spaCy/spacy/lang/de/__init__.py

49 lines
1.5 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
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
from ...language import Language
Reduce stored lexemes data, move feats to lookups (#5238) * Reduce stored lexemes data, move feats to lookups * Move non-derivable lexemes features (`norm / cluster / prob`) to `spacy-lookups-data` as lookups * Get/set `norm` in both lookups and `LexemeC`, serialize in lookups * Remove `cluster` and `prob` from `LexemesC`, get/set/serialize in lookups only * Remove serialization of lexemes data as `vocab/lexemes.bin` * Remove `SerializedLexemeC` * Remove `Lexeme.to_bytes/from_bytes` * Modify normalization exception loading: * Always create `Vocab.lookups` table `lexeme_norm` for normalization exceptions * Load base exceptions from `lang.norm_exceptions`, but load language-specific exceptions from lookups * Set `lex_attr_getter[NORM]` including new lookups table in `BaseDefaults.create_vocab()` and when deserializing `Vocab` * Remove all cached lexemes when deserializing vocab to override existing normalizations with the new normalizations (as a replacement for the previous step that replaced all lexemes data with the deserialized data) * Skip English normalization test Skip English normalization test because the data is now in `spacy-lookups-data`. * Remove norm exceptions Moved to spacy-lookups-data. * Move norm exceptions test to spacy-lookups-data * Load extra lookups from spacy-lookups-data lazily Load extra lookups (currently for cluster and prob) lazily from the entry point `lg_extra` as `Vocab.lookups_extra`. * Skip creating lexeme cache on load To improve model loading times, do not create the full lexeme cache when loading. The lexemes will be created on demand when processing. * Identify numeric values in Lexeme.set_attrs() With the removal of a special case for `PROB`, also identify `float` to avoid trying to convert it with the `StringStore`. * Skip lexeme cache init in from_bytes * Unskip and update lookups tests for python3.6+ * Update vocab pickle to include lookups_extra * Update vocab serialization tests Check strings rather than lexemes since lexemes aren't initialized automatically, account for addition of "_SP". * Re-skip lookups test because of python3.5 * Skip PROB/float values in Lexeme.set_attrs * Convert is_oov from lexeme flag to lex in vectors Instead of storing `is_oov` as a lexeme flag, `is_oov` reports whether the lexeme has a vector. Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com>
2020-05-19 16:59:14 +03:00
from ...attrs import LANG
from ...util import update_exc
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"
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"]