searchers.py 文件源码

def search(self, query, exclude=[], force=False, limit=20):

        # Fetches all document that have at least one of the terms
        pubs = self.index.search(query,
                                 search_fields=["title", "abstract"],
                                 return_fields=["id"],
                                 ignore=exclude)

        # Unpack and convert to a set for fast lookup
        pubs = set([pub_id for (pub_id,) in pubs])

        # index_ids, _scores = self.index.search(query, ["title", "abstract"], limit=limit, mode="ALL")
        # docs = set(self.index.get_documents(index_ids, "id"))

        g = nx.DiGraph()
        for u, v in self.edges:
            if (u in pubs) and (v in pubs):
                g.add_edge(u, v)

            #       print "PageRank with %d nodes." % g.number_of_nodes()
        r = nx.pagerank(g, alpha=0.7)

        if len(r) == 0:
            return []

        ids, _pg = zip(*sorted(r.items(), key=lambda (k, v): v, reverse=True))
        return ids[:limit]