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 and workflow to reflect new API

Browse Source 
on_match is now the second positional argument, to easily allow a
variable number of patterns while keeping the method clean and readable.
This commit is contained in:
ines 2017-05-20 12:59:03 +02:00
parent eb521af267
commit e10c48210d
2 changed files with 24 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
website/docs/api/matcher.jade
View File

@ -128,8 +128,8 @@ p
print('Matched!', matches)
matcher = Matcher(nlp.vocab)
matcher.add('HelloWorld', [{LOWER: "hello"}, {LOWER: "world"}], on_match=on_match)
matcher.add('GoogleMaps', [{ORTH: "Google"}, {ORTH: "Maps"}], on_match=on_match)
matcher.add('HelloWorld', on_match, [{LOWER: "hello"}, {LOWER: "world"}])
matcher.add('GoogleMaps', on_match, [{ORTH: "Google"}, {ORTH: "Maps"}])
doc = nlp(u'HELLO WORLD on Google Maps.')
matches = matcher(doc)
@ -140,16 +140,16 @@ p
+cell unicode
+cell An ID for the thing you're matching.
+row
+cell #[code *patterns]
+cell list
+cell
| Match pattern. A pattern consists of a list of dicts, where each
| dict describes a token.
+row
+cell #[code on_match]
+cell function
+cell
| Callback function to act on matches. Takes the arguments
| #[code matcher], #[code doc], #[code i] and #[code matches].
+row
+cell #[code *patterns]
+cell list
+cell
| Match pattern. A pattern consists of a list of dicts, where each
| dict describes a token.

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

@ -36,7 +36,9 @@ p
| First, we initialise the #[code Matcher] with a vocab. The matcher must
| always share the same vocab with the documents it will operate on. We
| can now call #[+api("matcher#add") #[code matcher.add()]] with an ID and
| our custom pattern:
| our custom pattern. The second argument lets you pass in an optional
| callback function to invoke on a successful match. For now, we set it
| to #[code None].
+code.
import spacy
@ -45,7 +47,9 @@ p
nlp = spacy.load('en')
matcher = Matcher(nlp.vocab)
matcher.add('HelloWorld', [{LOWER: 'hello'}, {IS_PUNCT: True}, {LOWER: 'world'}])
# add match ID "HelloWorld" with no callback and one pattern
matcher.add('HelloWorld', on_match=None,
[{LOWER: 'hello'}, {IS_PUNCT: True}, {LOWER: 'world'}])
doc = nlp(u'Hello, world! Hello world!')
matches = matcher(doc)
@ -58,8 +62,9 @@ p
| without punctuation between "hello" and "world":
+code.
matcher.add('HelloWorld', [{LOWER: 'hello'}, {IS_PUNCT: True}, {LOWER: 'world'}],
[{LOWER: 'hello'}, {LOWER: 'world'}])
matcher.add('HelloWorld', on_match=None,
[{LOWER: 'hello'}, {IS_PUNCT: True}, {LOWER: 'world'}],
[{LOWER: 'hello'}, {LOWER: 'world'}])
p
| By default, the matcher will only return the matches and
@ -92,9 +97,9 @@ p
nlp = spacy.load('en')
matcher = Matcher(nlp.vocab)
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)
matcher.add('GoogleIO', on_match=add_event_ent,
[{ORTH: 'Google'}, {UPPER: 'I'}, {ORTH: '/'}, {UPPER: 'O'}],
[{ORTH: 'Google'}, {UPPER: 'I'}, {ORTH: '/'}, {UPPER: 'O'}, {IS_DIGIT: True}])
# Get the ID of the 'EVENT' entity type. This is required to set an entity.
EVENT = nlp.vocab.strings['EVENT']
@ -114,9 +119,9 @@ p
| function #[code merge_and_flag]:
+code.
matcher.add('BAD_HTML', [{ORTH: '<'}, {LOWER: 'br'}, {ORTH: '>'}],
[{ORTH: '<'}, {LOWER: 'br/'}, {ORTH: '>'}]
on_match=merge_and_flag)
matcher.add('BAD_HTML', on_match=merge_and_flag,
[{ORTH: '<'}, {LOWER: 'br'}, {ORTH: '>'}],
[{ORTH: '<'}, {LOWER: 'br/'}, {ORTH: '>'}])
# Add a new custom flag to the vocab, which is always False by default.
# BAD_HTML_FLAG will be the flag ID, which we can use to set it to True on the span.