mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-11 13:25:43 +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.
61 lines
1.9 KiB
Python
61 lines
1.9 KiB
Python
import pytest
|
|
|
|
|
|
@pytest.fixture
|
|
def i_has(en_tokenizer):
|
|
doc = en_tokenizer("I has")
|
|
doc[0].tag_ = "PRP"
|
|
doc[1].tag_ = "VBZ"
|
|
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") == ["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") == ["PronType=prs"]
|
|
|
|
|
|
def test_morph_set(i_has):
|
|
assert i_has[0].morph.get("PronType") == ["PronType=prs"]
|
|
# set by string
|
|
i_has[0].morph_ = "PronType=unk"
|
|
assert i_has[0].morph.get("PronType") == ["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", "POS": "ADJ"}
|
|
assert i_has[0].morph_ == "AType=123|BType=unk|POS=ADJ"
|
|
# 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"
|