explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-08-06 05:10:21 +03:00
Code Issues Packages Projects Releases Wiki Activity

revert changes added for fuzzy param

Browse Source
This commit is contained in:
Kevin Humphreys 2022-08-29 18:28:17 +02:00
parent 3591a69d35
commit 568a843c09
2 changed files with 5 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
setup.py
View File

@ -11,7 +11,6 @@ from Cython.Build import cythonize
from Cython.Compiler import Options from Cython.Compiler import Options
import os import os
import subprocess import subprocess
import rapidfuzz_capi
ROOT = Path(__file__).parent ROOT = Path(__file__).parent
@ -203,7 +202,6 @@ def setup_package():
include_dirs = [ include_dirs = [
numpy.get_include(), numpy.get_include(),
rapidfuzz_capi.get_include(),
get_python_inc(plat_specific=True), get_python_inc(plat_specific=True),
] ]
ext_modules = [] ext_modules = []

13
spacy/matcher/matcher.pyx
View File

@ -354,7 +354,6 @@ cdef find_matches(TokenPatternC** patterns, int n, object doclike, int length, e
cdef PatternStateC state cdef PatternStateC state
cdef int i, j, nr_extra_attr cdef int i, j, nr_extra_attr
cdef Pool mem = Pool() cdef Pool mem = Pool()
output = [] output = []
if length == 0: if length == 0:
# avoid any processing or mem alloc if the document is empty # avoid any processing or mem alloc if the document is empty
@ -419,7 +418,7 @@ cdef void transition_states(vector[PatternStateC]& states, vector[MatchC]& match
if states[i].pattern.nr_py >= 1: if states[i].pattern.nr_py >= 1:
update_predicate_cache(cached_py_predicates, update_predicate_cache(cached_py_predicates,
states[i].pattern, token, py_predicates) states[i].pattern, token, py_predicates)
action = get_action(states[i], token, extra_attrs, action = get_action(states[i], token.c, extra_attrs,
cached_py_predicates) cached_py_predicates)
if action == REJECT: if action == REJECT:
continue continue
@ -456,7 +455,7 @@ cdef void transition_states(vector[PatternStateC]& states, vector[MatchC]& match
if states[q].pattern.nr_py != 0: if states[q].pattern.nr_py != 0:
update_predicate_cache(cached_py_predicates, update_predicate_cache(cached_py_predicates,
states[q].pattern, token, py_predicates) states[q].pattern, token, py_predicates)
action = get_action(states[q], token, extra_attrs, action = get_action(states[q], token.c, extra_attrs,
cached_py_predicates) cached_py_predicates)
# Update alignment before the transition of current state # Update alignment before the transition of current state
if with_alignments != 0: if with_alignments != 0:
@ -568,7 +567,7 @@ cdef void finish_states(vector[MatchC]& matches, vector[PatternStateC]& states,
cdef action_t get_action(PatternStateC state, cdef action_t get_action(PatternStateC state,
Token token, const attr_t* extra_attrs, const TokenC* token, const attr_t* extra_attrs,
const int8_t* predicate_matches) nogil: const int8_t* predicate_matches) nogil:
"""We need to consider: """We need to consider:
a) Does the token match the specification? [Yes, No] a) Does the token match the specification? [Yes, No]
@ -680,7 +679,7 @@ cdef action_t get_action(PatternStateC state,
cdef int8_t get_is_match(PatternStateC state, cdef int8_t get_is_match(PatternStateC state,
Token token, const attr_t* extra_attrs, const TokenC* token, const attr_t* extra_attrs,
const int8_t* predicate_matches) nogil: const int8_t* predicate_matches) nogil:
for i in range(state.pattern.nr_py): for i in range(state.pattern.nr_py):
if predicate_matches[state.pattern.py_predicates[i]] == -1: if predicate_matches[state.pattern.py_predicates[i]] == -1:
@ -688,8 +687,7 @@ cdef int8_t get_is_match(PatternStateC state,
spec = state.pattern spec = state.pattern
if spec.nr_attr > 0: if spec.nr_attr > 0:
for attr in spec.attrs[:spec.nr_attr]: for attr in spec.attrs[:spec.nr_attr]:
token_attr_value = get_token_attr_for_matcher(token.c, attr.attr) if get_token_attr_for_matcher(token, attr.attr) != attr.value:
if token_attr_value != attr.value:
return 0 return 0
for i in range(spec.nr_extra_attr): for i in range(spec.nr_extra_attr):
if spec.extra_attrs[i].value != extra_attrs[spec.extra_attrs[i].index]: if spec.extra_attrs[i].value != extra_attrs[spec.extra_attrs[i].index]:
@ -1007,7 +1005,6 @@ def _get_extra_predicates(spec, extra_predicates, vocab):
if attr.upper() == "TEXT": if attr.upper() == "TEXT":
attr = "ORTH" attr = "ORTH"
attr = IDS.get(attr.upper()) attr = IDS.get(attr.upper())
if isinstance(value, dict): if isinstance(value, dict):
output.extend(_get_extra_predicates_dict(attr, value, vocab, predicate_types, output.extend(_get_extra_predicates_dict(attr, value, vocab, predicate_types,
extra_predicates, seen_predicates)) extra_predicates, seen_predicates))