From 0a4a4c766ca4284ac844ad0d5f842c4ccf63d01c 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 15:18:46 +0800
Subject: [PATCH] =?UTF-8?q?fix:=20search=5Fdocuments=20=E7=AB=AF=E7=82=B9?=
 =?UTF-8?q?=E6=B7=BB=E5=8A=A0=E5=BC=82=E5=B8=B8=E5=A4=84=E7=90=86=E9=98=B2?=
 =?UTF-8?q?=E6=AD=A2=20traceback=20=E6=B3=84=E9=9C=B2?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 scripts/ingest_obsidian.py | 12 ------------
 src/core/splitters/pdf.py  | 11 +++++------
 src/server/app.py          | 12 +++++++++---
 3 files changed, 14 insertions(+), 21 deletions(-)

diff --git a/scripts/ingest_obsidian.py b/scripts/ingest_obsidian.py
index 4cee4ef..e05cd80 100644
--- a/scripts/ingest_obsidian.py
+++ b/scripts/ingest_obsidian.py
@@ -63,18 +63,6 @@ for label, d in targets:
             skipped.append((f.name, size))
             continue
         files.append((label, str(f)))
-# 顶层 .md 文件
-for target_info in targets:
-    d = target_info[1]
-    p = Path(d)
-    if not p.exists():
-        continue
-    for f in p.glob("*.md"):
-        sz = f.stat().st_size
-        if sz > MAX_SIZE:
-            skipped.append((f.name, sz))
-        else:
-            files.append(("顶层/" + p.name, str(f)))
 
 log(f"待处理: {len(files)} 个文件")
 if skipped:
diff --git a/src/core/splitters/pdf.py b/src/core/splitters/pdf.py
index 255ac93..9ee745a 100644
--- a/src/core/splitters/pdf.py
+++ b/src/core/splitters/pdf.py
@@ -32,12 +32,11 @@ class PDFSplitter:
         pdf_path = text  # text 参数实际是文件路径
         extracted_pages = []
         try:
-            doc = fitz.open(pdf_path)
-            for page in doc:
-                page_text = page.get_text()
-                if page_text.strip():
-                    extracted_pages.append(page_text)
-            doc.close()
+            with fitz.open(pdf_path) as doc:
+                for page in doc:
+                    page_text = page.get_text()
+                    if page_text.strip():
+                        extracted_pages.append(page_text)
         except Exception as e:
             logger.error("PDF 解析失败: %s — %s", pdf_path, e)
             raise ValueError(f"PDF 解析失败: {e}") from e
diff --git a/src/server/app.py b/src/server/app.py
index dc69e1d..179e934 100644
--- a/src/server/app.py
+++ b/src/server/app.py
@@ -150,9 +150,15 @@ def search_documents(
     state: AppState = Depends(get_state),
     _: bool = Depends(verify_api_key),
 ):
-    searcher = state.get_searcher(req.collection)
-    results = searcher.search(req.query, top_k=req.top_k)
-    return {"results": results, "collection": searcher.collection_name}
+    try:
+        searcher = state.get_searcher(req.collection)
+        results = searcher.search(req.query, top_k=req.top_k)
+        return {"results": results, "collection": searcher.collection_name}
+    except HTTPException:
+        raise
+    except Exception:
+        logger.exception("检索失败")
+        raise HTTPException(status_code=500, detail="服务器内部错误")
 
 
 @app.delete("/api/v1/documents/{file_name}")