spaCy/spacy/lang/zh/lex_attrs.py
Daniël de Kok e2b70df012
Configure isort to use the Black profile, recursively isort the spacy module (#12721)
* Use isort with Black profile

* isort all the things

* Fix import cycles as a result of import sorting

* Add DOCBIN_ALL_ATTRS type definition

* Add isort to requirements

* Remove isort from build dependencies check

* Typo
2023-06-14 17:48:41 +02:00

98 lines
1.6 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.

import re
from ...attrs import LIKE_NUM
_single_num_words = [
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"十一",
"十二",
"十三",
"十四",
"十五",
"十六",
"十七",
"十八",
"十九",
"廿",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"拾壹",
"拾贰",
"拾叁",
"拾肆",
"拾伍",
"拾陆",
"拾柒",
"拾捌",
"拾玖",
]
_count_num_words = [
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
]
_base_num_words = ["", "", "", "", "亿", "", "", "", ""]
def like_num(text):
if text.startswith(("+", "-", "±", "~")):
text = text[1:]
text = text.replace(",", "").replace(".", "").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 in _single_num_words:
return True
# fmt: off
if re.match('^((' + '|'.join(_count_num_words) + '){1}'
+ '(' + '|'.join(_base_num_words) + '){1})+'
+ '(' + '|'.join(_count_num_words) + ')?$', text):
return True
# fmt: on
return False
LEX_ATTRS = {LIKE_NUM: like_num}