How to use the spacy.language.Language.Defaults.lex_attr_getters function in spacy

from .syntax_iterators import SYNTAX_ITERATORS
from .tag_map import TAG_MAP

from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ..norm_exceptions import BASE_NORMS
from ...language import Language
from ...attrs import LANG, NORM
from ...util import update_exc, add_lookups


class IndonesianDefaults(Language.Defaults):
    lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
    lex_attr_getters[LANG] = lambda text: "id"
    lex_attr_getters.update(LEX_ATTRS)
    lex_attr_getters[NORM] = add_lookups(
        Language.Defaults.lex_attr_getters[NORM], BASE_NORMS, NORM_EXCEPTIONS
    )
    tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
    stop_words = STOP_WORDS
    prefixes = TOKENIZER_PREFIXES
    suffixes = TOKENIZER_SUFFIXES
    infixes = TOKENIZER_INFIXES
    syntax_iterators = SYNTAX_ITERATORS
    tag_map = TAG_MAP


class Indonesian(Language):
    lang = "id"
    Defaults = IndonesianDefaults


__all__ = ["Indonesian"]

from .tag_map import TAG_MAP
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .punctuation import TOKENIZER_INFIXES

from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ..norm_exceptions import BASE_NORMS
from ...language import Language
from ...attrs import LANG, NORM
from ...util import update_exc, add_lookups


class ItalianDefaults(Language.Defaults):
    lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
    lex_attr_getters[LANG] = lambda text: "it"
    lex_attr_getters[NORM] = add_lookups(
        Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
    )
    tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
    stop_words = STOP_WORDS
    tag_map = TAG_MAP
    infixes = TOKENIZER_INFIXES


class Italian(Language):
    lang = "it"
    Defaults = ItalianDefaults


__all__ = ["Italian"]

from .syntax_iterators import SYNTAX_ITERATORS

from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ..norm_exceptions import BASE_NORMS
from ...language import Language
from ...lookups import Lookups
from ...attrs import LANG, NORM
from ...util import update_exc, add_lookups


class FrenchDefaults(Language.Defaults):
    lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
    lex_attr_getters.update(LEX_ATTRS)
    lex_attr_getters[LANG] = lambda text: "fr"
    lex_attr_getters[NORM] = add_lookups(
        Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
    )
    tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
    tag_map = TAG_MAP
    stop_words = STOP_WORDS
    infixes = TOKENIZER_INFIXES
    suffixes = TOKENIZER_SUFFIXES
    token_match = TOKEN_MATCH
    syntax_iterators = SYNTAX_ITERATORS

    @classmethod
    def create_lemmatizer(cls, nlp=None, lookups=None):
        if lookups is None:
            lookups = Lookups()
        return FrenchLemmatizer(lookups)

# coding: utf8
from __future__ import unicode_literals

from ...attrs import LANG, NORM
from ..norm_exceptions import BASE_NORMS
from ...language import Language
from ...tokens import Doc
from .stop_words import STOP_WORDS
from ...util import add_lookups
from .lex_attrs import LEX_ATTRS


class VietnameseDefaults(Language.Defaults):
    lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
    lex_attr_getters[LANG] = lambda text: "vi"  # for pickling
    lex_attr_getters[NORM] = add_lookups(
        Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
    )
    lex_attr_getters.update(LEX_ATTRS)
    stop_words = STOP_WORDS
    use_pyvi = True


class Vietnamese(Language):
    lang = "vi"
    Defaults = VietnameseDefaults  # override defaults

    def make_doc(self, text):
        if self.Defaults.use_pyvi:
            try:

from ..norm_exceptions import BASE_NORMS
from ...language import Language
from ...attrs import LANG, NORM
from ...util import update_exc, add_lookups
from .tag_map import TAG_MAP

# Lemma data note:
# Original pairs downloaded from http://www.lexiconista.com/datasets/lemmatization/
# Replaced characters using cedillas with the correct ones (ș and ț)


class RomanianDefaults(Language.Defaults):
    lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
    lex_attr_getters[LANG] = lambda text: "ro"
    lex_attr_getters[NORM] = add_lookups(
        Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
    )
    tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
    stop_words = STOP_WORDS
    tag_map = TAG_MAP


class Romanian(Language):
    lang = "ro"
    Defaults = RomanianDefaults


__all__ = ["Romanian"]

# coding: utf8
from __future__ import unicode_literals


from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ..norm_exceptions import BASE_NORMS
from ...language import Language
from ...attrs import LANG, NORM
from ...util import update_exc, add_lookups


class MultiLanguageDefaults(Language.Defaults):
    lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
    lex_attr_getters[LANG] = lambda text: "xx"
    lex_attr_getters[NORM] = add_lookups(
        Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
    )
    tokenizer_exceptions = update_exc(BASE_EXCEPTIONS)


class MultiLanguage(Language):
    """Language class to be used for models that support multiple languages.
    This module allows models to specify their language ID as 'xx'.
    """

    lang = "xx"
    Defaults = MultiLanguageDefaults

# coding: utf8
from __future__ import unicode_literals

from .stop_words import STOP_WORDS

from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ...language import Language
from ...attrs import LANG
from ...util import update_exc


class HebrewDefaults(Language.Defaults):
    lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
    lex_attr_getters[LANG] = lambda text: "he"
    tokenizer_exceptions = update_exc(BASE_EXCEPTIONS)
    stop_words = STOP_WORDS
    writing_system = {"direction": "rtl", "has_case": False, "has_letters": True}


class Hebrew(Language):
    lang = "he"
    Defaults = HebrewDefaults


__all__ = ["Hebrew"]

from .norm_exceptions import NORM_EXCEPTIONS
from .punctuation import TOKENIZER_INFIXES
from .tag_map import TAG_MAP
from .stop_words import STOP_WORDS
from .lemmatizer import LOOKUP
from .syntax_iterators import SYNTAX_ITERATORS

from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ..norm_exceptions import BASE_NORMS
from ...language import Language
from ...attrs import LANG, NORM
from ...util import update_exc, add_lookups


class GermanDefaults(Language.Defaults):
    lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
    lex_attr_getters[LANG] = lambda text: "de"
    lex_attr_getters[NORM] = add_lookups(
        Language.Defaults.lex_attr_getters[NORM], NORM_EXCEPTIONS, BASE_NORMS
    )
    tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
    infixes = TOKENIZER_INFIXES
    tag_map = TAG_MAP
    stop_words = STOP_WORDS
    syntax_iterators = SYNTAX_ITERATORS
    lemma_lookup = LOOKUP


class German(Language):
    lang = "de"
    Defaults = GermanDefaults

from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES, TOKENIZER_INFIXES
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from .norm_exceptions import NORM_EXCEPTIONS
from ..norm_exceptions import BASE_NORMS
from ...language import Language
from ...lookups import Lookups
from ...attrs import LANG, NORM
from ...util import update_exc, add_lookups


class GreekDefaults(Language.Defaults):
    lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
    lex_attr_getters.update(LEX_ATTRS)
    lex_attr_getters[LANG] = lambda text: "el"
    lex_attr_getters[NORM] = add_lookups(
        Language.Defaults.lex_attr_getters[NORM], BASE_NORMS, NORM_EXCEPTIONS
    )
    tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
    stop_words = STOP_WORDS
    tag_map = TAG_MAP
    prefixes = TOKENIZER_PREFIXES
    suffixes = TOKENIZER_SUFFIXES
    infixes = TOKENIZER_INFIXES
    syntax_iterators = SYNTAX_ITERATORS

    @classmethod
    def create_lemmatizer(cls, nlp=None, lookups=None):
        if lookups is None:
            lookups = Lookups()
        return GreekLemmatizer(lookups)

from .punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES
from .lemmatizer import DutchLemmatizer
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ..norm_exceptions import BASE_NORMS
from ...language import Language
from ...lookups import Lookups
from ...attrs import LANG, NORM
from ...util import update_exc, add_lookups


class DutchDefaults(Language.Defaults):
    lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
    lex_attr_getters.update(LEX_ATTRS)
    lex_attr_getters[LANG] = lambda text: "nl"
    lex_attr_getters[NORM] = add_lookups(
        Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
    )
    tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
    stop_words = STOP_WORDS
    tag_map = TAG_MAP
    infixes = TOKENIZER_INFIXES
    suffixes = TOKENIZER_SUFFIXES

    @classmethod
    def create_lemmatizer(cls, nlp=None, lookups=None):
        if lookups is None:
            lookups = Lookups()
        return DutchLemmatizer(lookups)


class Dutch(Language):
    lang = "nl"