diff --git a/utils/Sync/settings.py b/utils/Sync/settings.py index ca9122fd..306946a7 100644 --- a/utils/Sync/settings.py +++ b/utils/Sync/settings.py @@ -14,23 +14,6 @@ default_description_version = 1 database_uri = os.environ['MONGO_URI'] -CYR_LOWER = 'йцукенгшщзхъфывапролджэячсмитьбю' -CYR_UPPER = 'ЙЦУКЕНГШЩЗХЪФЫВАПРОЛДЖЭЯЧСМИТЬБЮ' -EN_LOWER = 'qwertyuiopasdfghjklzxcvbnm' -EN_UPPER = 'QWERTYUIOPASDFGHJKLZXCVBNM' -DIGITS = '0123456789' -description_available_chars = CYR_LOWER + CYR_UPPER + EN_LOWER + EN_UPPER + DIGITS + ' _-' - -translit_table = ( - ['а', 'б', 'в', 'г', 'д', 'е', 'ё', 'ж', 'з', 'и', 'й', 'к', 'л', 'м', 'н', 'о', 'п', 'р', 'с', 'т', 'у', 'ф', 'х', - 'ц', 'ч', 'ш', 'щ', 'ъ', 'ы', 'ь', 'э', 'ю', 'я', 'А', 'Б', 'В', 'Г', 'Д', 'Е', 'Ё', 'Ж', 'З', 'И', 'Й', 'К', 'Л', - 'М', 'Н', 'О', 'П', 'Р', 'С', 'Т', 'У', 'Ф', 'Х', 'Ц', 'Ч', 'Ш', 'Щ', 'Ъ', 'Ы', 'Ь', 'Э', 'Ю', 'Я', '̆'], - ['a', 'b', 'v', 'g', 'd', 'e', 'e', 'zh', 'z', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'r', 's', 't', 'u', 'f', 'h', - 'z', 'ch', 'sh', 'sch', '_', 'y', '_', 'e', 'yu', 'ya', 'A', 'B', 'V', 'G', 'D', 'E', 'E', 'ZH', 'Z', 'I', 'J', - 'K', 'L', 'M', 'N', 'O', 'P', 'R', 'S', 'T', 'U', 'F', 'H', 'Z', 'CH', 'SH', 'SCH', '_', 'Y', '_', 'E', 'YU', 'YA', - '_'] -) - teachers_names = { 'Н.В.Андреева': 'nv-andreeva', 'И.Н.Втюрина': 'in-vturina', diff --git a/utils/Sync/utils/text/transform.py b/utils/Sync/utils/text/transform.py index 088a3b8e..323a868b 100644 --- a/utils/Sync/utils/text/transform.py +++ b/utils/Sync/utils/text/transform.py @@ -1,33 +1,18 @@ import re -from functools import reduce -import settings +from unidecode import unidecode + from utils.fn import iterate_over_fns -remove_pattr = re.compile('[«»,!&]') +remove_pattr = re.compile('[«»,!&"\']') reduce_dash_pattr = re.compile('[-]+') def translit(text): """ RUSSIAN TEXT => ENGLISH TEXT - based on table like: - ( - ['а', 'б', 'в'], - ['a', 'b', 'v'] - ) - Leave if character is not founded """ - table = settings.translit_table - ins, outs = table - out = lambda i: outs[ins.index(i)] - replace = lambda i: out(i) if i in ins else i - - return reduce( - lambda t, i: t + replace(i), - list(text), - '' - ) + return unidecode(text) def interpolate(text, storage, key_fn=None):