Update core/file_scanner.py

core/file_scanner.py

@@ -1,7 +1,7 @@
+import chardet
 from pathlib import Path
-from typing import List, Dict, Optional, Set
+from typing import List, Optional, Set
 from dataclasses import dataclass
-import chardet
 
 @dataclass
 class FileInfo:
@@ -10,63 +10,78 @@ class FileInfo:
     extension: str
     content: Optional[str] = None
     encoding: Optional[str] = None
-    
+
     @property
     def formatted_size(self) -> str:
+        """ファイルサイズを見やすい単位で表示"""
         if self.size < 1024:
             return f"{self.size} B"
         elif self.size < 1024 * 1024:
-            return f"{self.size/1024:.1f} KB"
+            return f"{self.size / 1024:.1f} KB"
         else:
-            return f"{self.size/(1024*1024):.1f} MB"
+            return f"{self.size / (1024 * 1024):.1f} MB"
+
 
 class FileScanner:
     EXCLUDED_DIRS = {
-        '.git', '__pycache__', 'node_modules', 'venv', 
+        '.git', '__pycache__', 'node_modules', 'venv',
         '.env', 'build', 'dist', 'target', 'bin', 'obj'
     }
     
     def __init__(self, base_dir: Path, target_extensions: Set[str]):
+        """
+        base_dir: 解析を開始するディレクトリ
+        target_extensions: 対象とする拡張子の集合（例: {'.py', '.js', '.md'}）
+        """
         self.base_dir = base_dir
-        self.target_extensions = target_extensions
-    
+        self.target_extensions = {ext.lower() for ext in target_extensions}
+
     def _should_scan_file(self, path: Path) -> bool:
+        """対象外フォルダ・拡張子を除外"""
+        # 除外フォルダ
         if any(excluded in path.parts for excluded in self.EXCLUDED_DIRS):
             return False
-        return path.suffix.lower() in self.target_extensions
-    
-    def _read_file_content(self, file_path: Path) -> tuple[Optional[str], Optional[str]]:
+        # 拡張子チェック
+        if path.suffix.lower() in self.target_extensions:
+            return True
+        return False
+
+    def _read_file_content(self, file_path: Path) -> (Optional[str], Optional[str]):
+        """ファイル内容を読み込み、エンコーディングを判定"""
         try:
-            with file_path.open('rb') as f:
-                raw_data = f.read(4096)
-                result = chardet.detect(raw_data)
-                encoding = result['encoding'] if result['confidence'] > 0.7 else 'utf-8'
+            # 先頭数KBを読み込み、エンコーディングを推定
+            with file_path.open('rb') as rb:
+                raw_data = rb.read(4096)
+                detect_result = chardet.detect(raw_data)
+                encoding = detect_result['encoding'] if detect_result['confidence'] > 0.7 else 'utf-8'
+            
+            # 推定したエンコーディングで読み込み
             try:
                 with file_path.open('r', encoding=encoding) as f:
                     return f.read(), encoding
             except UnicodeDecodeError:
-                try:
-                    with file_path.open('r', encoding='cp932') as f:
-                        return f.read(), 'cp932'
-                except UnicodeDecodeError:
-                    return None, None
-        except (OSError, ValueError):
+                # ダメなら cp932 を試す
+                with file_path.open('r', encoding='cp932') as f:
+                    return f.read(), 'cp932'
+        except Exception:
             return None, None
-    
+
     def scan_files(self) -> List[FileInfo]:
+        """再帰的にファイルを探して、指定拡張子ならFileInfoリストにまとめる"""
         if not self.base_dir.exists():
-            raise FileNotFoundError(f"ディレクトリが見つかりません: {self.base_dir}")
-        
-        files = []
+            raise FileNotFoundError(f"指定ディレクトリが見つかりません: {self.base_dir}")
+
+        collected_files = []
         for entry in self.base_dir.glob("**/*"):
             if entry.is_file() and self._should_scan_file(entry):
                 content, encoding = self._read_file_content(entry)
-                if content is not None:
-                    files.append(FileInfo(
-                        path=entry.absolute(),
-                        size=entry.stat().st_size,
-                        extension=entry.suffix.lower(),
-                        content=content,
-                        encoding=encoding
-                    ))
-        return sorted(files, key=lambda x: str(x.path))
+                file_info = FileInfo(
+                    path=entry.resolve(),
+                    size=entry.stat().st_size,
+                    extension=entry.suffix.lower(),
+                    content=content,
+                    encoding=encoding
+                )
+                collected_files.append(file_info)
+        # path の文字列表現でソート
+        return sorted(collected_files, key=lambda x: str(x.path))