spaCy/spacy/lang/zh/lex_attrs.py
2019-08-20 17:36:34 +02:00

99 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.

# coding: utf8
from __future__ import unicode_literals
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}