explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-12 18:26:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #622 from savkov/patch-2

Browse Source 
Added missing brackets & suggested import statmnt
This commit is contained in:
Matthew Honnibal 2016-11-12 04:21:04 +11:00 committed by GitHub
commit f27db1d9b5
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
website/docs/usage/rule-based-matching.jade
View File

@ -92,6 +92,7 @@ p
| return a 4-tuple #[code (ent_id, label, start, end)].
+code.
from spacy.tokens.doc import Doc
def trim_title(doc, ent_id, label, start, end):
if doc[start].check_flag(IS_TITLE_TERM):
return (ent_id, label, start+1, end)
@ -100,8 +101,8 @@ p
titles = set(title.lower() for title in [u'Mr.', 'Dr.', 'Ms.', u'Admiral'])
IS_TITLE_TERM = matcher.vocab.add_flag(lambda string: string.lower() in titles)
matcher.add_entity('PersonName', acceptor=trim_title)
matcher.add_pattern('PersonName', {LOWER: 'mr.'}, {LOWER: 'cruise'}])
matcher.add_pattern('PersonName', {LOWER: 'dr.'}, {LOWER: 'seuss'}])
matcher.add_pattern('PersonName', [{LOWER: 'mr.'}, {LOWER: 'cruise'}])
matcher.add_pattern('PersonName', [{LOWER: 'dr.'}, {LOWER: 'seuss'}])
doc = Doc(matcher.vocab, words=[u'Mr.', u'Cruise', u'likes', 'Dr.', u'Seuss'])
for ent_id, label, start, end in matcher(doc):
print(doc[start:end].text)