Struct NormalizerSpec

pub struct NormalizerSpec {
    pub name: Option<String>,
    pub precompiled_charsmap: Option<Vec<u8>>,
    pub add_dummy_prefix: Option<bool>,
    pub remove_extra_whitespaces: Option<bool>,
    pub escape_whitespaces: Option<bool>,
    pub normalization_rule_tsv: Option<String>,
}

NormalizerSpec encodes a various parameters for string normalizaiton

Fields

name: Option<String>

name of normalization rule.

precompiled_charsmap: Option<Vec<u8>>

Pre-compiled normalization rule created by Builder::GetPrecompiledCharsMap() or Builder::CompileCharsMap() method. Usually this field is set by Builder::GetNormalizerSpec() method.

add_dummy_prefix: Option<bool>

Adds dummy whitespace at the beginning of text in order to treat “world” in “world” and “hello world” in the same way.

remove_extra_whitespaces: Option<bool>

Removes leading, trailing, and duplicate internal whitespace.

escape_whitespaces: Option<bool>

Replaces whitespace with meta symbol. This field must be true to train sentence piece model.

normalization_rule_tsv: Option<String>

Custom normalization rule file in TSV format. https://github.com/google/sentencepiece/blob/master/doc/normalization.md This field is only used in SentencePieceTrainer::Train() method, which compiles the rule into the binary rule stored in precompiled_charsmap.

Implementations

impl NormalizerSpec

pub fn name(&self) -> &str

Returns the value of name, or the default value if name is unset.

pub fn precompiled_charsmap(&self) -> &[u8]

Returns the value of precompiled_charsmap, or the default value if precompiled_charsmap is unset.

pub fn add_dummy_prefix(&self) -> bool

Returns the value of add_dummy_prefix, or the default value if add_dummy_prefix is unset.

pub fn remove_extra_whitespaces(&self) -> bool

Returns the value of remove_extra_whitespaces, or the default value if remove_extra_whitespaces is unset.

pub fn escape_whitespaces(&self) -> bool

Returns the value of escape_whitespaces, or the default value if escape_whitespaces is unset.

pub fn normalization_rule_tsv(&self) -> &str

Returns the value of normalization_rule_tsv, or the default value if normalization_rule_tsv is unset.

Trait Implementations

impl Clone for NormalizerSpec

fn clone(&self) -> NormalizerSpec

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for NormalizerSpec

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for NormalizerSpec

fn default() -> Self

Returns the “default value” for a type.

impl Message for NormalizerSpec

fn encoded_len(&self) -> usize

Returns the encoded length of the message without a length delimiter.

fn clear(&mut self)

Clears the message, resetting all fields to their default.

fn encode(&self, buf: &mut impl BufMut) -> Result<(), EncodeError>

where Self: Sized,

Encodes the message to a buffer.

fn encode_to_vec(&self) -> Vec<u8>

where Self: Sized,

Encodes the message to a newly allocated buffer.

fn encode_length_delimited( &self, buf: &mut impl BufMut, ) -> Result<(), EncodeError>

where Self: Sized,

Encodes the message with a length-delimiter to a buffer.

fn encode_length_delimited_to_vec(&self) -> Vec<u8>

where Self: Sized,

Encodes the message with a length-delimiter to a newly allocated buffer.

fn decode(buf: impl Buf) -> Result<Self, DecodeError>

where Self: Default,

Decodes an instance of the message from a buffer.

fn decode_length_delimited(buf: impl Buf) -> Result<Self, DecodeError>

where Self: Default,

Decodes a length-delimited instance of the message from the buffer.

fn merge(&mut self, buf: impl Buf) -> Result<(), DecodeError>

where Self: Sized,

Decodes an instance of the message from a buffer, and merges it into self.

fn merge_length_delimited(&mut self, buf: impl Buf) -> Result<(), DecodeError>

where Self: Sized,

Decodes a length-delimited instance of the message from buffer, and merges it into self.

impl PartialEq for NormalizerSpec

fn eq(&self, other: &NormalizerSpec) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for NormalizerSpec