chore: initialize

.github/workflows/publish.yml

@@ -0,0 +1,35 @@
+name: Publish on NPM
+
+on:
+  push:
+    tags:
+      - 'js-v*.*.*'
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+
+    permissions:
+      contents: read
+      id-token: write
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: pnpm/action-setup@v4
+        with:
+          version: latest
+
+      - uses: actions/setup-node@v4
+        with:
+          cache: 'pnpm'
+          node-version: 20
+          registry-url: 'https://registry.npmjs.com'
+          cache-dependency-path: 'pnpm-lock.yaml'
+
+      - name: Publish package
+        env:
+          NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}
+        run: |
+          pnpm install && pnpm build
+          npm publish --provenance --access public

.gitignore

@@ -0,0 +1,2 @@
+node_modules/
+dist/

.vscode/extensions.json

@@ -0,0 +1,5 @@
+{
+  "recommendations": [
+    "dbaeumer.vscode-eslint"
+  ]
+}

.vscode/settings.json

@@ -0,0 +1,11 @@
+{
+  "editor.detectIndentation": false,
+  "editor.insertSpaces": true,
+  "editor.tabSize": 2,
+
+  "editor.codeActionsOnSave": {
+    "source.fixAll.eslint": "explicit"
+  },
+
+  "eslint.useFlatConfig": true
+}

README.md

@@ -0,0 +1,31 @@
+# `@literate.ink/pdf-inspector`
+
+## Installation
+
+```bash
+npm install @literate.ink/pdf-inspector
+yarn add @literate.ink/pdf-inspector
+pnpm add @literate.ink/pdf-inspector
+bun add @literate.ink/pdf-inspector
+```
+
+## Usage
+
+```typescript
+import { parsePDF } from "@literate.ink/pdf-inspector";
+
+const pages = await parsePDF(buffer);
+
+for (const page of pages) {
+  console.log(`Page of ${page.Width}x${page.Height}px`);
+  console.log("- contains", page.Texts.length, "texts");
+  console.log("- contains", page.Fills.length, "fills");
+}
+```
+
+## Credits
+
+The JS/TS implementation is a fork of the following projects :
+
+- [`pdf2json`](https://github.com/modesty/pdf2json) is a [Node.js](http://nodejs.org/) module that parses and converts PDF from binary to JSON format
+- [`pdf.js`](https://github.com/mozilla/pdf.js/) but lighter because we only need a few things from it for what we are doing

eslint.config.js

@@ -0,0 +1,36 @@
+module.exports = [
+  { // Apply to `cjs`, `.mjs` and `.js` files.
+    files: ["**/*.?([cm])js"]
+  },
+  { // Apply to `.ts` files.
+    files: ["**/*.ts"],
+    languageOptions: {
+      parser: require("@typescript-eslint/parser"),
+      parserOptions: {
+        sourceType: "module"
+      }
+    }
+  },
+  {
+    ignores: ["dist/**"],
+    plugins: {
+      stylistic: require("@stylistic/eslint-plugin")
+    },
+    rules: {
+      "stylistic/indent": ["error", 2],
+      "stylistic/semi": ["error", "always"],
+      "stylistic/eol-last": ["error", "always"],
+      "stylistic/quotes": ["error", "double"],
+      "stylistic/dot-location": ["error", "property"],
+      "stylistic/array-bracket-spacing": ["error", "never"],
+      "stylistic/arrow-parens": ["error", "always"],
+      "stylistic/arrow-spacing": "error",
+      "stylistic/block-spacing": ["error", "always"],
+      "stylistic/brace-style": ["error", "stroustrup"],
+      "stylistic/comma-dangle": ["error", "never"],
+      "stylistic/comma-spacing": ["error", { before: false, after: true }],
+      "stylistic/function-call-spacing": ["error", "never"],
+      "stylistic/no-trailing-spaces": "error"
+    }
+  }
+];

examples/main.ts

@@ -0,0 +1,18 @@
+import { parsePDF } from "../src";
+//     replace with this ^ "@literate.ink/pdf-inspector";
+
+import fs from "node:fs/promises";
+import path from "node:path";
+
+void async function main () {
+  const file = path.join(__dirname, "timetable.pdf");
+  const buffer = await fs.readFile(file);
+
+  const pages = await parsePDF(buffer);
+
+  for (const page of pages) {
+    console.log(`Page of ${page.Width}x${page.Height}px`);
+    console.log("- contains", page.Texts.length, "texts");
+    console.log("- contains", page.Fills.length, "fills");
+  }
+}();

package.json

@@ -0,0 +1,50 @@
+{
+  "name": "@literate.ink/pdf-inspector",
+  "version": "0.0.0",
+  "description": "",
+  "repository": "https://github.com/LiterateInk/PDFInspector",
+  "sideEffects": false,
+  "main": "./dist/index.js",
+  "module": "./dist/index.mjs",
+  "types": "./dist/index.d.ts",
+  "exports": {
+    "import": {
+      "types": "./dist/index.d.mts",
+      "default": "./dist/index.mjs"
+    },
+    "require": {
+      "types": "./dist/index.d.ts",
+      "default": "./dist/index.js"
+    }
+  },
+  "scripts": {
+    "build": "tsup",
+    "checks": "tsc && eslint ."
+  },
+  "files": [
+    "dist"
+  ],
+  "keywords": [
+    "pdf",
+    "inspection",
+    "scrapping"
+  ],
+  "author": "LiterateInk <[email protected]> (https://literate.ink)",
+  "homepage": "https://github.com/LiterateInk/PDFInspector",
+  "bugs": {
+    "url": "https://github.com/LiterateInk/PDFInspector/issues"
+  },
+  "license": "GPL-3.0-or-later",
+  "engines": {
+    "node": ">=18"
+  },
+  "devDependencies": {
+    "@stylistic/eslint-plugin": "^2.12.1",
+    "@types/node": "^22.10.2",
+    "@typescript-eslint/parser": "^8.18.0",
+    "eslint": "^9.16.0",
+    "terser": "^5.37.0",
+    "tsup": "^8.3.5",
+    "typescript": "^5.7.2"
+  }
+}