from .name import SIMPLE_NAME
from .person import POSITION_NAME
from yargy_uk.rule.transformators import RuleTransformator
class StripInterpretationTransformator(RuleTransformator):
def visit_InterpretationRule(self, item):
return self.visit(item.rule)
NAME = SIMPLE_NAME.transform(StripInterpretationTransformator)
PERSON = POSITION_NAME.transform(StripInterpretationTransformator)
Organisation = fact('Organisation', ['name'])
TYPE = morph_pipeline([
'АО',
'ОАО',
'ООО',
'ЗАО',
'ПАО',
# TODO Check abbrs
# 'ик',
# 'нк',
# 'хк',
# 'ип',
# 'чп',
from yargy_uk.predicates import (
gram, tag,
is_capitalized, vesum_tag
)
from yargy_uk.predicates.bank import DictionaryPredicate as dictionary
from yargy_uk.relations import gnc_relation
from natasha_uk.data import load_dict
from yargy_uk.rule.transformators import RuleTransformator
from yargy_uk.rule.constructors import Rule
from yargy_uk.predicates.constructors import AndPredicate
Name = fact(
'Name',
['first', 'middle', 'last', 'nick']
)
FIRST_DICT = set(load_dict('first_uk.txt'))
MAYBE_FIRST_DICT = set(load_dict('maybe_first.txt'))
LAST_DICT = set(load_dict('last_uk.txt'))
##########
#
# COMPONENTS
#
###########
# coding: utf-8
from __future__ import unicode_literals
from yargy_uk import (rule, or_, and_)
from yargy_uk.interpretation import fact, attribute
from yargy_uk.predicates import (eq, lte, gte, gram, type, tag, length_eq, in_,
in_caseless, dictionary, normalized, caseless,
is_title)
from yargy_uk.pipelines import morph_pipeline
from yargy_uk.tokenizer import QUOTES
Address = fact('Address', [attribute('parts').repeatable()])
Index = fact('Index', ['value'])
Country = fact('Country', ['name'])
Region = fact('Region', ['name', 'type'])
Settlement = fact('Settlement', ['name', 'type'])
Street = fact('Street', ['name', 'type'])
Building = fact('Building', ['number', 'type'])
Room = fact('Room', ['number', 'type'])
DASH = eq('-')
DOT = eq('.')
ADJF = gram('ADJF')
NOUN = gram('NOUN')
INT = type('INT')
TITLE = is_title()
ANUM = rule(INT, DASH.optional(),
in_caseless({'я', 'й', 'е', 'ое', 'ая', 'ий', 'ой'}))
# coding: utf-8
from __future__ import unicode_literals
from yargy_uk import (rule, and_, or_)
from yargy_uk.interpretation import fact, attribute
from yargy_uk.predicates import (
eq,
gte,
lte,
length_eq,
dictionary,
normalized,
)
Date = fact('Date', ['year', 'month', 'day', attribute('current_era', True)])
MONTHS = {
'січень': 1,
'лютий': 2,
'березень': 3,
'квітень': 4,
'травень': 5,
'червень': 6,
'липень': 7,
'серпень': 8,
'вересень': 9,
'жовтень': 10,
'листопад': 11,
'грудень': 12,
}
from __future__ import unicode_literals, division
import re
from yargy_uk import (
rule,
and_,
or_,
)
from yargy_uk.interpretation import (fact, const)
from yargy_uk.predicates import (eq, length_eq, in_, in_caseless, gram, type,
normalized, caseless, dictionary)
from natasha_uk.dsl import (Normalizable, money as dsl)
Money = fact('Money',
['integer', 'fraction', 'multiplier', 'currency', 'coins'])
class Money(Money, Normalizable):
@property
def normalized(self):
amount = self.integer
if self.fraction:
amount += self.fraction / 100
if self.multiplier:
amount *= self.multiplier
if self.coins:
amount += self.coins / 100
return dsl.Money(amount, self.currency)
# coding: utf-8
from __future__ import unicode_literals
from yargy_uk import (rule, and_, or_, not_)
from yargy_uk.interpretation import fact
from yargy_uk.predicates import (
gram,
dictionary,
vesum_tag,
)
Location = fact(
'Location',
['name'],
)
ADJECTIVE_TAG = or_(gram('ADJF'), vesum_tag('adj'))
GENITIVE_TAG = or_(gram('gent'), vesum_tag('v_rod'))
REGION = rule(
ADJECTIVE_TAG,
dictionary({
'край',
'район',
'область',
'губернія',
}),
).interpretation(Location.name.inflected())
AUTONOMOUS_DISTRICT = rule(
from yargy_uk import (
rule,
or_
)
from yargy_uk.interpretation import fact
from yargy_uk.predicates import gram, vesum_tag
from yargy_uk.pipelines import morph_pipeline
from .name import (
NAME,
SIMPLE_NAME
)
Person = fact(
'Person',
['position', 'name']
)
POSITION = morph_pipeline([
'святий',
'патріарх',
'митрополит',
'цар',
'король',
'цариця',
'імператор',
'імператриця',
'принц',
'принцеса',