import pathlib
import re
import unicodedata

def format_list(xs):
    return '[ ' + ', '.join([f'"{x}"' for x in xs]) + ' ]'

def path_part(name):
    simplified = ''.join([alnum_or_space(c) for c in unaccent(name.lower())])
    return '-'.join(simplified.split())

def unaccent(s):
   return ''.join(c for c in unicodedata.normalize('NFD', s) if unicodedata.category(c) != 'Mn')

def alnum_or_space(c):
    if c.isalnum():
        return c
    else:
        return ' '

def extension(path):
    return pathlib.Path(path).suffix

def cleanup_text(s, lang):
    s = re.sub('\'', '’', s)
    s = re.sub('\.\.\.', '…', s)
    s = re.sub('\. \. \.', '…', s)
    s = cleanup_quotes(s, lang)

    if lang == 'fr':
        s = re.sub('“', '«', s)
        s = re.sub('”', '»', s)

        # Replace space by insecable spaces
        s = re.sub(r' ([:?\!»])', r' \1', s)
        s = re.sub('« ', '« ', s)

        # Add missing insecable spaces
        s = re.sub(r'([^ ])([:?\!»])', r'\1 \2', s)
        s = re.sub(r'«([^ ])', r'« \1', s)

    elif lang == 'en':
        s = re.sub('«', '“', s)
        s = re.sub('»', '”', s)

    return s

def cleanup_quotes(s, lang):
    res = ''
    quoted = False
    for c in s:
        if c == '"':
            if quoted:
                quoted = False
                if lang == 'fr':
                    res += '»'
                elif lang == 'en':
                    res += '”'
            else:
                quoted = True
                if lang == 'fr':
                    res += '«'
                elif lang == 'en':
                    res += '“'
        else:
            res += c
    return res