Find resources in the Bioregistry whose regular expression patterns contain a banana (i.e., a redundant prefix or prefix synonym) for curation.

find_missing_bananas.py

import bioregistry


def main():
    """Identify resources with uncurated bananas."""
    for resource in bioregistry.resources():
        pattern = resource.get_pattern()
        if not pattern:
            continue
        for peel in ":_-":
            if resource.prefix + peel in pattern.lower() or any(
                synonym.lower() + peel in pattern.lower()
                for synonym in resource.get_synonyms()
            ):
                print(resource.prefix, pattern)


if __name__ == '__main__':
    main()