Skip to content

edsnlp.pipelines.core.matcher.factory

DEFAULT_CONFIG = dict(terms=None, regex=None, attr='TEXT', ignore_excluded=False, term_matcher=GenericTermMatcher.exact, term_matcher_config={}) module-attribute

create_component(nlp, name, terms, attr, regex, ignore_excluded, term_matcher, term_matcher_config)

Source code in edsnlp/pipelines/core/matcher/factory.py 
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
@deprecated_factory(
    "matcher",
    "eds.matcher",
    default_config=DEFAULT_CONFIG,
    assigns=["doc.ents", "doc.spans"],
)
@Language.factory(
    "eds.matcher", default_config=DEFAULT_CONFIG, assigns=["doc.ents", "doc.spans"]
)
def create_component(
    nlp: Language,
    name: str,
    terms: Optional[Dict[str, Union[str, List[str]]]],
    attr: Union[str, Dict[str, str]],
    regex: Optional[Dict[str, Union[str, List[str]]]],
    ignore_excluded: bool,
    term_matcher: GenericTermMatcher,
    term_matcher_config: Dict[str, Any],
):
    assert not (terms is None and regex is None)

    if terms is None:
        terms = dict()
    if regex is None:
        regex = dict()

    return GenericMatcher(
        nlp,
        terms=terms,
        attr=attr,
        regex=regex,
        ignore_excluded=ignore_excluded,
        term_matcher=term_matcher,
        term_matcher_config=term_matcher_config,
    )