lindera-wasm-nodejs-cc-cedict 1.2.1

package/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 by the project authors.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

package/README.md

@@ -0,0 +1,135 @@
+# lindera-wasm
+
+WebAssembly of Lindera
+
+![Screenshot from 2025-09-13 23-05-49](https://github.com/user-attachments/assets/a6ca165a-825c-4260-ba52-d76cd262a21f)
+
+## Demo Application
+
+- <https://lindera.github.io/lindera-wasm/>
+
+## npm
+
+### Web
+
+- <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>
+Lindera WASM with Japanese dictionary (IPADIC) for Web
+
+- <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>
+Lindera WASM with Korean dictionary (ko-dic) for Web
+
+- <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>
+Lindera WASM with CJK dictionaries (IPADIC, ko-dic, CC-CEDICT) for Node.js
+
+- <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>
+Lindera WASM with Japanese dictionary (UniDic) for Node.js
+
+- <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>
+Lindera WASM with Chinese dictionary (CC-CEDICT) for Node.js
+
+## Usage
+
+init the wasm module before construct `TokenizerBuilder`:
+
+```ts
+import __wbg_init, { TokenizerBuilder } from 'lindera-wasm'
+
+__wbg_init.then(() => {
+    const builder = new TokenizerBuilder()
+    //...
+})
+```
+
+### for [Vite](https://vite.dev/) base project
+
+You should exclude this package in the `optimizeDeps`:
+
+```ts
+// vite.config.js
+import { defineConfig } from 'vite'
+
+export default defineConfig({
+  optimizeDeps: {
+    exclude: [
+      "lindera-wasm"
+    ]
+  },
+})
+```
+
+### for Browser extension development
+
+Set the `cors` config in vite.config.js
+
+```ts
+// vite.config.js
+import { defineConfig } from 'vite'
+
+export default defineConfig({
+  server: {
+    cors: {
+      origin: [
+        /chrome-extension:\/\//,
+      ],
+    },
+  },
+})
+```
+
+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';"
+}
+```
+
+## Development
+
+### Install project dependencies
+
+- wasm-pack : <https://rustwasm.github.io/wasm-pack/installer/>
+
+### Setup repository
+
+```shell
+# Clone lindera-py project repository
+% git clone git@github.com:lindera/lindera-wasm.git
+% cd lindera-wasm
+```
+
+### Build project
+
+```shell
+% wasm-pack build --release --features=cjk --target=bundler
+```
+
+### Build example web application
+
+```shell
+% cd lindera-wasm && npm install && npm run build && cp index.html dist/index.html
+```
+
+### Run example web application
+
+```shell
+% cd lindera-wasm && npm run start
+```

package/lindera_wasm.d.ts

@@ -0,0 +1,257 @@
+/* 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;
+  [Symbol.dispose](): void;
+  /**
+   * Tokenizes the input text.
+   *
+   * Analyzes the input text and returns an array of token objects. Each token
+   * contains information such as surface form, part-of-speech tags, reading, etc.
+   * Field names in the returned objects are in camelCase.
+   *
+   * # Parameters
+   *
+   * - `input_text`: The text to tokenize.
+   *
+   * # Returns
+   *
+   * A JavaScript array of token objects. Each token object contains:
+   * - `surface`: The surface form of the token
+   * - `pos`: Part-of-speech tags
+   * - Additional language-specific fields
+   *
+   * # Errors
+   *
+   * Returns an error if tokenization fails.
+   *
+   * # Examples
+   *
+   * ```javascript
+   * const tokens = tokenizer.tokenize("東京都に行く");
+   * tokens.forEach(token => {
+   *     console.log(token.surface, token.pos);
+   * });
+   * ```
+   */
+  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.
+   *
+   * # Errors
+   *
+   * Returns an error if the builder cannot be initialized.
+   *
+   * # Examples
+   *
+   * ```javascript
+   * const builder = new TokenizerBuilder();
+   * ```
+   */
+  constructor();
+  /**
+   * Builds and returns a configured [`Tokenizer`] instance.
+   *
+   * This method consumes the builder and creates the final tokenizer with all
+   * configured settings.
+   *
+   * # Returns
+   *
+   * A configured `Tokenizer` instance.
+   *
+   * # Errors
+   *
+   * Returns an error if the tokenizer cannot be built with the current configuration.
+   *
+   * # Examples
+   *
+   * ```javascript
+   * const builder = new TokenizerBuilder();
+   * builder.setDictionary("embedded://ipadic");
+   * const tokenizer = builder.build();
+   * ```
+   */
+  build(): Tokenizer;
+  /**
+   * Sets the tokenization mode.
+   *
+   * # 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.
+   *
+   * # Examples
+   *
+   * ```javascript
+   * builder.setMode("normal");
+   * // or
+   * builder.setMode("decompose");
+   * ```
+   */
+  setMode(mode: string): void;
+  /**
+   * Sets the dictionary to use for tokenization.
+   *
+   * # 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
+   *
+   * # Examples
+   *
+   * ```javascript
+   * builder.setDictionary("embedded://ipadic");
+   * ```
+   */
+  setDictionary(uri: string): void;
+  /**
+   * Sets a user-defined dictionary.
+   *
+   * User dictionaries allow you to add custom words and their properties
+   * to supplement the main dictionary.
+   *
+   * # Parameters
+   *
+   * - `uri`: The URI to the user dictionary file.
+   *
+   * # Examples
+   *
+   * ```javascript
+   * builder.setUserDictionary("path/to/user_dict.csv");
+   * ```
+   */
+  setUserDictionary(uri: string): void;
+  /**
+   * Sets whether to keep whitespace tokens in the output.
+   *
+   * # Parameters
+   *
+   * - `keep`: If `true`, whitespace tokens are preserved; if `false`, they are removed.
+   *
+   * # Examples
+   *
+   * ```javascript
+   * builder.setKeepWhitespace(false); // Remove whitespace tokens
+   * // or
+   * builder.setKeepWhitespace(true);  // Keep whitespace tokens
+   * ```
+   */
+  setKeepWhitespace(keep: boolean): void;
+  /**
+   * Appends a character filter to the tokenization pipeline.
+   *
+   * Character filters transform the input text before tokenization.
+   *
+   * # Parameters
+   *
+   * - `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.appendCharacterFilter("unicode_normalize", { "kind": "nfkc" });
+   * ```
+   */
+  appendCharacterFilter(name: string, args: any): void;
+  /**
+   * Appends a token filter to the tokenization pipeline.
+   *
+   * Token filters transform or filter the tokens after tokenization.
+   *
+   * # Parameters
+   *
+   * - `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 arguments cannot be parsed.
+   *
+   * # Examples
+   *
+   * ```javascript
+   * builder.appendTokenFilter("lowercase");
+   * builder.appendTokenFilter("japanese_number", { "tags": ["名詞,数"] });
+   * ```
+   */
+  appendTokenFilter(name: string, args: any): void;
+}

package/lindera_wasm.js

@@ -0,0 +1,820 @@
+
+let imports = {};
+imports['__wbindgen_placeholder__'] = module.exports;
+
+let cachedUint8ArrayMemory0 = null;
+
+function getUint8ArrayMemory0() {
+    if (cachedUint8ArrayMemory0 === null || cachedUint8ArrayMemory0.byteLength === 0) {
+        cachedUint8ArrayMemory0 = new Uint8Array(wasm.memory.buffer);
+    }
+    return cachedUint8ArrayMemory0;
+}
+
+let cachedTextDecoder = new TextDecoder('utf-8', { ignoreBOM: true, fatal: true });
+
+cachedTextDecoder.decode();
+
+function decodeText(ptr, len) {
+    return cachedTextDecoder.decode(getUint8ArrayMemory0().subarray(ptr, ptr + len));
+}
+
+function getStringFromWasm0(ptr, len) {
+    ptr = ptr >>> 0;
+    return decodeText(ptr, len);
+}
+
+let WASM_VECTOR_LEN = 0;
+
+const cachedTextEncoder = new TextEncoder();
+
+if (!('encodeInto' in cachedTextEncoder)) {
+    cachedTextEncoder.encodeInto = function (arg, view) {
+        const buf = cachedTextEncoder.encode(arg);
+        view.set(buf);
+        return {
+            read: arg.length,
+            written: buf.length
+        };
+    }
+}
+
+function passStringToWasm0(arg, malloc, realloc) {
+
+    if (realloc === undefined) {
+        const buf = cachedTextEncoder.encode(arg);
+        const ptr = malloc(buf.length, 1) >>> 0;
+        getUint8ArrayMemory0().subarray(ptr, ptr + buf.length).set(buf);
+        WASM_VECTOR_LEN = buf.length;
+        return ptr;
+    }
+
+    let len = arg.length;
+    let ptr = malloc(len, 1) >>> 0;
+
+    const mem = getUint8ArrayMemory0();
+
+    let offset = 0;
+
+    for (; offset < len; offset++) {
+        const code = arg.charCodeAt(offset);
+        if (code > 0x7F) break;
+        mem[ptr + offset] = code;
+    }
+
+    if (offset !== len) {
+        if (offset !== 0) {
+            arg = arg.slice(offset);
+        }
+        ptr = realloc(ptr, len, len = offset + arg.length * 3, 1) >>> 0;
+        const view = getUint8ArrayMemory0().subarray(ptr + offset, ptr + len);
+        const ret = cachedTextEncoder.encodeInto(arg, view);
+
+        offset += ret.written;
+        ptr = realloc(ptr, len, offset, 1) >>> 0;
+    }
+
+    WASM_VECTOR_LEN = offset;
+    return ptr;
+}
+
+let cachedDataViewMemory0 = null;
+
+function getDataViewMemory0() {
+    if (cachedDataViewMemory0 === null || cachedDataViewMemory0.buffer.detached === true || (cachedDataViewMemory0.buffer.detached === undefined && cachedDataViewMemory0.buffer !== wasm.memory.buffer)) {
+        cachedDataViewMemory0 = new DataView(wasm.memory.buffer);
+    }
+    return cachedDataViewMemory0;
+}
+
+function addToExternrefTable0(obj) {
+    const idx = wasm.__externref_table_alloc();
+    wasm.__wbindgen_export_4.set(idx, obj);
+    return idx;
+}
+
+function handleError(f, args) {
+    try {
+        return f.apply(this, args);
+    } catch (e) {
+        const idx = addToExternrefTable0(e);
+        wasm.__wbindgen_exn_store(idx);
+    }
+}
+
+function getArrayU8FromWasm0(ptr, len) {
+    ptr = ptr >>> 0;
+    return getUint8ArrayMemory0().subarray(ptr / 1, ptr / 1 + len);
+}
+
+function isLikeNone(x) {
+    return x === undefined || x === null;
+}
+
+function debugString(val) {
+    // primitive types
+    const type = typeof val;
+    if (type == 'number' || type == 'boolean' || val == null) {
+        return  `${val}`;
+    }
+    if (type == 'string') {
+        return `"${val}"`;
+    }
+    if (type == 'symbol') {
+        const description = val.description;
+        if (description == null) {
+            return 'Symbol';
+        } else {
+            return `Symbol(${description})`;
+        }
+    }
+    if (type == 'function') {
+        const name = val.name;
+        if (typeof name == 'string' && name.length > 0) {
+            return `Function(${name})`;
+        } else {
+            return 'Function';
+        }
+    }
+    // objects
+    if (Array.isArray(val)) {
+        const length = val.length;
+        let debug = '[';
+        if (length > 0) {
+            debug += debugString(val[0]);
+        }
+        for(let i = 1; i < length; i++) {
+            debug += ', ' + debugString(val[i]);
+        }
+        debug += ']';
+        return debug;
+    }
+    // Test for built-in
+    const builtInMatches = /\[object ([^\]]+)\]/.exec(toString.call(val));
+    let className;
+    if (builtInMatches && builtInMatches.length > 1) {
+        className = builtInMatches[1];
+    } else {
+        // Failed to match the standard '[object ClassName]'
+        return toString.call(val);
+    }
+    if (className == 'Object') {
+        // we're a user defined class or Object
+        // JSON.stringify avoids problems with cycles, and is generally much
+        // easier than looping through ownProperties of `val`.
+        try {
+            return 'Object(' + JSON.stringify(val) + ')';
+        } catch (_) {
+            return 'Object';
+        }
+    }
+    // errors
+    if (val instanceof Error) {
+        return `${val.name}: ${val.message}\n${val.stack}`;
+    }
+    // TODO we could test for more things here, like `Set`s and `Map`s.
+    return className;
+}
+/**
+ * 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"
+ * ```
+ * @returns {string}
+ */
+exports.getVersion = function() {
+    let deferred1_0;
+    let deferred1_1;
+    try {
+        const ret = wasm.getVersion();
+        deferred1_0 = ret[0];
+        deferred1_1 = ret[1];
+        return getStringFromWasm0(ret[0], ret[1]);
+    } finally {
+        wasm.__wbindgen_free(deferred1_0, deferred1_1, 1);
+    }
+};
+
+function takeFromExternrefTable0(idx) {
+    const value = wasm.__wbindgen_export_4.get(idx);
+    wasm.__externref_table_dealloc(idx);
+    return value;
+}
+
+const TokenizerFinalization = (typeof FinalizationRegistry === 'undefined')
+    ? { register: () => {}, unregister: () => {} }
+    : new FinalizationRegistry(ptr => wasm.__wbg_tokenizer_free(ptr >>> 0, 1));
+/**
+ * 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", ... },
+ * //   ...
+ * // ]
+ * ```
+ */
+class Tokenizer {
+
+    static __wrap(ptr) {
+        ptr = ptr >>> 0;
+        const obj = Object.create(Tokenizer.prototype);
+        obj.__wbg_ptr = ptr;
+        TokenizerFinalization.register(obj, obj.__wbg_ptr, obj);
+        return obj;
+    }
+
+    __destroy_into_raw() {
+        const ptr = this.__wbg_ptr;
+        this.__wbg_ptr = 0;
+        TokenizerFinalization.unregister(this);
+        return ptr;
+    }
+
+    free() {
+        const ptr = this.__destroy_into_raw();
+        wasm.__wbg_tokenizer_free(ptr, 0);
+    }
+    /**
+     * Tokenizes the input text.
+     *
+     * Analyzes the input text and returns an array of token objects. Each token
+     * contains information such as surface form, part-of-speech tags, reading, etc.
+     * Field names in the returned objects are in camelCase.
+     *
+     * # Parameters
+     *
+     * - `input_text`: The text to tokenize.
+     *
+     * # Returns
+     *
+     * A JavaScript array of token objects. Each token object contains:
+     * - `surface`: The surface form of the token
+     * - `pos`: Part-of-speech tags
+     * - Additional language-specific fields
+     *
+     * # Errors
+     *
+     * Returns an error if tokenization fails.
+     *
+     * # Examples
+     *
+     * ```javascript
+     * const tokens = tokenizer.tokenize("東京都に行く");
+     * tokens.forEach(token => {
+     *     console.log(token.surface, token.pos);
+     * });
+     * ```
+     * @param {string} input_text
+     * @returns {any}
+     */
+    tokenize(input_text) {
+        const ptr0 = passStringToWasm0(input_text, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
+        const len0 = WASM_VECTOR_LEN;
+        const ret = wasm.tokenizer_tokenize(this.__wbg_ptr, ptr0, len0);
+        if (ret[2]) {
+            throw takeFromExternrefTable0(ret[1]);
+        }
+        return takeFromExternrefTable0(ret[0]);
+    }
+}
+if (Symbol.dispose) Tokenizer.prototype[Symbol.dispose] = Tokenizer.prototype.free;
+
+exports.Tokenizer = Tokenizer;
+
+const TokenizerBuilderFinalization = (typeof FinalizationRegistry === 'undefined')
+    ? { register: () => {}, unregister: () => {} }
+    : new FinalizationRegistry(ptr => wasm.__wbg_tokenizerbuilder_free(ptr >>> 0, 1));
+/**
+ * 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();
+ * ```
+ */
+class TokenizerBuilder {
+
+    __destroy_into_raw() {
+        const ptr = this.__wbg_ptr;
+        this.__wbg_ptr = 0;
+        TokenizerBuilderFinalization.unregister(this);
+        return ptr;
+    }
+
+    free() {
+        const ptr = this.__destroy_into_raw();
+        wasm.__wbg_tokenizerbuilder_free(ptr, 0);
+    }
+    /**
+     * Creates a new `TokenizerBuilder` instance.
+     *
+     * # Returns
+     *
+     * A new `TokenizerBuilder` instance.
+     *
+     * # Errors
+     *
+     * Returns an error if the builder cannot be initialized.
+     *
+     * # Examples
+     *
+     * ```javascript
+     * const builder = new TokenizerBuilder();
+     * ```
+     */
+    constructor() {
+        const ret = wasm.tokenizerbuilder_new();
+        if (ret[2]) {
+            throw takeFromExternrefTable0(ret[1]);
+        }
+        this.__wbg_ptr = ret[0] >>> 0;
+        TokenizerBuilderFinalization.register(this, this.__wbg_ptr, this);
+        return this;
+    }
+    /**
+     * Builds and returns a configured [`Tokenizer`] instance.
+     *
+     * This method consumes the builder and creates the final tokenizer with all
+     * configured settings.
+     *
+     * # Returns
+     *
+     * A configured `Tokenizer` instance.
+     *
+     * # Errors
+     *
+     * Returns an error if the tokenizer cannot be built with the current configuration.
+     *
+     * # Examples
+     *
+     * ```javascript
+     * const builder = new TokenizerBuilder();
+     * builder.setDictionary("embedded://ipadic");
+     * const tokenizer = builder.build();
+     * ```
+     * @returns {Tokenizer}
+     */
+    build() {
+        const ptr = this.__destroy_into_raw();
+        const ret = wasm.tokenizerbuilder_build(ptr);
+        if (ret[2]) {
+            throw takeFromExternrefTable0(ret[1]);
+        }
+        return Tokenizer.__wrap(ret[0]);
+    }
+    /**
+     * Sets the tokenization mode.
+     *
+     * # 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.
+     *
+     * # Examples
+     *
+     * ```javascript
+     * builder.setMode("normal");
+     * // or
+     * builder.setMode("decompose");
+     * ```
+     * @param {string} mode
+     */
+    setMode(mode) {
+        const ptr0 = passStringToWasm0(mode, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
+        const len0 = WASM_VECTOR_LEN;
+        const ret = wasm.tokenizerbuilder_setMode(this.__wbg_ptr, ptr0, len0);
+        if (ret[1]) {
+            throw takeFromExternrefTable0(ret[0]);
+        }
+    }
+    /**
+     * Sets the dictionary to use for tokenization.
+     *
+     * # 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
+     *
+     * # Examples
+     *
+     * ```javascript
+     * builder.setDictionary("embedded://ipadic");
+     * ```
+     * @param {string} uri
+     */
+    setDictionary(uri) {
+        const ptr0 = passStringToWasm0(uri, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
+        const len0 = WASM_VECTOR_LEN;
+        const ret = wasm.tokenizerbuilder_setDictionary(this.__wbg_ptr, ptr0, len0);
+        if (ret[1]) {
+            throw takeFromExternrefTable0(ret[0]);
+        }
+    }
+    /**
+     * Sets a user-defined dictionary.
+     *
+     * User dictionaries allow you to add custom words and their properties
+     * to supplement the main dictionary.
+     *
+     * # Parameters
+     *
+     * - `uri`: The URI to the user dictionary file.
+     *
+     * # Examples
+     *
+     * ```javascript
+     * builder.setUserDictionary("path/to/user_dict.csv");
+     * ```
+     * @param {string} uri
+     */
+    setUserDictionary(uri) {
+        const ptr0 = passStringToWasm0(uri, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
+        const len0 = WASM_VECTOR_LEN;
+        const ret = wasm.tokenizerbuilder_setUserDictionary(this.__wbg_ptr, ptr0, len0);
+        if (ret[1]) {
+            throw takeFromExternrefTable0(ret[0]);
+        }
+    }
+    /**
+     * Sets whether to keep whitespace tokens in the output.
+     *
+     * # Parameters
+     *
+     * - `keep`: If `true`, whitespace tokens are preserved; if `false`, they are removed.
+     *
+     * # Examples
+     *
+     * ```javascript
+     * builder.setKeepWhitespace(false); // Remove whitespace tokens
+     * // or
+     * builder.setKeepWhitespace(true);  // Keep whitespace tokens
+     * ```
+     * @param {boolean} keep
+     */
+    setKeepWhitespace(keep) {
+        const ret = wasm.tokenizerbuilder_setKeepWhitespace(this.__wbg_ptr, keep);
+        if (ret[1]) {
+            throw takeFromExternrefTable0(ret[0]);
+        }
+    }
+    /**
+     * Appends a character filter to the tokenization pipeline.
+     *
+     * Character filters transform the input text before tokenization.
+     *
+     * # Parameters
+     *
+     * - `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.appendCharacterFilter("unicode_normalize", { "kind": "nfkc" });
+     * ```
+     * @param {string} name
+     * @param {any} args
+     */
+    appendCharacterFilter(name, args) {
+        const ptr0 = passStringToWasm0(name, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
+        const len0 = WASM_VECTOR_LEN;
+        const ret = wasm.tokenizerbuilder_appendCharacterFilter(this.__wbg_ptr, ptr0, len0, args);
+        if (ret[1]) {
+            throw takeFromExternrefTable0(ret[0]);
+        }
+    }
+    /**
+     * Appends a token filter to the tokenization pipeline.
+     *
+     * Token filters transform or filter the tokens after tokenization.
+     *
+     * # Parameters
+     *
+     * - `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 arguments cannot be parsed.
+     *
+     * # Examples
+     *
+     * ```javascript
+     * builder.appendTokenFilter("lowercase");
+     * builder.appendTokenFilter("japanese_number", { "tags": ["名詞,数"] });
+     * ```
+     * @param {string} name
+     * @param {any} args
+     */
+    appendTokenFilter(name, args) {
+        const ptr0 = passStringToWasm0(name, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
+        const len0 = WASM_VECTOR_LEN;
+        const ret = wasm.tokenizerbuilder_appendTokenFilter(this.__wbg_ptr, ptr0, len0, args);
+        if (ret[1]) {
+            throw takeFromExternrefTable0(ret[0]);
+        }
+    }
+}
+if (Symbol.dispose) TokenizerBuilder.prototype[Symbol.dispose] = TokenizerBuilder.prototype.free;
+
+exports.TokenizerBuilder = TokenizerBuilder;
+
+exports.__wbg_Error_e17e777aac105295 = function(arg0, arg1) {
+    const ret = Error(getStringFromWasm0(arg0, arg1));
+    return ret;
+};
+
+exports.__wbg_String_8f0eb39a4a4c2f66 = function(arg0, arg1) {
+    const ret = String(arg1);
+    const ptr1 = passStringToWasm0(ret, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
+    const len1 = WASM_VECTOR_LEN;
+    getDataViewMemory0().setInt32(arg0 + 4 * 1, len1, true);
+    getDataViewMemory0().setInt32(arg0 + 4 * 0, ptr1, true);
+};
+
+exports.__wbg_call_13410aac570ffff7 = function() { return handleError(function (arg0, arg1) {
+    const ret = arg0.call(arg1);
+    return ret;
+}, arguments) };
+
+exports.__wbg_done_75ed0ee6dd243d9d = function(arg0) {
+    const ret = arg0.done;
+    return ret;
+};
+
+exports.__wbg_entries_2be2f15bd5554996 = function(arg0) {
+    const ret = Object.entries(arg0);
+    return ret;
+};
+
+exports.__wbg_get_0da715ceaecea5c8 = function(arg0, arg1) {
+    const ret = arg0[arg1 >>> 0];
+    return ret;
+};
+
+exports.__wbg_get_458e874b43b18b25 = function() { return handleError(function (arg0, arg1) {
+    const ret = Reflect.get(arg0, arg1);
+    return ret;
+}, arguments) };
+
+exports.__wbg_instanceof_ArrayBuffer_67f3012529f6a2dd = function(arg0) {
+    let result;
+    try {
+        result = arg0 instanceof ArrayBuffer;
+    } catch (_) {
+        result = false;
+    }
+    const ret = result;
+    return ret;
+};
+
+exports.__wbg_instanceof_Map_ebb01a5b6b5ffd0b = function(arg0) {
+    let result;
+    try {
+        result = arg0 instanceof Map;
+    } catch (_) {
+        result = false;
+    }
+    const ret = result;
+    return ret;
+};
+
+exports.__wbg_instanceof_Uint8Array_9a8378d955933db7 = function(arg0) {
+    let result;
+    try {
+        result = arg0 instanceof Uint8Array;
+    } catch (_) {
+        result = false;
+    }
+    const ret = result;
+    return ret;
+};
+
+exports.__wbg_isArray_030cce220591fb41 = function(arg0) {
+    const ret = Array.isArray(arg0);
+    return ret;
+};
+
+exports.__wbg_isSafeInteger_1c0d1af5542e102a = function(arg0) {
+    const ret = Number.isSafeInteger(arg0);
+    return ret;
+};
+
+exports.__wbg_iterator_f370b34483c71a1c = function() {
+    const ret = Symbol.iterator;
+    return ret;
+};
+
+exports.__wbg_length_186546c51cd61acd = function(arg0) {
+    const ret = arg0.length;
+    return ret;
+};
+
+exports.__wbg_length_6bb7e81f9d7713e4 = function(arg0) {
+    const ret = arg0.length;
+    return ret;
+};
+
+exports.__wbg_new_19c25a3f2fa63a02 = function() {
+    const ret = new Object();
+    return ret;
+};
+
+exports.__wbg_new_1f3a344cf3123716 = function() {
+    const ret = new Array();
+    return ret;
+};
+
+exports.__wbg_new_638ebfaedbf32a5e = function(arg0) {
+    const ret = new Uint8Array(arg0);
+    return ret;
+};
+
+exports.__wbg_next_5b3530e612fde77d = function(arg0) {
+    const ret = arg0.next;
+    return ret;
+};
+
+exports.__wbg_next_692e82279131b03c = function() { return handleError(function (arg0) {
+    const ret = arg0.next();
+    return ret;
+}, arguments) };
+
+exports.__wbg_prototypesetcall_3d4a26c1ed734349 = function(arg0, arg1, arg2) {
+    Uint8Array.prototype.set.call(getArrayU8FromWasm0(arg0, arg1), arg2);
+};
+
+exports.__wbg_push_330b2eb93e4e1212 = function(arg0, arg1) {
+    const ret = arg0.push(arg1);
+    return ret;
+};
+
+exports.__wbg_set_453345bcda80b89a = function() { return handleError(function (arg0, arg1, arg2) {
+    const ret = Reflect.set(arg0, arg1, arg2);
+    return ret;
+}, arguments) };
+
+exports.__wbg_value_dd9372230531eade = function(arg0) {
+    const ret = arg0.value;
+    return ret;
+};
+
+exports.__wbg_wbindgenbigintgetasi64_ac743ece6ab9bba1 = function(arg0, arg1) {
+    const v = arg1;
+    const ret = typeof(v) === 'bigint' ? v : undefined;
+    getDataViewMemory0().setBigInt64(arg0 + 8 * 1, isLikeNone(ret) ? BigInt(0) : ret, true);
+    getDataViewMemory0().setInt32(arg0 + 4 * 0, !isLikeNone(ret), true);
+};
+
+exports.__wbg_wbindgenbooleanget_3fe6f642c7d97746 = function(arg0) {
+    const v = arg0;
+    const ret = typeof(v) === 'boolean' ? v : undefined;
+    return isLikeNone(ret) ? 0xFFFFFF : ret ? 1 : 0;
+};
+
+exports.__wbg_wbindgendebugstring_99ef257a3ddda34d = function(arg0, arg1) {
+    const ret = debugString(arg1);
+    const ptr1 = passStringToWasm0(ret, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
+    const len1 = WASM_VECTOR_LEN;
+    getDataViewMemory0().setInt32(arg0 + 4 * 1, len1, true);
+    getDataViewMemory0().setInt32(arg0 + 4 * 0, ptr1, true);
+};
+
+exports.__wbg_wbindgenin_d7a1ee10933d2d55 = function(arg0, arg1) {
+    const ret = arg0 in arg1;
+    return ret;
+};
+
+exports.__wbg_wbindgenisbigint_ecb90cc08a5a9154 = function(arg0) {
+    const ret = typeof(arg0) === 'bigint';
+    return ret;
+};
+
+exports.__wbg_wbindgenisfunction_8cee7dce3725ae74 = function(arg0) {
+    const ret = typeof(arg0) === 'function';
+    return ret;
+};
+
+exports.__wbg_wbindgenisobject_307a53c6bd97fbf8 = function(arg0) {
+    const val = arg0;
+    const ret = typeof(val) === 'object' && val !== null;
+    return ret;
+};
+
+exports.__wbg_wbindgenjsvaleq_e6f2ad59ccae1b58 = function(arg0, arg1) {
+    const ret = arg0 === arg1;
+    return ret;
+};
+
+exports.__wbg_wbindgenjsvallooseeq_9bec8c9be826bed1 = function(arg0, arg1) {
+    const ret = arg0 == arg1;
+    return ret;
+};
+
+exports.__wbg_wbindgennumberget_f74b4c7525ac05cb = function(arg0, arg1) {
+    const obj = arg1;
+    const ret = typeof(obj) === 'number' ? obj : undefined;
+    getDataViewMemory0().setFloat64(arg0 + 8 * 1, isLikeNone(ret) ? 0 : ret, true);
+    getDataViewMemory0().setInt32(arg0 + 4 * 0, !isLikeNone(ret), true);
+};
+
+exports.__wbg_wbindgenstringget_0f16a6ddddef376f = function(arg0, arg1) {
+    const obj = arg1;
+    const ret = typeof(obj) === 'string' ? obj : undefined;
+    var ptr1 = isLikeNone(ret) ? 0 : passStringToWasm0(ret, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
+    var len1 = WASM_VECTOR_LEN;
+    getDataViewMemory0().setInt32(arg0 + 4 * 1, len1, true);
+    getDataViewMemory0().setInt32(arg0 + 4 * 0, ptr1, true);
+};
+
+exports.__wbg_wbindgenthrow_451ec1a8469d7eb6 = function(arg0, arg1) {
+    throw new Error(getStringFromWasm0(arg0, arg1));
+};
+
+exports.__wbindgen_cast_2241b6af4c4b2941 = function(arg0, arg1) {
+    // Cast intrinsic for `Ref(String) -> Externref`.
+    const ret = getStringFromWasm0(arg0, arg1);
+    return ret;
+};
+
+exports.__wbindgen_cast_4625c577ab2ec9ee = function(arg0) {
+    // Cast intrinsic for `U64 -> Externref`.
+    const ret = BigInt.asUintN(64, arg0);
+    return ret;
+};
+
+exports.__wbindgen_cast_9ae0607507abb057 = function(arg0) {
+    // Cast intrinsic for `I64 -> Externref`.
+    const ret = arg0;
+    return ret;
+};
+
+exports.__wbindgen_cast_d6cd19b81560fd6e = function(arg0) {
+    // Cast intrinsic for `F64 -> Externref`.
+    const ret = arg0;
+    return ret;
+};
+
+exports.__wbindgen_init_externref_table = function() {
+    const table = wasm.__wbindgen_export_4;
+    const offset = table.grow(4);
+    table.set(0, undefined);
+    table.set(offset + 0, undefined);
+    table.set(offset + 1, null);
+    table.set(offset + 2, true);
+    table.set(offset + 3, false);
+    ;
+};
+
+const wasmPath = `${__dirname}/lindera_wasm_bg.wasm`;
+const wasmBytes = require('fs').readFileSync(wasmPath);
+const wasmModule = new WebAssembly.Module(wasmBytes);
+const wasm = exports.__wasm = new WebAssembly.Instance(wasmModule, imports).exports;
+
+wasm.__wbindgen_start();
+

package/package.json

@@ -0,0 +1,25 @@
+{
+  "name": "lindera-wasm-nodejs-cc-cedict",
+  "description": "Lindera WASM with Chinese dictionary (CC-CEDICT) (nodejs target)",
+  "version": "1.2.1",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/lindera/lindera-wasm"
+  },
+  "files": [
+    "lindera_wasm_bg.wasm",
+    "lindera_wasm.js",
+    "lindera_wasm.d.ts"
+  ],
+  "main": "lindera_wasm.js",
+  "homepage": "https://github.com/lindera/lindera-wasm",
+  "types": "lindera_wasm.d.ts",
+  "keywords": [
+    "morphological",
+    "analysis",
+    "library",
+    "wasm",
+    "webassembly"
+  ]
+}