def is_combining_remove(code_point):
'''Check whether this is a combining character which should be listed
in the section of the translit_combining file where combining
characters are replaced by empty strings.
We ignore combining characters from many scripts here because
the original translit_combining file didn’t do this for the
combining characters from these scripts either and I am not
sure yet whether this would be useful to do for all combining
characters or not. For the moment I think it is better to keep
close to the spirit of the original file.
'''
if not unicode_utils.is_combining(code_point):
return False
name = unicode_utils.UNICODE_ATTRIBUTES[code_point]['name']
for substring in ('DEVANAGARI', 'BENGALI', 'CYRILLIC', 'SYRIAC', 'THAANA',
'NKO', 'GURMUKHI', 'TAMIL', 'GUJARATI', 'ORIYA',
'TELUGU', 'KANNADA', 'MALAYALAM', 'SINHALA', 'THAI',
'LAO', 'TIBETAN', 'MYANMAR', 'ETHIOPIC', 'TAGALOG',
'HANUNOO', 'BUHID', 'TAGBANWA', 'KHMER', 'MONGOLIAN',
'LIMBU', 'NEW TAI LUE', 'BUGINESE', 'BALINESE',
'SUNDANESE', 'LEPCHA', 'IDEOGRAPHIC', 'HANGUL', 'SYLOTI',
'SAURASHTRA', 'KAYAH', 'REJANG', 'CHAM',
'VARIATION SELECTOR', 'KHAROSHTHI', 'MUSICAL SYMBOL',
'SAMARITAN', 'MANDAIC', 'TAI THAM', 'BATAK', 'VEDIC',
'COPTIC', 'TIFINAGH', 'BAMUM', 'JAVANESE', 'TAI VIET',
'MEETEI', 'MANICHAEAN', 'BRAHMI', 'KAITHI', 'CHAKMA',
'MAHAJANI', 'SHARADA', 'KHOJKI', 'KHUDAWADI', 'GRANTHA',
'TIRHUTA', 'SIDDHAM', 'MODI VOWEL', 'MODI SIGN', 'TAKRI',
'BASSA VAH', 'PAHAWH HMONG', 'MIAO', 'DUPLOYAN',
'MENDE KIKAKUI', 'AHOM', 'SIGNWRITING'):
if substring in name:
return False
return True
def is_combining_remove(code_point):
'''Check whether this is a combining character which should be listed
in the section of the translit_combining file where combining
characters are replaced by empty strings.
We ignore combining characters from many scripts here because
the original translit_combining file didn’t do this for the
combining characters from these scripts either and I am not
sure yet whether this would be useful to do for all combining
characters or not. For the moment I think it is better to keep
close to the spirit of the original file.
'''
if not unicode_utils.is_combining(code_point):
return False
name = unicode_utils.UNICODE_ATTRIBUTES[code_point]['name']
for substring in ('DEVANAGARI',
'BENGALI',
'CYRILLIC',
'SYRIAC',
'THAANA',
'NKO',
'GURMUKHI',
'TAMIL',
'GUJARATI',
'ORIYA',
'TELUGU',
'KANNADA',
'MALAYALAM',
'SINHALA',
'THAI',
'LAO',
'TIBETAN',
'MYANMAR',
'ETHIOPIC',
'TAGALOG',
'HANUNOO',
'BUHID',
'TAGBANWA',
'KHMER',
'MONGOLIAN',
'LIMBU',
'NEW TAI LUE',
'BUGINESE',
'BALINESE',
'SUNDANESE',
'LEPCHA',
'IDEOGRAPHIC',
'HANGUL',
'SYLOTI',
'SAURASHTRA',
'KAYAH',
'REJANG',
'CHAM',
'VARIATION SELECTOR',
'KHAROSHTHI',
'MUSICAL SYMBOL',
'SAMARITAN',
'MANDAIC',
'TAI THAM',
'BATAK',
'VEDIC',
'COPTIC',
'TIFINAGH',
'BAMUM',
'JAVANESE',
'TAI VIET',
'MEETEI',
'MANICHAEAN',
'BRAHMI',
'KAITHI',
'CHAKMA',
'MAHAJANI',
'SHARADA',
'KHOJKI',
'KHUDAWADI',
'GRANTHA',
'TIRHUTA',
'SIDDHAM',
'MODI VOWEL',
'MODI SIGN',
'TAKRI',
'BASSA VAH',
'PAHAWH HMONG',
'MIAO',
'DUPLOYAN',
'MENDE KIKAKUI',
'AHOM',
'SIGNWRITING'
):
if substring in name:
return False
return True
def is_combining_remove(code_point):
"""Check whether this is a combining character which should be listed
in the section of the translit_combining file where combining
characters are replaced by empty strings.
We ignore combining characters from many scripts here because
the original translit_combining file didn’t do this for the
combining characters from these scripts either and I am not
sure yet whether this would be useful to do for all combining
characters or not. For the moment I think it is better to keep
close to the spirit of the original file.
"""
if not unicode_utils.is_combining(code_point):
return False
name = unicode_utils.UNICODE_ATTRIBUTES[code_point]["name"]
for substring in (
"DEVANAGARI",
"BENGALI",
"CYRILLIC",
"SYRIAC",
"THAANA",
"NKO",
"GURMUKHI",
"TAMIL",
"GUJARATI",
"ORIYA",
"TELUGU",
"KANNADA",
"MALAYALAM",
"SINHALA",
"THAI",
"LAO",
"TIBETAN",
"MYANMAR",
"ETHIOPIC",
"TAGALOG",
"HANUNOO",
"BUHID",
"TAGBANWA",
"KHMER",
"MONGOLIAN",
"LIMBU",
"NEW TAI LUE",
"BUGINESE",
"BALINESE",
"SUNDANESE",
"LEPCHA",
"IDEOGRAPHIC",
"HANGUL",
"SYLOTI",
"SAURASHTRA",
"KAYAH",
"REJANG",
"CHAM",
"VARIATION SELECTOR",
"KHAROSHTHI",
"MUSICAL SYMBOL",
"SAMARITAN",
"MANDAIC",
"TAI THAM",
"BATAK",
"VEDIC",
"COPTIC",
"TIFINAGH",
"BAMUM",
"JAVANESE",
"TAI VIET",
"MEETEI",
"MANICHAEAN",
"BRAHMI",
"KAITHI",
"CHAKMA",
"MAHAJANI",
"SHARADA",
"KHOJKI",
"KHUDAWADI",
"GRANTHA",
"TIRHUTA",
"SIDDHAM",
"MODI VOWEL",
"MODI SIGN",
"TAKRI",
"BASSA VAH",
"PAHAWH HMONG",
"MIAO",
"DUPLOYAN",
"MENDE KIKAKUI",
"AHOM",
"SIGNWRITING",
):
if substring in name:
return False
return True