mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 13:47:13 +03:00
e962784531
* Add Lemmatizer and simplify related components * Add `Lemmatizer` pipe with `lookup` and `rule` modes using the `Lookups` tables. * Reduce `Tagger` to a simple tagger that sets `Token.tag` (no pos or lemma) * Reduce `Morphology` to only keep track of morph tags (no tag map, lemmatizer, or morph rules) * Remove lemmatizer from `Vocab` * Adjust many many tests Differences: * No default lookup lemmas * No special treatment of TAG in `from_array` and similar required * Easier to modify labels in a `Tagger` * No extra strings added from morphology / tag map * Fix test * Initial fix for Lemmatizer config/serialization * Adjust init test to be more generic * Adjust init test to force empty Lookups * Add simple cache to rule-based lemmatizer * Convert language-specific lemmatizers Convert language-specific lemmatizers to component lemmatizers. Remove previous lemmatizer class. * Fix French and Polish lemmatizers * Remove outdated UPOS conversions * Update Russian lemmatizer init in tests * Add minimal init/run tests for custom lemmatizers * Add option to overwrite existing lemmas * Update mode setting, lookup loading, and caching * Make `mode` an immutable property * Only enforce strict `load_lookups` for known supported modes * Move caching into individual `_lemmatize` methods * Implement strict when lang is not found in lookups * Fix tables/lookups in make_lemmatizer * Reallow provided lookups and allow for stricter checks * Add lookups asset to all Lemmatizer pipe tests * Rename lookups in lemmatizer init test * Clean up merge * Refactor lookup table loading * Add helper from `load_lemmatizer_lookups` that loads required and optional lookups tables based on settings provided by a config. Additional slight refactor of lookups: * Add `Lookups.set_table` to set a table from a provided `Table` * Reorder class definitions to be able to specify type as `Table` * Move registry assets into test methods * Refactor lookups tables config Use class methods within `Lemmatizer` to provide the config for particular modes and to load the lookups from a config. * Add pipe and score to lemmatizer * Simplify Tagger.score * Add missing import * Clean up imports and auto-format * Remove unused kwarg * Tidy up and auto-format * Update docstrings for Lemmatizer Update docstrings for Lemmatizer. Additionally modify `is_base_form` API to take `Token` instead of individual features. * Update docstrings * Remove tag map values from Tagger.add_label * Update API docs * Fix relative link in Lemmatizer API docs
79 lines
2.8 KiB
Python
79 lines
2.8 KiB
Python
import pytest
|
|
|
|
from ...util import get_doc
|
|
|
|
|
|
def test_ru_doc_lemmatization(ru_lemmatizer):
|
|
words = ["мама", "мыла", "раму"]
|
|
pos = ["NOUN", "VERB", "NOUN"]
|
|
morphs = [
|
|
"Animacy=Anim|Case=Nom|Gender=Fem|Number=Sing",
|
|
"Aspect=Imp|Gender=Fem|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Act",
|
|
"Animacy=Anim|Case=Acc|Gender=Fem|Number=Sing",
|
|
]
|
|
doc = get_doc(ru_lemmatizer.vocab, words=words, pos=pos, morphs=morphs)
|
|
doc = ru_lemmatizer(doc)
|
|
lemmas = [token.lemma_ for token in doc]
|
|
assert lemmas == ["мама", "мыть", "рама"]
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,lemmas",
|
|
[
|
|
("гвоздики", ["гвоздик", "гвоздика"]),
|
|
("люди", ["человек"]),
|
|
("реки", ["река"]),
|
|
("кольцо", ["кольцо"]),
|
|
("пепперони", ["пепперони"]),
|
|
],
|
|
)
|
|
def test_ru_lemmatizer_noun_lemmas(ru_lemmatizer, text, lemmas):
|
|
doc = get_doc(ru_lemmatizer.vocab, words=[text], pos=["NOUN"])
|
|
result_lemmas = ru_lemmatizer.pymorphy2_lemmatize(doc[0])
|
|
assert sorted(result_lemmas) == lemmas
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,pos,morph,lemma",
|
|
[
|
|
("рой", "NOUN", "", "рой"),
|
|
("рой", "VERB", "", "рыть"),
|
|
("клей", "NOUN", "", "клей"),
|
|
("клей", "VERB", "", "клеить"),
|
|
("три", "NUM", "", "три"),
|
|
("кос", "NOUN", "Number=Sing", "кос"),
|
|
("кос", "NOUN", "Number=Plur", "коса"),
|
|
("кос", "ADJ", "", "косой"),
|
|
("потом", "NOUN", "", "пот"),
|
|
("потом", "ADV", "", "потом"),
|
|
],
|
|
)
|
|
def test_ru_lemmatizer_works_with_different_pos_homonyms(
|
|
ru_lemmatizer, text, pos, morph, lemma
|
|
):
|
|
doc = get_doc(ru_lemmatizer.vocab, words=[text], pos=[pos], morphs=[morph])
|
|
result_lemmas = ru_lemmatizer.pymorphy2_lemmatize(doc[0])
|
|
assert result_lemmas == [lemma]
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,morph,lemma",
|
|
[
|
|
("гвоздики", "Gender=Fem", "гвоздика"),
|
|
("гвоздики", "Gender=Masc", "гвоздик"),
|
|
("вина", "Gender=Fem", "вина"),
|
|
("вина", "Gender=Neut", "вино"),
|
|
],
|
|
)
|
|
def test_ru_lemmatizer_works_with_noun_homonyms(ru_lemmatizer, text, morph, lemma):
|
|
doc = get_doc(ru_lemmatizer.vocab, words=[text], pos=["NOUN"], morphs=[morph])
|
|
result_lemmas = ru_lemmatizer.pymorphy2_lemmatize(doc[0])
|
|
assert result_lemmas == [lemma]
|
|
|
|
|
|
def test_ru_lemmatizer_punct(ru_lemmatizer):
|
|
doc = get_doc(ru_lemmatizer.vocab, words=["«"], pos=["PUNCT"])
|
|
assert ru_lemmatizer.pymorphy2_lemmatize(doc[0]) == ['"']
|
|
doc = get_doc(ru_lemmatizer.vocab, words=["»"], pos=["PUNCT"])
|
|
assert ru_lemmatizer.pymorphy2_lemmatize(doc[0]) == ['"']
|