mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-20 09:46:02 +03:00
adc9745718
* Restructure tag maps for MorphAnalysis changes
Prepare tag maps for upcoming MorphAnalysis changes that allow
arbritrary features.
* Use default tag map rather than duplicating for ca / uk / vi
* Import tag map into defaults for ga
* Modify tag maps so all morphological fields and features are strings
* Move features from `"Other"` to the top level
* Rewrite tuples as strings separated by `","`
* Rewrite morph symbols for fr lemmatizer as strings
* Export MorphAnalysis under spacy.tokens
* Modify morphology to support arbitrary features
Modify `Morphology` and `MorphAnalysis` so that arbitrary features are
supported.
* Modify `MorphAnalysisC` so that it can support arbitrary features and
multiple values per field. `MorphAnalysisC` is redesigned to contain:
* key: hash of UD FEATS string of morphological features
* array of `MorphFeatureC` structs that each contain a hash of `Field`
and `Field=Value` for a given morphological feature, which makes it
possible to:
* find features by field
* represent multiple values for a given field
* `get_field()` is renamed to `get_by_field()` and is no longer `nogil`.
Instead a new helper function `get_n_by_field()` is `nogil` and returns
`n` features by field.
* `MorphAnalysis.get()` returns all possible values for a field as a
list of individual features such as `["Tense=Pres", "Tense=Past"]`.
* `MorphAnalysis`'s `str()` and `repr()` are the UD FEATS string.
* `Morphology.feats_to_dict()` converts a UD FEATS string to a dict
where:
* Each field has one entry in the dict
* Multiple values remain separated by a separator in the value string
* `Token.morph_` returns the UD FEATS string and you can set
`Token.morph_` with a UD FEATS string or with a tag map dict.
* Modify get_by_field to use np.ndarray
Modify `get_by_field()` to use np.ndarray. Remove `max_results` from
`get_n_by_field()` and always iterate over all the fields.
* Rewrite without MorphFeatureC
* Add shortcut for existing feats strings as keys
Add shortcut for existing feats strings as keys in `Morphology.add()`.
* Check for '_' as empty analysis when adding morphs
* Extend helper converters in Morphology
Add and extend helper converters that convert and normalize between:
* UD FEATS strings (`"Case=dat,gen|Number=sing"`)
* per-field dict of feats (`{"Case": "dat,gen", "Number": "sing"}`)
* list of individual features (`["Case=dat", "Case=gen",
"Number=sing"]`)
All converters sort fields and values where applicable.
46 lines
1.4 KiB
Python
46 lines
1.4 KiB
Python
import pytest
|
|
from spacy.morphology import Morphology
|
|
from spacy.strings import StringStore, get_string_id
|
|
from spacy.lemmatizer import Lemmatizer
|
|
from spacy.lookups import Lookups
|
|
|
|
|
|
@pytest.fixture
|
|
def morphology():
|
|
lemmatizer = Lemmatizer(Lookups())
|
|
return Morphology(StringStore(), {}, lemmatizer)
|
|
|
|
|
|
def test_init(morphology):
|
|
pass
|
|
|
|
|
|
def test_add_morphology_with_string_names(morphology):
|
|
morphology.add({"Case": "gen", "Number": "sing"})
|
|
|
|
|
|
def test_add_morphology_with_int_ids(morphology):
|
|
morphology.strings.add("Case")
|
|
morphology.strings.add("gen")
|
|
morphology.strings.add("Number")
|
|
morphology.strings.add("sing")
|
|
morphology.add({get_string_id("Case"): get_string_id("gen"), get_string_id("Number"): get_string_id("sing")})
|
|
|
|
|
|
def test_add_morphology_with_mix_strings_and_ints(morphology):
|
|
morphology.strings.add("PunctSide")
|
|
morphology.strings.add("ini")
|
|
morphology.add({get_string_id("PunctSide"): get_string_id("ini"), "VerbType": "aux"})
|
|
|
|
|
|
def test_morphology_tags_hash_distinctly(morphology):
|
|
tag1 = morphology.add({"PunctSide": "ini", "VerbType": "aux"})
|
|
tag2 = morphology.add({"Case": "gen", "Number": "sing"})
|
|
assert tag1 != tag2
|
|
|
|
|
|
def test_morphology_tags_hash_independent_of_order(morphology):
|
|
tag1 = morphology.add({"Case": "gen", "Number": "sing"})
|
|
tag2 = morphology.add({"Number": "sing", "Case": "gen"})
|
|
assert tag1 == tag2
|