Fix Custom Tokenizer docs

- Fix mismatched quotations
- Make it more clear where ORTH, LEMMA, and POS symbols come from
- Make strings consistent
- Fix lemma_ assertion s/-PRON-/me/
This commit is contained in:
Kevin Gao 2017-01-17 10:35:55 -08:00
parent dbe8dafb52
commit 7ec710af0e

View File

@ -26,6 +26,9 @@ p
| #[+api("tokenizer") #[code Tokenizer]] instance:
+code.
import spacy
from spacy.symbols import ORTH, LEMMA, POS
nlp = spacy.load('en')
assert [w.text for w in nlp(u'gimme that')] == [u'gimme', u'that']
nlp.tokenizer.add_special_case(u'gimme',
@ -37,7 +40,7 @@ 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'-PRON-', u'that']
assert [w.lemma_ for w in nlp(u'gimme that')] == [u'give', u'me', u'that']
p
| The special case doesn't have to match an entire whitespace-delimited
@ -52,9 +55,9 @@ p
| The special case rules have precedence over the punctuation splitting:
+code.
nlp.tokenizer.add_special_case(u"...gimme...?",
nlp.tokenizer.add_special_case(u'...gimme...?',
[{
ORTH: u'...gimme...?", LEMMA: "give", TAG: "VB"}])
ORTH: u'...gimme...?', LEMMA: u'give', TAG: u'VB'}])
assert len(nlp(u'...gimme...?')) == 1
p