根据文件名称获取分段模型 :param limit: 每段大小 :param with_filter: 是否过滤特殊字符 :param filename: 文件名称 :return: 分段模型
(filename: str, with_filter: bool = False, limit: int = 100000)
| 476 | |
| 477 | |
| 478 | def get_split_model(filename: str, with_filter: bool = False, limit: int = 100000): |
| 479 | """ |
| 480 | 根据文件名称获取分段模型 |
| 481 | :param limit: 每段大小 |
| 482 | :param with_filter: 是否过滤特殊字符 |
| 483 | :param filename: 文件名称 |
| 484 | :return: 分段模型 |
| 485 | """ |
| 486 | if filename.endswith(".md"): |
| 487 | pattern_list = default_split_pattern.get('md') |
| 488 | return SplitModel(pattern_list, with_filter=with_filter, limit=limit) |
| 489 | |
| 490 | pattern_list = default_split_pattern.get('md') |
| 491 | return SplitModel(pattern_list, with_filter=with_filter, limit=limit) |
| 492 | |
| 493 | |
| 494 | def to_title_tree_string(result_tree: List): |
no test coverage detected