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
142 lines
5.0 KiB
Python
142 lines
5.0 KiB
Python
"""测试 python-docx Reader 的解析功能。"""
|
||
|
||
import pytest
|
||
import os
|
||
from readers.docx import DocxReader
|
||
|
||
|
||
class TestPythonDocxReaderParse:
|
||
"""测试 python-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"]
|
||
)
|
||
|
||
reader = DocxReader()
|
||
content, failures = reader.parse(file_path)
|
||
|
||
# 验证解析成功
|
||
assert content is not None, f"解析失败: {failures}"
|
||
assert len(failures) == 0 or all("成功" in f or not f for f in failures)
|
||
|
||
# 验证关键内容存在
|
||
assert "主标题" in content
|
||
assert "子标题" in content
|
||
assert "第一段内容" in content
|
||
assert "第二段内容" in content
|
||
assert "列1" in content or "列2" in content # 表格内容
|
||
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.docx")
|
||
|
||
reader = DocxReader()
|
||
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_docx):
|
||
"""测试空 DOCX 文件。"""
|
||
# 创建没有任何内容的文件
|
||
file_path = temp_docx()
|
||
|
||
reader = DocxReader()
|
||
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_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 - 完全覆盖文件
|
||
with open(file_path, "wb") as f:
|
||
f.write(b"corrupted content that is not a valid docx file")
|
||
|
||
reader = DocxReader()
|
||
content, failures = reader.parse(file_path)
|
||
|
||
# 验证返回 None 和错误信息
|
||
assert content is None
|
||
assert len(failures) > 0
|
||
|
||
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)
|
||
|
||
reader = DocxReader()
|
||
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 "😀" in content or "🎉" in content # 至少包含一个 emoji
|
||
assert "©" in content or "®" in content # 至少包含一个特殊符号
|
||
assert "Hello你好" in content or "World世界" in content
|
||
|
||
|
||
class TestPythonDocxReaderSupports:
|
||
"""测试 python-docx Reader 的 supports 方法。"""
|
||
|
||
def test_supports_docx_extension(self):
|
||
"""测试识别 .docx 扩展名。"""
|
||
reader = DocxReader()
|
||
assert reader.supports("test.docx") is True
|
||
|
||
def test_supports_uppercase_extension(self):
|
||
"""测试识别大写扩展名。"""
|
||
reader = DocxReader()
|
||
assert reader.supports("TEST.DOCX") is True
|
||
|
||
def test_supports_doc_extension(self):
|
||
"""测试 .doc 扩展名（某些 Reader 可能不支持）。"""
|
||
reader = DocxReader()
|
||
# python-docx Reader 只支持 .docx
|
||
result = reader.supports("test.doc")
|
||
# 根据实际实现，可能返回 True 或 False
|
||
|
||
def test_rejects_unsupported_format(self):
|
||
"""测试拒绝不支持的格式。"""
|
||
reader = DocxReader()
|
||
assert reader.supports("test.pdf") is False
|
||
assert reader.supports("test.txt") is False
|
||
|
||
def test_supports_url(self):
|
||
"""测试 URL 路径。"""
|
||
reader = DocxReader()
|
||
# 根据实际实现，URL 可能被支持或不支持
|
||
result = reader.supports("http://example.com/file.docx")
|
||
# 这里不做断言，因为不同 Reader 实现可能不同
|
||
|
||
def test_supports_path_with_spaces(self):
|
||
"""测试包含空格的路径。"""
|
||
reader = DocxReader()
|
||
assert reader.supports("path with spaces/test.docx") is True
|
||
|
||
def test_supports_absolute_path(self):
|
||
"""测试绝对路径。"""
|
||
reader = DocxReader()
|
||
assert reader.supports("/absolute/path/test.docx") is True
|
||
assert reader.supports("C:\\Windows\\path\\test.docx") is True
|