spaCy/website/docs/api/matcher.jade

//- 💫 DOCS > API > MATCHER

include ../../_includes/_mixins

p Match sequences of tokens, based on pattern rules.

+infobox("⚠️ Deprecation note")
    |  As of spaCy 2.0, #[code Matcher.add_pattern] and #[code Matcher.add_entity]
    |  are deprecated and have been replaced with a simpler
    |  #[+api("matcher#add") #[code Matcher.add]] that lets you add a list of
    |  patterns and a callback for a given match ID. #[code Matcher.get_entity]
    |  is now called #[+api("matcher#get") #[code matcher.get]].
    |  #[code Matcher.load] (not useful, as it didn't allow specifying callbacks),
    |  and #[code Matcher.has_entity] (now redundant) have been removed.

+h(2, "init") Matcher.__init__
    +tag method

p Create the rule-based #[code Matcher].

+aside-code("Example").
    from spacy.matcher import Matcher

    patterns = {'HelloWorld': [{'LOWER': 'hello'}, {'LOWER': 'world'}]}
    matcher = Matcher(nlp.vocab)

+table(["Name", "Type", "Description"])
    +row
        +cell #[code vocab]
        +cell #[code Vocab]
        +cell
            |  The vocabulary object, which must be shared with the documents
            |  the matcher will operate on.

    +row
        +cell #[code patterns]
        +cell dict
        +cell Patterns to add to the matcher, keyed by ID.

    +footrow
        +cell returns
        +cell #[code Matcher]
        +cell The newly constructed object.

+h(2, "call") Matcher.__call__
    +tag method

p Find all token sequences matching the supplied patterns on the #[code Doc].

+aside-code("Example").
    from spacy.matcher import Matcher

    matcher = Matcher(nlp.vocab)
    pattern = [{'LOWER': "hello"}, {'LOWER': "world"}]
    matcher.add("HelloWorld", None, pattern)
    doc = nlp(u'hello world!')
    matches = matcher(doc)

+infobox("Important note")
    |  By default, the matcher #[strong does not perform any action] on matches,
    |  like tagging matched phrases with entity types. Instead, actions need to
    |  be specified when #[strong adding patterns or entities], by
    |  passing in a callback function as the #[code on_match] argument on
    |  #[+api("matcher#add") #[code add]]. This allows you to define custom
    |  actions per pattern within the same matcher. For example, you might only
    |  want to merge some entity types, and set custom flags for other matched
    |  patterns. For more details and examples, see the usage workflow on
    |  #[+a("/docs/usage/rule-based-matching") rule-based matching].

+table(["Name", "Type", "Description"])
    +row
        +cell #[code doc]
        +cell #[code Doc]
        +cell The document to match over.

    +footrow
        +cell returns
        +cell list
        +cell
            |  A list of #[code (match_id, start, end)] tuples, describing the
            |  matches. A match tuple describes a span #[code doc[start:end]].
            |  The #[code match_id] is the ID of the added match pattern.

+h(2, "pipe") Matcher.pipe
    +tag method

p Match a stream of documents, yielding them in turn.

+aside-code("Example").
    from spacy.matcher import Matcher
    matcher = Matcher(nlp.vocab)
    for doc in matcher.pipe(texts, batch_size=50, n_threads=4):
        pass

+table(["Name", "Type", "Description"])
    +row
        +cell #[code docs]
        +cell iterable
        +cell A stream of documents.

    +row
        +cell #[code batch_size]
        +cell int
        +cell The number of documents to accumulate into a working set.

    +row
        +cell #[code n_threads]
        +cell int
        +cell
            |  The number of threads with which to work on the buffer in
            |  parallel, if the #[code Matcher] implementation supports
            |  multi-threading.

    +footrow
        +cell yields
        +cell #[code Doc]
        +cell Documents, in order.

+h(2, "len") Matcher.__len__
    +tag method
    +tag-new(2)

p
    |  Get the number of rules added to the matcher. Note that this only returns
    |  the number of rules (identical with the number of IDs), not the number
    |  of individual patterns.

+aside-code("Example").
    matcher = Matcher(nlp.vocab)
    assert len(matcher) == 0
    matcher.add('Rule', None, [{'ORTH': 'test'}])
    assert len(matcher) == 1

+table(["Name", "Type", "Description"])
    +footrow
        +cell returns
        +cell int
        +cell The number of rules.

+h(2, "contains") Matcher.__contains__
    +tag method
    +tag-new(2)

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'}])
    assert 'Rule' in matcher == True

+table(["Name", "Type", "Description"])
    +row
        +cell #[code key]
        +cell unicode
        +cell The match ID.
    +footrow
        +cell returns
        +cell int
        +cell Whether the matcher contains rules for this match ID.

+h(2, "add") Matcher.add
    +tag method
    +tag-new(2)

p
    |  Add a rule to the matcher, consisting of an ID key, one or more patterns, and
    |  a callback function to act on the matches. The callback function will
    |  receive the arguments #[code matcher], #[code doc], #[code i] and
    |  #[code matches]. If a pattern already exists for the given ID, the
    |  patterns will be extended. An #[code on_match] callback will be
    |  overwritten.

+aside-code("Example").
    def on_match(matcher, doc, id, matches):
        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'}])
    doc = nlp(u'HELLO WORLD on Google Maps.')
    matches = matcher(doc)

+table(["Name", "Type", "Description"])
    +row
        +cell #[code match_id]
        +cell unicode
        +cell An ID for the thing you're matching.

    +row
        +cell #[code on_match]
        +cell callable or #[code None]
        +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.

+h(2, "remove") Matcher.remove
    +tag method
    +tag-new(2)

p
    |  Remove a rule from the matcher. A #[code KeyError] is raised if the match
    |  ID does not exist.

+aside-code("Example").
    matcher.add('Rule', None, [{'ORTH': 'test'}])
    assert 'Rule' in matcher == True
    matcher.remove('Rule')
    assert 'Rule' in matcher == False

+table(["Name", "Type", "Description"])
    +row
        +cell #[code key]
        +cell unicode
        +cell The ID of the match rule.

+h(2, "get") Matcher.get
    +tag method
    +tag-new(2)

p
    |  Retrieve the pattern stored for a key. Returns the rule as an
    |  #[code (on_match, patterns)] tuple containing the callback and available
    |  patterns.

+aside-code("Example").
    pattern = [{'ORTH': 'test'}]
    matcher.add('Rule', None, pattern)
    (on_match, patterns) = matcher.get('Rule')
    assert patterns = [pattern]

+table(["Name", "Type", "Description"])
    +row
        +cell #[code key]
        +cell unicode
        +cell The ID of the match rule.

    +footrow
        +cell returns
        +cell tuple
        +cell The rule, as an #[code (on_match, patterns)] tuple.