mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-24 17:06:29 +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.
82 lines
2.6 KiB
Cython
82 lines
2.6 KiB
Cython
from libc.string cimport memset
|
|
cimport numpy as np
|
|
|
|
from ..vocab cimport Vocab
|
|
from ..typedefs cimport hash_t, attr_t
|
|
from ..morphology cimport list_features, check_feature, get_by_field
|
|
|
|
|
|
cdef class MorphAnalysis:
|
|
"""Control access to morphological features for a token."""
|
|
def __init__(self, Vocab vocab, features=dict()):
|
|
self.vocab = vocab
|
|
self.key = self.vocab.morphology.add(features)
|
|
analysis = <const MorphAnalysisC*>self.vocab.morphology.tags.get(self.key)
|
|
if analysis is not NULL:
|
|
self.c = analysis[0]
|
|
else:
|
|
memset(&self.c, 0, sizeof(self.c))
|
|
|
|
@classmethod
|
|
def from_id(cls, Vocab vocab, hash_t key):
|
|
"""Create a morphological analysis from a given ID."""
|
|
cdef MorphAnalysis morph = MorphAnalysis.__new__(MorphAnalysis, vocab)
|
|
morph.vocab = vocab
|
|
morph.key = key
|
|
analysis = <const MorphAnalysisC*>vocab.morphology.tags.get(key)
|
|
if analysis is not NULL:
|
|
morph.c = analysis[0]
|
|
else:
|
|
memset(&morph.c, 0, sizeof(morph.c))
|
|
return morph
|
|
|
|
def __contains__(self, feature):
|
|
"""Test whether the morphological analysis contains some feature."""
|
|
cdef attr_t feat_id = self.vocab.strings.as_int(feature)
|
|
return check_feature(&self.c, feat_id)
|
|
|
|
def __iter__(self):
|
|
"""Iterate over the features in the analysis."""
|
|
cdef attr_t feature
|
|
for feature in list_features(&self.c):
|
|
yield self.vocab.strings[feature]
|
|
|
|
def __len__(self):
|
|
"""The number of features in the analysis."""
|
|
return self.c.length
|
|
|
|
def __str__(self):
|
|
return self.to_json()
|
|
|
|
def __repr__(self):
|
|
return self.to_json()
|
|
|
|
def __hash__(self):
|
|
return self.key
|
|
|
|
def __eq__(self, other):
|
|
return self.key == other.key
|
|
|
|
def __ne__(self, other):
|
|
return self.key != other.key
|
|
|
|
def get(self, field):
|
|
"""Retrieve a feature by field."""
|
|
cdef attr_t field_id = self.vocab.strings.as_int(field)
|
|
cdef np.ndarray results = get_by_field(&self.c, field_id)
|
|
return [self.vocab.strings[result] for result in results]
|
|
|
|
def to_json(self):
|
|
"""Produce a json serializable representation as a UD FEATS-style
|
|
string.
|
|
"""
|
|
morph_string = self.vocab.strings[self.c.key]
|
|
if morph_string == self.vocab.morphology.EMPTY_MORPH:
|
|
return ""
|
|
return morph_string
|
|
|
|
def to_dict(self):
|
|
"""Produce a dict representation.
|
|
"""
|
|
return self.vocab.morphology.feats_to_dict(self.to_json())
|