loc.py 文件源码

def __process_loc_results__(self, results, label):
        """Method takes the json results from running the 

        Args:
            results(list): List of JSON rows from LOC ID call
            label(str): Original Label
        """
        title, loc_uri, term_weights = None, None, dict()
        for row in results:
            if isinstance(row, dict) or not row[0].startswith('atom:entry'):
                continue
            if row[2][0].startswith("atom:title"):
                title = row[2][-1]
            if row[3][0].startswith("atom:link"):
                loc_url = row[3][-1].get('href')
                if "subjects/" in loc_url:
                    bf_class = BF.Topic
                elif "organizations/" in loc_url:
                    bf_class = BF.Organization
                else:
                    bf_class = BF.Agent
                loc_uri = rdflib.URIRef(loc_url)
                term_weights[str(loc_uri)] = {
                        "weight": fuzz.ratio(label, title),
                        "class": bf_class,
                        "title": title}

        results = sorted(term_weights.items(), key=lambda x: x[1]['weight'])
        results.reverse()
        for row in results:
            loc_url = row[0]
            weight = row[1].get('weight')
            title = row[1].get('title')
            if weight >= self.cutoff:
                return rdflib.URIRef(loc_url), rdflib.Literal(title)
        return None, None