(file_path)
| 15 | |
| 16 | |
| 17 | def load_dpr_wiki(file_path): |
| 18 | title_set = set() |
| 19 | |
| 20 | with open(file_path, 'r', encoding='utf-8') as tsvfile: |
| 21 | reader = csv.reader(tsvfile, delimiter='\t') |
| 22 | headers = next(reader) # Get the header row |
| 23 | |
| 24 | for row in tqdm(reader, desc="Loading TSV", unit=" rows"): |
| 25 | # row: id text title |
| 26 | title_set.add(_normalize(row[2])) |
| 27 | |
| 28 | return title_set |
| 29 | |
| 30 | |
| 31 | def load_tsv_file(file_path): |
no test coverage detected