Initializes the TextContext processor. Sets up the characters used to determine valid context boundaries. Args: split_tokens: An optional set of strings. Each string is treated as a potential end-of-context marker. If None, a default s
(self, split_tokens: Optional[Set[str]] = None)
| 13 | of alphanumeric characters. |
| 14 | """ |
| 15 | def __init__(self, split_tokens: Optional[Set[str]] = None) -> None: |
| 16 | """ |
| 17 | Initializes the TextContext processor. |
| 18 | |
| 19 | Sets up the characters used to determine valid context boundaries. |
| 20 | |
| 21 | Args: |
| 22 | split_tokens: An optional set of strings. Each string is treated as a |
| 23 | potential end-of-context marker. If None, a default set |
| 24 | of punctuation and whitespace characters is used. |
| 25 | """ |
| 26 | if split_tokens is None: |
| 27 | # Using a more explicit variable name internally for clarity |
| 28 | default_splits: Set[str] = {".", "!", "?", ",", ";", ":", "\n", "-", "。", "、"} |
| 29 | self.split_tokens: Set[str] = default_splits |
| 30 | else: |
| 31 | self.split_tokens: Set[str] = set(split_tokens) |
| 32 | |
| 33 | def get_context(self, txt: str, min_len: int = 6, max_len: int = 120, min_alnum_count: int = 10) -> Tuple[Optional[str], Optional[str]]: |
| 34 | """ |
nothing calls this directly
no outgoing calls
no test coverage detected