def text2norm(cls, text_in):
if not text_in:
return text_in
text_out = StringTool.str2strip_eachline(StringTool.str2strip(text_in))
return text_out
# WARMER.warmup()
def j2valid_trend(j):
nonlocal entities_list
if j < 3:
return False
j_tuple = j_param_types2j_latest(j, Param.Type.list())
if any(map(is_none, j_tuple)):
return False
entities_tuple = [
entities_list[j] if j is not None else None for j in j_tuple
]
if any(map(lambda x: len(x) != 1, entities_tuple)):
return False
j_portlike, j_tradegood, j_rate, j_trend = j_tuple
assert_equal(j_trend, j)
if j_rate != j - 1:
return False
if j - 2 not in {j_portlike, j_tradegood}:
return False
entity_portlike, entity_tradegood, entity_rate, entity_trend = map(
l_singleton2obj, entities_tuple)
if FoxylibEntity.entity2type(
entity_portlike) != PortEntity.entity_type(
): # not culture
return False
entity_latter = max([entity_portlike, entity_tradegood],
key=FoxylibEntity.entity2span)
span_latter, span_rate, span_trend = lmap(
FoxylibEntity.entity2span,
[entity_latter, entity_rate, entity_trend])
span_latter_rate = SpanTool.span_pair2between(
span_latter, span_rate)
str_between_latter_rate = StringTool.str_span2substr(
text, span_latter_rate)
if not RegexTool.pattern_str2match_full(
RegexTool.pattern_blank_or_nullstr(),
str_between_latter_rate):
return False
span_rate_trend = SpanTool.span_pair2between(span_rate, span_trend)
str_between_rate_trend = StringTool.str_span2substr(
text, span_rate_trend)
if not RegexTool.pattern_str2match_full(
RegexTool.pattern_blank_or_nullstr(),
str_between_rate_trend):
return False
return True
def entity_pair2is_appendable(
cls,
text,
entity_pair,
):
Param = PriceSkillParameter
entity_type_pair = lmap(FoxylibEntity.entity2type, entity_pair)
param_type_pair = lmap(Param.Type.entity_type2parameter_type,
entity_type_pair)
for param_type in param_type_pair:
if param_type not in {Param.Type.PORTLIKE, Param.Type.TRADEGOOD}:
return False
param_type_1, param_type_2 = param_type_pair
if param_type_1 != param_type_2:
return False
span_pair = lmap(FoxylibEntity.entity2span, entity_pair)
text_between = StringTool.str_span2substr(
text, SpanTool.span_pair2between(*span_pair))
is_fullmatch = RegexTool.pattern_str2match_full(
Param.pattern_delim(), text_between)
if not is_fullmatch:
return False
return True
def indextuple2entity(indextuple):
i, j = indextuple
match_sign = match_list_sign[i]
span_sign = span_list_sign[i]
sign = match_sign.group()
entity_timedelta = entity_list_timedelta[j]
span_timedelta = span_list_timedelta[j]
value = {
cls.Value.Field.SIGN: sign,
cls.Value.Field.TIMEDELTA: entity_timedelta
}
span = (
span_sign[0],
span_timedelta[1],
)
entity = {
FoxylibEntity.Field.SPAN: span,
FoxylibEntity.Field.TEXT:
StringTool.str_span2substr(text_in, span),
FoxylibEntity.Field.VALUE: value,
FoxylibEntity.Field.TYPE: cls.entity_type(),
}
return entity
def match2entity_list(match):
span = match.span()
assert_in(SpanTool.span2len(span), (2, 3))
entity_list = []
s, e = span
span_nutmeg = (s, s + 1)
entity_nutmeg = {
FoxylibEntity.Field.SPAN:
span_nutmeg,
FoxylibEntity.Field.TEXT:
StringTool.str_span2substr(text_in, span_nutmeg),
FoxylibEntity.Field.VALUE:
"Nutmeg",
FoxylibEntity.Field.TYPE:
TradegoodEntity.entity_type(),
}
entity_list.append(entity_nutmeg)
span_mace = (s + 1, s + 2)
entity_mace = {
FoxylibEntity.Field.SPAN:
span_mace,
FoxylibEntity.Field.TEXT:
StringTool.str_span2substr(text_in, span_mace),
FoxylibEntity.Field.VALUE:
"Mace",
FoxylibEntity.Field.TYPE:
TradegoodEntity.entity_type(),
}
entity_list.append(entity_mace)
if SpanTool.span2len(span) == 3:
span_clove = (s + 2, s + 3)
entity_cloves = {
FoxylibEntity.Field.SPAN:
span_clove,
FoxylibEntity.Field.TEXT:
StringTool.str_span2substr(text_in, span_clove),
FoxylibEntity.Field.VALUE:
"Cloves",
FoxylibEntity.Field.TYPE:
TradegoodEntity.entity_type(),
}
entity_list.append(entity_cloves)
return entity_list
def _zzz(
cls,
str_PREV,
kwarg_KEY,
h_KWARG,
):
str_ARGs = None
#str_PREV = str2strip(LexerTool.token_list_DELIM2str_DELIM(token_list_DELIM[:iSTART_INFIX]))
if not kwarg_KEY:
if str_PREV:
str_ARGs = str_PREV
else:
if not str_PREV: raise cls.SyntacticError()
h_KWARG[StringTool.quoted2stripped(
kwarg_KEY.strip())] = StringTool.quoted2stripped(
str_PREV.strip())
return str_ARGs
def match2entity(m):
span = m.span()
entity = {
FoxylibEntity.Field.SPAN: span,
FoxylibEntity.Field.TEXT:
StringTool.str_span2substr(text_in, span),
FoxylibEntity.Field.VALUE: cls.match2value(m),
FoxylibEntity.Field.TYPE: cls.entity_type(),
}
return entity
def index2token(index):
span = span_list[index]
text = StringTool.str_span2substr(str_in, span)
token = {
cls.Token.Field.INDEX: index,
cls.Token.Field.SPAN: span,
cls.Token.Field.TEXT: text,
cls.Token.Field.NORM: normalizer(text) if normalizer else text,
}
return token
def match2entity(match):
span = match.span()
text = StringTool.str_span2substr(text_in, span)
codename = cls.lang_alias2codename(lang, text)
entity = {
FoxylibEntity.Field.VALUE: codename,
FoxylibEntity.Field.TEXT: text,
FoxylibEntity.Field.SPAN: span,
FoxylibEntity.Field.TYPE: cls.entity_type(),
}
return entity
def cospan2match(cospan):
span_ref = Cospan.cospan2span_ref(cospan)
charspan_ref = cls.Token.token_list_span2charspan(
token_list_ref, span_ref)
text_ref = StringTool.str_span2substr(
cls.Config.config2reference(matcher.config), charspan_ref)
span_hyp = Cospan.cospan2span_hyp(cospan)
charspan_hyp = cls.Token.token_list_span2charspan(
token_list_hyp, span_hyp)
text_hyp = StringTool.str_span2substr(text, charspan_hyp)
match = {
SubphraseMatch.Field.TOKENSPAN_REF: span_ref,
SubphraseMatch.Field.CHARSPAN_REF: charspan_ref,
SubphraseMatch.Field.TEXT_REF: text_ref,
SubphraseMatch.Field.TOKENSPAN_HYP: span_hyp,
SubphraseMatch.Field.CHARSPAN_HYP: charspan_hyp,
SubphraseMatch.Field.TEXT_HYP: text_hyp,
}
return match
def text2entity_list(cls, text_in, config=None):
lang = LocaleTool.locale2lang(HenriqueEntity.Config.config2locale(config))
span_value_list = list(cls.lang2matcher(lang).text2span_value_iter(text_in))
entity_list = [{FoxylibEntity.Field.SPAN: span,
FoxylibEntity.Field.TEXT: StringTool.str_span2substr(text_in, span),
FoxylibEntity.Field.VALUE: value,
FoxylibEntity.Field.TYPE: cls.entity_type(),
}
for span, value in span_value_list]
return entity_list
def indexes2entity(indexes):
span = (
span_list_element[indexes[0]][0],
span_list_element[indexes[-1]][1],
)
value = ListTool.indexes2filtered(element_list, indexes)
entity = {
FoxylibEntity.Field.SPAN: span,
FoxylibEntity.Field.TEXT:
StringTool.str_span2substr(text_in, span),
FoxylibEntity.Field.VALUE: value,
FoxylibEntity.Field.TYPE: cls.entity_type(),
}
return entity
def _text2entity_list_names(cls, text_in):
matcher_names = cls.matcher_names()
span_value_list = list(matcher_names.text2span_value_iter(text_in), )
entity_list = [{
FoxylibEntity.Field.SPAN:
span,
FoxylibEntity.Field.TEXT:
StringTool.str_span2substr(text_in, span),
FoxylibEntity.Field.VALUE:
value,
FoxylibEntity.Field.TYPE:
cls.entity_type(),
} for span, value in span_value_list]
return entity_list
def text2entity_list(cls, str_in, config=None):
def entity2is_wordbound_prefixed(entity):
return StringTool.str_span2is_wordbound_prefixed(
str_in, FoxylibEntity.entity2span(entity))
cardinal_entity_list = lfilter(entity2is_wordbound_prefixed,
CardinalEntity.text2entity_list(str_in))
m_list_suffix = cls.pattern_suffix().finditer(str_in)
span_ll = [
lmap(FoxylibEntity.entity2span, cardinal_entity_list),
lmap(MatchTool.match2span, m_list_suffix),
]
f_span2is_gap = lambda span: StringTool.str_span2match_blank_or_nullstr(
str_in,
span,
)
j_tuple_list = ContextfreeTool.spans_list2reducible_indextuple_list(
span_ll, f_span2is_gap)
for j1, j2 in j_tuple_list:
cardinal_entity = cardinal_entity_list[j1]
m_suffix = m_list_suffix[j2]
span = (FoxylibEntity.entity2span(cardinal_entity)[0],
MatchTool.match2span(m_suffix)[1])
j_entity = {
FoxylibEntity.Field.TYPE:
HourEntity.entity_type(),
FoxylibEntity.Field.SPAN:
span,
FoxylibEntity.Field.FULLTEXT:
str_in,
FoxylibEntity.Field.VALUE:
FoxylibEntity.entity2value(cardinal_entity),
}
yield j_entity
def str2token_list(cls, str_in):
span_list = cls.str2token_span_list(str_in)
return [StringTool.str_span2substr(str_in, span) for span in span_list]
def _match2matchstring_hyp(_match):
fulltext_hyp = cls.match2fulltext_hyp(_match)
charspan_hyp = cls.match2charspan_hyp(_match)
return StringTool.str_span2substr(fulltext_hyp, charspan_hyp)
def _match2matchstring_ref(_match):
fulltext_ref = cls.match2fulltext_ref(_match)
charspan_ref = cls.match2charspan_ref(_match)
return StringTool.str_span2substr(fulltext_ref, charspan_ref)
def text2sub(self, text):
span_value_list = list(self.text2span_value_iter(text))
text_subbed = StringTool.str_spans2replace_all(text, span_value_list)
return text_subbed
def entity2is_wordbound_prefixed(entity):
return StringTool.str_span2is_wordbound_prefixed(
str_in, FoxylibEntity.entity2span(entity))
def str_span2is_gap(cls, str_in, span):
return StringTool.str_span2match_blank_or_nullstr(str_in, span)
