explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-06-02 20:23:12 +03:00
Code Issues Packages Projects Releases Wiki Activity

Use the same tuple in Span cmp and hash (#12251)

Browse Source
This commit is contained in:
Adriane Boyd 2023-02-08 14:28:34 +01:00 committed by GitHub
parent eec5ccd72f
commit 5089efa2d0
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 15 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
spacy/tokens/span.pyx
View File

@ -134,10 +134,8 @@ cdef class Span:
else: else:
return True return True
cdef SpanC* span_c = self.span_c() self_tuple = self._cmp_tuple()
cdef SpanC* other_span_c = other.span_c() other_tuple = other._cmp_tuple()
self_tuple = (span_c.start_char, span_c.end_char, span_c.label, span_c.kb_id, self.id, self.doc)
other_tuple = (other_span_c.start_char, other_span_c.end_char, other_span_c.label, other_span_c.kb_id, other.id, other.doc)
# < # <
if op == 0: if op == 0:
return self_tuple < other_tuple return self_tuple < other_tuple
@ -158,8 +156,20 @@ cdef class Span:
return self_tuple >= other_tuple return self_tuple >= other_tuple
def __hash__(self): def __hash__(self):
return hash(self._cmp_tuple())
def _cmp_tuple(self):
cdef SpanC* span_c = self.span_c() cdef SpanC* span_c = self.span_c()
return hash((self.doc, span_c.start_char, span_c.end_char, span_c.label, span_c.kb_id, span_c.id)) return (
span_c.start_char,
span_c.end_char,
span_c.start,
span_c.end,
span_c.label,
span_c.kb_id,
span_c.id,
self.doc,
)
def __len__(self): def __len__(self):
"""Get the number of tokens in the span. """Get the number of tokens in the span.