lanyuanxiaoyao
9daff73589
- 更新 openspec/config.yaml 中 git 任务相关说明 - 将 scripts.core.* 改为 core.*，scripts.readers.* 改为 readers.* - 优化 lyxy_document_reader.py 中 sys.path 设置方式 - 同步更新所有测试文件的导入路径
80 lines
2.8 KiB
Python
80 lines
2.8 KiB
Python
"""测试 MarkItDown DOCX Reader 的解析功能。"""
|
||
|
||
import pytest
|
||
import os
|
||
from readers.docx import markitdown
|
||
|
||
|
||
class TestMarkitdownDocxReaderParse:
|
||
"""测试 MarkItDown DOCX Reader 的 parse 方法。"""
|
||
|
||
def test_normal_file(self, temp_docx):
|
||
"""测试正常 DOCX 文件解析。"""
|
||
# 创建包含多种内容的测试文件
|
||
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 = markitdown.parse(file_path)
|
||
|
||
# 验证解析成功
|
||
if content is not None:
|
||
# 验证关键内容存在（MarkItDown 可能有不同的格式化方式）
|
||
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 = markitdown.parse(non_existent_file)
|
||
|
||
# 验证返回 None 和错误信息
|
||
assert content is None
|
||
assert error is not None
|
||
|
||
def test_empty_file(self, temp_docx):
|
||
"""测试空 DOCX 文件。"""
|
||
# 创建没有任何内容的文件
|
||
file_path = temp_docx()
|
||
|
||
content, error = markitdown.parse(file_path)
|
||
|
||
# 空文件可能返回 None 或空字符串
|
||
assert content is None or content.strip() == ""
|
||
|
||
def test_corrupted_file(self, temp_docx, tmp_path):
|
||
"""测试损坏的 DOCX 文件。"""
|
||
# 先创建正常文件
|
||
file_path = temp_docx(paragraphs=["测试内容"])
|
||
|
||
# 破坏文件内容
|
||
with open(file_path, "wb") as f:
|
||
f.write(b"corrupted content that is not a valid docx file")
|
||
|
||
content, error = markitdown.parse(file_path)
|
||
|
||
# MarkItDown 可能会尝试解析任何内容,所以不强制要求返回 None
|
||
# 只验证它不会崩溃
|
||
assert content is not None or error is not 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: ©®™°±",
|
||
"混合内容: Hello你好🎉World世界",
|
||
"阿拉伯文: مرحبا", # RTL 文本
|
||
]
|
||
|
||
file_path = temp_docx(paragraphs=special_texts)
|
||
|
||
content, error = markitdown.parse(file_path)
|
||
|
||
# 如果解析成功，验证特殊字符处理
|
||
if content is not None:
|
||
assert "中文测试内容" in content or "😀" in content or "Hello你好" in content
|