check_code_formatting.py

#!/usr/bin/env python3
"""
Code formatting and quality checker for TranscriptorEnhanced
Checks for common formatting issues, syntax errors, and code quality problems
"""

import os
import sys
import py_compile
import ast
from pathlib import Path

def check_syntax(filepath):
    """Check if Python file has valid syntax"""
    try:
        with open(filepath, 'r', encoding='utf-8') as f:
            code = f.read()
        ast.parse(code)
        return True, "✓ Valid syntax"
    except SyntaxError as e:
        return False, f"✗ Syntax error at line {e.lineno}: {e.msg}"
    except Exception as e:
        return False, f"✗ Error: {str(e)}"

def check_indentation(filepath):
    """Check for mixed tabs/spaces and indentation issues"""
    issues = []
    try:
        with open(filepath, 'r', encoding='utf-8') as f:
            lines = f.readlines()

        has_tabs = False
        has_spaces = False

        for i, line in enumerate(lines, 1):
            if line.startswith('\t'):
                has_tabs = True
            if line.startswith(' '):
                has_spaces = True

            # Check for trailing whitespace
            if line.rstrip() != line.rstrip('\n').rstrip('\r'):
                issues.append(f"Line {i}: Trailing whitespace")

        if has_tabs and has_spaces:
            issues.append("Mixed tabs and spaces detected")

        return len(issues) == 0, issues if issues else ["✓ Clean indentation"]
    except Exception as e:
        return False, [f"✗ Error checking indentation: {str(e)}"]

def check_line_length(filepath, max_length=120):
    """Check for overly long lines"""
    long_lines = []
    try:
        with open(filepath, 'r', encoding='utf-8') as f:
            lines = f.readlines()

        for i, line in enumerate(lines, 1):
            if len(line.rstrip()) > max_length:
                long_lines.append(f"Line {i}: {len(line.rstrip())} chars")

        if long_lines:
            return False, long_lines[:5]  # Show first 5 only
        return True, ["✓ All lines within limit"]
    except Exception as e:
        return False, [f"✗ Error: {str(e)}"]

def check_file(filepath):
    """Run all checks on a Python file"""
    print(f"\n{'='*80}")
    print(f"Checking: {filepath}")
    print('='*80)

    all_passed = True

    # Syntax check
    print("\n1. SYNTAX CHECK:")
    passed, result = check_syntax(filepath)
    print(f"   {result}")
    all_passed = all_passed and passed

    # Indentation check
    print("\n2. INDENTATION CHECK:")
    passed, results = check_indentation(filepath)
    for r in results[:5]:  # Show first 5 issues
        print(f"   {r}")
    if len(results) > 5:
        print(f"   ... and {len(results) - 5} more issues")
    all_passed = all_passed and passed

    # Line length check
    print("\n3. LINE LENGTH CHECK (max 120 chars):")
    passed, results = check_line_length(filepath)
    for r in results:
        print(f"   {r}")
    all_passed = all_passed and passed

    return all_passed

def main():
    """Check all Python files in the project"""
    base_dir = Path('/home/john/TranscriptorEnhanced')

    # Core Python files to check
    core_files = [
        'app.py',
        'llm.py',
        'quote_extractor.py',
        'story_writer.py',
        'production_logger.py',
        'narrative_report_generator.py',
        'reporting.py',
        'validation.py',
        'report_parser.py',
        'table_builder.py'
    ]

    print("="*80)
    print("TRANSCRIPTORAI - CODE FORMATTING CHECK")
    print("="*80)

    all_passed = True
    checked = 0
    failed = []

    for filename in core_files:
        filepath = base_dir / filename
        if filepath.exists():
            checked += 1
            passed = check_file(str(filepath))
            if not passed:
                failed.append(filename)
                all_passed = False
        else:
            print(f"\n⚠️  File not found: {filename}")

    # Summary
    print("\n" + "="*80)
    print("SUMMARY")
    print("="*80)
    print(f"Files checked: {checked}")
    print(f"Files passed: {checked - len(failed)}")
    print(f"Files failed: {len(failed)}")

    if failed:
        print("\n❌ Files with issues:")
        for f in failed:
            print(f"   - {f}")
    else:
        print("\n✅ All files passed formatting checks!")

    print("="*80)

    return 0 if all_passed else 1

if __name__ == "__main__":
    sys.exit(main())