日常报销和差旅报销都可以走通

src/doc/extractor.py

@@ -51,16 +51,17 @@ def _get_cache_dir(source_dir: Path) -> Path:
 
 
 def _get_json_path(file_path: Path, cache_dir: Path) -> Path:
-    """根据文件路径生成对应的 JSON 缓存路径"""
-    return cache_dir / f"{file_path.stem}.json"
+    """根据文件路径生成对应的 JSON 缓存路径（包含后缀名以区分同名的 PDF/图片）"""
+    return cache_dir / f"{file_path.stem}{file_path.suffix}.json"
 
 
 def _save_to_cache(file_path: Path, extracted_data: dict[str, Any], cache_dir: Path) -> Path:
-    """将提取结果保存到 JSON 缓存文件，并记录源文件路径"""
+    """将提取结果保存到 JSON 缓存文件，并记录源文件路径和后缀名"""
     json_path = _get_json_path(file_path, cache_dir)
     cache_data = {
         "source_file": str(file_path),
         "source_filename": file_path.name,
+        "source_extension": file_path.suffix.lower(),
         "extracted_data": extracted_data,
     }
     with open(json_path, "w", encoding="utf-8") as f:
@@ -69,13 +70,16 @@ def _save_to_cache(file_path: Path, extracted_data: dict[str, Any], cache_dir: P
     return json_path
 
 
-def _load_from_cache(json_path: Path) -> dict[str, Any] | None:
-    """从 JSON 缓存文件加载提取结果"""
+def _load_from_cache(json_path: Path, expected_extension: str | None = None) -> dict[str, Any] | None:
+    """从 JSON 缓存文件加载提取结果，可选校验后缀名一致性"""
     if not json_path.exists():
         return None
     try:
         with open(json_path, encoding="utf-8") as f:
             cache_data: dict[str, Any] = json.load(f)
+        # 校验后缀名是否一致，防止同名不同后缀的文件误命中缓存
+        if expected_extension and cache_data.get("source_extension", "").lower() != expected_extension.lower():
+            return None
         result: dict[str, Any] | None = cache_data.get("extracted_data")
         return result
     except Exception as e:
@@ -100,7 +104,7 @@ def _extract_document(file_path: Path, cache_dir: Path) -> dict[str, str] | None
         提取结果字典，失败时返回 None。
     """
     json_path = _get_json_path(file_path, cache_dir)
-    cached = _load_from_cache(json_path)
+    cached = _load_from_cache(json_path, expected_extension=file_path.suffix.lower())
     if cached:
         cached["_source_file"] = file_path.name
         log.info(f"使用缓存: {file_path.name}")