explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-10-31 07:57:35 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #1352 from hscspring/patch-5

Browse Source 
Update customizing-tokenizer.jade
This commit is contained in:
Matthew Honnibal 2017-09-22 16:11:49 +02:00 committed by GitHub
commit 9177313063
1 changed files with 8 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
website/docs/usage/customizing-tokenizer.jade
View File

@ -40,7 +40,9 @@ p
{
ORTH: u'me'}])
assert [w.text for w in nlp(u'gimme that')] == [u'gim', u'me', u'that']
assert [w.lemma_ for w in nlp(u'gimme that')] == [u'give', u'me', u'that']
# Pronoun lemma is returned as -PRON-
# More details please see: https://spacy.io/docs/usage/troubleshooting#pron-lemma
assert [w.lemma_ for w in nlp(u'gimme that')] == [u'give', u'-PRON-', u'that']
p
| The special case doesn't have to match an entire whitespace-delimited
@ -172,12 +174,14 @@ p
prefix_re = re.compile(r'''[\[\("']''')
suffix_re = re.compile(r'''[\]\)"']''')
infix_re = re.compile(r'''[-~]''')
def create_tokenizer(nlp):
return Tokenizer(nlp.vocab,
return Tokenizer(nlp.vocab, rules={},
prefix_search=prefix_re.search,
suffix_search=suffix_re.search)
suffix_search=suffix_re.search,
infix_finditer=infix_re.finditer)
nlp = spacy.load('en', tokenizer=create_make_doc)
nlp = spacy.load('en', create_make_doc=create_tokenizer)
p
| If you need to subclass the tokenizer instead, the relevant methods to