torchtext/datasets/iwslt2016.py [241:260]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    extracted_dataset_tar = extract_archive(iwslt_tar)
    extracted_files.extend(extracted_dataset_tar)

    # Clean the xml and tag file in the archives
    file_archives = []
    for fname in extracted_files:
        if 'xml' in fname:
            _clean_xml_file(fname)
            file_archives.append(os.path.splitext(fname)[0])
        elif "tags" in fname:
            _clean_tags_file(fname)
            file_archives.append(fname.replace('.tags', ''))
        else:
            file_archives.append(fname)

    data_filenames = {
        "train": _construct_filepaths(file_archives, src_train, tgt_train),
        "valid": _construct_filepaths(file_archives, src_eval, tgt_eval),
        "test": _construct_filepaths(file_archives, src_test, tgt_test)
    }
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



torchtext/datasets/iwslt2017.py [202:221]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    extracted_dataset_tar = extract_archive(iwslt_tar)
    extracted_files.extend(extracted_dataset_tar)

    # Clean the xml and tag file in the archives
    file_archives = []
    for fname in extracted_files:
        if 'xml' in fname:
            _clean_xml_file(fname)
            file_archives.append(os.path.splitext(fname)[0])
        elif "tags" in fname:
            _clean_tags_file(fname)
            file_archives.append(fname.replace('.tags', ''))
        else:
            file_archives.append(fname)

    data_filenames = {
        "train": _construct_filepaths(file_archives, src_train, tgt_train),
        "valid": _construct_filepaths(file_archives, src_eval, tgt_eval),
        "test": _construct_filepaths(file_archives, src_test, tgt_test)
    }
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -