govdoc-md-cleaner v0.1.0: 政务文档 Markdown 清洗工具(规则引擎 + CLI + 测试)
- 8 条 YAML 声明规则:页码/页眉页脚/目录点线/图片/HTML表格/散落标签/行尾空白/空行 - 防误伤设计:protect 正则 + 内容形态豁免 + OCR burst 检测 - md-clean single/batch CLI,JSON 清洗报告 - 18 个单元测试 Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
@@ -0,0 +1,21 @@
|
||||
[build-system]
|
||||
requires = ["setuptools>=68"]
|
||||
build-backend = "setuptools.build_meta"
|
||||
|
||||
[project]
|
||||
name = "govdoc-md-cleaner"
|
||||
version = "0.1.0"
|
||||
description = "政务文档(招标/投标/采购/合同)PDF→Markdown 产物的清洗工具"
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
license = { text = "MIT" }
|
||||
dependencies = ["PyYAML>=6.0"]
|
||||
|
||||
[project.scripts]
|
||||
md-clean = "cleaner.cli:main"
|
||||
|
||||
[tool.setuptools.packages.find]
|
||||
include = ["cleaner*"]
|
||||
|
||||
[tool.setuptools.package-data]
|
||||
cleaner = ["../rules/*.yaml"]
|
||||
Reference in New Issue
Block a user