File size: 2,587 Bytes
227e75d
 
 
 
 
 
 
5a2169d
 
227e75d
5a2169d
 
 
 
 
 
 
 
 
 
227e75d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
20c757d
 
227e75d
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
from pathlib import Path
from typing import List, Dict, Optional
from dataclasses import dataclass

@dataclass
class FileInfo:
    path: Path
    size: int
    extension: str
    content: Optional[str] = None
    encoding: Optional[str] = None
    
    @property
    def formatted_size(self) -> str:
        if self.size < 1024:
            return f"{self.size} B"
        elif self.size < 1024 * 1024:
            return f"{self.size/1024:.1f} KB"
        else:
            return f"{self.size/(1024*1024):.1f} MB"

class FileScanner:
    # スキャン対象の拡張子
    TARGET_EXTENSIONS = {
        '.py', '.js', '.java', '.cpp', '.hpp', '.c', '.h',
        '.go', '.rs', '.php', '.rb', '.ts', '.scala', '.kt',
        '.cs', '.swift', '.m', '.sh', '.pl', '.r'
    }
    
    # スキャン対象から除外するディレクトリ
    EXCLUDED_DIRS = {
        '.git', '__pycache__', 'node_modules', 'venv', '.env',
        'build', 'dist', 'target', 'bin', 'obj'
    }
    
    def __init__(self, base_dir: Path):
        self.base_dir = base_dir
    
    def _should_scan_file(self, path: Path) -> bool:
        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) -> Optional[str]:
        try:
            # まずUTF-8で試す
            try:
                with file_path.open('r', encoding='utf-8') as f:
                    return f.read()
            except UnicodeDecodeError:
                # UTF-8で失敗したらcp932を試す
                with file_path.open('r', encoding='cp932') as f:
                    return f.read()
        except (OSError, UnicodeDecodeError):
            return None
    
    def scan_files(self) -> List[FileInfo]:
        if not self.base_dir.exists():
            raise FileNotFoundError(f"Directory not found: {self.base_dir}")
        
        files = []
        
        for entry in self.base_dir.rglob('*'):
            if entry.is_file() and self._should_scan_file(entry):
                content = self._read_file_content(entry)
                if content is not None:
                    files.append(FileInfo(
                        path=entry.relative_to(self.base_dir),
                        size=entry.stat().st_size,  # ファイルサイズを追加
                        extension=entry.suffix,      # 拡張子を追加
                        content=content
                    ))
        
        return sorted(files, key=lambda x: str(x.path))