@qretaio/html2json 0.5.4 → 0.5.6

package/README.md

@@ -44,7 +44,7 @@ just install
 ### JavaScript / TypeScript
 
 ```javascript
-import { extract } from '@qretaio/html2json';
+import { extract } from "@qretaio/html2json";
 
 const html = `
   <article class="post">
@@ -57,16 +57,18 @@ const html = `
   </article>
 `;
 
-const spec = JSON.stringify({
+const spec = {
   title: "h2",
   author: ".author",
-  tags: [{
-    "$": ".tags span",
-    "name": "$"
-  }]
-});
-
-const result = extract(html, spec);
+  tags: [
+    {
+      $: ".tags span",
+      name: "$",
+    },
+  ],
+};
+
+const result = await extract(html, spec);
 console.log(result);
 // {
 //   "title": "My Article",
@@ -129,6 +131,7 @@ The spec is a JSON object where each key defines an output field and each value
 ```
 
 Available pipes:
+
 - `trim` - Trim whitespace
 - `lower` - Convert to lowercase
 - `upper` - Convert to uppercase
@@ -143,11 +146,13 @@ Available pipes:
 
 ```json
 {
-  "items": [{
-    "$": ".item",
-    "title": "h2",
-    "description": "p"
-  }]
+  "items": [
+    {
+      "$": ".item",
+      "title": "h2",
+      "description": "p"
+    }
+  ]
 }
 ```
 

package/html2json.d.ts

@@ -1,11 +1,45 @@
 /* tslint:disable */
 /* eslint-disable */
 
+/**
+ * Extract JSON from HTML using a spec
+ *
+ * # Arguments
+ *
+ * * `html` - The HTML source to parse
+ * * `spec_json` - The extraction specification as JSON string
+ *
+ * # Returns
+ *
+ * A JSON string with the extracted data
+ *
+ * # Errors
+ *
+ * Returns a JsValue error if the HTML parsing or extraction fails
+ *
+ * # Example
+ *
+ * ```javascript
+ * import { extract } from 'html2json';
+ *
+ * const html = '<div class="item"><span>Price: $25.00</span></div>';
+ * const spec = '{"price": ".item span | regex:\\\\$(\\\\d+\\\\.\\\\d+)"}';
+ * const result = extract(html, spec);
+ * console.log(result); // {"price":"25.00"}
+ * ```
+ */
+export function extract(html: string, spec_json: string): string;
+
 export type InitInput = RequestInfo | URL | Response | BufferSource | WebAssembly.Module;
 
 export interface InitOutput {
     readonly memory: WebAssembly.Memory;
+    readonly extract: (a: number, b: number, c: number, d: number) => [number, number, number, number];
     readonly __wbindgen_externrefs: WebAssembly.Table;
+    readonly __wbindgen_malloc: (a: number, b: number) => number;
+    readonly __wbindgen_realloc: (a: number, b: number, c: number, d: number) => number;
+    readonly __externref_table_dealloc: (a: number) => void;
+    readonly __wbindgen_free: (a: number, b: number, c: number) => void;
     readonly __wbindgen_start: () => void;
 }
 

package/html2json.js

@@ -1,8 +1,66 @@
 /* @ts-self-types="./html2json.d.ts" */
 
+/**
+ * Extract JSON from HTML using a spec
+ *
+ * # Arguments
+ *
+ * * `html` - The HTML source to parse
+ * * `spec_json` - The extraction specification as JSON string
+ *
+ * # Returns
+ *
+ * A JSON string with the extracted data
+ *
+ * # Errors
+ *
+ * Returns a JsValue error if the HTML parsing or extraction fails
+ *
+ * # Example
+ *
+ * ```javascript
+ * import { extract } from 'html2json';
+ *
+ * const html = '<div class="item"><span>Price: $25.00</span></div>';
+ * const spec = '{"price": ".item span | regex:\\\\$(\\\\d+\\\\.\\\\d+)"}';
+ * const result = extract(html, spec);
+ * console.log(result); // {"price":"25.00"}
+ * ```
+ * @param {string} html
+ * @param {string} spec_json
+ * @returns {string}
+ */
+export function extract(html, spec_json) {
+    let deferred4_0;
+    let deferred4_1;
+    try {
+        const ptr0 = passStringToWasm0(html, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
+        const len0 = WASM_VECTOR_LEN;
+        const ptr1 = passStringToWasm0(spec_json, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
+        const len1 = WASM_VECTOR_LEN;
+        const ret = wasm.extract(ptr0, len0, ptr1, len1);
+        var ptr3 = ret[0];
+        var len3 = ret[1];
+        if (ret[3]) {
+            ptr3 = 0; len3 = 0;
+            throw takeFromExternrefTable0(ret[2]);
+        }
+        deferred4_0 = ptr3;
+        deferred4_1 = len3;
+        return getStringFromWasm0(ptr3, len3);
+    } finally {
+        wasm.__wbindgen_free(deferred4_0, deferred4_1, 1);
+    }
+}
+
 function __wbg_get_imports() {
     const import0 = {
         __proto__: null,
+        __wbindgen_cast_0000000000000001: function(arg0, arg1) {
+            // Cast intrinsic for `Ref(String) -> Externref`.
+            const ret = getStringFromWasm0(arg0, arg1);
+            return ret;
+        },
         __wbindgen_init_externref_table: function() {
             const table = wasm.__wbindgen_externrefs;
             const offset = table.grow(4);
@@ -19,10 +77,96 @@ function __wbg_get_imports() {
     };
 }
 
+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 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;
+    cachedUint8ArrayMemory0 = null;
     wasm.__wbindgen_start();
     return wasm;
 }

package/index.js

@@ -0,0 +1,27 @@
+// Auto-initializing wrapper for convenience
+import _init from "./html2json.js";
+import { extract as _extract, initSync } from "./html2json.js";
+
+let initPromise;
+
+// Auto-init on first call
+function init() {
+  if (!initPromise) {
+    initPromise = _init();
+  }
+  return initPromise;
+}
+
+// Export auto-initialized extract (async for first call)
+export async function extract(html, spec_json) {
+  await init();
+  return _extract(html, spec_json);
+}
+
+// Also export init functions for those who want to control timing
+export { init, initSync };
+
+// Export raw extract for advanced use (sync, requires manual init)
+export { _extract as extractSync };
+
+export default init;

package/package.json

@@ -5,7 +5,7 @@
     "Qreta Dev <qretadev@gmail.com>"
   ],
   "description": "HTML to JSON extractor",
-  "version": "0.5.4",
+  "version": "0.5.6",
   "license": "MIT",
   "repository": {
     "type": "git",
@@ -14,11 +14,12 @@
   "files": [
     "html2json_bg.wasm",
     "html2json.js",
-    "html2json.d.ts"
+    "html2json.d.ts",
+    "index.js"
   ],
-  "main": "html2json.js",
+  "main": "index.js",
   "types": "html2json.d.ts",
   "sideEffects": [
     "./snippets/*"
   ]
-}
+}