604e889ca4
- spikes/：Word 转 PDF（Gotenberg）、格式识别、原句坐标、DeepSeek 抽取四项验证代码与两版提示词；样本派生产物和 .env 不进 git - tech-validation.md：完整结论。四项都可行：WPS 字体字符集要修正并改用行高调整过的字体；格式识别不需要 Docling；表格内切句待改进；抽取需第三道依据校验与规则兜底 - architecture.md：§3.5 加预处理与字体包，§3.6 证据校验改为三道，§10 回填结论 - 03 功能需求与 decisions.md（TV1）：召回 ≥ 99%、采纳准确率 ≥ 95%、页码 100%、高亮正文 ≥ 98% / 表格 ≥ 95% Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
32 lines
1.4 KiB
Python
32 lines
1.4 KiB
Python
"""修正 WPS 写错的字体字符集：中文字体（名字含汉字，或是常见中文字体英文名）被标成 SYMBOL(02) 时改成 GB2312(86)。
|
||
输入、输出都是 DOCX。用法：python -I fix_charset.py in.docx out.docx"""
|
||
import re, sys, zipfile
|
||
|
||
CJK_LATIN = {"SimSun", "NSimSun", "SimHei", "FangSong", "KaiTi", "Microsoft YaHei", "DengXian"}
|
||
|
||
def is_cjk_font(name: str) -> bool:
|
||
return bool(re.search(r"[一-鿿]", name)) or name in CJK_LATIN
|
||
|
||
def fix_font_table(xml: str) -> tuple[str, list[str]]:
|
||
fixed = []
|
||
def repl(m):
|
||
name, body = m.group(1), m.group(2)
|
||
if is_cjk_font(name) and re.search(r'w:charset w:val="02"', body):
|
||
fixed.append(name)
|
||
body = body.replace('w:charset w:val="02"', 'w:charset w:val="86"')
|
||
return f'<w:font w:name="{name}">{body}</w:font>'
|
||
return re.sub(r'<w:font w:name="([^"]+)">(.*?)</w:font>', repl, xml, flags=re.S), fixed
|
||
|
||
def main(src, dst):
|
||
with zipfile.ZipFile(src) as zin, zipfile.ZipFile(dst, "w", zipfile.ZIP_DEFLATED) as zout:
|
||
for item in zin.infolist():
|
||
data = zin.read(item.filename)
|
||
if item.filename == "word/fontTable.xml":
|
||
xml, fixed = fix_font_table(data.decode("utf-8"))
|
||
data = xml.encode("utf-8")
|
||
print("fixed:", fixed)
|
||
zout.writestr(item, data)
|
||
|
||
if __name__ == "__main__":
|
||
main(sys.argv[1], sys.argv[2])
|