Created
January 23, 2023 22:01
-
-
Save afparsons/7e4891de96bc896e2ac30af26c2e5f5a to your computer and use it in GitHub Desktop.
spaCy 3.x RegularExpressionMatcher: Bibliographer
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
""" | |
A quick excerpt demonstrating usage of a custom `RegularExpressionMatcher` for spaCy 3. | |
This is from one of my personal projects (HaleyNLP/Irnerius). Module-level imports and other code blocks have been elided. | |
""" | |
class ComponentExtractionBibliographer( | |
AbstractComponentMatcher, | |
matcher=RegularExpressionMatcher, | |
): | |
""" | |
""" | |
def __init__(self, nlp: Language, matcher_rules): | |
super().__init__(nlp, matcher_rules) | |
Span.set_extension('citation', default=None, force=True) | |
@classmethod | |
def _make_span_groups(cls, doc: Doc) -> None: | |
""" | |
""" | |
citations: List[Span] = [] | |
# noinspection PyProtectedMember | |
for annotation in doc._.annotations.citations: # type: Annotation | |
citations.append(annotation.span) | |
# noinspection PyProtectedMember | |
annotation.span._.set( | |
name='citation', | |
value=annotation, | |
) | |
doc.spans['citations'] = citations | |
@Language.factory( | |
name='haleynlp_extraction_bibliographer', | |
default_config={'matcher_rules': {'@misc': 'haleynlp.en.component.config.bibliography'}}, | |
requires=['doc._.annotations', 'doc._.db'] | |
) | |
def produce_component_extraction_bibliographer( | |
nlp: Language, | |
name: str, | |
matcher_rules: Tuple, | |
) -> ComponentExtractionBibliographer: | |
""" | |
""" | |
return ComponentExtractionBibliographer(nlp=nlp, matcher_rules=matcher_rules) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment