@jackgreen2018/pdf-engine 1.0.15 → 1.0.16

package/pkg/pdf_engine.js

@@ -1,122 +1,9 @@
 /* @ts-self-types="./pdf_engine.d.ts" */
+import * as wasm from "./pdf_engine_bg.wasm";
+import { __wbg_set_wasm } from "./pdf_engine_bg.js";
 
-/**
- * Merge multiple PDFs into a single PDF.
- * Input: js_sys::Array of Uint8Array (each a valid PDF byte stream).
- * Returns raw bytes of the merged PDF (to be wrapped as Uint8Array by wasm).
- * @param {Array<any>} pdfs
- * @returns {Uint8Array}
- */
-function merge(pdfs) {
-    const ret = wasm.merge(pdfs);
-    var v1 = getArrayU8FromWasm0(ret[0], ret[1]).slice();
-    wasm.__wbindgen_free(ret[0], ret[1] * 1, 1);
-    return v1;
-}
-exports.merge = merge;
-
-/**
- * Split a PDF by page ranges (inclusive, 0-indexed).
- * pdf: Uint8Array of valid PDF bytes.
- * ranges: Array of Uint8Array, each 8 bytes = [start_u32_le, end_u32_le].
- * Returns Array of Uint8Array, one per range.
- * @param {Uint8Array} pdf
- * @param {Array<any>} ranges
- * @returns {Array<any>}
- */
-function split(pdf, ranges) {
-    const ret = wasm.split(pdf, ranges);
-    return ret;
-}
-exports.split = split;
-function __wbg_get_imports() {
-    const import0 = {
-        __proto__: null,
-        __wbg___wbindgen_throw_344f42d3211c4765: function(arg0, arg1) {
-            throw new Error(getStringFromWasm0(arg0, arg1));
-        },
-        __wbg_get_unchecked_6e0ad6d2a41b06f6: function(arg0, arg1) {
-            const ret = arg0[arg1 >>> 0];
-            return ret;
-        },
-        __wbg_instanceof_Uint8Array_309b927aaf7a3fc7: function(arg0) {
-            let result;
-            try {
-                result = arg0 instanceof Uint8Array;
-            } catch (_) {
-                result = false;
-            }
-            const ret = result;
-            return ret;
-        },
-        __wbg_length_1f0964f4a5e2c6d8: function(arg0) {
-            const ret = arg0.length;
-            return ret;
-        },
-        __wbg_length_370319915dc99107: function(arg0) {
-            const ret = arg0.length;
-            return ret;
-        },
-        __wbg_new_32b398fb48b6d94a: function() {
-            const ret = new Array();
-            return ret;
-        },
-        __wbg_new_with_length_e6785c33c8e4cce8: function(arg0) {
-            const ret = new Uint8Array(arg0 >>> 0);
-            return ret;
-        },
-        __wbg_prototypesetcall_4770620bbe4688a0: function(arg0, arg1, arg2) {
-            Uint8Array.prototype.set.call(getArrayU8FromWasm0(arg0, arg1), arg2);
-        },
-        __wbg_push_d2ae3af0c1217ae6: function(arg0, arg1) {
-            const ret = arg0.push(arg1);
-            return ret;
-        },
-        __wbg_set_4d7dd76f3dae2926: function(arg0, arg1, arg2) {
-            arg0.set(getArrayU8FromWasm0(arg1, arg2));
-        },
-        __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,
-        "./pdf_engine_bg.js": import0,
-    };
-}
-
-function getArrayU8FromWasm0(ptr, len) {
-    ptr = ptr >>> 0;
-    return getUint8ArrayMemory0().subarray(ptr / 1, ptr / 1 + len);
-}
-
-function getStringFromWasm0(ptr, len) {
-    return decodeText(ptr >>> 0, len);
-}
-
-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));
-}
-
-const wasmPath = `${__dirname}/pdf_engine_bg.wasm`;
-const wasmBytes = require('fs').readFileSync(wasmPath);
-const wasmModule = new WebAssembly.Module(wasmBytes);
-let wasmInstance = new WebAssembly.Instance(wasmModule, __wbg_get_imports());
-let wasm = wasmInstance.exports;
+__wbg_set_wasm(wasm);
 wasm.__wbindgen_start();
+export {
+    extract_text, get_page_count, get_pdf_info, init, merge, split
+} from "./pdf_engine_bg.js";

package/pkg/pdf_engine_bg.js

@@ -0,0 +1,220 @@
+/**
+ * @param {Uint8Array} buffer
+ * @returns {string}
+ */
+export function extract_text(buffer) {
+    let deferred3_0;
+    let deferred3_1;
+    try {
+        const ptr0 = passArray8ToWasm0(buffer, wasm.__wbindgen_malloc);
+        const len0 = WASM_VECTOR_LEN;
+        const ret = wasm.extract_text(ptr0, len0);
+        var ptr2 = ret[0];
+        var len2 = ret[1];
+        if (ret[3]) {
+            ptr2 = 0; len2 = 0;
+            throw takeFromExternrefTable0(ret[2]);
+        }
+        deferred3_0 = ptr2;
+        deferred3_1 = len2;
+        return getStringFromWasm0(ptr2, len2);
+    } finally {
+        wasm.__wbindgen_free(deferred3_0, deferred3_1, 1);
+    }
+}
+
+/**
+ * @param {Uint8Array} buffer
+ * @returns {number}
+ */
+export function get_page_count(buffer) {
+    const ptr0 = passArray8ToWasm0(buffer, wasm.__wbindgen_malloc);
+    const len0 = WASM_VECTOR_LEN;
+    const ret = wasm.get_page_count(ptr0, len0);
+    if (ret[2]) {
+        throw takeFromExternrefTable0(ret[1]);
+    }
+    return ret[0] >>> 0;
+}
+
+/**
+ * @param {Uint8Array} buffer
+ * @returns {string}
+ */
+export function get_pdf_info(buffer) {
+    let deferred3_0;
+    let deferred3_1;
+    try {
+        const ptr0 = passArray8ToWasm0(buffer, wasm.__wbindgen_malloc);
+        const len0 = WASM_VECTOR_LEN;
+        const ret = wasm.get_pdf_info(ptr0, len0);
+        var ptr2 = ret[0];
+        var len2 = ret[1];
+        if (ret[3]) {
+            ptr2 = 0; len2 = 0;
+            throw takeFromExternrefTable0(ret[2]);
+        }
+        deferred3_0 = ptr2;
+        deferred3_1 = len2;
+        return getStringFromWasm0(ptr2, len2);
+    } finally {
+        wasm.__wbindgen_free(deferred3_0, deferred3_1, 1);
+    }
+}
+
+export function init() {
+    const ret = wasm.init();
+    if (ret[1]) {
+        throw takeFromExternrefTable0(ret[0]);
+    }
+}
+
+/**
+ * @param {Array<any>} pdf_buffers
+ * @returns {Uint8Array}
+ */
+export function merge(pdf_buffers) {
+    const ret = wasm.merge(pdf_buffers);
+    if (ret[2]) {
+        throw takeFromExternrefTable0(ret[1]);
+    }
+    return takeFromExternrefTable0(ret[0]);
+}
+
+/**
+ * @param {Uint8Array} buffer
+ * @param {Array<any>} pages
+ * @returns {Array<any>}
+ */
+export function split(buffer, pages) {
+    const ptr0 = passArray8ToWasm0(buffer, wasm.__wbindgen_malloc);
+    const len0 = WASM_VECTOR_LEN;
+    const ret = wasm.split(ptr0, len0, pages);
+    if (ret[2]) {
+        throw takeFromExternrefTable0(ret[1]);
+    }
+    return takeFromExternrefTable0(ret[0]);
+}
+export function __wbg___wbindgen_number_get_394265ed1e1b84ee(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);
+}
+export function __wbg___wbindgen_throw_344f42d3211c4765(arg0, arg1) {
+    throw new Error(getStringFromWasm0(arg0, arg1));
+}
+export function __wbg_get_507a50627bffa49b(arg0, arg1) {
+    const ret = arg0[arg1 >>> 0];
+    return ret;
+}
+export function __wbg_instanceof_Uint8Array_309b927aaf7a3fc7(arg0) {
+    let result;
+    try {
+        result = arg0 instanceof Uint8Array;
+    } catch (_) {
+        result = false;
+    }
+    const ret = result;
+    return ret;
+}
+export function __wbg_length_1f0964f4a5e2c6d8(arg0) {
+    const ret = arg0.length;
+    return ret;
+}
+export function __wbg_length_370319915dc99107(arg0) {
+    const ret = arg0.length;
+    return ret;
+}
+export function __wbg_new_32b398fb48b6d94a() {
+    const ret = new Array();
+    return ret;
+}
+export function __wbg_new_from_slice_77cdfb7977362f3c(arg0, arg1) {
+    const ret = new Uint8Array(getArrayU8FromWasm0(arg0, arg1));
+    return ret;
+}
+export function __wbg_prototypesetcall_4770620bbe4688a0(arg0, arg1, arg2) {
+    Uint8Array.prototype.set.call(getArrayU8FromWasm0(arg0, arg1), arg2);
+}
+export function __wbg_push_d2ae3af0c1217ae6(arg0, arg1) {
+    const ret = arg0.push(arg1);
+    return ret;
+}
+export function __wbindgen_cast_0000000000000001(arg0, arg1) {
+    // Cast intrinsic for `Ref(String) -> Externref`.
+    const ret = getStringFromWasm0(arg0, arg1);
+    return ret;
+}
+export function __wbindgen_init_externref_table() {
+    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);
+}
+function getArrayU8FromWasm0(ptr, len) {
+    ptr = ptr >>> 0;
+    return getUint8ArrayMemory0().subarray(ptr / 1, ptr / 1 + len);
+}
+
+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) {
+    return decodeText(ptr >>> 0, len);
+}
+
+let cachedUint8ArrayMemory0 = null;
+function getUint8ArrayMemory0() {
+    if (cachedUint8ArrayMemory0 === null || cachedUint8ArrayMemory0.byteLength === 0) {
+        cachedUint8ArrayMemory0 = new Uint8Array(wasm.memory.buffer);
+    }
+    return cachedUint8ArrayMemory0;
+}
+
+function isLikeNone(x) {
+    return x === undefined || x === null;
+}
+
+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 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));
+}
+
+let WASM_VECTOR_LEN = 0;
+
+
+let wasm;
+export function __wbg_set_wasm(val) {
+    wasm = val;
+}

package/pkg/pdf_engine_bg.wasm.d.ts

@@ -1,8 +1,14 @@
 /* tslint:disable */
 /* eslint-disable */
 export const memory: WebAssembly.Memory;
-export const merge: (a: any) => [number, number];
-export const split: (a: any, b: any) => any;
+export const extract_text: (a: number, b: number) => [number, number, number, number];
+export const get_page_count: (a: number, b: number) => [number, number, number];
+export const get_pdf_info: (a: number, b: number) => [number, number, number, number];
+export const init: () => [number, number];
+export const merge: (a: any) => [number, number, number];
+export const split: (a: number, b: number, c: any) => [number, number, number];
 export const __wbindgen_externrefs: WebAssembly.Table;
+export const __wbindgen_malloc: (a: number, b: number) => number;
+export const __externref_table_dealloc: (a: number) => void;
 export const __wbindgen_free: (a: number, b: number, c: number) => void;
 export const __wbindgen_start: () => void;

package/src/cli.ts

@@ -0,0 +1,66 @@
+#!/usr/bin/env node
+import { createRequire } from 'module';
+import pdfEngine from './index.js';
+const require = createRequire(import.meta.url);
+
+const USAGE = `pdf-engine — Rust/WASM PDF processing (v${require('../package.json').version})
+
+Usage:
+  pdf-engine <command> [args]
+
+Commands:
+  page-count <file>           Print the page count of a PDF
+  extract-text <file>         Extract text from a PDF
+  merge <file1> <file2> ...  Merge PDFs into a single output
+  split <file> <page1> ...   Split a PDF by 0-based page indices
+  help                       Print this message
+`;
+
+async function main(): Promise<number> {
+  const [cmd, ...args] = process.argv.slice(2);
+  if (!cmd || cmd === '-h' || cmd === '--help' || cmd === 'help') {
+    process.stdout.write(USAGE);
+    return 0;
+  }
+  const fs = await import('fs/promises');
+  const read = async (p: string) => new Uint8Array(await fs.readFile(p));
+  await pdfEngine.init();
+  switch (cmd) {
+    case 'page-count': {
+      const n = await pdfEngine.getPageCount(await read(args[0]));
+      process.stdout.write(String(n) + '\n');
+      return 0;
+    }
+    case 'extract-text': {
+      const t = await pdfEngine.extractText(await read(args[0]));
+      process.stdout.write(t + '\n');
+      return 0;
+    }
+    case 'merge': {
+      const out = await pdfEngine.merge(await Promise.all(args.map(read)));
+      await fs.writeFile('merged.pdf', out);
+      process.stdout.write(`wrote merged.pdf (${out.byteLength} bytes)\n`);
+      return 0;
+    }
+    case 'split': {
+      const [file, ...pages] = args;
+      const out = await pdfEngine.split(
+        await read(file),
+        pages.map(Number),
+      );
+      for (let i = 0; i < out.length; i++) {
+        await fs.writeFile(`part-${i}.pdf`, out[i]);
+      }
+      process.stdout.write(`wrote ${out.length} part-*.pdf files\n`);
+      return 0;
+    }
+    default:
+      process.stderr.write(`unknown command: ${cmd}\n${USAGE}`);
+      return 1;
+  }
+}
+
+main().then((c) => process.exit(c)).catch((e) => {
+  process.stderr.write(String(e) + '\n');
+  process.exit(1);
+});

package/src/index.ts

@@ -0,0 +1,62 @@
+// PDF Engine TypeScript bindings for Rust/WASM PDF processing library
+
+import * as wasm from '../pkg/pdf_engine.js';
+
+export async function initialize(): Promise<void> {
+    await wasm.init();
+}
+
+export async function getPageCount(buffer: Uint8Array): Promise<number> {
+    return await wasm.get_page_count(buffer);
+}
+
+export async function extractText(buffer: Uint8Array): Promise<string> {
+    return await wasm.extract_text(buffer);
+}
+
+export async function merge(pdfBuffers: Uint8Array[]): Promise<Uint8Array> {
+    const result = await wasm.merge(pdfBuffers);
+    return result;
+}
+
+export async function split(buffer: Uint8Array, pages: number[]): Promise<Uint8Array[]> {
+    const resultArray = await wasm.split(buffer, pages);
+    return Array.from(resultArray).map(arr => arr as Uint8Array);
+}
+
+export class PdfEngineImpl {
+    constructor() {
+        this.initialized = false;
+    }
+    private initialized = false;
+
+    async init(): Promise<void> {
+        if (!this.initialized) {
+            await initialize();
+            this.initialized = true;
+        }
+    }
+
+    async getPageCount(buffer: Uint8Array): Promise<number> {
+        await this.init();
+        return await getPageCount(buffer);
+    }
+
+    async extractText(buffer: Uint8Array): Promise<string> {
+        await this.init();
+        return await extractText(buffer);
+    }
+
+    async merge(pdfBuffers: Uint8Array[]): Promise<Uint8Array> {
+        await this.init();
+        return await merge(pdfBuffers);
+    }
+
+    async split(buffer: Uint8Array, pages: number[]): Promise<Uint8Array[]> {
+        await this.init();
+        return await split(buffer, pages);
+    }
+}
+
+const pdfEngine = new PdfEngineImpl();
+export default pdfEngine;