explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-11 04:08:09 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update Matcher API docs

Browse Source
This commit is contained in:
ines 2017-05-20 12:27:22 +02:00
parent e39ad78267
commit 9edc7fb0ba
1 changed files with 12 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
website/docs/usage/rule-based-matching.jade
View File

@ -45,7 +45,7 @@ p
nlp = spacy.load('en')
matcher = Matcher(nlp.vocab)
matcher.add_pattern('HelloWorld', [{LOWER: 'hello'}, {IS_PUNCT: True}, {LOWER: 'world'}])
matcher.add('HelloWorld', [{LOWER: 'hello'}, {IS_PUNCT: True}, {LOWER: 'world'}])
doc = nlp(u'Hello, world! Hello world!')
matches = matcher(doc)
@ -58,8 +58,8 @@ p
| without punctuation between "hello" and "world":
+code.
matcher.add_pattern('HelloWorld', [{LOWER: 'hello'}, {IS_PUNCT: True}, {LOWER: 'world'}],
[{LOWER: 'hello'}, {LOWER: 'world'}])
matcher.add('HelloWorld', [{LOWER: 'hello'}, {IS_PUNCT: True}, {LOWER: 'world'}],
[{LOWER: 'hello'}, {LOWER: 'world'}])
p
| By default, the matcher will only return the matches and
@ -81,7 +81,7 @@ p
| To be safe, you only match on the uppercase versions, in case someone has
| written it as "Google i/o". You also add a second pattern with an added
| #[code {IS_DIGIT: True}] token – this will make sure you also match on
| "Google I/O 2017". If this pattern matches, spaCy should execute your
| "Google I/O 2017". If your pattern matches, spaCy should execute your
| custom callback function #[code add_event_ent].
+code.
@ -92,17 +92,16 @@ p
nlp = spacy.load('en')
matcher = Matcher(nlp.vocab)
matcher.add_pattern('GoogleIO', [{ORTH: 'Google'}, {UPPER: 'I'}, {ORTH: '/'}, {UPPER: 'O'}],
[{ORTH: 'Google'}, {UPPER: 'I'}, {ORTH: '/'}, {UPPER: 'O'}, {IS_DIGIT: True}],
on_match=add_event_ent)
matcher.add('GoogleIO', [{ORTH: 'Google'}, {UPPER: 'I'}, {ORTH: '/'}, {UPPER: 'O'}],
[{ORTH: 'Google'}, {UPPER: 'I'}, {ORTH: '/'}, {UPPER: 'O'}, {IS_DIGIT: True}],
on_match=add_event_ent)
# Get the ID of the 'EVENT' entity type. This is required to set an entity.
EVENT = nlp.vocab.strings['EVENT']
def add_event_ent(matcher, doc, i, matches):
# Get the current match and create tuple of entity label, start and end.
# Append entity to the doc's entity. (Don't overwrite doc.ents, in case
# it already has other entities!)
# Append entity to the doc's entity. (Don't overwrite doc.ents!)
match_id, start, end = matches[i]
doc.ents += ((EVENT, start, end),)
@ -115,12 +114,12 @@ p
| function #[code merge_and_flag]:
+code.
matcher.add_pattern('BAD_HTML', [{ORTH: '<'}, {LOWER: 'br'}, {ORTH: '>'}],
[{ORTH: '<'}, {LOWER: 'br/'}, {ORTH: '>'}]
on_match=merge_and_flag)
matcher.add('BAD_HTML', [{ORTH: '<'}, {LOWER: 'br'}, {ORTH: '>'}],
[{ORTH: '<'}, {LOWER: 'br/'}, {ORTH: '>'}]
on_match=merge_and_flag)
# Add a new custom flag to the vocab, which is always False by default.
# BAD_HTML will be the flag ID, which we can use to set it to True on the span.
# BAD_HTML_FLAG will be the flag ID, which we can use to set it to True on the span.
BAD_HTML_FLAG = doc.vocab.add_flag(lambda text: False)
def merge_and_flag(matcher, doc, i, matches):