{
  "name": "officeparser",
  "version": "6.1.0",
  "description": "A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf) into structured AST with rich metadata, formatting, and attachment support.",
  "funding": "https://github.com/sponsors/harshankur",
  "main": "dist/index.js",
  "module": "dist/index.mjs",
  "types": "dist/index.d.ts",
  "browser": "./dist/officeparser.browser.mjs",
  "exports": {
    ".": {
      "types": "./dist/index.d.ts",
      "browser": "./dist/officeparser.browser.mjs",
      "import": "./dist/index.mjs",
      "require": "./dist/index.js"
    }
  },
  "sideEffects": false,
  "engines": {
    "node": ">=18.0.0"
  },
  "files": [
    "dist"
  ],
  "scripts": {
    "build": "npm run sync:versions && npm run build:node && npm run build:esm-wrapper && npm run build:browser:types && npm run build:browser",
    "build:node": "tsc",
    "build:esm-wrapper": "node scripts/generate-esm-wrapper.js",
    "build:browser:types": "dts-bundle-generator --no-check -o dist/officeparser.browser.d.ts src/index.ts",
    "build:browser": "node build_browser.js && npm run sync:docs",
    "sync:versions": "node scripts/sync-pdfjs-versions.js",
    "sync:docs": "mkdir -p docs/dist && cp dist/officeparser.browser.iife.js docs/dist/ && cp dist/officeparser.browser.mjs docs/dist/",
    "test": "npm run test:clean && npm run build && npm run test:license && npm run test:artifacts && npm run test:parser",
    "test:baseline": "npm run test baseline",
    "test:parser": "npx tsx test/testOfficeParser.ts",
    "test:artifacts": "npx tsx test/testShippingArtifacts.ts",
    "test:license": "npm run sbom && node scripts/validate-licenses.js",
    "test:clean": "rm -rf test/results",
    "clean": "rm -rf dist && npm run test:clean",
    "sbom": "npx --yes @cyclonedx/cyclonedx-npm --output-format json --output-file dist/sbom.cdx.json --omit dev",
    "prepublishOnly": "npm run build",
    "prepare": "husky"
  },
  "repository": {
    "type": "git",
    "url": "git+https://github.com/harshankur/officeParser.git"
  },
  "bin": {
    "officeparser": "dist/cli.js"
  },
  "publishConfig": {
    "access": "public",
    "provenance": true
  },
  "keywords": [
    "office",
    "docx",
    "pptx",
    "xlsx",
    "odt",
    "odp",
    "ods",
    "pdf",
    "rtf",
    "parser",
    "text extraction",
    "document parser",
    "word",
    "excel",
    "powerpoint",
    "spreadsheet",
    "presentation",
    "slides",
    "ast",
    "ocr",
    "typescript",
    "browser",
    "metadata",
    "formatting",
    "attachments",
    "tesseract",
    "pdf.js",
    "structured-data",
    "openoffice",
    "libreoffice"
  ],
  "author": "Harsh Ankur",
  "license": "MIT",
  "bugs": {
    "url": "https://github.com/harshankur/officeParser/issues"
  },
  "homepage": "https://officeparser.harshankur.com",
  "dependencies": {
    "@xmldom/xmldom": "^0.9.9",
    "fflate": "^0.8.2",
    "file-type": "^22.0.1",
    "pdfjs-dist": "5.6.205",
    "tesseract.js": "^7.0.0"
  },
  "devDependencies": {
    "@types/node": "^25.5.0",
    "buffer": "^6.0.3",
    "dts-bundle-generator": "^9.5.1",
    "esbuild": "^0.27.4",
    "esbuild-plugins-node-modules-polyfill": "^1.8.1",
    "husky": "^9.1.7",
    "process": "^0.11.10",
    "tsx": "^4.21.0",
    "typescript": "^6.0.2"
  }
}