Source code for harvesttext.algorithms.match_patterns

import re
import jieba
import jieba.posseg
from harvesttext import HarvestText

[docs]def AllEnglish(): rule = lambda x: bool(re.fullmatch(r"[a-zA-Z]*",x)) return rule
[docs]def AllEnglishOrNum(): rule = lambda x: bool(re.fullmatch(r"[a-zA-Z0-9]*",x)) return rule
[docs]def UpperFirst(): rule = lambda x: bool(re.fullmatch(r"[A-Z]",x[0])) return rule
[docs]def StartsWith(prefix): return (lambda x: x.startswith(prefix))
[docs]def EndsWith(suffix): return (lambda x: x.endswith(suffix))
[docs]def Contains(span): rule = lambda x: bool(re.search(span,x)) return rule
[docs]def WithLength(length): return (lambda x: len(x) == length)