Method add

paddleformers/transformers/legacy/tokenizer_utils.py:291–318

Passes over every char (utf-8 char) on word and recursively adds it to the internal `data` trie representation. The special key `""` is used to represent termination. This function is idempotent, adding twice the same word will leave the trie unchanged Example:

(self, word: str)

        self.data = {}

    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 `""` 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
        ref = self.data
        for char in word:
            ref[char] = char in ref and ref[char] or {}
            ref = ref[char]
        ref[""] = 1

    def split(self, text: str) -> List[str]:
        """