lanyuanxiaoyao
7eab1dcef1
- 测试数量从 83 个增加到 193 个 (+132%) - 代码覆盖率从 48% 提升到 69% (+44%) - 为每种文档格式的所有 Reader 实现创建独立测试 - 添加跨 Reader 的一致性验证测试 - 新增 4 个测试规范 (cli-testing, exception-testing, reader-testing, test-fixtures) - 更新 README 测试统计信息 测试覆盖: - DOCX: python-docx, markitdown, docling, native-xml, pypandoc, unstructured - PDF: pypdf, markitdown, docling, docling-ocr, unstructured, unstructured-ocr - HTML: html2text, markitdown, trafilatura, domscribe - PPTX: python-pptx, markitdown, docling, native-xml, unstructured - XLSX: pandas, markitdown, docling, native-xml, unstructured - CLI: 所有命令行选项和错误处理 所有 193 个测试通过。
152 lines
5.0 KiB
Python
152 lines
5.0 KiB
Python
"""测试 html2text Reader 的解析功能。"""
|
|
|
|
import pytest
|
|
import os
|
|
from scripts.readers.html import HtmlReader
|
|
|
|
|
|
class TestHtml2TextReaderParse:
|
|
"""测试 html2text Reader 的 parse 方法。"""
|
|
|
|
def test_normal_file(self, temp_html):
|
|
"""测试正常 HTML 文件解析。"""
|
|
html_content = """
|
|
<h1>主标题</h1>
|
|
<p>这是一段测试内容。</p>
|
|
<h2>子标题</h2>
|
|
<ul>
|
|
<li>列表项1</li>
|
|
<li>列表项2</li>
|
|
</ul>
|
|
<table>
|
|
<tr><td>单元格1</td><td>单元格2</td></tr>
|
|
</table>
|
|
"""
|
|
file_path = temp_html(content=html_content)
|
|
|
|
reader = HtmlReader()
|
|
content, failures = reader.parse(file_path)
|
|
|
|
# 验证解析成功
|
|
assert content is not None, f"解析失败: {failures}"
|
|
|
|
# 验证关键内容存在
|
|
assert "主标题" in content
|
|
assert "测试内容" in content
|
|
assert "子标题" in content
|
|
assert "列表项1" 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.html")
|
|
|
|
reader = HtmlReader()
|
|
content, failures = reader.parse(non_existent_file)
|
|
|
|
# 验证返回 None 和错误信息
|
|
assert content is None
|
|
assert len(failures) > 0
|
|
assert any("不存在" in f or "找不到" in f for f in failures)
|
|
|
|
def test_empty_file(self, temp_html):
|
|
"""测试空 HTML 文件。"""
|
|
file_path = temp_html(content="<html><body></body></html>")
|
|
|
|
reader = HtmlReader()
|
|
content, failures = reader.parse(file_path)
|
|
|
|
# 空文件应该返回 None 或空字符串
|
|
assert content is None or content.strip() == ""
|
|
|
|
def test_corrupted_file(self, temp_html):
|
|
"""测试损坏的 HTML 文件。"""
|
|
# HTML 解析器通常比较宽容，但我们可以测试完全无效的内容
|
|
file_path = temp_html(content="<<>>invalid<<html>>")
|
|
|
|
reader = HtmlReader()
|
|
content, failures = reader.parse(file_path)
|
|
|
|
# HTML 解析器可能仍然能解析，或返回错误
|
|
# 这里只验证不会崩溃
|
|
|
|
def test_special_chars(self, temp_html):
|
|
"""测试特殊字符处理。"""
|
|
html_content = """
|
|
<p>中文测试内容</p>
|
|
<p>Emoji测试: 😀🎉🚀</p>
|
|
<p>特殊符号: ©®™°±</p>
|
|
<p>混合内容: Hello你好🎉World世界</p>
|
|
"""
|
|
file_path = temp_html(content=html_content)
|
|
|
|
reader = HtmlReader()
|
|
content, failures = reader.parse(file_path)
|
|
|
|
assert content is not None, f"解析失败: {failures}"
|
|
|
|
# 验证各种特殊字符都被正确处理
|
|
assert "中文测试内容" in content
|
|
assert "Hello你好" in content or "World世界" in content
|
|
|
|
def test_encoding_gbk(self, temp_html):
|
|
"""测试 GBK 编码的 HTML 文件。"""
|
|
html_content = "<html><head><meta charset='gbk'></head><body><p>中文内容</p></body></html>"
|
|
file_path = temp_html(content=html_content, encoding='gbk')
|
|
|
|
reader = HtmlReader()
|
|
content, failures = reader.parse(file_path)
|
|
|
|
# 验证能够正确处理 GBK 编码
|
|
# 注意：某些 Reader 可能无法自动检测编码
|
|
if content:
|
|
assert len(content.strip()) > 0
|
|
|
|
def test_encoding_utf8_bom(self, temp_html, tmp_path):
|
|
"""测试 UTF-8 BOM 的 HTML 文件。"""
|
|
html_content = "<html><body><p>测试内容</p></body></html>"
|
|
file_path = tmp_path / "test_bom.html"
|
|
|
|
# 写入带 BOM 的 UTF-8 文件
|
|
with open(file_path, 'wb') as f:
|
|
f.write(b'\xef\xbb\xbf') # UTF-8 BOM
|
|
f.write(html_content.encode('utf-8'))
|
|
|
|
reader = HtmlReader()
|
|
content, failures = reader.parse(str(file_path))
|
|
|
|
# 验证能够正确处理 UTF-8 BOM
|
|
if content:
|
|
assert "测试内容" in content
|
|
|
|
|
|
class TestHtml2TextReaderSupports:
|
|
"""测试 html2text Reader 的 supports 方法。"""
|
|
|
|
def test_supports_html_extension(self):
|
|
"""测试识别 .html 扩展名。"""
|
|
reader = HtmlReader()
|
|
assert reader.supports("test.html") is True
|
|
|
|
def test_supports_htm_extension(self):
|
|
"""测试识别 .htm 扩展名。"""
|
|
reader = HtmlReader()
|
|
assert reader.supports("test.htm") is True
|
|
|
|
def test_supports_uppercase_extension(self):
|
|
"""测试识别大写扩展名。"""
|
|
reader = HtmlReader()
|
|
assert reader.supports("TEST.HTML") is True
|
|
|
|
def test_supports_url(self):
|
|
"""测试 URL。"""
|
|
reader = HtmlReader()
|
|
# HTML Reader 通常支持 URL
|
|
result = reader.supports("http://example.com/page.html")
|
|
# 根据实际实现可能返回 True
|
|
|
|
def test_rejects_unsupported_format(self):
|
|
"""测试拒绝不支持的格式。"""
|
|
reader = HtmlReader()
|
|
assert reader.supports("test.pdf") is False
|
|
assert reader.supports("test.docx") is False
|