From 788f610d3f900830ec37e92319adf07afd94546a 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 15:28:13 +0800
Subject: [PATCH] =?UTF-8?q?test:=20=E4=BF=AE=E5=A4=8D=20EPUB=20=E7=BC=BA?=
 =?UTF-8?q?=E5=A4=B1=E4=BE=9D=E8=B5=96=E6=B5=8B=E8=AF=95=E8=AE=BE=E8=AE=A1?=
 =?UTF-8?q?=E9=97=AE=E9=A2=98?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 README.md                    | 14 +++++++++++---
 tests/test_splitters_epub.py | 28 ++++++++++++++++++++--------
 2 files changed, 31 insertions(+), 11 deletions(-)

diff --git a/README.md b/README.md
index cb1fc9d..f2bc35b 100644
--- a/README.md
+++ b/README.md
@@ -224,7 +224,15 @@ md-vector-db/
 │   │   ├── db.py            # ChromaDB 封装（线程安全）
 │   │   ├── embedder.py      # 嵌入器（Local/OpenAI/Dashscope）
 │   │   ├── ingest.py        # 混合分块 + 入库
-│   │   └── search.py        # 语义检索
+│   │   ├── search.py        # 语义检索
+│   │   └── splitters/       # 文档分块器包
+│   │       ├── base.py      # Splitter(Protocol) + BaseTextSplitter(ABC)
+│   │       ├── markdown.py  # MarkdownSplitter
+│   │       ├── text.py      # TextSplitter
+│   │       ├── pdf.py       # PDFSplitter
+│   │       ├── html.py      # HTMLSplitter
+│   │       ├── epub.py      # EPUBSplitter
+│   │       └── registry.py  # 扩展名 → Splitter 自动选择
 │   ├── server/              # FastAPI HTTP 层
 │   │   ├── app.py           # 路由 + 中间件
 │   │   ├── deps.py          # 依赖注入（AppState）
@@ -236,7 +244,7 @@ md-vector-db/
 ├── scripts/
 │   ├── serve.py                  # 快速启动脚本
 │   └── ingest_obsidian.py        # 批量入库 Obsidian 知识库
-└── tests/                   # 测试（46 个）
+└── tests/                   # 测试（115+ 个）
 ```
 
 ## 测试
@@ -250,7 +258,7 @@ uv run pytest tests/ -v --cov=src --cov-report=term-missing  # 覆盖率
 
 ## 架构
 
-**数据流**: MD 文件 → `MarkdownSplitter.split()` (标题→段落分块) → `batch_embed()` (分批嵌入) → `ChromaDB collection.add()` → `Searcher.search()` 查询
+**数据流**: 文件 → `get_splitter(path)` 自动选择 → `Splitter.split()` → `batch_embed()` (分批嵌入) → `ChromaDB collection.add()` → `Searcher.search()` 查询
 
 **依赖方向**: `config` ← `db` ← `embedder` ← `ingest` / `search` ← `server` / `cli`
 
diff --git a/tests/test_splitters_epub.py b/tests/test_splitters_epub.py
index c695f45..9885c8f 100644
--- a/tests/test_splitters_epub.py
+++ b/tests/test_splitters_epub.py
@@ -1,11 +1,30 @@
 """EPUBSplitter 测试."""
 import pytest
 
-ebooklib = pytest.importorskip("ebooklib", reason="ebooklib 未安装")
+
+class TestEPUBSplitterMissingDep:
+    """缺失依赖时的行为测试（不 skip 整个文件）."""
+
+    def test_split_raises_clear_import_error(self, monkeypatch):
+        """未安装 ebooklib 时给出明确提示."""
+        from src.core.splitters.epub import EPUBSplitter
+        s = EPUBSplitter()
+        import builtins
+        original_import = builtins.__import__
+
+        def mock_import(name, *args, **kwargs):
+            if name == "ebooklib" or name.startswith("ebooklib."):
+                raise ImportError("No module named 'ebooklib'")
+            return original_import(name, *args, **kwargs)
+
+        monkeypatch.setattr(builtins, "__import__", mock_import)
+        with pytest.raises(ImportError, match="ebooklib"):
+            s.split("dummy.epub", source_file="test.epub")
 
 
 class TestEPUBSplitter:
     """EPUBSplitter 测试（需 ebooklib）."""
+    ebooklib = pytest.importorskip("ebooklib", reason="ebooklib 未安装")
 
     def test_split_simple_epub(self, tmp_path):
         """用 ebooklib 创建一个简单 EPUB 并测试分块."""
@@ -47,10 +66,3 @@ class TestEPUBSplitter:
         from src.core.splitters.epub import EPUBSplitter
         s = EPUBSplitter()
         assert hasattr(s, "split")
-
-    def test_epub_missing_dependency_message(self):
-        """EPUBSplitter.split() 在未安装 ebooklib 时应给出明确提示."""
-        from src.core.splitters.epub import EPUBSplitter
-        s = EPUBSplitter()
-        # 验证 split 方法存在且可调用（有明确的 import error 信息）
-        assert callable(s.split)