garu-ko 0.1.0

package/dist/index.d.ts

@@ -0,0 +1,62 @@
+export type POS = 'NNG' | 'NNP' | 'NNB' | 'NR' | 'NP' | 'VV' | 'VA' | 'VX' | 'VCP' | 'VCN' | 'MAG' | 'MAJ' | 'MM' | 'IC' | 'JKS' | 'JKC' | 'JKG' | 'JKO' | 'JKB' | 'JKV' | 'JKQ' | 'JX' | 'JC' | 'EP' | 'EF' | 'EC' | 'ETN' | 'ETM' | 'XPN' | 'XSN' | 'XSV' | 'XSA' | 'XR' | 'SF' | 'SP' | 'SS' | 'SE' | 'SO' | 'SW' | 'SH' | 'SL' | 'SN';
+export interface Token {
+    text: string;
+    pos: POS;
+    start: number;
+    end: number;
+    score?: number;
+}
+export interface AnalyzeResult {
+    tokens: Token[];
+    score: number;
+    elapsed: number;
+}
+export interface AnalyzeOptions {
+    topN?: number;
+}
+export interface LoadOptions {
+    modelData?: ArrayBuffer;
+    modelUrl?: string;
+}
+export interface ModelInfo {
+    version: string;
+    size: number;
+    accuracy: number;
+}
+export declare class Garu {
+    private _wasm;
+    private _loaded;
+    private _modelSize;
+    private constructor();
+    /**
+     * Load the WASM module and model data, returning a ready-to-use Garu instance.
+     *
+     * @param options.modelData - Provide model bytes directly as an ArrayBuffer
+     * @param options.modelUrl  - Fetch model from this URL
+     * If neither is provided, the model is fetched from the default CDN URL.
+     */
+    static load(options?: LoadOptions): Promise<Garu>;
+    /**
+     * Analyze Korean text, returning morphological tokens with scores.
+     *
+     * When `options.topN` is greater than 1, returns an array of N-best results.
+     * Otherwise returns a single AnalyzeResult.
+     */
+    analyze(text: string, options?: AnalyzeOptions): AnalyzeResult | AnalyzeResult[];
+    /**
+     * Quick tokenisation — returns an array of surface-form strings.
+     */
+    tokenize(text: string): string[];
+    /**
+     * Whether the WASM analyzer is loaded and ready.
+     */
+    isLoaded(): boolean;
+    /**
+     * Return metadata about the loaded model.
+     */
+    modelInfo(): ModelInfo;
+    /**
+     * Free the WASM instance and mark this Garu as unloaded.
+     */
+    destroy(): void;
+}

package/dist/index.js

@@ -0,0 +1,97 @@
+const DEFAULT_MODEL_URL = 'https://cdn.jsdelivr.net/npm/garu@latest/models/base.gmdl';
+const EMPTY_RESULT = Object.freeze({
+    tokens: [],
+    score: 0,
+    elapsed: 0,
+});
+export class Garu {
+    constructor(wasmInstance, modelSize) {
+        this._wasm = wasmInstance;
+        this._loaded = true;
+        this._modelSize = modelSize;
+    }
+    /**
+     * Load the WASM module and model data, returning a ready-to-use Garu instance.
+     *
+     * @param options.modelData - Provide model bytes directly as an ArrayBuffer
+     * @param options.modelUrl  - Fetch model from this URL
+     * If neither is provided, the model is fetched from the default CDN URL.
+     */
+    static async load(options) {
+        // Dynamic import of the WASM glue module and initialise it
+        // @ts-ignore dynamic WASM import
+        const wasmModule = await import('../pkg/garu_wasm.js');
+        await wasmModule.default();
+        // Resolve model bytes
+        let modelBytes;
+        if (options?.modelData) {
+            modelBytes = new Uint8Array(options.modelData);
+        }
+        else {
+            const url = options?.modelUrl ?? DEFAULT_MODEL_URL;
+            const response = await fetch(url);
+            if (!response.ok) {
+                throw new Error(`Failed to fetch model from ${url}: ${response.status} ${response.statusText}`);
+            }
+            const buffer = await response.arrayBuffer();
+            modelBytes = new Uint8Array(buffer);
+        }
+        // Construct the WASM analyzer
+        const wasmInstance = new wasmModule.GaruWasm(modelBytes);
+        return new Garu(wasmInstance, modelBytes.byteLength);
+    }
+    /**
+     * Analyze Korean text, returning morphological tokens with scores.
+     *
+     * When `options.topN` is greater than 1, returns an array of N-best results.
+     * Otherwise returns a single AnalyzeResult.
+     */
+    analyze(text, options) {
+        const topN = options?.topN ?? 1;
+        if (topN > 1) {
+            if (text === '') {
+                return [{ ...EMPTY_RESULT, tokens: [] }];
+            }
+            return this._wasm.analyze_topn(text, topN);
+        }
+        if (text === '') {
+            return { ...EMPTY_RESULT, tokens: [] };
+        }
+        return this._wasm.analyze(text);
+    }
+    /**
+     * Quick tokenisation — returns an array of surface-form strings.
+     */
+    tokenize(text) {
+        if (text === '') {
+            return [];
+        }
+        return this._wasm.tokenize(text);
+    }
+    /**
+     * Whether the WASM analyzer is loaded and ready.
+     */
+    isLoaded() {
+        return this._loaded;
+    }
+    /**
+     * Return metadata about the loaded model.
+     */
+    modelInfo() {
+        return {
+            version: this._wasm.constructor.version(),
+            size: this._modelSize,
+            accuracy: 0.8,
+        };
+    }
+    /**
+     * Free the WASM instance and mark this Garu as unloaded.
+     */
+    destroy() {
+        if (this._wasm) {
+            this._wasm.free();
+            this._wasm = null;
+        }
+        this._loaded = false;
+    }
+}

package/package.json

@@ -0,0 +1,26 @@
+{
+  "name": "garu-ko",
+  "version": "0.1.0",
+  "description": "Ultra-lightweight Korean morphological analyzer for the web (2.2MB model, WASM 93KB, F1 95.3%)",
+  "type": "module",
+  "main": "dist/index.js",
+  "types": "dist/index.d.ts",
+  "files": ["dist", "pkg", "models"],
+  "scripts": {
+    "build:wasm": "wasm-pack build ../crates/garu-wasm --target web --out-dir ../../js/pkg",
+    "build:js": "tsc",
+    "build": "npm run build:wasm && npm run build:js",
+    "test": "vitest run"
+  },
+  "keywords": ["korean", "morphological-analysis", "nlp", "wasm", "lightweight", "browser"],
+  "author": "cyj <dydwls140@naver.com>",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/ongjin/garu.git"
+  },
+  "license": "MIT",
+  "devDependencies": {
+    "typescript": "^5.4",
+    "vitest": "^2.0"
+  }
+}

package/pkg/garu_wasm.d.ts

@@ -0,0 +1,52 @@
+/* tslint:disable */
+/* eslint-disable */
+
+export class GaruWasm {
+    free(): void;
+    [Symbol.dispose](): void;
+    analyze(text: string): any;
+    analyze_topn(text: string, n: number): any;
+    constructor(model_data: Uint8Array);
+    tokenize(text: string): any;
+    static version(): string;
+}
+
+export type InitInput = RequestInfo | URL | Response | BufferSource | WebAssembly.Module;
+
+export interface InitOutput {
+    readonly memory: WebAssembly.Memory;
+    readonly __wbg_garuwasm_free: (a: number, b: number) => void;
+    readonly garuwasm_analyze: (a: number, b: number, c: number) => [number, number, number];
+    readonly garuwasm_analyze_topn: (a: number, b: number, c: number, d: number) => [number, number, number];
+    readonly garuwasm_new: (a: number, b: number) => [number, number, number];
+    readonly garuwasm_tokenize: (a: number, b: number, c: number) => [number, number, number];
+    readonly garuwasm_version: () => [number, number];
+    readonly __wbindgen_malloc: (a: number, b: number) => number;
+    readonly __wbindgen_realloc: (a: number, b: number, c: number, d: number) => number;
+    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`.
+ *
+ * @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>;

package/pkg/garu_wasm.js

@@ -0,0 +1,343 @@
+/* @ts-self-types="./garu_wasm.d.ts" */
+
+export class GaruWasm {
+    __destroy_into_raw() {
+        const ptr = this.__wbg_ptr;
+        this.__wbg_ptr = 0;
+        GaruWasmFinalization.unregister(this);
+        return ptr;
+    }
+    free() {
+        const ptr = this.__destroy_into_raw();
+        wasm.__wbg_garuwasm_free(ptr, 0);
+    }
+    /**
+     * @param {string} text
+     * @returns {any}
+     */
+    analyze(text) {
+        const ptr0 = passStringToWasm0(text, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
+        const len0 = WASM_VECTOR_LEN;
+        const ret = wasm.garuwasm_analyze(this.__wbg_ptr, ptr0, len0);
+        if (ret[2]) {
+            throw takeFromExternrefTable0(ret[1]);
+        }
+        return takeFromExternrefTable0(ret[0]);
+    }
+    /**
+     * @param {string} text
+     * @param {number} n
+     * @returns {any}
+     */
+    analyze_topn(text, n) {
+        const ptr0 = passStringToWasm0(text, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
+        const len0 = WASM_VECTOR_LEN;
+        const ret = wasm.garuwasm_analyze_topn(this.__wbg_ptr, ptr0, len0, n);
+        if (ret[2]) {
+            throw takeFromExternrefTable0(ret[1]);
+        }
+        return takeFromExternrefTable0(ret[0]);
+    }
+    /**
+     * @param {Uint8Array} model_data
+     */
+    constructor(model_data) {
+        const ptr0 = passArray8ToWasm0(model_data, wasm.__wbindgen_malloc);
+        const len0 = WASM_VECTOR_LEN;
+        const ret = wasm.garuwasm_new(ptr0, len0);
+        if (ret[2]) {
+            throw takeFromExternrefTable0(ret[1]);
+        }
+        this.__wbg_ptr = ret[0] >>> 0;
+        GaruWasmFinalization.register(this, this.__wbg_ptr, this);
+        return this;
+    }
+    /**
+     * @param {string} text
+     * @returns {any}
+     */
+    tokenize(text) {
+        const ptr0 = passStringToWasm0(text, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
+        const len0 = WASM_VECTOR_LEN;
+        const ret = wasm.garuwasm_tokenize(this.__wbg_ptr, ptr0, len0);
+        if (ret[2]) {
+            throw takeFromExternrefTable0(ret[1]);
+        }
+        return takeFromExternrefTable0(ret[0]);
+    }
+    /**
+     * @returns {string}
+     */
+    static version() {
+        let deferred1_0;
+        let deferred1_1;
+        try {
+            const ret = wasm.garuwasm_version();
+            deferred1_0 = ret[0];
+            deferred1_1 = ret[1];
+            return getStringFromWasm0(ret[0], ret[1]);
+        } finally {
+            wasm.__wbindgen_free(deferred1_0, deferred1_1, 1);
+        }
+    }
+}
+if (Symbol.dispose) GaruWasm.prototype[Symbol.dispose] = GaruWasm.prototype.free;
+
+function __wbg_get_imports() {
+    const import0 = {
+        __proto__: null,
+        __wbg_Error_83742b46f01ce22d: function(arg0, arg1) {
+            const ret = Error(getStringFromWasm0(arg0, arg1));
+            return ret;
+        },
+        __wbg_String_8564e559799eccda: 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);
+        },
+        __wbg___wbindgen_throw_6ddd609b62940d55: function(arg0, arg1) {
+            throw new Error(getStringFromWasm0(arg0, arg1));
+        },
+        __wbg_new_a70fbab9066b301f: function() {
+            const ret = new Array();
+            return ret;
+        },
+        __wbg_new_ab79df5bd7c26067: function() {
+            const ret = new Object();
+            return ret;
+        },
+        __wbg_set_282384002438957f: function(arg0, arg1, arg2) {
+            arg0[arg1 >>> 0] = arg2;
+        },
+        __wbg_set_6be42768c690e380: function(arg0, arg1, arg2) {
+            arg0[arg1] = arg2;
+        },
+        __wbindgen_cast_0000000000000001: function(arg0) {
+            // Cast intrinsic for `F64 -> Externref`.
+            const ret = arg0;
+            return ret;
+        },
+        __wbindgen_cast_0000000000000002: function(arg0, arg1) {
+            // Cast intrinsic for `Ref(String) -> Externref`.
+            const ret = getStringFromWasm0(arg0, arg1);
+            return ret;
+        },
+        __wbindgen_cast_0000000000000003: function(arg0) {
+            // Cast intrinsic for `U64 -> Externref`.
+            const ret = BigInt.asUintN(64, arg0);
+            return ret;
+        },
+        __wbindgen_init_externref_table: function() {
+            const table = wasm.__wbindgen_externrefs;
+            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);
+        },
+    };
+    return {
+        __proto__: null,
+        "./garu_wasm_bg.js": import0,
+    };
+}
+
+const GaruWasmFinalization = (typeof FinalizationRegistry === 'undefined')
+    ? { register: () => {}, unregister: () => {} }
+    : new FinalizationRegistry(ptr => wasm.__wbg_garuwasm_free(ptr >>> 0, 1));
+
+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 getStringFromWasm0(ptr, len) {
+    ptr = ptr >>> 0;
+    return decodeText(ptr, len);
+}
+
+let cachedUint8ArrayMemory0 = null;
+function getUint8ArrayMemory0() {
+    if (cachedUint8ArrayMemory0 === null || cachedUint8ArrayMemory0.byteLength === 0) {
+        cachedUint8ArrayMemory0 = new Uint8Array(wasm.memory.buffer);
+    }
+    return cachedUint8ArrayMemory0;
+}
+
+function passArray8ToWasm0(arg, malloc) {
+    const ptr = malloc(arg.length * 1, 1) >>> 0;
+    getUint8ArrayMemory0().set(arg, ptr / 1);
+    WASM_VECTOR_LEN = arg.length;
+    return ptr;
+}
+
+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;
+}
+
+function takeFromExternrefTable0(idx) {
+    const value = wasm.__wbindgen_externrefs.get(idx);
+    wasm.__externref_table_dealloc(idx);
+    return value;
+}
+
+let cachedTextDecoder = new TextDecoder('utf-8', { ignoreBOM: true, fatal: true });
+cachedTextDecoder.decode();
+const MAX_SAFARI_DECODE_BYTES = 2146435072;
+let numBytesDecoded = 0;
+function decodeText(ptr, len) {
+    numBytesDecoded += len;
+    if (numBytesDecoded >= MAX_SAFARI_DECODE_BYTES) {
+        cachedTextDecoder = new TextDecoder('utf-8', { ignoreBOM: true, fatal: true });
+        cachedTextDecoder.decode();
+        numBytesDecoded = len;
+    }
+    return cachedTextDecoder.decode(getUint8ArrayMemory0().subarray(ptr, ptr + len));
+}
+
+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
+        };
+    };
+}
+
+let WASM_VECTOR_LEN = 0;
+
+let wasmModule, wasm;
+function __wbg_finalize_init(instance, module) {
+    wasm = instance.exports;
+    wasmModule = module;
+    cachedDataViewMemory0 = null;
+    cachedUint8ArrayMemory0 = null;
+    wasm.__wbindgen_start();
+    return wasm;
+}
+
+async function __wbg_load(module, imports) {
+    if (typeof Response === 'function' && module instanceof Response) {
+        if (typeof WebAssembly.instantiateStreaming === 'function') {
+            try {
+                return await WebAssembly.instantiateStreaming(module, imports);
+            } catch (e) {
+                const validResponse = module.ok && expectedResponseType(module.type);
+
+                if (validResponse && module.headers.get('Content-Type') !== 'application/wasm') {
+                    console.warn("`WebAssembly.instantiateStreaming` failed because your server does not serve Wasm with `application/wasm` MIME type. Falling back to `WebAssembly.instantiate` which is slower. Original error:\n", e);
+
+                } else { throw e; }
+            }
+        }
+
+        const bytes = await module.arrayBuffer();
+        return await WebAssembly.instantiate(bytes, imports);
+    } else {
+        const instance = await WebAssembly.instantiate(module, imports);
+
+        if (instance instanceof WebAssembly.Instance) {
+            return { instance, module };
+        } else {
+            return instance;
+        }
+    }
+
+    function expectedResponseType(type) {
+        switch (type) {
+            case 'basic': case 'cors': case 'default': return true;
+        }
+        return false;
+    }
+}
+
+function initSync(module) {
+    if (wasm !== undefined) return wasm;
+
+
+    if (module !== undefined) {
+        if (Object.getPrototypeOf(module) === Object.prototype) {
+            ({module} = module)
+        } else {
+            console.warn('using deprecated parameters for `initSync()`; pass a single object instead')
+        }
+    }
+
+    const imports = __wbg_get_imports();
+    if (!(module instanceof WebAssembly.Module)) {
+        module = new WebAssembly.Module(module);
+    }
+    const instance = new WebAssembly.Instance(module, imports);
+    return __wbg_finalize_init(instance, module);
+}
+
+async function __wbg_init(module_or_path) {
+    if (wasm !== undefined) return wasm;
+
+
+    if (module_or_path !== undefined) {
+        if (Object.getPrototypeOf(module_or_path) === Object.prototype) {
+            ({module_or_path} = module_or_path)
+        } else {
+            console.warn('using deprecated parameters for the initialization function; pass a single object instead')
+        }
+    }
+
+    if (module_or_path === undefined) {
+        module_or_path = new URL('garu_wasm_bg.wasm', import.meta.url);
+    }
+    const imports = __wbg_get_imports();
+
+    if (typeof module_or_path === 'string' || (typeof Request === 'function' && module_or_path instanceof Request) || (typeof URL === 'function' && module_or_path instanceof URL)) {
+        module_or_path = fetch(module_or_path);
+    }
+
+    const { instance, module } = await __wbg_load(await module_or_path, imports);
+
+    return __wbg_finalize_init(instance, module);
+}
+
+export { initSync, __wbg_init as default };

package/pkg/garu_wasm_bg.wasm.d.ts

@@ -0,0 +1,15 @@
+/* tslint:disable */
+/* eslint-disable */
+export const memory: WebAssembly.Memory;
+export const __wbg_garuwasm_free: (a: number, b: number) => void;
+export const garuwasm_analyze: (a: number, b: number, c: number) => [number, number, number];
+export const garuwasm_analyze_topn: (a: number, b: number, c: number, d: number) => [number, number, number];
+export const garuwasm_new: (a: number, b: number) => [number, number, number];
+export const garuwasm_tokenize: (a: number, b: number, c: number) => [number, number, number];
+export const garuwasm_version: () => [number, number];
+export const __wbindgen_malloc: (a: number, b: number) => number;
+export const __wbindgen_realloc: (a: number, b: number, c: number, d: number) => number;
+export const __wbindgen_externrefs: WebAssembly.Table;
+export const __externref_table_dealloc: (a: number) => void;
+export const __wbindgen_free: (a: number, b: number, c: number) => void;
+export const __wbindgen_start: () => void;