RDMP/check_copyright_headers.py at main · jas88/RDMP · GitHub

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
#!/usr/bin/env python3
import os
import re
from pathlib import Path

def check_copyright_headers():
    """Check for missing copyright headers in C# files"""
    root_dir = Path('.')

    # Pattern to match University of Dundee copyright header
    dundee_pattern = r'// Copyright \(c\) The University of Dundee \d{4}(-\d{4})?'

    # Files to ignore
    ignore_patterns = [
        '.Designer.cs',
        'Program.cs',
        'Settings.Designer.cs',
        'Class1.cs',
        'Images.Designer.cs',
        'ToolTips.Designer.cs',
        'Resources.Designer.cs',
        'ProjectInstaller.cs',
        'ProjectInstaller.Designer.cs',
        'TableView.cs',
        'TreeView.cs'
    ]

    issues = []

    for cs_file in root_dir.rglob('*.cs'):
        # Skip ignored files
        if any(pattern in cs_file.name for pattern in ignore_patterns):
            continue

        # Skip git and build directories
        if '.git' in str(cs_file) or 'obj' in str(cs_file) or 'bin' in str(cs_file):
            continue

        # Skip if it's auto-generated
        try:
            with open(cs_file, 'r', encoding='utf-8') as f:
                first_line = f.readline().strip()
                if first_line == '// <autogenerated />':
                    continue
        except:
            continue

        # Check if file has proper copyright header
        try:
            with open(cs_file, 'r', encoding='utf-8') as f:
                content = f.read(500)  # Read first 500 characters
                if not re.search(dundee_pattern, content):
                    issues.append(f"Missing/correct copyright header: {cs_file}")

                    # Check what copyright it does have
                    if 'Copyright' in content:
                        lines = content.split('\n')[:10]
                        for line in lines:
                            if 'Copyright' in line:
                                issues.append(f"  Has: {line.strip()}")
                                break
        except Exception as e:
            issues.append(f"Could not read {cs_file}: {e}")

    return issues

if __name__ == '__main__':
    issues = check_copyright_headers()
    if issues:
        print(f"Found {len(issues)} copyright issues:")
        for issue in issues:
            print(issue)
    else:
        print("No copyright header issues found")