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。
45 lines
1.7 KiB
Python
45 lines
1.7 KiB
Python
"""测试 Unstructured OCR PDF Reader 的解析功能。"""
|
|
|
|
import pytest
|
|
from scripts.readers.pdf import unstructured_ocr
|
|
|
|
|
|
class TestUnstructuredOcrPdfReaderParse:
|
|
"""测试 Unstructured OCR PDF Reader 的 parse 方法。"""
|
|
|
|
def test_normal_file(self, temp_pdf):
|
|
"""测试正常 PDF 文件解析。"""
|
|
file_path = temp_pdf(text="测试PDF内容\n第二行内容")
|
|
content, error = unstructured_ocr.parse(file_path)
|
|
if content is not None:
|
|
assert "测试" in content or "PDF" in content or "内容" 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.pdf")
|
|
content, error = unstructured_ocr.parse(non_existent_file)
|
|
assert content is None
|
|
assert error is not None
|
|
|
|
def test_empty_file(self, temp_pdf):
|
|
"""测试空 PDF 文件。"""
|
|
file_path = temp_pdf()
|
|
content, error = unstructured_ocr.parse(file_path)
|
|
assert content is None or content.strip() == ""
|
|
|
|
def test_corrupted_file(self, temp_pdf, tmp_path):
|
|
"""测试损坏的 PDF 文件。"""
|
|
file_path = temp_pdf(text="测试内容")
|
|
with open(file_path, "wb") as f:
|
|
f.write(b"corrupted content")
|
|
content, error = unstructured_ocr.parse(file_path)
|
|
assert content is None
|
|
assert error is not None
|
|
|
|
def test_special_chars(self, temp_pdf):
|
|
"""测试特殊字符处理。"""
|
|
file_path = temp_pdf(text="中文测试\nEmoji: 😀\n特殊符号: ©®")
|
|
content, error = unstructured_ocr.parse(file_path)
|
|
if content is not None:
|
|
assert "中文" in content or "测试" in content
|