Fix tokenizer jieba tag flow and debug logging
This commit is contained in:
438
libs/jieba-wasm/jieba_rs_wasm.js
Normal file
438
libs/jieba-wasm/jieba_rs_wasm.js
Normal file
@@ -0,0 +1,438 @@
|
||||
let wasm;
|
||||
|
||||
let cachedUint8ArrayMemory0 = null;
|
||||
|
||||
function getUint8ArrayMemory0() {
|
||||
if (cachedUint8ArrayMemory0 === null || cachedUint8ArrayMemory0.byteLength === 0) {
|
||||
cachedUint8ArrayMemory0 = new Uint8Array(wasm.memory.buffer);
|
||||
}
|
||||
return cachedUint8ArrayMemory0;
|
||||
}
|
||||
|
||||
let cachedTextDecoder = (typeof TextDecoder !== 'undefined' ? new TextDecoder('utf-8', { ignoreBOM: true, fatal: true }) : { decode: () => { throw Error('TextDecoder not available') } } );
|
||||
|
||||
if (typeof TextDecoder !== 'undefined') { cachedTextDecoder.decode(); };
|
||||
|
||||
const MAX_SAFARI_DECODE_BYTES = 2146435072;
|
||||
let numBytesDecoded = 0;
|
||||
function decodeText(ptr, len) {
|
||||
numBytesDecoded += len;
|
||||
if (numBytesDecoded >= MAX_SAFARI_DECODE_BYTES) {
|
||||
cachedTextDecoder = (typeof TextDecoder !== 'undefined' ? new TextDecoder('utf-8', { ignoreBOM: true, fatal: true }) : { decode: () => { throw Error('TextDecoder not available') } } );
|
||||
cachedTextDecoder.decode();
|
||||
numBytesDecoded = len;
|
||||
}
|
||||
return cachedTextDecoder.decode(getUint8ArrayMemory0().subarray(ptr, ptr + len));
|
||||
}
|
||||
|
||||
function getStringFromWasm0(ptr, len) {
|
||||
ptr = ptr >>> 0;
|
||||
return decodeText(ptr, len);
|
||||
}
|
||||
|
||||
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;
|
||||
}
|
||||
|
||||
let WASM_VECTOR_LEN = 0;
|
||||
|
||||
const cachedTextEncoder = (typeof TextEncoder !== 'undefined' ? new TextEncoder('utf-8') : { encode: () => { throw Error('TextEncoder not available') } } );
|
||||
|
||||
const encodeString = (typeof cachedTextEncoder.encodeInto === 'function'
|
||||
? function (arg, view) {
|
||||
return cachedTextEncoder.encodeInto(arg, view);
|
||||
}
|
||||
: 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 = encodeString(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 isLikeNone(x) {
|
||||
return x === undefined || x === null;
|
||||
}
|
||||
|
||||
function getArrayJsValueFromWasm0(ptr, len) {
|
||||
ptr = ptr >>> 0;
|
||||
const mem = getDataViewMemory0();
|
||||
const result = [];
|
||||
for (let i = ptr; i < ptr + 4 * len; i += 4) {
|
||||
result.push(wasm.__wbindgen_export_2.get(mem.getUint32(i, true)));
|
||||
}
|
||||
wasm.__externref_drop_slice(ptr, len);
|
||||
return result;
|
||||
}
|
||||
/**
|
||||
* @param {string} text
|
||||
* @param {boolean | null} [hmm]
|
||||
* @returns {string[]}
|
||||
*/
|
||||
export function cut(text, hmm) {
|
||||
const ptr0 = passStringToWasm0(text, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
|
||||
const len0 = WASM_VECTOR_LEN;
|
||||
const ret = wasm.cut(ptr0, len0, isLikeNone(hmm) ? 0xFFFFFF : hmm ? 1 : 0);
|
||||
var v2 = getArrayJsValueFromWasm0(ret[0], ret[1]).slice();
|
||||
wasm.__wbindgen_free(ret[0], ret[1] * 4, 4);
|
||||
return v2;
|
||||
}
|
||||
|
||||
/**
|
||||
* @param {string} text
|
||||
* @returns {string[]}
|
||||
*/
|
||||
export function cut_all(text) {
|
||||
const ptr0 = passStringToWasm0(text, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
|
||||
const len0 = WASM_VECTOR_LEN;
|
||||
const ret = wasm.cut_all(ptr0, len0);
|
||||
var v2 = getArrayJsValueFromWasm0(ret[0], ret[1]).slice();
|
||||
wasm.__wbindgen_free(ret[0], ret[1] * 4, 4);
|
||||
return v2;
|
||||
}
|
||||
|
||||
/**
|
||||
* @param {string} text
|
||||
* @param {boolean | null} [hmm]
|
||||
* @returns {string[]}
|
||||
*/
|
||||
export function cut_for_search(text, hmm) {
|
||||
const ptr0 = passStringToWasm0(text, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
|
||||
const len0 = WASM_VECTOR_LEN;
|
||||
const ret = wasm.cut_for_search(ptr0, len0, isLikeNone(hmm) ? 0xFFFFFF : hmm ? 1 : 0);
|
||||
var v2 = getArrayJsValueFromWasm0(ret[0], ret[1]).slice();
|
||||
wasm.__wbindgen_free(ret[0], ret[1] * 4, 4);
|
||||
return v2;
|
||||
}
|
||||
|
||||
function takeFromExternrefTable0(idx) {
|
||||
const value = wasm.__wbindgen_export_2.get(idx);
|
||||
wasm.__externref_table_dealloc(idx);
|
||||
return value;
|
||||
}
|
||||
/**
|
||||
* @param {string} text
|
||||
* @param {string} mode
|
||||
* @param {boolean | null} [hmm]
|
||||
* @returns {Token[]}
|
||||
*/
|
||||
export function tokenize(text, mode, hmm) {
|
||||
const ptr0 = passStringToWasm0(text, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
|
||||
const len0 = WASM_VECTOR_LEN;
|
||||
const ptr1 = passStringToWasm0(mode, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
|
||||
const len1 = WASM_VECTOR_LEN;
|
||||
const ret = wasm.tokenize(ptr0, len0, ptr1, len1, isLikeNone(hmm) ? 0xFFFFFF : hmm ? 1 : 0);
|
||||
if (ret[3]) {
|
||||
throw takeFromExternrefTable0(ret[2]);
|
||||
}
|
||||
var v3 = getArrayJsValueFromWasm0(ret[0], ret[1]).slice();
|
||||
wasm.__wbindgen_free(ret[0], ret[1] * 4, 4);
|
||||
return v3;
|
||||
}
|
||||
|
||||
/**
|
||||
* @param {string} word
|
||||
* @param {number | null} [freq]
|
||||
* @param {string | null} [tag]
|
||||
* @returns {number}
|
||||
*/
|
||||
export function add_word(word, freq, tag) {
|
||||
const ptr0 = passStringToWasm0(word, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
|
||||
const len0 = WASM_VECTOR_LEN;
|
||||
var ptr1 = isLikeNone(tag) ? 0 : passStringToWasm0(tag, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
|
||||
var len1 = WASM_VECTOR_LEN;
|
||||
const ret = wasm.add_word(ptr0, len0, isLikeNone(freq) ? 0x100000001 : (freq) >>> 0, ptr1, len1);
|
||||
return ret >>> 0;
|
||||
}
|
||||
|
||||
/**
|
||||
* @param {string} sentence
|
||||
* @param {boolean | null} [hmm]
|
||||
* @returns {Tag[]}
|
||||
*/
|
||||
export function tag(sentence, hmm) {
|
||||
const ptr0 = passStringToWasm0(sentence, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
|
||||
const len0 = WASM_VECTOR_LEN;
|
||||
const ret = wasm.tag(ptr0, len0, isLikeNone(hmm) ? 0xFFFFFF : hmm ? 1 : 0);
|
||||
var v2 = getArrayJsValueFromWasm0(ret[0], ret[1]).slice();
|
||||
wasm.__wbindgen_free(ret[0], ret[1] * 4, 4);
|
||||
return v2;
|
||||
}
|
||||
|
||||
/**
|
||||
* @param {string} dict
|
||||
*/
|
||||
export function with_dict(dict) {
|
||||
const ptr0 = passStringToWasm0(dict, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
|
||||
const len0 = WASM_VECTOR_LEN;
|
||||
const ret = wasm.with_dict(ptr0, len0);
|
||||
if (ret[1]) {
|
||||
throw takeFromExternrefTable0(ret[0]);
|
||||
}
|
||||
}
|
||||
|
||||
const EXPECTED_RESPONSE_TYPES = new Set(['basic', 'cors', 'default']);
|
||||
|
||||
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 && EXPECTED_RESPONSE_TYPES.has(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 __wbg_get_imports() {
|
||||
const imports = {};
|
||||
imports.wbg = {};
|
||||
imports.wbg.__wbg_Error_0497d5bdba9362e5 = function(arg0, arg1) {
|
||||
const ret = Error(getStringFromWasm0(arg0, arg1));
|
||||
return ret;
|
||||
};
|
||||
imports.wbg.__wbg_new_07b483f72211fd66 = function() {
|
||||
const ret = new Object();
|
||||
return ret;
|
||||
};
|
||||
imports.wbg.__wbg_set_3f1d0b984ed272ed = function(arg0, arg1, arg2) {
|
||||
arg0[arg1] = arg2;
|
||||
};
|
||||
imports.wbg.__wbindgen_bigint_from_u64 = function(arg0) {
|
||||
const ret = BigInt.asUintN(64, arg0);
|
||||
return ret;
|
||||
};
|
||||
imports.wbg.__wbindgen_debug_string = 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);
|
||||
};
|
||||
imports.wbg.__wbindgen_init_externref_table = function() {
|
||||
const table = wasm.__wbindgen_export_2;
|
||||
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);
|
||||
;
|
||||
};
|
||||
imports.wbg.__wbindgen_number_new = function(arg0) {
|
||||
const ret = arg0;
|
||||
return ret;
|
||||
};
|
||||
imports.wbg.__wbindgen_string_new = function(arg0, arg1) {
|
||||
const ret = getStringFromWasm0(arg0, arg1);
|
||||
return ret;
|
||||
};
|
||||
imports.wbg.__wbindgen_throw = function(arg0, arg1) {
|
||||
throw new Error(getStringFromWasm0(arg0, arg1));
|
||||
};
|
||||
|
||||
return imports;
|
||||
}
|
||||
|
||||
function __wbg_init_memory(imports, memory) {
|
||||
|
||||
}
|
||||
|
||||
function __wbg_finalize_init(instance, module) {
|
||||
wasm = instance.exports;
|
||||
__wbg_init.__wbindgen_wasm_module = module;
|
||||
cachedDataViewMemory0 = null;
|
||||
cachedUint8ArrayMemory0 = null;
|
||||
|
||||
|
||||
wasm.__wbindgen_start();
|
||||
return wasm;
|
||||
}
|
||||
|
||||
function initSync(module) {
|
||||
if (wasm !== undefined) return wasm;
|
||||
|
||||
|
||||
if (typeof 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();
|
||||
|
||||
__wbg_init_memory(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 (typeof 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 (typeof module_or_path === 'undefined') {
|
||||
module_or_path = new URL('jieba_rs_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);
|
||||
}
|
||||
|
||||
__wbg_init_memory(imports);
|
||||
|
||||
const { instance, module } = await __wbg_load(await module_or_path, imports);
|
||||
|
||||
return __wbg_finalize_init(instance, module);
|
||||
}
|
||||
|
||||
export { initSync };
|
||||
export default __wbg_init;
|
||||
372
libs/jieba-wasm/jieba_rs_wasm_bg.js
Normal file
372
libs/jieba-wasm/jieba_rs_wasm_bg.js
Normal file
@@ -0,0 +1,372 @@
|
||||
let wasm;
|
||||
export function __wbg_set_wasm(val) {
|
||||
wasm = val;
|
||||
}
|
||||
|
||||
|
||||
const heap = new Array(128).fill(undefined);
|
||||
|
||||
heap.push(undefined, null, true, false);
|
||||
|
||||
function getObject(idx) { return heap[idx]; }
|
||||
|
||||
let heap_next = heap.length;
|
||||
|
||||
function dropObject(idx) {
|
||||
if (idx < 132) return;
|
||||
heap[idx] = heap_next;
|
||||
heap_next = idx;
|
||||
}
|
||||
|
||||
function takeObject(idx) {
|
||||
const ret = getObject(idx);
|
||||
dropObject(idx);
|
||||
return ret;
|
||||
}
|
||||
|
||||
const lTextDecoder = typeof TextDecoder === 'undefined' ? (0, module.require)('util').TextDecoder : TextDecoder;
|
||||
|
||||
let cachedTextDecoder = new lTextDecoder('utf-8', { ignoreBOM: true, fatal: true });
|
||||
|
||||
cachedTextDecoder.decode();
|
||||
|
||||
let cachedUint8ArrayMemory0 = null;
|
||||
|
||||
function getUint8ArrayMemory0() {
|
||||
if (cachedUint8ArrayMemory0 === null || cachedUint8ArrayMemory0.byteLength === 0) {
|
||||
cachedUint8ArrayMemory0 = new Uint8Array(wasm.memory.buffer);
|
||||
}
|
||||
return cachedUint8ArrayMemory0;
|
||||
}
|
||||
|
||||
function getStringFromWasm0(ptr, len) {
|
||||
ptr = ptr >>> 0;
|
||||
return cachedTextDecoder.decode(getUint8ArrayMemory0().subarray(ptr, ptr + len));
|
||||
}
|
||||
|
||||
function addHeapObject(obj) {
|
||||
if (heap_next === heap.length) heap.push(heap.length + 1);
|
||||
const idx = heap_next;
|
||||
heap_next = heap[idx];
|
||||
|
||||
heap[idx] = obj;
|
||||
return idx;
|
||||
}
|
||||
|
||||
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.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;
|
||||
}
|
||||
|
||||
let WASM_VECTOR_LEN = 0;
|
||||
|
||||
const lTextEncoder = typeof TextEncoder === 'undefined' ? (0, module.require)('util').TextEncoder : TextEncoder;
|
||||
|
||||
let cachedTextEncoder = new lTextEncoder('utf-8');
|
||||
|
||||
const encodeString = (typeof cachedTextEncoder.encodeInto === 'function'
|
||||
? function (arg, view) {
|
||||
return cachedTextEncoder.encodeInto(arg, view);
|
||||
}
|
||||
: 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 = encodeString(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 isLikeNone(x) {
|
||||
return x === undefined || x === null;
|
||||
}
|
||||
|
||||
function getArrayJsValueFromWasm0(ptr, len) {
|
||||
ptr = ptr >>> 0;
|
||||
const mem = getDataViewMemory0();
|
||||
const result = [];
|
||||
for (let i = ptr; i < ptr + 4 * len; i += 4) {
|
||||
result.push(takeObject(mem.getUint32(i, true)));
|
||||
}
|
||||
return result;
|
||||
}
|
||||
/**
|
||||
* @param {string} text
|
||||
* @param {boolean | undefined} [hmm]
|
||||
* @returns {any[]}
|
||||
*/
|
||||
export function cut(text, hmm) {
|
||||
try {
|
||||
const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
|
||||
const ptr0 = passStringToWasm0(text, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
|
||||
const len0 = WASM_VECTOR_LEN;
|
||||
wasm.cut(retptr, ptr0, len0, isLikeNone(hmm) ? 0xFFFFFF : hmm ? 1 : 0);
|
||||
var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
|
||||
var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
|
||||
var v2 = getArrayJsValueFromWasm0(r0, r1).slice();
|
||||
wasm.__wbindgen_free(r0, r1 * 4, 4);
|
||||
return v2;
|
||||
} finally {
|
||||
wasm.__wbindgen_add_to_stack_pointer(16);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* @param {string} text
|
||||
* @returns {any[]}
|
||||
*/
|
||||
export function cut_all(text) {
|
||||
try {
|
||||
const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
|
||||
const ptr0 = passStringToWasm0(text, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
|
||||
const len0 = WASM_VECTOR_LEN;
|
||||
wasm.cut_all(retptr, ptr0, len0);
|
||||
var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
|
||||
var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
|
||||
var v2 = getArrayJsValueFromWasm0(r0, r1).slice();
|
||||
wasm.__wbindgen_free(r0, r1 * 4, 4);
|
||||
return v2;
|
||||
} finally {
|
||||
wasm.__wbindgen_add_to_stack_pointer(16);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* @param {string} text
|
||||
* @param {boolean | undefined} [hmm]
|
||||
* @returns {any[]}
|
||||
*/
|
||||
export function cut_for_search(text, hmm) {
|
||||
try {
|
||||
const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
|
||||
const ptr0 = passStringToWasm0(text, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
|
||||
const len0 = WASM_VECTOR_LEN;
|
||||
wasm.cut_for_search(retptr, ptr0, len0, isLikeNone(hmm) ? 0xFFFFFF : hmm ? 1 : 0);
|
||||
var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
|
||||
var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
|
||||
var v2 = getArrayJsValueFromWasm0(r0, r1).slice();
|
||||
wasm.__wbindgen_free(r0, r1 * 4, 4);
|
||||
return v2;
|
||||
} finally {
|
||||
wasm.__wbindgen_add_to_stack_pointer(16);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* @param {string} text
|
||||
* @param {string} mode
|
||||
* @param {boolean | undefined} [hmm]
|
||||
* @returns {any[]}
|
||||
*/
|
||||
export function tokenize(text, mode, hmm) {
|
||||
try {
|
||||
const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
|
||||
const ptr0 = passStringToWasm0(text, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
|
||||
const len0 = WASM_VECTOR_LEN;
|
||||
const ptr1 = passStringToWasm0(mode, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
|
||||
const len1 = WASM_VECTOR_LEN;
|
||||
wasm.tokenize(retptr, ptr0, len0, ptr1, len1, isLikeNone(hmm) ? 0xFFFFFF : hmm ? 1 : 0);
|
||||
var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
|
||||
var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
|
||||
var r2 = getDataViewMemory0().getInt32(retptr + 4 * 2, true);
|
||||
var r3 = getDataViewMemory0().getInt32(retptr + 4 * 3, true);
|
||||
if (r3) {
|
||||
throw takeObject(r2);
|
||||
}
|
||||
var v3 = getArrayJsValueFromWasm0(r0, r1).slice();
|
||||
wasm.__wbindgen_free(r0, r1 * 4, 4);
|
||||
return v3;
|
||||
} finally {
|
||||
wasm.__wbindgen_add_to_stack_pointer(16);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* @param {string} word
|
||||
* @param {number | undefined} [freq]
|
||||
* @param {string | undefined} [tag]
|
||||
* @returns {number}
|
||||
*/
|
||||
export function add_word(word, freq, tag) {
|
||||
const ptr0 = passStringToWasm0(word, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
|
||||
const len0 = WASM_VECTOR_LEN;
|
||||
var ptr1 = isLikeNone(tag) ? 0 : passStringToWasm0(tag, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
|
||||
var len1 = WASM_VECTOR_LEN;
|
||||
const ret = wasm.add_word(ptr0, len0, !isLikeNone(freq), isLikeNone(freq) ? 0 : freq, ptr1, len1);
|
||||
return ret >>> 0;
|
||||
}
|
||||
|
||||
/**
|
||||
* @param {string} sentence
|
||||
* @param {boolean | undefined} [hmm]
|
||||
* @returns {any[]}
|
||||
*/
|
||||
export function tag(sentence, hmm) {
|
||||
try {
|
||||
const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
|
||||
const ptr0 = passStringToWasm0(sentence, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
|
||||
const len0 = WASM_VECTOR_LEN;
|
||||
wasm.tag(retptr, ptr0, len0, isLikeNone(hmm) ? 0xFFFFFF : hmm ? 1 : 0);
|
||||
var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
|
||||
var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
|
||||
var v2 = getArrayJsValueFromWasm0(r0, r1).slice();
|
||||
wasm.__wbindgen_free(r0, r1 * 4, 4);
|
||||
return v2;
|
||||
} finally {
|
||||
wasm.__wbindgen_add_to_stack_pointer(16);
|
||||
}
|
||||
}
|
||||
|
||||
export function __wbindgen_object_drop_ref(arg0) {
|
||||
takeObject(arg0);
|
||||
};
|
||||
|
||||
export function __wbindgen_string_new(arg0, arg1) {
|
||||
const ret = getStringFromWasm0(arg0, arg1);
|
||||
return addHeapObject(ret);
|
||||
};
|
||||
|
||||
export function __wbindgen_object_clone_ref(arg0) {
|
||||
const ret = getObject(arg0);
|
||||
return addHeapObject(ret);
|
||||
};
|
||||
|
||||
export function __wbg_new_1e7c00339420672b() {
|
||||
const ret = new Object();
|
||||
return addHeapObject(ret);
|
||||
};
|
||||
|
||||
export function __wbindgen_number_new(arg0) {
|
||||
const ret = arg0;
|
||||
return addHeapObject(ret);
|
||||
};
|
||||
|
||||
export function __wbg_set_1754fb90457a8cce(arg0, arg1, arg2) {
|
||||
getObject(arg0)[takeObject(arg1)] = takeObject(arg2);
|
||||
};
|
||||
|
||||
export function __wbg_new_b44ab9ef6060dd36(arg0, arg1) {
|
||||
const ret = new Error(getStringFromWasm0(arg0, arg1));
|
||||
return addHeapObject(ret);
|
||||
};
|
||||
|
||||
export function __wbindgen_debug_string(arg0, arg1) {
|
||||
const ret = debugString(getObject(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);
|
||||
};
|
||||
|
||||
export function __wbindgen_throw(arg0, arg1) {
|
||||
throw new Error(getStringFromWasm0(arg0, arg1));
|
||||
};
|
||||
|
||||
BIN
libs/jieba-wasm/jieba_rs_wasm_bg.wasm
Normal file
BIN
libs/jieba-wasm/jieba_rs_wasm_bg.wasm
Normal file
Binary file not shown.
25
libs/jieba-wasm/jieba_rs_wasm_bg.wasm.d.ts
vendored
Normal file
25
libs/jieba-wasm/jieba_rs_wasm_bg.wasm.d.ts
vendored
Normal file
@@ -0,0 +1,25 @@
|
||||
/* tslint:disable */
|
||||
/* eslint-disable */
|
||||
export const memory: WebAssembly.Memory;
|
||||
export const cut: (a: number, b: number, c: number) => [number, number];
|
||||
export const cut_all: (a: number, b: number) => [number, number];
|
||||
export const cut_for_search: (a: number, b: number, c: number) => [number, number];
|
||||
export const tokenize: (a: number, b: number, c: number, d: number, e: number) => [number, number, number, number];
|
||||
export const add_word: (a: number, b: number, c: number, d: number, e: number) => number;
|
||||
export const tag: (a: number, b: number, c: number) => [number, number];
|
||||
export const with_dict: (a: number, b: number) => [number, number];
|
||||
export const rust_zstd_wasm_shim_qsort: (a: number, b: number, c: number, d: number) => void;
|
||||
export const rust_zstd_wasm_shim_malloc: (a: number) => number;
|
||||
export const rust_zstd_wasm_shim_memcmp: (a: number, b: number, c: number) => number;
|
||||
export const rust_zstd_wasm_shim_calloc: (a: number, b: number) => number;
|
||||
export const rust_zstd_wasm_shim_free: (a: number) => void;
|
||||
export const rust_zstd_wasm_shim_memcpy: (a: number, b: number, c: number) => number;
|
||||
export const rust_zstd_wasm_shim_memmove: (a: number, b: number, c: number) => number;
|
||||
export const rust_zstd_wasm_shim_memset: (a: number, b: number, c: 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_export_2: WebAssembly.Table;
|
||||
export const __externref_drop_slice: (a: number, b: number) => void;
|
||||
export const __wbindgen_free: (a: number, b: number, c: number) => void;
|
||||
export const __externref_table_dealloc: (a: number) => void;
|
||||
export const __wbindgen_start: () => void;
|
||||
Reference in New Issue
Block a user