harvesttext.match_patterns 源代码
import re
import jieba
import jieba.posseg
from harvesttext import HarvestText
[文档]def AllEnglish():
rule = lambda x: bool(re.fullmatch(r"[a-zA-Z]*",x))
return rule
[文档]def AllEnglishOrNum():
rule = lambda x: bool(re.fullmatch(r"[a-zA-Z0-9]*",x))
return rule
[文档]def UpperFirst():
rule = lambda x: bool(re.fullmatch(r"[A-Z]",x[0]))
return rule
[文档]def StartsWith(prefix):
return (lambda x: x.startswith(prefix))
[文档]def EndsWith(suffix):
return (lambda x: x.endswith(suffix))
[文档]def Contains(span):
rule = lambda x: bool(re.search(span,x))
return rule
[文档]def WithLength(length):
return (lambda x: len(x) == length)