mirror of
https://github.com/explosion/spaCy.git
synced 2025-02-22 22:40:32 +03:00
f42c9026f5
* Fix typos and auto-format [ci skip] * Add pkuseg warnings and auto-format [ci skip] * Update Binder URL [ci skip] * Update Binder version [ci skip] * Update alignment example for new gold.align * Update POS in tagging example * Fix numpy.zeros() dtype for Doc.from_array * Change example title to Dr. Change example title to Dr. so the current model does exclude the title in the initial example. * Fix spacy convert argument * Warning for sudachipy 0.4.5 (#5611) * Create myavrum.md (#5612) * Update lex_attrs.py (#5608) * Create mahnerak.md (#5615) * Some changes for Armenian (#5616) * Fixing numericals * We need a Armenian question sign to make the sentence a question * Add Nepali Language (#5622) * added support for nepali lang * added examples and test files * added spacy contributor agreement * Japanese model: add user_dict entries and small refactor (#5573) * user_dict fields: adding inflections, reading_forms, sub_tokens deleting: unidic_tags improve code readability around the token alignment procedure * add test cases, replace fugashi with sudachipy in conftest * move bunsetu.py to spaCy Universe as a pipeline component BunsetuRecognizer * tag is space -> both surface and tag are spaces * consider len(text)==0 * Add warnings example in v2.3 migration guide (#5627) * contribute (#5632) * Fix polarity of Token.is_oov and Lexeme.is_oov (#5634) Fix `Token.is_oov` and `Lexeme.is_oov` so they return `True` when the lexeme does **not** have a vector. * Extend what's new in v2.3 with vocab / is_oov (#5635) * Skip vocab in component config overrides (#5624) * Fix backslashes in warnings config diff (#5640) Fix backslashes in warnings config diff in v2.3 migration section. * Disregard special tag _SP in check for new tag map (#5641) * Skip special tag _SP in check for new tag map In `Tagger.begin_training()` check for new tags aside from `_SP` in the new tag map initialized from the provided gold tuples when determining whether to reinitialize the morphology with the new tag map. * Simplify _SP check Co-authored-by: Ines Montani <ines@ines.io> Co-authored-by: Marat M. Yavrumyan <myavrum@ysu.am> Co-authored-by: Karen Hambardzumyan <mahnerak@gmail.com> Co-authored-by: Rameshh <30867740+rameshhpathak@users.noreply.github.com> Co-authored-by: Hiroshi Matsuda <40782025+hiroshi-matsuda-rit@users.noreply.github.com> Co-authored-by: Richard Liaw <rliaw@berkeley.edu>
61 lines
1.2 KiB
Python
61 lines
1.2 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...attrs import LIKE_NUM
|
|
|
|
|
|
_num_words = [
|
|
"զրո",
|
|
"մեկ",
|
|
"երկու",
|
|
"երեք",
|
|
"չորս",
|
|
"հինգ",
|
|
"վեց",
|
|
"յոթ",
|
|
"ութ",
|
|
"ինը",
|
|
"տասը",
|
|
"տասնմեկ",
|
|
"տասներկու",
|
|
"տասներեք",
|
|
"տասնչորս",
|
|
"տասնհինգ",
|
|
"տասնվեց",
|
|
"տասնյոթ",
|
|
"տասնութ",
|
|
"տասնինը",
|
|
"քսան",
|
|
"երեսուն",
|
|
"քառասուն",
|
|
"հիսուն",
|
|
"վաթսուն",
|
|
"յոթանասուն",
|
|
"ութսուն",
|
|
"իննսուն",
|
|
"հարյուր",
|
|
"հազար",
|
|
"միլիոն",
|
|
"միլիարդ",
|
|
"տրիլիոն",
|
|
"քվինտիլիոն",
|
|
]
|
|
|
|
|
|
def like_num(text):
|
|
if text.startswith(("+", "-", "±", "~")):
|
|
text = text[1:]
|
|
text = text.replace(",", "").replace(".", "")
|
|
if text.isdigit():
|
|
return True
|
|
if text.count("/") == 1:
|
|
num, denom = text.split("/")
|
|
if num.isdigit() and denom.isdigit():
|
|
return True
|
|
if text.lower() in _num_words:
|
|
return True
|
|
return False
|
|
|
|
|
|
LEX_ATTRS = {LIKE_NUM: like_num}
|