From 60e2f520ba47679453feaf87a362a583fcdc9c8f Mon Sep 17 00:00:00 2001
From: panda <1415243231@qq.com>
Date: Thu, 21 May 2026 23:05:27 +0800
Subject: [PATCH] fix: image files silently falling to text parser due to
 suffix dot mismatch

api_server.py passed "jpg" (no dot) from rsplit, but file_parser.py
parser dict keys all have dots (".jpg"), causing image files to fall
through to _parse_text() which fails on binary data, skipping ALL OCR
and layout analysis. Every image upload was affected.

- file_parser.py: normalize file_type to always have leading dot
- api_server.py: use Path.suffix instead of manual rsplit
---
 api_server.py          | 2 +-
 backend/file_parser.py | 4 +++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/api_server.py b/api_server.py
index feca84f..86c143e 100644
--- a/api_server.py
+++ b/api_server.py
@@ -400,7 +400,7 @@ def _process_files(file_ids: list[str], session_id: str) -> dict:
         file_path = info["path"]
         uploaded_paths.append(file_path)
 
-        parsed = parse_file(file_path, info["filename"].rsplit(".", 1)[-1] if "." in info["filename"] else "")
+        parsed = parse_file(file_path, Path(info["filename"]).suffix)
         if parsed.get("error"):
             parts.append(f"[文件: {info['filename']}]\n解析失败: {parsed['error']}")
             continue
diff --git a/backend/file_parser.py b/backend/file_parser.py
index b767ee2..88ee2cd 100644
--- a/backend/file_parser.py
+++ b/backend/file_parser.py
@@ -41,7 +41,9 @@ def parse_file(file_path: str, file_type: str = "") -> dict:
     if not path.exists():
         return {"text": "", "file_type": file_type, "method": "none", "error": "文件不存在"}
 
-    suffix = file_type or path.suffix.lower()
+    suffix = path.suffix.lower()
+    if file_type:
+        suffix = file_type if file_type.startswith(".") else f".{file_type}"
 
     parsers = {
         ".png":  _parse_image,