64 lines
2.3 KiB
Python
64 lines
2.3 KiB
Python
|
import argparse
|
||
|
|
import re
|
||
|
|
|
||
|
|
|
||
|
|
def upper_capital_prefix_postfix(match,prefix,postfix):
|
||
|
|
return prefix + upper_capital(match) + postfix
|
||
|
|
|
||
|
|
def upper_capital(match):
|
||
|
|
return match.group(1).capitalize()
|
||
|
|
|
||
|
|
def upper_capital_dot(match):
|
||
|
|
return upper_capital_prefix_postfix(match, '','.')
|
||
|
|
|
||
|
|
def upper_capital_dot_interrogation(match):
|
||
|
|
return upper_capital_prefix_postfix(match, '','?')
|
||
|
|
|
||
|
|
def upper_capital_dot_exclamation(match):
|
||
|
|
return upper_capital_prefix_postfix(match, '','!')
|
||
|
|
|
||
|
|
def upper_capital_org_title(match):
|
||
|
|
return upper_capital_prefix_postfix(match, '* ','')
|
||
|
|
|
||
|
|
def upper_capital_tiret(match):
|
||
|
|
return '- ' + upper_capital(match)
|
||
|
|
|
||
|
|
|
||
|
|
def normalize_text(content):
|
||
|
|
# Remplacer les doubles ou plus d'espaces par des espaces simples
|
||
|
|
content = re.sub(r'\s+',' ', content)
|
||
|
|
# Remplacer les retours à la ligne consécutifs supérieurs à 2 par au maximum 2
|
||
|
|
# content = re.sub(r'\n\n\n', '\n\n', content)
|
||
|
|
# Corriger les règles d'espacement avec les deux points
|
||
|
|
# content = re.sub(r'\s+', '. ', content)
|
||
|
|
# Remplacer les eo par des vrais e dans l'o
|
||
|
|
content = re.sub(r'eo', 'œ', content)
|
||
|
|
# Remplacer trois points par le vrai caractère trois points
|
||
|
|
content = re.sub(r'\.\.\.|\.{3}', '…', content)
|
||
|
|
return content
|
||
|
|
|
||
|
|
def capitalize_text(file_path):
|
||
|
|
with open(file_path, 'r') as file:
|
||
|
|
content = file.read()
|
||
|
|
# Capitaliser les premiers mots des phrases
|
||
|
|
content = re.sub(r'(\w+.*)\.', upper_capital_dot, content)
|
||
|
|
content = re.sub(r'(\w+.*)\?', upper_capital_dot_interrogation, content)
|
||
|
|
content = re.sub(r'(\w+.*)\!', upper_capital_dot_exclamation, content)
|
||
|
|
# Capitaliser les mots dans les titres Org-mode
|
||
|
|
# content = re.sub(r'\*+\[([^\]]+)\]', r'* \1', content)
|
||
|
|
content = re.sub(r'\*+\s(\w+)', upper_capital_org_title, content)
|
||
|
|
# Capitaliser les éléments de liste
|
||
|
|
content = re.sub(r'\-\s*(\w+)', upper_capital_tiret, content)
|
||
|
|
|
||
|
|
|
||
|
|
content = normalize_text(content)
|
||
|
|
|
||
|
|
with open(file_path, 'w') as file:
|
||
|
|
file.write(content)
|
||
|
|
|
||
|
|
if __name__ == '__main__':
|
||
|
|
parser = argparse.ArgumentParser(description='Capitaliser les premiers mots des phrases dans un fichier texte.')
|
||
|
|
parser.add_argument('file_path', help='Le chemin du fichier à corriger.')
|
||
|
|
args = parser.parse_args()
|
||
|
|
capitalize_text(args.file_path)
|