paper-drift 0.0.0-stage → 0.1.1

package/LICENSE

@@ -0,0 +1,190 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   Copyright 2026 Sooriya
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

package/README.md

@@ -1,3 +1,207 @@
-# Temporary Holding Version
+# paper-drift
 
-This version is a temporary placeholder for this package. An operational version to replace this has been submitted for review and is awaiting a staged release.
+[![CI](https://github.com/Sooriya04/Paper-Drift/actions/workflows/ci.yml/badge.svg)](https://github.com/Sooriya04/Paper-Drift/actions/workflows/ci.yml)
+[![License: Apache-2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+[![Node Version](https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg)](https://nodejs.org)
+[![WASM Powered](https://img.shields.io/badge/engine-WebAssembly-purple.svg)](https://webassembly.org/)
+
+> **Zero-Python, zero-Chromium WebAssembly document parser, HTML renderer, and Markdown engine with GFM tables and math.**
+
+Convert complex academic research papers and enterprise PDFs directly into clean, structured **Markdown** or standalone **HTML** with pixel-perfect visual fidelity—without Puppeteer, Python, Docker, or external servers. Slashes AI Agent token ingestion costs by 90%+.
+
+---
+
+## ⚡ Why paper-drift?
+
+Most PDF conversion pipelines in JavaScript suffer from two major flaws:
+1. **The Heavyweight Trap**: Requiring Headless Chromium (Puppeteer / Playwright) or Python microservices (`unstructured`, `poppler`, `nougat`) that need 500MB+ Docker images, multi-second cold boots, and high cloud costs.
+2. **The "Text Soup" Trap**: Spatially naive parsers that dump unordered lines, break multi-column layouts, and butcher tabular grids.
+
+**`paper-drift` solves this natively:**
+* **Zero-Python & Zero-Chromium**: Runs compiled WebAssembly directly in any V8 runtime (Node.js, Bun, or modern browsers). Under 20 KB package footprint.
+* **Direct Markdown Engine**: Converts directly into GitHub Flavored Markdown (GFM) with auto-detected `#`, `##` headings, list markers, and clean math.
+* **Geometric Table Reconstruction**: Discovers column gutters and slices cells into standard pipe tables (`| col1 | col2 |`) with clean universal math exponents (`O(n² · d)`, `10¹⁹`).
+* **Multi-Column Spatial Ordering**: Resolves 2-column papers via Recursive XY-Cut without column interweaving.
+* **Dual-Layer HTML Mode**: High-DPI background raster rendering paired with a 1:1 selectable, searchable text layer.
+* **100% Private & Instant**: Ingests pages in under 50ms locally. Zero data leaves your machine.
+
+---
+
+## 🚀 Quick Start (CLI)
+
+### Run with `npx` (Zero installation required)
+```bash
+# Convert to Markdown (for Claude, LLMs, or AI Agents)
+npx paper-drift paper.pdf output.md --format md
+
+# Convert to Standalone HTML (for human viewing)
+npx paper-drift paper.pdf output.html
+```
+
+### Install Globally
+```bash
+npm install -g paper-drift
+```
+
+### Common Commands
+```bash
+# Convert to clean Markdown
+paper-drift research-paper.pdf paper.md --format md
+
+# Convert specific pages to Markdown
+paper-drift paper.pdf output.md --format md --pages 1-5,8
+
+# Convert to pixel-perfect HTML at 2.0x Retina scale
+paper-drift report.pdf output.html --scale 2.0
+
+# Text-only HTML mode (skips background raster)
+paper-drift book.pdf book.html --no-bg
+```
+
+### CLI Options
+
+| Flag | Type | Default | Description |
+| :--- | :--- | :--- | :--- |
+| `<input.pdf>` | `string` | *(required)* | Path to the source PDF file |
+| `[output]` | `string` | `<name>.<ext>` | Destination output file path |
+| `--format <fmt>` | `string` | `html` | Output format: `markdown` (`md`) \| `html` \| `text` \| `json` |
+| `--pages <range>` | `string` | `"all"` | Target page range (e.g. `1-10`, `2,4,6`) |
+| `--scale <num>` | `number` | `2.0` | DPI multiplier for background raster rendering in HTML mode |
+| `--no-bg` | `boolean` | `false` | Disables background rasterization (text-only HTML) |
+| `-v, --version` | `flag` | — | Display current version |
+| `-h, --help` | `flag` | — | Display CLI help menu |
+
+---
+
+## 💻 Programmatic API (Node.js / Bun)
+
+Install in your project:
+```bash
+npm install paper-drift
+```
+
+### Direct PDF to Markdown
+```javascript
+import { convertPdfToMarkdown } from 'paper-drift';
+
+const result = await convertPdfToMarkdown('research-paper.pdf', {
+  pageRange: '1-10'
+});
+
+console.log(`Converted ${result.pagesProcessed} pages in ${result.durationMs}ms`);
+console.log(result.markdown);
+```
+
+### PDF to Standalone HTML
+```javascript
+import { convertPdfToHtml } from 'paper-drift';
+import fs from 'fs';
+
+const result = await convertPdfToHtml('document.pdf', {
+  scale: 2.0,
+  withBg: true
+});
+
+fs.writeFileSync('output.html', result.html);
+```
+
+### Buffer Input Support
+Both functions accept raw `Buffer` or `Uint8Array` inputs:
+```javascript
+import { convertPdfToMarkdown } from 'paper-drift';
+
+const pdfBuffer = await fetch('https://example.com/paper.pdf').then(r => r.arrayBuffer());
+const { markdown } = await convertPdfToMarkdown(Buffer.from(pdfBuffer));
+```
+
+---
+
+## 💸 AI Agent Token Savings
+
+When feeding 10-page academic papers into LLMs (Claude, GPT-4, Cursor, Antigravity):
+
+| Mode | Tokens Consumed | Cost / Ingestion | Reading Accuracy |
+| :--- | :--- | :--- | :--- |
+| **Multimodal Vision (Images)** | ~16,000 – 20,000 tokens | ~$0.15 – $0.40 | Heavy hallucinations on dense math |
+| **Naive OCR / PDF Text Dump** | ~8,000 tokens | ~$0.08 | Tables destroyed into loose lines |
+| **`paper-drift` Markdown** | **~1,200 – 1,800 tokens** | **~$0.01** | **Pixel-accurate reading order, GFM tables, math** |
+
+> **Net Savings:** Over **90% token reduction** and **12x faster ingestion**.
+
+---
+
+## 🤖 Turnkey AI Agent Skill (Claude, Cursor, Antigravity)
+
+`paper-drift` is built from the ground up as a native **AI Agent Skill** to eliminate the **"Multimodal PDF Token Tax"**. 
+
+When an AI coding or research agent ingests raw PDFs as images, it burns ~1,500 to 2,000 vision tokens per page (crowding context windows and costing $0.50–$2.00 per query). By equipping your agent with the `paper-drift` skill, the agent pre-processes PDFs locally via WebAssembly into clean Markdown, GFM tables, and LaTeX equations in **< 400ms**—cutting token consumption by **90%+**.
+
+### 1-Click Skill Installation
+
+Install the canonical [`SKILL.md`](skills/paper-drift/SKILL.md) into any workspace with a single command:
+
+```bash
+# 1. Default: Auto-install to current workspace (.agent/skills/paper-drift/SKILL.md)
+npx paper-drift skill
+
+# 2. Target Claude Code workspace (.claude/skills/paper-drift/SKILL.md)
+npx paper-drift skill --claude
+
+# 3. Target Cursor workspace rules (.cursor/rules/paper-drift.md)
+npx paper-drift skill --cursor
+
+# 4. Install globally for all projects (~/.gemini/... & ~/.claude/...)
+npx paper-drift skill --global
+
+# 5. Output raw SKILL.md to stdout (for piping or custom paths)
+npx paper-drift skill cat
+```
+
+### How the Agent Uses It
+
+Once installed, your agent automatically activates the skill whenever you provide a PDF:
+
+```text
+User: "Summarize the experimental results from attention-is-all-you-need.pdf"
+
+Agent (Internal):
+  1. Detects paper-drift skill
+  2. Executes: npx -y paper-drift attention-is-all-you-need.pdf --format md --pages 6-8
+  3. Receives clean GFM Table 1 and BLEU score comparisons in < 250ms
+  4. Answers your query using 1,200 text tokens instead of 20,000 vision tokens!
+```
+
+- 📖 **Skill Specification:** [`skills/paper-drift/SKILL.md`](skills/paper-drift/SKILL.md)
+- 🌐 **Interactive Documentation:** [https://sooriya04.github.io/Paper-Drift/#skill](https://sooriya04.github.io/Paper-Drift/#skill)
+
+---
+
+## 🌐 Interactive Web Playground
+
+`paper-drift` includes a local WebAssembly playground with live GFM table and KaTeX formula preview:
+
+1. Start the local server:
+   ```bash
+   npm start
+   ```
+2. Open your browser at **http://localhost:3000** and drag-and-drop any PDF.
+
+---
+
+## 🧪 Testing & Benchmarks
+
+Run the complete test suite:
+```bash
+npm test
+```
+
+Benchmark throughput and layout fidelity across landmark ArXiv papers:
+```bash
+npm run benchmark
+```
+
+---
+
+## 📄 License
+
+Apache-2.0 License. See [LICENSE](LICENSE) for details.

package/bin/cli.js

@@ -0,0 +1,227 @@
+#!/usr/bin/env node
+/**
+ * @file bin/cli.js
+ * @description Command-line interface executable for paper-drift.
+ * Enables zero-Chromium PDF to high-fidelity HTML, Markdown, and natural spatial text conversion straight from terminal.
+ * Part of paper-drift - https://github.com/Sooriya04/Paper-Drift
+ */
+
+import fs from 'fs';
+import path from 'path';
+import { fileURLToPath } from 'url';
+import { convertPdfToHtml, convertPdfToMarkdown } from '../src/index.js';
+import { installSkill, getSkillContent } from '../src/skill/installer.js';
+
+const __filename = fileURLToPath(import.meta.url);
+const __dirname = path.dirname(__filename);
+
+// Read package metadata for version flag
+const packageJson = JSON.parse(
+  fs.readFileSync(path.join(__dirname, '../package.json'), 'utf-8')
+);
+
+function printHelp() {
+  console.log(`
+\x1b[1m\x1b[36mpaper-drift\x1b[0m v${packageJson.version}
+High-fidelity, zero-Chromium PDF parser powered by WebAssembly & spatial layout decomposition.
+
+\x1b[1mUSAGE:\x1b[0m
+  $ paper-drift <input.pdf> [output] [options]
+
+\x1b[1mARGUMENTS:\x1b[0m
+  input.pdf        Path to the PDF file to convert
+  output           (Optional) Destination file path (default: <input>.<ext>)
+
+\x1b[1mOPTIONS:\x1b[0m
+  --format <fmt>   Output format: markdown (md) | html | text | json (default: html)
+  --scale <num>    DPI scale for background raster rendering (default: 2.0)
+  --no-bg          Text-only mode; disables background raster rendering
+  --pages <range>  Target pages to convert (e.g. "1-5", "2,4,6", default: "all")
+  -v, --version    Show version number
+  -h, --help       Display this help message
+
+\x1b[1mEXAMPLES:\x1b[0m
+  $ paper-drift document.pdf
+  $ paper-drift paper.pdf output.md --format md
+  $ paper-drift paper.pdf output.txt --format text
+  $ paper-drift paper.pdf output.html --scale 2.5
+  $ paper-drift manual.pdf manual.html --pages 1-10 --no-bg
+
+\x1b[1mAGENT SKILL:\x1b[0m
+  $ paper-drift skill                 Install skill into agent workspace (.agent/skills)
+  $ paper-drift skill --claude        Install skill into Claude workspace (.claude/skills)
+  $ paper-drift skill --cursor        Install skill into Cursor rules (.cursor/rules)
+  $ paper-drift skill --global        Install skill globally to user home directory
+  $ paper-drift skill cat             Output raw SKILL.md to stdout
+`);
+}
+
+async function run() {
+  const args = process.argv.slice(2);
+
+  // Handle agent skill subcommands
+  if (args[0] === 'skill' || args.includes('--install-skill')) {
+    if (args.includes('cat') || args.includes('print')) {
+      process.stdout.write(getSkillContent());
+      process.exit(0);
+    }
+
+    const isGlobal = args.includes('--global');
+    const isClaude = args.includes('--claude');
+    const isCursor = args.includes('--cursor');
+    const isAgent = args.includes('--agent') || args.includes('--antigravity');
+    let dest = null;
+    const destIdx = args.indexOf('--dest');
+    if (destIdx !== -1 && args[destIdx + 1]) {
+      dest = args[destIdx + 1];
+    }
+
+    try {
+      const installed = installSkill({
+        global: isGlobal,
+        claude: isClaude,
+        cursor: isCursor,
+        agent: isAgent,
+        dest
+      });
+
+      console.log('\n\x1b[1m\x1b[36mpaper-drift\x1b[0m \x1b[32mAgent Skill Installed Successfully!\x1b[0m\n');
+      for (const p of installed) {
+        console.log(`  \x1b[32m✔\x1b[0m ${path.relative(process.cwd(), p) || p}`);
+      }
+      console.log('\n\x1b[90mYour AI coding agent can now parse PDFs with zero multimodal token tax.\x1b[0m');
+      console.log('\x1b[90mAsk your agent: "Read this PDF" or "Extract Table 1 from paper.pdf"\x1b[0m\n');
+      process.exit(0);
+    } catch (err) {
+      console.error(`\x1b[31mError installing skill:\x1b[0m ${err.message}`);
+      process.exit(1);
+    }
+  }
+
+  if (args.length === 0 || args.includes('-h') || args.includes('--help')) {
+    printHelp();
+    process.exit(0);
+  }
+
+  if (args.includes('-v') || args.includes('--version')) {
+    console.log(`paper-drift v${packageJson.version}`);
+    process.exit(0);
+  }
+
+  // Parse positional and flag arguments
+  let inputFile = null;
+  let outputFile = null;
+  let format = 'html';
+  let scale = 2.0;
+  let withBg = true;
+  let pageRange = 'all';
+
+  for (let i = 0; i < args.length; i++) {
+    const arg = args[i];
+    if (arg === '--format') {
+      format = (args[++i] || 'html').toLowerCase();
+    } else if (arg === '--scale') {
+      scale = parseFloat(args[++i]) || 2.0;
+    } else if (arg === '--no-bg') {
+      withBg = false;
+    } else if (arg === '--pages') {
+      pageRange = args[++i] || 'all';
+    } else if (!arg.startsWith('-')) {
+      if (!inputFile) {
+        inputFile = arg;
+      } else if (!outputFile) {
+        outputFile = arg;
+      }
+    }
+  }
+
+  if (!inputFile) {
+    console.error('\x1b[31mError: Missing required argument <input.pdf>\x1b[0m');
+    printHelp();
+    process.exit(1);
+  }
+
+  const resolvedInput = path.resolve(process.cwd(), inputFile);
+  if (!fs.existsSync(resolvedInput)) {
+    console.error(`\x1b[31mError: Input file does not exist: ${resolvedInput}\x1b[0m`);
+    process.exit(1);
+  }
+
+  const validFormats = ['html', 'md', 'markdown', 'text', 'json'];
+  if (!validFormats.includes(format)) {
+    console.error(`\x1b[31mError: Unsupported format "${format}". Supported: markdown (md) | html | text | json\x1b[0m`);
+    process.exit(1);
+  }
+
+  const isMarkdown = format === 'md' || format === 'markdown';
+  const ext = isMarkdown ? 'md' : (format === 'text' ? 'txt' : (format === 'json' ? 'json' : 'html'));
+  if (!outputFile) {
+    const parsedPath = path.parse(resolvedInput);
+    outputFile = path.join(process.cwd(), `${parsedPath.name}.${ext}`);
+  } else {
+    outputFile = path.resolve(process.cwd(), outputFile);
+  }
+
+  console.log(`\x1b[36m⚡ paper-drift\x1b[0m v${packageJson.version}`);
+  console.log(`📄 Input:   ${resolvedInput}`);
+  console.log(`🎯 Output:  ${outputFile} (Format: ${format.toUpperCase()})`);
+  console.log(`⚙️  Config:  Scale=${scale}x, Background=${withBg ? 'lossless' : 'disabled'}, Pages=${pageRange}`);
+  console.log('🔄 Running WebAssembly parser with spatial reading order decomposition...');
+
+  try {
+    let outputContent = '';
+    let durationMs = 0;
+    let pagesProcessed = 0;
+    let totalPages = 0;
+    let columnsOrTablesInfo = '';
+
+    if (isMarkdown) {
+      const result = await convertPdfToMarkdown(resolvedInput, {
+        pageRange,
+        onProgress: ({ current, total, pageNumber }) => {
+          process.stdout.write(`   ⏳ Processing page ${pageNumber} (${current}/${total})...\r`);
+        }
+      });
+      outputContent = result.markdown;
+      durationMs = result.durationMs;
+      pagesProcessed = result.pagesProcessed;
+      totalPages = result.totalPages;
+      columnsOrTablesInfo = result.pages.map(p => `p${p.pageNumber}:${p.tablesCount}tables`).join(', ');
+    } else {
+      const result = await convertPdfToHtml(resolvedInput, {
+        scale,
+        withBg,
+        pageRange,
+        format,
+        onProgress: ({ current, total, pageNumber }) => {
+          process.stdout.write(`   ⏳ Processing page ${pageNumber} (${current}/${total})...\r`);
+        }
+      });
+      durationMs = result.durationMs;
+      pagesProcessed = result.pagesProcessed;
+      totalPages = result.totalPages;
+      columnsOrTablesInfo = result.pages.map(p => `p${p.pageNumber}:${p.columnsDetected}col`).join(', ');
+
+      if (format === 'text') {
+        outputContent = result.text;
+      } else if (format === 'json') {
+        outputContent = JSON.stringify(result.pages, null, 2);
+      } else {
+        outputContent = result.html;
+      }
+    }
+
+    fs.writeFileSync(outputFile, outputContent, 'utf-8');
+    const stats = fs.statSync(outputFile);
+    const sizeKb = (stats.size / 1024).toFixed(1);
+
+    console.log(`\n\x1b[32m✔ Conversion complete in ${durationMs}ms!\x1b[0m`);
+    console.log(`📊 Converted ${pagesProcessed} of ${totalPages} pages (${sizeKb} KB) [${columnsOrTablesInfo}]`);
+    console.log(`✨ Open your file: \x1b[4mfile://${outputFile}\x1b[0m\n`);
+  } catch (err) {
+    console.error(`\n\x1b[31m❌ Conversion failed:\x1b[0m ${err.message}`);
+    process.exit(1);
+  }
+}
+
+run();

package/package.json

@@ -1,6 +1,52 @@
 {
   "name": "paper-drift",
-  "version": "0.0.0-stage",
-  "stub": true,
-  "description": "Temporary package placeholder for staged publishing"
-}
+  "version": "0.1.1",
+  "description": "Zero-Python, zero-Chromium WebAssembly document parser, HTML renderer, and Markdown engine with GFM tables and math",
+  "type": "module",
+  "main": "src/index.js",
+  "types": "src/index.d.ts",
+  "exports": {
+    ".": {
+      "types": "./src/index.d.ts",
+      "import": "./src/index.js"
+    }
+  },
+  "files": [
+    "src",
+    "bin",
+    "skills",
+    "README.md",
+    "LICENSE"
+  ],
+  "bin": {
+    "paper-drift": "./bin/cli.js"
+  },
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/Sooriya04/Paper-Drift.git"
+  },
+  "scripts": {
+    "start": "node playground/server.js",
+    "test": "node test/cli.test.js && node test/spatial.test.js && node test/math.test.js && node test/tables.test.js && node test/markdown.test.js",
+    "convert": "node bin/cli.js test/fixtures/sample.pdf output.html",
+    "generate:sample": "node test/scripts/generate-sample.js",
+    "benchmark": "node test/scripts/benchmark-papers.js run --limit 3 --pages 1-2",
+    "benchmark:20": "node test/scripts/benchmark-papers.js run --limit 20 --pages 1-2",
+    "benchmark:download": "node test/scripts/benchmark-papers.js download 20",
+    "benchmark:list": "node test/scripts/benchmark-papers.js list"
+  },
+  "keywords": [
+    "pdf",
+    "webassembly",
+    "wasm",
+    "pdf-to-html",
+    "rag",
+    "mupdf",
+    "document-parser"
+  ],
+  "author": "Sooriya",
+  "license": "Apache-2.0",
+  "dependencies": {
+    "mupdf": "^1.28.1"
+  }
+}