6

backend/app/public/routes.py

@@ -12,12 +12,14 @@ import json
 
 from fastapi import APIRouter, Depends, Query, Request, Response
 from fastapi.responses import HTMLResponse, PlainTextResponse
+from fastapi import Path as PathParam
 from sqlalchemy.orm import Session
 
 from app.api.deps import get_db
 from app.core.errors import NotFoundError, RateLimitedError
 from app.core.rate_limit import check_rate_limit
 from app.core.security import decrypt_token
+from app.models.document_category import DocumentCategory
 from app.services.access_log_service import AccessLogService
 from app.services.kb_public_service import KbPublicService
 
@@ -151,10 +153,14 @@ def kb_index_json(
             "updated_at": doc.updated_at,
         })
 
+    # 获取目录树
+    category_tree = svc.get_category_tree(kb)
+
     data = {
         "name": kb.name,
         "description": kb.description,
         "document_count": len(doc_list),
+        "categories": category_tree,
         "documents": doc_list,
     }
 
@@ -168,15 +174,52 @@ def kb_index_json(
 def kb_index_html(
     token: str,
     request: Request,
+    category: str = Query(None, description="按分类路径过滤，如 /01公司层/公司基本信息/"),
     page: int = Query(1, ge=1),
     db: Session = Depends(get_db),
 ) -> HTMLResponse:
-    """知识库首页（HTML）。"""
+    """知识库首页（HTML）。支持按目录过滤。"""
     _rate_limit(request, token)
     svc = KbPublicService(db)
     kb = svc.get_kb_by_token(token)
     _log_access(db, kb.id, f"/k/{token}", request, req_type="html")
-    docs, total = svc.list_documents(kb, page=page, page_size=50)
+
+    # 获取目录树
+    category_tree = svc.get_category_tree(kb)
+
+    # 按分类过滤
+    category_id = None
+    if category:
+        # 根据路径查找分类 ID
+        from sqlalchemy import select
+        stmt = select(DocumentCategory).where(
+            DocumentCategory.knowledge_base_id == kb.id,
+            DocumentCategory.path == category,
+        )
+        cat = db.scalars(stmt).first()
+        if cat:
+            category_id = cat.id
+
+    docs, total = svc.list_documents(kb, category_id=category_id, page=page, page_size=50)
+
+    # 渲染目录树侧边栏
+    def render_tree(nodes: list, level: int = 0) -> str:
+        html = ""
+        for node in nodes:
+            indent = "  " * level
+            is_active = category == node["path"]
+            active_class = ' class="active"' if is_active else ""
+            doc_count = f' <span class="count">({node["doc_count"]})</span>' if node["doc_count"] > 0 else ""
+
+            if node["is_folder"]:
+                html += f'{indent}<li{active_class}><a href="/k/{token}?category={node["path"]}">{node["name"]}</a>{doc_count}</li>\n'
+                if node["children"]:
+                    html += f'{indent}<ul>\n{render_tree(node["children"], level + 1)}{indent}</ul>\n'
+            else:
+                html += f'{indent}<li{active_class}><a href="/k/{token}?category={node["path"]}">{node["name"]}</a>{doc_count}</li>\n'
+        return html
+
+    tree_html = render_tree(category_tree)
 
     doc_rows = ""
     for doc in docs:
@@ -208,8 +251,19 @@ def kb_index_html(
     {_robots_meta()}
     {_referrer_meta()}
     <style>
-        body {{ font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif; max-width: 800px; margin: 0 auto; padding: 20px; line-height: 1.6; }}
-        h1 {{ color: #333; }}
+        * {{ box-sizing: border-box; }}
+        body {{ font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif; margin: 0; padding: 20px; line-height: 1.6; display: flex; gap: 30px; }}
+        .sidebar {{ width: 280px; flex-shrink: 0; }}
+        .main {{ flex: 1; max-width: 800px; }}
+        h1 {{ color: #333; margin-top: 0; }}
+        .tree {{ list-style: none; padding: 0; margin: 0; }}
+        .tree ul {{ list-style: none; padding-left: 20px; margin: 0; }}
+        .tree li {{ padding: 6px 10px; border-radius: 4px; }}
+        .tree li:hover {{ background: #f5f7fa; }}
+        .tree li.active {{ background: #ecf5ff; }}
+        .tree a {{ color: #333; text-decoration: none; font-size: 0.95em; }}
+        .tree a:hover {{ color: #409eff; }}
+        .tree .count {{ color: #999; font-size: 0.85em; }}
         .doc-item {{ border-bottom: 1px solid #eee; padding: 15px 0; }}
         .doc-item h3 {{ margin: 0 0 5px 0; }}
         .doc-item a {{ color: #0066cc; text-decoration: none; }}
@@ -220,17 +274,29 @@ def kb_index_html(
         .pagination {{ color: #666; font-size: 0.9em; text-align: center; }}
         .status-badge {{ color: #e67e22; font-size: 0.8em; font-weight: normal; }}
         .footer {{ margin-top: 30px; padding-top: 15px; border-top: 1px solid #eee; color: #999; font-size: 0.85em; }}
+        .back-link {{ display: inline-block; margin-bottom: 15px; color: #0066cc; text-decoration: none; }}
+        .back-link:hover {{ text-decoration: underline; }}
     </style>
 </head>
 <body>
-    <h1>{kb.name}</h1>
-    {"<p>" + kb.description + "</p>" if kb.description else ""}
-    <h2>文档列表</h2>
-    {doc_rows if doc_rows else "<p>暂无文档。</p>"}
-    {pagination}
-    <div class="footer">
-        <p>This page is an AI-readable knowledge base index. Use the document links above to retrieve specific documents.</p>
-        <p>本页为 AI 可读知识库目录，请通过上述文档链接获取具体内容。</p>
+    <div class="sidebar">
+        <h2 style="margin-top: 0; font-size: 1.1em;">目录</h2>
+        <ul class="tree">
+            <li{" class='active'" if not category else ""}><a href="/k/{token}">全部文档</a> <span class="count">({total})</span></li>
+            {tree_html}
+        </ul>
+    </div>
+    <div class="main">
+        <h1>{kb.name}</h1>
+        {"<p>" + kb.description + "</p>" if kb.description else ""}
+        {"<a href='/k/" + token + "' class='back-link'>← 返回全部文档</a>" if category else ""}
+        <h2>{"当前分类：" + category if category else "文档列表"}</h2>
+        {doc_rows if doc_rows else "<p>暂无文档。</p>"}
+        {pagination}
+        <div class="footer">
+            <p>This page is an AI-readable knowledge base index. Use the document links above to retrieve specific documents.</p>
+            <p>本页为 AI 可读知识库目录，请通过上述文档链接获取具体内容。</p>
+        </div>
     </div>
 </body>
 </html>"""
@@ -240,12 +306,49 @@ def kb_index_html(
 # --- 单文档访问 ---
 
 
-@router.get("/{token}/doc/{doc_token}")
-def doc_page_html(
+@router.get("/{token}/doc/{doc_token}.md")
+def doc_page_markdown(
     token: str,
     doc_token: str,
     request: Request,
     db: Session = Depends(get_db),
+) -> PlainTextResponse:
+    """文档（Markdown）。"""
+    _rate_limit(request, token)
+    svc = KbPublicService(db)
+    kb = svc.get_kb_by_token(token)
+    doc = svc.get_document_by_token(kb, doc_token)
+    _log_access(db, kb.id, f"/k/{token}/doc/{doc_token}.md", request, doc_id=doc.id, req_type="doc_md")
+    markdown_content = svc.get_document_content(doc)
+    return PlainTextResponse(content=markdown_content, media_type="text/markdown")
+
+
+@router.get("/{token}/doc/{doc_token}.txt")
+def doc_page_text(
+    token: str,
+    doc_token: str,
+    request: Request,
+    db: Session = Depends(get_db),
+) -> PlainTextResponse:
+    """文档（纯文本）。"""
+    _rate_limit(request, token)
+    svc = KbPublicService(db)
+    kb = svc.get_kb_by_token(token)
+    doc = svc.get_document_by_token(kb, doc_token)
+    _log_access(db, kb.id, f"/k/{token}/doc/{doc_token}.txt", request, doc_id=doc.id, req_type="doc_txt")
+    markdown_content = svc.get_document_content(doc)
+    import re
+    text = re.sub(r"[#*_`\[\]()>]", "", markdown_content)
+    text = re.sub(r"\n{3,}", "\n\n", text)
+    return PlainTextResponse(content=text.strip(), media_type="text/plain")
+
+
+@router.get("/{token}/doc/{doc_token}")
+def doc_page_html(
+    token: str,
+    doc_token: str = PathParam(pattern=r"^[A-Za-z0-9_-]+$"),
+    request: Request = None,
+    db: Session = Depends(get_db),
 ) -> HTMLResponse:
     """文档页面（HTML）。"""
     _rate_limit(request, token)
@@ -253,7 +356,7 @@ def doc_page_html(
     kb = svc.get_kb_by_token(token)
     doc = svc.get_document_by_token(kb, doc_token)
     _log_access(db, kb.id, f"/k/{token}/doc/{doc_token}", request, doc_id=doc.id, req_type="doc_html")
-    markdown_content = svc.get_document_markdown(doc)
+    markdown_content = svc.get_document_content(doc)
 
     # Markdown → HTML（简单转换）
     html_content = _markdown_to_html(markdown_content)
@@ -313,7 +416,7 @@ def doc_page_markdown(
     kb = svc.get_kb_by_token(token)
     doc = svc.get_document_by_token(kb, doc_token)
     _log_access(db, kb.id, f"/k/{token}/doc/{doc_token}.md", request, doc_id=doc.id, req_type="doc_md")
-    markdown_content = svc.get_document_markdown(doc)
+    markdown_content = svc.get_document_content(doc)
     return PlainTextResponse(content=markdown_content, media_type="text/markdown")
 
 
@@ -330,7 +433,7 @@ def doc_page_text(
     kb = svc.get_kb_by_token(token)
     doc = svc.get_document_by_token(kb, doc_token)
     _log_access(db, kb.id, f"/k/{token}/doc/{doc_token}.txt", request, doc_id=doc.id, req_type="doc_txt")
-    markdown_content = svc.get_document_markdown(doc)
+    markdown_content = svc.get_document_content(doc)
 
     # 去掉 Markdown 标记
     import re