From f8ec682474c38f6c761c24ae75b193f8f70fb4a8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E5=88=98=E8=88=AA=E5=AE=87?= <3364451258@qq.com>
Date: Fri, 10 Jul 2026 15:29:10 +0800
Subject: [PATCH] =?UTF-8?q?test:=20=E6=8F=90=E5=8F=96=20MarkdownSplitter?=
 =?UTF-8?q?=20=E8=BE=B9=E7=95=8C=E6=B5=8B=E8=AF=95=E5=88=B0=E7=8B=AC?=
 =?UTF-8?q?=E7=AB=8B=E6=96=87=E4=BB=B6?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 tests/test_splitters_markdown.py | 43 ++++++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)
 create mode 100644 tests/test_splitters_markdown.py

diff --git a/tests/test_splitters_markdown.py b/tests/test_splitters_markdown.py
new file mode 100644
index 0000000..513f462
--- /dev/null
+++ b/tests/test_splitters_markdown.py
@@ -0,0 +1,43 @@
+"""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)