Class Trie

src/transformers/tokenization_python.py:45–273

Trie in Python. Creates a Trie out of a list of words. The trie is used to split on `added_tokens` in one pass Loose reference https://en.wikipedia.org/wiki/Trie

class Trie:
    """
    Trie in Python. Creates a Trie out of a list of words. The trie is used to split on `added_tokens` in one pass
    Loose reference https://en.wikipedia.org/wiki/Trie
    """

    def __init__(self, *args):
        self.data = {}
        self._tokens = set()
        self._termination_char = ""
        self.update(*args)

    def update(self, *args):
        """
        Updates the Trie with new tokens provided as arguments.

        Args:
            *args: Variable number of words to be added to the Trie.
        """
        for token in tuple(*args):
            self.add(token)

    def add(self, word: str):
        """
        Passes over every char (utf-8 char) on word and recursively adds it to the internal `data` trie representation.
        The special key `""` in `self._termination_char` is used to represent termination.

        This function is idempotent, adding twice the same word will leave the trie unchanged

        Example:

        ```python
        >>> trie = Trie()
        >>> trie.add("Hello 友達")
        >>> trie.data
        {"H": {"e": {"l": {"l": {"o": {" ": {"友": {"達": {"": 1}}}}}}}}}

        >>> trie.add("Hello")
        >>> trie.data
        {"H": {"e": {"l": {"l": {"o": {"": 1, " ": {"友": {"達": {"": 1}}}}}}}}}
        ```
        """
        if not word:
            # Prevent empty string
            return

        self._tokens.add(word)
        ref = self.data
        for char in word:
            ref[char] = ref.setdefault(char, {})
            ref = ref[char]
        ref[self._termination_char] = 1

    def split(self, text: str) -> list[str]:
        """
        Will look for the words added to the trie within `text`. Output is the original string split along the
        boundaries of the words found.