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

Use string values for attrs in Matcher docs

Browse Source
This commit is contained in:
ines 2017-05-22 13:54:45 +02:00
parent b3c7ee0148
commit d5a6a9a6a9
2 changed files with 16 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -20,9 +20,8 @@ p Create the rule-based #[code Matcher].
+aside-code("Example").
from spacy.matcher import Matcher
from spacy.attrs import LOWER
patterns = {"HelloWorld": [{LOWER: "hello"}, {LOWER: "world"}]}
patterns = {'HelloWorld': [{'LOWER': 'hello'}, {'LOWER': 'world'}]}
matcher = Matcher(nlp.vocab)
+table(["Name", "Type", "Description"])
@ -50,10 +49,9 @@ p Find all token sequences matching the supplied patterns on the #[code Doc].
+aside-code("Example").
from spacy.matcher import Matcher
from spacy.attrs import LOWER
matcher = Matcher(nlp.vocab)
pattern = [{LOWER: "hello"}, {LOWER: "world"}]
pattern = [{'LOWER': "hello"}, {'LOWER': "world"}]
matcher.add("HelloWorld", on_match=None, pattern)
doc = nlp(u'hello world!')
matches = matcher(doc)
@ -129,7 +127,7 @@ p
+aside-code("Example").
matcher = Matcher(nlp.vocab)
assert len(matcher) == 0
matcher.add('Rule', None, [{ORTH: 'test'}])
matcher.add('Rule', None, [{'ORTH': 'test'}])
assert len(matcher) == 1
+table(["Name", "Type", "Description"])
@ -146,7 +144,7 @@ p Check whether the matcher contains rules for a match ID.
+aside-code("Example").
matcher = Matcher(nlp.vocab)
assert 'Rule' in matcher == False
matcher.add('Rule', None, [{ORTH: 'test'}])
matcher.add('Rule', None, [{'ORTH': 'test'}])
assert 'Rule' in matcher == True
+table(["Name", "Type", "Description"])
@ -175,8 +173,8 @@ p
print('Matched!', matches)
matcher = Matcher(nlp.vocab)
matcher.add('HelloWorld', on_match, [{LOWER: "hello"}, {LOWER: "world"}])
matcher.add('GoogleMaps', on_match, [{ORTH: "Google"}, {ORTH: "Maps"}])
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)
@ -208,7 +206,7 @@ p
| ID does not exist.
+aside-code("Example").
matcher.add('Rule', None, [{ORTH: 'test'}])
matcher.add('Rule', None, [{'ORTH': 'test'}])
assert 'Rule' in matcher == True
matcher.remove('Rule')
assert 'Rule' in matcher == False
@ -228,7 +226,7 @@ p
| patterns.
+aside-code("Example").
pattern = [{ORTH: 'test'}]
pattern = [{'ORTH': 'test'}]
matcher.add('Rule', None, pattern)
(on_match, patterns) = matcher.get('Rule')
assert patterns = [pattern]

18
website/docs/usage/rule-based-matching.jade
View File

@ -30,7 +30,7 @@ p
| or "WORLD".
+code.
[{LOWER: 'hello'}, {IS_PUNCT: True}, {LOWER: 'world'}]
[{'LOWER': 'hello'}, {'IS_PUNCT': True}, {'LOWER': 'world'}]
p
| First, we initialise the #[code Matcher] with a vocab. The matcher must
@ -43,13 +43,12 @@ p
+code.
import spacy
from spacy.matcher import Matcher
from spacy.attrs import LOWER, IS_PUNCT # don't forget to import the attrs!
nlp = spacy.load('en')
matcher = Matcher(nlp.vocab)
# add match ID "HelloWorld" with no callback and one pattern
matcher.add('HelloWorld', on_match=None,
[{LOWER: 'hello'}, {IS_PUNCT: True}, {LOWER: 'world'}])
[{'LOWER': 'hello'}, {'IS_PUNCT': True}, {'LOWER': 'world'}])
doc = nlp(u'Hello, world! Hello world!')
matches = matcher(doc)
@ -63,8 +62,8 @@ p
+code.
matcher.add('HelloWorld', on_match=None,
[{LOWER: 'hello'}, {IS_PUNCT: True}, {LOWER: 'world'}],
[{LOWER: 'hello'}, {LOWER: 'world'}])
[{'LOWER': 'hello'}, {'IS_PUNCT': True}, {'LOWER': 'world'}],
[{'LOWER': 'hello'}, {'LOWER': 'world'}])
p
| By default, the matcher will only return the matches and
@ -92,14 +91,13 @@ p
+code.
import spacy
from spacy.matcher import Matcher
from spacy.attrs import ORTH, UPPER, LOWER, IS_DIGIT
nlp = spacy.load('en')
matcher = Matcher(nlp.vocab)
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}])
[{'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']
@ -120,8 +118,8 @@ p
+code.
matcher.add('BAD_HTML', on_match=merge_and_flag,
[{ORTH: '<'}, {LOWER: 'br'}, {ORTH: '>'}],
[{ORTH: '<'}, {LOWER: 'br/'}, {ORTH: '>'}])
[{'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.