mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-04 09:57:26 +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 * Fix French and Polish lemmatizers * Remove outdated UPOS conversions * Update Russian lemmatizer init in tests * Add minimal init/run tests for custom lemmatizers * Add option to overwrite existing lemmas *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
66 lines
2.2 KiB
Python
66 lines
2.2 KiB
Python
import pytest
|
|
from spacy.vocab import Vocab
|
|
from spacy.tokens import Doc
|
|
from spacy import util
|
|
|
|
|
|
@pytest.fixture
|
|
def vocab():
|
|
return Vocab()
|
|
|
|
|
|
def test_empty_doc(vocab):
|
|
doc = Doc(vocab)
|
|
assert len(doc) == 0
|
|
|
|
|
|
def test_single_word(vocab):
|
|
doc = Doc(vocab, words=["a"])
|
|
assert doc.text == "a "
|
|
doc = Doc(vocab, words=["a"], spaces=[False])
|
|
assert doc.text == "a"
|
|
|
|
|
|
def test_create_from_words_and_text(vocab):
|
|
# no whitespace in words
|
|
words = ["'", "dogs", "'", "run"]
|
|
text = " 'dogs'\n\nrun "
|
|
(words, spaces) = util.get_words_and_spaces(words, text)
|
|
doc = Doc(vocab, words=words, spaces=spaces)
|
|
assert [t.text for t in doc] == [" ", "'", "dogs", "'", "\n\n", "run", " "]
|
|
assert [t.whitespace_ for t in doc] == ["", "", "", "", "", " ", ""]
|
|
assert doc.text == text
|
|
assert [t.text for t in doc if not t.text.isspace()] == [
|
|
word for word in words if not word.isspace()
|
|
]
|
|
|
|
# partial whitespace in words
|
|
words = [" ", "'", "dogs", "'", "\n\n", "run", " "]
|
|
text = " 'dogs'\n\nrun "
|
|
(words, spaces) = util.get_words_and_spaces(words, text)
|
|
doc = Doc(vocab, words=words, spaces=spaces)
|
|
assert [t.text for t in doc] == [" ", "'", "dogs", "'", "\n\n", "run", " "]
|
|
assert [t.whitespace_ for t in doc] == ["", "", "", "", "", " ", ""]
|
|
assert doc.text == text
|
|
assert [t.text for t in doc if not t.text.isspace()] == [
|
|
word for word in words if not word.isspace()
|
|
]
|
|
|
|
# non-standard whitespace tokens
|
|
words = [" ", " ", "'", "dogs", "'", "\n\n", "run"]
|
|
text = " 'dogs'\n\nrun "
|
|
(words, spaces) = util.get_words_and_spaces(words, text)
|
|
doc = Doc(vocab, words=words, spaces=spaces)
|
|
assert [t.text for t in doc] == [" ", "'", "dogs", "'", "\n\n", "run", " "]
|
|
assert [t.whitespace_ for t in doc] == ["", "", "", "", "", " ", ""]
|
|
assert doc.text == text
|
|
assert [t.text for t in doc if not t.text.isspace()] == [
|
|
word for word in words if not word.isspace()
|
|
]
|
|
|
|
# mismatch between words and text
|
|
with pytest.raises(ValueError):
|
|
words = [" ", " ", "'", "dogs", "'", "\n\n", "run"]
|
|
text = " 'dogs'\n\nrun "
|
|
(words, spaces) = util.get_words_and_spaces(words + ["away"], text)
|