explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-10 19:57:17 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix memory leak when adding empty morph (#6581)

Browse Source 
Fix lookup of empty morph in the morphology table, which fixes a memory
leak where a new morphology tag was allocated each time the empty morph
tag was added.
This commit is contained in:
Adriane Boyd 2020-12-18 11:51:01 +01:00 committed by GitHub
parent fd640afcd8
commit e10295c9fd
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
spacy/morphology.pyx
View File

@ -29,7 +29,7 @@ cdef class Morphology:
FEATURE_SEP = "|" FEATURE_SEP = "|"
FIELD_SEP = "=" FIELD_SEP = "="
VALUE_SEP = "," VALUE_SEP = ","
# not an empty string so that the PreshMap key is not 0 # not an empty string so we can distinguish unset morph from empty morph
EMPTY_MORPH = symbols.NAMES[symbols._] EMPTY_MORPH = symbols.NAMES[symbols._]
def __init__(self, StringStore strings): def __init__(self, StringStore strings):
@ -50,8 +50,8 @@ cdef class Morphology:
""" """
cdef MorphAnalysisC* tag_ptr cdef MorphAnalysisC* tag_ptr
if isinstance(features, str): if isinstance(features, str):
if features == self.EMPTY_MORPH: if features == "":
features = "" features = self.EMPTY_MORPH
tag_ptr = <MorphAnalysisC*>self.tags.get(<hash_t>self.strings[features]) tag_ptr = <MorphAnalysisC*>self.tags.get(<hash_t>self.strings[features])
if tag_ptr != NULL: if tag_ptr != NULL:
return tag_ptr.key return tag_ptr.key
@ -71,13 +71,9 @@ cdef class Morphology:
)) ))
cdef MorphAnalysisC tag = self.create_morph_tag(field_feature_pairs) cdef MorphAnalysisC tag = self.create_morph_tag(field_feature_pairs)
# the hash key for the tag is either the hash of the normalized UFEATS # the hash key for the tag is either the hash of the normalized UFEATS
# string or the hash of an empty placeholder (using the empty string # string or the hash of an empty placeholder
# would give a hash key of 0, which is not good for PreshMap)
norm_feats_string = self.normalize_features(features) norm_feats_string = self.normalize_features(features)
if norm_feats_string: tag.key = self.strings.add(norm_feats_string)
tag.key = self.strings.add(norm_feats_string)
else:
tag.key = self.strings.add(self.EMPTY_MORPH)
self.insert(tag) self.insert(tag)
return tag.key return tag.key