3.2.2

.gitea/workflows/default_nottags.yaml

@@ -0,0 +1,66 @@
+name: Default (not tags)
+
+on:
+  push:
+    tags-ignore:
+      - '**'
+
+env:
+  IMAGE: registry.gitlab.com/hosttoday/ht-docker-node:npmci
+  NPMCI_COMPUTED_REPOURL: https://${{gitea.repository_owner}}:${{secrets.GITEA_TOKEN}}@gitea.lossless.digital/${{gitea.repository}}.git
+  NPMCI_TOKEN_NPM: ${{secrets.NPMCI_TOKEN_NPM}}
+  NPMCI_TOKEN_NPM2: ${{secrets.NPMCI_TOKEN_NPM2}}
+  NPMCI_GIT_GITHUBTOKEN: ${{secrets.NPMCI_GIT_GITHUBTOKEN}}
+  NPMCI_URL_CLOUDLY: ${{secrets.NPMCI_URL_CLOUDLY}}
+
+jobs:
+  security:
+    runs-on: ubuntu-latest
+    continue-on-error: true
+    container:
+      image: ${{ env.IMAGE }}
+
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Install pnpm and npmci
+        run: |
+          pnpm install -g pnpm
+          pnpm install -g @shipzone/npmci
+
+      - name: Run npm prepare
+        run: npmci npm prepare
+
+      - name: Audit production dependencies
+        run: |
+          npmci command npm config set registry https://registry.npmjs.org
+          npmci command pnpm audit --audit-level=high --prod
+        continue-on-error: true
+
+      - name: Audit development dependencies
+        run: |
+          npmci command npm config set registry https://registry.npmjs.org
+          npmci command pnpm audit --audit-level=high --dev
+        continue-on-error: true
+
+  test:
+    if: ${{ always() }}
+    needs: security
+    runs-on: ubuntu-latest
+    container:
+      image: ${{ env.IMAGE }}
+
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Test stable
+        run: |
+          npmci node install stable
+          npmci npm install
+          npmci npm test
+
+      - name: Test build
+        run: |
+          npmci node install stable
+          npmci npm install
+          npmci npm build

.gitea/workflows/default_tags.yaml

@@ -0,0 +1,124 @@
+name: Default (tags)
+
+on:
+  push:
+    tags:
+      - '*'
+
+env:
+  IMAGE: registry.gitlab.com/hosttoday/ht-docker-node:npmci
+  NPMCI_COMPUTED_REPOURL: https://${{gitea.repository_owner}}:${{secrets.GITEA_TOKEN}}@gitea.lossless.digital/${{gitea.repository}}.git
+  NPMCI_TOKEN_NPM: ${{secrets.NPMCI_TOKEN_NPM}}
+  NPMCI_TOKEN_NPM2: ${{secrets.NPMCI_TOKEN_NPM2}}
+  NPMCI_GIT_GITHUBTOKEN: ${{secrets.NPMCI_GIT_GITHUBTOKEN}}
+  NPMCI_URL_CLOUDLY: ${{secrets.NPMCI_URL_CLOUDLY}}
+
+jobs:
+  security:
+    runs-on: ubuntu-latest
+    continue-on-error: true
+    container:
+      image: ${{ env.IMAGE }}
+
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Prepare
+        run: |
+          pnpm install -g pnpm
+          pnpm install -g @shipzone/npmci
+          npmci npm prepare
+
+      - name: Audit production dependencies
+        run: |
+          npmci command npm config set registry https://registry.npmjs.org
+          npmci command pnpm audit --audit-level=high --prod
+        continue-on-error: true
+
+      - name: Audit development dependencies
+        run: |
+          npmci command npm config set registry https://registry.npmjs.org
+          npmci command pnpm audit --audit-level=high --dev
+        continue-on-error: true
+
+  test:
+    if: ${{ always() }}
+    needs: security
+    runs-on: ubuntu-latest
+    container:
+      image: ${{ env.IMAGE }}
+
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Prepare
+        run: |
+          pnpm install -g pnpm
+          pnpm install -g @shipzone/npmci
+          npmci npm prepare
+
+      - name: Test stable
+        run: |
+          npmci node install stable
+          npmci npm install
+          npmci npm test
+
+      - name: Test build
+        run: |
+          npmci node install stable
+          npmci npm install
+          npmci npm build
+
+  release:
+    needs: test
+    if: github.event_name == 'push' && startsWith(github.ref, 'refs/tags/')
+    runs-on: ubuntu-latest
+    container:
+      image: ${{ env.IMAGE }}
+
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Prepare
+        run: |
+          pnpm install -g pnpm
+          pnpm install -g @shipzone/npmci
+          npmci npm prepare
+
+      - name: Release
+        run: |
+          npmci node install stable
+          npmci npm publish
+
+  metadata:
+    needs: test
+    if: github.event_name == 'push' && startsWith(github.ref, 'refs/tags/')
+    runs-on: ubuntu-latest
+    container:
+      image: ${{ env.IMAGE }}
+    continue-on-error: true
+
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Prepare
+        run: |
+          pnpm install -g pnpm
+          pnpm install -g @shipzone/npmci
+          npmci npm prepare
+
+      - name: Code quality
+        run: |
+          npmci command npm install -g typescript
+          npmci npm install
+
+      - name: Trigger
+        run: npmci trigger
+
+      - name: Build docs and upload artifacts
+        run: |
+          npmci node install stable
+          npmci npm install
+          pnpm install -g @git.zone/tsdoc
+          npmci command tsdoc
+        continue-on-error: true

.gitignore

@@ -1,7 +1,20 @@
 .nogit/
-node_modules/
-assets/pdfdir/
+
+# artifacts
 coverage/
 public/
 pages/
+
+# installs
+node_modules/
+
+# caches
 .yarn/
+.cache/
+.rpt2_cache
+
+# builds
+dist/
+dist_*/
+
+# custom

.gitlab-ci.yml

@@ -1,147 +0,0 @@
-# gitzone standard
-image: hosttoday/ht-docker-node:npmci
-
-cache:
-  paths:
-  - .npmci_cache/
-  key: "$CI_BUILD_STAGE"
-
-stages:
-- security
-- test
-- release
-- metadata
-
-# ====================
-# security stage
-# ====================
-mirror:
-  stage: security
-  script:
-  - npmci git mirror
-  tags:
-  - docker
-  - notpriv
-
-snyk:
-  stage: security
-  script:
-    - npmci npm prepare
-    - npmci command npm install -g snyk
-    - npmci command npm install --ignore-scripts
-    - npmci command snyk test
-  tags:
-  - docker
-  - notpriv
-
-# ====================
-# test stage
-# ====================
-testLEGACY:
-  stage: test
-  script:
-  - npmci npm prepare
-  - npmci node install legacy
-  - npmci npm install
-  - npmci npm test
-  coverage: /\d+.?\d+?\%\s*coverage/
-  tags:
-  - docker
-  - notpriv
-  allow_failure: true
-
-testLTS:
-  stage: test
-  script:
-  - npmci npm prepare
-  - npmci node install lts
-  - npmci npm install
-  - npmci npm test
-  coverage: /\d+.?\d+?\%\s*coverage/
-  tags:
-  - docker
-  - notpriv
-    
-testSTABLE:
-  stage: test
-  script:
-  - npmci npm prepare
-  - npmci node install stable
-  - npmci npm install
-  - npmci npm test
-  coverage: /\d+.?\d+?\%\s*coverage/
-  tags:
-  - docker
-  - notpriv
-
-release:
-  stage: release
-  script:
-  - npmci node install stable
-  - npmci npm publish
-  only:
-  - tags
-  tags:
-  - docker
-  - notpriv
-
-# ====================
-# metadata stage
-# ====================
-codequality:
-  stage: metadata
-  image: docker:stable
-  allow_failure: true
-  services:
-    - docker:stable-dind
-  script:
-    - export SP_VERSION=$(echo "$CI_SERVER_VERSION" | sed 's/^\([0-9]*\)\.\([0-9]*\).*/\1-\2-stable/')
-    - docker run
-        --env SOURCE_CODE="$PWD"
-        --volume "$PWD":/code
-        --volume /var/run/docker.sock:/var/run/docker.sock
-        "registry.gitlab.com/gitlab-org/security-products/codequality:$SP_VERSION" /code
-  artifacts:
-    paths: [codeclimate.json]
-  tags:
-  - docker
-  - priv
-
-trigger:
-  stage: metadata
-  script:
-  - npmci trigger
-  only:
-  - tags
-  tags:
-  - docker
-  - notpriv
-
-pages:
-  image: hosttoday/ht-docker-node:npmci
-  stage: metadata
-  script:
-    - npmci command npm install -g typedoc typescript
-    - npmci npm prepare
-    - npmci npm install
-    - npmci command typedoc --module "commonjs" --target "ES2016" --out public/ ts/
-  tags:
-    - docker
-    - notpriv
-  only:
-    - tags
-  artifacts:
-    expire_in: 1 week
-    paths:
-    - public
-  allow_failure: true
-
-windowsCompatibility:
-  image: stefanscherer/node-windows:10-build-tools
-  stage: metadata
-  script:
-  - npm install & npm test
-  coverage: /\d+.?\d+?\%\s*coverage/
-  tags:
-  - windows
-  allow_failure: true

.vscode/launch.json

@@ -0,0 +1,11 @@
+{
+  "version": "0.2.0",
+  "configurations": [
+    {
+      "command": "npm test",
+      "name": "Run npm test",
+      "request": "launch",
+      "type": "node-terminal"
+    }
+  ]
+}

.vscode/settings.json

@@ -0,0 +1,26 @@
+{
+  "json.schemas": [
+    {
+      "fileMatch": ["/npmextra.json"],
+      "schema": {
+        "type": "object",
+        "properties": {
+          "npmci": {
+            "type": "object",
+            "description": "settings for npmci"
+          },
+          "gitzone": {
+            "type": "object",
+            "description": "settings for gitzone",
+            "properties": {
+              "projectType": {
+                "type": "string",
+                "enum": ["website", "element", "service", "npm", "wcc"]
+              }
+            }
+          }
+        }
+      }
+    }
+  ]
+}

changelog.md

@@ -0,0 +1,131 @@
+# Changelog
+
+## 2025-02-25 - 3.2.2 - fix(SmartPdf)
+Fix buffer handling for PDF conversion and text extraction
+
+- Ensure Uint8Array is converted to Node Buffer for PDF conversion.
+- Correct the PDF page viewport handling by using document dimensions.
+- Fix extractTextFromPdfBuffer argument type from Uint8Array to Buffer.
+
+## 2025-02-25 - 3.2.1 - fix(SmartPdf)
+Fix type for extractTextFromPdfBuffer function
+
+- Corrected the parameter type from Buffer to Uint8Array for extractTextFromPdfBuffer function.
+
+## 2025-02-25 - 3.2.0 - feat(smartpdf)
+Improve dependency versions and optimize PDF to PNG conversion.
+
+- Update several dependencies to newer versions for better stability and performance.
+- Refactor tests to enhance readability and add directory creation validations.
+- Optimize PDF to PNG conversion by switching to a more efficient Puppeteer and PDF.js-based method.
+- Add checks for presence of required dependencies (GraphicsMagick and Ghostscript).
+- Fix media emulation issue by properly awaiting the emulateMediaType function.
+
+## 2024-11-30 - 3.1.8 - fix(core)
+Fix candidate handling in PDF generation
+
+- Added error handling for missing PDF candidates in server requests.
+- Updated devDependencies and dependencies to latest versions for better stability and new features.
+- Patched header retrieval logic during PDF generation for security check.
+
+## 2024-09-27 - 3.1.7 - fix(dependencies)
+Update dependencies to latest versions
+
+- Updated @git.zone/tsbuild to version ^2.1.84
+- Updated @git.zone/tsdoc to version ^1.3.12
+- Updated @git.zone/tsrun to version ^1.2.49
+- Updated @push.rocks/tapbundle to version ^5.3.0
+- Updated @types/node to version ^22.7.4
+- Updated @push.rocks/smartfile to version ^11.0.21
+- Updated @push.rocks/smartpromise to version ^4.0.4
+- Updated @tsclass/tsclass to version ^4.1.2
+- Updated express to version ^4.21.0
+- Updated pdf2pic to version ^3.1.3
+
+## 2024-05-29 - 3.1.6 - Core
+Updated description
+
+- Minor changes to documentation and internal text.
+
+## 2024-04-25 to 2024-04-30 - 3.1.0 to 3.1.5 - Core
+Fix updates in core functionality
+
+- Fixes and updates in core function in versions 3.1.0 to 3.1.5.
+
+## 2024-04-25 - 3.0.17 - Feature
+Now supports PDF to JPG conversion
+
+- Added support for converting PDF files to JPG format.
+  
+## 2024-03-19 to 2024-04-14 - 3.0.17 - Maintenance
+Various updates to project configuration files
+
+- Updated `tsconfig`.
+- Updated `npmextra.json`.
+
+## 2023-07-11 to 2024-03-19 - 3.0.15 to 3.0.16 - Organization
+Switch to new organization scheme and core updates
+
+- Switched to new organization scheme.
+- Applied core updates and bug fixes.
+
+## 2022-11-07 to 2023-07-10 - 3.0.13 to 3.0.14 - Core
+Fixes and updates to core functionality
+
+- Various minor bug fixes and updates to core components.
+
+## 2022-09-13 to 2022-11-07 - 3.0.10 to 3.0.12 - Core
+Ongoing core updates and maintenance
+
+- Regular fixes and operational improvements in core functionalities.
+
+## 2022-06-12 to 2022-09-13 - 3.0.7 to 3.0.9 - Core
+Continued focus on high-priority bug fixes and core functionalities
+
+- Regular fixes for critical bugs and enhancements.
+
+## 2022-03-24 to 2022-06-29 - 3.0.3 to 3.0.6 - Core
+Further optimization and maintenance releases
+
+- Further improvements and refinements of issues in core functionalities.
+
+## 2022-01-05 to 2022-03-25 - 3.0.0 to 3.0.2 - Major Version Release
+Major release for version 3.0.x, including core fixes
+
+- Increased version from 2.x to 3.0. New significant changes and fixes.
+
+## 2022-01-05 to 2022-03-24 - 2.0.13 to 2.0.19 - Core
+Routine core updates and bug fixes
+
+- Regular bug fixes in core components.
+
+## 2019-11-19 to 2022-01-06 - 2.0.0 to 2.0.11 - Core
+Multiple core updates and a few performance improvements
+
+- Some performance enhancements and multiple bug fixes.
+  
+## 2019-11-16 to 2019-11-19 - 1.0.27 to 1.0.29 - API
+Breaking change in API
+
+- Naming PDF results to better represent their content.
+
+## 2019-05-29 to 2019-11-15 - 1.0.13 to 1.0.26 - Core
+Core functional updates and some major restructuring
+
+- Introduced multiple updates to the core, addressing bugs and improving stability.
+  
+## 2019-04-10 to 2019-05-28 - 1.0.4 to 1.0.12 - Core
+Fixes and updates in the core
+
+- Implementation of multiple essential fixes for core components.
+
+## 2018-10-06 - 1.0.1 to 1.0.3 - Core and Typings
+Initial implementation and core fixes
+
+- Initial implementation of the project.
+- Fixed compilation problems in typings.
+  
+## 2016-01-29 - unknown - Initial
+Initial commit
+
+- Initial commit for the project setup.

npmextra.json

@@ -2,5 +2,33 @@
   "npmci": {
     "npmGlobalTools": [],
     "npmAccessLevel": "public"
+  },
+  "gitzone": {
+    "projectType": "npm",
+    "module": {
+      "githost": "code.foss.global",
+      "gitscope": "push.rocks",
+      "gitrepo": "smartpdf",
+      "description": "A library for creating PDFs dynamically from HTML or websites with additional features like merging PDFs.",
+      "npmPackagename": "@push.rocks/smartpdf",
+      "license": "MIT",
+      "keywords": [
+        "PDF generation",
+        "HTML to PDF",
+        "website to PDF",
+        "PDF manipulation",
+        "puppeteer",
+        "express",
+        "node.js",
+        "typescript",
+        "automation",
+        "PDF merging",
+        "text extraction",
+        "PDF management"
+      ]
+    }
+  },
+  "tsdoc": {
+    "legal": "\n## License and Legal Information\n\nThis repository contains open-source code that is licensed under the MIT License. A copy of the MIT License can be found in the [license](license) file within this repository. \n\n**Please note:** The MIT License does not grant permission to use the trade names, trademarks, service marks, or product names of the project, except as required for reasonable and customary use in describing the origin of the work and reproducing the content of the NOTICE file.\n\n### Trademarks\n\nThis project is owned and maintained by Task Venture Capital GmbH. The names and logos associated with Task Venture Capital GmbH and any related products or services are trademarks of Task Venture Capital GmbH and are not included within the scope of the MIT license granted herein. Use of these trademarks must comply with Task Venture Capital GmbH's Trademark Guidelines, and any usage must be approved in writing by Task Venture Capital GmbH.\n\n### Company Information\n\nTask Venture Capital GmbH  \nRegistered at District court Bremen HRB 35230 HB, Germany\n\nFor any legal inquiries or if you require further information, please contact us via email at hello@task.vc.\n\nBy using this repository, you acknowledge that you have read this section, agree to comply with its terms, and understand that the licensing of the code does not imply endorsement by Task Venture Capital GmbH of any derivative works.\n"
   }
-}
+}

package.json

@@ -1,32 +1,73 @@
 {
-  "name": "@pushrocks/smartpdf",
-  "version": "1.0.3",
+  "name": "@push.rocks/smartpdf",
+  "version": "3.2.2",
   "private": false,
-  "description": "create pdfs on the fly",
-  "main": "dist/index.js",
-  "typings": "dist/index.d.ts",
+  "description": "A library for creating PDFs dynamically from HTML or websites with additional features like merging PDFs.",
+  "main": "dist_ts/index.js",
+  "typings": "dist_ts/index.d.ts",
+  "type": "module",
   "author": "Lossless GmbH",
   "license": "MIT",
   "scripts": {
-    "test": "(tstest test/)",
-    "format": "(gitzone format)",
-    "build": "(tsbuild)"
+    "test": "(tstest test/ --web)",
+    "build": "(tsbuild --web --allowimplicitany)",
+    "buildDocs": "tsdoc"
   },
   "devDependencies": {
-    "@gitzone/tsbuild": "^2.0.22",
-    "@gitzone/tsrun": "^1.1.12",
-    "@gitzone/tstest": "^1.0.15",
-    "@pushrocks/tapbundle": "^3.0.7",
-    "@types/node": "^10.11.4"
+    "@git.zone/tsbuild": "^2.2.1",
+    "@git.zone/tsdoc": "^1.4.3",
+    "@git.zone/tsrun": "^1.3.3",
+    "@git.zone/tstest": "^1.0.96",
+    "@push.rocks/tapbundle": "^5.5.6",
+    "@types/node": "^22.13.5"
   },
   "dependencies": {
-    "@pushrocks/smartfile": "^6.0.8",
-    "@pushrocks/smartnetwork": "^1.1.0",
-    "@pushrocks/smartpromise": "^2.0.5",
-    "@pushrocks/smartunique": "^3.0.1",
-    "@types/express": "^4.16.0",
-    "@types/puppeteer": "^1.9.0",
-    "express": "^4.16.3",
-    "puppeteer": "^1.9.0"
+    "@push.rocks/smartbuffer": "^3.0.4",
+    "@push.rocks/smartdelay": "^3.0.5",
+    "@push.rocks/smartfile": "^11.2.0",
+    "@push.rocks/smartnetwork": "^3.0.0",
+    "@push.rocks/smartpath": "^5.0.18",
+    "@push.rocks/smartpromise": "^4.2.3",
+    "@push.rocks/smartpuppeteer": "^2.0.5",
+    "@push.rocks/smartunique": "^3.0.9",
+    "@tsclass/tsclass": "^4.4.0",
+    "@types/express": "^5.0.0",
+    "express": "^4.21.2",
+    "pdf-lib": "^1.17.1",
+    "pdf2json": "3.1.5"
+  },
+  "files": [
+    "ts/**/*",
+    "ts_web/**/*",
+    "dist/**/*",
+    "dist_*/**/*",
+    "dist_ts/**/*",
+    "dist_ts_web/**/*",
+    "assets/**/*",
+    "cli.js",
+    "npmextra.json",
+    "readme.md"
+  ],
+  "browserslist": [
+    "last 1 chrome versions"
+  ],
+  "keywords": [
+    "PDF generation",
+    "HTML to PDF",
+    "website to PDF",
+    "PDF manipulation",
+    "puppeteer",
+    "express",
+    "node.js",
+    "typescript",
+    "automation",
+    "PDF merging",
+    "text extraction",
+    "PDF management"
+  ],
+  "homepage": "https://code.foss.global/push.rocks/smartpdf",
+  "repository": {
+    "type": "git",
+    "url": "https://code.foss.global/push.rocks/smartpdf.git"
   }
 }

readme.hints.md

@@ -0,0 +1 @@
+ 

readme.md

@@ -0,0 +1,116 @@
+# @push.rocks/smartpdf
+Create PDFs on the fly
+
+## Install
+To install `@push.rocks/smartpdf`, use the following command with npm:
+
+```bash
+npm install @push.rocks/smartpdf --save
+```
+
+Or with yarn:
+
+```bash
+yarn add @push.rocks/smartpdf
+```
+
+## Usage
+This documentation will guide you through using `@push.rocks/smartpdf` to create PDFs in various ways, such as from HTML strings or full web pages, and provides examples on how to merge multiple PDFs into one. Remember, all examples provided here use ESM syntax and TypeScript.
+
+### Getting Started
+First, ensure you have the package installed and you can import it into your TypeScript project:
+
+```typescript
+import { SmartPdf, IPdf } from '@push.rocks/smartpdf';
+```
+
+### Creating a PDF from an HTML String
+To create a PDF from a simple HTML string, you’ll need to instantiate `SmartPdf` and call `getA4PdfResultForHtmlString`.
+
+```typescript
+async function createPdfFromHtml() {
+  const smartPdf = await SmartPdf.create();
+  await smartPdf.start();
+  const htmlString = `<h1>Hello World</h1>`;
+  const pdf: IPdf = await smartPdf.getA4PdfResultForHtmlString(htmlString);
+  console.log(pdf.buffer); // This is your PDF buffer
+  await smartPdf.stop();
+}
+createPdfFromHtml();
+```
+
+### Generating a PDF from a Website
+You may want to capture a full webpage as a PDF. `SmartPdf` provides two methods to accomplish this. One captures the viewable area as an A4 pdf, and the other captures the entire webpage.
+
+#### A4 PDF from a Website
+
+```typescript
+async function createA4PdfFromWebsite() {
+  const smartPdf = await SmartPdf.create();
+  await smartPdf.start();
+  const pdf: IPdf = await smartPdf.getPdfResultForWebsite('https://example.com');
+  console.log(pdf.buffer); // PDF buffer of the webpage
+  await smartPdf.stop();
+}
+createA4PdfFromWebsite();
+```
+
+#### Full Webpage as a Single PDF
+
+```typescript
+async function createFullPdfFromWebsite() {
+  const smartPdf = await SmartPdf.create();
+  await smartPdf.start();
+  const pdf: IPdf = await smartPdf.getFullWebsiteAsSinglePdf('https://example.com');
+  console.log(pdf.buffer); // PDF buffer with the full webpage
+  await smartPdf.stop();
+}
+createFullPdfFromWebsite();
+```
+
+### Merging Multiple PDFs
+If you have multiple PDF objects (`IPdf`) that you wish to merge into a single PDF file, you can use the `mergePdfs` method.
+
+```typescript
+async function mergePdfs() {
+  const smartPdf = await SmartPdf.create();
+  // Assume pdf1 and pdf2 are objects of type IPdf that you want to merge
+  const mergedPdf: IPdf = await smartPdf.mergePdfs([pdf1, pdf2]);
+  console.log(mergedPdf.buffer); // Buffer of the merged PDF
+}
+mergePdfs();
+```
+
+### Reading PDF from Disk and Extracting Text
+To read a PDF from the disk and extract its text content:
+
+```typescript
+async function readAndExtractFromPdf() {
+  const smartPdf = await SmartPdf.create();
+  const pdf: IPdf = await smartPdf.readFileToPdfObject('/path/to/your/pdf/file.pdf');
+  const extractedText = await smartPdf.extractTextFromPdfBuffer(pdf.buffer);
+  console.log(extractedText);  // Extracted text from the PDF
+}
+readAndExtractFromPdf();
+```
+
+This guide provides a comprehensive overview of generating PDFs using `@push.rocks/smartpdf`. Remember to start and stop your `SmartPdf` instance to properly initialize and clean up resources, especially when working with server-side rendering or capturing web pages.
+
+## License and Legal Information
+
+This repository contains open-source code that is licensed under the MIT License. A copy of the MIT License can be found in the [license](license) file within this repository. 
+
+**Please note:** The MIT License does not grant permission to use the trade names, trademarks, service marks, or product names of the project, except as required for reasonable and customary use in describing the origin of the work and reproducing the content of the NOTICE file.
+
+### Trademarks
+
+This project is owned and maintained by Task Venture Capital GmbH. The names and logos associated with Task Venture Capital GmbH and any related products or services are trademarks of Task Venture Capital GmbH and are not included within the scope of the MIT license granted herein. Use of these trademarks must comply with Task Venture Capital GmbH's Trademark Guidelines, and any usage must be approved in writing by Task Venture Capital GmbH.
+
+### Company Information
+
+Task Venture Capital GmbH  
+Registered at District court Bremen HRB 35230 HB, Germany
+
+For any legal inquiries or if you require further information, please contact us via email at hello@task.vc.
+
+By using this repository, you acknowledge that you have read this section, agree to comply with its terms, and understand that the licensing of the code does not imply endorsement by Task Venture Capital GmbH of any derivative works.

test/test.ts

@@ -1,23 +1,85 @@
-import { expect, tap } from '@pushrocks/tapbundle';
-import * as smartpdf from '../ts/index';
+import { expect, tap } from '@push.rocks/tapbundle';
+import * as smartpdf from '../ts/index.js';
+import * as fs from 'fs';
+import * as path from 'path';
 
 let testSmartPdf: smartpdf.SmartPdf;
 
-tap.test('should create a valid instance of smartpdf', async () => {
+/**
+ * Ensures that a directory exists.
+ * @param dirPath - The directory path to ensure.
+ */
+function ensureDir(dirPath: string): void {
+  if (!fs.existsSync(dirPath)) {
+    fs.mkdirSync(dirPath, { recursive: true });
+  }
+}
+
+tap.test('should create a valid instance of SmartPdf', async () => {
   testSmartPdf = new smartpdf.SmartPdf();
-  expect(testSmartPdf).to.be.instanceof(smartpdf.SmartPdf);
+  expect(testSmartPdf).toBeInstanceOf(smartpdf.SmartPdf);
 });
 
-tap.test('should create a pdf from html string', async () => {
-  await testSmartPdf.getPdfForHtmlString('hi');
+tap.test('should start the SmartPdf instance', async () => {
+  await testSmartPdf.start();
 });
 
-tap.test('should create a pdf from website', async () => {
-  await testSmartPdf.getPdfForWebsite('https://wikipedia.org');
+tap.test('should create PDFs from HTML string', async () => {
+  const pdf1 = await testSmartPdf.getA4PdfResultForHtmlString('hi');
+  const pdf2 = await testSmartPdf.getA4PdfResultForHtmlString('hello');
+  expect(pdf1.buffer).toBeInstanceOf(Buffer);
+  expect(pdf2.buffer).toBeInstanceOf(Buffer);
 });
 
-tap.test('should be able to close properly', async () => {
-  await testSmartPdf.close();
+tap.test('should create PDFs from websites', async () => {
+  const pdfA4 = await testSmartPdf.getPdfResultForWebsite('https://www.wikipedia.org');
+  const pdfSingle = await testSmartPdf.getFullWebsiteAsSinglePdf('https://www.wikipedia.org');
+  expect(pdfA4.buffer).toBeInstanceOf(Buffer);
+  expect(pdfSingle.buffer).toBeInstanceOf(Buffer);
 });
 
-tap.start();
+tap.test('should create valid PDF results and write them to disk', async () => {
+  const writePdfToDisk = async (urlArg: string, fileName: string) => {
+    const pdfResult = await testSmartPdf.getFullWebsiteAsSinglePdf(urlArg);
+    expect(pdfResult.buffer).toBeInstanceOf(Buffer);
+    ensureDir('.nogit');
+    fs.writeFileSync(path.join('.nogit', fileName), pdfResult.buffer as Buffer);
+  };
+  await writePdfToDisk('https://lossless.com/', '1.pdf');
+  await writePdfToDisk('https://layer.io', '2.pdf');
+});
+
+tap.test('should merge PDFs into a combined PDF', async () => {
+  const pdf1 = await testSmartPdf.readFileToPdfObject('.nogit/1.pdf');
+  const pdf2 = await testSmartPdf.readFileToPdfObject('.nogit/2.pdf');
+  const mergedBuffer = await testSmartPdf.mergePdfs([pdf1.buffer, pdf2.buffer]);
+  ensureDir('.nogit');
+  fs.writeFileSync(path.join('.nogit', 'combined.pdf'), mergedBuffer);
+});
+
+tap.test('should create PNG images from combined PDF using Puppeteer conversion', async () => {
+  const pdfObject = await testSmartPdf.readFileToPdfObject('.nogit/combined.pdf');
+  const images = await testSmartPdf.convertPDFToPngBytes(pdfObject.buffer);
+  expect(images.length).toBeGreaterThan(0);
+  console.log('Puppeteer-based conversion image sizes:', images.map(img => img.length));
+});
+
+tap.test('should store PNG results from both conversion functions in .nogit/testresults', async () => {
+  const testResultsDir = path.join('.nogit', 'testresults');
+  ensureDir(testResultsDir);
+
+  const pdfObject = await testSmartPdf.readFileToPdfObject('.nogit/combined.pdf');
+
+  // Convert using Puppeteer-based function and store images
+  const imagesPuppeteer = await testSmartPdf.convertPDFToPngBytes(pdfObject.buffer);
+  imagesPuppeteer.forEach((img, index) => {
+    const filePath = path.join(testResultsDir, `puppeteer_method_page_${index + 1}.png`);
+    fs.writeFileSync(filePath, Buffer.from(img));
+  });
+});
+
+tap.test('should close the SmartPdf instance properly', async () => {
+  await testSmartPdf.stop();
+});
+
+tap.start();

ts/00_commitinfo_data.ts

@@ -0,0 +1,8 @@
+/**
+ * autocreated commitinfo by @push.rocks/commitinfo
+ */
+export const commitinfo = {
+  name: '@push.rocks/smartpdf',
+  version: '3.2.2',
+  description: 'A library for creating PDFs dynamically from HTML or websites with additional features like merging PDFs.'
+}

ts/index.ts

@@ -1,9 +1,15 @@
 // compatibility
 declare global {
-  interface Element { }
-  interface Node { }
-  interface NodeListOf<TNode = Node> { }
+  interface Element {}
+  interface Node {}
+  interface NodeListOf<TNode = Node> {}
 }
 
 // normal
-export * from './smartpdf.classes.smartpdf';
+export * from './smartpdf.classes.smartpdf.js';
+
+// additional types
+import type * as tsclassTypes from '@tsclass/tsclass';
+type IPdf = tsclassTypes.business.IPdf;
+
+export type { IPdf };

ts/smartpdf.classes.pdfcandidate.ts

@@ -1,8 +1,15 @@
-import * as plugins from './smartpdf.plugins';
+/*
+ * pdf candidate is a construct used internally for mapping html
+ * to pdf buffers delivered by puppeteer
+ */
+import * as plugins from './smartpdf.plugins.js';
 
 export class PdfCandidate {
-  pdfId = plugins.smartunique.shortId();
-  doneDeferred = plugins.smartpromise.defer();
+  public htmlString: string;
+  public pdfId = plugins.smartunique.shortId();
+  public doneDeferred = plugins.smartpromise.defer();
 
-  constructor(public htmlString) {}
+  constructor(htmlStringArg: string) {
+    this.htmlString = htmlStringArg;
+  }
 }

ts/smartpdf.classes.pdfresult.ts

@@ -1 +0,0 @@
-import * as plugins from './smartpdf.plugins';

ts/smartpdf.classes.smartpdf.ts

@@ -1,58 +1,94 @@
-import * as plugins from './smartpdf.plugins';
-import * as paths from './smartpdf.paths';
+import * as plugins from './smartpdf.plugins.js';
+import * as paths from './smartpdf.paths.js';
 import { Server } from 'http';
-import { PdfCandidate } from './smartpdf.classes.pdfcandidate';
+import { PdfCandidate } from './smartpdf.classes.pdfcandidate.js';
+import { type IPdf } from '@tsclass/tsclass/dist_ts/business/pdf.js';
+import { execFile } from 'child_process';
+
+declare const document: any;
 
 export class SmartPdf {
+  // STATIC
+  public static async create() {
+    const smartpdfInstance = new SmartPdf();
+    return smartpdfInstance;
+  }
+
+  // INSTANCE
   htmlServerInstance: Server;
   serverPort: number;
-  headlessBrowser: plugins.puppeteer.Browser;
+  headlessBrowser: plugins.smartpuppeteer.puppeteer.Browser;
+  externalBrowserBool: boolean = false;
   private _readyDeferred: plugins.smartpromise.Deferred<void>;
   private _candidates: { [key: string]: PdfCandidate } = {};
 
   constructor() {
     this._readyDeferred = new plugins.smartpromise.Deferred();
-    this.init();
   }
 
-  async init() {
+  async start(headlessBrowserArg?: plugins.smartpuppeteer.puppeteer.Browser) {
+    const done = plugins.smartpromise.defer();
+    // lets set the external browser in case one is provided
+    this.headlessBrowser = headlessBrowserArg;
     // setup puppeteer
-    this.headlessBrowser = await plugins.puppeteer.launch();
+    if (this.headlessBrowser) {
+      this.externalBrowserBool = true;
+    } else {
+      this.headlessBrowser = await plugins.smartpuppeteer.getEnvAwareBrowserInstance({
+        forceNoSandbox: false,
+      });
+    }
 
     // setup server
     const app = plugins.express();
     app.get('/:pdfId', (req, res) => {
-      res.setHeader('PDF-ID', this._candidates[req.params.pdfId].pdfId);
-      res.send(this._candidates[req.params.pdfId].htmlString);
+      const wantedCandidate = this._candidates[req.params.pdfId];
+      if (!wantedCandidate) {
+        console.log(`${req.url} not attached to a candidate`);
+        return;
+      }
+      res.setHeader('pdf-id', wantedCandidate.pdfId);
+      res.send(wantedCandidate.htmlString);
     });
     this.htmlServerInstance = plugins.http.createServer(app);
     const smartnetworkInstance = new plugins.smartnetwork.SmartNetwork();
-    const portAvailable = smartnetworkInstance.isLocalPortAvailable(3210);
+    const portAvailable = smartnetworkInstance.isLocalPortUnused(3210);
     this.htmlServerInstance.listen(3210, 'localhost');
     this.htmlServerInstance.on('listening', () => {
       this._readyDeferred.resolve();
+      done.resolve();
     });
+    await done.promise;
   }
 
-  async close () {
+  // stop
+  async stop() {
     const done = plugins.smartpromise.defer<void>();
     this.htmlServerInstance.close(() => {
       done.resolve();
     });
-    await this.headlessBrowser.close();
+
+    if (!this.externalBrowserBool) {
+      await this.headlessBrowser.close();
+    }
+
     await done.promise;
-  } 
+  }
 
   /**
-   * returns a pdf for a given html string;
+   * Returns a PDF for a given HTML string.
    */
-  async getPdfForHtmlString(htmlStringArg: string) {
+  async getA4PdfResultForHtmlString(htmlStringArg: string): Promise<plugins.tsclass.business.IPdf> {
     await this._readyDeferred.promise;
     const pdfCandidate = new PdfCandidate(htmlStringArg);
     this._candidates[pdfCandidate.pdfId] = pdfCandidate;
     const page = await this.headlessBrowser.newPage();
+    await page.setViewport({
+      width: 794,
+      height: 1122,
+    });
     const response = await page.goto(`http://localhost:3210/${pdfCandidate.pdfId}`, {
-      waitUntil: 'networkidle2'
+      waitUntil: 'networkidle2',
     });
     const headers = response.headers();
     if (headers['pdf-id'] !== pdfCandidate.pdfId) {
@@ -62,24 +98,255 @@ export class SmartPdf {
       console.log(`id security check passed for ${pdfCandidate.pdfId}`);
     }
 
-    await page.pdf({
-      path: plugins.path.join(paths.pdfDir, `${pdfCandidate.pdfId}.pdf`),
-      format: 'A4'
+    const pdfBuffer = await page.pdf({
+      width: 794,
+      height: 1122,
+      printBackground: true,
+      displayHeaderFooter: false,
     });
+    // Convert Uint8Array to Node Buffer
+    const nodePdfBuffer = Buffer.from(pdfBuffer);
     await page.close();
     delete this._candidates[pdfCandidate.pdfId];
     pdfCandidate.doneDeferred.resolve();
     await pdfCandidate.doneDeferred.promise;
+    return {
+      id: pdfCandidate.pdfId,
+      name: `${pdfCandidate.pdfId}.js`,
+      metadata: {
+        textExtraction: await this.extractTextFromPdfBuffer(nodePdfBuffer),
+      },
+      buffer: nodePdfBuffer,
+    };
   }
 
-  async getPdfForWebsite(websiteUrl: string) {
+  async getPdfResultForWebsite(websiteUrl: string): Promise<plugins.tsclass.business.IPdf> {
     const page = await this.headlessBrowser.newPage();
+    await page.setViewport({
+      width: 1980,
+      height: 1200,
+    });
+    await page.emulateMediaType('screen');
     const response = await page.goto(websiteUrl, { waitUntil: 'networkidle2' });
     const pdfId = plugins.smartunique.shortId();
-    await page.pdf({
-      path: plugins.path.join(paths.pdfDir, `${pdfId}.pdf`),
-      format: 'A4'
+    const { documentHeight, documentWidth } = await page.evaluate(() => {
+      return {
+        documentHeight: document.height,
+        documentWidth: document.width,
+      };
     });
+    const pdfBuffer = await page.pdf({
+      height: documentHeight,
+      width: documentWidth,
+      printBackground: true,
+      displayHeaderFooter: false,
+    });
+    // Convert Uint8Array to Node Buffer
+    const nodePdfBuffer = Buffer.from(pdfBuffer);
     await page.close();
+    return {
+      id: pdfId,
+      name: `${pdfId}.js`,
+      metadata: {
+        textExtraction: await this.extractTextFromPdfBuffer(nodePdfBuffer),
+      },
+      buffer: nodePdfBuffer,
+    };
   }
-}
+
+  async getFullWebsiteAsSinglePdf(websiteUrl: string): Promise<plugins.tsclass.business.IPdf> {
+    const page = await this.headlessBrowser.newPage();
+    await page.setViewport({
+      width: 1920,
+      height: 1200,
+    });
+    await page.emulateMediaType('screen');
+    const response = await page.goto(websiteUrl, { waitUntil: 'networkidle2' });
+    const pdfId = plugins.smartunique.shortId();
+    // Use both document.body and document.documentElement to ensure we have a valid height and width.
+    const { documentHeight, documentWidth } = await page.evaluate(() => {
+      return {
+        documentHeight: Math.max(
+          document.body.scrollHeight,
+          document.documentElement.scrollHeight
+        ) || 1200,
+        documentWidth: Math.max(
+          document.body.clientWidth,
+          document.documentElement.clientWidth
+        ) || 1920,
+      };
+    });
+    // Update viewport height to the full document height.
+    await page.setViewport({
+      width: 1920,
+      height: documentHeight,
+    });
+    const pdfBuffer = await page.pdf({
+      height: documentHeight,
+      width: 1920,
+      printBackground: true,
+      displayHeaderFooter: false,
+      scale: 1,
+      pageRanges: '1',
+    });
+    // Convert Uint8Array to Node Buffer
+    const nodePdfBuffer = Buffer.from(pdfBuffer);
+    await page.close();
+    return {
+      id: pdfId,
+      name: `${pdfId}.js`,
+      metadata: {
+        textExtraction: await this.extractTextFromPdfBuffer(nodePdfBuffer),
+      },
+      buffer: nodePdfBuffer,
+    };
+  }
+
+  public async mergePdfs(inputPdfBuffers: Uint8Array[]): Promise<Uint8Array> {
+    const mergedPdf = await plugins.pdfLib.PDFDocument.create();
+    for (const pdfBytes of inputPdfBuffers) {
+      const pdfDoc = await plugins.pdfLib.PDFDocument.load(pdfBytes);
+      const pages = await mergedPdf.copyPages(pdfDoc, pdfDoc.getPageIndices());
+      pages.forEach((page) => mergedPdf.addPage(page));
+    }
+
+    const mergedPdfBytes = await mergedPdf.save();
+    return mergedPdfBytes;
+  }
+
+  public async readFileToPdfObject(pathArg: string): Promise<plugins.tsclass.business.IPdf> {
+    const absolutePath = plugins.smartpath.transform.makeAbsolute(pathArg);
+    const parsedPath = plugins.path.parse(absolutePath);
+    const buffer = await plugins.smartfile.fs.toBuffer(absolutePath);
+    return {
+      name: parsedPath.base,
+      buffer,
+      id: null,
+      metadata: null,
+    };
+  }
+
+  public async extractTextFromPdfBuffer(pdfBufferArg: Buffer): Promise<string> {
+    const deferred = plugins.smartpromise.defer<string>();
+    const pdfParser: any = new plugins.pdf2json();
+    pdfParser.on('pdfParser_dataReady', (pdfData: any) => {
+      let finalText = '';
+      for (const page of pdfData.Pages) {
+        for (const text of page.Texts) {
+          for (const letter of text.R) {
+            finalText = finalText + letter.T;
+          }
+        }
+      }
+      deferred.resolve(finalText);
+    });
+    pdfParser.parseBuffer(pdfBufferArg);
+    return deferred.promise;
+  }
+
+  /**
+   * Checks for the presence of required dependencies: GraphicsMagick and Ghostscript.
+   */
+  private async checkDependencies(): Promise<void> {
+    await Promise.all([
+      this.checkCommandExists('gm', ['version']),
+      this.checkCommandExists('gs', ['--version']),
+    ]);
+  }
+
+  /**
+   * Checks if a given command exists by trying to execute it.
+   */
+  private checkCommandExists(command: string, args: string[]): Promise<void> {
+    return new Promise((resolve, reject) => {
+      execFile(command, args, (error, stdout, stderr) => {
+        if (error) {
+          reject(new Error(`Dependency check failed: ${command} is not installed or not in the PATH. ${error.message}`));
+        } else {
+          resolve();
+        }
+      });
+    });
+  }
+
+  /**
+   * Converts a PDF to PNG bytes for each page using Puppeteer and PDF.js.
+   * This method creates a temporary HTML page that loads PDF.js from a CDN,
+   * renders each PDF page to a canvas, and then screenshots each canvas element.
+   */
+  public async convertPDFToPngBytes(
+    pdfBytes: Uint8Array,
+    options: { width?: number; height?: number; quality?: number } = {}
+  ): Promise<Uint8Array[]> {
+    // Note: options.width, options.height, and options.quality are not applied here,
+    // as the rendered canvas size is determined by the PDF page dimensions.
+
+    // Create a new page using the headless browser.
+    const page = await this.headlessBrowser.newPage();
+
+    // Prepare PDF data as a base64 string.
+    const base64Pdf: string = Buffer.from(pdfBytes).toString('base64');
+
+    // HTML template that loads PDF.js and renders the PDF.
+    const htmlTemplate: string = `
+      <!DOCTYPE html>
+      <html>
+        <head>
+          <meta charset="utf-8">
+          <title>PDF to PNG Converter</title>
+          <style>
+            body { margin: 0; }
+            canvas { display: block; margin: 10px auto; }
+          </style>
+          <script src="https://cdnjs.cloudflare.com/ajax/libs/pdf.js/2.16.105/pdf.min.js"></script>
+        </head>
+        <body>
+          <script>
+            (async function() {
+              pdfjsLib.GlobalWorkerOptions.workerSrc = 'https://cdnjs.cloudflare.com/ajax/libs/pdf.js/2.16.105/pdf.worker.min.js';
+              const pdfData = "__PDF_DATA__";
+              const raw = atob(pdfData);
+              const pdfArray = new Uint8Array([...raw].map(c => c.charCodeAt(0)));
+              const loadingTask = pdfjsLib.getDocument({data: pdfArray});
+              const pdf = await loadingTask.promise;
+              const numPages = pdf.numPages;
+              for (let pageNum = 1; pageNum <= numPages; pageNum++) {
+                const page = await pdf.getPage(pageNum);
+                const viewport = page.getViewport({ scale: 1.0 });
+                const canvas = document.createElement('canvas');
+                const context = canvas.getContext('2d');
+                canvas.width = viewport.width;
+                canvas.height = viewport.height;
+                await page.render({ canvasContext: context, viewport: viewport }).promise;
+                document.body.appendChild(canvas);
+              }
+              window.renderComplete = true;
+            })();
+          </script>
+        </body>
+      </html>
+    `;
+
+    // Replace the placeholder with the actual base64 PDF data.
+    const htmlContent: string = htmlTemplate.replace("__PDF_DATA__", base64Pdf);
+
+    // Set the page content.
+    await page.setContent(htmlContent, { waitUntil: 'networkidle0' });
+
+    // Wait until the PDF.js rendering is complete.
+    await page.waitForFunction(() => (window as any).renderComplete === true, { timeout: 30000 });
+
+    // Query all canvas elements (each representing a rendered PDF page).
+    const canvasElements = await page.$$('canvas');
+    const pngBuffers: Uint8Array[] = [];
+
+    for (const canvasElement of canvasElements) {
+      // Screenshot the canvas element. The screenshot will be a PNG buffer.
+      const screenshotBuffer = (await canvasElement.screenshot({ encoding: 'binary' })) as Buffer;
+      pngBuffers.push(new Uint8Array(screenshotBuffer));
+    }
+
+    await page.close();
+    return pngBuffers;
+  }
+}

ts/smartpdf.paths.ts

@@ -1,6 +1,6 @@
-import * as plugins from './smartpdf.plugins';
+import * as plugins from './smartpdf.plugins.js';
 
-export const packageDir = plugins.path.join(__dirname, '../');
-export const pdfDir = plugins.path.join(packageDir, 'assets/pdfdir');
-
-plugins.smartfile.fs.ensureDirSync(pdfDir);
+export const packageDir = plugins.path.join(
+  plugins.smartpath.get.dirnameFromImportMetaUrl(import.meta.url),
+  '../'
+);

ts/smartpdf.plugins.ts

@@ -5,15 +5,34 @@ import * as path from 'path';
 export { http, path };
 
 // @pushrocks
-import * as smartfile from '@pushrocks/smartfile';
-import * as smartpromise from '@pushrocks/smartpromise';
-import * as smartnetwork from '@pushrocks/smartnetwork';
-import * as smartunique from '@pushrocks/smartunique';
+import * as smartbuffer from '@push.rocks/smartbuffer';
+import * as smartfile from '@push.rocks/smartfile';
+import * as smartdelay from '@push.rocks/smartdelay';
+import * as smartpromise from '@push.rocks/smartpromise';
+import * as smartpath from '@push.rocks/smartpath';
+import * as smartpuppeteer from '@push.rocks/smartpuppeteer';
+import * as smartnetwork from '@push.rocks/smartnetwork';
+import * as smartunique from '@push.rocks/smartunique';
 
-export { smartfile, smartpromise, smartunique, smartnetwork };
+export {
+  smartbuffer,
+  smartfile,
+  smartdelay,
+  smartpromise,
+  smartpath,
+  smartpuppeteer,
+  smartunique,
+  smartnetwork,
+};
+
+// tsclass scope
+import * as tsclass from '@tsclass/tsclass';
+
+export { tsclass };
 
 // thirdparty
-import * as express from 'express';
-import * as puppeteer from 'puppeteer';
+import express from 'express';
+import pdf2json from 'pdf2json';
+import pdfLib from 'pdf-lib';
 
-export { express, puppeteer };
+export { express, pdf2json, pdfLib, };

tsconfig.json

@@ -0,0 +1,14 @@
+{
+  "compilerOptions": {
+    "experimentalDecorators": true,
+    "useDefineForClassFields": false,
+    "target": "ES2022",
+    "module": "NodeNext",
+    "moduleResolution": "NodeNext",
+    "esModuleInterop": true,
+    "verbatimModuleSyntax": true
+  },
+  "exclude": [
+    "dist_*/**/*.d.ts"
+  ]
+}

tslint.json

@@ -1,7 +0,0 @@
-{
-    "extends": ["tslint:latest", "tslint-config-prettier"],
-    "rules": {
-      "semicolon": [true, "always"]
-    }
-  }
-