Struct icu_capi::segmenter_line::ffi::LineSegmenter

pub struct LineSegmenter(/* private fields */);

An ICU4X line-break segmenter, capable of finding breakpoints in strings.

Implementations

impl LineSegmenter

pub fn create_auto() -> Box<LineSegmenter>

Construct a LineSegmenter with default options using compiled data. It automatically loads the best available payload data for Burmese, Khmer, Lao, and Thai.

pub fn create_auto_with_provider( provider: &DataProvider, ) -> Result<Box<LineSegmenter>, DataError>

Construct a LineSegmenter with default options using a particular data source. It automatically loads the best available payload data for Burmese, Khmer, Lao, and Thai.

pub fn create_lstm() -> Box<LineSegmenter>

Construct a LineSegmenter with default options and LSTM payload data for Burmese, Khmer, Lao, and Thai, using compiled data.

pub fn create_lstm_with_provider( provider: &DataProvider, ) -> Result<Box<LineSegmenter>, DataError>

Construct a LineSegmenter with default options and LSTM payload data for Burmese, Khmer, Lao, and Thai, using a particular data source.

pub fn create_dictionary() -> Box<LineSegmenter>

Construct a LineSegmenter with default options and dictionary payload data for Burmese, Khmer, Lao, and Thai, using compiled data

pub fn create_dictionary_with_provider( provider: &DataProvider, ) -> Result<Box<LineSegmenter>, DataError>

Construct a LineSegmenter with default options and dictionary payload data for Burmese, Khmer, Lao, and Thai, using a particular data source.

pub fn create_auto_with_options_v2( content_locale: &Locale, options: LineBreakOptionsV2, ) -> Box<LineSegmenter>

Construct a LineSegmenter with custom options using compiled data. It automatically loads the best available payload data for Burmese, Khmer, Lao, and Thai.

pub fn create_auto_with_options_v2_and_provider( provider: &DataProvider, content_locale: &Locale, options: LineBreakOptionsV2, ) -> Result<Box<LineSegmenter>, DataError>

Construct a LineSegmenter with custom options. It automatically loads the best available payload data for Burmese, Khmer, Lao, and Thai, using a particular data source.

pub fn create_lstm_with_options_v2( content_locale: &Locale, options: LineBreakOptionsV2, ) -> Box<LineSegmenter>

Construct a LineSegmenter with custom options and LSTM payload data for Burmese, Khmer, Lao, and Thai, using compiled data.

pub fn create_lstm_with_options_v2_and_provider( provider: &DataProvider, content_locale: &Locale, options: LineBreakOptionsV2, ) -> Result<Box<LineSegmenter>, DataError>

Construct a LineSegmenter with custom options and LSTM payload data for Burmese, Khmer, Lao, and Thai, using a particular data source.

pub fn create_dictionary_with_options_v2( content_locale: &Locale, options: LineBreakOptionsV2, ) -> Box<LineSegmenter>

Construct a LineSegmenter with custom options and dictionary payload data for Burmese, Khmer, Lao, and Thai, using compiled data.

pub fn create_dictionary_with_options_v2_and_provider( provider: &DataProvider, content_locale: &Locale, options: LineBreakOptionsV2, ) -> Result<Box<LineSegmenter>, DataError>

Construct a LineSegmenter with custom options and dictionary payload data for Burmese, Khmer, Lao, and Thai, using a particular data source.

pub fn segment_utf8<'a>( &'a self, input: &'a DiplomatStr, ) -> Box<LineBreakIteratorUtf8<'a>>

Segments a string.

Ill-formed input is treated as if errors had been replaced with REPLACEMENT CHARACTERs according to the WHATWG Encoding Standard.

pub fn segment_utf16<'a>( &'a self, input: &'a DiplomatStr16, ) -> Box<LineBreakIteratorUtf16<'a>>

Segments a string.

Ill-formed input is treated as if errors had been replaced with REPLACEMENT CHARACTERs according to the WHATWG Encoding Standard.

pub fn segment_latin1<'a>( &'a self, input: &'a [u8], ) -> Box<LineBreakIteratorLatin1<'a>>

Segments a Latin-1 string.