50 lines
1.6 KiB
Python
50 lines
1.6 KiB
Python
"""PDFSplitter 测试."""
|
||
import pytest
|
||
from pathlib import Path
|
||
|
||
pymupdf = pytest.importorskip("fitz", reason="pymupdf 未安装")
|
||
|
||
|
||
class TestPDFSplitter:
|
||
"""PDFSplitter 测试（需 pymupdf）."""
|
||
|
||
def test_split_simple_pdf(self, tmp_path):
|
||
"""用 pymupdf 创建一个简单 PDF 并测试分块."""
|
||
from src.core.splitters.pdf import PDFSplitter
|
||
import fitz
|
||
|
||
pdf_path = tmp_path / "test.pdf"
|
||
doc = fitz.open()
|
||
# 插入纯 ASCII 文本避免 CJK 字体编码问题
|
||
doc.new_page().insert_text((72, 72), "This is PDF document content.\n\nSecond paragraph text.")
|
||
doc.save(str(pdf_path))
|
||
doc.close()
|
||
|
||
s = PDFSplitter(max_size=500)
|
||
chunks = s.split(str(pdf_path), source_file="test.pdf")
|
||
assert len(chunks) >= 1
|
||
all_text = "".join(c["content"] for c in chunks)
|
||
assert "PDF document" in all_text
|
||
assert "Second paragraph" in all_text
|
||
|
||
def test_empty_pdf(self, tmp_path):
|
||
"""空 PDF（有页但无文字）返回空列表."""
|
||
from src.core.splitters.pdf import PDFSplitter
|
||
import fitz
|
||
|
||
pdf_path = tmp_path / "empty.pdf"
|
||
doc = fitz.open()
|
||
doc.new_page() # pymupdf 必须有至少一页才能保存
|
||
doc.save(str(pdf_path))
|
||
doc.close()
|
||
|
||
s = PDFSplitter()
|
||
chunks = s.split(str(pdf_path), source_file="empty.pdf")
|
||
assert chunks == []
|
||
|
||
def test_pdf_has_split_method(self):
|
||
"""PDFSplitter 遵循 Splitter Protocol."""
|
||
from src.core.splitters.pdf import PDFSplitter
|
||
s = PDFSplitter()
|
||
assert hasattr(s, "split")
|