45 lines
1.8 KiB
Python
45 lines
1.8 KiB
Python
"""MarkdownSplitter 边界测试."""
|
|
import pytest
|
|
|
|
from src.core.splitters import MarkdownSplitter
|
|
|
|
|
|
class TestMarkdownSplitterEdgeCases:
|
|
"""Markdown 分块边界情况."""
|
|
|
|
@pytest.fixture
|
|
def splitter(self):
|
|
return MarkdownSplitter(max_size=1000, overlap=100)
|
|
|
|
def test_no_headings_document(self, splitter):
|
|
"""无标题文档正常分块."""
|
|
md = "这是一段没有标题的纯文本。\n\n第二段内容。"
|
|
chunks = splitter.split(md, source_file="nohead.md")
|
|
assert len(chunks) >= 1
|
|
|
|
def test_deep_headings(self, splitter):
|
|
"""h4-h6 深层标题."""
|
|
md = "# 一级\n## 二级\n### 三级\n#### 四级\n内容在这里。\n##### 五级\n更多内容。\n###### 六级\n最深的内容。"
|
|
chunks = splitter.split(md, source_file="deep.md")
|
|
assert len(chunks) >= 1
|
|
|
|
def test_hash_in_code_block_not_heading(self, splitter):
|
|
"""代码块中的 # 号不被误识别为标题."""
|
|
md = "# 真实标题\n这是内容。\n```python\n# 这不是标题，是注释\nx = 1\n## 这也不是标题\n```\n更多内容。"
|
|
chunks = splitter.split(md, source_file="codehash.md")
|
|
section_titles = [c.get("section_title", "") for c in chunks]
|
|
for title in section_titles:
|
|
assert "不是标题" not in title
|
|
|
|
def test_adjacent_headings_empty_content(self, splitter):
|
|
"""标题后紧接标题（空内容）."""
|
|
md = "# 标题 A\n# 标题 B\n内容 B。"
|
|
chunks = splitter.split(md, source_file="adjacent.md")
|
|
assert len(chunks) >= 1
|
|
|
|
def test_only_headings_no_content(self, splitter):
|
|
"""仅有标题无正文."""
|
|
md = "# 只有标题\n## 没有内容"
|
|
chunks = splitter.split(md, source_file="headingsonly.md")
|
|
assert isinstance(chunks, list)
|