Struct LexiconSet 

pub struct LexiconSet<'a> { /* private fields */ }

Set of Lexicons

Handles multiple lexicons as one lexicon The first lexicon in the list must be from system dictionary

Implementations

impl<'a> LexiconSet<'a>

pub fn from_system_binary( system_lexicon: BinaryLexicon<'a>, num_system_pos: usize, ) -> LexiconSet<'a>

Creates a LexiconSet from a system lexicon

pub fn new(system_lexicon: Lexicon<'a>, num_system_pos: usize) -> LexiconSet<'a>

Creates a LexiconSet given a system lexicon

pub fn append( &mut self, lexicon: Lexicon<'a>, pos_offset: usize, ) -> Result<(), LexiconSetError>

Add a lexicon to the lexicon list

pos_offset: number of pos in the grammar

pub fn is_full(&self) -> bool

Returns if dictionary capacity is full

impl LexiconSet<'_>

pub fn lookup<'b>( &'b self, input: &'b [u8], offset: usize, ) -> impl Iterator<Item = LexiconEntry> + 'b

Returns iterator which yields all words in the dictionary, starting from the offset bytes

Searches dictionaries in the reverse order: user dictionaries first and then system dictionary

pub fn lookup_batch<F: FnMut(usize, LexiconEntry)>( &self, input: &[u8], starts: &[usize], emit: F, )

Pipelined + prefetched batch form of LexiconSet::lookup.

Calls emit(bucket, entry) for every match; bucket indexes starts. Within a bucket the order matches repeated LexiconSet::lookup calls (user dictionaries first, then system, each in trie-walk order), so grouping by bucket reproduces the scalar result.

pub fn get_word_info(&self, id: WordId) -> SudachiResult<WordInfo>

Returns WordInfo for given WordId

pub fn get_word_info_subset( &self, id: WordId, subset: InfoSubset, ) -> SudachiResult<WordInfo>

Returns WordInfo for given WordId. Only fills a requested subset of fields. Rest will be of default values (0 or empty).

pub fn get_word_param(&self, id: WordId) -> (i16, i16, i16)

Returns word_param for given word_id

pub fn get_word_param_checked( &self, id: WordId, ) -> SudachiResult<(i16, i16, i16)>

Returns word_param for given word_id.

pub fn get_string( &self, word_id: WordId, strptr: StringPointer, ) -> SudachiResult<String>

pub fn size(&self) -> u32

pub fn word_ids(&self) -> impl Iterator<Item = SudachiResult<WordId>> + '_

pub fn system_word_ids_in_order(&self) -> Vec<WordId>

Trait Implementations

impl LexiconAccess for LexiconSet<'_>

fn lexicon(&self) -> &LexiconSet<'_>