explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 17:36:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

fix attrs field in the matcher (#4423)

Browse Source 
* raise specific error when removing a matcher rule that doesn't exist

* rephrasing

* ensure attrs is NULL when nr_attr == 0 + several fixes to prevent OOB
This commit is contained in:
Sofie Van Landeghem 2019-10-10 15:20:59 +02:00 committed by Matthew Honnibal
parent 5efae495f1
commit da6e0de34f
1 changed files with 13 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
spacy/matcher/matcher.pyx
View File

@ -523,6 +523,7 @@ cdef char get_is_match(PatternStateC state,
if predicate_matches[state.pattern.py_predicates[i]] == -1: if predicate_matches[state.pattern.py_predicates[i]] == -1:
return 0 return 0
spec = state.pattern spec = state.pattern
if spec.nr_attr > 0:
for attr in spec.attrs[:spec.nr_attr]: for attr in spec.attrs[:spec.nr_attr]:
if get_token_attr(token, attr.attr) != attr.value: if get_token_attr(token, attr.attr) != attr.value:
return 0 return 0
@ -533,7 +534,11 @@ cdef char get_is_match(PatternStateC state,
cdef char get_is_final(PatternStateC state) nogil: cdef char get_is_final(PatternStateC state) nogil:
if state.pattern[1].attrs[0].attr == ID and state.pattern[1].nr_attr == 0: if state.pattern[1].nr_attr == 0 and state.pattern[1].attrs != NULL:
id_attr = state.pattern[1].attrs[0]
if id_attr.attr != ID:
with gil:
raise ValueError(Errors.E074.format(attr=ID, bad_attr=id_attr.attr))
return 1 return 1
else: else:
return 0 return 0
@ -548,6 +553,8 @@ cdef TokenPatternC* init_pattern(Pool mem, attr_t entity_id, object token_specs)
cdef int i, index cdef int i, index
for i, (quantifier, spec, extensions, predicates) in enumerate(token_specs): for i, (quantifier, spec, extensions, predicates) in enumerate(token_specs):
pattern[i].quantifier = quantifier pattern[i].quantifier = quantifier
# Ensure attrs refers to a null pointer if nr_attr == 0
if len(spec) > 0:
pattern[i].attrs = <AttrValueC*>mem.alloc(len(spec), sizeof(AttrValueC)) pattern[i].attrs = <AttrValueC*>mem.alloc(len(spec), sizeof(AttrValueC))
pattern[i].nr_attr = len(spec) pattern[i].nr_attr = len(spec)
for j, (attr, value) in enumerate(spec): for j, (attr, value) in enumerate(spec):
@ -564,6 +571,7 @@ cdef TokenPatternC* init_pattern(Pool mem, attr_t entity_id, object token_specs)
pattern[i].nr_py = len(predicates) pattern[i].nr_py = len(predicates)
pattern[i].key = hash64(pattern[i].attrs, pattern[i].nr_attr * sizeof(AttrValueC), 0) pattern[i].key = hash64(pattern[i].attrs, pattern[i].nr_attr * sizeof(AttrValueC), 0)
i = len(token_specs) i = len(token_specs)
# Even though here, nr_attr == 0, we're storing the ID value in attrs[0] (bug-prone, thread carefully!)
pattern[i].attrs = <AttrValueC*>mem.alloc(2, sizeof(AttrValueC)) pattern[i].attrs = <AttrValueC*>mem.alloc(2, sizeof(AttrValueC))
pattern[i].attrs[0].attr = ID pattern[i].attrs[0].attr = ID
pattern[i].attrs[0].value = entity_id pattern[i].attrs[0].value = entity_id