def _transliterate(self):
registry.register(HebrewLanguagePack, force=True)
registry.register(GreekLanguagePack, force=True)
if self.lang_id.code == 'el_GR':
self.transliteration = translit(self.name, 'el', reversed=True)
else:
self.transliteration = translit(self.name, 'he', reversed=True)
def test_33_register_unregister(self):
"""
Testing register/unregister.
"""
from transliterate.contrib.languages.hy.translit_language_pack import (
ArmenianLanguagePack)
class A(TranslitLanguagePack):
language_code = "ru"
language_name = "Example"
mapping = data.test_33_register_unregister_mapping
# Since key `ru` already exists in the registry it can't be replaced
# (without force-register).
res = registry.register(A)
self.assertTrue(not res)
# Now with force-register it can.
res = registry.register(A, force=True)
self.assertTrue(res)
# Once we have it there and it's forced, we can't register another.
res = registry.register(A, force=True)
self.assertTrue(not res)
# Unregister non-forced language pack.
res = registry.unregister(ArmenianLanguagePack)
self.assertTrue(res and not ArmenianLanguagePack.language_code
in get_available_language_codes())
res = registry.unregister(A)
self.assertTrue(not res
and A.language_code in get_available_language_codes())
def test_33_register_unregister(self):
"""
Testing register/unregister.
"""
from transliterate.contrib.languages.hy.translit_language_pack import ArmenianLanguagePack
class A(TranslitLanguagePack):
language_code = "ru"
language_name = "Example"
mapping = (
u"abcdefghij",
u"1234567890",
)
# Since key `ru` already exists in the registry it can't be replaced (without force-register).
res = registry.register(A)
self.assertTrue(not res)
# Now with force-register it can.
res = registry.register(A, force=True)
self.assertTrue(res)
# Once we have it there and it's forced, we can't register another.
res = registry.register(A, force=True)
self.assertTrue(not res)
# Unregister non-forced language pack.
res = registry.unregister(ArmenianLanguagePack)
self.assertTrue(res and not ArmenianLanguagePack.language_code in get_available_language_codes())
res = registry.unregister(A)
self.assertTrue(not res and A.language_code in get_available_language_codes())
def _transliterating(self):
if self.lang_id.name == 'Greek':
registry.register(GreekLanguagePack, force=True)
transliteration = translit(self.content, 'el', reversed=True)
elif self.lang_id.name == 'Hebrew':
registry.register(HebrewLanguagePack, force=True)
transliteration = translit(self.content, 'he', reversed=True)
return transliteration
def content_file_name(instance, filename):
autodiscover()
registry.register(KazakhLanguagePack)
ext = filename.split('.')[-1]
filename = "%s_%s_%s.%s" % (
str(instance.pk), translit(instance.last_name, 'kz', reversed=True),
translit(instance.first_name, 'kz', reversed=True), ext)
filename = filename.lower()
return os.path.join('portraits', filename)
def test_15_register_custom_language_pack(self):
"""Test registering of a custom language pack."""
class ExampleLanguagePack(TranslitLanguagePack):
"""Example language pack."""
language_code = "example"
language_name = "Example"
mapping = data.test_15_register_custom_language_pack_mapping
registry.register(ExampleLanguagePack)
assert 'example' in get_available_language_codes()
res = translit(self.latin_text, 'example')
self.assertEqual(res, 'Lor5m 9psum 4olor s9t 1m5t')
return res
def test_15_register_custom_language_pack(self):
"""
Testing registering of a custom language pack.
"""
class ExampleLanguagePack(TranslitLanguagePack):
"""
Example language pack.
"""
language_code = "example"
language_name = "Example"
mapping = data.test_15_register_custom_language_pack_mapping
registry.register(ExampleLanguagePack)
assert 'example' in get_available_language_codes()
res = translit(self.latin_text, 'example')
self.assertEqual(res, 'Lor5m 9psum 4olor s9t 1m5t')
return res
async def cyrillify(self, ctx, *text):
class ExampleLanguagePack(TranslitLanguagePack):
language_code = "custom"
language_name = "Custom"
mapping = (
"AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwYyZz",
"АаБбКкДдЕеФфГгХхИиЙйКкЛлМмНнОоПпКкРрСсТтУуВвУуЙйЗз",
)
pre_processor_mapping = {
"scht": "щ",
"sht": "щ",
"sh": "ш",
"tsch": "ч",
"tch": "ч",
"sch": "ш",
"zh": "ж",
"tz": "ц",
"ch": "ч",
"yu": "ю",
"ya": "я",
"x": "кс",
"ck": "к",
"ph": "ф",
}
chars = list(pre_processor_mapping.keys())
for lat in chars:
cyr = pre_processor_mapping[lat]
pre_processor_mapping[lat.capitalize()] = cyr.capitalize()
registry.register(ExampleLanguagePack)
if not text:
text = "Lorem ipsum dolor sit amet."
else:
text = " ".join(text)
await ctx.send(translit(text, "custom"))
def __test_34_latin_to_latin(self):
class LatinToLatinLanguagePack(TranslitLanguagePack):
"""
Custom language pack which gets rid of accented characters in Greek but leaves other characters intact.
"""
language_code = "l2l"
language_name = "Latin to Latin"
mapping = data.test_34_latin_to_latin_mapping
characters = data.test_34_latin_to_latin_characters
reversed_characters = data.test_34_latin_to_latin_reversed_characters
res = registry.register(LatinToLatinLanguagePack)
self.assertTrue(res)
text = data.test_34_latin_to_latin_text
pack = LatinToLatinLanguagePack()
res = pack.translit(text, strict=True, fail_silently=False)
def __test_34_latin_to_latin(self):
class LatinToLatinLanguagePack(TranslitLanguagePack):
"""
Custom language pack which gets rid of accented characters in Greek but leaves other characters intact.
"""
language_code = "l2l"
language_name = "Latin to Latin"
mapping = data.test_34_latin_to_latin_mapping
characters = data.test_34_latin_to_latin_characters
reversed_characters = data.test_34_latin_to_latin_reversed_characters
res = registry.register(LatinToLatinLanguagePack)
self.assertTrue(res)
text = data.test_34_latin_to_latin_text
pack = LatinToLatinLanguagePack()
res = pack.translit(text, strict=True, fail_silently=False)
:example:
>>> from foo.greekunaccented import *
>>> from transliterate import translit
>>> print translit(u'άέήίϊΐόύϋΰώΆΈΉΊΪΌΎΫΏ', 'el2')
αεηιιιουυυωΑΕΗΙΙΟΥΥΩ
"""
from transliterate import translit
from transliterate.discover import autodiscover
from transliterate.base import TranslitLanguagePack, registry
# First autodicover bundled language packs.
autodiscover()
class GreekUnaccentedLanguagePack(TranslitLanguagePack):
"""
Custom language pack which gets rid of accented characters in Greek but leaves other characters intact.
"""
language_code = "el2"
language_name = "Greek without accented characters"
mapping = (
u"άέήίϊΐόύϋΰώΆΈΉΊΪΌΎΫΏ",
u"αεηιιιουυυωΑΕΗΙΙΟΥΥΩ",
)
# Register
registry.register(GreekUnaccentedLanguagePack)
# -*- coding: utf-8 -*-
__title__ = 'transliterate.contrib.languages.uk.translit_language_pack'
__author__ = 'Timofey Pchelintsev'
__copyright__ = '2014-2015 Timofey Pchelintsev'
__license__ = 'GPL 2.0/LGPL 2.1'
__all__ = ('UkrainianLanguagePack', )
from transliterate.base import TranslitLanguagePack, registry
from transliterate.contrib.languages.uk import data
class UkrainianLanguagePack(TranslitLanguagePack):
"""
Language pack for Ukrainian language.
See `http://en.wikipedia.org/wiki/Ukrainian_alphabet` for details.
"""
language_code = "uk"
language_name = "Ukrainian"
character_ranges = ((0x0400, 0x04FF), (0x0500, 0x052F))
mapping = data.mapping
reversed_specific_mapping = data.reversed_specific_mapping
pre_processor_mapping = data.pre_processor_mapping
registry.register(UkrainianLanguagePack)
widgets = [Percentage(), Bar('>'), ' ', ETA(), ' ']
pbar = ProgressBar(widgets=widgets, maxval=10000000)
autodiscover()
class ReverseInverseRussianLanguagePack(TranslitLanguagePack):
language_code = "ru_inv_en"
language_name = "ru_inv_en"
mapping = (
u"йцукенгшщзхъфывапролджэёячсмитьбю",
u"qwertyuiop[]asdfghjkl;'\zxcvbnm,.",
)
registry.register(ReverseInverseRussianLanguagePack)
def _reporthook(numblocks, blocksize, filesize, url=None):
base = os.path.basename(url)
try:
percent = min((numblocks * blocksize * 100) / filesize, 100)
except:
percent = 100
if numblocks != 0:
sys.stdout.write("\b" * 70)
sys.stdout.write("%-66s%3d%%" % (base, percent))
def downloaddictionaries(dictionary_strings):
url = dictionary_urls[dictionary_strings]
# -*- coding: utf-8 -*-
from transliterate.base import TranslitLanguagePack, registry
from transliterate.contrib.languages.el import data
__title__ = 'transliterate.contrib.languages.el.translit_language_pack'
__author__ = 'Artur Barseghyan'
__copyright__ = '2013-2018 Artur Barseghyan'
__license__ = 'GPL-2.0-only OR LGPL-2.1-or-later'
__all__ = ('GreekLanguagePack',)
class GreekLanguagePack(TranslitLanguagePack):
"""Language pack for Greek language.
See `http://en.wikipedia.org/wiki/Greek_alphabet` and
`https://en.wikipedia.org/wiki/Romanization_of_Greek#Modern_Greek`
for details.
"""
language_code = "el"
language_name = "Greek"
character_ranges = ((0x0370, 0x03FF), (0x1F00, 0x1FFF))
mapping = data.mapping
reversed_specific_mapping = data.reversed_specific_mapping
pre_processor_mapping = data.pre_processor_mapping
detectable = True
registry.register(GreekLanguagePack)
)
# TODO
# reversed_specific_mapping = (
# )
# TODO
# reversed_specific_pre_processor_mapping = {
# }
pre_processor_mapping = {
u"ч": u"ch",
u"щ": u"şh",
u"ю": u"iu",
u"я": u"ia",
u"Ч": u"Ch",
u"Щ": u"Şh",
u"Ю": u"İu",
u"Я": u"İa",
}
registry.register(KazakhLanguagePack)
translit_kk = get_translit_function("kk")
def translit(value: str) -> str:
"""Transliterate the text."""
return translit_kk(value)
# -*- coding: utf-8 -*-
from transliterate.base import TranslitLanguagePack, registry
from transliterate.contrib.languages.sr import data
__title__ = 'transliterate.contrib.languages.sr.translit_language_pack'
__author__ = 'Saša Kelečević'
__copyright__ = '2017 Saša Kelečević'
__license__ = 'GPL-2.0-only OR LGPL-2.1-or-later'
__all__ = ('SerbianLanguagePack',)
class SerbianLanguagePack(TranslitLanguagePack):
"""Language pack for Serbian language.
See https://en.wikipedia.org/wiki/Romanization_of_Serbian for details.
"""
language_code = "sr"
language_name = "Serbian"
character_ranges = ((0x0408, 0x04F0), (0x0000, 0x017F))
mapping = data.mapping
reversed_specific_mapping = data.reversed_specific_mapping
pre_processor_mapping = data.pre_processor_mapping
detectable = False
registry.register(SerbianLanguagePack)
u"ю": u"yu",
u"я": u"ya",
u"Е": u"Ye",
u"Ё": u"Yo",
u"Ж": u"ZH",
u"Х": u"Kh",
u"Ц": u"Ts",
u"Ч": u"Ch",
u"Ш": u"Sh",
u"Щ": u"Shch",
u"Ю": u"Yu",
u"Я": u"Ya",
}
registry.register(LanguagePack)
def get_cities(page, count):
if page == 1:
page = 0
else:
page = (page - 1) * count
results = []
file = open('RU.txt', 'r', encoding='utf-8')
lines = file.readlines()
for i in range(page, page + count):
try:
city = main_dictionary(lines[i])
results.append(city)
# -*- coding: utf-8 -*-
__title__ = 'transliterate.contrib.languages.mk.translit_language_pack'
__author__ = 'Igor Stamatovski'
__copyright__ = '2016 Igor Stamatovski'
__license__ = 'GPL 2.0/LGPL 2.1'
__all__ = ('MacedonianLanguagePack', )
from transliterate.base import TranslitLanguagePack, registry
from transliterate.contrib.languages.mk import data
class MacedonianLanguagePack(TranslitLanguagePack):
"""
Language pack for Macedonian language.
See http://en.wikipedia.org/wiki/Romanization_of_Macedonian for details.
"""
language_code = "mk"
language_name = "Macedonian"
character_ranges = ((0x0400, 0x04FF), (0x0500, 0x052F))
mapping = data.mapping
reversed_specific_mapping = data.reversed_specific_mapping
pre_processor_mapping = data.pre_processor_mapping
detectable = False
registry.register(MacedonianLanguagePack)
u'Є': 'E',
u'Ж': 'J',
u'З': 'Z',
u'И': 'I',
u'І': 'I',
u'Ї': 'Yi',
u'Й': 'Y',
u'К': 'K',
u'Л': 'L',
u'М': 'M',
u'Н': 'N',
u'О': 'O',
u'П': 'P',
u'Р': 'R',
u'С': 'S',
u'Т': 'T',
u'У': 'U',
u'Ф': 'F',
u'Х': 'H',
u'Ц': 'C',
u'Ч': 'Ch',
u'Ш': 'Sh',
u'Щ': "Sh'",
u'Ь': "'",
u'Ю': 'Yu',
u'Я': 'Ya',
}
registry.register(UkrainskiyLanguagePack, force=True)
print '\nRegistering custom language pack\n---------------------------------------'
from transliterate.base import TranslitLanguagePack, registry
class ExampleLanguagePack(TranslitLanguagePack):
"""
Example language pack.
"""
language_code = "example"
language_name = "Example"
mapping = (
u"abcdefghij",
u"1234567890",
)
registry.register(ExampleLanguagePack)
print '\nList of available (registered) languages after registering a new language pack \n---------------------------------------'
print get_available_language_codes()
print '\nTransliteration to Example\n---------------------------------------'
print translit(text, 'example')
print '\nTransliterated lorem ipsum generator \n---------------------------------------'
from transliterate.contrib.apps.translipsum import TranslipsumGenerator
g_am = TranslipsumGenerator(language_code='hy')
print 'Generating paragraphs'
print g_am.generate_paragraph()
g_ru = TranslipsumGenerator(language_code='ru')
# -*- coding: utf-8 -*-
"""
Latin to Latin example.
"""
from transliterate import translit
from transliterate.discover import autodiscover
from transliterate.base import TranslitLanguagePack, registry
# First autodicover bundled language packs.
autodiscover()
class LatinToLatinLanguagePack(TranslitLanguagePack):
"""
Custom language pack which gets rid of accented characters in Greek but leaves other characters intact.
"""
language_code = "l2l"
language_name = "Latin to Latin"
mapping = (
u"abgdezilxkhmjnpsvtrcqw&ofABGDEZILXKHMJNPSVTRCQOFW",
u"zbgdeailxkhnjmpswtrcqv&ofZBGDEAILXKHNJMPSWTRCQOFV",
)
characters = u"abgdezilxkhmjnpsvtrcqw&ofABGDEZILXKHMJNPSVTRCQOFW"
reversed_characters = u"abgdezilxkhmjnpsvtrcqw&ofABGDEZILXKHMJNPSVTRCQOFW"
# Register
registry.register(LatinToLatinLanguagePack)
# -*- coding: utf-8 -*-
__title__ = 'transliterate.contrib.languages.mk.translit_language_pack'
__author__ = 'Igor Stamatovski'
__copyright__ = '2016 Igor Stamatovski'
__license__ = 'GPL 2.0/LGPL 2.1'
__all__ = ('MacedonianLanguagePack',)
from transliterate.base import TranslitLanguagePack, registry
from transliterate.contrib.languages.mk import data
class MacedonianLanguagePack(TranslitLanguagePack):
"""
Language pack for Macedonian language.
See http://en.wikipedia.org/wiki/Romanization_of_Macedonian for details.
"""
language_code = "mk"
language_name = "Macedonian"
character_ranges = ((0x0400, 0x04FF), (0x0500, 0x052F))
mapping = data.mapping
reversed_specific_mapping = data.reversed_specific_mapping
pre_processor_mapping = data.pre_processor_mapping
detectable = False
registry.register(MacedonianLanguagePack)
u"Shch": u"Щ",
# u"Iu": u"Ю",
# u"Ia": u"Я",
u"Yu": u"Ю",
u"Ya": u"Я",
}
reversed_specific_pre_processor_mapping = {
u"ъ": u"",
u"ь": u"",
u"Ъ": u"",
u"Ь": u""
}
registry.register(Gost2006RuLangPack, force=True)
LANG_PADDING = max([len(lang) for lang in get_available_language_codes()])
@lru_cache
def transliterate(text, lang='ru-gost', reversed=True):
trans = translit(text, lang, reversed)
print(f"translit[{lang:{LANG_PADDING}}]: {text} => {trans}")
if trans.isascii():
return trans
else:
for i in trans:
if not i.isascii():
print(i, i.isascii())
See `http://en.wikipedia.org/wiki/Georgian_alphabet for details.
"""
language_code = "ka"
language_name = "Georgian"
character_ranges = ((0x10A0, 0x10C5), (0x10D0, 0x10FC), (0x2D00, 0x2D25))
mapping = data.mapping
pre_processor_mapping = data.pre_processor_mapping
detectable = True
def translit(self,
value,
reversed=False,
strict=False,
fail_silently=True):
# Georgian language knows no capitals. Therefore, we convert
# everything to lowercase.
value = value.lower()
# Continue the standard way
return super(GeorgianLanguagePack, self).translit(
value=value,
reversed=reversed,
strict=strict,
fail_silently=fail_silently
)
registry.register(GeorgianLanguagePack)
from transliterate.base import TranslitLanguagePack, registry
from transliterate.contrib.languages.l1 import data
__title__ = 'transliterate.contrib.languages.l1.translit_language_pack'
__author__ = 'Marco Pattaro'
__copyright__ = '2016-2017 Marco Pattaro'
__license__ = 'GPL-2.0-only OR LGPL-2.1-or-later'
__all__ = ('Latin1SupplementLanguagePack',)
class Latin1SupplementLanguagePack(TranslitLanguagePack):
"""Language pack for Latin1 Supplement.
Though not exactly a language, it's a set of commonly found unicode
characters. See
`http://en.wikipedia.org/wiki/Latin-1_Supplement_%28Unicode_block%29` for
details.
"""
language_code = "l1"
language_name = "Latin1 Supplement"
character_ranges = ((0x00C0, 0x00D6), (0x00D8, 0x00F6), (0x00F8, 0x00FF))
mapping = data.mapping
reversed_specific_mapping = data.reversed_specific_mapping
reversed_specific_pre_processor_mapping = \
data.reversed_specific_pre_processor_mapping
detectable = True
registry.register(Latin1SupplementLanguagePack)
from transliterate.base import TranslitLanguagePack, registry
class ExampleLanguagePack(TranslitLanguagePack):
"""
Example language pack.
"""
language_code = "example"
language_name = "Example"
mapping = (
u"abcdefghij",
u"1234567890",
)
registry.register(ExampleLanguagePack)
print '\nList of available (registered) languages after registering a new language pack \n---------------------------------------'
print get_available_language_codes()
print '\nTransliteration to Example\n---------------------------------------'
print translit(text, 'example')
print '\nTransliterated lorem ipsum generator \n---------------------------------------'
from transliterate.contrib.apps.translipsum import TranslipsumGenerator
g_am = TranslipsumGenerator(language_code='hy')
print 'Generating paragraphs'
print g_am.generate_paragraph()
g_ru = TranslipsumGenerator(language_code='ru')
u'ф': u'f',
u'х': u'h',
u'ц': u'ts',
u'ч': u'ch',
u'ш': u'sh',
u'щ': u'sch',
u'ъ': u'',
u'ы': u'y',
u'ь': u'',
u'э': u'e',
u'ю': u'yu',
u'я': u'ya',
}
registry.register(ExampleLanguagePack, force=True)
print(get_available_language_codes())
# ['el', 'hy', 'ka', 'ru', 'example']
text = '40 лет Октября'
def transliterate(text):
trans = translit(text, 'example')
print(trans)
return trans
if __name__ == "__main__":
transliterate('Коммунистическая')
from transliterate import get_available_language_codes, translit, slugify
from transliterate.base import TranslitLanguagePack, registry
from transliterate.contrib.languages.ru.translit_language_pack import RussianLanguagePack
from functools import lru_cache
registry.register(RussianLanguagePack)
class ExampleLanguagePack(TranslitLanguagePack):
language_code = "example"
language_name = "Example"
mapping = {u"", u""}
pre_processor_mapping = {
u'А': u'A',
u'Б': u'B',
u'В': u'V',
u'Г': u'G',
u'Д': u'D',
u'Е': u'E',
u'Ё': u'E',
u'Ж': u'Zh',
u'З': u'Z',
u'И': u'I',
u'Й': u'Y',
u'К': u'K',
u'Л': u'L',
u'М': u'M',
u'Н': u'N',
u'О': u'O',
u'П': u'P',
# -*- coding: utf-8 -*-
__title__ = 'transliterate.contrib.languages.hy.translit_language_pack'
__author__ = 'Artur Barseghyan'
__copyright__ = 'Copyright (c) 2013 Artur Barseghyan'
__license__ = 'GPL 2.0/LGPL 2.1'
__all__ = ('ArmenianLanguagePack', )
from transliterate.base import TranslitLanguagePack, registry
from transliterate.contrib.languages.hy import data
class ArmenianLanguagePack(TranslitLanguagePack):
"""
Language pack for Armenian language. See https://en.wikipedia.org/wiki/Armenian_alphabet for details.
"""
language_code = "hy"
language_name = "Armenian"
character_ranges = ((0x0530, 0x058F), (0xFB10, 0xFB1F))
mapping = data.mapping
reversed_specific_mapping = data.reversed_specific_mapping
reversed_specific_pre_processor_mapping = data.reversed_specific_pre_processor_mapping
pre_processor_mapping = data.pre_processor_mapping
detectable = True
registry.register(ArmenianLanguagePack)
widgets = [Percentage(), Bar('>'), ' ', ETA(), ' ']
pbar = ProgressBar(widgets=widgets, maxval=10000000)
autodiscover()
class ReverseInverseRussianLanguagePack(TranslitLanguagePack):
language_code = "ru_inv_en"
language_name = "ru_inv_en"
mapping = (
u"йцукенгшщзхъфывапролджэёячсмитьбю",
u"qwertyuiop[]asdfghjkl;'\zxcvbnm,.",
)
registry.register(ReverseInverseRussianLanguagePack)
def _reporthook(numblocks, blocksize, filesize, url=None):
base = os.path.basename(url)
try:
percent = min((numblocks * blocksize * 100) / filesize, 100)
except:
percent = 100
if numblocks != 0:
sys.stdout.write("\b" * 70)
sys.stdout.write("%-66s%3d%%" % (base, percent))
def downloaddictionaries(dictionary_strings):
# -*- coding: utf-8 -*-
__title__ = 'transliterate.contrib.languages.ru.translit_language_pack'
__author__ = 'Artur Barseghyan'
__copyright__ = '2013-2015 Artur Barseghyan'
__license__ = 'GPL 2.0/LGPL 2.1'
__all__ = ('RussianLanguagePack',)
from transliterate.base import TranslitLanguagePack, registry
from transliterate.contrib.languages.ru import data
class RussianLanguagePack(TranslitLanguagePack):
"""
Language pack for Russian language. See
`http://en.wikipedia.org/wiki/Russian_alphabet` for details.
"""
language_code = "ru"
language_name = "Russian"
character_ranges = ((0x0400, 0x04FF), (0x0500, 0x052F))
mapping = data.mapping
reversed_specific_mapping = data.reversed_specific_mapping
pre_processor_mapping = data.pre_processor_mapping
detectable = True
registry.register(RussianLanguagePack)
from typing import Iterator, TYPE_CHECKING
from algoliasearch_django import raw_search
from django.db import models
from django.utils.translation import ugettext_lazy as _
from transliterate import translit
from transliterate.base import registry
from cinemanio.api.helpers import global_id
from cinemanio.core.translit.ru import RussianLanguagePack
if TYPE_CHECKING:
from django.db.models import QuerySet # noqa
from typing import Iterable, List # noqa
registry.register(RussianLanguagePack)
class BaseModel(models.Model):
"""
Base model for Movie and Person
"""
# TODO: remove field
slug = models.SlugField(_('Slug'),
max_length=100,
unique=True,
null=True,
blank=True)
site_official_url = models.URLField(_('Official site'),
null=True,
# -*- coding: utf-8 -*-
__title__ = 'transliterate.contrib.languages.bg.translit_language_pack'
__author__ = 'Petar Chakarov'
__copyright__ = 'Copyright (c) 2014 Petar Chakarov'
__license__ = 'GPL 2.0/LGPL 2.1'
__all__ = ('BulgarianLanguagePack', )
from transliterate.base import TranslitLanguagePack, registry
from transliterate.contrib.languages.bg import data
class BulgarianLanguagePack(TranslitLanguagePack):
"""
Language pack for Bulgarian language.
See http://en.wikipedia.org/wiki/Romanization_of_Bulgarian for details.
"""
language_code = "bg"
language_name = "Bulgarian"
character_ranges = ((0x0400, 0x04FF), (0x0500, 0x052F))
mapping = data.mapping
reversed_specific_mapping = data.reversed_specific_mapping
pre_processor_mapping = data.pre_processor_mapping
detectable = False
registry.register(BulgarianLanguagePack)
# -*- coding: utf-8 -*-
from transliterate.base import TranslitLanguagePack, registry
from transliterate.contrib.languages.mn import data
__title__ = 'transliterate.contrib.languages.mn.translit_language_pack'
__author__ = 'Enkhbold Bataa'
__copyright__ = '2016 Enkhbold Bataa'
__license__ = 'GPL 2.0/LGPL 2.1'
__all__ = ('MongolianLanguagePack',)
class MongolianLanguagePack(TranslitLanguagePack):
"""Language pack for Mongolian language.
See `https://en.wikipedia.org/wiki/Mongolian_Cyrillic_alphabet` for
details.
"""
language_code = "mn"
language_name = "Mongolian"
character_ranges = ((0x0400, 0x04FF), (0x0500, 0x052F))
mapping = data.mapping
reversed_specific_mapping = data.reversed_specific_mapping
pre_processor_mapping = data.pre_processor_mapping
detectable = False
registry.register(MongolianLanguagePack)
# -*- coding: utf-8 -*-
from transliterate.base import TranslitLanguagePack, registry
from transliterate.contrib.languages.uk import data
__title__ = 'transliterate.contrib.languages.uk.translit_language_pack'
__author__ = 'Timofey Pchelintsev'
__copyright__ = '2014-2015 Timofey Pchelintsev'
__license__ = 'GPL-2.0-only OR LGPL-2.1-or-later'
__all__ = ('UkrainianLanguagePack',)
class UkrainianLanguagePack(TranslitLanguagePack):
"""Language pack for Ukrainian language.
See `http://en.wikipedia.org/wiki/Ukrainian_alphabet` for details.
"""
language_code = "uk"
language_name = "Ukrainian"
character_ranges = ((0x0400, 0x04FF), (0x0500, 0x052F))
mapping = data.mapping
reversed_specific_mapping = data.reversed_specific_mapping
pre_processor_mapping = data.pre_processor_mapping
registry.register(UkrainianLanguagePack)
u"ч": u"ch",
u"Ш": u"Sh",
u"ш": u"sh",
u"Щ": u"Shch",
u"щ": u"shch",
u"Ю": u"Yu",
u"ю": u"iu",
u"Я": u"Ya",
u"я": u"ia",
u"ь": u"",
u"ъ": u"",
u"\'": u"",
}
registry.register(UkrTranslitLanguagePack)
def transliterateField(request):
fieldData = request.GET.get('fieldData')
# print(translit(fieldData, 'en'))
print(get_available_language_codes())
print(translit(fieldData, 'ukrTranslit'))
fieldData = fieldData.lower().title()
data = {
'transliteration': translit(fieldData, 'ukrTranslit'),
}
return JsonResponse(data)
def translit2ru(s):
registry.register(ImprovedRussianLanguagePack)
return translit(s.replace(u"zhy",u"жи").replace(u"Zhy",u"Жи"), 'ru_new')
# -*- coding: utf-8 -*-
"""
Latin to Latin example.
"""
from transliterate import translit
from transliterate.discover import autodiscover
from transliterate.base import TranslitLanguagePack, registry
# First autodicover bundled language packs.
autodiscover()
class LatinToLatinLanguagePack(TranslitLanguagePack):
"""
Custom language pack which gets rid of accented characters in Greek but leaves other characters intact.
"""
language_code = "l2l"
language_name = "Latin to Latin"
mapping = (
u"abgdezilxkhmjnpsvtrcqw&ofABGDEZILXKHMJNPSVTRCQOFW",
u"zbgdeailxkhnjmpswtrcqv&ofZBGDEAILXKHNJMPSWTRCQOFV",
)
characters = u"abgdezilxkhmjnpsvtrcqw&ofABGDEZILXKHMJNPSVTRCQOFW"
reversed_characters = u"abgdezilxkhmjnpsvtrcqw&ofABGDEZILXKHMJNPSVTRCQOFW"
# Register
registry.register(LatinToLatinLanguagePack)
u"dz": u"ձ",
u"gh": u"ղ",
u"tch": u"ճ",
u"sh": u"շ",
u"vo": u"ո",
u"ch": u"չ",
u"dj": u"ջ",
u"ph": u"փ",
u"u": u"ու",
# uppercase
u"E'": u"Է",
u"Y": u"Ը",
u"Th": u"Թ",
u"Jh": u"Ժ",
u"Ts": u"Ծ",
u"Dz": u"Ձ",
u"Gh": u"Ղ",
u"Tch": u"Ճ",
u"Sh": u"Շ",
u"Vo": u"Ո",
u"Ch": u"Չ",
u"Dj": u"Ջ",
u"Ph": u"Փ",
u"U": u"Ու"
}
detectable = True
registry.register(ArmenianLanguagePack)
"""Language pack for Georgian language.
See `http://en.wikipedia.org/wiki/Georgian_alphabet for details.
"""
language_code = "ka"
language_name = "Georgian"
character_ranges = ((0x10A0, 0x10C5), (0x10D0, 0x10FC), (0x2D00, 0x2D25))
mapping = data.mapping
pre_processor_mapping = data.pre_processor_mapping
detectable = True
def translit(self,
value,
reversed=False,
strict=False,
fail_silently=True):
# Georgian language knows no capitals. Therefore, we convert
# everything to lowercase.
value = value.lower()
# Continue the standard way
return super(GeorgianLanguagePack,
self).translit(value=value,
reversed=reversed,
strict=strict,
fail_silently=fail_silently)
registry.register(GeorgianLanguagePack)
# -*- coding: utf-8 -*-
from transliterate.base import TranslitLanguagePack, registry
from transliterate.contrib.languages.el import data
__title__ = 'transliterate.contrib.languages.el.translit_language_pack'
__author__ = 'Artur Barseghyan'
__copyright__ = '2013-2018 Artur Barseghyan'
__license__ = 'GPL-2.0-only OR LGPL-2.1-or-later'
__all__ = ('GreekLanguagePack', )
class GreekLanguagePack(TranslitLanguagePack):
"""Language pack for Greek language.
See `http://en.wikipedia.org/wiki/Greek_alphabet` and
`https://en.wikipedia.org/wiki/Romanization_of_Greek#Modern_Greek`
for details.
"""
language_code = "el"
language_name = "Greek"
character_ranges = ((0x0370, 0x03FF), (0x1F00, 0x1FFF))
mapping = data.mapping
reversed_specific_mapping = data.reversed_specific_mapping
pre_processor_mapping = data.pre_processor_mapping
detectable = True
registry.register(GreekLanguagePack)
# -*- coding: utf-8 -*-
from transliterate.base import TranslitLanguagePack, registry
from transliterate.contrib.languages.mn import data
__title__ = 'transliterate.contrib.languages.mn.translit_language_pack'
__author__ = 'Enkhbold Bataa'
__copyright__ = '2016 Enkhbold Bataa'
__license__ = 'GPL-2.0-only OR LGPL-2.1-or-later'
__all__ = ('MongolianLanguagePack',)
class MongolianLanguagePack(TranslitLanguagePack):
"""Language pack for Mongolian language.
See `https://en.wikipedia.org/wiki/Mongolian_Cyrillic_alphabet` for
details.
"""
language_code = "mn"
language_name = "Mongolian"
character_ranges = ((0x0400, 0x04FF), (0x0500, 0x052F))
mapping = data.mapping
reversed_specific_mapping = data.reversed_specific_mapping
pre_processor_mapping = data.pre_processor_mapping
detectable = False
registry.register(MongolianLanguagePack)
# -*- coding: utf-8 -*-
from transliterate.base import TranslitLanguagePack, registry
from transliterate.contrib.languages.sr import data
__title__ = 'transliterate.contrib.languages.sr.translit_language_pack'
__author__ = 'Saša Kelečević'
__copyright__ = '2017 Saša Kelečević'
__license__ = 'GPL 2.0/LGPL 2.1'
__all__ = ('SerbianLanguagePack',)
class SerbianLanguagePack(TranslitLanguagePack):
"""Language pack for Serbian language.
See https://en.wikipedia.org/wiki/Romanization_of_Serbian for details.
"""
language_code = "sr"
language_name = "Serbian"
character_ranges = ((0x0408, 0x04F0), (0x0000, 0x017F))
mapping = data.mapping
reversed_specific_mapping = data.reversed_specific_mapping
pre_processor_mapping = data.pre_processor_mapping
detectable = False
registry.register(SerbianLanguagePack)
# -*- coding: utf-8 -*-
__title__ = 'transliterate.contrib.languages.bg.translit_language_pack'
__author__ = 'Petar Chakarov'
__copyright__ = 'Copyright (c) 2014 Petar Chakarov'
__license__ = 'GPL 2.0/LGPL 2.1'
__all__ = ('BulgarianLanguagePack',)
from transliterate.base import TranslitLanguagePack, registry
from transliterate.contrib.languages.bg import data
class BulgarianLanguagePack(TranslitLanguagePack):
"""
Language pack for Bulgarian language.
See http://en.wikipedia.org/wiki/Romanization_of_Bulgarian for details.
"""
language_code = "bg"
language_name = "Bulgarian"
character_ranges = ((0x0400, 0x04FF), (0x0500, 0x052F))
mapping = data.mapping
reversed_specific_mapping = data.reversed_specific_mapping
pre_processor_mapping = data.pre_processor_mapping
detectable = False
registry.register(BulgarianLanguagePack)
get rid of accented characters in Greek but leave other characters intact.
:example:
>>> from foo.greekunaccented import *
>>> from transliterate import translit
>>> print translit(u'άέήίϊΐόύϋΰώΆΈΉΊΪΌΎΫΏ', 'el2')
αεηιιιουυυωΑΕΗΙΙΟΥΥΩ
"""
from transliterate import translit
from transliterate.discover import autodiscover
from transliterate.base import TranslitLanguagePack, registry
# First autodicover bundled language packs.
autodiscover()
class GreekUnaccentedLanguagePack(TranslitLanguagePack):
"""
Custom language pack which gets rid of accented characters in Greek but leaves other characters intact.
"""
language_code = "el2"
language_name = "Greek without accented characters"
mapping = (
u"άέήίϊΐόύϋΰώΆΈΉΊΪΌΎΫΏ",
u"αεηιιιουυυωΑΕΗΙΙΟΥΥΩ",
)
# Register
registry.register(GreekUnaccentedLanguagePack)
from transliterate.base import TranslitLanguagePack, registry
from transliterate.discover import autodiscover
from transliterate import translit
autodiscover()
class CzechLanguagePack(TranslitLanguagePack):
language_code = 'cs'
language_name = 'Czech'
pre_processor_mapping = {u'ch': u'ch'}
mapping = (u'aábcčdďeéěfghiíjklmnňoópqrřsštťuúůvwxyýzž',
u'aabccddeeefghiijklmnnoopqrrssttuuuvwxyyzz')
registry.register(CzechLanguagePack)
class Translit:
def __init__(self):
pass
@staticmethod
def translit(string):
# Try CZ
string = translit(string, 'cs')
# Normalize for RU chars
string = translit(string, 'ru', reversed=True)
# Remove spaces and punctuation