def listauthors(root): ''' parses xml with lxml objectify parser and calls filter_authors to extract authors ''' res = SimilaritySet(cutoff=CUTOFF) if root.algorithm is None: return res # the similarity_set callback to replace or remove special characters res.set_callback(replace) for alg in root.algorithm: # hibakezelesek, ha nem letezik a tag akkor ne is nezze if alg.find("variant") is not None and alg.variant.find("author") is not None: res.update(filter_authors(alg.variant.author)) return res