
|
| 288 |
-
from picarones.measurements.runner import _compute_document_result
|
| 289 |
-
from picarones.adapters.legacy_engines.base import EngineResult
|
| 290 |
-
|
| 291 |
-
ocr_result = EngineResult(
|
| 292 |
-
engine_name="TestEngine",
|
| 293 |
-
image_path="fake.png",
|
| 294 |
-
text="",
|
| 295 |
-
duration_seconds=0.0,
|
| 296 |
-
error="Moteur en erreur",
|
| 297 |
-
)
|
| 298 |
-
|
| 299 |
-
doc_result = _compute_document_result(
|
| 300 |
-
doc_id="doc1",
|
| 301 |
-
image_path="fake.png",
|
| 302 |
-
ground_truth="Bonjour le monde",
|
| 303 |
-
ocr_result=ocr_result,
|
| 304 |
-
char_exclude=None,
|
| 305 |
-
)
|
| 306 |
-
|
| 307 |
-
assert doc_result.metrics.cer == pytest.approx(1.0)
|
| 308 |
-
assert doc_result.metrics.error is not None
|
|
|
|
| 247 |
if rec.levelno >= logging.WARNING
|
| 248 |
)
|
| 249 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@@ -12,10 +12,7 @@ Couverture :
|
|
| 12 |
|
| 13 |
from __future__ import annotations
|
| 14 |
|
| 15 |
-
import json
|
| 16 |
-
from pathlib import Path
|
| 17 |
|
| 18 |
-
from picarones.evaluation.corpus import Corpus, Document
|
| 19 |
from picarones.measurements.narrative import (
|
| 20 |
DetectorRegistry,
|
| 21 |
Fact,
|
|
@@ -23,219 +20,6 @@ from picarones.measurements.narrative import (
|
|
| 23 |
FactType,
|
| 24 |
detect_all,
|
| 25 |
)
|
| 26 |
-
from picarones.measurements.runner import (
|
| 27 |
-
_aggregate_hallucination,
|
| 28 |
-
_aggregate_line_metrics,
|
| 29 |
-
_compute_document_result,
|
| 30 |
-
run_benchmark,
|
| 31 |
-
)
|
| 32 |
-
from picarones.adapters.legacy_engines.base import BaseOCREngine, EngineResult
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
class _FakeEngine(BaseOCREngine):
|
| 36 |
-
"""Moteur factice — renvoie un texte configurable, utile en test."""
|
| 37 |
-
|
| 38 |
-
def __init__(self, output_text: str, name: str = "fake", config=None):
|
| 39 |
-
super().__init__(config)
|
| 40 |
-
self._output = output_text
|
| 41 |
-
self._display_name = name
|
| 42 |
-
|
| 43 |
-
@property
|
| 44 |
-
def name(self) -> str:
|
| 45 |
-
return self._display_name
|
| 46 |
-
|
| 47 |
-
def version(self) -> str:
|
| 48 |
-
return "test"
|
| 49 |
-
|
| 50 |
-
def _run_ocr(self, image_path):
|
| 51 |
-
return self._output, None
|
| 52 |
-
|
| 53 |
-
def run(self, image_path) -> EngineResult:
|
| 54 |
-
return EngineResult(
|
| 55 |
-
engine_name=self.name,
|
| 56 |
-
image_path=str(image_path),
|
| 57 |
-
text=self._output,
|
| 58 |
-
duration_seconds=0.01,
|
| 59 |
-
)
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
# ---------------------------------------------------------------------------
|
| 63 |
-
# 1. Câblage line_metrics et hallucination par document
|
| 64 |
-
# ---------------------------------------------------------------------------
|
| 65 |
-
|
| 66 |
-
class TestDocumentResultWiring:
|
| 67 |
-
"""Vérifie que ``_compute_document_result`` peuple les nouveaux champs."""
|
| 68 |
-
|
| 69 |
-
def test_line_metrics_populated_on_success(self, tmp_path: Path):
|
| 70 |
-
image = tmp_path / "doc.png"
|
| 71 |
-
image.write_bytes(b"\x89PNG\r\n\x1a\n") # stub — image_quality loggera un warning
|
| 72 |
-
|
| 73 |
-
ocr = EngineResult(
|
| 74 |
-
engine_name="fake",
|
| 75 |
-
image_path=str(image),
|
| 76 |
-
text="ligne une\nligne deux\nligne trois",
|
| 77 |
-
duration_seconds=0.1,
|
| 78 |
-
)
|
| 79 |
-
gt = "ligne une\nligne deux\nligne trois"
|
| 80 |
-
|
| 81 |
-
result = _compute_document_result(
|
| 82 |
-
doc_id="doc1",
|
| 83 |
-
image_path=str(image),
|
| 84 |
-
ground_truth=gt,
|
| 85 |
-
ocr_result=ocr,
|
| 86 |
-
char_exclude=None,
|
| 87 |
-
)
|
| 88 |
-
|
| 89 |
-
assert result.line_metrics is not None, "line_metrics doit être peuplé"
|
| 90 |
-
assert "percentiles" in result.line_metrics
|
| 91 |
-
assert "gini" in result.line_metrics
|
| 92 |
-
assert result.line_metrics["line_count"] == 3
|
| 93 |
-
|
| 94 |
-
def test_hallucination_metrics_populated_on_success(self, tmp_path: Path):
|
| 95 |
-
image = tmp_path / "doc.png"
|
| 96 |
-
image.write_bytes(b"")
|
| 97 |
-
|
| 98 |
-
gt = "le chat est sur le tapis rouge et dort paisiblement"
|
| 99 |
-
hyp = "le chat mange des bananes spatiales en orbite lunaire"
|
| 100 |
-
|
| 101 |
-
ocr = EngineResult(
|
| 102 |
-
engine_name="fake",
|
| 103 |
-
image_path=str(image),
|
| 104 |
-
text=hyp,
|
| 105 |
-
duration_seconds=0.1,
|
| 106 |
-
)
|
| 107 |
-
|
| 108 |
-
result = _compute_document_result(
|
| 109 |
-
doc_id="doc1",
|
| 110 |
-
image_path=str(image),
|
| 111 |
-
ground_truth=gt,
|
| 112 |
-
ocr_result=ocr,
|
| 113 |
-
char_exclude=None,
|
| 114 |
-
)
|
| 115 |
-
|
| 116 |
-
assert result.hallucination_metrics is not None
|
| 117 |
-
assert "anchor_score" in result.hallucination_metrics
|
| 118 |
-
assert "length_ratio" in result.hallucination_metrics
|
| 119 |
-
assert "is_hallucinating" in result.hallucination_metrics
|
| 120 |
-
|
| 121 |
-
def test_new_fields_empty_on_engine_failure(self, tmp_path: Path):
|
| 122 |
-
"""Si l'OCR échoue (success=False), pas de calcul line_metrics/hallucination."""
|
| 123 |
-
image = tmp_path / "doc.png"
|
| 124 |
-
image.write_bytes(b"")
|
| 125 |
-
|
| 126 |
-
ocr = EngineResult(
|
| 127 |
-
engine_name="fake",
|
| 128 |
-
image_path=str(image),
|
| 129 |
-
text="",
|
| 130 |
-
duration_seconds=0.1,
|
| 131 |
-
error="simulated failure",
|
| 132 |
-
)
|
| 133 |
-
result = _compute_document_result(
|
| 134 |
-
doc_id="doc1",
|
| 135 |
-
image_path=str(image),
|
| 136 |
-
ground_truth="ground truth text",
|
| 137 |
-
ocr_result=ocr,
|
| 138 |
-
char_exclude=None,
|
| 139 |
-
)
|
| 140 |
-
|
| 141 |
-
assert result.line_metrics is None
|
| 142 |
-
assert result.hallucination_metrics is None
|
| 143 |
-
|
| 144 |
-
|
| 145 |
-
# ---------------------------------------------------------------------------
|
| 146 |
-
# 2. Agrégation au niveau EngineReport
|
| 147 |
-
# ---------------------------------------------------------------------------
|
| 148 |
-
|
| 149 |
-
class TestAggregationWiring:
|
| 150 |
-
"""Vérifie que le benchmark complet produit les agrégations."""
|
| 151 |
-
|
| 152 |
-
def test_aggregate_line_metrics_helper_with_empty_list(self):
|
| 153 |
-
assert _aggregate_line_metrics([]) is None
|
| 154 |
-
|
| 155 |
-
def test_aggregate_hallucination_helper_with_empty_list(self):
|
| 156 |
-
assert _aggregate_hallucination([]) is None
|
| 157 |
-
|
| 158 |
-
def test_benchmark_end_to_end_produces_aggregations(self, tmp_path: Path):
|
| 159 |
-
img = tmp_path / "test.png"
|
| 160 |
-
img.write_bytes(b"")
|
| 161 |
-
|
| 162 |
-
corpus = Corpus(
|
| 163 |
-
name="test",
|
| 164 |
-
documents=[
|
| 165 |
-
Document(
|
| 166 |
-
doc_id="d1",
|
| 167 |
-
image_path=img,
|
| 168 |
-
ground_truth="bonjour le monde\nligne deux\nfin",
|
| 169 |
-
),
|
| 170 |
-
Document(
|
| 171 |
-
doc_id="d2",
|
| 172 |
-
image_path=img,
|
| 173 |
-
ground_truth="autre document test\navec deux lignes",
|
| 174 |
-
),
|
| 175 |
-
],
|
| 176 |
-
source_path=str(tmp_path),
|
| 177 |
-
)
|
| 178 |
-
|
| 179 |
-
engine = _FakeEngine(
|
| 180 |
-
output_text="bonjour le monde\nligne deux\nfin",
|
| 181 |
-
name="fake_engine",
|
| 182 |
-
)
|
| 183 |
-
|
| 184 |
-
result = run_benchmark(
|
| 185 |
-
corpus=corpus,
|
| 186 |
-
engines=[engine],
|
| 187 |
-
show_progress=False,
|
| 188 |
-
max_workers=1,
|
| 189 |
-
partial_dir=str(tmp_path / "partial"),
|
| 190 |
-
)
|
| 191 |
-
|
| 192 |
-
assert len(result.engine_reports) == 1
|
| 193 |
-
report = result.engine_reports[0]
|
| 194 |
-
|
| 195 |
-
assert report.aggregated_line_metrics is not None, (
|
| 196 |
-
"aggregated_line_metrics doit être peuplé après benchmark"
|
| 197 |
-
)
|
| 198 |
-
assert "gini_mean" in report.aggregated_line_metrics
|
| 199 |
-
assert "document_count" in report.aggregated_line_metrics
|
| 200 |
-
assert report.aggregated_line_metrics["document_count"] == 2
|
| 201 |
-
|
| 202 |
-
assert report.aggregated_hallucination is not None, (
|
| 203 |
-
"aggregated_hallucination doit être peuplé après benchmark"
|
| 204 |
-
)
|
| 205 |
-
assert "anchor_score_mean" in report.aggregated_hallucination
|
| 206 |
-
assert report.aggregated_hallucination["document_count"] == 2
|
| 207 |
-
|
| 208 |
-
def test_json_export_includes_new_aggregations(self, tmp_path: Path):
|
| 209 |
-
img = tmp_path / "t.png"
|
| 210 |
-
img.write_bytes(b"")
|
| 211 |
-
corpus = Corpus(
|
| 212 |
-
name="test",
|
| 213 |
-
documents=[
|
| 214 |
-
Document(doc_id="d1", image_path=img, ground_truth="un\ndeux"),
|
| 215 |
-
],
|
| 216 |
-
source_path=str(tmp_path),
|
| 217 |
-
)
|
| 218 |
-
engine = _FakeEngine(output_text="un\ndeux", name="fake")
|
| 219 |
-
|
| 220 |
-
out = tmp_path / "bench.json"
|
| 221 |
-
run_benchmark(
|
| 222 |
-
corpus=corpus,
|
| 223 |
-
engines=[engine],
|
| 224 |
-
output_json=out,
|
| 225 |
-
show_progress=False,
|
| 226 |
-
max_workers=1,
|
| 227 |
-
partial_dir=str(tmp_path / "partial"),
|
| 228 |
-
)
|
| 229 |
-
|
| 230 |
-
data = json.loads(out.read_text(encoding="utf-8"))
|
| 231 |
-
report = data["engine_reports"][0]
|
| 232 |
-
assert "aggregated_line_metrics" in report
|
| 233 |
-
assert "aggregated_hallucination" in report
|
| 234 |
-
|
| 235 |
-
|
| 236 |
-
# ---------------------------------------------------------------------------
|
| 237 |
-
# 3. Modèle Fact et DetectorRegistry
|
| 238 |
-
# ---------------------------------------------------------------------------
|
| 239 |
|
| 240 |
class TestFactModel:
|
| 241 |
def test_fact_is_serializable(self):
|
|
|
|
| 12 |
|
| 13 |
from __future__ import annotations
|
| 14 |
|
|
|
|
|
|
|
| 15 |
|
|
|
|
| 16 |
from picarones.measurements.narrative import (
|
| 17 |
DetectorRegistry,
|
| 18 |
Fact,
|
|
|
|
| 20 |
FactType,
|
| 21 |
detect_all,
|
| 22 |
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
class TestFactModel:
|
| 25 |
def test_fact_is_serializable(self):
|
|
@@ -1,311 +0,0 @@
|
|
| 1 |
-
"""Tests Sprint 40 — backend extracteur NER + câblage runner.
|
| 2 |
-
|
| 3 |
-
Couvre :
|
| 4 |
-
|
| 5 |
-
1. ``SpacyEntityExtractor`` lazy-importe spaCy ; sans spaCy installé,
|
| 6 |
-
l'extracteur retourne ``[]`` avec un warning explicite.
|
| 7 |
-
2. ``is_spacy_available`` reflète l'état réel.
|
| 8 |
-
3. ``get_extractor(profile)`` accepte une clé de profil ou un nom de
|
| 9 |
-
modèle direct.
|
| 10 |
-
4. ``DocumentResult.ner_metrics`` est sérialisé via ``as_dict``
|
| 11 |
-
uniquement quand renseigné, et libéré par ``compact()``.
|
| 12 |
-
5. ``EngineReport.aggregated_ner`` apparaît dans ``as_dict`` quand
|
| 13 |
-
renseigné (rétrocompat sinon).
|
| 14 |
-
6. Câblage runner avec un extracteur **mock** (callable injecté) :
|
| 15 |
-
- ``ner_metrics`` est attaché aux DR dont le doc a une GT entités ;
|
| 16 |
-
- ``aggregated_ner`` est calculé sur l'EngineReport ;
|
| 17 |
-
- les docs sans GT entités sont ignorés.
|
| 18 |
-
7. Sans extracteur fourni au runner, rien n'est calculé (rétrocompat).
|
| 19 |
-
8. Un extracteur qui lève sur un doc spécifique → warning, autres docs
|
| 20 |
-
inchangés.
|
| 21 |
-
"""
|
| 22 |
-
|
| 23 |
-
from __future__ import annotations
|
| 24 |
-
|
| 25 |
-
from pathlib import Path
|
| 26 |
-
|
| 27 |
-
import pytest
|
| 28 |
-
|
| 29 |
-
from picarones.domain.artifacts import ArtifactType
|
| 30 |
-
from picarones.evaluation.corpus import Corpus, Document, EntitiesGT, TextGT
|
| 31 |
-
from picarones.evaluation.metrics.ner_backends import (
|
| 32 |
-
SPACY_PROFILES,
|
| 33 |
-
SpacyEntityExtractor,
|
| 34 |
-
get_extractor,
|
| 35 |
-
is_spacy_available,
|
| 36 |
-
)
|
| 37 |
-
from picarones.evaluation.benchmark_result import DocumentResult, EngineReport
|
| 38 |
-
from picarones.measurements.runner import _aggregate_ner, _attach_ner_metrics
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 42 |
-
# 1-3. Backend SpacyEntityExtractor
|
| 43 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 44 |
-
|
| 45 |
-
|
| 46 |
-
class TestSpacyExtractor:
|
| 47 |
-
def test_falls_back_silently_without_spacy(
|
| 48 |
-
self, caplog: pytest.LogCaptureFixture
|
| 49 |
-
) -> None:
|
| 50 |
-
"""Sans spaCy installé, l'extracteur retourne [] avec un warning
|
| 51 |
-
explicite et ne lève pas."""
|
| 52 |
-
ext = SpacyEntityExtractor("fr_core_news_sm")
|
| 53 |
-
with caplog.at_level("WARNING", logger="picarones.evaluation.metrics.ner_backends"):
|
| 54 |
-
result = ext("Marie de Bourgogne en 1477.")
|
| 55 |
-
# Sans spaCy, on a toujours [] et un warning
|
| 56 |
-
if not is_spacy_available():
|
| 57 |
-
assert result == []
|
| 58 |
-
assert any(
|
| 59 |
-
"spaCy" in rec.message or "spacy" in rec.message
|
| 60 |
-
for rec in caplog.records
|
| 61 |
-
)
|
| 62 |
-
assert ext.available is False
|
| 63 |
-
|
| 64 |
-
def test_empty_text_returns_empty(self) -> None:
|
| 65 |
-
ext = SpacyEntityExtractor()
|
| 66 |
-
assert ext("") == []
|
| 67 |
-
|
| 68 |
-
def test_idempotent_load(self) -> None:
|
| 69 |
-
"""L'appel répété ne re-tente pas le chargement."""
|
| 70 |
-
ext = SpacyEntityExtractor("inexistant_model_xyz")
|
| 71 |
-
ext("test") # premier appel : tentative de chargement
|
| 72 |
-
ext("test") # deuxième : pas de re-tentative
|
| 73 |
-
assert ext._loaded is True
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
class TestProfilesAndFactory:
|
| 77 |
-
def test_known_profiles_listed(self) -> None:
|
| 78 |
-
for key in ("fr", "en", "multilingual"):
|
| 79 |
-
assert key in SPACY_PROFILES
|
| 80 |
-
|
| 81 |
-
def test_get_extractor_with_known_profile(self) -> None:
|
| 82 |
-
ext = get_extractor("fr")
|
| 83 |
-
assert isinstance(ext, SpacyEntityExtractor)
|
| 84 |
-
assert ext.model_name == SPACY_PROFILES["fr"]
|
| 85 |
-
|
| 86 |
-
def test_get_extractor_with_direct_model_name(self) -> None:
|
| 87 |
-
ext = get_extractor("custom_model_name")
|
| 88 |
-
assert ext.model_name == "custom_model_name"
|
| 89 |
-
|
| 90 |
-
|
| 91 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 92 |
-
# 4-5. DocumentResult / EngineReport sérialisation
|
| 93 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 94 |
-
|
| 95 |
-
|
| 96 |
-
def _make_document_result(
|
| 97 |
-
doc_id: str = "d1",
|
| 98 |
-
hypothesis: str = "Marie de Bourgogne en 1477.",
|
| 99 |
-
ner_metrics: dict | None = None,
|
| 100 |
-
) -> DocumentResult:
|
| 101 |
-
from picarones.evaluation.metric_result import MetricsResult
|
| 102 |
-
|
| 103 |
-
return DocumentResult(
|
| 104 |
-
doc_id=doc_id,
|
| 105 |
-
image_path="/tmp/x.png",
|
| 106 |
-
ground_truth="Marie de Bourgogne en 1477.",
|
| 107 |
-
hypothesis=hypothesis,
|
| 108 |
-
metrics=MetricsResult(
|
| 109 |
-
cer=0.0, cer_nfc=0.0, cer_caseless=0.0,
|
| 110 |
-
wer=0.0, wer_normalized=0.0, mer=0.0, wil=0.0,
|
| 111 |
-
reference_length=27, hypothesis_length=27,
|
| 112 |
-
),
|
| 113 |
-
duration_seconds=0.1,
|
| 114 |
-
ner_metrics=ner_metrics,
|
| 115 |
-
)
|
| 116 |
-
|
| 117 |
-
|
| 118 |
-
class TestModelSerialization:
|
| 119 |
-
def test_ner_metrics_omitted_when_none(self) -> None:
|
| 120 |
-
dr = _make_document_result(ner_metrics=None)
|
| 121 |
-
d = dr.as_dict()
|
| 122 |
-
assert "ner_metrics" not in d
|
| 123 |
-
|
| 124 |
-
def test_ner_metrics_present_when_set(self) -> None:
|
| 125 |
-
dr = _make_document_result(ner_metrics={"global": {"f1": 0.8}})
|
| 126 |
-
d = dr.as_dict()
|
| 127 |
-
assert d["ner_metrics"] == {"global": {"f1": 0.8}}
|
| 128 |
-
|
| 129 |
-
def test_compact_clears_ner_metrics(self) -> None:
|
| 130 |
-
# Sprint A14-S1 — A.I.0 P0 : ``compact()`` est désormais no-op
|
| 131 |
-
# par défaut (cf. core/results.py). Le comportement
|
| 132 |
-
# "efface les analyses" est explicitement opt-in via
|
| 133 |
-
# ``drop_analyses=True``.
|
| 134 |
-
dr = _make_document_result(ner_metrics={"global": {"f1": 0.8}})
|
| 135 |
-
dr.compact(drop_analyses=True)
|
| 136 |
-
assert dr.ner_metrics is None
|
| 137 |
-
|
| 138 |
-
def test_compact_default_is_noop(self) -> None:
|
| 139 |
-
"""Sprint A14-S1 — défaut sans argument ne touche à rien."""
|
| 140 |
-
dr = _make_document_result(ner_metrics={"global": {"f1": 0.8}})
|
| 141 |
-
dr.compact()
|
| 142 |
-
assert dr.ner_metrics == {"global": {"f1": 0.8}}
|
| 143 |
-
|
| 144 |
-
def test_engine_report_aggregated_ner_omitted_when_none(self) -> None:
|
| 145 |
-
rep = EngineReport(
|
| 146 |
-
engine_name="t", engine_version="1", engine_config={},
|
| 147 |
-
document_results=[_make_document_result()],
|
| 148 |
-
)
|
| 149 |
-
d = rep.as_dict()
|
| 150 |
-
assert "aggregated_ner" not in d
|
| 151 |
-
|
| 152 |
-
def test_engine_report_aggregated_ner_included_when_set(self) -> None:
|
| 153 |
-
rep = EngineReport(
|
| 154 |
-
engine_name="t", engine_version="1", engine_config={},
|
| 155 |
-
document_results=[_make_document_result()],
|
| 156 |
-
aggregated_ner={"global": {"f1": 0.75}, "doc_count": 1},
|
| 157 |
-
)
|
| 158 |
-
d = rep.as_dict()
|
| 159 |
-
assert d["aggregated_ner"] == {"global": {"f1": 0.75}, "doc_count": 1}
|
| 160 |
-
|
| 161 |
-
|
| 162 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 163 |
-
# 6. Câblage runner avec extracteur mock
|
| 164 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 165 |
-
|
| 166 |
-
|
| 167 |
-
def _mock_extractor_factory(per_text: dict[str, list[dict]]) -> callable:
|
| 168 |
-
"""Construit un extracteur qui renvoie une réponse prédéfinie par
|
| 169 |
-
texte d'entrée — utile pour tester le câblage runner sans dépendance
|
| 170 |
-
NLP réelle."""
|
| 171 |
-
|
| 172 |
-
def _extract(text: str) -> list[dict]:
|
| 173 |
-
return per_text.get(text, [])
|
| 174 |
-
|
| 175 |
-
return _extract
|
| 176 |
-
|
| 177 |
-
|
| 178 |
-
def _corpus_with_entities(tmp_path: Path) -> Corpus:
|
| 179 |
-
"""Crée un corpus minimal avec deux documents, dont un seul porte
|
| 180 |
-
une GT entités."""
|
| 181 |
-
image1 = tmp_path / "doc1.png"
|
| 182 |
-
image2 = tmp_path / "doc2.png"
|
| 183 |
-
image1.write_bytes(b"fake")
|
| 184 |
-
image2.write_bytes(b"fake")
|
| 185 |
-
|
| 186 |
-
doc1 = Document(
|
| 187 |
-
image_path=image1,
|
| 188 |
-
ground_truth="Marie de Bourgogne en 1477.",
|
| 189 |
-
ground_truths={
|
| 190 |
-
ArtifactType.RAW_TEXT: TextGT(text="Marie de Bourgogne en 1477."),
|
| 191 |
-
ArtifactType.ENTITIES: EntitiesGT(entities=[
|
| 192 |
-
{"label": "PER", "start": 0, "end": 17, "text": "Marie de Bourgogne"},
|
| 193 |
-
{"label": "DATE", "start": 21, "end": 25, "text": "1477"},
|
| 194 |
-
]),
|
| 195 |
-
},
|
| 196 |
-
)
|
| 197 |
-
doc2 = Document(
|
| 198 |
-
image_path=image2,
|
| 199 |
-
ground_truth="Texte sans GT entités.",
|
| 200 |
-
)
|
| 201 |
-
return Corpus(name="test", documents=[doc1, doc2])
|
| 202 |
-
|
| 203 |
-
|
| 204 |
-
class TestRunnerWiring:
|
| 205 |
-
def test_attach_ner_only_for_docs_with_entities(self, tmp_path: Path) -> None:
|
| 206 |
-
corpus = _corpus_with_entities(tmp_path)
|
| 207 |
-
# Mock extractor : renvoie la même chose que la GT pour doc1 (parfait)
|
| 208 |
-
extractor = _mock_extractor_factory({
|
| 209 |
-
"Marie de Bourgogne en 1477.": [
|
| 210 |
-
{"label": "PER", "start": 0, "end": 17, "text": "Marie de Bourgogne"},
|
| 211 |
-
{"label": "DATE", "start": 21, "end": 25, "text": "1477"},
|
| 212 |
-
],
|
| 213 |
-
"Texte sans GT entités.": [], # pas appelé en réalité
|
| 214 |
-
})
|
| 215 |
-
dr1 = _make_document_result(
|
| 216 |
-
doc_id="doc1", hypothesis="Marie de Bourgogne en 1477.",
|
| 217 |
-
)
|
| 218 |
-
dr2 = _make_document_result(
|
| 219 |
-
doc_id="doc2", hypothesis="Texte sans GT entités.",
|
| 220 |
-
)
|
| 221 |
-
_attach_ner_metrics(corpus, [dr1, dr2], extractor)
|
| 222 |
-
|
| 223 |
-
# doc1 : a une GT entités → ner_metrics calculé
|
| 224 |
-
assert dr1.ner_metrics is not None
|
| 225 |
-
assert dr1.ner_metrics["global"]["f1"] == pytest.approx(1.0)
|
| 226 |
-
|
| 227 |
-
# doc2 : pas de GT entités → rien
|
| 228 |
-
assert dr2.ner_metrics is None
|
| 229 |
-
|
| 230 |
-
def test_aggregate_ner_combines_doc_metrics(self, tmp_path: Path) -> None:
|
| 231 |
-
# Deux documents avec ner_metrics fournis
|
| 232 |
-
dr1 = _make_document_result()
|
| 233 |
-
dr1.ner_metrics = {
|
| 234 |
-
"global": {"precision": 1.0, "recall": 0.5, "f1": 2/3, "support": 2},
|
| 235 |
-
"per_category": {
|
| 236 |
-
"PER": {"precision": 1.0, "recall": 0.5, "f1": 2/3, "support": 2},
|
| 237 |
-
},
|
| 238 |
-
"true_positives": 1, "false_positives": 0, "false_negatives": 1,
|
| 239 |
-
"hallucinated_entities": [], "missed_entities": [{"label": "PER"}],
|
| 240 |
-
"iou_threshold": 0.5,
|
| 241 |
-
}
|
| 242 |
-
dr2 = _make_document_result()
|
| 243 |
-
dr2.ner_metrics = {
|
| 244 |
-
"global": {"precision": 1.0, "recall": 1.0, "f1": 1.0, "support": 1},
|
| 245 |
-
"per_category": {
|
| 246 |
-
"LOC": {"precision": 1.0, "recall": 1.0, "f1": 1.0, "support": 1},
|
| 247 |
-
},
|
| 248 |
-
"true_positives": 1, "false_positives": 0, "false_negatives": 0,
|
| 249 |
-
"hallucinated_entities": [], "missed_entities": [],
|
| 250 |
-
"iou_threshold": 0.5,
|
| 251 |
-
}
|
| 252 |
-
agg = _aggregate_ner([dr1, dr2])
|
| 253 |
-
assert agg is not None
|
| 254 |
-
assert agg["doc_count"] == 2
|
| 255 |
-
assert agg["true_positives"] == 2
|
| 256 |
-
assert agg["false_negatives"] == 1
|
| 257 |
-
assert agg["missed_total"] == 1
|
| 258 |
-
# Micro F1 global : TP=2, FP=0, FN=1 → P=1, R=2/3, F1=0.8
|
| 259 |
-
assert agg["global"]["f1"] == pytest.approx(0.8)
|
| 260 |
-
|
| 261 |
-
def test_aggregate_returns_none_when_no_ner_metrics(self) -> None:
|
| 262 |
-
dr = _make_document_result(ner_metrics=None)
|
| 263 |
-
assert _aggregate_ner([dr]) is None
|
| 264 |
-
|
| 265 |
-
|
| 266 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 267 |
-
# 7. Rétrocompat : sans extractor, rien ne change
|
| 268 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 269 |
-
|
| 270 |
-
|
| 271 |
-
class TestBackwardCompat:
|
| 272 |
-
def test_no_extractor_no_calculation(self, tmp_path: Path) -> None:
|
| 273 |
-
"""Si entity_extractor=None, le runner ne touche pas aux
|
| 274 |
-
ner_metrics. On valide que le DocumentResult par défaut a bien
|
| 275 |
-
ner_metrics=None — le runner ne l'attribue pas spontanément."""
|
| 276 |
-
# Les deux DRs ne reçoivent jamais d'extracteur ; ils restent
|
| 277 |
-
# tels quels. Le corpus n'est pas nécessaire ici (valide la
|
| 278 |
-
# rétrocompat du modèle).
|
| 279 |
-
dr1 = _make_document_result(doc_id="doc1")
|
| 280 |
-
dr2 = _make_document_result(doc_id="doc2")
|
| 281 |
-
assert dr1.ner_metrics is None
|
| 282 |
-
assert dr2.ner_metrics is None
|
| 283 |
-
|
| 284 |
-
|
| 285 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 286 |
-
# 8. Robustesse : extracteur qui lève
|
| 287 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 288 |
-
|
| 289 |
-
|
| 290 |
-
class TestRobustness:
|
| 291 |
-
def test_extractor_raising_does_not_break_others(
|
| 292 |
-
self, tmp_path: Path, caplog: pytest.LogCaptureFixture
|
| 293 |
-
) -> None:
|
| 294 |
-
"""Si l'extracteur lève sur le doc1, le doc2 doit tout de même
|
| 295 |
-
être traité (et inversement, ici doc1 est le seul avec GT
|
| 296 |
-
entités, donc on vérifie qu'aucun crash ne casse le runner)."""
|
| 297 |
-
corpus = _corpus_with_entities(tmp_path)
|
| 298 |
-
|
| 299 |
-
def _broken_extractor(text: str) -> list[dict]:
|
| 300 |
-
raise RuntimeError("boom")
|
| 301 |
-
|
| 302 |
-
dr1 = _make_document_result(
|
| 303 |
-
doc_id="doc1", hypothesis="Marie de Bourgogne en 1477.",
|
| 304 |
-
)
|
| 305 |
-
with caplog.at_level("WARNING", logger="picarones.measurements.runner"):
|
| 306 |
-
_attach_ner_metrics(corpus, [dr1], _broken_extractor)
|
| 307 |
-
|
| 308 |
-
# Pas de propagation, ner_metrics reste None
|
| 309 |
-
assert dr1.ner_metrics is None
|
| 310 |
-
# Et un warning explicite a été émis
|
| 311 |
-
assert any("ner.attach" in rec.message for rec in caplog.records)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@@ -1,285 +0,0 @@
|
|
| 1 |
-
"""Tests Sprint 42 — exposition des token_confidences + câblage runner.
|
| 2 |
-
|
| 3 |
-
Le runner peut maintenant calculer des métriques de calibration
|
| 4 |
-
(ECE / MCE / reliability) dès qu'un moteur expose des
|
| 5 |
-
``token_confidences`` sur l'``EngineResult``.
|
| 6 |
-
|
| 7 |
-
Couvre :
|
| 8 |
-
|
| 9 |
-
1. ``EngineResult.token_confidences`` accepte ``None`` (rétrocompat
|
| 10 |
-
stricte) ou une liste de dicts.
|
| 11 |
-
2. ``DocumentResult.calibration_metrics`` est sérialisé via ``as_dict``
|
| 12 |
-
uniquement quand renseigné, libéré par ``compact()``.
|
| 13 |
-
3. ``EngineReport.aggregated_calibration`` apparaît dans ``as_dict``
|
| 14 |
-
quand renseigné.
|
| 15 |
-
4. ``_calibration_from_engine_result`` :
|
| 16 |
-
- Aligne en bag-of-words avec multiplicité (proxy oracle)
|
| 17 |
-
- Normalise les confidences en pourcentage (>1) à [0, 1]
|
| 18 |
-
- Ignore les confidences négatives (Tesseract -1 pour non-mots)
|
| 19 |
-
- Retourne ``None`` sur entrée vide / ``None``
|
| 20 |
-
5. ``_aggregate_calibration`` :
|
| 21 |
-
- Combine les bins de plusieurs documents en somme pondérée
|
| 22 |
-
- Recalcule ECE/MCE micro à partir des sommes
|
| 23 |
-
- Retourne ``None`` si aucun doc n'a de calibration
|
| 24 |
-
6. Rétrocompat : sans token_confidences sur l'EngineResult, aucun
|
| 25 |
-
calcul calibration ; ``aggregated_calibration = None``.
|
| 26 |
-
"""
|
| 27 |
-
|
| 28 |
-
from __future__ import annotations
|
| 29 |
-
|
| 30 |
-
import pytest
|
| 31 |
-
|
| 32 |
-
from picarones.measurements.runner import (
|
| 33 |
-
_aggregate_calibration,
|
| 34 |
-
_calibration_from_engine_result,
|
| 35 |
-
)
|
| 36 |
-
from picarones.evaluation.benchmark_result import DocumentResult, EngineReport
|
| 37 |
-
from picarones.adapters.legacy_engines.base import EngineResult
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 41 |
-
# 1. EngineResult.token_confidences
|
| 42 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 43 |
-
|
| 44 |
-
|
| 45 |
-
class TestEngineResultExtension:
|
| 46 |
-
def test_default_is_none(self) -> None:
|
| 47 |
-
r = EngineResult("e", "/tmp/x.png", "hello", 1.0)
|
| 48 |
-
assert r.token_confidences is None
|
| 49 |
-
|
| 50 |
-
def test_accepts_list_of_dicts(self) -> None:
|
| 51 |
-
confs = [{"token": "hello", "confidence": 0.95}]
|
| 52 |
-
r = EngineResult("e", "/tmp/x.png", "hello", 1.0, token_confidences=confs)
|
| 53 |
-
assert r.token_confidences == confs
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 57 |
-
# 2-3. Modèles : sérialisation et compact
|
| 58 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 59 |
-
|
| 60 |
-
|
| 61 |
-
def _make_dr(calibration_metrics: dict | None = None) -> DocumentResult:
|
| 62 |
-
from picarones.evaluation.metric_result import MetricsResult
|
| 63 |
-
|
| 64 |
-
return DocumentResult(
|
| 65 |
-
doc_id="d1", image_path="/tmp/x.png",
|
| 66 |
-
ground_truth="a b c", hypothesis="a b c",
|
| 67 |
-
metrics=MetricsResult(
|
| 68 |
-
cer=0.0, cer_nfc=0.0, cer_caseless=0.0,
|
| 69 |
-
wer=0.0, wer_normalized=0.0, mer=0.0, wil=0.0,
|
| 70 |
-
reference_length=5, hypothesis_length=5,
|
| 71 |
-
),
|
| 72 |
-
duration_seconds=0.1,
|
| 73 |
-
calibration_metrics=calibration_metrics,
|
| 74 |
-
)
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
class TestModelsSerialization:
|
| 78 |
-
def test_calibration_metrics_omitted_when_none(self) -> None:
|
| 79 |
-
d = _make_dr(None).as_dict()
|
| 80 |
-
assert "calibration_metrics" not in d
|
| 81 |
-
|
| 82 |
-
def test_calibration_metrics_present_when_set(self) -> None:
|
| 83 |
-
d = _make_dr({"ece": 0.05, "mce": 0.1}).as_dict()
|
| 84 |
-
assert d["calibration_metrics"] == {"ece": 0.05, "mce": 0.1}
|
| 85 |
-
|
| 86 |
-
def test_compact_clears_calibration(self) -> None:
|
| 87 |
-
# Sprint A14-S1 — ``compact()`` est désormais opt-in.
|
| 88 |
-
dr = _make_dr({"ece": 0.05})
|
| 89 |
-
dr.compact(drop_analyses=True)
|
| 90 |
-
assert dr.calibration_metrics is None
|
| 91 |
-
|
| 92 |
-
def test_engine_report_aggregated_calibration_omitted_when_none(self) -> None:
|
| 93 |
-
rep = EngineReport(
|
| 94 |
-
engine_name="t", engine_version="1", engine_config={},
|
| 95 |
-
document_results=[_make_dr()],
|
| 96 |
-
)
|
| 97 |
-
assert "aggregated_calibration" not in rep.as_dict()
|
| 98 |
-
|
| 99 |
-
def test_engine_report_aggregated_calibration_included_when_set(self) -> None:
|
| 100 |
-
rep = EngineReport(
|
| 101 |
-
engine_name="t", engine_version="1", engine_config={},
|
| 102 |
-
document_results=[_make_dr()],
|
| 103 |
-
aggregated_calibration={"ece": 0.05, "n_predictions": 100},
|
| 104 |
-
)
|
| 105 |
-
assert rep.as_dict()["aggregated_calibration"] == {
|
| 106 |
-
"ece": 0.05, "n_predictions": 100,
|
| 107 |
-
}
|
| 108 |
-
|
| 109 |
-
|
| 110 |
-
# ──────────────────────────────────────────────────────────────────���───────
|
| 111 |
-
# 4. Helper d'alignement
|
| 112 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 113 |
-
|
| 114 |
-
|
| 115 |
-
class TestCalibrationFromEngineResult:
|
| 116 |
-
def test_returns_none_for_empty_inputs(self) -> None:
|
| 117 |
-
assert _calibration_from_engine_result("text", None) is None
|
| 118 |
-
assert _calibration_from_engine_result("text", []) is None
|
| 119 |
-
|
| 120 |
-
def test_perfect_calibration_when_conf_matches_accuracy(self) -> None:
|
| 121 |
-
gt = "a b c d e f g h i j"
|
| 122 |
-
# 7 tokens dans la GT à conf=0.7, 3 hors de la GT à conf=0.7 → ECE = 0
|
| 123 |
-
tcs = (
|
| 124 |
-
[{"token": c, "confidence": 0.7} for c in "abcdefg"]
|
| 125 |
-
+ [{"token": c, "confidence": 0.7} for c in ["X", "Y", "Z"]]
|
| 126 |
-
)
|
| 127 |
-
m = _calibration_from_engine_result(gt, tcs)
|
| 128 |
-
assert m is not None
|
| 129 |
-
assert m["ece"] == pytest.approx(0.0, abs=1e-9)
|
| 130 |
-
assert m["overall_accuracy"] == pytest.approx(0.7)
|
| 131 |
-
assert m["n_predictions"] == 10
|
| 132 |
-
|
| 133 |
-
def test_normalizes_percentage_confidences(self) -> None:
|
| 134 |
-
"""Conf > 1 est interprétée en pourcentage et divisée par 100."""
|
| 135 |
-
m = _calibration_from_engine_result(
|
| 136 |
-
"hello", [{"token": "hello", "confidence": 95.0}],
|
| 137 |
-
)
|
| 138 |
-
assert m is not None
|
| 139 |
-
# 95/100 = 0.95
|
| 140 |
-
assert m["overall_confidence"] == 0.95
|
| 141 |
-
|
| 142 |
-
def test_skips_negative_confidences(self) -> None:
|
| 143 |
-
"""Tesseract met -1 pour les non-mots ; on les ignore."""
|
| 144 |
-
m = _calibration_from_engine_result(
|
| 145 |
-
"hello", [
|
| 146 |
-
{"token": "hello", "confidence": 0.9},
|
| 147 |
-
{"token": ".", "confidence": -1.0},
|
| 148 |
-
],
|
| 149 |
-
)
|
| 150 |
-
assert m is not None
|
| 151 |
-
assert m["n_predictions"] == 1
|
| 152 |
-
|
| 153 |
-
def test_bag_of_words_with_multiplicity(self) -> None:
|
| 154 |
-
# GT contient deux 'le'. L'hypothèse en a trois → 2 corrects, 1 incorrect.
|
| 155 |
-
gt = "le chat le chien"
|
| 156 |
-
tcs = [
|
| 157 |
-
{"token": "le", "confidence": 0.9},
|
| 158 |
-
{"token": "le", "confidence": 0.9},
|
| 159 |
-
{"token": "le", "confidence": 0.9}, # 3e 'le' : pas dans la GT
|
| 160 |
-
{"token": "chat", "confidence": 0.9},
|
| 161 |
-
{"token": "chien", "confidence": 0.9},
|
| 162 |
-
]
|
| 163 |
-
m = _calibration_from_engine_result(gt, tcs)
|
| 164 |
-
# 4 corrects sur 5
|
| 165 |
-
assert m["overall_accuracy"] == 0.8
|
| 166 |
-
assert m["n_predictions"] == 5
|
| 167 |
-
|
| 168 |
-
def test_skips_invalid_entries(self) -> None:
|
| 169 |
-
m = _calibration_from_engine_result(
|
| 170 |
-
"hello", [
|
| 171 |
-
"not a dict",
|
| 172 |
-
{"no_token": True, "confidence": 0.5},
|
| 173 |
-
{"token": "hello"}, # pas de confidence
|
| 174 |
-
{"token": "hello", "confidence": "abc"}, # conf non numérique
|
| 175 |
-
{"token": "hello", "confidence": 0.9}, # valide
|
| 176 |
-
],
|
| 177 |
-
)
|
| 178 |
-
assert m is not None
|
| 179 |
-
assert m["n_predictions"] == 1
|
| 180 |
-
|
| 181 |
-
|
| 182 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 183 |
-
# 5. Agrégateur
|
| 184 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 185 |
-
|
| 186 |
-
|
| 187 |
-
class TestAggregateCalibration:
|
| 188 |
-
def test_returns_none_when_no_doc_has_calibration(self) -> None:
|
| 189 |
-
drs = [_make_dr(None), _make_dr(None)]
|
| 190 |
-
assert _aggregate_calibration(drs) is None
|
| 191 |
-
|
| 192 |
-
def test_combines_bins_across_docs(self) -> None:
|
| 193 |
-
# Doc 1 : bin [0.5, 0.6) avec 10 prédictions, conf=0.55, acc=0.5
|
| 194 |
-
# Doc 2 : bin [0.5, 0.6) avec 20 prédictions, conf=0.55, acc=0.7
|
| 195 |
-
# Agrégat attendu : 30 prédictions dans ce bin, conf moy = 0.55,
|
| 196 |
-
# acc moy pondérée = (10*0.5 + 20*0.7) / 30 = 19/30 ≈ 0.633
|
| 197 |
-
empty_bin = lambda lo, hi: { # noqa: E731
|
| 198 |
-
"bin_low": lo, "bin_high": hi,
|
| 199 |
-
"avg_confidence": None, "accuracy": None,
|
| 200 |
-
"count": 0, "gap": None,
|
| 201 |
-
}
|
| 202 |
-
bins1 = [empty_bin(k / 10, (k + 1) / 10) for k in range(10)]
|
| 203 |
-
bins1[5] = {
|
| 204 |
-
"bin_low": 0.5, "bin_high": 0.6,
|
| 205 |
-
"avg_confidence": 0.55, "accuracy": 0.5,
|
| 206 |
-
"count": 10, "gap": 0.05,
|
| 207 |
-
}
|
| 208 |
-
m1 = {
|
| 209 |
-
"ece": 0.05, "mce": 0.05, "n_bins": 10, "n_predictions": 10,
|
| 210 |
-
"overall_accuracy": 0.5, "overall_confidence": 0.55, "bins": bins1,
|
| 211 |
-
}
|
| 212 |
-
bins2 = [empty_bin(k / 10, (k + 1) / 10) for k in range(10)]
|
| 213 |
-
bins2[5] = {
|
| 214 |
-
"bin_low": 0.5, "bin_high": 0.6,
|
| 215 |
-
"avg_confidence": 0.55, "accuracy": 0.7,
|
| 216 |
-
"count": 20, "gap": 0.15,
|
| 217 |
-
}
|
| 218 |
-
m2 = {
|
| 219 |
-
"ece": 0.15, "mce": 0.15, "n_bins": 10, "n_predictions": 20,
|
| 220 |
-
"overall_accuracy": 0.7, "overall_confidence": 0.55, "bins": bins2,
|
| 221 |
-
}
|
| 222 |
-
drs = [_make_dr(m1), _make_dr(m2)]
|
| 223 |
-
agg = _aggregate_calibration(drs)
|
| 224 |
-
assert agg is not None
|
| 225 |
-
assert agg["n_predictions"] == 30
|
| 226 |
-
assert agg["doc_count"] == 2
|
| 227 |
-
# Accuracy combinée = (10*0.5 + 20*0.7) / 30
|
| 228 |
-
assert agg["overall_accuracy"] == (10 * 0.5 + 20 * 0.7) / 30
|
| 229 |
-
# Confidence combinée = 0.55 (constante)
|
| 230 |
-
assert abs(agg["overall_confidence"] - 0.55) < 1e-9
|
| 231 |
-
# ECE micro : seul bin non vide (bin 5), avec count=30,
|
| 232 |
-
# avg_conf=0.55, accuracy=19/30 ≈ 0.633, gap = |0.55 - 0.633|
|
| 233 |
-
expected_ece = abs(0.55 - 19 / 30)
|
| 234 |
-
assert abs(agg["ece"] - expected_ece) < 1e-9
|
| 235 |
-
assert agg["mce"] == agg["ece"] # un seul bin non vide → MCE = ECE
|
| 236 |
-
|
| 237 |
-
|
| 238 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 239 |
-
# 6. Rétrocompat : sans token_confidences, rien ne change
|
| 240 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 241 |
-
|
| 242 |
-
|
| 243 |
-
class TestBackwardCompat:
|
| 244 |
-
def test_engine_result_default_no_calibration(self) -> None:
|
| 245 |
-
# Un EngineResult sans token_confidences → calibration_metrics
|
| 246 |
-
# ne doit pas être calculée.
|
| 247 |
-
from picarones.measurements.runner import _compute_document_result
|
| 248 |
-
ocr = EngineResult(
|
| 249 |
-
engine_name="e",
|
| 250 |
-
image_path="/tmp/x.png",
|
| 251 |
-
text="a b c",
|
| 252 |
-
duration_seconds=0.1,
|
| 253 |
-
token_confidences=None,
|
| 254 |
-
)
|
| 255 |
-
dr = _compute_document_result(
|
| 256 |
-
doc_id="d1", image_path="/tmp/x.png",
|
| 257 |
-
ground_truth="a b c",
|
| 258 |
-
ocr_result=ocr,
|
| 259 |
-
char_exclude=None,
|
| 260 |
-
)
|
| 261 |
-
assert dr.calibration_metrics is None
|
| 262 |
-
|
| 263 |
-
def test_engine_result_with_confs_triggers_calibration(self) -> None:
|
| 264 |
-
from picarones.measurements.runner import _compute_document_result
|
| 265 |
-
ocr = EngineResult(
|
| 266 |
-
engine_name="e",
|
| 267 |
-
image_path="/tmp/x.png",
|
| 268 |
-
text="a b c",
|
| 269 |
-
duration_seconds=0.1,
|
| 270 |
-
token_confidences=[
|
| 271 |
-
{"token": "a", "confidence": 0.9},
|
| 272 |
-
{"token": "b", "confidence": 0.9},
|
| 273 |
-
{"token": "c", "confidence": 0.9},
|
| 274 |
-
],
|
| 275 |
-
)
|
| 276 |
-
dr = _compute_document_result(
|
| 277 |
-
doc_id="d1", image_path="/tmp/x.png",
|
| 278 |
-
ground_truth="a b c",
|
| 279 |
-
ocr_result=ocr,
|
| 280 |
-
char_exclude=None,
|
| 281 |
-
)
|
| 282 |
-
assert dr.calibration_metrics is not None
|
| 283 |
-
# 3 tokens, tous corrects, conf 0.9 → accuracy = 1, conf = 0.9
|
| 284 |
-
assert dr.calibration_metrics["overall_accuracy"] == 1.0
|
| 285 |
-
assert dr.calibration_metrics["overall_confidence"] == 0.9
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@@ -1,303 +0,0 @@
|
|
| 1 |
-
"""Tests Sprint 61 — câblage backend des métriques philologiques.
|
| 2 |
-
|
| 3 |
-
Couvre :
|
| 4 |
-
|
| 5 |
-
1. Champs ``DocumentResult.philological_metrics`` et
|
| 6 |
-
``EngineReport.aggregated_philological`` posés.
|
| 7 |
-
2. Sérialisation conditionnelle dans ``as_dict``.
|
| 8 |
-
3. Libération par ``compact``.
|
| 9 |
-
4. ``compute_philological_metrics`` :
|
| 10 |
-
- GT médiéval déclenche abbreviations + mufi
|
| 11 |
-
- GT imprimé ancien déclenche early_modern
|
| 12 |
-
- GT moderne déclenche modern_archives
|
| 13 |
-
- GT avec numéraux romains déclenche roman_numerals
|
| 14 |
-
- GT avec caractères hors Basic Latin déclenche unicode_blocks
|
| 15 |
-
- GT en ASCII pur sans marqueur → ``None``
|
| 16 |
-
- GT vide / None → ``None``
|
| 17 |
-
5. ``aggregate_philological_metrics`` :
|
| 18 |
-
- Somme correcte des compteurs par module
|
| 19 |
-
- Recalcul correct des scores globaux
|
| 20 |
-
- Doc count cohérent
|
| 21 |
-
- Aucun document avec signal → ``None``
|
| 22 |
-
6. Intégration runner end-to-end via fixture mock.
|
| 23 |
-
"""
|
| 24 |
-
|
| 25 |
-
from __future__ import annotations
|
| 26 |
-
|
| 27 |
-
from picarones.measurements.philological_hooks import (
|
| 28 |
-
aggregate_philological_metrics,
|
| 29 |
-
compute_philological_metrics,
|
| 30 |
-
)
|
| 31 |
-
from picarones.evaluation.benchmark_result import DocumentResult, EngineReport
|
| 32 |
-
from picarones.evaluation.metric_result import MetricsResult
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
def _make_doc(
|
| 36 |
-
doc_id: str = "d1",
|
| 37 |
-
gt: str = "",
|
| 38 |
-
hyp: str = "",
|
| 39 |
-
philological: dict | None = None,
|
| 40 |
-
) -> DocumentResult:
|
| 41 |
-
"""Helper : construit un DocumentResult minimal pour les tests."""
|
| 42 |
-
return DocumentResult(
|
| 43 |
-
doc_id=doc_id,
|
| 44 |
-
image_path=f"/tmp/{doc_id}.png",
|
| 45 |
-
ground_truth=gt,
|
| 46 |
-
hypothesis=hyp,
|
| 47 |
-
metrics=MetricsResult(
|
| 48 |
-
cer=0.0, cer_nfc=0.0, cer_caseless=0.0,
|
| 49 |
-
wer=0.0, wer_normalized=0.0, mer=0.0, wil=0.0,
|
| 50 |
-
reference_length=len(gt), hypothesis_length=len(hyp),
|
| 51 |
-
),
|
| 52 |
-
duration_seconds=0.1,
|
| 53 |
-
philological_metrics=philological,
|
| 54 |
-
)
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 58 |
-
# 1. Champs posés sur DocumentResult / EngineReport
|
| 59 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
class TestFields:
|
| 63 |
-
def test_document_result_default_none(self) -> None:
|
| 64 |
-
dr = _make_doc()
|
| 65 |
-
assert dr.philological_metrics is None
|
| 66 |
-
|
| 67 |
-
def test_document_result_accepts_dict(self) -> None:
|
| 68 |
-
dr = _make_doc(philological={"mufi": {"coverage": 0.9}})
|
| 69 |
-
assert dr.philological_metrics == {"mufi": {"coverage": 0.9}}
|
| 70 |
-
|
| 71 |
-
def test_engine_report_default_none(self) -> None:
|
| 72 |
-
report = EngineReport(
|
| 73 |
-
engine_name="test", engine_version="1.0",
|
| 74 |
-
engine_config={}, document_results=[],
|
| 75 |
-
)
|
| 76 |
-
assert report.aggregated_philological is None
|
| 77 |
-
|
| 78 |
-
def test_engine_report_accepts_dict(self) -> None:
|
| 79 |
-
report = EngineReport(
|
| 80 |
-
engine_name="test", engine_version="1.0",
|
| 81 |
-
engine_config={}, document_results=[],
|
| 82 |
-
aggregated_philological={"mufi": {"coverage": 0.9}},
|
| 83 |
-
)
|
| 84 |
-
assert report.aggregated_philological == {"mufi": {"coverage": 0.9}}
|
| 85 |
-
|
| 86 |
-
|
| 87 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 88 |
-
# 2. Sérialisation as_dict
|
| 89 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
class TestSerialization:
|
| 93 |
-
def test_as_dict_omits_none(self) -> None:
|
| 94 |
-
dr = _make_doc()
|
| 95 |
-
d = dr.as_dict()
|
| 96 |
-
assert "philological_metrics" not in d
|
| 97 |
-
|
| 98 |
-
def test_as_dict_includes_when_present(self) -> None:
|
| 99 |
-
dr = _make_doc(philological={"mufi": {"coverage": 1.0}})
|
| 100 |
-
d = dr.as_dict()
|
| 101 |
-
assert d["philological_metrics"] == {"mufi": {"coverage": 1.0}}
|
| 102 |
-
|
| 103 |
-
def test_engine_report_as_dict_omits_none(self) -> None:
|
| 104 |
-
report = EngineReport(
|
| 105 |
-
engine_name="t", engine_version="1", engine_config={},
|
| 106 |
-
document_results=[],
|
| 107 |
-
)
|
| 108 |
-
assert "aggregated_philological" not in report.as_dict()
|
| 109 |
-
|
| 110 |
-
def test_engine_report_as_dict_includes_when_present(self) -> None:
|
| 111 |
-
report = EngineReport(
|
| 112 |
-
engine_name="t", engine_version="1", engine_config={},
|
| 113 |
-
document_results=[],
|
| 114 |
-
aggregated_philological={"mufi": {"coverage": 0.5}},
|
| 115 |
-
)
|
| 116 |
-
d = report.as_dict()
|
| 117 |
-
assert d["aggregated_philological"] == {"mufi": {"coverage": 0.5}}
|
| 118 |
-
|
| 119 |
-
|
| 120 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 121 |
-
# 3. Libération par compact()
|
| 122 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 123 |
-
|
| 124 |
-
|
| 125 |
-
class TestCompact:
|
| 126 |
-
def test_compact_clears_philological(self) -> None:
|
| 127 |
-
# Sprint A14-S1 — opt-in via drop_analyses=True.
|
| 128 |
-
dr = _make_doc(philological={"mufi": {"coverage": 1.0}})
|
| 129 |
-
dr.compact(drop_analyses=True)
|
| 130 |
-
assert dr.philological_metrics is None
|
| 131 |
-
|
| 132 |
-
|
| 133 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 134 |
-
# 4. compute_philological_metrics — adaptive masking
|
| 135 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 136 |
-
|
| 137 |
-
|
| 138 |
-
class TestComputeAdaptive:
|
| 139 |
-
def test_medieval_triggers_abbreviations_and_mufi(self) -> None:
|
| 140 |
-
gt = "fait en lan ꝑ regem þæt"
|
| 141 |
-
m = compute_philological_metrics(gt, gt)
|
| 142 |
-
assert m is not None
|
| 143 |
-
assert "abbreviations" in m
|
| 144 |
-
assert "mufi" in m
|
| 145 |
-
|
| 146 |
-
def test_early_modern_triggers_typography(self) -> None:
|
| 147 |
-
gt = "le ſerpent finement & ã"
|
| 148 |
-
m = compute_philological_metrics(gt, gt)
|
| 149 |
-
assert m is not None
|
| 150 |
-
assert "early_modern" in m
|
| 151 |
-
|
| 152 |
-
def test_modern_archives_triggers_module(self) -> None:
|
| 153 |
-
gt = "Mme Dupont au bd Voltaire vol. II"
|
| 154 |
-
m = compute_philological_metrics(gt, gt)
|
| 155 |
-
assert m is not None
|
| 156 |
-
assert "modern_archives" in m
|
| 157 |
-
|
| 158 |
-
def test_roman_numerals_triggers_module(self) -> None:
|
| 159 |
-
gt = "Louis XIV mourut en MDCCXV"
|
| 160 |
-
m = compute_philological_metrics(gt, gt)
|
| 161 |
-
assert m is not None
|
| 162 |
-
assert "roman_numerals" in m
|
| 163 |
-
|
| 164 |
-
def test_unicode_blocks_triggered_only_outside_basic_latin(self) -> None:
|
| 165 |
-
# ASCII pur sans marqueur → unicode_blocks omis (Basic Latin
|
| 166 |
-
# uniquement, breakdown trivial).
|
| 167 |
-
m = compute_philological_metrics("hello world", "hello world")
|
| 168 |
-
assert m is None
|
| 169 |
-
|
| 170 |
-
def test_unicode_blocks_triggered_with_diacritics(self) -> None:
|
| 171 |
-
# Du Latin Extended → unicode_blocks inclus
|
| 172 |
-
gt = "café à é ô"
|
| 173 |
-
m = compute_philological_metrics(gt, gt)
|
| 174 |
-
assert m is not None
|
| 175 |
-
assert "unicode_blocks" in m
|
| 176 |
-
|
| 177 |
-
def test_empty_returns_none(self) -> None:
|
| 178 |
-
assert compute_philological_metrics("", "") is None
|
| 179 |
-
assert compute_philological_metrics(None, None) is None
|
| 180 |
-
|
| 181 |
-
def test_no_signal_returns_none(self) -> None:
|
| 182 |
-
# Pure Basic Latin sans aucun marqueur philologique
|
| 183 |
-
m = compute_philological_metrics("hello", "hello")
|
| 184 |
-
assert m is None
|
| 185 |
-
|
| 186 |
-
|
| 187 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 188 |
-
# 5. aggregate_philological_metrics
|
| 189 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 190 |
-
|
| 191 |
-
|
| 192 |
-
class TestAggregation:
|
| 193 |
-
def test_no_data_returns_none(self) -> None:
|
| 194 |
-
assert aggregate_philological_metrics([]) is None
|
| 195 |
-
assert aggregate_philological_metrics([None, None]) is None
|
| 196 |
-
|
| 197 |
-
def test_aggregates_only_present_modules(self) -> None:
|
| 198 |
-
# Doc 1 a mufi+abbr, Doc 2 a juste roman_numerals
|
| 199 |
-
d1 = compute_philological_metrics("ꝑ ꝓ ꝗ", "per pro qui")
|
| 200 |
-
d2 = compute_philological_metrics("Louis XIV", "Louis 14")
|
| 201 |
-
agg = aggregate_philological_metrics([d1, d2])
|
| 202 |
-
assert agg is not None
|
| 203 |
-
# mufi présent (Doc1 le déclenchait avec ꝑ/ꝓ/ꝗ qui sont MUFI)
|
| 204 |
-
assert "abbreviations" in agg
|
| 205 |
-
assert "roman_numerals" in agg
|
| 206 |
-
# doc_count par module
|
| 207 |
-
assert agg["abbreviations"]["doc_count"] == 1
|
| 208 |
-
assert agg["roman_numerals"]["doc_count"] == 1
|
| 209 |
-
|
| 210 |
-
def test_aggregation_sums_counters(self) -> None:
|
| 211 |
-
# 3 docs avec MUFI : "þæt ꝑ" = 3 caractères MUFI (þ, æ, ꝑ)
|
| 212 |
-
gt = "þæt ꝑ"
|
| 213 |
-
per_doc = [compute_philological_metrics(gt, gt) for _ in range(3)]
|
| 214 |
-
agg = aggregate_philological_metrics(per_doc)
|
| 215 |
-
assert agg is not None
|
| 216 |
-
assert "mufi" in agg
|
| 217 |
-
# 3 caractères × 3 docs = 9
|
| 218 |
-
assert agg["mufi"]["n_mufi_chars_reference"] == 9
|
| 219 |
-
assert agg["mufi"]["n_mufi_chars_preserved"] == 9
|
| 220 |
-
assert agg["mufi"]["coverage"] == 1.0
|
| 221 |
-
assert agg["mufi"]["doc_count"] == 3
|
| 222 |
-
|
| 223 |
-
def test_aggregation_recomputes_global_score(self) -> None:
|
| 224 |
-
# Doc1 préserve 100%, Doc2 préserve 0% → moyenne pondérée
|
| 225 |
-
d1 = compute_philological_metrics("XIV", "XIV")
|
| 226 |
-
d2 = compute_philological_metrics("V", "perdu")
|
| 227 |
-
agg = aggregate_philological_metrics([d1, d2])
|
| 228 |
-
roman = agg["roman_numerals"]
|
| 229 |
-
# Doc1 : 1 strict_preserved (XIV)
|
| 230 |
-
# Doc2 : 1 lost (V)
|
| 231 |
-
# Total : 2 numéraux, 1 strict → 0.5
|
| 232 |
-
assert roman["n_numerals_reference"] == 2
|
| 233 |
-
assert roman["global_strict_score"] == 0.5
|
| 234 |
-
|
| 235 |
-
def test_per_category_aggregation_modern_archives(self) -> None:
|
| 236 |
-
# Deux docs avec modern_archives sur catégories différentes
|
| 237 |
-
d1 = compute_philological_metrics("Mme bd", "Mme bd")
|
| 238 |
-
d2 = compute_philological_metrics("vol. p.", "vol. p.")
|
| 239 |
-
agg = aggregate_philological_metrics([d1, d2])
|
| 240 |
-
per_cat = agg["modern_archives"]["per_category"]
|
| 241 |
-
# Doc1 : civility_titles + address ; Doc2 : bibliographic
|
| 242 |
-
assert "civility_titles" in per_cat
|
| 243 |
-
assert "address" in per_cat
|
| 244 |
-
assert "bibliographic" in per_cat
|
| 245 |
-
for cat in per_cat.values():
|
| 246 |
-
assert cat["strict_score"] == 1.0
|
| 247 |
-
|
| 248 |
-
|
| 249 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 250 |
-
# 6. Intégration end-to-end (mock léger sur le runner)
|
| 251 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 252 |
-
|
| 253 |
-
|
| 254 |
-
class TestRunnerIntegration:
|
| 255 |
-
"""Vérifie que ``_compute_document_result`` attache bien les
|
| 256 |
-
``philological_metrics`` quand la GT a du signal."""
|
| 257 |
-
|
| 258 |
-
def test_runner_attaches_philological(self, tmp_path) -> None:
|
| 259 |
-
from picarones.measurements.runner import _compute_document_result
|
| 260 |
-
from picarones.adapters.legacy_engines.base import EngineResult
|
| 261 |
-
|
| 262 |
-
# Créer une image fictive (le module image_quality échouera
|
| 263 |
-
# gracieusement, ce qui est OK pour le test).
|
| 264 |
-
img = tmp_path / "doc.png"
|
| 265 |
-
img.write_bytes(b"") # vide ; on ignore le résultat image_quality
|
| 266 |
-
|
| 267 |
-
gt = "ꝑ regem mcclxxxij"
|
| 268 |
-
ocr_result = EngineResult(
|
| 269 |
-
engine_name="mock", image_path=str(img),
|
| 270 |
-
text=gt, duration_seconds=0.1, error=None,
|
| 271 |
-
)
|
| 272 |
-
dr = _compute_document_result(
|
| 273 |
-
doc_id="d1",
|
| 274 |
-
image_path=str(img),
|
| 275 |
-
ground_truth=gt,
|
| 276 |
-
ocr_result=ocr_result,
|
| 277 |
-
char_exclude=None,
|
| 278 |
-
)
|
| 279 |
-
assert dr.philological_metrics is not None
|
| 280 |
-
assert "abbreviations" in dr.philological_metrics
|
| 281 |
-
assert "roman_numerals" in dr.philological_metrics
|
| 282 |
-
|
| 283 |
-
def test_runner_omits_philological_on_plain_text(self, tmp_path) -> None:
|
| 284 |
-
from picarones.measurements.runner import _compute_document_result
|
| 285 |
-
from picarones.adapters.legacy_engines.base import EngineResult
|
| 286 |
-
|
| 287 |
-
img = tmp_path / "doc.png"
|
| 288 |
-
img.write_bytes(b"")
|
| 289 |
-
|
| 290 |
-
# Texte ASCII pur sans marqueur philologique
|
| 291 |
-
gt = "hello world without any markers"
|
| 292 |
-
ocr_result = EngineResult(
|
| 293 |
-
engine_name="mock", image_path=str(img),
|
| 294 |
-
text=gt, duration_seconds=0.1, error=None,
|
| 295 |
-
)
|
| 296 |
-
dr = _compute_document_result(
|
| 297 |
-
doc_id="d1",
|
| 298 |
-
image_path=str(img),
|
| 299 |
-
ground_truth=gt,
|
| 300 |
-
ocr_result=ocr_result,
|
| 301 |
-
char_exclude=None,
|
| 302 |
-
)
|
| 303 |
-
assert dr.philological_metrics is None
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@@ -19,15 +19,11 @@ from __future__ import annotations
|
|
| 19 |
|
| 20 |
import inspect
|
| 21 |
|
|
|
|
| 22 |
from picarones.evaluation.metrics.normalization import (
|
| 23 |
NORMALIZATION_PROFILES,
|
| 24 |
get_builtin_profile,
|
| 25 |
)
|
| 26 |
-
from picarones.app.services._legacy_runner_adapter import run_benchmark_via_service
|
| 27 |
-
from picarones.measurements.runner.document import _compute_document_result
|
| 28 |
-
from picarones.measurements.runner.workers import (
|
| 29 |
-
_io_doc_worker,
|
| 30 |
-
)
|
| 31 |
|
| 32 |
|
| 33 |
class TestRunBenchmarkSignature:
|
|
@@ -38,14 +34,6 @@ class TestRunBenchmarkSignature:
|
|
| 38 |
# Et avec une valeur par défaut sûre.
|
| 39 |
assert sig.parameters["normalization_profile"].default is None
|
| 40 |
|
| 41 |
-
def test_io_worker_accepts_normalization_profile(self) -> None:
|
| 42 |
-
sig = inspect.signature(_io_doc_worker)
|
| 43 |
-
assert "normalization_profile" in sig.parameters
|
| 44 |
-
|
| 45 |
-
def test_compute_document_result_accepts_normalization_profile(self) -> None:
|
| 46 |
-
sig = inspect.signature(_compute_document_result)
|
| 47 |
-
assert "normalization_profile" in sig.parameters
|
| 48 |
-
|
| 49 |
|
| 50 |
class TestProfileResolution:
|
| 51 |
def test_all_eleven_profiles_resolvable(self) -> None:
|
|
|
|
| 19 |
|
| 20 |
import inspect
|
| 21 |
|
| 22 |
+
from picarones.app.services._legacy_runner_adapter import run_benchmark_via_service
|
| 23 |
from picarones.evaluation.metrics.normalization import (
|
| 24 |
NORMALIZATION_PROFILES,
|
| 25 |
get_builtin_profile,
|
| 26 |
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
|
| 28 |
|
| 29 |
class TestRunBenchmarkSignature:
|
|
|
|
| 34 |
# Et avec une valeur par défaut sûre.
|
| 35 |
assert sig.parameters["normalization_profile"].default is None
|
| 36 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
|
| 38 |
class TestProfileResolution:
|
| 39 |
def test_all_eleven_profiles_resolvable(self) -> None:
|