class Person(Enum):
# Иванов Иван Иванович
Full = [
{
'labels': [
gram('Surn'),
gram_not('Abbr'),
],
'normalization': NormalizationType.Inflected,
'interpretation': {
'attribute': PersonObject.Attributes.Lastname,
},
},
{
'labels': [
gram('Name'),
gram_not('Abbr'),
gnc_match(-1, solve_disambiguation=True),
],
'normalization':
NormalizationType.Inflected,
'interpretation': {
'attribute': PersonObject.Attributes.Firstname,
},
},
{
'labels': [
gram('Patr'),
gram_not('Abbr'),
gnc_match(-1, solve_disambiguation=True),
],
'normalization':
NormalizationType.Inflected,
'interpretation': {
'attribute': PersonObject.Attributes.Middlename,
},
},
]
# Иван Иванович Иванов
FullReversed = [
{
'labels': [
gram('Name'),
gram_not('Abbr'),
],
'normalization': NormalizationType.Inflected,
'interpretation': {
'attribute': PersonObject.Attributes.Firstname,
},
},
{
'labels': [
gram('Patr'),
gram_not('Abbr'),
gnc_match(-1, solve_disambiguation=True),
],
'normalization':
NormalizationType.Inflected,
'interpretation': {
'attribute': PersonObject.Attributes.Middlename,
},
},
{
'labels': [
gram('Surn'),
gram_not('Abbr'),
gnc_match(-1, solve_disambiguation=True),
],
'normalization':
NormalizationType.Inflected,
'interpretation': {
'attribute': PersonObject.Attributes.Lastname,
},
},
]
# Фелипе Родригес Фернандес
# https://www.englishelp.ru/business-english/other/284-patronymic-vs-middle-name.html
FullReversedWithLatinMiddlename = [
{
'labels': [
gram('Name'),
],
'normalization': NormalizationType.Inflected,
'interpretation': {
'attribute': PersonObject.Attributes.Firstname,
},
},
{
'labels': [
gram('Name'),
gnc_match(-1, solve_disambiguation=True),
],
'repeatable': True,
'normalization': NormalizationType.Inflected,
'interpretation': {
'attribute': PersonObject.Attributes.Middlename,
},
},
{
'labels': [
gram('Surn'),
gnc_match(0, solve_disambiguation=True),
gnc_match(-1, solve_disambiguation=True),
],
'normalization':
NormalizationType.Inflected,
'interpretation': {
'attribute': PersonObject.Attributes.Lastname,
},
},
]
# Л. А. Раневская
InitialsAndLastname = [
{
'labels': [
gram_in(['Name', 'Abbr']),
],
'interpretation': {
'attribute': PersonObject.Attributes.Firstname,
},
'normalization': NormalizationType.Original,
},
{
'labels': [
gram('PUNCT'),
eq('.'),
],
},
{
'labels': [
gram_in(['Patr', 'Abbr']),
gnc_match(0, solve_disambiguation=True),
],
'interpretation': {
'attribute': PersonObject.Attributes.Middlename,
},
'normalization':
NormalizationType.Original,
},
{
'labels': [
gram('PUNCT'),
eq('.'),
],
},
{
'labels': [
gram('Surn'),
gram_not('Abbr'),
gnc_match(0, solve_disambiguation=True),
],
'normalization':
NormalizationType.Inflected,
'interpretation': {
'attribute': PersonObject.Attributes.Lastname,
},
},
]
# Иван Иванов
FirstnameAndLastname = [
{
'labels': [
gram('Name'),
gram_not('Abbr'),
],
'normalization': NormalizationType.Inflected,
'interpretation': {
'attribute': PersonObject.Attributes.Firstname,
},
},
{
'labels': [
gram('Surn'),
gram_not('Abbr'),
gnc_match(-1, solve_disambiguation=True),
],
'normalization':
NormalizationType.Inflected,
'interpretation': {
'attribute': PersonObject.Attributes.Lastname,
},
},
]
FirstnameAndLastnameWithQuotedNickname = [
FirstnameAndLastname[0], {
'labels': {
gram('QUOTE'),
gram_any({
'G-QUOTE',
'L-QUOTE',
}),
},
'normalization': NormalizationType.Original,
}, {
'labels': {
gram_not_in({
'QUOTE',
'PUNCT',
}),
},
'normalization': NormalizationType.Original,
'interpretation': {
'attribute': PersonObject.Attributes.Nickname,
},
}, {
'labels': {
gram('QUOTE'),
},
'normalization': NormalizationType.Original,
}, InitialsAndLastname[-1]
]
# Иванов Иван
LastnameAndFirstname = [
{
'labels': [
gram('Surn'),
gram_not('Abbr'),
],
'normalization': NormalizationType.Inflected,
'interpretation': {
'attribute': PersonObject.Attributes.Lastname,
},
},
{
'labels': [
gram('Name'),
gram_not('Abbr'),
gnc_match(-1, solve_disambiguation=True),
],
'normalization':
NormalizationType.Inflected,
'interpretation': {
'attribute': PersonObject.Attributes.Firstname,
},
},
]
# Александр Ф. Скляр
FullReversedWithMiddlenameAsInitials = FullReversed[:
1] + InitialsAndLastname[
3:]
# Раневская Л. А.
LastnameAndInitials = [
LastnameAndFirstname[0],
] + InitialsAndLastname[:4]
# Раневская Л.
LastnameAndFirstnameAsInitials = [
LastnameAndFirstname[0],
] + InitialsAndLastname[:2]
# Л. Раневская
FirstnameAsInitialsAndLastname = InitialsAndLastname[:2] + [
InitialsAndLastname[-1],
]
# Иван Иванович
FirstnameAndMiddlename = [
{
'labels': [
gram('Name'),
gram_not('Abbr'),
],
'normalization': NormalizationType.Inflected,
'interpretation': {
'attribute': PersonObject.Attributes.Firstname,
},
},
{
'labels': [
gram('Patr'),
gram_not('Abbr'),
gnc_match(-1, solve_disambiguation=True),
],
'normalization':
NormalizationType.Inflected,
'interpretation': {
'attribute': PersonObject.Attributes.Middlename,
},
},
]
# Иванов
Lastname = [
{
'labels': [
gram('Surn'),
gram_any({
'sing',
'Stgm',
}),
gram_not('Abbr'),
is_capitalized(True),
],
'normalization':
NormalizationType.Inflected,
'interpretation': {
'attribute': PersonObject.Attributes.Lastname,
},
},
]
# Иванович
Middlename = [{
'labels': [
gram('Patr'),
gram_any({
'sing',
'Stgm',
}),
gram_not('Abbr'),
is_capitalized(True),
],
'normalization':
NormalizationType.Inflected,
'interpretation': {
'attribute': PersonObject.Attributes.Middlename,
},
}]
# Иван
Firstname = [
{
'labels': [
gram('Name'),
gram_any({
'sing',
'Stgm',
}),
gram_not('Abbr'),
is_capitalized(True),
],
'normalization':
NormalizationType.Inflected,
'interpretation': {
'attribute': PersonObject.Attributes.Firstname,
},
},
]
# Отто фон Бисмарк
FirstnameAndLastnameWithNobilityParticle = [
FullReversed[0],
{
'labels': [
dictionary(NAME_NOBILITY_PARTICLE_DICTIONARY),
],
'normalization': NormalizationType.Original,
'interpretation': {
'attribute': PersonObject.Attributes.Lastname,
}
},
{
'labels': [
gram('Surn'),
gram_not('Abbr'),
gnc_match(0, solve_disambiguation=True)
],
'normalization':
NormalizationType.Inflected,
'interpretation': {
'attribute': PersonObject.Attributes.Lastname,
},
},
]
# Премьер-министр РФ Дмитрий Медведев
WithPosition = [
{
'labels': [
gram('Person/Position'),
],
'interpretation': {
'attribute': PersonObject.Attributes.Descriptor,
},
},
{
'labels': [
or_((
and_((
or_((
gram_any({
'ablt',
'loct',
'gent',
}),
gram('Fixd'),
)),
gram_not_in({
'Name',
'Patr',
'Surn',
}),
)),
gram('Abbr'),
gram('LATN'),
)),
],
'optional':
True,
'repeatable':
True,
'normalization':
NormalizationType.Original,
},
{
'labels': [
gram('Name'),
case_match(0, solve_disambiguation=True),
number_match(0, solve_disambiguation=True),
],
'normalization':
NormalizationType.Inflected,
'interpretation': {
'attribute': PersonObject.Attributes.Firstname,
},
},
{
'labels': [
gram('Patr'),
case_match(0, solve_disambiguation=True),
number_match(0, solve_disambiguation=True),
gnc_match(-1, solve_disambiguation=True),
],
'optional':
True,
'normalization':
NormalizationType.Inflected,
'interpretation': {
'attribute': PersonObject.Attributes.Middlename,
},
},
{
'labels': [
gram('Surn'),
case_match(0, solve_disambiguation=True),
number_match(0, solve_disambiguation=True),
gnc_match(-1, solve_disambiguation=True),
],
'normalization':
NormalizationType.Inflected,
'interpretation': {
'attribute': PersonObject.Attributes.Lastname,
},
},
]
# Пресс-секретарь «Роснефти» Михаил Леонтьев
WithPositionAndQuotedOrganisationName = (WithPosition[:2] + [
{
'labels': [
gram('QUOTE'),
],
'normalization': NormalizationType.Original,
},
{
'labels': [
gram_not('QUOTE'),
gram_not_in('END-OF-LINE'),
],
'repeatable': True,
'normalization': NormalizationType.Original,
},
{
'labels': [
gram('QUOTE'),
],
'normalization': NormalizationType.Original,
},
] + WithPosition[2:])
# граф де Кристо
PositionAndNobilitySurname = [{
'labels': [
gram('Person/Position'),
],
}, {
'labels': [
dictionary(NAME_NOBILITY_PARTICLE_DICTIONARY),
],
}, {
'labels': [
gram('Surn'),
gnc_match(0, solve_disambiguation=True),
],
'interpretation': {
'attribute': PersonObject.Attributes.Lastname,
},
}]
# Генрих Восьмой / Карл XII
NameWithNumericPart = [{
'labels': [
gram_in({
'Name',
'sing',
}),
gram_not('Abbr'),
],
'interpretation': {
'attribute': PersonObject.Attributes.Firstname,
},
}, {
'labels': [
or_((
and_((gram_in({
'ADJF',
'Anum',
}), gnc_match(-1, solve_disambiguation=True))),
gram('ROMN'),
))
]
}]
}
SHORT_STREET_DESCRIPTOR_RULE = [
{
'labels': {
or_((
dictionary({
'ул', # улица
'пр', # проспект / проезд?
'проспа', # проспект
'пр-том', # see kmike/github issue #88
'площадь', # площадь,
'пр-кт', # проспект
'пр-далее', # проезд
'б-литр', # бульвар, #88
'б-р', # бульвар
'бул', # бульвар
'наб', # набережная
'ш', # шоссе
'тупой', # тупик, #88
'дора', # дорога, #88
}),
in_({
'пер', # переулок, #88,
'н', # набережная
}),
)),
},
'normalization': NormalizationType.Original,
'interpretation': {
'attribute': AddressObject.Attributes.Street_Descriptor,
},
class Organisation(Enum):
OfficialQuoted = [
{
'labels': [
or_((
gram('Orgn/Commercial'),
gram('Orgn/Social'),
gram('Orgn/Abbr'),
)),
],
'normalization':
NormalizationType.Inflected,
'interpretation': {
'attribute': OrganisationObject.Attributes.Descriptor,
},
},
{
'labels': [
is_abbr(True),
],
'optional': True,
'repeatable': True,
'normalization': NormalizationType.Original,
'interpretation': {
'attribute': OrganisationObject.Attributes.Descriptor,
},
},
{
'labels': [
gram('QUOTE'),
],
},
{
'labels': [
gram_not('QUOTE'),
gram_not_in('END-OF-LINE'),
not_eq('.'),
],
'repeatable': True,
'normalization': NormalizationType.Original,
'interpretation': {
'attribute': OrganisationObject.Attributes.Name,
},
},
{
'labels': [
gram('QUOTE'),
],
},
]
Abbr = [
{
'labels': [
gram('Abbr'),
gram('Orgn'),
gram_not('Orgn/Abbr'),
],
'normalization': NormalizationType.Original,
'interpretation': {
'attribute': OrganisationObject.Attributes.Name,
},
},
]
IndividualEntrepreneur = [
{
'labels': [
eq('ИП'),
],
'normalization': NormalizationType.Original,
},
Person.Full.value[0],
Person.Full.value[1],
Person.Full.value[2],
]
SimpleLatin = [
{
'labels': [
gram('Orgn/Commercial'),
],
'normalization': NormalizationType.Normalized,
'interpretation': {
'attribute': OrganisationObject.Attributes.Descriptor,
},
},
{
'labels': [
gram_any({
'LATN',
'NUMBER',
}),
],
'repeatable': True,
'normalization': NormalizationType.Original,
'interpretation': {
'attribute': OrganisationObject.Attributes.Name,
},
},
]
# Санкт-Петербургский Государственный университет
Educational = [{
'labels': [
gram('ADJF'),
is_capitalized(True),
],
'normalization': NormalizationType.Inflected,
'interpretation': {
'attribute': OrganisationObject.Attributes.Name,
},
}, {
'labels': [
gram('ADJF'),
gnc_match(-1, solve_disambiguation=True),
],
'optional':
True,
'repeatable':
True,
'normalization':
NormalizationType.Inflected,
'interpretation': {
'attribute': OrganisationObject.Attributes.Name,
},
}, {
'labels': [
gram('Orgn/Educational'),
gnc_match(0, solve_disambiguation=True),
gnc_match(-1, solve_disambiguation=True),
],
'normalization':
NormalizationType.Normalized,
'interpretation': {
'attribute': OrganisationObject.Attributes.Descriptor,
},
}, {
'labels': [
gram_any({
'ablt',
'gent',
}),
gram_not_in({
'PREP',
}),
dictionary_not({
'имя',
}),
],
'normalization':
NormalizationType.Original,
'interpretation': {
'attribute': OrganisationObject.Attributes.Name,
},
'optional':
True,
'repeatable':
True,
}]
# Публичная библиотека имени М. Е. Салтыкова-Щедрина
EducationalWithInitials = Educational + NAMED_ORG_INITIALS_PREFIX_RULE + NAMED_ORG_INITIALS_RULE
# Публичная библиотека имени Салтыкова-Щедрина
EducationalWithLastname = Educational + NAMED_ORG_INITIALS_PREFIX_RULE + LASTNAME_GRAMMAR
# Кировский завод
AdjCommercial = Educational[:2] + [
{
'labels': [
gram('Orgn/Commercial'),
gnc_match(0, solve_disambiguation=True),
gnc_match(-1, solve_disambiguation=True),
],
'normalization':
NormalizationType.Normalized,
'interpretation': {
'attribute': OrganisationObject.Attributes.Descriptor,
},
},
Educational[-1],
]
AdjCommercialWithInitials = AdjCommercial + NAMED_ORG_INITIALS_PREFIX_RULE + NAMED_ORG_INITIALS_RULE
AdjCommercialWithLastname = AdjCommercial + NAMED_ORG_INITIALS_PREFIX_RULE + LASTNAME_GRAMMAR
# Общества андрологии и сексуальной медицины
Social = [
{
'labels': [
gram('Orgn/Social'),
gram('sing'),
],
'normalization': NormalizationType.Inflected,
'interpretation': {
'attribute': OrganisationObject.Attributes.Descriptor,
},
},
{
'labels': [
gram_not_in({
'PREP',
'CONJ',
}),
gram_any({
'accs',
'datv',
'gent',
}),
],
'normalization':
NormalizationType.Original,
'interpretation': {
'attribute': OrganisationObject.Attributes.Name,
},
},
{
'labels': [
gram_any({
'gent',
'accs',
'ablt',
}),
gram_not_in({
'PREP',
'Name',
'Patr',
'Surn',
}),
],
'optional':
True,
'repeatable':
True,
'normalization':
NormalizationType.Original,
'interpretation': {
'attribute': OrganisationObject.Attributes.Name,
},
},
]
SocialWithInitials = Social + NAMED_ORG_INITIALS_PREFIX_RULE + NAMED_ORG_INITIALS_RULE
SocialWithLastname = Social + NAMED_ORG_INITIALS_PREFIX_RULE + LASTNAME_GRAMMAR
AdjSocial = [
{
'labels': [
gram('ADJF'),
],
'normalization': NormalizationType.Inflected,
'interpretation': {
'attribute': OrganisationObject.Attributes.Name,
},
},
{
'labels': [
gram('ADJF'),
gnc_match(-1, solve_disambiguation=True),
],
'optional': True,
'repeatable': True,
'normalization': NormalizationType.Inflected,
'interpretation': {
'attribute': OrganisationObject.Attributes.Name,
},
},
{
'labels': [
gram('Orgn/Social'),
gnc_match(0, solve_disambiguation=True),
gnc_match(-1, solve_disambiguation=True),
],
'interpretation': {
'attribute': OrganisationObject.Attributes.Descriptor,
},
},
Social[-1],
]
AdjSocialWithInitials = AdjSocial + NAMED_ORG_INITIALS_PREFIX_RULE + NAMED_ORG_INITIALS_RULE
AdjSocialWithLastname = AdjSocial + NAMED_ORG_INITIALS_PREFIX_RULE + LASTNAME_GRAMMAR