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:
197
tests/test_readers/conftest.py
Normal file
197
tests/test_readers/conftest.py
Normal file
@@ -0,0 +1,197 @@
|
||||
"""Reader 测试专用 fixtures。"""
|
||||
|
||||
import pytest
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def temp_docx(tmp_path):
|
||||
"""创建临时 DOCX 文件的 fixture 工厂。
|
||||
|
||||
Args:
|
||||
paragraphs: 段落文本列表
|
||||
headings: 标题列表，格式为 [(level, text), ...]
|
||||
table_data: 表格数据，格式为 [[cell1, cell2], [cell3, cell4]]
|
||||
list_items: 列表项列表
|
||||
|
||||
Returns:
|
||||
str: 临时文件路径
|
||||
"""
|
||||
def _create_docx(paragraphs=None, headings=None, table_data=None, list_items=None):
|
||||
try:
|
||||
from docx import Document
|
||||
except ImportError:
|
||||
pytest.skip("python-docx 未安装")
|
||||
|
||||
doc = Document()
|
||||
|
||||
# 添加标题
|
||||
if headings:
|
||||
for level, text in headings:
|
||||
doc.add_heading(text, level=level)
|
||||
|
||||
# 添加段落
|
||||
if paragraphs:
|
||||
for para_text in paragraphs:
|
||||
doc.add_paragraph(para_text)
|
||||
|
||||
# 添加表格
|
||||
if table_data:
|
||||
table = doc.add_table(rows=len(table_data), cols=len(table_data[0]))
|
||||
for i, row_data in enumerate(table_data):
|
||||
for j, cell_text in enumerate(row_data):
|
||||
table.rows[i].cells[j].text = str(cell_text)
|
||||
|
||||
# 添加列表项
|
||||
if list_items:
|
||||
for item in list_items:
|
||||
doc.add_paragraph(item, style='List Bullet')
|
||||
|
||||
file_path = tmp_path / "test.docx"
|
||||
doc.save(str(file_path))
|
||||
return str(file_path)
|
||||
|
||||
return _create_docx
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def temp_pdf(tmp_path):
|
||||
"""创建临时 PDF 文件的 fixture 工厂。
|
||||
|
||||
Args:
|
||||
text: PDF 文本内容
|
||||
lines: 文本行列表
|
||||
|
||||
Returns:
|
||||
str: 临时文件路径
|
||||
"""
|
||||
def _create_pdf(text=None, lines=None):
|
||||
try:
|
||||
from reportlab.pdfgen import canvas
|
||||
from reportlab.lib.pagesizes import letter
|
||||
from reportlab.pdfbase import pdfmetrics
|
||||
from reportlab.pdfbase.ttfonts import TTFont
|
||||
except ImportError:
|
||||
pytest.skip("reportlab 未安装")
|
||||
|
||||
file_path = tmp_path / "test.pdf"
|
||||
c = canvas.Canvas(str(file_path), pagesize=letter)
|
||||
|
||||
# 尝试注册中文字体（如果可用）
|
||||
try:
|
||||
# 使用系统字体
|
||||
pdfmetrics.registerFont(TTFont('SimSun', 'simsun.ttc'))
|
||||
c.setFont('SimSun', 12)
|
||||
except:
|
||||
# 回退到默认字体
|
||||
c.setFont('Helvetica', 12)
|
||||
|
||||
y_position = 750
|
||||
|
||||
if text:
|
||||
# 单个文本块
|
||||
for line in text.split('\n'):
|
||||
c.drawString(100, y_position, line)
|
||||
y_position -= 20
|
||||
|
||||
if lines:
|
||||
# 多行文本
|
||||
for line in lines:
|
||||
c.drawString(100, y_position, line)
|
||||
y_position -= 20
|
||||
|
||||
c.save()
|
||||
return str(file_path)
|
||||
|
||||
return _create_pdf
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def temp_html(tmp_path):
|
||||
"""创建临时 HTML 文件的 fixture 工厂。
|
||||
|
||||
Args:
|
||||
content: HTML 内容字符串
|
||||
encoding: 文件编码，默认 'utf-8'
|
||||
|
||||
Returns:
|
||||
str: 临时文件路径
|
||||
"""
|
||||
def _create_html(content="<html><body><p>Test</p></body></html>", encoding='utf-8'):
|
||||
file_path = tmp_path / "test.html"
|
||||
|
||||
# 如果内容不包含完整的 HTML 结构，添加基本结构
|
||||
if not content.strip().startswith('<html'):
|
||||
content = f"<html><head><meta charset='{encoding}'></head><body>{content}</body></html>"
|
||||
|
||||
with open(file_path, 'w', encoding=encoding) as f:
|
||||
f.write(content)
|
||||
|
||||
return str(file_path)
|
||||
|
||||
return _create_html
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def temp_pptx(tmp_path):
|
||||
"""创建临时 PPTX 文件的 fixture 工厂。
|
||||
|
||||
Args:
|
||||
slides: 幻灯片内容列表，每个元素为 (title, content) 元组
|
||||
|
||||
Returns:
|
||||
str: 临时文件路径
|
||||
"""
|
||||
def _create_pptx(slides=None):
|
||||
try:
|
||||
from pptx import Presentation
|
||||
except ImportError:
|
||||
pytest.skip("python-pptx 未安装")
|
||||
|
||||
prs = Presentation()
|
||||
|
||||
if slides:
|
||||
for title, content in slides:
|
||||
slide = prs.slides.add_slide(prs.slide_layouts[1]) # Title and Content layout
|
||||
slide.shapes.title.text = title
|
||||
if content:
|
||||
text_frame = slide.shapes.placeholders[1].text_frame
|
||||
text_frame.text = content
|
||||
|
||||
file_path = tmp_path / "test.pptx"
|
||||
prs.save(str(file_path))
|
||||
return str(file_path)
|
||||
|
||||
return _create_pptx
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def temp_xlsx(tmp_path):
|
||||
"""创建临时 XLSX 文件的 fixture 工厂。
|
||||
|
||||
Args:
|
||||
data: 表格数据，格式为 [[cell1, cell2], [cell3, cell4]]
|
||||
|
||||
Returns:
|
||||
str: 临时文件路径
|
||||
"""
|
||||
def _create_xlsx(data=None):
|
||||
try:
|
||||
import pandas as pd
|
||||
except ImportError:
|
||||
pytest.skip("pandas 未安装")
|
||||
|
||||
file_path = tmp_path / "test.xlsx"
|
||||
|
||||
if data:
|
||||
df = pd.DataFrame(data)
|
||||
df.to_excel(str(file_path), index=False, header=False)
|
||||
else:
|
||||
# 创建空的 Excel 文件
|
||||
df = pd.DataFrame()
|
||||
df.to_excel(str(file_path), index=False)
|
||||
|
||||
return str(file_path)
|
||||
|
||||
return _create_xlsx
|
||||
|
||||
Reference in New Issue
Block a user