sentiment.py 文件源码

def tag_by_phrase(self, tag_query, source):
        print('query=%s source=%s' % (json.dumps(tag_query), source))
        resp = self.es.search(index='fcc-comments', body=tag_query, size=0)
        total = resp['hits']['total']
        print('tagging %s / %s matches' % (self.limit, total))
        docs = []
        for doc in scan(self.es, index='fcc-comments', query=tag_query, size=1000):
            docs.append(lib.bulk_update_doc(doc['_id'], {'source': source}))
            if not len(docs) % 1000:
                print('\tfetched %s\n%s\t%s' % (len(docs), doc['_id'], doc['_source']['text_data'][:400]))
            if len(docs) >= self.limit:
                break

        print('indexing %s' % (len(docs)))
        tagged = lib.bulk_update(self.es, docs)
        print('tagged %s / %s matches' % (tagged, total))
        return tagged