spaCy/website/docs/_api-matcher.jade

//- ----------------------------------
//- 💫 DOCS > API > MATCHER
//- ----------------------------------

+section("matcher")
    +h(2, "matcher", "https://github.com/" + SOCIAL.github + "/spaCy/blob/master/spacy/matcher.pyx")
        | #[+tag class] Matcher

    p A full example can be found #[a(href="https://github.com/" + SOCIAL.github + "blob/master/examples/matcher_example.py") here].

    +table(["Usage", "Description"])
            +row
                +cell #[code.lang-python nlp(doc)]
                +cell As part of annotation pipeline.

            +row
                +cell #[code.lang-python nlp.matcher(doc)]
                +cell Explicit invocation.

            +row
                +cell #[code.lang-python nlp.matcher.add(u'FooCorp', u'ORG', {}, [[{u'ORTH': u'Foo'}]])]
                +cell Add a pattern to match.

    +section("matcher-init")
        +h(3, "matcher-init") __init__(self, vocab, patterns)
            +table(["Name", "Type", "Description"])
                +row
                    +cell vocab
                    +cell #[code.lang-python spacy.vocab.Vocab]
                    +cell Reference to the shared vocabulary object.

                +row
                    +cell patterns
                    +cell #[code {entity_key: (etype, attrs, specs)}]
                    +cell.
                        Initial patterns to match. See #[code Matcher.add]

    +section("matcher-add")
        +h(3, "matcher-add") add(self, entity_key, etype, attrs, specs)
            +table(["Name", "Type", "Description"])
                +row
                    +cell entity_key
                    +cell unicode or int
                    +cell Your arbitrary ID string (or its integer encoding)
                +row
                    +cell etype
                    +cell unicode or int
                    +cell A pre-registered entity type, e.g. u'PERSON', u'ORG', etc.
                +row
                    +cell attrs
                    +cell #[code dict]
                    +cell Placeholder for future support of entity attributes.
                +row
                    +cell specs
                    +cell #[code [[{int: unicode}]]]
                    +cell A list of surface forms, where each surface form is defined as a list of token definitions, and each token definition is a dictionary mapping attribute IDs to attribute values.

    +section("matcher-saveload")
        +h(3, "matcher-saveload")
            | Save and Load

        +section("matcher-saveload-dump")
            +h(4, "matcher-saveload-dump") dump(loc)

            +table(["Name", "Type", "Description"])
                    +row
                        +cell loc
                        +cell #[+a(link_unicode) unicode]
                        +cell Path to save the gazetteer.json file.

        +section("matcher-saveload-load")
            +h(4, "matcher-saveload-load") load(loc)

            +table(["Name", "Type", "Description"])
                    +row
                        +cell loc
                        +cell #[+a(link_unicode) unicode]
                        +cell.
                            Path to load the gazetteer.json file from.