feat: 添加 EPUBSplitter — ebooklib 提取章节文字后分块

- 新增 splitters/epub.py: ebooklib 读取 EPUB → BeautifulSoup 去标签 → TextSplitter 分块
- epub 作为可选依赖: uv sync --extra epub
- registry 新增 .epub 映射, ingest_file 处理 EPUB 二进制文件
- 测试: 3 个 EPUBSplitter 测试 (含空 EPUB/Protocol 合规)

Co-Authored-By: Claude <noreply@anthropic.com>

src/core/splitters/registry.py

@@ -10,6 +10,7 @@ _DEFAULT_MAP: dict[str, str] = {
     ".pdf": "pdf",
     ".html": "html",
     ".htm": "html",
+    ".epub": "epub",
 }
 
 # 所有支持的扩展名集合（供外部遍历文件使用）
@@ -64,6 +65,10 @@ def get_splitter(
         from src.core.splitters.html import HTMLSplitter
         return HTMLSplitter(max_size=max_size, overlap=overlap)
 
+    if kind == "epub":
+        from src.core.splitters.epub import EPUBSplitter
+        return EPUBSplitter(max_size=max_size, overlap=overlap)
+
     # 回退
     from src.core.splitters.text import TextSplitter
     return TextSplitter(max_size=max_size, overlap=overlap)