def test_name():
Name = fact(
'Name',
['first', 'last']
)
gnc = gnc_relation()
FIRST = gram('Name').interpretation(
Name.first.inflected()
).match(gnc)
LAST = gram('Surn').interpretation(
Name.last.inflected()
).match(gnc)
NAME = rule(
FIRST,
LAST
).interpretation(Name)
parser = Parser(NAME)
match = parser.match('саше иванову')
assert match.fact == Name(first='саша', last='иванов')
match = parser.match('сашу иванову')
assert match.fact == Name(first='саша', last='иванова')
match = parser.match('сашу ивановой')
assert not match
def test_person():
Name = fact(
'Name',
['first', 'last'],
)
Person = fact('Person', ['position', 'name'])
LAST = and_(
gram('Surn'),
not_(gram('Abbr')),
)
FIRST = and_(
gram('Name'),
not_(gram('Abbr')),
)
POSITION = morph_pipeline(['управляющий директор', 'вице-мэр'])
gnc = gnc_relation()
NAME = rule(
FIRST.interpretation(Name.first).match(gnc),
LAST.interpretation(Name.last).match(gnc)).interpretation(Name)
PERSON = rule(
POSITION.interpretation(Person.position).match(gnc),
NAME.interpretation(Person.name)).interpretation(Person)
parser = Parser(PERSON)
match = parser.match('управляющий директор Иван Ульянов')
assert match
assert match.fact == Person(position='управляющий директор',
name=Name(first='Иван', last='Ульянов'))
def test_bnf():
from yargy.interpretation import fact
from yargy.relations import gnc_relation
F = fact('F', ['a'])
gnc = gnc_relation()
assert_bnf(rule('a').named('A').interpretation(F), "F -> 'a'")
assert_bnf(
rule('a').interpretation(F.a).interpretation(F), 'F -> F.a',
"F.a -> 'a'")
assert_bnf(rule('a').match(gnc).interpretation(F.a), "F.a^gnc -> 'a'")
assert_bnf(
rule('a').interpretation(F.a).repeatable(), 'R0 -> F.a | F.a R0',
"F.a -> 'a'")
assert_bnf(
rule('a').repeatable().interpretation(F.a), 'F.a -> R1',
"R1 -> 'a' | 'a' R1")
def test_bnf():
from yargy.interpretation import fact
from yargy.relations import gnc_relation
F = fact('F', ['a'])
gnc = gnc_relation()
assert_bnf(
rule('a').named('A').interpretation(F),
"F -> 'a'"
)
assert_bnf(
rule('a').interpretation(F.a).interpretation(F),
'F -> F.a',
"F.a -> 'a'"
)
assert_bnf(
rule('a').match(gnc).interpretation(F.a),
"F.a^gnc -> 'a'"
)
assert_bnf(
rule('a').interpretation(F.a).repeatable(),
'R0 -> F.a R0 | F.a',
"F.a -> 'a'"
)
assert_bnf(
rule('a').repeatable().interpretation(F.a),
'F.a -> R1',
"R1 -> 'a' R1 | 'a'"
)
A = rule('a')
B = A.named('B')
C = A.named('C')
D = rule(B, C).named('D')
assert_bnf(
D,
'D -> B C',
'B -> R0',
'C -> R0',
"R0 -> 'a'"
)
def test_person():
Name = fact(
'Name',
['first', 'last'],
)
Person = fact('Person', ['position', 'name'])
LAST = and_(
gram('Surn'),
not_(gram('Abbr')),
)
FIRST = and_(
gram('Name'),
not_(gram('Abbr')),
)
class PositionPipeline(MorphPipeline):
grammemes = {'Position'}
keys = ['управляющий директор', 'вице-мэр']
POSITION = gram('Position')
gnc = gnc_relation()
NAME = rule(
FIRST.match(gnc).interpretation(Name.first),
LAST.match(gnc).interpretation(Name.last)).interpretation(Name)
PERSON = rule(POSITION.interpretation(Person.position),
NAME.interpretation(Person.name)).interpretation(Person)
parser = Parser(PERSON, pipelines=[PositionPipeline()])
matches = list(parser.match('управляющий директор Иван Ульянов'))
assert len(matches) == 1
assert matches[0].fact == Person(position='управляющий директор',
name=Name(first='Иван', last='Ульянов'))
# coding: utf-8
from __future__ import unicode_literals
from yargy import (rule, and_, or_, not_, fact)
from yargy.predicates import (caseless, normalized, eq, length_eq, gram,
dictionary, is_single, is_title)
from yargy.relations import gnc_relation
Location = fact(
'Location',
['name'],
)
gnc = gnc_relation()
REGION = rule(
gram('ADJF').match(gnc),
dictionary({
'край',
'район',
'область',
'губерния',
'уезд',
}).match(gnc),
).interpretation(Location.name.inflected())
gnc1 = gnc_relation()
gnc2 = gnc_relation()
tagger = CrfTagger(NAME_MODEL, get_name_features)
super(nameExtractor, self).__init__(NAME, tagger=tagger)
###
### Dictionaries
IN_FIRST = dictionary(set(load_dict('first.txt')))
IN_MAYBE_FIRST = dictionary(set(load_dict('maybe_first.txt')))
IN_LAST = dictionary(set(load_dict('last.txt')))
###
Name = fact('Name', ['first', 'middle', 'last', 'nick'])
################# UNMODIFIED NATASHA #################
gnc = gnc_relation()
########
#
# FIRST
#
########
TITLE = is_capitalized()
NOUN = gram('NOUN')
NAME_CRF = tag('I')
ABBR = gram('Abbr')
SURN = gram('Surn')
NAME = and_(gram('Name'), not_(ABBR))
from yargy.predicates import (
caseless, normalized,
eq, length_eq,
gram, dictionary,
is_single, is_title
)
from yargy.relations import gnc_relation
Location = fact(
'Location',
['name'],
)
gnc = gnc_relation()
REGION = rule(
gram('ADJF').match(gnc),
dictionary({
'край',
'район',
'область',
'губерния',
'уезд',
}).match(gnc),
).interpretation(Location.name.inflected())
gnc = gnc_relation()
FEDERAL_DISTRICT = rule(