mirror of
https://github.com/explosion/spaCy.git
synced 2025-10-31 16:07:41 +03:00
3711af74e5
* Add tokenizer option to allow Matcher handling for all rules
Add tokenizer option `with_faster_rules_heuristics` that determines
whether the special cases applied by the internal `Matcher` are filtered
by whether they contain affixes or space. If `True` (default), the rules
are filtered to prioritize speed over rare edge cases. If `False`, all
rules are included in the final `Matcher`-based pass over the doc.
* Reset all caches when reloading special cases
* Revert "Reset all caches when reloading special cases"
This reverts commit 4ef6bd171d.
* Initialize max_length properly
* Add new tag to API docs
* Rename to faster heuristics
55 lines
2.3 KiB
Cython
55 lines
2.3 KiB
Cython
from libcpp.vector cimport vector
|
|
from preshed.maps cimport PreshMap
|
|
from cymem.cymem cimport Pool
|
|
|
|
from .typedefs cimport hash_t
|
|
from .structs cimport LexemeC, SpanC, TokenC
|
|
from .strings cimport StringStore
|
|
from .tokens.doc cimport Doc
|
|
from .vocab cimport Vocab, LexemesOrTokens, _Cached
|
|
from .matcher.phrasematcher cimport PhraseMatcher
|
|
|
|
|
|
cdef class Tokenizer:
|
|
cdef Pool mem
|
|
cdef PreshMap _cache
|
|
cdef PreshMap _specials
|
|
cdef readonly Vocab vocab
|
|
|
|
cdef object _token_match
|
|
cdef object _url_match
|
|
cdef object _prefix_search
|
|
cdef object _suffix_search
|
|
cdef object _infix_finditer
|
|
cdef object _rules
|
|
cdef PhraseMatcher _special_matcher
|
|
# TODO convert to bool in v4
|
|
cdef int _faster_heuristics
|
|
# TODO next one is unused and should be removed in v4
|
|
# https://github.com/explosion/spaCy/pull/9150
|
|
cdef int _unused_int2
|
|
|
|
cdef Doc _tokenize_affixes(self, str string, bint with_special_cases)
|
|
cdef int _apply_special_cases(self, Doc doc) except -1
|
|
cdef void _filter_special_spans(self, vector[SpanC] &original,
|
|
vector[SpanC] &filtered, int doc_len) nogil
|
|
cdef object _prepare_special_spans(self, Doc doc,
|
|
vector[SpanC] &filtered)
|
|
cdef int _retokenize_special_spans(self, Doc doc, TokenC* tokens,
|
|
object span_data)
|
|
cdef int _try_specials_and_cache(self, hash_t key, Doc tokens,
|
|
int* has_special,
|
|
bint with_special_cases) except -1
|
|
cdef int _tokenize(self, Doc tokens, str span, hash_t key,
|
|
int* has_special, bint with_special_cases) except -1
|
|
cdef str _split_affixes(self, Pool mem, str string,
|
|
vector[LexemeC*] *prefixes,
|
|
vector[LexemeC*] *suffixes, int* has_special,
|
|
bint with_special_cases)
|
|
cdef int _attach_tokens(self, Doc tokens, str string,
|
|
vector[LexemeC*] *prefixes,
|
|
vector[LexemeC*] *suffixes, int* has_special,
|
|
bint with_special_cases) except -1
|
|
cdef int _save_cached(self, const TokenC* tokens, hash_t key,
|
|
int* has_special, int n) except -1
|