lindera-wasm-web-ipadic 1.2.1 → 1.2.2

package/README.md

@@ -12,36 +12,36 @@ WebAssembly of Lindera
 
 ### Web
 
-- <https://www.npmjs.com/package/lindera-wasm-web-cjk>
+- <https://www.npmjs.com/package/lindera-wasm-web-cjk>  
 Lindera WASM with CJK dictionaries (IPADIC, ko-dic, CC-CEDICT) for Web
 
-- <https://www.npmjs.com/package/lindera-wasm-web-ipadic>
+- <https://www.npmjs.com/package/lindera-wasm-web-ipadic>  
 Lindera WASM with Japanese dictionary (IPADIC) for Web
 
-- <https://www.npmjs.com/package/lindera-wasm-web-unidic>
+- <https://www.npmjs.com/package/lindera-wasm-web-unidic>  
 Lindera WASM with Japanese dictionary (UniDic) for Web
 
-- <https://www.npmjs.com/package/lindera-wasm-web-ko-dic>
+- <https://www.npmjs.com/package/lindera-wasm-web-ko-dic>  
 Lindera WASM with Korean dictionary (ko-dic) for Web
 
-- <https://www.npmjs.com/package/lindera-wasm-web-cc-cedict>
+- <https://www.npmjs.com/package/lindera-wasm-web-cc-cedict>  
 Lindera WASM with Chinese dictionary (CC-CEDICT) for Web
 
 ### Node.js
 
-- <https://www.npmjs.com/package/lindera-wasm-nodejs-cjk>
+- <https://www.npmjs.com/package/lindera-wasm-nodejs-cjk>  
 Lindera WASM with CJK dictionaries (IPADIC, ko-dic, CC-CEDICT) for Node.js
 
-- <https://www.npmjs.com/package/lindera-wasm-nodejs-ipadic>
+- <https://www.npmjs.com/package/lindera-wasm-nodejs-ipadic>  
 Lindera WASM with Japanese dictionary (IPADIC) for Node.js
 
-- <https://www.npmjs.com/package/lindera-wasm-nodejs-unidic>
+- <https://www.npmjs.com/package/lindera-wasm-nodejs-unidic>  
 Lindera WASM with Japanese dictionary (UniDic) for Node.js
 
-- <https://www.npmjs.com/package/lindera-wasm-nodejs-ko-dic>
+- <https://www.npmjs.com/package/lindera-wasm-nodejs-ko-dic>  
 Lindera WASM with Korean dictionary (ko-dic) for Node.js
 
-- <https://www.npmjs.com/package/lindera-wasm-nodejs-cc-cedict>
+- <https://www.npmjs.com/package/lindera-wasm-nodejs-cc-cedict>  
 Lindera WASM with Chinese dictionary (CC-CEDICT) for Node.js
 
 ## Usage
@@ -96,7 +96,6 @@ export default defineConfig({
 and set the `content_security_policy` to contains `wasm-unsafe-eval` in manifest.json:
 
 ```json
-// manifest.json
 "content_security_policy": {
   "extension_pages": "script-src 'self' 'wasm-unsafe-eval';"
 }

package/lindera_wasm.d.ts

@@ -1,42 +1,6 @@
 /* tslint:disable */
 /* eslint-disable */
-/**
- * Gets the version of the lindera-wasm library.
- *
- * # Returns
- *
- * The version string of the library (e.g., "1.0.0").
- *
- * # Examples
- *
- * ```javascript
- * import { getVersion } from 'lindera-wasm';
- * console.log(getVersion()); // "1.0.0"
- * ```
- */
-export function getVersion(): string;
-/**
- * A tokenizer for morphological analysis.
- *
- * The `Tokenizer` performs text tokenization based on the configuration
- * provided by [`TokenizerBuilder`].
- *
- * # Examples
- *
- * ```javascript
- * const builder = new TokenizerBuilder();
- * builder.setDictionary("embedded://ipadic");
- * builder.setMode("normal");
- *
- * const tokenizer = builder.build();
- * const tokens = tokenizer.tokenize("関西国際空港");
- * console.log(tokens);
- * // Output: [
- * //   { surface: "関西国際空港", ... },
- * //   ...
- * // ]
- * ```
- */
+
 export class Tokenizer {
   private constructor();
   free(): void;
@@ -74,215 +38,213 @@ export class Tokenizer {
    */
   tokenize(input_text: string): any;
 }
-/**
- * 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.
- *
- * # Examples
- *
- * ```javascript
- * const builder = new TokenizerBuilder();
- * builder.setDictionary("embedded://ipadic");
- * builder.setMode("normal");
- * builder.setKeepWhitespace(false);
- * builder.appendCharacterFilter("unicode_normalize", { "kind": "nfkc" });
- * builder.appendTokenFilter("lowercase");
- *
- * const tokenizer = builder.build();
- * ```
- */
+
 export class TokenizerBuilder {
   free(): void;
   [Symbol.dispose](): void;
   /**
-   * Creates a new `TokenizerBuilder` instance.
-   *
-   * # Returns
-   *
-   * A new `TokenizerBuilder` instance.
+   * Sets the dictionary to use for tokenization.
    *
-   * # Errors
+   * # Parameters
    *
-   * Returns an error if the builder cannot be initialized.
+   * - `uri`: The dictionary URI. Valid embedded dictionaries are:
+   *   - `"embedded://ipadic"`: Japanese IPADIC dictionary
+   *   - `"embedded://unidic"`: Japanese UniDic dictionary
+   *   - `"embedded://ko-dic"`: Korean ko-dic dictionary
+   *   - `"embedded://cc-cedict"`: Chinese CC-CEDICT dictionary
    *
    * # Examples
    *
    * ```javascript
-   * const builder = new TokenizerBuilder();
+   * builder.setDictionary("embedded://ipadic");
    * ```
    */
-  constructor();
+  setDictionary(uri: string): void;
   /**
-   * Builds and returns a configured [`Tokenizer`] instance.
+   * Appends a token filter to the tokenization pipeline.
    *
-   * This method consumes the builder and creates the final tokenizer with all
-   * configured settings.
+   * Token filters transform or filter the tokens after tokenization.
    *
-   * # Returns
+   * # Parameters
    *
-   * A configured `Tokenizer` instance.
+   * - `name`: The name of the token filter (e.g., `"lowercase"`, `"japanese_number"`).
+   * - `args`: A JavaScript object containing filter-specific arguments.
    *
    * # Errors
    *
-   * Returns an error if the tokenizer cannot be built with the current configuration.
+   * Returns an error if the arguments cannot be parsed.
    *
    * # Examples
    *
    * ```javascript
-   * const builder = new TokenizerBuilder();
-   * builder.setDictionary("embedded://ipadic");
-   * const tokenizer = builder.build();
+   * builder.appendTokenFilter("lowercase");
+   * builder.appendTokenFilter("japanese_number", { "tags": ["名詞,数"] });
    * ```
    */
-  build(): Tokenizer;
+  appendTokenFilter(name: string, args: any): void;
   /**
-   * Sets the tokenization mode.
+   * Sets whether to keep whitespace tokens in the output.
    *
    * # Parameters
    *
-   * - `mode`: The tokenization mode. Valid values are:
-   *   - `"normal"`: Standard tokenization
-   *   - `"decompose"`: Decomposes compound words into their components
-   *
-   * # Errors
-   *
-   * Returns an error if the mode string is invalid.
+   * - `keep`: If `true`, whitespace tokens are preserved; if `false`, they are removed.
    *
    * # Examples
    *
    * ```javascript
-   * builder.setMode("normal");
+   * builder.setKeepWhitespace(false); // Remove whitespace tokens
    * // or
-   * builder.setMode("decompose");
+   * builder.setKeepWhitespace(true);  // Keep whitespace tokens
    * ```
    */
-  setMode(mode: string): void;
+  setKeepWhitespace(keep: boolean): void;
   /**
-   * Sets the dictionary to use for tokenization.
+   * Sets a user-defined dictionary.
+   *
+   * User dictionaries allow you to add custom words and their properties
+   * to supplement the main dictionary.
    *
    * # Parameters
    *
-   * - `uri`: The dictionary URI. Valid embedded dictionaries are:
-   *   - `"embedded://ipadic"`: Japanese IPADIC dictionary
-   *   - `"embedded://unidic"`: Japanese UniDic dictionary
-   *   - `"embedded://ko-dic"`: Korean ko-dic dictionary
-   *   - `"embedded://cc-cedict"`: Chinese CC-CEDICT dictionary
+   * - `uri`: The URI to the user dictionary file.
    *
    * # Examples
    *
    * ```javascript
-   * builder.setDictionary("embedded://ipadic");
+   * builder.setUserDictionary("path/to/user_dict.csv");
    * ```
    */
-  setDictionary(uri: string): void;
+  setUserDictionary(uri: string): void;
   /**
-   * Sets a user-defined dictionary.
+   * Appends a character filter to the tokenization pipeline.
    *
-   * User dictionaries allow you to add custom words and their properties
-   * to supplement the main dictionary.
+   * Character filters transform the input text before tokenization.
    *
    * # Parameters
    *
-   * - `uri`: The URI to the user dictionary file.
+   * - `name`: The name of the character filter (e.g., `"unicode_normalize"`).
+   * - `args`: A JavaScript object containing filter-specific arguments.
+   *
+   * # Errors
+   *
+   * Returns an error if the arguments cannot be parsed.
    *
    * # Examples
    *
    * ```javascript
-   * builder.setUserDictionary("path/to/user_dict.csv");
+   * builder.appendCharacterFilter("unicode_normalize", { "kind": "nfkc" });
    * ```
    */
-  setUserDictionary(uri: string): void;
+  appendCharacterFilter(name: string, args: any): void;
   /**
-   * Sets whether to keep whitespace tokens in the output.
+   * Creates a new `TokenizerBuilder` instance.
    *
-   * # Parameters
+   * # Returns
    *
-   * - `keep`: If `true`, whitespace tokens are preserved; if `false`, they are removed.
+   * A new `TokenizerBuilder` instance.
+   *
+   * # Errors
+   *
+   * Returns an error if the builder cannot be initialized.
    *
    * # Examples
    *
    * ```javascript
-   * builder.setKeepWhitespace(false); // Remove whitespace tokens
-   * // or
-   * builder.setKeepWhitespace(true);  // Keep whitespace tokens
+   * const builder = new TokenizerBuilder();
    * ```
    */
-  setKeepWhitespace(keep: boolean): void;
+  constructor();
   /**
-   * Appends a character filter to the tokenization pipeline.
+   * Builds and returns a configured [`Tokenizer`] instance.
    *
-   * Character filters transform the input text before tokenization.
+   * This method consumes the builder and creates the final tokenizer with all
+   * configured settings.
    *
-   * # Parameters
+   * # Returns
    *
-   * - `name`: The name of the character filter (e.g., `"unicode_normalize"`).
-   * - `args`: A JavaScript object containing filter-specific arguments.
+   * A configured `Tokenizer` instance.
    *
    * # Errors
    *
-   * Returns an error if the arguments cannot be parsed.
+   * Returns an error if the tokenizer cannot be built with the current configuration.
    *
    * # Examples
    *
    * ```javascript
-   * builder.appendCharacterFilter("unicode_normalize", { "kind": "nfkc" });
+   * const builder = new TokenizerBuilder();
+   * builder.setDictionary("embedded://ipadic");
+   * const tokenizer = builder.build();
    * ```
    */
-  appendCharacterFilter(name: string, args: any): void;
+  build(): Tokenizer;
   /**
-   * Appends a token filter to the tokenization pipeline.
-   *
-   * Token filters transform or filter the tokens after tokenization.
+   * Sets the tokenization mode.
    *
    * # Parameters
    *
-   * - `name`: The name of the token filter (e.g., `"lowercase"`, `"japanese_number"`).
-   * - `args`: A JavaScript object containing filter-specific arguments.
+   * - `mode`: The tokenization mode. Valid values are:
+   *   - `"normal"`: Standard tokenization
+   *   - `"decompose"`: Decomposes compound words into their components
    *
    * # Errors
    *
-   * Returns an error if the arguments cannot be parsed.
+   * Returns an error if the mode string is invalid.
    *
    * # Examples
    *
    * ```javascript
-   * builder.appendTokenFilter("lowercase");
-   * builder.appendTokenFilter("japanese_number", { "tags": ["名詞,数"] });
+   * builder.setMode("normal");
+   * // or
+   * builder.setMode("decompose");
    * ```
    */
-  appendTokenFilter(name: string, args: any): void;
+  setMode(mode: string): void;
 }
 
+/**
+ * Gets the version of the lindera-wasm library.
+ *
+ * # Returns
+ *
+ * The version string of the library (e.g., "1.0.0").
+ *
+ * # Examples
+ *
+ * ```javascript
+ * import { getVersion } from 'lindera-wasm';
+ * console.log(getVersion()); // "1.0.0"
+ * ```
+ */
+export function getVersion(): string;
+
 export type InitInput = RequestInfo | URL | Response | BufferSource | WebAssembly.Module;
 
 export interface InitOutput {
   readonly memory: WebAssembly.Memory;
-  readonly getVersion: () => [number, number];
+  readonly __wbg_tokenizer_free: (a: number, b: number) => void;
   readonly __wbg_tokenizerbuilder_free: (a: number, b: number) => void;
-  readonly tokenizerbuilder_new: () => [number, number, number];
+  readonly getVersion: () => [number, number];
+  readonly tokenizer_tokenize: (a: number, b: number, c: 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_build: (a: number) => [number, number, number];
-  readonly tokenizerbuilder_setMode: (a: number, b: number, c: number) => [number, number];
+  readonly tokenizerbuilder_new: () => [number, number, number];
   readonly tokenizerbuilder_setDictionary: (a: number, b: number, c: number) => [number, number];
-  readonly tokenizerbuilder_setUserDictionary: (a: number, b: number, c: number) => [number, number];
   readonly tokenizerbuilder_setKeepWhitespace: (a: number, b: 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 __wbg_tokenizer_free: (a: number, b: number) => void;
-  readonly tokenizer_tokenize: (a: number, b: number, c: number) => [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 __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_export_4: WebAssembly.Table;
-  readonly __wbindgen_free: (a: number, b: number, c: number) => void;
+  readonly __wbindgen_externrefs: WebAssembly.Table;
   readonly __externref_table_dealloc: (a: number) => void;
+  readonly __wbindgen_free: (a: number, b: number, c: 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`.