feat: 新增 DocxSplitter — 支持 .docx 文档入库

tests/test_splitters_docx.py

@@ -0,0 +1,53 @@
+"""DocxSplitter 测试."""
+import pytest
+
+pytest.importorskip("markitdown", reason="需要 markitdown 库")
+
+from src.core.splitters.docx import DocxSplitter
+
+
+def test_docx_splitter_creates():
+    """创建 DocxSplitter 实例."""
+    s = DocxSplitter(max_size=500, overlap=50)
+    assert s is not None
+
+
+def test_docx_splitter_empty_text():
+    """空纯文本返回空列表."""
+    s = DocxSplitter()
+    result = s.split("   ", source_file="empty.docx")
+    assert result == []
+
+
+def test_docx_splitter_basic_text():
+    """基本文本文档分块."""
+    s = DocxSplitter(max_size=200, overlap=20)
+    text = "段落A。\n\n段落B。\n\n段落C。"
+    result = s.split(text, source_file="test.docx")
+    assert len(result) >= 1
+    assert all("content" in r for r in result)
+    assert all(r["source_file"] == "test.docx" for r in result)
+
+
+def test_docx_splitter_long_text():
+    """长文本分多块."""
+    s = DocxSplitter(max_size=100, overlap=10)
+    text = "这是一段非常长的文本。\n\n" * 50
+    result = s.split(text, source_file="long.docx")
+    assert len(result) >= 5
+
+
+def test_docx_splitter_source_file():
+    """source_file 正确传递到每个 chunk."""
+    s = DocxSplitter(max_size=500, overlap=50)
+    result = s.split("测试内容。", source_file="myfile.docx")
+    assert all(r["source_file"] == "myfile.docx" for r in result)
+
+
+def test_docx_splitter_chunk_index():
+    """chunk_index 从 0 递增."""
+    s = DocxSplitter(max_size=100, overlap=10)
+    text = "chunk A。\n\n" * 20
+    result = s.split(text, source_file="index.docx")
+    indices = [r["chunk_index"] for r in result]
+    assert indices == list(range(len(result)))