Struct rust_tokenizers::tokenizer::BaseTokenizer

pub struct BaseTokenizer<T: Vocab> { /* fields omitted */ }

Base tokenizer

Base tokenizer performing:

• whitespace tokenization
• splitting on special characters
• splitting on punctuation
• splitting on CJK characters
• (optional) lower casing
• (optional) accent stripping

This tokenizer is used as a pre-tokenizer step in the BERT and GPT tokenizers.

Implementations

impl<T: Vocab + Sync + Send> BaseTokenizer<T>

pub fn from_file(
    path: &str,
    lower_case: bool,
    strip_accents: bool
) -> Result<BaseTokenizer<T>, TokenizerError>

Create a new instance of a BaseTokenizer Expects a vocabulary flat-file as an input.

Parameters

• path (&str): path to the vocabulary file (only used for special character splitting)
• lower_case (bool): flag indicating if the text should be lower-cased as part of the tokenization
• strip_accents (bool): flag indicating if accents should be stripped from the text

Example

use rust_tokenizers::tokenizer::{BaseTokenizer, Tokenizer};
use rust_tokenizers::vocab::BaseVocab;
let strip_accents = false;
let lower_case = false;
let tokenizer: BaseTokenizer<BaseVocab> =
    BaseTokenizer::from_file("path/to/vocab/file", lower_case, strip_accents).unwrap();

pub fn from_existing_vocab(
    vocab: T,
    lower_case: bool,
    strip_accents: bool
) -> BaseTokenizer<T>

Create a new instance of a BaseTokenizer from an existing vocabulary

Parameters

• vocab (Vocab): Thread-safe reference to a vocabulary
• lower_case (bool): flag indicating if the text should be lower-cased as part of the tokenization
• strip_accents (bool): flag indicating if accents should be stripped from the text

Example

use rust_tokenizers::tokenizer::{BaseTokenizer, Tokenizer};
use rust_tokenizers::vocab::{BaseVocab, Vocab};
let strip_accents = false;
let lower_case = false;
let base_vocab = BaseVocab::from_file("path/to/vocab/file").unwrap();

let tokenizer = BaseTokenizer::from_existing_vocab(base_vocab, lower_case, strip_accents);

Trait Implementations

impl<T: Vocab + Sync + Send> MultiThreadedTokenizer<T> for BaseTokenizer<T>

fn vocab(&self) -> &T

returns a reference to the tokenizer vocabulary

fn tokenize_list_with_offsets<S, ST>(
    &self,
    text_list: S
) -> Vec<TokensWithOffsets> where
    S: AsRef<[ST]>,
    ST: AsRef<str> + Sync, 

Tokenize a list of strings (with multithreading), where each corresponds to for example a sentence, returns a vector of TokensWithOffsets containing the tokens and their offset information. This calls tokenize_with_offsets on the list provided.

fn tokenize_list<S, ST>(&self, text_list: S) -> Vec<Vec<String>> where
    S: AsRef<[ST]>,
    ST: AsRef<str> + Sync, 

Multithreaded tokenization of a list of strings, returning tokens with offset information

fn encode_list<S, ST>(
    &self,
    text_list: S,
    max_len: usize,
    truncation_strategy: &TruncationStrategy,
    stride: usize
) -> Vec<TokenizedInput> where
    S: AsRef<[ST]>,
    ST: AsRef<str> + Sync, 

Multithreaded encoding of a sequence of string-like texts (tokenization followed by encoding). Not that in contrast with encode optional second text, each text provided is encoded independently.

fn encode_pair_list<S, ST>(
    &self,
    text_list: S,
    max_len: usize,
    truncation_strategy: &TruncationStrategy,
    stride: usize
) -> Vec<TokenizedInput> where
    S: AsRef<[(ST, ST)]>,
    ST: AsRef<str> + Sync, 

Multithreaded ncoding of a sequence of string-like text pairs (tokenization followed by encoding). This combines with encode with the list processing of encode_list.

fn decode_list(
    &self,
    token_ids_list: Vec<Vec<i64>>,
    skip_special_tokens: bool,
    clean_up_tokenization_spaces: bool
) -> Vec<String>

Multithreaded conversion a list of sequence of ids (integer) into a string, using the tokenizer and vocabulary with options to remove special tokens and clean up tokenization spaces. This calls decode for each provided sequence of ids

impl<T: Vocab + Sync + Send> Tokenizer<T> for BaseTokenizer<T>

fn vocab(&self) -> &T

returns a reference to the tokenizer vocabulary

fn tokenize_to_tokens(&self, initial_token: TokenRef<'_>) -> Vec<Token>

Tokenize a TokenRef, returning a sequence of tokens

fn tokenize<S: AsRef<str>>(&self, text: S) -> Vec<String>

Tokenize a string, returns a vector of tokens as strings. Use tokenize_with_offsets or tokenize_to_tokens to return offset information.

fn tokenize_with_offsets<S: AsRef<str>>(&self, text: S) -> TokensWithOffsets

Tokenize a string, returning tokens with offset information

fn tokenize_list<S, ST>(&self, text_list: S) -> Vec<Vec<String>> where
    S: AsRef<[ST]>,
    ST: AsRef<str>, 

Tokenize a list of strings, returning tokens with offset information

fn tokenize_list_with_offsets<S, ST>(
    &self,
    text_list: S
) -> Vec<TokensWithOffsets> where
    S: AsRef<[ST]>,
    ST: AsRef<str>, 

Tokenize a list of strings, where each corresponds to for example a sentence, returns a vector of TokensWithOffsets containing the tokens and their offset information. This calls tokenize_with_offsets on the list provided.

fn convert_tokens_to_ids<S, ST>(&self, tokens: S) -> Vec<i64> where
    S: AsRef<[ST]>,
    ST: AsRef<str>, 

Convert a slice of string-like to a vector ot token indices

fn encode<S: AsRef<str>>(
    &self,
    text_1: S,
    text_2: Option<S>,
    max_len: usize,
    truncation_strategy: &TruncationStrategy,
    stride: usize
) -> TokenizedInput

Encode a string-like (tokenization followed by encoding)

fn encode_list<S, ST>(
    &self,
    text_list: S,
    max_len: usize,
    truncation_strategy: &TruncationStrategy,
    stride: usize
) -> Vec<TokenizedInput> where
    S: AsRef<[ST]>,
    ST: AsRef<str>, 

Encode a sequence of string-like texts (tokenization followed by encoding). Not that in contrast with encode optional second text, each text provided is encoded independently.

fn encode_pair_list<S, ST>(
    &self,
    text_list: S,
    max_len: usize,
    truncation_strategy: &TruncationStrategy,
    stride: usize
) -> Vec<TokenizedInput> where
    S: AsRef<[(ST, ST)]>,
    ST: AsRef<str>, 

Encode a sequence of string-like text pairs (tokenization followed by encoding). This combines with encode with the list processing of encode_list.

fn decode_to_vec(
    &self,
    token_ids: Vec<i64>,
    skip_special_tokens: bool
) -> Vec<String>

Decode a sequence of token indices to a sequence of Strings, optionally skipping special indices

fn decode(
    &self,
    token_ids: Vec<i64>,
    skip_special_tokens: bool,
    clean_up_tokenization_spaces: bool
) -> String

Converts a sequence of ids (integer) into a string, using the tokenizer and vocabulary with options to remove special tokens and clean up tokenization spaces.

fn convert_tokens_to_string(&self, tokens: Vec<String>) -> String

Converts a sequence of strings into a single string. This will clean-up artifacts from tokenization (for example sub ##word) and generate a single output string

fn clean_up_tokenization(&self, input_string: String) -> String

Cleans-up tokenization artifacts (for example whitespace before punctuation)

fn decode_list(
    &self,
    token_ids_list: Vec<Vec<i64>>,
    skip_special_tokens: bool,
    clean_up_tokenization_spaces: bool
) -> Vec<String>

Converts a list of sequence of ids (integer) into a string, using the tokenizer and vocabulary with options to remove special tokens and clean up tokenization spaces. This calls decode for each provided sequence of ids

fn build_input_with_special_tokens(
    &self,
    tokens_ids_with_offsets_1: TokenIdsWithOffsets,
    tokens_ids_with_offsets_2: Option<TokenIdsWithOffsets>
) -> TokenIdsWithSpecialTokens

Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens.