explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-09-23 04:19:11 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into spacy.io

Browse Source
This commit is contained in:
Ines Montani 2019-06-01 11:35:12 +02:00
commit 2b8bfd6cc7
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
website/docs/usage/rule-based-matching.md
View File

@ -405,7 +405,7 @@ class BadHTMLMerger(object):
for match_id, start, end in matches: for match_id, start, end in matches:
spans.append(doc[start:end]) spans.append(doc[start:end])
with doc.retokenize() as retokenizer: with doc.retokenize() as retokenizer:
for span in hashtags: for span in spans:
retokenizer.merge(span) retokenizer.merge(span)
for token in span: for token in span:
token._.bad_html = True # Mark token as bad HTML token._.bad_html = True # Mark token as bad HTML
@ -679,7 +679,7 @@ for match_id, start, end in matches:
if doc.vocab.strings[match_id] == "HASHTAG": if doc.vocab.strings[match_id] == "HASHTAG":
hashtags.append(doc[start:end]) hashtags.append(doc[start:end])
with doc.retokenize() as retokenizer: with doc.retokenize() as retokenizer:
for span in spans: for span in hashtags:
retokenizer.merge(span) retokenizer.merge(span)
for token in span: for token in span:
token._.is_hashtag = True token._.is_hashtag = True