upload_documents_to_discovery_collection.py 文件源码

def document_corpus_as_iterable(corpus):
    stats = defaultdict(int)
    with smart_file_open(corpus) as infile:
        LOGGER.info("Loading documents from solr xml file: %s" % corpus)
        # reader = UnicodeRecoder(infile, encoding='utf-8')
        for event, element in ET.iterparse(infile):
            if event == 'end' and element.tag == 'doc':
                stats['num_xml_entries'] += 1
                yield _parse_doc_elements(element)