explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-12 10:16:27 +03:00
Code Issues Packages Projects Releases Wiki Activity

Maintain support for empty DocBin span groups (#10538)

Browse Source
This commit is contained in:
Adriane Boyd 2022-03-24 11:51:07 +01:00 committed by GitHub
parent 2ff197603e
commit 31a5d99efa
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
spacy/tokens/_serialize.py
View File

@ -147,7 +147,8 @@ class DocBin:
doc = Doc(vocab, words=tokens[:, orth_col], spaces=spaces) # type: ignore doc = Doc(vocab, words=tokens[:, orth_col], spaces=spaces) # type: ignore
doc = doc.from_array(self.attrs, tokens) # type: ignore doc = doc.from_array(self.attrs, tokens) # type: ignore
doc.cats = self.cats[i] doc.cats = self.cats[i]
if self.span_groups[i] != SpanGroups._EMPTY_BYTES: # backwards-compatibility: may be b'' or serialized empty list
if self.span_groups[i] and self.span_groups[i] != SpanGroups._EMPTY_BYTES:
doc.spans.from_bytes(self.span_groups[i]) doc.spans.from_bytes(self.span_groups[i])
else: else:
doc.spans.clear() doc.spans.clear()