Spaces:
Sleeping
Sleeping
File size: 3,735 Bytes
49cc409 bff1348 49cc409 cecde1f bff1348 49cc409 b283975 49cc409 bff1348 49cc409 bff1348 49cc409 a0dc23e 49cc409 bff1348 cecde1f bff1348 49cc409 bff1348 e224609 bff1348 7afb12e 35001ff d733b48 bff1348 b4cc1c5 bff1348 001e605 bff1348 49cc409 8c509eb a0dc23e b914841 a0dc23e d28d854 b6bdecc 76e79a0 a0dc23e 8c509eb 49cc409 a76711b | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 | [build-system]
requires = ["setuptools>=68.0", "wheel"]
build-backend = "setuptools.build_meta"
[project]
name = "picarones"
version = "1.0.0"
description = "Plateforme de comparaison de moteurs OCR/HTR pour documents patrimoniaux"
readme = "README.md"
requires-python = ">=3.11"
license = { text = "Apache-2.0" }
authors = [{ name = "maribakulj" }]
keywords = ["ocr", "htr", "patrimoine", "benchmark", "cer", "wer", "gallica", "escriptorium", "iiif"]
classifiers = [
"Development Status :: 4 - Beta",
"Programming Language :: Python :: 3.11",
"Programming Language :: Python :: 3.12",
"License :: OSI Approved :: Apache Software License",
"Operating System :: OS Independent",
"Topic :: Scientific/Engineering :: Artificial Intelligence",
"Topic :: Text Processing :: Linguistic",
"Intended Audience :: Science/Research",
"Natural Language :: French",
]
dependencies = [
"click>=8.1.0",
"jiwer>=3.0.0",
"Pillow>=10.0.0",
"pyyaml>=6.0.0",
"pytesseract>=0.3.10",
"tqdm>=4.66.0",
"numpy>=1.24.0",
"jinja2>=3.1.0",
]
[project.urls]
Homepage = "https://github.com/maribakulj/Picarones"
Documentation = "https://github.com/maribakulj/Picarones/blob/main/INSTALL.md"
Repository = "https://github.com/maribakulj/Picarones"
Changelog = "https://github.com/maribakulj/Picarones/blob/main/CHANGELOG.md"
"Bug Tracker" = "https://github.com/maribakulj/Picarones/issues"
[project.optional-dependencies]
# Développement et tests
dev = ["pytest>=7.4.0", "pytest-cov>=4.1.0", "httpx>=0.27.0", "fastapi>=0.111.0", "uvicorn[standard]>=0.29.0", "python-multipart>=0.0.9"]
# Interface web FastAPI
web = ["fastapi>=0.111.0", "uvicorn[standard]>=0.29.0", "httpx>=0.27.0", "python-multipart>=0.0.9"]
# Tests statistiques avancés (Wilcoxon exact, Friedman chi² exact, Nemenyi)
# Sinon fallback pur Python (approximations normale / Wilson-Hilferty).
stats = ["scipy>=1.11.0"]
# Extracteurs d'entités nommées (Sprint 40 — A.II.1.a du plan d'évolution).
# Sans cet extra, picarones.core.ner_backends.SpacyEntityExtractor tombe
# en mode dégradé silencieux et le runner saute le calcul NER.
ner = ["spacy>=3.7.0"]
# Import HuggingFace Datasets
hf = ["datasets>=2.19.0"]
# Moteurs OCR optionnels
pero = ["pero-ocr>=0.1.0"]
kraken = ["kraken>=4.0.0"]
# Adaptateurs LLM
llm = [
"openai>=1.0.0",
"anthropic>=0.20.0",
"mistralai>=1.0.0",
]
# OCR cloud APIs
ocr-cloud = [
"google-cloud-vision>=3.0.0",
"boto3>=1.34.0",
"azure-ai-formrecognizer>=3.3.0",
]
# Installation complète (tous les extras sauf les OCR cloud)
all = [
"picarones[web,hf,llm,dev]",
]
[project.scripts]
picarones = "picarones.cli:cli"
[tool.setuptools.packages.find]
where = ["."]
include = ["picarones*"]
[tool.setuptools.package-data]
picarones = [
"prompts/*.txt",
"web/static/*.css",
"web/static/*.js",
"web/templates/*.j2",
"web/templates/*.html",
"report/templates/*.j2",
"report/templates/*.html",
"report/templates/*.css",
"report/templates/*.js",
"report/i18n/*.json",
"core/narrative/templates/*.yaml",
"data/*.yaml",
"report/glossary/*.yaml",
]
[tool.pytest.ini_options]
testpaths = ["tests"]
addopts = "-v --tb=short"
[tool.ruff]
# Configuration centralisée pour que `ruff check`, `make lint` et le job CI
# produisent exactement les mêmes résultats sans flags en ligne de commande.
line-length = 100
target-version = "py311"
[tool.ruff.lint]
# E/W = pycodestyle, F = pyflakes. On conserve les mêmes règles que le CI
# d'origine (avant Sprint 22), qui excluait les lignes longues (E501) et les
# imports non-top (E402, parfois utiles pour imports conditionnels).
select = ["E", "W", "F"]
ignore = ["E501", "E402"]
|