spaCy/spacy/lang/ru/lex_attrs.py
Ines Montani db55577c45
Drop Python 2.7 and 3.5 (#4828)
* Remove unicode declarations

* Remove Python 3.5 and 2.7 from CI

* Don't require pathlib

* Replace compat helpers

* Remove OrderedDict

* Use f-strings

* Set Cython compiler language level

* Fix typo

* Re-add OrderedDict for Table

* Update setup.cfg

* Revert CONTRIBUTING.md

* Revert lookups.md

* Revert top-level.md

* Small adjustments and docs [ci skip]
2019-12-22 01:53:56 +01:00

67 lines
1.5 KiB
Python

from ...attrs import LIKE_NUM
_num_words = [
"ноль",
"один",
"два",
"три",
"четыре",
"пять",
"шесть",
"семь",
"восемь",
"девять",
"десять",
"одиннадцать",
"двенадцать",
"тринадцать",
"четырнадцать",
"пятнадцать",
"шестнадцать",
"семнадцать",
"восемнадцать",
"девятнадцать",
"двадцать",
"тридцать",
"сорок",
"пятьдесят",
"шестьдесят",
"семьдесят",
"восемьдесят",
"девяносто",
"сто",
"двести",
"триста",
"четыреста",
"пятьсот",
"шестьсот",
"семьсот",
"восемьсот",
"девятьсот",
"тысяча",
"миллион",
"миллиард",
"триллион",
"квадриллион",
"квинтиллион",
]
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}