找到页码最小的_page_x_merged.json 文件
(json_files: list)
| 43 | |
| 44 | |
| 45 | def find_min_page_file(json_files: list) -> str: |
| 46 | """找到页码最小的_page_x_merged.json 文件""" |
| 47 | min_page = float('inf') |
| 48 | min_file = None |
| 49 | |
| 50 | for file_path in json_files: |
| 51 | filename = file_path.name |
| 52 | # 匹配_page_x_merged.json 模式 |
| 53 | match = re.search(r'_page_(\d+)_merged\.json', filename) |
| 54 | if match: |
| 55 | # 修复：直接使用 match.group(1)，去掉多余的 .group |
| 56 | page_num = int(match.group(1)) |
| 57 | if page_num < min_page: |
| 58 | min_page = page_num |
| 59 | min_file = filename |
| 60 | |
| 61 | return min_file |
| 62 | |
| 63 | |
| 64 | def normalize_levels(data: list) -> list: |