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
36 lines
1.4 KiB
Python
36 lines
1.4 KiB
Python
"""测试 MarkItDown HTML Reader 的解析功能。"""
|
|
|
|
import pytest
|
|
from readers.html import markitdown
|
|
|
|
|
|
class TestMarkitdownHtmlReaderParse:
|
|
"""测试 MarkItDown HTML Reader 的 parse 方法。"""
|
|
|
|
def test_normal_file(self, temp_html):
|
|
"""测试正常 HTML 文件解析。"""
|
|
file_path = temp_html(content="<h1>标题</h1><p>段落内容</p>")
|
|
content, error = markitdown.parse(file_path)
|
|
if content is not None:
|
|
assert "标题" in content or "段落" in content
|
|
|
|
def test_file_not_exists(self, tmp_path):
|
|
"""测试文件不存在的情况。"""
|
|
non_existent_path = str(tmp_path / "non_existent.html")
|
|
content, error = markitdown.parse(non_existent_path)
|
|
# markitdown 库自己会处理文件不存在的情况
|
|
assert content is None or error is not None
|
|
|
|
def test_empty_file(self, temp_html):
|
|
"""测试空 HTML 文件。"""
|
|
file_path = temp_html(content="<html><body></body></html>")
|
|
content, error = markitdown.parse(file_path)
|
|
assert content is None or content.strip() == ""
|
|
|
|
def test_special_chars(self, temp_html):
|
|
"""测试特殊字符处理。"""
|
|
file_path = temp_html(content="<p>中文测试 😀 ©®</p>")
|
|
content, error = markitdown.parse(file_path)
|
|
if content is not None:
|
|
assert "中文" in content or "测试" in content
|