@jackgreen2018/pdf-engine 1.0.12 → 1.0.13

package/pkg/README.md

@@ -1,160 +0,0 @@
-> Scope: full engine (see [SCOPE.md](./SCOPE.md)).
-
-# pdf-engine — Rust/WASM PDF Processing Library
-
-[![npm version](https://img.shields.io/npm/v/@jackgreen2018/pdf-engine)](https://www.npmjs.com/package/@jackgreen2018/pdf-engine)
-[![npm downloads](https://img.shields.io/npm/dt/@jackgreen2018/pdf-engine)](https://www.npmjs.com/package/@jackgreen2018/pdf-engine)
-[![License: MIT](https://img.shields.io/github/license/jackgreen/pdf-engine)](LICENSE)
-[![Sponsor](https://img.shields.io/static/v1?label=Sponsor&message=GitHub%20Sponsors&color=ea4aaa&logo=github-sponsors)](https://github.com/sponsors/jackgreen)
-
-A high-performance PDF processing library for Node.js and the browser. Built with Rust + WebAssembly. Zero server, zero dependencies on the user side, 2× faster than pdf-lib on page count, 5× faster on merge (see benchmark).
-
-## Features
-
-- **Page Count**: Quickly determine the number of pages in a PDF using a proper PDF parser
-- **Text Extraction**: Extract text content from PDF files with accurate parsing
-- **PDF Merge**: Combine multiple PDFs into a single file
-- **PDF Split**: Split PDFs by page range
-- **Privacy**: All processing happens in the user's browser or local environment
-- **Performance**: Rust-powered with WASM for maximum speed
-
-## Installation
-
-```bash
-npm install @jackgreen2018/pdf-engine
-```
-
-Or build from source:
-
-```bash
-git clone <this-repo>
-cd pdf-engine
-npm install
-npm run build
-```
-
-## Usage
-
-### Browser
-
-```javascript
-import pdfEngine from '@jackgreen2018/pdf-engine';
-
-// Initialize the engine
-await pdfEngine.init();
-
-// Get page count of a PDF file
-const file = document.querySelector('input[type="file"]').files[0];
-const arrayBuffer = await file.arrayBuffer();
-const pageCount = await pdfEngine.getPageCount(new Uint8Array(arrayBuffer));
-console.log(`Pages: ${pageCount}`);
-
-// Extract text from a PDF
-const text = await pdfEngine.extractText(new Uint8Array(arrayBuffer));
-console.log(text);
-
-// Merge multiple PDFs
-const mergedPdf = await pdfEngine.merge([pdf1Buffer, pdf2Buffer, pdf3Buffer]);
-
-// Split a PDF by page numbers
-const pagesToExtract = [1, 3, 5];
-const splitParts = await pdfEngine.split(new Uint8Array(arrayBuffer), pagesToExtract);
-```
-
-### Node.js
-
-```javascript
-const pdfEngine = require('@jackgreen2018/pdf-engine');
-
-async function processPdf() {
-  await pdfEngine.init();
-
-  const buffer = require('fs').readFileSync('document.pdf');
-  const pageCount = await pdfEngine.getPageCount(buffer);
-  console.log(`Pages: ${pageCount}`);
-
-  const text = await pdfEngine.extractText(buffer);
-  console.log(text);
-}
-
-processPdf().catch(console.error);
-```
-
-## Build
-
-```bash
-npm run build
-```
-
-This compiles the Rust code to WASM using `wasm-pack` and builds the TypeScript definitions.
-
-## Development
-
-```bash
-# Install dependencies
-npm install
-
-# Build the project
-npm run build
-
-# Run benchmarks
-npm run benchmark
-
-# Test locally
-npm test
-```
-
-## Benchmark
-
-Performance benchmarks for pdf-engine operations:
-
-```
-npm run benchmark
-```
-
-| Operation | pdf-engine (ms) | pdf-lib (ms) |
-|-----------|-----------------|--------------|
-| Page Count | 0.60 | 1.34 |
-| Text Extraction | 0.29 | — |
-| Merge (2 files) | 1.01 | 3.84 |
-| Split (pages [0,1]) | 0.21 | 2.01 |
-
-*extractText correctness: PASS — gated via `tests/fixtures/text-fixture.pdf` (FlateDecode-compressed, real-world content stream)*
-
-*Run 2026-07-31 v1.0.10; full stdout at evidence/benchmark-output-v1.0.10.log.*
-
-## Commercial license & support
-
-For teams or organizations that need the package without MIT attribution obligations, or require a formal SLA, a commercial license is available. See [COMMERCIAL-LICENSE.md](./COMMERCIAL-LICENSE.md) for pricing and terms. To purchase, email `jackgreen2018+sponsors@gmail.com`.
-
-## License
-
-MIT
-
-## Verify locally
-
-```bash
-npm install @jackgreen2018/pdf-engine
-node -e '
-const fs = require("fs");
-const m = require("@jackgreen2018/pdf-engine");
-const buf = fs.readFileSync("test.pdf");
-m.initialize().then(() => m.getPageCount(new Uint8Array(buf)))
-  .then(n => console.log("pages:", n));
-'
-```
-
-## Launch post
-
-Draft lives at [`evidence/devto-launch-post.md`](./evidence/devto-launch-post.md).
-Posting requires a `DEVTO_API_KEY` (manual step). README's published benchmark
-numbers (`evidence/benchmark-output-v1.0.10.log`) are the source of truth until
-the dev.to URL exists.
-
-## See Also
-
-- [pdf-lib](https://www.npmjs.com/package/pdf-lib) — A popular JavaScript PDF library for comparison
-
-## Backlinks
-
-- Dev.to launch post (canonical for this version): TODO_FILL_AFTER_DEV_TO_PUBLISH

package/pkg/pdf_engine_bg.js

@@ -1,220 +0,0 @@
-/**
- * @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/src/cli.ts

@@ -1,66 +0,0 @@
-#!/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

@@ -1,62 +0,0 @@
-// 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;