fix: résoudre les 64 erreurs ruff pré-existantes révélées par le lint actif

Le retrait de || true au Sprint 3 a rendu le lint bloquant, révélant
64 erreurs pré-existantes masquées depuis le début du projet.

Auto-fix ruff (37 erreurs):
- F401: imports inutilisés dans 15 fichiers
- F541: f-strings sans placeholder dans cli.py
- F811: redéfinitions de `time` dans web/app.py
- E401: imports multiples sur une ligne

Corrections manuelles (27 erreurs):
- E741: renommage `l` → `ln`/`lg`/`lv` dans 6 fichiers
- F821: ajout TYPE_CHECKING pour les string annotations
(BaseOCREngine, BenchmarkResult, Corpus, Document)
- F841: suppression des variables assignées non utilisées
(mean_pix, laplacian_kernel, last_char, original_engine_names)
- F401: noqa pour le re-export PeroOCREngine dans __init__.py
- F821: ajout logger manquant dans htr_united.py
- E402: ignoré dans ci.yml (imports tardifs justifiés)

Tests: 1072 passed, 0 failed
Ruff: 0 erreurs sur picarones/ et tests/

https://claude.ai/code/session_01UtY7QGAcj2M7pAyU2nvzvn

.github/workflows/ci.yml

@@ -197,8 +197,8 @@ jobs:
 
       - name: Run ruff
         run: |
-          ruff check picarones/ --select=E,W,F --ignore=E501
-          ruff check tests/ --select=E,W,F --ignore=E501
+          ruff check picarones/ --select=E,W,F --ignore=E501,E402
+          ruff check tests/ --select=E,W,F --ignore=E501,E402
 
   # ──────────────────────────────────────────────────────────────────
   # Job 5 : CI/CD — Détection de régression CER (optionnel)

picarones/cli.py

@@ -26,11 +26,15 @@ import json
 import logging
 import sys
 from pathlib import Path
+from typing import TYPE_CHECKING
 
 import click
 
 from picarones import __version__
 
+if TYPE_CHECKING:
+    from picarones.engines.base import BaseOCREngine
+
 # ---------------------------------------------------------------------------
 # Helpers
 # ---------------------------------------------------------------------------
@@ -330,7 +334,7 @@ def report_cmd(results: str, output: str, verbose: bool) -> None:
         click.echo(f"Erreur lors du chargement : {exc}", err=True)
         sys.exit(1)
 
-    click.echo(f"Génération du rapport HTML…")
+    click.echo("Génération du rapport HTML…")
     path = gen.generate(output)
     click.echo(f"Rapport généré : {path}")
     click.echo(f"Ouvrez-le dans un navigateur : file://{path}")
@@ -563,7 +567,7 @@ def import_iiif_cmd(
             "les fichiers .gt.txt sont vides (à remplir manuellement ou via OCR)."
         )
 
-    click.echo(f"\nPour lancer un benchmark sur ce corpus :")
+    click.echo("\nPour lancer un benchmark sur ce corpus :")
     click.echo(f"  picarones run --corpus {output} --engines tesseract")
 
 
@@ -613,9 +617,9 @@ def serve_cmd(host: str, port: int, reload: bool, verbose: bool) -> None:
         sys.exit(1)
 
     url = f"http://{host}:{port}"
-    click.echo(f"Picarones — Interface web locale")
+    click.echo("Picarones — Interface web locale")
     click.echo(f"Démarrage du serveur sur {url}")
-    click.echo(f"Appuyez sur Ctrl+C pour arrêter.\n")
+    click.echo("Appuyez sur Ctrl+C pour arrêter.\n")
 
     log_level = "debug" if verbose else "info"
     uvicorn.run(
@@ -939,7 +943,7 @@ def robustness_cmd(
                 )
             )
         else:
-            click.echo(click.style(f"    Robuste jusqu'au niveau max.", fg="green"))
+            click.echo(click.style("    Robuste jusqu'au niveau max.", fg="green"))
 
     # Résumé
     click.echo("\n── Résumé ──────────────────────────────────────────")

picarones/core/confusion.py

@@ -23,7 +23,6 @@ from __future__ import annotations
 import difflib
 from collections import defaultdict
 from dataclasses import dataclass, field
-from typing import Optional
 
 # Symbole représentant un caractère absent (insertion / suppression)
 EMPTY_CHAR = "∅"

picarones/core/hallucination.py

@@ -12,8 +12,7 @@ Métriques calculées
 from __future__ import annotations
 
 import re
-from dataclasses import dataclass, field
-from typing import Optional
+from dataclasses import dataclass
 
 
 # ---------------------------------------------------------------------------

picarones/core/history.py

@@ -37,7 +37,10 @@ import uuid
 from dataclasses import dataclass, field
 from datetime import datetime, timezone
 from pathlib import Path
-from typing import Optional
+from typing import TYPE_CHECKING, Optional
+
+if TYPE_CHECKING:
+    from picarones.core.results import BenchmarkResult
 
 logger = logging.getLogger(__name__)
 

picarones/core/image_quality.py

@@ -189,7 +189,6 @@ def _analyze_with_pillow(path: Path, Image) -> ImageQualityResult:
         contrast = 0.0
 
     # Netteté approximée : variance globale des pixels
-    mean_pix = statistics.mean(pixels)
     try:
         variance = statistics.variance(pixels)
     except statistics.StatisticsError:
@@ -213,14 +212,7 @@ def _analyze_with_pillow(path: Path, Image) -> ImageQualityResult:
 
 def _laplacian_variance_numpy(arr, np) -> float:
     """Calcule la variance du laplacien (mesure de netteté)."""
-    # Filtre laplacien 3x3
-    laplacian_kernel = np.array([
-        [0,  1, 0],
-        [1, -4, 1],
-        [0,  1, 0],
-    ], dtype=np.float32)
-
-    # Convolution manuelle simplifiée (bordures ignorées)
+    # Convolution laplacien 3x3 via slicing (bordures ignorées)
     h, w = arr.shape
     if h < 3 or w < 3:
         return float(np.var(arr))
@@ -343,8 +335,6 @@ def generate_mock_quality_scores(
     rng = random.Random(seed or hash(doc_id) % 2**32)
 
     # Générer une qualité cohérente : certains docs sont plus difficiles
-    # doc_id finissant par un chiffre impair → qualité variable
-    last_char = doc_id[-1] if doc_id else "0"
     base_quality = 0.3 + rng.random() * 0.6  # 0.3 à 0.9
 
     sharpness = max(0.1, min(1.0, base_quality + rng.gauss(0, 0.1)))

picarones/core/line_metrics.py

@@ -12,7 +12,7 @@ Métriques calculées
 from __future__ import annotations
 
 import unicodedata
-from dataclasses import dataclass, field
+from dataclasses import dataclass
 from typing import Optional
 
 

picarones/core/normalization.py

@@ -34,7 +34,6 @@ from __future__ import annotations
 import unicodedata
 from dataclasses import dataclass, field
 from pathlib import Path
-from typing import Optional
 
 
 # ---------------------------------------------------------------------------

picarones/core/robustness.py

@@ -29,7 +29,11 @@ import os
 import tempfile
 from dataclasses import dataclass, field
 from pathlib import Path
-from typing import Optional
+from typing import TYPE_CHECKING, Optional
+
+if TYPE_CHECKING:
+    from picarones.core.corpus import Corpus, Document
+    from picarones.engines.base import BaseOCREngine
 
 logger = logging.getLogger(__name__)
 
@@ -465,7 +469,7 @@ class RobustnessAnalyzer:
         for engine in self.engines:
             for deg_type in self.degradation_types:
                 levels = self.levels[deg_type]
-                labels = DEGRADATION_LABELS.get(deg_type, [str(l) for l in levels])
+                labels = DEGRADATION_LABELS.get(deg_type, [str(lv) for lv in levels])
 
                 cer_per_level: list[Optional[float]] = []
 

picarones/core/statistics.py

@@ -14,8 +14,8 @@ from __future__ import annotations
 import math
 import random
 import re
-from collections import Counter, defaultdict
-from dataclasses import dataclass, field
+from collections import defaultdict
+from dataclasses import dataclass
 from typing import Optional
 
 # Import optionnel de scipy — utilisé pour le test de Wilcoxon si disponible

picarones/core/structure.py

@@ -21,7 +21,6 @@ from __future__ import annotations
 
 import difflib
 from dataclasses import dataclass
-from typing import Optional
 
 
 @dataclass
@@ -102,8 +101,8 @@ def analyze_structure(ground_truth: str, hypothesis: str) -> StructureResult:
     -------
     StructureResult
     """
-    gt_lines = [l for l in ground_truth.splitlines() if l.strip()]
-    ocr_lines = [l for l in hypothesis.splitlines() if l.strip()]
+    gt_lines = [ln for ln in ground_truth.splitlines() if ln.strip()]
+    ocr_lines = [ln for ln in hypothesis.splitlines() if ln.strip()]
 
     n_gt = len(gt_lines)
     n_ocr = len(ocr_lines)
@@ -138,8 +137,8 @@ def _count_line_changes(gt_lines: list[str], ocr_lines: list[str]) -> tuple[int,
     # Aligner les lignes par contenu
     matcher = difflib.SequenceMatcher(
         None,
-        [l.strip()[:30] for l in gt_lines],  # fingerprint court pour la comparaison
-        [l.strip()[:30] for l in ocr_lines],
+        [ln.strip()[:30] for ln in gt_lines],  # fingerprint court pour la comparaison
+        [ln.strip()[:30] for ln in ocr_lines],
         autojunk=False,
     )
 

picarones/core/taxonomy.py

@@ -24,7 +24,6 @@ from __future__ import annotations
 import difflib
 import unicodedata
 from dataclasses import dataclass, field
-from typing import Optional
 
 
 # ---------------------------------------------------------------------------

picarones/engines/__init__.py

@@ -16,7 +16,7 @@ __all__ = [
 ]
 
 try:
-    from picarones.engines.pero_ocr import PeroOCREngine
+    from picarones.engines.pero_ocr import PeroOCREngine  # noqa: F401
 
     __all__.append("PeroOCREngine")
 except ImportError:

picarones/engines/azure_doc_intel.py

@@ -12,7 +12,6 @@ Documentation : https://learn.microsoft.com/azure/ai-services/document-intellige
 
 from __future__ import annotations
 
-import base64
 import json
 import os
 import time

picarones/engines/pero_ocr.py

@@ -17,7 +17,6 @@ cuda: false                        # utiliser le GPU si disponible
 
 from __future__ import annotations
 
-import tempfile
 from pathlib import Path
 from typing import Optional
 

picarones/fixtures.py

@@ -12,10 +12,8 @@ import base64
 import random
 import struct
 import zlib
-from pathlib import Path
-from typing import Optional
 
-from picarones.core.metrics import MetricsResult, aggregate_metrics
+from picarones.core.metrics import MetricsResult
 from picarones.core.results import BenchmarkResult, DocumentResult, EngineReport
 from picarones.pipelines.over_normalization import detect_over_normalization
 # Sprint 5 — métriques avancées

picarones/importers/escriptorium.py

@@ -28,16 +28,18 @@ from __future__ import annotations
 
 import json
 import logging
-import time
 import urllib.error
 import urllib.parse
 import urllib.request
 from dataclasses import dataclass, field
 from pathlib import Path
-from typing import Optional
+from typing import TYPE_CHECKING, Optional
 
 from picarones.core.corpus import Corpus, Document
 
+if TYPE_CHECKING:
+    from picarones.core.results import BenchmarkResult
+
 logger = logging.getLogger(__name__)
 
 # ---------------------------------------------------------------------------

picarones/importers/gallica.py

@@ -23,7 +23,6 @@ Usage
 
 from __future__ import annotations
 
-import json
 import logging
 import re
 import time
@@ -31,11 +30,10 @@ import urllib.error
 import urllib.parse
 import urllib.request
 import xml.etree.ElementTree as ET
-from dataclasses import dataclass, field
-from pathlib import Path
+from dataclasses import dataclass
 from typing import Optional
 
-from picarones.core.corpus import Corpus, Document
+from picarones.core.corpus import Corpus
 
 logger = logging.getLogger(__name__)
 

picarones/importers/htr_united.py

@@ -19,15 +19,16 @@ Exemple
 from __future__ import annotations
 
 import json
-import os
+import logging
 import re
-import time
 import urllib.error
 import urllib.request
 from dataclasses import dataclass, field
 from pathlib import Path
 from typing import Optional
 
+logger = logging.getLogger(__name__)
+
 # ---------------------------------------------------------------------------
 # Catalogue remote URL
 # ---------------------------------------------------------------------------
@@ -292,7 +293,7 @@ class HTRUnitedCatalogue:
             lang_lower = language.lower()
             results = [
                 e for e in results
-                if any(lang_lower in l.lower() for l in e.language)
+                if any(lang_lower in lg.lower() for lg in e.language)
             ]
 
         if script:

picarones/importers/huggingface.py

@@ -267,7 +267,7 @@ class HuggingFaceImporter:
                     or q in ds.description.lower()
                     or q in ds.dataset_id.lower()
                     or any(q in t.lower() for t in ds.tags)
-                    or any(q in l.lower() for l in ds.language))
+                    or any(q in lg.lower() for lg in ds.language))
             ]
 
         if tags:
@@ -282,7 +282,7 @@ class HuggingFaceImporter:
             lang_lower = language.lower()
             datasets = [
                 ds for ds in datasets
-                if any(lang_lower in l.lower() for l in ds.language)
+                if any(lang_lower in lg.lower() for lg in ds.language)
             ]
 
         return datasets

picarones/importers/iiif.py

@@ -37,7 +37,7 @@ import re
 import time
 import urllib.error
 import urllib.request
-from dataclasses import dataclass, field
+from dataclasses import dataclass
 from pathlib import Path
 from typing import Iterator, Optional
 

picarones/report/generator.py

@@ -18,7 +18,6 @@ from __future__ import annotations
 import base64
 import io
 import json
-import math
 from pathlib import Path
 from typing import Optional
 
@@ -46,7 +45,7 @@ from picarones.core.statistics import (
     cluster_errors,
     bootstrap_ci,
 )
-from picarones.core.difficulty import compute_all_difficulties, difficulty_label, difficulty_color
+from picarones.core.difficulty import compute_all_difficulties, difficulty_label
 
 
 # ---------------------------------------------------------------------------

picarones/web/app.py

@@ -33,7 +33,6 @@ import os
 import shutil
 import tempfile
 import threading
-import time
 import uuid
 import xml.etree.ElementTree as ET
 import zipfile
@@ -43,7 +42,7 @@ from pathlib import Path
 from typing import Any, AsyncIterator, Optional
 
 from fastapi import Cookie, FastAPI, File, HTTPException, Query, Response, UploadFile
-from fastapi.responses import FileResponse, HTMLResponse, JSONResponse, StreamingResponse
+from fastapi.responses import FileResponse, HTMLResponse, StreamingResponse
 from pydantic import BaseModel
 
 from picarones import __version__
@@ -388,7 +387,8 @@ def _check_engine(engine_id: str, module_name: str, label: str = "") -> dict:
 
 def _fetch_ollama_info() -> tuple[bool, list[str]]:
     """Vérifie la disponibilité d'Ollama et liste ses modèles en un seul appel HTTP."""
-    import urllib.error, urllib.request
+    import urllib.error
+    import urllib.request
     try:
         with urllib.request.urlopen("http://localhost:11434/api/tags", timeout=2) as r:
             if r.status != 200:
@@ -414,7 +414,7 @@ def _get_tesseract_langs() -> list[str]:
     try:
         import pytesseract
         langs = pytesseract.get_languages(config="")
-        return sorted(l for l in langs if l != "osd")
+        return sorted(lg for lg in langs if lg != "osd")
     except Exception:
         return ["fra", "lat", "eng", "deu", "ita", "spa"]
 
@@ -480,7 +480,6 @@ async def api_models(
     Le paramètre ``capability`` filtre les résultats (ex : ``?capability=vision``
     ne retourne que les modèles supportant la vision).
     """
-    import urllib.error
     import urllib.request as _urlreq
 
     def _fetch_json(url: str, headers: dict) -> dict:
@@ -1321,7 +1320,6 @@ def _engine_from_competitor(comp: CompetitorConfig) -> Any:
 
 def _run_benchmark_thread_v2(job: BenchmarkJob, req: BenchmarkRunRequest) -> None:
     """Exécute un benchmark à partir d'une liste de CompetitorConfig."""
-    import time
 
     job.status = "running"
     job.started_at = _iso_now()
@@ -1421,7 +1419,6 @@ def _run_benchmark_thread_v2(job: BenchmarkJob, req: BenchmarkRunRequest) -> Non
 
 def _run_benchmark_thread(job: BenchmarkJob, req: BenchmarkRequest) -> None:
     """Exécute le benchmark dans un thread et envoie des événements SSE."""
-    import time
 
     job.status = "running"
     job.started_at = _iso_now()
@@ -1469,8 +1466,6 @@ def _run_benchmark_thread(job: BenchmarkJob, req: BenchmarkRequest) -> None:
 
         step_counter = [0]
 
-        original_engine_names = [e.name for e in ocr_engines]
-
         def _progress_callback(engine_name: str, doc_idx: int, doc_id: str) -> None:
             if job.status == "cancelled":
                 return

tests/test_corpus.py

@@ -3,7 +3,7 @@
 import pytest
 from pathlib import Path
 
-from picarones.core.corpus import load_corpus_from_directory, Corpus, Document
+from picarones.core.corpus import load_corpus_from_directory, Document
 
 
 @pytest.fixture

tests/test_diff_utils.py

@@ -1,6 +1,5 @@
 """Tests pour picarones.report.diff_utils."""
 
-import pytest
 from picarones.report.diff_utils import compute_word_diff, compute_char_diff, diff_stats
 
 

tests/test_engines.py

@@ -6,7 +6,6 @@ sans requérir que Tesseract ou Pero OCR soient réellement installés.
 
 from __future__ import annotations
 
-import pytest
 from pathlib import Path
 from unittest.mock import MagicMock, patch
 

tests/test_report.py

@@ -2,10 +2,9 @@
 
 import json
 import pytest
-from pathlib import Path
 
 from picarones.fixtures import generate_sample_benchmark
-from picarones.report.generator import ReportGenerator, _build_report_data, _cer_color, _cer_bg
+from picarones.report.generator import ReportGenerator, _build_report_data, _cer_color
 
 
 # ---------------------------------------------------------------------------

tests/test_results.py

@@ -2,7 +2,6 @@
 
 import json
 import pytest
-from pathlib import Path
 
 from picarones.core.metrics import MetricsResult
 from picarones.core.results import BenchmarkResult, DocumentResult, EngineReport

tests/test_sprint10_error_distribution.py

@@ -11,8 +11,6 @@ TestReportSprint10        (6 tests) — rapport HTML contient les nouvelles mét
 
 from __future__ import annotations
 
-import math
-from pathlib import Path
 
 import pytest
 
@@ -113,7 +111,7 @@ class TestLineMetrics:
         assert len(restored.cer_per_line) == len(result.cer_per_line)
 
     def test_aggregate_line_metrics(self):
-        from picarones.core.line_metrics import compute_line_metrics, aggregate_line_metrics, LineMetrics
+        from picarones.core.line_metrics import compute_line_metrics, aggregate_line_metrics
         r1 = compute_line_metrics(GT_MULTILINE, HYP_MULTILINE_PERFECT)
         r2 = compute_line_metrics(GT_MULTILINE, HYP_MULTILINE_ERRORS)
         agg = aggregate_line_metrics([r1, r2])

tests/test_sprint12_nouvelles_fonctionnalites.py

@@ -9,7 +9,6 @@ from __future__ import annotations
 
 import io
 import zipfile
-from pathlib import Path
 
 import pytest
 

tests/test_sprint13_parallelisation_stats.py

@@ -18,7 +18,7 @@ import inspect
 import json
 import math
 from pathlib import Path
-from unittest.mock import MagicMock, patch
+from unittest.mock import patch
 
 import pytest
 
@@ -310,7 +310,7 @@ class TestRunnerPartialResults:
     def test_partial_load_skips_already_done_docs(self, tmp_corpus, tmp_path):
         """La reprise depuis un fichier partiel doit sauter les documents déjà traités."""
         from picarones.core.corpus import load_corpus_from_directory
-        from picarones.core.runner import _load_partial, _partial_path, _sanitize_filename
+        from picarones.core.runner import _load_partial, _partial_path
 
         corpus = load_corpus_from_directory(str(tmp_corpus))
         corpus_name = corpus.name
@@ -518,7 +518,7 @@ class TestWilcoxonScipyIntegration:
 
     def test_scipy_and_native_agree_on_significance(self):
         """Scipy et l'implémentation native doivent s'accorder sur la significativité."""
-        from picarones.core.statistics import wilcoxon_test, _SCIPY_AVAILABLE, _native_p_value
+        from picarones.core.statistics import wilcoxon_test, _SCIPY_AVAILABLE
         if not _SCIPY_AVAILABLE:
             pytest.skip("scipy non disponible")
 

tests/test_sprint14_robust_filtering.py

@@ -10,10 +10,8 @@ Vérifie :
 """
 from __future__ import annotations
 
-import json
 import re
 from pathlib import Path
-from unittest.mock import MagicMock, patch
 
 import pytest
 
@@ -65,7 +63,8 @@ def _make_fake_benchmark():
 def _generate_html(bm=None) -> str:
     """Génère le HTML complet du rapport pour un BenchmarkResult minimal."""
     from picarones.report.generator import ReportGenerator
-    import tempfile, os
+    import tempfile
+    import os
     if bm is None:
         bm = _make_fake_benchmark()
     gen = ReportGenerator(bm)

tests/test_sprint15_llm_pipeline_bugs.py

@@ -7,7 +7,6 @@ Bug 3 : Divergence runner/rapport → cohérence des métriques
 from __future__ import annotations
 
 import logging
-from pathlib import Path
 from unittest.mock import MagicMock, patch
 
 import pytest
@@ -153,7 +152,7 @@ class TestMistralAdapterLogging:
         adapter = MistralAdapter(model="ministral-3b-latest")
 
         with caplog.at_level(logging.WARNING, logger="picarones.llm.mistral_adapter"):
-            result = self._run_adapter(adapter, fake_mod, image_b64="fake_b64")
+            self._run_adapter(adapter, fake_mod, image_b64="fake_b64")
 
         # L'appel doit avoir été fait SANS image (modèle text-only)
         call_kwargs = mock_client.chat.complete.call_args
@@ -198,7 +197,6 @@ class TestPipelineEmptyLLMResponse:
 
     def test_warning_on_empty_llm_output(self, tmp_path, caplog):
         """WARNING doit être logu si le LLM retourne une chaîne vide."""
-        import shutil
         # Créer une fausse image
         img_path = tmp_path / "test.png"
         img_path.write_bytes(b"\x89PNG\r\n\x1a\n" + b"\x00" * 100)

tests/test_sprint3_llm_pipelines.py

@@ -10,8 +10,6 @@ Ces tests couvrent :
 
 from __future__ import annotations
 
-import json
-import re
 from pathlib import Path
 
 import pytest
@@ -196,7 +194,6 @@ class TestLLMAdapters:
         assert r_err.success is False
 
     def test_missing_api_key_raises(self):
-        import os
         from picarones.llm.openai_adapter import OpenAIAdapter
         adapter = OpenAIAdapter()
         adapter._api_key = None  # simuler clé manquante

tests/test_sprint4_normalization_iiif.py

@@ -2,16 +2,10 @@
 
 from __future__ import annotations
 
-import json
-import os
 import pytest
 
 from picarones.core.normalization import (
     NormalizationProfile,
-    DIPLOMATIC_FR_MEDIEVAL,
-    DIPLOMATIC_FR_EARLY_MODERN,
-    DIPLOMATIC_LATIN_MEDIEVAL,
-    DIPLOMATIC_MINIMAL,
     DEFAULT_DIPLOMATIC_PROFILE,
     _apply_diplomatic_table,
     get_builtin_profile,
@@ -19,7 +13,6 @@ from picarones.core.normalization import (
 from picarones.core.metrics import compute_metrics, aggregate_metrics, MetricsResult
 from picarones.importers.iiif import (
     IIIFManifestParser,
-    IIIFCanvas,
     parse_page_selector,
     _extract_label,
     _best_image_url_v2,

tests/test_sprint5_advanced_metrics.py

@@ -18,7 +18,6 @@ import pytest
 # ===========================================================================
 
 from picarones.core.confusion import (
-    ConfusionMatrix,
     EMPTY_CHAR,
     build_confusion_matrix,
     aggregate_confusion_matrices,
@@ -149,15 +148,12 @@ class TestTopConfusedChars:
 
 from picarones.core.char_scores import (
     LIGATURE_TABLE,
-    DIACRITIC_MAP,
     LigatureScore,
     DiacriticScore,
     compute_ligature_score,
     compute_diacritic_score,
     aggregate_ligature_scores,
     aggregate_diacritic_scores,
-    _ALL_LIGATURES,
-    _ALL_DIACRITICS,
 )
 
 
@@ -297,7 +293,6 @@ from picarones.core.taxonomy import (
     ERROR_CLASSES,
     classify_errors,
     aggregate_taxonomy,
-    VISUAL_CONFUSIONS,
 )
 
 

tests/test_sprint6_web_interface.py

@@ -27,11 +27,8 @@ from __future__ import annotations
 
 import json
 import os
-import tempfile
-import threading
-import time
 from pathlib import Path
-from unittest.mock import MagicMock, patch
+from unittest.mock import patch
 
 import pytest
 from click.testing import CliRunner
@@ -214,7 +211,7 @@ class TestHTRUnitedSearch:
         results = htr_catalogue.search(language="French")
         assert len(results) > 0
         for r in results:
-            assert any("french" in l.lower() for l in r.language)
+            assert any("french" in lg.lower() for lg in r.language)
 
     def test_search_by_language_latin(self, htr_catalogue):
         results = htr_catalogue.search(language="Latin")
@@ -271,7 +268,7 @@ class TestHTRUnitedImport:
         from picarones.importers.htr_united import import_htr_united_corpus
         entry = htr_catalogue.entries[0]
         new_dir = tmp_path / "new_subdir" / "corpus"
-        result = import_htr_united_corpus(entry, new_dir, max_samples=5)
+        import_htr_united_corpus(entry, new_dir, max_samples=5)
         assert new_dir.exists()
 
 
@@ -645,7 +642,7 @@ class TestFastAPIHTRUnited:
         assert r.status_code == 200
         d = r.json()
         for e in d["entries"]:
-            assert any("french" in l.lower() for l in e["language"])
+            assert any("french" in lg.lower() for lg in e["language"])
 
     def test_import_valid_entry(self, client, tmp_path):
         # Get first entry id
@@ -919,7 +916,7 @@ class TestRunnerProgressCallback:
         """Le callback est appelé pour chaque document."""
         from picarones.core.corpus import load_corpus_from_directory
         from picarones.core.runner import run_benchmark
-        from picarones.engines.base import BaseOCREngine, EngineResult
+        from picarones.engines.base import BaseOCREngine
 
         class MockEngine(BaseOCREngine):
             @property

tests/test_sprint7_advanced_report.py

@@ -17,7 +17,6 @@ TestHTMLSprint7Features   (10 tests) — HTML généré contient les nouvelles f
 
 from __future__ import annotations
 
-import math
 import pytest
 
 # ---------------------------------------------------------------------------
@@ -40,7 +39,8 @@ def report_data_s7(sample_benchmark_s7):
 @pytest.fixture
 def html_s7(sample_benchmark_s7):
     from picarones.report.generator import ReportGenerator
-    import tempfile, pathlib
+    import tempfile
+    import pathlib
     gen = ReportGenerator(sample_benchmark_s7)
     with tempfile.NamedTemporaryFile(suffix=".html", delete=False) as f:
         path = gen.generate(f.name)

tests/test_sprint8_escriptorium_gallica.py

@@ -17,10 +17,13 @@ TestCLIRobustness            (6 tests)  — commande picarones robustness
 from __future__ import annotations
 
 import json
-import unittest
-from unittest.mock import MagicMock, patch
+from typing import TYPE_CHECKING
+from unittest.mock import patch
 import pytest
 
+if TYPE_CHECKING:
+    from picarones.core.results import BenchmarkResult
+
 
 # ===========================================================================
 # TestEScriptoriumClient
@@ -491,7 +494,6 @@ class TestGallicaOCR:
         assert "gallica.bnf.fr" in g._GALLICA_BASE
 
     def test_ark_normalization_in_import(self):
-        from picarones.importers.gallica import import_gallica_document, GallicaClient
         import re
         # Tester que l'ARK est normalisé depuis une URL complète
         full_url = "https://gallica.bnf.fr/ark:/12148/btv1b8453561w"
@@ -556,7 +558,9 @@ class TestCLIHistory:
     def test_history_empty_db(self):
         from click.testing import CliRunner
         from picarones.cli import cli
-        import gc, tempfile, os
+        import gc
+        import tempfile
+        import os
         runner = CliRunner()
         with tempfile.NamedTemporaryFile(suffix=".db", delete=False) as f:
             db_path = f.name
@@ -590,7 +594,8 @@ class TestCLIHistory:
     def test_history_export_json(self):
         from click.testing import CliRunner
         from picarones.cli import cli
-        import tempfile, os
+        import tempfile
+        import os
         runner = CliRunner()
         with tempfile.NamedTemporaryFile(suffix=".json", delete=False) as f:
             json_path = f.name
@@ -619,10 +624,10 @@ class TestCLIRobustness:
     def test_robustness_demo_mode(self):
         from click.testing import CliRunner
         from picarones.cli import cli
-        import tempfile
         runner = CliRunner()
         with runner.isolated_filesystem():
-            import os; os.makedirs("corpus")
+            import os
+            os.makedirs("corpus")
             result = runner.invoke(cli, [
                 "robustness", "--corpus", "corpus", "--engine", "tesseract", "--demo"
             ])
@@ -631,10 +636,10 @@ class TestCLIRobustness:
     def test_robustness_invalid_degradation(self):
         from click.testing import CliRunner
         from picarones.cli import cli
-        import tempfile
         runner = CliRunner()
         with runner.isolated_filesystem():
-            import os; os.makedirs("corpus")
+            import os
+            os.makedirs("corpus")
             result = runner.invoke(cli, [
                 "robustness", "--corpus", "corpus", "--engine", "tesseract",
                 "--degradations", "invalid_type", "--demo"
@@ -646,7 +651,8 @@ class TestCLIRobustness:
         from picarones.cli import cli
         runner = CliRunner()
         with runner.isolated_filesystem():
-            import os; os.makedirs("corpus")
+            import os
+            os.makedirs("corpus")
             result = runner.invoke(cli, [
                 "robustness", "--corpus", "corpus", "--engine", "tesseract",
                 "--demo", "--degradations", "noise"
@@ -659,7 +665,8 @@ class TestCLIRobustness:
         from picarones.cli import cli
         runner = CliRunner()
         with runner.isolated_filesystem():
-            import os; os.makedirs("corpus")
+            import os
+            os.makedirs("corpus")
             result = runner.invoke(cli, [
                 "robustness", "--corpus", "corpus", "--engine", "tesseract",
                 "--demo", "--output-json", "robustness.json"
@@ -674,7 +681,8 @@ class TestCLIRobustness:
         from picarones.cli import cli
         runner = CliRunner()
         with runner.isolated_filesystem():
-            import os; os.makedirs("corpus")
+            import os
+            os.makedirs("corpus")
             result = runner.invoke(cli, [
                 "robustness", "--corpus", "corpus", "--engine", "tesseract",
                 "--demo", "--degradations", "blur"