diacritice 3534.py

diacritice 3534.py

import os

BASE_DIR = r'e:\Carte\BB\17 - Site Leadership\Principal\ro'

REPLACEMENTS = {
    # ă / Ă
    'ă': 'ă', 'ă': 'ă', 'ă': 'ă',
    'Ă': 'Ă', 'Ă': 'Ă', 'Ă': 'Ă',

    # â / Â
    'â': 'â', 'â': 'â', 'â': 'â',
    'Â': 'Â', 'Â': 'Â', 'Â': 'Â',
    'â': 'â', 'Â': 'Â',

    # î / Î
    'î': 'î', 'î': 'î', 'î': 'î',
    'Î': 'Î', 'Î': 'Î', 'Î': 'Î',
    'î': 'î', 'Î': 'Î',

    # ș mic / mare (virgulă + sedilă)
    'ș': 'ș', 'ș': 'ș', 'ș': 'ș',   # ș
    'ş': 'ș', 'ş': 'ș', 'ş': 'ș',   # ş
    'Ș': 'Ș', 'Ș': 'Ș', 'Ș': 'Ș',   # Ș
    'Ş': 'Ș', 'Ş': 'Ș', 'Ş': 'Ș',   # Ş

    # ț mic / mare (virgulă + sedilă)
    'ț': 'ț', 'ț': 'ț', 'ț': 'ț',   # ț
    'ţ': 'ț', 'ţ': 'ț', 'ţ': 'ț',   # ţ
    'Ț': 'Ț', 'Ț': 'Ț', 'Ț': 'Ț',   # Ț
    'Ţ': 'Ț', 'Ţ': 'Ț', 'Ţ': 'Ț',   # Ţ

    # entități text uzuale
    '"': '"',
    ''': "'",
}

# AICI extindem corecțiile pentru caracterele „ciudate”
RAW_CHAR_REPLACEMENTS = {
    # sedilă → virgulă
    'ş': 'ș',
    'Ş': 'Ș',
    'ţ': 'ț',
    'Ţ': 'Ț',

    # punct dedesubt (ṭ, Ṭ, ṣ, Ṣ) → diacritice românești
    'ṭ': 'ț',   # U+1E6D LATIN SMALL LETTER T WITH DOT BELOW
    'Ṭ': 'Ț',   # U+1E6C LATIN CAPITAL LETTER T WITH DOT BELOW
    'ṣ': 'ș',   # U+1E63 LATIN SMALL LETTER S WITH DOT BELOW
    'Ṣ': 'Ș',   # U+1E62 LATIN CAPITAL LETTER S WITH DOT BELOW
}

def normalize_content(text: str) -> str:
    # 1. Numeric / named entities → UTF-8
    for src, dst in REPLACEMENTS.items():
        text = text.replace(src, dst)

    # 2. Caractere greșite (sedilă, punct) → diacritice românești corecte
    for src, dst in RAW_CHAR_REPLACEMENTS.items():
        text = text.replace(src, dst)

    return text

def main():
    print(f"Încep înlocuirea în: {BASE_DIR}\n")
    changed_files = 0

    for root, dirs, files in os.walk(BASE_DIR):
        for name in files:
            if not name.lower().endswith('.html'):
                continue
            full_path = os.path.join(root, name)
            try:
                with open(full_path, 'r', encoding='utf-8') as f:
                    content = f.read()
            except UnicodeDecodeError:
                continue

            new_content = normalize_content(content)
            if new_content != content:
                with open(full_path, 'w', encoding='utf-8') as f:
                    f.write(new_content)
                changed_files += 1
                print(f"✅ Actualizat: {full_path}")

    if changed_files == 0:
        print("Nu a fost nevoie de nicio modificare.")
    else:
        print(f"\nGata. Au fost actualizate {changed_files} fișiere.")

if __name__ == '__main__':
    main()