spaCy/spacy/lang/de/__init__.py
2019-08-28 09:19:18 +02:00

42 lines
1.5 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# coding: utf8
from __future__ import unicode_literals
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .norm_exceptions import NORM_EXCEPTIONS
from .punctuation import TOKENIZER_INFIXES
from .tag_map import TAG_MAP
from .stop_words import STOP_WORDS
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
resources = {"lemma_lookup": "lemma_lookup.json"}
single_orth_variants = [{"tags": ["$("], "variants": ["", "..."]},
{"tags": ["$("], "variants": ["-", "", "", "--", "---", "——"]}]
paired_orth_variants = [{"tags": ["$("], "variants": [("'", "'"), (",", "'"), ("", "")]},
{"tags": ["$("], "variants": [("``", "''"), ('"', '"'), ("", "")]}]
class German(Language):
lang = "de"
Defaults = GermanDefaults
__all__ = ["German"]