mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 20:28:20 +03:00
43b960c01b
* Update with WIP * Update with WIP * Update with pipeline serialization * Update types and pipe factories * Add deep merge, tidy up and add tests * Fix pipe creation from config * Don't validate default configs on load * Update spacy/language.py Co-authored-by: Ines Montani <ines@ines.io> * Adjust factory/component meta error * Clean up factory args and remove defaults * Add test for failing empty dict defaults * Update pipeline handling and methods * provide KB as registry function instead of as object * small change in test to make functionality more clear * update example script for EL configuration * Fix typo * Simplify test * Simplify test * splitting pipes.pyx into separate files * moving default configs to each component file * fix batch_size type * removing default values from component constructors where possible (TODO: test 4725) * skip instead of xfail * Add test for config -> nlp with multiple instances * pipeline.pipes -> pipeline.pipe * Tidy up, document, remove kwargs * small cleanup/generalization for Tok2VecListener * use DEFAULT_UPSTREAM field * revert to avoid circular imports * Fix tests * Replace deprecated arg * Make model dirs require config * fix pickling of keyword-only arguments in constructor * WIP: clean up and integrate full config * Add helper to handle function args more reliably Now also includes keyword-only args * Fix config composition and serialization * Improve config debugging and add visual diff * Remove unused defaults and fix type * Remove pipeline and factories from meta * Update spacy/default_config.cfg Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/default_config.cfg * small UX edits * avoid printing stack trace for debug CLI commands * Add support for language-specific factories * specify the section of the config which holds the model to debug * WIP: add Language.from_config * Update with language data refactor WIP * Auto-format * Add backwards-compat handling for Language.factories * Update morphologizer.pyx * Fix morphologizer * Update and simplify lemmatizers * Fix Japanese tests * Port over tagger changes * Fix Chinese and tests * Update to latest Thinc * WIP: xfail first Russian lemmatizer test * Fix component-specific overrides * fix nO for output layers in debug_model * Fix default value * Fix tests and don't pass objects in config * Fix deep merging * Fix lemma lookup data registry Only load the lookups if an entry is available in the registry (and if spacy-lookups-data is installed) * Add types * Add Vocab.from_config * Fix typo * Fix tests * Make config copying more elegant * Fix pipe analysis * Fix lemmatizers and is_base_form * WIP: move language defaults to config * Fix morphology type * Fix vocab * Remove comment * Update to latest Thinc * Add morph rules to config * Tidy up * Remove set_morphology option from tagger factory * Hack use_gpu * Move [pipeline] to top-level block and make [nlp.pipeline] list Allows separating component blocks from component order – otherwise, ordering the config would mean a changed component order, which is bad. Also allows initial config to define more components and not use all of them * Fix use_gpu and resume in CLI * Auto-format * Remove resume from config * Fix formatting and error * [pipeline] -> [components] * Fix types * Fix tagger test: requires set_morphology? Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com>
62 lines
1.6 KiB
Python
62 lines
1.6 KiB
Python
from typing import Set
|
||
from thinc.api import Config
|
||
|
||
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
||
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES
|
||
from .punctuation import TOKENIZER_INFIXES
|
||
from .stop_words import STOP_WORDS
|
||
from .syntax_iterators import SYNTAX_ITERATORS
|
||
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
||
from ...language import Language
|
||
from ...util import update_exc, registry
|
||
|
||
|
||
DEFAULT_CONFIG = """
|
||
[nlp]
|
||
lang = "de"
|
||
stop_words = {"@language_data": "spacy.de.stop_words"}
|
||
|
||
[nlp.lemmatizer]
|
||
@lemmatizers = "spacy.Lemmatizer.v1"
|
||
|
||
[nlp.lemmatizer.data_paths]
|
||
@language_data = "spacy-lookups-data"
|
||
lang = ${nlp:lang}
|
||
"""
|
||
|
||
|
||
@registry.language_data("spacy.de.stop_words")
|
||
def stop_words() -> Set[str]:
|
||
return STOP_WORDS
|
||
|
||
|
||
class GermanDefaults(Language.Defaults):
|
||
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
||
prefixes = TOKENIZER_PREFIXES
|
||
suffixes = TOKENIZER_SUFFIXES
|
||
infixes = TOKENIZER_INFIXES
|
||
syntax_iterators = SYNTAX_ITERATORS
|
||
single_orth_variants = [
|
||
{"tags": ["$("], "variants": ["…", "..."]},
|
||
{"tags": ["$("], "variants": ["-", "—", "–", "--", "---", "——"]},
|
||
]
|
||
paired_orth_variants = [
|
||
{
|
||
"tags": ["$("],
|
||
"variants": [("'", "'"), (",", "'"), ("‚", "‘"), ("›", "‹"), ("‹", "›")],
|
||
},
|
||
{
|
||
"tags": ["$("],
|
||
"variants": [("``", "''"), ('"', '"'), ("„", "“"), ("»", "«"), ("«", "»")],
|
||
},
|
||
]
|
||
|
||
|
||
class German(Language):
|
||
lang = "de"
|
||
Defaults = GermanDefaults
|
||
default_config = Config().from_str(DEFAULT_CONFIG)
|
||
|
||
|
||
__all__ = ["German"]
|