explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-02-11 17:10:36 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix corpus when no raw text supplied

Browse Source
This commit is contained in:
Matthew Honnibal 2020-06-09 12:33:14 +02:00
parent d9289712ba
commit 549164c31c
1 changed files with 10 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
spacy/gold/corpus.py
View File

@ -201,7 +201,16 @@ class GoldCorpus(object):
): ):
""" Setting gold_preproc will result in creating a doc per sentence """ """ Setting gold_preproc will result in creating a doc per sentence """
for eg_dict in annotations: for eg_dict in annotations:
example = Example.from_dict(eg_dict, doc=nlp.make_doc(eg_dict["text"])) if eg_dict["text"]:
example = Example.from_dict(
eg_dict,
doc=nlp.make_doc(eg_dict["text"])
)
else:
example = Example.from_dict(
eg_dict,
doc=Doc(nlp.vocab, words=eg_dict["words"])
)
example_docs = [] example_docs = []
if gold_preproc: if gold_preproc:
split_examples = example.split_sents() split_examples = example.split_sents()