mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-28 02:46:35 +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 * Fix French and Polish lemmatizers * Remove outdated UPOS conversions * Update Russian lemmatizer init in tests * Add minimal init/run tests for custom lemmatizers * Add option to overwrite existing lemmas *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
69 lines
2.0 KiB
Python
69 lines
2.0 KiB
Python
import pytest
|
|
|
|
|
|
@pytest.fixture
|
|
def i_has(en_tokenizer):
|
|
doc = en_tokenizer("I has")
|
|
doc[0].morph_ = {"PronType": "prs"}
|
|
doc[1].morph_ = {
|
|
"VerbForm": "fin",
|
|
"Tense": "pres",
|
|
"Number": "sing",
|
|
"Person": "three",
|
|
}
|
|
|
|
return doc
|
|
|
|
|
|
def test_token_morph_eq(i_has):
|
|
assert i_has[0].morph is not i_has[0].morph
|
|
assert i_has[0].morph == i_has[0].morph
|
|
assert i_has[0].morph != i_has[1].morph
|
|
|
|
|
|
def test_token_morph_key(i_has):
|
|
assert i_has[0].morph.key != 0
|
|
assert i_has[1].morph.key != 0
|
|
assert i_has[0].morph.key == i_has[0].morph.key
|
|
assert i_has[0].morph.key != i_has[1].morph.key
|
|
|
|
|
|
def test_morph_props(i_has):
|
|
assert i_has[0].morph.get("PronType") == ["prs"]
|
|
assert i_has[1].morph.get("PronType") == []
|
|
|
|
|
|
def test_morph_iter(i_has):
|
|
assert set(i_has[0].morph) == set(["PronType=prs"])
|
|
assert set(i_has[1].morph) == set(
|
|
["Number=sing", "Person=three", "Tense=pres", "VerbForm=fin"]
|
|
)
|
|
|
|
|
|
def test_morph_get(i_has):
|
|
assert i_has[0].morph.get("PronType") == ["prs"]
|
|
|
|
|
|
def test_morph_set(i_has):
|
|
assert i_has[0].morph.get("PronType") == ["prs"]
|
|
# set by string
|
|
i_has[0].morph_ = "PronType=unk"
|
|
assert i_has[0].morph.get("PronType") == ["unk"]
|
|
# set by string, fields are alphabetized
|
|
i_has[0].morph_ = "PronType=123|NounType=unk"
|
|
assert i_has[0].morph_ == "NounType=unk|PronType=123"
|
|
# set by dict
|
|
i_has[0].morph_ = {"AType": "123", "BType": "unk"}
|
|
assert i_has[0].morph_ == "AType=123|BType=unk"
|
|
# set by string with multiple values, fields and values are alphabetized
|
|
i_has[0].morph_ = "BType=c|AType=b,a"
|
|
assert i_has[0].morph_ == "AType=a,b|BType=c"
|
|
# set by dict with multiple values, fields and values are alphabetized
|
|
i_has[0].morph_ = {"AType": "b,a", "BType": "c"}
|
|
assert i_has[0].morph_ == "AType=a,b|BType=c"
|
|
|
|
|
|
def test_morph_str(i_has):
|
|
assert str(i_has[0].morph) == "PronType=prs"
|
|
assert str(i_has[1].morph) == "Number=sing|Person=three|Tense=pres|VerbForm=fin"
|