Files
lyxy-document/scripts/readers/docx/libreoffice.py
lanyuanxiaoyao 0dd7aa221c feat: 新增 LibreOffice soffice DOCX 解析器
- 新增 scripts/readers/docx/libreoffice.py
- 在 MarkItDown 之后、python-docx 之前插入解析器
- 新增 tests/test_readers/test_docx/test_libreoffice.py
- 更新 openspec/specs/docx-reader/spec.md

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-15 22:04:39 +08:00

68 lines
2.0 KiB
Python

"""使用 LibreOffice soffice 命令行解析 DOCX 文件"""
import subprocess
import tempfile
import shutil
from pathlib import Path
from typing import Optional, Tuple
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
"""使用 LibreOffice soffice 解析 DOCX 文件"""
# 检测 soffice 是否在 PATH 中
soffice_path = shutil.which("soffice")
if not soffice_path:
return None, "LibreOffice 未安装"
# 创建临时输出目录
with tempfile.TemporaryDirectory() as temp_dir:
temp_path = Path(temp_dir)
input_path = Path(file_path)
expected_output = temp_path / (input_path.stem + ".md")
# 构建命令
cmd = [
soffice_path,
"--headless",
"--convert-to", "md",
"--outdir", str(temp_path),
str(input_path)
]
# 执行命令,超时 60 秒
try:
result = subprocess.run(
cmd,
capture_output=True,
text=True,
timeout=60
)
except subprocess.TimeoutExpired:
return None, "LibreOffice 转换超时 (60秒)"
# 检查返回码
if result.returncode != 0:
return None, f"LibreOffice 转换失败 (code: {result.returncode})"
# 检查输出文件是否存在
output_file = None
if expected_output.exists():
output_file = expected_output
else:
# Fallback: 遍历目录找任意 .md 文件
md_files = list(temp_path.glob("*.md"))
if md_files:
output_file = md_files[0]
if not output_file:
return None, "LibreOffice 未生成输出文件"
# 读取输出内容
content = output_file.read_text(encoding="utf-8", errors="replace")
content = content.strip()
if not content:
return None, "LibreOffice 输出为空"
return content, None