mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-01 00:17:44 +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 * Fix French and Polish lemmatizers * Remove outdated UPOS conversions * Update Russian lemmatizer init in tests * Add minimal init/run tests for custom lemmatizers * Add option to overwrite existing lemmas *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
35 lines
1.1 KiB
Cython
35 lines
1.1 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 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
|