spaCy/spacy/lang/tt/tokenizer_exceptions.py
Aliia E 428bae66b5 Add Tatar Language Support (#2444)
* add Tatar lang support

* add Tatar letters

* add Tatar tests

* sign contributor agreement

* sign contributor agreement [x]

* remove comments from Language class

* remove all template comments
2018-06-19 10:17:53 +02:00

53 lines
1.8 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# coding: utf8
from __future__ import unicode_literals
from ...symbols import ORTH, LEMMA, NORM
_exc = {}
_abbrev_exc = [
# Weekdays abbreviations
{ORTH: "дш", LEMMA: "дүшәмбе"},
{ORTH: "сш", LEMMA: "сишәмбе"},
{ORTH: "чш", LEMMA: "чәршәмбе"},
{ORTH: "пш", LEMMA: "пәнҗешәмбе"},
{ORTH: "җм", LEMMA: "җомга"},
{ORTH: "шб", LEMMA: "шимбә"},
{ORTH: "яш", LEMMA: "якшәмбе"},
# Months abbreviations
{ORTH: "гый", LEMMA: "гыйнвар"},
{ORTH: "фев", LEMMA: "февраль"},
{ORTH: "мар", LEMMA: "март"},
{ORTH: "мар", LEMMA: "март"},
{ORTH: "апр", LEMMA: "апрель"},
{ORTH: "июн", LEMMA: "июнь"},
{ORTH: "июл", LEMMA: "июль"},
{ORTH: "авг", LEMMA: "август"},
{ORTH: "сен", LEMMA: "сентябрь"},
{ORTH: "окт", LEMMA: "октябрь"},
{ORTH: "ноя", LEMMA: "ноябрь"},
{ORTH: "дек", LEMMA: "декабрь"},
# Number abbreviations
{ORTH: "млрд", LEMMA: "миллиард"},
{ORTH: "млн", LEMMA: "миллион"},
]
for abbr in _abbrev_exc:
for orth in (abbr[ORTH], abbr[ORTH].capitalize(), abbr[ORTH].upper()):
_exc[orth] = [{ORTH: orth, LEMMA: abbr[LEMMA], NORM: abbr[LEMMA]}]
_exc[orth + "."] = [
{ORTH: orth + ".", LEMMA: abbr[LEMMA], NORM: abbr[LEMMA]}
]
for exc_data in [ # "etc." abbreviations
{ORTH: "һ.б.ш.", NORM: "һәм башка шундыйлар"},
{ORTH: "һ.б.", NORM: "һәм башка"},
{ORTH: "б.э.к.", NORM: "безнең эрага кадәр"},
{ORTH: "б.э.", NORM: "безнең эра"}]:
exc_data[LEMMA] = exc_data[NORM]
_exc[exc_data[ORTH]] = [exc_data]
TOKENIZER_EXCEPTIONS = _exc