lindera-wasm/lindera_wasm.d.ts

A morphological analysis library for WebAssembly.

/* tslint:disable */
/* eslint-disable */

/**
 * Compression algorithm for dictionary data.
 */
export enum CompressionAlgorithm {
    Deflate = 0,
    Zlib = 1,
    Gzip = 2,
    Raw = 3,
}

/**
 * A morphological analysis dictionary.
 */
export class Dictionary {
    private constructor();
    free(): void;
    [Symbol.dispose](): void;
}

/**
 * Field definition in dictionary schema.
 */
export class FieldDefinition {
    private constructor();
    free(): void;
    [Symbol.dispose](): void;
    get description(): string | undefined;
    set description(value: string | null | undefined);
    field_type: FieldType;
    index: number;
    name: string;
}

/**
 * Field type in dictionary schema.
 */
export enum FieldType {
    /**
     * Surface form (word text)
     */
    Surface = 0,
    /**
     * Left context ID for morphological analysis
     */
    LeftContextId = 1,
    /**
     * Right context ID for morphological analysis
     */
    RightContextId = 2,
    /**
     * Word cost (used in path selection)
     */
    Cost = 3,
    /**
     * Custom field (morphological features)
     */
    Custom = 4,
}

/**
 * Error type for Lindera operations.
 */
export class LinderaError {
    private constructor();
    free(): void;
    [Symbol.dispose](): void;
    message: string;
}

/**
 * Dictionary metadata configuration.
 */
export class Metadata {
    private constructor();
    free(): void;
    [Symbol.dispose](): void;
}

/**
 * Tokenization mode.
 *
 * Determines how text is segmented into tokens.
 */
export enum Mode {
    /**
     * Standard tokenization based on dictionary cost
     */
    Normal = 0,
    /**
     * Decompose compound words using penalty-based segmentation
     */
    Decompose = 1,
}

/**
 * Penalty configuration for decompose mode.
 *
 * Controls how aggressively compound words are decomposed based on
 * character type and length thresholds.
 */
export class Penalty {
    private constructor();
    free(): void;
    [Symbol.dispose](): void;
    kanji_penalty_length_penalty: number;
    kanji_penalty_length_threshold: number;
    other_penalty_length_penalty: number;
    other_penalty_length_threshold: number;
}

/**
 * Dictionary schema definition.
 */
export class Schema {
    private constructor();
    free(): void;
    [Symbol.dispose](): void;
}

/**
 * Core segmenter for morphological analysis.
 */
export class Segmenter {
    private constructor();
    free(): void;
    [Symbol.dispose](): void;
}

/**
 * Token object wrapping the Rust Token data.
 *
 * This class provides robust access to token field and details.
 */
export class Token {
    private constructor();
    free(): void;
    [Symbol.dispose](): void;
    /**
     * End byte position in the original text.
     */
    byte_end: number;
    /**
     * Start byte position in the original text.
     */
    byte_start: number;
    /**
     * Morphological details of the token.
     */
    details: string[];
    /**
     * Position index of the token.
     */
    position: number;
    /**
     * Surface form of the token.
     */
    surface: string;
    /**
     * Word ID in the dictionary.
     */
    word_id: number;
}

/**
 * A tokenizer for morphological analysis.
 */
export class Tokenizer {
    free(): void;
    [Symbol.dispose](): void;
    constructor(dictionary: Dictionary, mode?: string | null, user_dictionary?: UserDictionary | null);
    /**
     * Tokenizes the input text.
     */
    tokenize(input_text: string): Token[];
}

/**
 * Builder for creating a [`Tokenizer`] instance.
 *
 * `TokenizerBuilder` provides a fluent API for configuring and building a tokenizer
 * with various options such as dictionary selection, tokenization mode, character filters,
 * and token filters.
 */
export class TokenizerBuilder {
    free(): void;
    [Symbol.dispose](): void;
    /**
     * Appends a character filter to the tokenization pipeline.
     */
    appendCharacterFilter(name: string, args: any): void;
    /**
     * Appends a token filter to the tokenization pipeline.
     */
    appendTokenFilter(name: string, args: any): void;
    append_character_filter(name: string, args: any): void;
    append_token_filter(name: string, args: any): void;
    /**
     * Builds and returns a configured [`Tokenizer`] instance.
     */
    build(): Tokenizer;
    /**
     * Creates a new `TokenizerBuilder` instance.
     */
    constructor();
    /**
     * Sets the dictionary to use for tokenization.
     */
    setDictionary(uri: string): void;
    /**
     * Sets whether to keep whitespace tokens in the output.
     */
    setKeepWhitespace(keep: boolean): void;
    /**
     * Sets the tokenization mode.
     */
    setMode(mode: string): void;
    /**
     * Sets a user-defined dictionary.
     */
    setUserDictionary(uri: string): void;
    set_dictionary(uri: string): void;
    set_keep_whitespace(keep: boolean): void;
    set_mode(mode: string): void;
    set_user_dictionary(uri: string): void;
}

/**
 * A user-defined dictionary for custom words.
 */
export class UserDictionary {
    private constructor();
    free(): void;
    [Symbol.dispose](): void;
}

/**
 * Builds a dictionary from source files.
 */
export function buildDictionary(input_dir: string, output_dir: string, metadata: Metadata): void;

/**
 * Builds a user dictionary from a CSV file.
 */
export function buildUserDictionary(input_file: string, output_dir: string, metadata?: Metadata | null): void;

export function build_dictionary(input_dir: string, output_dir: string, metadata: Metadata): void;

export function build_user_dictionary(input_file: string, output_dir: string, metadata?: Metadata | null): void;

/**
 * Gets the version of the lindera-wasm library.
 * Backward compatibility alias for version().
 */
export function getVersion(): string;

/**
 * Loads a dictionary from the specified URI.
 */
export function loadDictionary(uri: string): Dictionary;

/**
 * Loads a user dictionary from the specified URI.
 */
export function loadUserDictionary(uri: string, metadata: Metadata): UserDictionary;

export function load_dictionary(uri: string): Dictionary;

export function load_user_dictionary(uri: string, metadata: Metadata): UserDictionary;

/**
 * Returns the version of the lindera-wasm package.
 */
export function version(): string;

export type InitInput = RequestInfo | URL | Response | BufferSource | WebAssembly.Module;

export interface InitOutput {
    readonly memory: WebAssembly.Memory;
    readonly __wbg_linderaerror_free: (a: number, b: number) => void;
    readonly __wbg_metadata_free: (a: number, b: number) => void;
    readonly jslinderaerror_new: (a: number, b: number) => number;
    readonly jslinderaerror_toString: (a: number) => [number, number];
    readonly jsmetadata_compress_algorithm: (a: number) => number;
    readonly jsmetadata_createDefault: () => number;
    readonly jsmetadata_dictionary_schema: (a: number) => number;
    readonly jsmetadata_encoding: (a: number) => [number, number];
    readonly jsmetadata_name: (a: number) => [number, number];
    readonly jsmetadata_new: (a: number, b: number, c: number, d: number, e: number) => number;
    readonly jsmetadata_set_compress_algorithm: (a: number, b: number) => void;
    readonly jsmetadata_set_dictionary_schema: (a: number, b: number) => void;
    readonly jsmetadata_set_encoding: (a: number, b: number, c: number) => void;
    readonly jsmetadata_set_name: (a: number, b: number, c: number) => void;
    readonly jsmetadata_set_user_dictionary_schema: (a: number, b: number) => void;
    readonly jsmetadata_user_dictionary_schema: (a: number) => number;
    readonly __wbg_get_token_byte_end: (a: number) => number;
    readonly __wbg_get_token_details: (a: number) => [number, number];
    readonly __wbg_get_token_position: (a: number) => number;
    readonly __wbg_get_token_word_id: (a: number) => number;
    readonly __wbg_set_token_byte_end: (a: number, b: number) => void;
    readonly __wbg_set_token_details: (a: number, b: number, c: number) => void;
    readonly __wbg_set_token_position: (a: number, b: number) => void;
    readonly __wbg_set_token_word_id: (a: number, b: number) => void;
    readonly __wbg_token_free: (a: number, b: number) => void;
    readonly jstoken_getDetail: (a: number, b: number) => [number, number];
    readonly jstoken_toJSON: (a: number) => any;
    readonly __wbg_get_penalty_kanji_penalty_length_penalty: (a: number) => number;
    readonly __wbg_get_penalty_kanji_penalty_length_threshold: (a: number) => number;
    readonly __wbg_get_penalty_other_penalty_length_penalty: (a: number) => number;
    readonly __wbg_get_penalty_other_penalty_length_threshold: (a: number) => number;
    readonly __wbg_penalty_free: (a: number, b: number) => void;
    readonly __wbg_segmenter_free: (a: number, b: number) => void;
    readonly __wbg_set_penalty_kanji_penalty_length_penalty: (a: number, b: number) => void;
    readonly __wbg_set_penalty_kanji_penalty_length_threshold: (a: number, b: number) => void;
    readonly __wbg_set_penalty_other_penalty_length_penalty: (a: number, b: number) => void;
    readonly __wbg_set_penalty_other_penalty_length_threshold: (a: number, b: number) => void;
    readonly build_dictionary: (a: number, b: number, c: number, d: number, e: number) => [number, number];
    readonly build_user_dictionary: (a: number, b: number, c: number, d: number, e: number) => [number, number];
    readonly getVersion: () => [number, number];
    readonly jspenalty_new: (a: number, b: number, c: number, d: number) => number;
    readonly load_dictionary: (a: number, b: number) => [number, number, number];
    readonly load_user_dictionary: (a: number, b: number, c: number) => [number, number, number];
    readonly __wbg_tokenizer_free: (a: number, b: number) => void;
    readonly __wbg_tokenizerbuilder_free: (a: number, b: number) => void;
    readonly tokenizer_new: (a: number, b: number, c: number, d: number) => [number, number, number];
    readonly tokenizer_tokenize: (a: number, b: number, c: number) => [number, number, number, number];
    readonly tokenizerbuilder_appendCharacterFilter: (a: number, b: number, c: number, d: any) => [number, number];
    readonly tokenizerbuilder_appendTokenFilter: (a: number, b: number, c: number, d: any) => [number, number];
    readonly tokenizerbuilder_append_character_filter: (a: number, b: number, c: number, d: any) => [number, number];
    readonly tokenizerbuilder_append_token_filter: (a: number, b: number, c: number, d: any) => [number, number];
    readonly tokenizerbuilder_build: (a: number) => [number, number, number];
    readonly tokenizerbuilder_new: () => [number, number, number];
    readonly tokenizerbuilder_setDictionary: (a: number, b: number, c: number) => [number, number];
    readonly tokenizerbuilder_setKeepWhitespace: (a: number, b: number) => [number, number];
    readonly tokenizerbuilder_setMode: (a: number, b: number, c: number) => [number, number];
    readonly tokenizerbuilder_setUserDictionary: (a: number, b: number, c: number) => [number, number];
    readonly tokenizerbuilder_set_dictionary: (a: number, b: number, c: number) => [number, number];
    readonly tokenizerbuilder_set_keep_whitespace: (a: number, b: number) => [number, number];
    readonly tokenizerbuilder_set_mode: (a: number, b: number, c: number) => [number, number];
    readonly tokenizerbuilder_set_user_dictionary: (a: number, b: number, c: number) => [number, number];
    readonly __wbg_fielddefinition_free: (a: number, b: number) => void;
    readonly __wbg_get_fielddefinition_description: (a: number) => [number, number];
    readonly __wbg_get_fielddefinition_field_type: (a: number) => number;
    readonly __wbg_get_fielddefinition_index: (a: number) => number;
    readonly __wbg_get_fielddefinition_name: (a: number) => [number, number];
    readonly __wbg_schema_free: (a: number, b: number) => void;
    readonly __wbg_set_fielddefinition_description: (a: number, b: number, c: number) => void;
    readonly __wbg_set_fielddefinition_field_type: (a: number, b: number) => void;
    readonly __wbg_set_fielddefinition_index: (a: number, b: number) => void;
    readonly __wbg_set_fielddefinition_name: (a: number, b: number, c: number) => void;
    readonly jsfielddefinition_new: (a: number, b: number, c: number, d: number, e: number, f: number) => number;
    readonly jsschema_create_default: () => number;
    readonly jsschema_field_count: (a: number) => number;
    readonly jsschema_get_all_fields: (a: number) => [number, number];
    readonly jsschema_get_custom_fields: (a: number) => [number, number];
    readonly jsschema_get_field_by_name: (a: number, b: number, c: number) => number;
    readonly jsschema_get_field_index: (a: number, b: number, c: number) => number;
    readonly jsschema_get_field_name: (a: number, b: number) => [number, number];
    readonly jsschema_new: (a: number, b: number) => number;
    readonly __wbg_dictionary_free: (a: number, b: number) => void;
    readonly __wbg_userdictionary_free: (a: number, b: number) => void;
    readonly buildDictionary: (a: number, b: number, c: number, d: number, e: number) => [number, number];
    readonly buildUserDictionary: (a: number, b: number, c: number, d: number, e: number) => [number, number];
    readonly jsdictionary_encoding: (a: number) => [number, number];
    readonly jsdictionary_metadata: (a: number) => number;
    readonly jsdictionary_name: (a: number) => [number, number];
    readonly loadDictionary: (a: number, b: number) => [number, number, number];
    readonly loadUserDictionary: (a: number, b: number, c: number) => [number, number, number];
    readonly version: () => [number, number];
    readonly __wbg_set_token_byte_start: (a: number, b: number) => void;
    readonly __wbg_set_token_surface: (a: number, b: number, c: number) => void;
    readonly __wbg_set_linderaerror_message: (a: number, b: number, c: number) => void;
    readonly __wbg_get_token_byte_start: (a: number) => number;
    readonly __wbg_get_token_surface: (a: number) => [number, number];
    readonly __wbg_get_linderaerror_message: (a: number) => [number, number];
    readonly __wbindgen_malloc: (a: number, b: number) => number;
    readonly __wbindgen_realloc: (a: number, b: number, c: number, d: number) => number;
    readonly __wbindgen_exn_store: (a: number) => void;
    readonly __externref_table_alloc: () => number;
    readonly __wbindgen_externrefs: WebAssembly.Table;
    readonly __externref_table_dealloc: (a: number) => void;
    readonly __wbindgen_free: (a: number, b: number, c: number) => void;
    readonly __externref_drop_slice: (a: number, b: number) => void;
    readonly __wbindgen_start: () => void;
}

export type SyncInitInput = BufferSource | WebAssembly.Module;

/**
 * Instantiates the given `module`, which can either be bytes or
 * a precompiled `WebAssembly.Module`.
 *
 * @param {{ module: SyncInitInput }} module - Passing `SyncInitInput` directly is deprecated.
 *
 * @returns {InitOutput}
 */
export function initSync(module: { module: SyncInitInput } | SyncInitInput): InitOutput;

/**
 * If `module_or_path` is {RequestInfo} or {URL}, makes a request and
 * for everything else, calls `WebAssembly.instantiate` directly.
 *
 * @param {{ module_or_path: InitInput | Promise<InitInput> }} module_or_path - Passing `InitInput` directly is deprecated.
 *
 * @returns {Promise<InitOutput>}
 */
export default function __wbg_init (module_or_path?: { module_or_path: InitInput | Promise<InitInput> } | InitInput | Promise<InitInput>): Promise<InitOutput>;