# Pre-tokenizers

## BertPreTokenizer[[tokenizers.pre_tokenizers.BertPreTokenizer]]

#### tokenizers.pre_tokenizers.BertPreTokenizer[[tokenizers.pre_tokenizers.BertPreTokenizer]]

BertPreTokenizer

This pre-tokenizer splits tokens on spaces, and also on punctuation.
Each occurrence of a punctuation character will be treated separately.

## ByteLevel[[tokenizers.pre_tokenizers.ByteLevel]]

#### tokenizers.pre_tokenizers.ByteLevel[[tokenizers.pre_tokenizers.ByteLevel]]

ByteLevel PreTokenizer

This pre-tokenizer takes care of replacing all bytes of the given string
with a corresponding representation, as well as splitting into words.

alphabettokenizers.pre_tokenizers.ByteLevel.alphabet[]`List[str]`A list of characters that compose the alphabet
Returns the alphabet used by this PreTokenizer.

Since the ByteLevel works as its name suggests, at the byte level, it
encodes each byte value to a unique visible character. This means that there is a
total of 256 different characters composing this alphabet.

**Parameters:**

add_prefix_space (`bool`, *optional*, defaults to `True`) : Whether to add a space to the first word if there isn't already one. This lets us treat *hello* exactly like *say hello*.

use_regex (`bool`, *optional*, defaults to `True`) : Set this to `False` to prevent this *pre_tokenizer* from using the GPT2 specific regexp for spliting on whitespace.

**Returns:**

``List[str]``

A list of characters that compose the alphabet

## CharDelimiterSplit[[tokenizers.pre_tokenizers.CharDelimiterSplit]]

#### tokenizers.pre_tokenizers.CharDelimiterSplit[[tokenizers.pre_tokenizers.CharDelimiterSplit]]

This pre-tokenizer simply splits on the provided char. Works like `.split(delimiter)`

**Parameters:**

delimiter : str: The delimiter char that will be used to split input

## Digits[[tokenizers.pre_tokenizers.Digits]]

#### tokenizers.pre_tokenizers.Digits[[tokenizers.pre_tokenizers.Digits]]

This pre-tokenizer simply splits using the digits in separate tokens

If set to True, digits will each be separated as follows:

```python
"Call 123 please" -> "Call ", "1", "2", "3", " please"
```

If set to False, digits will grouped as follows:

```python
"Call 123 please" -> "Call ", "123", " please"
```

**Parameters:**

individual_digits (`bool`, *optional*, defaults to `False`) --

## Metaspace[[tokenizers.pre_tokenizers.Metaspace]]

#### tokenizers.pre_tokenizers.Metaspace[[tokenizers.pre_tokenizers.Metaspace]]

Metaspace pre-tokenizer

This pre-tokenizer replaces any whitespace by the provided replacement character.
It then tries to split on these spaces.

**Parameters:**

replacement (`str`, *optional*, defaults to `▁`) : The replacement character. Must be exactly one character. By default we use the *▁* (U+2581) meta symbol (Same as in SentencePiece). 

prepend_scheme (`str`, *optional*, defaults to `"always"`) : Whether to add a space to the first word if there isn't already one. This lets us treat *hello* exactly like *say hello*. Choices: "always", "never", "first". First means the space is only added on the first token (relevant when special tokens are used or other pre_tokenizer are used).

## PreTokenizer[[tokenizers.pre_tokenizers.PreTokenizer]]

#### tokenizers.pre_tokenizers.PreTokenizer[[tokenizers.pre_tokenizers.PreTokenizer]]

Base class for all pre-tokenizers

This class is not supposed to be instantiated directly. Instead, any implementation of a
PreTokenizer will return an instance of this class when instantiated.

pre_tokenizetokenizers.pre_tokenizers.PreTokenizer.pre_tokenize[{"name": "pretok", "val": ""}]- **pretok** (`~tokenizers.PreTokenizedString) --
  The pre-tokenized string on which to apply this
  :class:`~tokenizers.pre_tokenizers.PreTokenizer`0
Pre-tokenize a `~tokenizers.PyPreTokenizedString` in-place

This method allows to modify a `PreTokenizedString` to
keep track of the pre-tokenization, and leverage the capabilities of the
`PreTokenizedString`. If you just want to see the result of
the pre-tokenization of a raw string, you can use
`pre_tokenize_str()`

**Parameters:**

pretok (`~tokenizers.PreTokenizedString) : The pre-tokenized string on which to apply this :class:`~tokenizers.pre_tokenizers.PreTokenizer`
#### pre_tokenize_str[[tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize_str]]

Pre tokenize the given string

This method provides a way to visualize the effect of a
[PreTokenizer](/docs/tokenizers/v0.22.2/en/api/pre-tokenizers#tokenizers.pre_tokenizers.PreTokenizer) but it does not keep track of the
alignment, nor does it provide all the capabilities of the
`PreTokenizedString`. If you need some of these, you can use
`pre_tokenize()`

**Parameters:**

sequence (`str`) : A string to pre-tokeize

**Returns:**

``List[Tuple[str, Offsets]]``

A list of tuple with the pre-tokenized parts and their offsets

## Punctuation[[tokenizers.pre_tokenizers.Punctuation]]

#### tokenizers.pre_tokenizers.Punctuation[[tokenizers.pre_tokenizers.Punctuation]]

This pre-tokenizer simply splits on punctuation as individual characters.

**Parameters:**

behavior (`SplitDelimiterBehavior`) : The behavior to use when splitting. Choices: "removed", "isolated" (default), "merged_with_previous", "merged_with_next", "contiguous"

## Sequence[[tokenizers.pre_tokenizers.Sequence]]

#### tokenizers.pre_tokenizers.Sequence[[tokenizers.pre_tokenizers.Sequence]]

This pre-tokenizer composes other pre_tokenizers and applies them in sequence

## Split[[tokenizers.pre_tokenizers.Split]]

#### tokenizers.pre_tokenizers.Split[[tokenizers.pre_tokenizers.Split]]

Split PreTokenizer

This versatile pre-tokenizer splits using the provided pattern and
according to the provided behavior. The pattern can be inverted by
making use of the invert flag.

**Parameters:**

pattern (`str` or `Regex`) : A pattern used to split the string. Usually a string or a regex built with *tokenizers.Regex*. If you want to use a regex pattern, it has to be wrapped around a *tokenizers.Regex*, otherwise we consider is as a string pattern. For example *pattern="|"* means you want to split on *|* (imagine a csv file for example), while *pattern=tokenizers.Regex("1|2")* means you split on either '1' or '2'.

behavior (`SplitDelimiterBehavior`) : The behavior to use when splitting. Choices: "removed", "isolated", "merged_with_previous", "merged_with_next", "contiguous" 

invert (`bool`, *optional*, defaults to `False`) : Whether to invert the pattern.

## UnicodeScripts[[tokenizers.pre_tokenizers.UnicodeScripts]]

#### tokenizers.pre_tokenizers.UnicodeScripts[[tokenizers.pre_tokenizers.UnicodeScripts]]

This pre-tokenizer splits on characters that belong to different language family
It roughly follows https://github.com/google/sentencepiece/blob/master/data/Scripts.txt
Actually Hiragana and Katakana are fused with Han, and 0x30FC is Han too.
This mimicks SentencePiece Unigram implementation.

## Whitespace[[tokenizers.pre_tokenizers.Whitespace]]

#### tokenizers.pre_tokenizers.Whitespace[[tokenizers.pre_tokenizers.Whitespace]]

This pre-tokenizer splits on word boundaries according to the `\w+|[^\w\s]+`
regex pattern. It splits on word characters or characters that aren't words or
whitespaces (punctuation such as hyphens, apostrophes, commas, etc.).

Example:

Use the `Whitespace` function as shown below::

```python
from tokenizers.pre_tokenizers import Whitespace

pre_tokenizer = Whitespace()
text = "Hello, world! Let's try the Whitespace pre-tokenizer."
pre_tokenizer.pre_tokenize_str(text)
[('Hello', (0, 5)),
 (',', (5, 6)),
 ('world', (7, 12)),
 ('!', (12, 13)),
 ('Let', (14, 17)),
 ("'", (17, 18)),
 ('s', (18, 19)),
 ('try', (20, 23)),
 ('the', (24, 27)),
 ('Whitespace', (28, 38)),
 ('pre', (39, 42)),
 ('-', (42, 43)),
 ('tokenizer', (43, 52)),
 ('.', (52, 53))]
```

## WhitespaceSplit[[tokenizers.pre_tokenizers.WhitespaceSplit]]

#### tokenizers.pre_tokenizers.WhitespaceSplit[[tokenizers.pre_tokenizers.WhitespaceSplit]]

This pre-tokenizer simply splits on the whitespace. Works like `.split()`

The Rust API Reference is available directly on the [Docs.rs](https://docs.rs/tokenizers/latest/tokenizers/) website.

The node API has not been documented yet.