explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-11 04:08:09 +03:00
Code Issues Packages Projects Releases Wiki Activity

Unify matcher get_ent_id and get_pattern_key (#4415)

Browse Source 
This is basically stabbing blindly at the ghost match problem, but it at
least seems like there was a bug previously here --- so this should
hopefully be an improvement, even if it doesn't fix the ghost match
problem.
This commit is contained in:
Matthew Honnibal 2019-10-09 15:26:31 +02:00 committed by GitHub
parent 77643de2ca
commit fa95c030a5
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 21 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
spacy/matcher/matcher.pyx
View File

@ -138,7 +138,7 @@ cdef class Matcher:
self._callbacks.pop(key)
cdef int i = 0
while i < self.patterns.size():
pattern_key = get_pattern_key(self.patterns.at(i))
pattern_key = get_ent_id(self.patterns.at(i))
if pattern_key == key:
self.patterns.erase(self.patterns.begin()+i)
else:
@ -293,18 +293,6 @@ cdef find_matches(TokenPatternC** patterns, int n, Doc doc, extensions=None,
return output
cdef attr_t get_ent_id(const TokenPatternC* pattern) nogil:
# There have been a few bugs here.
# The code was originally designed to always have pattern[1].attrs.value
# be the ent_id when we get to the end of a pattern. However, Issue #2671
# showed this wasn't the case when we had a reject-and-continue before a
# match.
# The patch to #2671 was wrong though, which came up in #3839.
while pattern.attrs.attr != ID:
pattern += 1
return pattern.attrs.value
cdef void transition_states(vector[PatternStateC]& states, vector[MatchC]& matches,
char* cached_py_predicates,
Token token, const attr_t* extra_attrs, py_predicates) except *:
@ -583,8 +571,26 @@ cdef TokenPatternC* init_pattern(Pool mem, attr_t entity_id, object token_specs)
return pattern
cdef attr_t get_pattern_key(const TokenPatternC* pattern) nogil:
while pattern.nr_attr != 0 or pattern.nr_extra_attr != 0 or pattern.nr_py != 0:
cdef attr_t get_ent_id(const TokenPatternC* pattern) nogil:
# There have been a few bugs here. We used to have two functions,
# get_ent_id and get_pattern_key that tried to do the same thing. These
# are now unified to try to solve the "ghost match" problem.
# Below is the previous implementation of get_ent_id and the comment on it,
# preserved for reference while we figure out whether the heisenbug in the
# matcher is resolved.
#
#
# cdef attr_t get_ent_id(const TokenPatternC* pattern) nogil:
# # The code was originally designed to always have pattern[1].attrs.value
# # be the ent_id when we get to the end of a pattern. However, Issue #2671
# # showed this wasn't the case when we had a reject-and-continue before a
# # match.
# # The patch to #2671 was wrong though, which came up in #3839.
# while pattern.attrs.attr != ID:
# pattern += 1
# return pattern.attrs.value
while pattern.nr_attr != 0 or pattern.nr_extra_attr != 0 or pattern.nr_py != 0 \
or pattern.quantifier != ZERO:
pattern += 1
id_attr = pattern[0].attrs[0]
if id_attr.attr != ID: