explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 09:26:27 +03:00
Code Issues Packages Projects Releases Wiki Activity

Matcher performance fix for extension predicates: use shared key function (#12272)

Browse Source 
* standardize predicate key format

* single key function

* Make optional args in key function keyword-only

---------

Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
This commit is contained in:
Kevin Humphreys 2023-02-26 23:35:08 -08:00 committed by GitHub
parent 1e8bac99f3
commit acdd993071
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 10 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
spacy/matcher/matcher.pyx
View File

@ -828,6 +828,11 @@ def _get_attr_values(spec, string_store):
return attr_values return attr_values
def _predicate_cache_key(attr, predicate, value, *, regex=False, fuzzy=None):
# tuple order affects performance
return (attr, regex, fuzzy, predicate, srsly.json_dumps(value, sort_keys=True))
# These predicate helper classes are used to match the REGEX, IN, >= etc # These predicate helper classes are used to match the REGEX, IN, >= etc
# extensions to the matcher introduced in #3173. # extensions to the matcher introduced in #3173.
@ -847,7 +852,7 @@ class _FuzzyPredicate:
fuzz = self.predicate[len("FUZZY"):] # number after prefix fuzz = self.predicate[len("FUZZY"):] # number after prefix
self.fuzzy = int(fuzz) if fuzz else -1 self.fuzzy = int(fuzz) if fuzz else -1
self.fuzzy_compare = fuzzy_compare self.fuzzy_compare = fuzzy_compare
self.key = (self.attr, self.fuzzy, self.predicate, srsly.json_dumps(value, sort_keys=True)) self.key = _predicate_cache_key(self.attr, self.predicate, value, fuzzy=self.fuzzy)
def __call__(self, Token token): def __call__(self, Token token):
if self.is_extension: if self.is_extension:
@ -869,7 +874,7 @@ class _RegexPredicate:
self.value = re.compile(value) self.value = re.compile(value)
self.predicate = predicate self.predicate = predicate
self.is_extension = is_extension self.is_extension = is_extension
self.key = (self.attr, self.predicate, srsly.json_dumps(value, sort_keys=True)) self.key = _predicate_cache_key(self.attr, self.predicate, value)
if self.predicate not in self.operators: if self.predicate not in self.operators:
raise ValueError(Errors.E126.format(good=self.operators, bad=self.predicate)) raise ValueError(Errors.E126.format(good=self.operators, bad=self.predicate))
@ -905,7 +910,7 @@ class _SetPredicate:
self.value = set(get_string_id(v) for v in value) self.value = set(get_string_id(v) for v in value)
self.predicate = predicate self.predicate = predicate
self.is_extension = is_extension self.is_extension = is_extension
self.key = (self.attr, self.regex, self.fuzzy, self.predicate, srsly.json_dumps(value, sort_keys=True)) self.key = _predicate_cache_key(self.attr, self.predicate, value, regex=self.regex, fuzzy=self.fuzzy)
if self.predicate not in self.operators: if self.predicate not in self.operators:
raise ValueError(Errors.E126.format(good=self.operators, bad=self.predicate)) raise ValueError(Errors.E126.format(good=self.operators, bad=self.predicate))
@ -977,7 +982,7 @@ class _ComparisonPredicate:
self.value = value self.value = value
self.predicate = predicate self.predicate = predicate
self.is_extension = is_extension self.is_extension = is_extension
self.key = (self.attr, self.predicate, srsly.json_dumps(value, sort_keys=True)) self.key = _predicate_cache_key(self.attr, self.predicate, value)
if self.predicate not in self.operators: if self.predicate not in self.operators:
raise ValueError(Errors.E126.format(good=self.operators, bad=self.predicate)) raise ValueError(Errors.E126.format(good=self.operators, bad=self.predicate))
@ -1092,7 +1097,7 @@ def _get_extension_extra_predicates(spec, extra_predicates, predicate_types,
if isinstance(value, dict): if isinstance(value, dict):
for type_, cls in predicate_types.items(): for type_, cls in predicate_types.items():
if type_ in value: if type_ in value:
key = (attr, type_, srsly.json_dumps(value[type_], sort_keys=True)) key = _predicate_cache_key(attr, type_, value[type_])
if key in seen_predicates: if key in seen_predicates:
output.append(seen_predicates[key]) output.append(seen_predicates[key])
else: else: