def pattern_hour(cls):
left_bounds = RegexTool.left_wordbounds()
right_bounds = lchain(
RegexTool.right_wordbounds(),
[r":"],
)
rstr = RegexTool.rstr2bounded(r"\d+", left_bounds, right_bounds)
return re.compile(rstr, re.I)
def lang2pattern(cls, lang):
from henrique.main.document.price.rate.rate_entity import RateEntity
logger = HenriqueLogger.func_level2logger(cls.lang2pattern,
logging.DEBUG)
left_bounds = [
RateEntity.rstr_last_char(),
r"\s",
]
right_bounds = RegexTool.right_wordbounds()
rstr = RegexTool.rstr2bounded(cls.lang2rstr(lang), left_bounds,
right_bounds)
logger.debug({"left_bounds": left_bounds, "rstr": rstr})
return re.compile(rstr, re.I)
def texts2pattern(texts):
rstr_raw = RegexTool.rstr_iter2or(map(re.escape, texts))
left_bounds = lchain(
RegexTool.bounds2suffixed(RegexTool.left_wordbounds(), "\d"),
RegexTool.left_wordbounds(),
)
right_bounds = RegexTool.right_wordbounds()
rstr = RegexTool.rstr2bounded(rstr_raw, left_bounds, right_bounds)
logger.debug({
"rstr": rstr,
"rstr_raw": rstr_raw,
})
return re.compile(rstr, re.I)
def texts2pattern_word(cls, texts):
regex_raw = cls.texts2regex(texts)
regex_word = RegexTool.rstr2bounded(regex_raw, RegexTool.left_wordbounds(), RegexTool.right_wordbounds())
return re.compile(regex_word, ) # re.I can be dealt with normalizer
