47 lines
1.8 KiB
Python
47 lines
1.8 KiB
Python
"""测试 Unstructured PDF Reader 的解析功能。"""
|
|
|
|
import pytest
|
|
from readers.pdf import unstructured
|
|
|
|
|
|
class TestUnstructuredPdfReaderParse:
|
|
"""测试 Unstructured 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.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.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.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.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.parse(file_path)
|
|
if content is not None:
|
|
# PDF 解析可能无法完美保留所有字符，只验证部分内容
|
|
# 至少应该包含一些可识别的内容（如特殊符号）
|
|
assert len(content.strip()) > 0
|