test: 添加全面的测试套件，覆盖所有 Reader 实现
- 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。
This commit is contained in:
87
tests/test_cli/conftest.py
Normal file
87
tests/test_cli/conftest.py
Normal file
@@ -0,0 +1,87 @@
|
||||
"""CLI 测试专用 fixtures。"""
|
||||
|
||||
import pytest
|
||||
import sys
|
||||
from io import StringIO
|
||||
from contextlib import redirect_stdout, redirect_stderr
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def cli_runner():
|
||||
"""CLI 运行器 fixture，用于调用 main() 函数并捕获输出。
|
||||
|
||||
Returns:
|
||||
function: 接受 args 列表，返回 (stdout, stderr, exit_code) 元组
|
||||
"""
|
||||
def _run_cli(args):
|
||||
"""运行 CLI 并捕获输出。
|
||||
|
||||
Args:
|
||||
args: 命令行参数列表（不包含程序名）
|
||||
|
||||
Returns:
|
||||
tuple: (stdout, stderr, exit_code)
|
||||
"""
|
||||
from scripts.lyxy_document_reader import main
|
||||
|
||||
# 保存原始 sys.argv 和 sys.exit
|
||||
original_argv = sys.argv
|
||||
original_exit = sys.exit
|
||||
|
||||
stdout_capture = StringIO()
|
||||
stderr_capture = StringIO()
|
||||
exit_code = 0
|
||||
|
||||
def mock_exit(code=0):
|
||||
nonlocal exit_code
|
||||
exit_code = code
|
||||
raise SystemExit(code)
|
||||
|
||||
try:
|
||||
# 设置命令行参数
|
||||
sys.argv = ['lyxy_document_reader'] + args
|
||||
sys.exit = mock_exit
|
||||
|
||||
# 捕获输出
|
||||
with redirect_stdout(stdout_capture), redirect_stderr(stderr_capture):
|
||||
try:
|
||||
main()
|
||||
except SystemExit:
|
||||
pass
|
||||
|
||||
finally:
|
||||
# 恢复原始状态
|
||||
sys.argv = original_argv
|
||||
sys.exit = original_exit
|
||||
|
||||
return stdout_capture.getvalue(), stderr_capture.getvalue(), exit_code
|
||||
|
||||
return _run_cli
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def temp_test_file(tmp_path, temp_docx, temp_pdf, temp_html, temp_pptx, temp_xlsx):
|
||||
"""根据格式类型创建临时测试文件的 fixture 工厂。
|
||||
|
||||
Args:
|
||||
format_type: 文件格式类型 ('docx', 'pdf', 'html', 'pptx', 'xlsx')
|
||||
**kwargs: 传递给对应 fixture 的参数
|
||||
|
||||
Returns:
|
||||
str: 临时文件路径
|
||||
"""
|
||||
def _create_file(format_type, **kwargs):
|
||||
if format_type == 'docx':
|
||||
return temp_docx(**kwargs)
|
||||
elif format_type == 'pdf':
|
||||
return temp_pdf(**kwargs)
|
||||
elif format_type == 'html':
|
||||
return temp_html(**kwargs)
|
||||
elif format_type == 'pptx':
|
||||
return temp_pptx(**kwargs)
|
||||
elif format_type == 'xlsx':
|
||||
return temp_xlsx(**kwargs)
|
||||
else:
|
||||
raise ValueError(f"不支持的格式类型: {format_type}")
|
||||
|
||||
return _create_file
|
||||
201
tests/test_cli/test_main.py
Normal file
201
tests/test_cli/test_main.py
Normal file
@@ -0,0 +1,201 @@
|
||||
"""测试 CLI 主函数功能。"""
|
||||
|
||||
import pytest
|
||||
import os
|
||||
|
||||
|
||||
class TestCLIDefaultOutput:
|
||||
"""测试 CLI 默认输出功能。"""
|
||||
|
||||
def test_default_output_docx(self, cli_runner, temp_docx):
|
||||
"""测试默认输出 DOCX 文件的 Markdown 内容。"""
|
||||
file_path = temp_docx(paragraphs=["测试内容段落"])
|
||||
|
||||
stdout, stderr, exit_code = cli_runner([file_path])
|
||||
|
||||
assert exit_code == 0
|
||||
assert "测试内容段落" in stdout
|
||||
assert len(stdout.strip()) > 0
|
||||
|
||||
def test_default_output_pdf(self, cli_runner, temp_pdf):
|
||||
"""测试默认输出 PDF 文件的 Markdown 内容。"""
|
||||
file_path = temp_pdf(text="PDF测试内容")
|
||||
|
||||
stdout, stderr, exit_code = cli_runner([file_path])
|
||||
|
||||
assert exit_code == 0
|
||||
# PDF 解析可能有格式差异，只验证有输出
|
||||
assert len(stdout.strip()) > 0
|
||||
|
||||
def test_default_output_html(self, cli_runner, temp_html):
|
||||
"""测试默认输出 HTML 文件的 Markdown 内容。"""
|
||||
file_path = temp_html(content="<h1>HTML标题</h1><p>HTML内容</p>")
|
||||
|
||||
stdout, stderr, exit_code = cli_runner([file_path])
|
||||
|
||||
assert exit_code == 0
|
||||
assert "HTML标题" in stdout or "HTML内容" in stdout
|
||||
|
||||
|
||||
class TestCLICountOption:
|
||||
"""测试 CLI 字数统计功能。"""
|
||||
|
||||
def test_count_option(self, cli_runner, temp_docx):
|
||||
"""测试 -c 选项统计字数。"""
|
||||
file_path = temp_docx(paragraphs=["测试内容"])
|
||||
|
||||
stdout, stderr, exit_code = cli_runner([file_path, "-c"])
|
||||
|
||||
assert exit_code == 0
|
||||
# 输出应该是一个数字
|
||||
assert stdout.strip().isdigit()
|
||||
count = int(stdout.strip())
|
||||
assert count > 0
|
||||
|
||||
def test_count_option_long_form(self, cli_runner, temp_docx):
|
||||
"""测试 --count 选项。"""
|
||||
file_path = temp_docx(paragraphs=["测试"])
|
||||
|
||||
stdout, stderr, exit_code = cli_runner([file_path, "--count"])
|
||||
|
||||
assert exit_code == 0
|
||||
assert stdout.strip().isdigit()
|
||||
|
||||
|
||||
class TestCLILinesOption:
|
||||
"""测试 CLI 行数统计功能。"""
|
||||
|
||||
def test_lines_option(self, cli_runner, temp_docx):
|
||||
"""测试 -l 选项统计行数。"""
|
||||
file_path = temp_docx(paragraphs=["第一行", "第二行", "第三行"])
|
||||
|
||||
stdout, stderr, exit_code = cli_runner([file_path, "-l"])
|
||||
|
||||
assert exit_code == 0
|
||||
# 输出应该是一个数字
|
||||
assert stdout.strip().isdigit()
|
||||
lines = int(stdout.strip())
|
||||
assert lines > 0
|
||||
|
||||
|
||||
class TestCLITitlesOption:
|
||||
"""测试 CLI 标题提取功能。"""
|
||||
|
||||
def test_titles_option(self, cli_runner, temp_docx):
|
||||
"""测试 -t 选项提取标题。"""
|
||||
file_path = temp_docx(
|
||||
headings=[(1, "一级标题"), (2, "二级标题")],
|
||||
paragraphs=["普通段落"]
|
||||
)
|
||||
|
||||
stdout, stderr, exit_code = cli_runner([file_path, "-t"])
|
||||
|
||||
assert exit_code == 0
|
||||
# 输出应该包含标题
|
||||
assert "一级标题" in stdout
|
||||
assert "二级标题" in stdout
|
||||
# 不应该包含普通段落
|
||||
assert "普通段落" not in stdout
|
||||
|
||||
|
||||
class TestCLITitleContentOption:
|
||||
"""测试 CLI 标题内容提取功能。"""
|
||||
|
||||
def test_title_content_option(self, cli_runner, temp_docx):
|
||||
"""测试 -tc 选项提取标题内容。"""
|
||||
file_path = temp_docx(
|
||||
headings=[(1, "目标标题")],
|
||||
paragraphs=["标题下的内容"]
|
||||
)
|
||||
|
||||
stdout, stderr, exit_code = cli_runner([file_path, "-tc", "目标标题"])
|
||||
|
||||
assert exit_code == 0
|
||||
assert "目标标题" in stdout
|
||||
assert "标题下的内容" in stdout
|
||||
|
||||
def test_title_content_not_found(self, cli_runner, temp_docx):
|
||||
"""测试标题不存在时的错误处理。"""
|
||||
file_path = temp_docx(paragraphs=["测试内容"])
|
||||
|
||||
stdout, stderr, exit_code = cli_runner([file_path, "-tc", "不存在的标题"])
|
||||
|
||||
assert exit_code != 0
|
||||
# 应该输出错误信息
|
||||
output = stdout + stderr
|
||||
assert "未找到" in output or "不存在" in output or "错误" in output
|
||||
|
||||
|
||||
class TestCLISearchOption:
|
||||
"""测试 CLI 搜索功能。"""
|
||||
|
||||
def test_search_option(self, cli_runner, temp_docx):
|
||||
"""测试 -s 选项搜索内容。"""
|
||||
file_path = temp_docx(paragraphs=["包含关键词的段落", "其他内容"])
|
||||
|
||||
stdout, stderr, exit_code = cli_runner([file_path, "-s", "关键词"])
|
||||
|
||||
assert exit_code == 0
|
||||
assert "关键词" in stdout
|
||||
|
||||
def test_search_no_match(self, cli_runner, temp_docx):
|
||||
"""测试搜索无匹配时的错误处理。"""
|
||||
file_path = temp_docx(paragraphs=["测试内容"])
|
||||
|
||||
stdout, stderr, exit_code = cli_runner([file_path, "-s", "不存在的内容"])
|
||||
|
||||
assert exit_code != 0
|
||||
# 应该输出错误信息
|
||||
output = stdout + stderr
|
||||
assert "未找到" in output or "无匹配" in output or "错误" in output
|
||||
|
||||
def test_search_with_context(self, cli_runner, temp_docx):
|
||||
"""测试 -n 选项设置上下文行数。"""
|
||||
file_path = temp_docx(
|
||||
paragraphs=["第一行", "第二行", "包含关键词的行", "第四行", "第五行"]
|
||||
)
|
||||
|
||||
stdout, stderr, exit_code = cli_runner([file_path, "-s", "关键词", "-n", "2"])
|
||||
|
||||
assert exit_code == 0
|
||||
assert "关键词" in stdout
|
||||
# 应该包含上下文
|
||||
assert "第二行" in stdout or "第四行" in stdout
|
||||
|
||||
|
||||
class TestCLIErrorHandling:
|
||||
"""测试 CLI 错误处理。"""
|
||||
|
||||
def test_file_not_exists(self, cli_runner, tmp_path):
|
||||
"""测试文件不存在时的错误处理。"""
|
||||
non_existent = str(tmp_path / "non_existent.docx")
|
||||
|
||||
stdout, stderr, exit_code = cli_runner([non_existent])
|
||||
|
||||
assert exit_code != 0
|
||||
output = stdout + stderr
|
||||
assert "错误" in output or "不存在" in output
|
||||
|
||||
def test_unsupported_format(self, cli_runner, tmp_path):
|
||||
"""测试不支持的文件类型。"""
|
||||
unsupported_file = tmp_path / "test.xyz"
|
||||
unsupported_file.write_text("test content")
|
||||
|
||||
stdout, stderr, exit_code = cli_runner([str(unsupported_file)])
|
||||
|
||||
assert exit_code != 0
|
||||
output = stdout + stderr
|
||||
assert "reader" in output.lower() or "支持" in output
|
||||
|
||||
def test_all_readers_failed(self, cli_runner, tmp_path):
|
||||
"""测试所有 Reader 失败时的错误输出。"""
|
||||
# 创建一个看起来像 DOCX 但实际损坏的文件
|
||||
fake_docx = tmp_path / "fake.docx"
|
||||
fake_docx.write_bytes(b"not a real docx file")
|
||||
|
||||
stdout, stderr, exit_code = cli_runner([str(fake_docx)])
|
||||
|
||||
assert exit_code != 0
|
||||
output = stdout + stderr
|
||||
# 应该列出失败原因
|
||||
assert "失败" in output or "错误" in output
|
||||
Reference in New Issue
Block a user