mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-30 20:06:30 +03:00
19650ebb52
* enable fuzzy matching * add fuzzy param to EntityMatcher * include rapidfuzz_capi not yet used * fix type * add FUZZY predicate * add fuzzy attribute list * fix type properly * tidying * remove unnecessary dependency * handle fuzzy sets * simplify fuzzy sets * case fix * switch to FUZZYn predicates use Levenshtein distance. remove fuzzy param. remove rapidfuzz_capi. * revert changes added for fuzzy param * switch to polyleven (Python package) * enable fuzzy matching * add fuzzy param to EntityMatcher * include rapidfuzz_capi not yet used * fix type * add FUZZY predicate * add fuzzy attribute list * fix type properly * tidying * remove unnecessary dependency * handle fuzzy sets * simplify fuzzy sets * case fix * switch to FUZZYn predicates use Levenshtein distance. remove fuzzy param. remove rapidfuzz_capi. * revert changes added for fuzzy param * switch to polyleven (Python package) * fuzzy match only on oov tokens * remove polyleven * exclude whitespace tokens * don't allow more edits than characters * fix min distance * reinstate FUZZY operator with length-based distance function * handle sets inside regex operator * remove is_oov check * attempt build fix no mypy failure locally * re-attempt build fix * don't overwrite fuzzy param value * move fuzzy_match to its own Python module to allow patching * move fuzzy_match back inside Matcher simplify logic and add tests * Format tests * Parametrize fuzzyn tests * Parametrize and merge fuzzy+set tests * Format * Move fuzzy_match to a standalone method * Change regex kwarg type to bool * Add types for fuzzy_match - Refactor variable names - Add test for symmetrical behavior * Parametrize fuzzyn+set tests * Minor refactoring for fuzz/fuzzy * Make fuzzy_match a Matcher kwarg * Update type for _default_fuzzy_match * don't overwrite function param * Rename to fuzzy_compare * Update fuzzy_compare default argument declarations * allow fuzzy_compare override from EntityRuler * define new Matcher keyword arg * fix type definition * Implement fuzzy_compare config option for EntityRuler and SpanRuler * Rename _default_fuzzy_compare to fuzzy_compare, remove from reexported objects * Use simpler fuzzy_compare algorithm * Update types * Increase minimum to 2 in fuzzy_compare to allow one transposition * Fix predicate keys and matching for SetPredicate with FUZZY and REGEX * Add FUZZY6..9 * Add initial docs * Increase default fuzzy to rounded 30% of pattern length * Update docs for fuzzy_compare in components * Update EntityRuler and SpanRuler API docs * Rename EntityRuler and SpanRuler setting to matcher_fuzzy_compare To having naming similar to `phrase_matcher_attr`, rename `fuzzy_compare` setting for `EntityRuler` and `SpanRuler` to `matcher_fuzzy_compare. Organize next to `phrase_matcher_attr` in docs. * Fix schema aliases Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix typo Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Add FUZZY6-9 operators and update tests * Parameterize test over greedy Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix type for fuzzy_compare to remove Optional * Rename to spacy.levenshtein_compare.v1, move to spacy.matcher.levenshtein * Update docs following levenshtein_compare renaming Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
81 lines
1.5 KiB
Cython
81 lines
1.5 KiB
Cython
from libc.stdint cimport int32_t
|
|
from libcpp.vector cimport vector
|
|
from cymem.cymem cimport Pool
|
|
|
|
from ..vocab cimport Vocab
|
|
from ..typedefs cimport attr_t, hash_t
|
|
from ..structs cimport TokenC
|
|
from ..lexeme cimport attr_id_t
|
|
|
|
|
|
cdef enum action_t:
|
|
REJECT = 0000
|
|
MATCH = 1000
|
|
ADVANCE = 0100
|
|
RETRY = 0010
|
|
RETRY_EXTEND = 0011
|
|
RETRY_ADVANCE = 0110
|
|
MATCH_EXTEND = 1001
|
|
MATCH_REJECT = 2000
|
|
MATCH_DOUBLE = 3000
|
|
|
|
|
|
cdef enum quantifier_t:
|
|
ZERO
|
|
ZERO_ONE
|
|
ZERO_PLUS
|
|
ONE
|
|
ONE_PLUS
|
|
FINAL_ID
|
|
|
|
|
|
cdef struct AttrValueC:
|
|
attr_id_t attr
|
|
attr_t value
|
|
|
|
cdef struct IndexValueC:
|
|
int32_t index
|
|
attr_t value
|
|
|
|
cdef struct TokenPatternC:
|
|
AttrValueC* attrs
|
|
int32_t* py_predicates
|
|
IndexValueC* extra_attrs
|
|
int32_t nr_attr
|
|
int32_t nr_extra_attr
|
|
int32_t nr_py
|
|
quantifier_t quantifier
|
|
hash_t key
|
|
int32_t token_idx
|
|
|
|
|
|
cdef struct MatchAlignmentC:
|
|
int32_t token_idx
|
|
int32_t length
|
|
|
|
|
|
cdef struct PatternStateC:
|
|
TokenPatternC* pattern
|
|
int32_t start
|
|
int32_t length
|
|
|
|
|
|
cdef struct MatchC:
|
|
attr_t pattern_id
|
|
int32_t start
|
|
int32_t length
|
|
|
|
|
|
cdef class Matcher:
|
|
cdef Pool mem
|
|
cdef vector[TokenPatternC*] patterns
|
|
cdef readonly Vocab vocab
|
|
cdef public object validate
|
|
cdef public object _patterns
|
|
cdef public object _callbacks
|
|
cdef public object _filter
|
|
cdef public object _extensions
|
|
cdef public object _extra_predicates
|
|
cdef public object _seen_attrs
|
|
cdef public object _fuzzy_compare
|