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>
This commit is contained in:
@@ -9,7 +9,7 @@ DOCX 文档解析能力,支持多种解析方法。
|
||||
|
||||
#### Scenario: 按优先级尝试解析器
|
||||
- **WHEN** 解析 DOCX 文档
|
||||
- **THEN** 系统按 docling → unstructured → markitdown → pypandoc-binary → python-docx → XML原生解析的顺序尝试
|
||||
- **THEN** 系统按 docling → unstructured → pypandoc-binary → MarkItDown → LibreOffice → python-docx → XML原生解析的顺序尝试
|
||||
|
||||
#### Scenario: 成功解析
|
||||
- **WHEN** 任一解析器成功
|
||||
@@ -85,6 +85,25 @@ DOCX 文档解析能力,支持多种解析方法。
|
||||
- **WHEN** XML 原生解析失败
|
||||
- **THEN** 系统返回失败信息
|
||||
|
||||
### Requirement: LibreOffice 解析器
|
||||
系统 SHALL 支持使用 LibreOffice soffice 命令行解析 DOCX。
|
||||
|
||||
#### Scenario: LibreOffice 解析成功
|
||||
- **WHEN** soffice 可用且文档有效
|
||||
- **THEN** 系统返回 Markdown 内容
|
||||
|
||||
#### Scenario: LibreOffice 未安装
|
||||
- **WHEN** soffice 未在 PATH 中
|
||||
- **THEN** 系统尝试下一个解析器
|
||||
|
||||
#### Scenario: LibreOffice 转换超时
|
||||
- **WHEN** soffice 执行超过 60 秒
|
||||
- **THEN** 系统返回超时错误并尝试下一个解析器
|
||||
|
||||
#### Scenario: LibreOffice 转换失败
|
||||
- **WHEN** soffice 返回非零退出码
|
||||
- **THEN** 系统返回失败信息并尝试下一个解析器
|
||||
|
||||
### Requirement: 每个解析器独立文件
|
||||
系统 SHALL 将每个解析器实现为独立的单文件模块。
|
||||
|
||||
@@ -111,3 +130,7 @@ DOCX 文档解析能力,支持多种解析方法。
|
||||
#### Scenario: XML 原生解析器在独立文件
|
||||
- **WHEN** 使用 XML 原生解析器
|
||||
- **THEN** 从 readers/docx/native_xml.py 导入
|
||||
|
||||
#### Scenario: LibreOffice 解析器在独立文件
|
||||
- **WHEN** 使用 LibreOffice 解析器
|
||||
- **THEN** 从 readers/docx/libreoffice.py 导入
|
||||
|
||||
@@ -10,6 +10,7 @@ from . import docling
|
||||
from . import unstructured
|
||||
from . import markitdown
|
||||
from . import pypandoc
|
||||
from . import libreoffice
|
||||
from . import python_docx
|
||||
from . import native_xml
|
||||
|
||||
@@ -19,6 +20,7 @@ PARSERS = [
|
||||
("unstructured", unstructured.parse),
|
||||
("pypandoc-binary", pypandoc.parse),
|
||||
("MarkItDown", markitdown.parse),
|
||||
("LibreOffice", libreoffice.parse),
|
||||
("python-docx", python_docx.parse),
|
||||
("XML 原生解析", native_xml.parse),
|
||||
]
|
||||
|
||||
67
scripts/readers/docx/libreoffice.py
Normal file
67
scripts/readers/docx/libreoffice.py
Normal file
@@ -0,0 +1,67 @@
|
||||
"""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
|
||||
55
tests/test_readers/test_docx/test_libreoffice.py
Normal file
55
tests/test_readers/test_docx/test_libreoffice.py
Normal file
@@ -0,0 +1,55 @@
|
||||
"""测试 LibreOffice DOCX Reader 的解析功能。"""
|
||||
|
||||
import pytest
|
||||
import os
|
||||
from readers.docx import libreoffice
|
||||
|
||||
|
||||
class TestLibreOfficeDocxReaderParse:
|
||||
"""测试 LibreOffice DOCX Reader 的 parse 方法。"""
|
||||
|
||||
def test_normal_file(self, temp_docx):
|
||||
"""测试正常 DOCX 文件解析。"""
|
||||
file_path = temp_docx(
|
||||
headings=[(1, "主标题"), (2, "子标题")],
|
||||
paragraphs=["这是第一段内容。", "这是第二段内容。"],
|
||||
table_data=[["列1", "列2"], ["数据1", "数据2"]],
|
||||
list_items=["列表项1", "列表项2"]
|
||||
)
|
||||
|
||||
content, error = libreoffice.parse(file_path)
|
||||
|
||||
assert content is not None, f"解析失败: {error}"
|
||||
assert "主标题" in content or "子标题" in content or "第一段内容" in content
|
||||
|
||||
def test_file_not_exists(self, tmp_path):
|
||||
"""测试文件不存在的情况。"""
|
||||
non_existent_file = str(tmp_path / "non_existent.docx")
|
||||
content, error = libreoffice.parse(non_existent_file)
|
||||
assert content is None
|
||||
assert error is not None
|
||||
|
||||
def test_empty_file(self, temp_docx):
|
||||
"""测试空 DOCX 文件。"""
|
||||
file_path = temp_docx()
|
||||
content, error = libreoffice.parse(file_path)
|
||||
# 空文件可能返回 None 或空字符串
|
||||
if content is not None:
|
||||
assert content.strip() == ""
|
||||
|
||||
def test_corrupted_file(self, temp_docx, tmp_path):
|
||||
"""测试损坏的 DOCX 文件。"""
|
||||
file_path = temp_docx(paragraphs=["测试内容"])
|
||||
with open(file_path, "wb") as f:
|
||||
f.write(b"corrupted content")
|
||||
content, error = libreoffice.parse(file_path)
|
||||
# LibreOffice 太健壮了,即使是损坏的文件也可能解析出内容
|
||||
# 所以这里不强制断言 content 是 None
|
||||
|
||||
def test_special_chars(self, temp_docx):
|
||||
"""测试特殊字符处理。"""
|
||||
special_texts = ["中文测试内容", "Emoji测试: 😀🎉🚀", "特殊符号: ©®™°±"]
|
||||
file_path = temp_docx(paragraphs=special_texts)
|
||||
content, error = libreoffice.parse(file_path)
|
||||
if content is not None:
|
||||
assert "中文测试内容" in content or "😀" in content
|
||||
Reference in New Issue
Block a user