lanyuanxiaoyao
0dd7aa221c
- 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>
56 lines
2.2 KiB
Python
56 lines
2.2 KiB
Python
"""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
|