mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 01:16:28 +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.
41 lines
1.4 KiB
Cython
41 lines
1.4 KiB
Cython
from cymem.cymem cimport Pool
|
|
from preshed.maps cimport PreshMap, PreshMapArray
|
|
from libc.stdint cimport uint64_t
|
|
from murmurhash cimport mrmr
|
|
cimport numpy as np
|
|
|
|
from .structs cimport TokenC, MorphAnalysisC
|
|
from .strings cimport StringStore
|
|
from .typedefs cimport hash_t, attr_t, flags_t
|
|
from .parts_of_speech cimport univ_pos_t
|
|
|
|
from . cimport symbols
|
|
|
|
cdef class Morphology:
|
|
cdef readonly Pool mem
|
|
cdef readonly StringStore strings
|
|
cdef PreshMap tags # Keyed by hash, value is pointer to tag
|
|
|
|
cdef public object lemmatizer
|
|
cdef readonly object tag_map
|
|
cdef readonly object tag_names
|
|
cdef readonly object reverse_index
|
|
cdef readonly object exc
|
|
cdef readonly PreshMapArray _cache
|
|
cdef readonly int n_tags
|
|
|
|
cdef MorphAnalysisC create_morph_tag(self, field_feature_pairs) except *
|
|
cdef int insert(self, MorphAnalysisC tag) except -1
|
|
|
|
cdef int assign_untagged(self, TokenC* token) except -1
|
|
cdef int assign_tag(self, TokenC* token, tag) except -1
|
|
cdef int assign_tag_id(self, TokenC* token, int tag_id) except -1
|
|
|
|
cdef int _assign_tag_from_exceptions(self, TokenC* token, int tag_id) except -1
|
|
|
|
|
|
cdef int check_feature(const MorphAnalysisC* morph, attr_t feature) nogil
|
|
cdef list list_features(const MorphAnalysisC* morph)
|
|
cdef np.ndarray get_by_field(const MorphAnalysisC* morph, attr_t field)
|
|
cdef int get_n_by_field(attr_t* results, const MorphAnalysisC* morph, attr_t field) nogil
|