spaCy/spacy/lang/de/__init__.py

54 lines
1.7 KiB
Python
Raw Normal View History

2017-03-12 15:07:28 +03:00
# coding: utf8
2017-05-08 16:44:26 +03:00
from __future__ import unicode_literals
2015-09-06 22:56:47 +03:00
2017-05-08 16:44:26 +03:00
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
2017-06-03 21:54:18 +03:00
from .norm_exceptions import NORM_EXCEPTIONS
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES
from .punctuation import TOKENIZER_INFIXES
2017-05-08 16:44:26 +03:00
from .tag_map import TAG_MAP
from .stop_words import STOP_WORDS
from .syntax_iterators import SYNTAX_ITERATORS
2015-09-06 22:56:47 +03:00
2017-05-08 23:29:04 +03:00
from ..tokenizer_exceptions import BASE_EXCEPTIONS
2017-06-03 21:54:18 +03:00
from ..norm_exceptions import BASE_NORMS
2017-05-08 23:29:04 +03:00
from ...language import Language
2017-06-03 21:54:18 +03:00
from ...attrs import LANG, NORM
from ...util import update_exc, add_lookups
2015-09-06 22:56:47 +03:00
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)
prefixes = TOKENIZER_PREFIXES
suffixes = TOKENIZER_SUFFIXES
infixes = TOKENIZER_INFIXES
tag_map = TAG_MAP
stop_words = STOP_WORDS
syntax_iterators = SYNTAX_ITERATORS
2019-09-11 15:00:36 +03:00
single_orth_variants = [
{"tags": ["$("], "variants": ["", "..."]},
{"tags": ["$("], "variants": ["-", "", "", "--", "---", "——"]},
]
paired_orth_variants = [
{
"tags": ["$("],
"variants": [("'", "'"), (",", "'"), ("", ""), ("", ""), ("", "")],
},
{
"tags": ["$("],
"variants": [("``", "''"), ('"', '"'), ("", ""), ("»", "«"), ("«", "»")],
},
]
2017-05-03 12:01:42 +03:00
class German(Language):
lang = "de"
Defaults = GermanDefaults
2017-05-03 12:01:42 +03:00
__all__ = ["German"]