Document Processing documentprocessing
documentprocessing
/ custom-template-processing-with-pandoc-api.java
Created
June 21, 2025 08:06
Custom Template Processing with Pandoc API
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import com.github.davidmoten.pandoc.Pandoc; | |
| import java.nio.file.*; | |
| import java.util.*; | |
| /** | |
| * Generates legal contracts using custom Pandoc templates with dynamic variables. | |
| * Features: | |
| * - YAML front-matter injection for client-specific terms | |
| * - Conditional clauses via Pandoc filters | |
| * - Multi-format output (PDF for signing, DOCX for editing) |
documentprocessing
/ html-to-docx-conversion-pandoc.java
Created
June 21, 2025 08:03
HTML to DOCX Conversion using Java
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import com.github.davidmoten.pandoc.Pandoc; | |
| import java.io.*; | |
| /** | |
| * Converts HTML business reports to MS Word (DOCX) with corporate styling. | |
| * Features: | |
| * - Preserves tables, images, and CSS classes from HTML | |
| * - Applies custom DOCX template (e.g., company-branded styles) | |
| * - Handles embedded base64 images | |
| * - Post-processes with Office-Open-XML (OOXML) hooks |
documentprocessing
/ convert-markdown-to-pdf-with-latext-support.java
Created
June 21, 2025 07:57
Converting Markdown to PDF with LaTeX support in Java
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import com.github.davidmoten.pandoc.Pandoc; | |
| import java.io.IOException; | |
| import java.nio.file.Files; | |
| import java.nio.file.Paths; | |
| /** | |
| * Converts academic Markdown (with LaTeX math and citations) to PDF using Pandoc. | |
| * Requires: | |
| * - Pandoc installed (v2.11+) | |
| * - LaTeX distribution (e.g., TeX Live/MiKTeX) |
documentprocessing
/ add-annotations-to-pdf.java
Created
June 10, 2025 06:47
Add Annotations to PDF using PDFClown API in Java
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| // Import PDF Clown annotation and action classes | |
| import org.pdfclown.documents.Document; | |
| import org.pdfclown.documents.Page; | |
| import org.pdfclown.documents.interaction.annotations.Link; | |
| import org.pdfclown.documents.interaction.actions.GoToURI; | |
| import org.pdfclown.files.File; | |
| import org.pdfclown.documents.interaction.navigation.document.Destination; | |
| import org.pdfclown.documents.interaction.navigation.document.LocalDestination; | |
| import java.awt.geom.Rectangle2D; |
documentprocessing
/ extract-text-from-pdf-using-pdfclown.java
Created
June 10, 2025 06:44
Extract Text from PDF with PDF Clown Java API
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| // Import PDF Clown text extraction classes | |
| import org.pdfclown.documents.Document; | |
| import org.pdfclown.documents.Page; | |
| import org.pdfclown.files.File; | |
| import org.pdfclown.tools.TextExtractor; | |
| public class ExtractTextFromPDF { | |
| public static void main(String[] args) { | |
| try { | |
| // 1. Load an existing PDF file |
documentprocessing
/ create-pdf-with-pdfclown-api.java
Created
June 10, 2025 06:42
Create PDF using PDF Clown API for Java
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| // Import PDF Clown core classes | |
| import org.pdfclown.documents.Document; | |
| import org.pdfclown.documents.Page; | |
| import org.pdfclown.documents.contents.composition.PrimitiveComposer; | |
| import org.pdfclown.documents.contents.fonts.StandardType1Font; | |
| import org.pdfclown.files.File; | |
| import java.awt.geom.Point2D; | |
| public class CreateBasicPDF { |
documentprocessing
/ generate-pdf-a-compliant-docuement.java
Created
June 2, 2025 16:13
Generate PDF/A Compliant Document in Java
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import com.lowagie.text.Document; | |
| import com.lowagie.text.Font; | |
| import com.lowagie.text.FontFactory; | |
| import com.lowagie.text.Paragraph; | |
| import com.lowagie.text.pdf.PdfAConformanceLevel; | |
| import com.lowagie.text.pdf.PdfAWriter; | |
| import com.lowagie.text.pdf.PdfReader; | |
| import com.lowagie.text.pdf.ICC_Profile; | |
| import java.io.FileOutputStream; | |
| import java.io.InputStream; |
documentprocessing
/ add-table-to-pdf.java
Created
June 2, 2025 16:11
Add a Table to a PDF with OpenPDF Java API
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import com.lowagie.text.Document; | |
| import com.lowagie.text.Font; | |
| import com.lowagie.text.FontFactory; | |
| import com.lowagie.text.Paragraph; | |
| import com.lowagie.text.pdf.PdfPTable; | |
| import com.lowagie.text.pdf.PdfWriter; | |
| import java.io.FileOutputStream; | |
| public class PdfTableExample { | |
| public static void main(String[] args) { |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import com.lowagie.text.Document; | |
| import com.lowagie.text.Font; | |
| import com.lowagie.text.FontFactory; | |
| import com.lowagie.text.Paragraph; | |
| import com.lowagie.text.pdf.PdfWriter; | |
| import java.io.FileOutputStream; | |
| public class SimplePdfCreator { | |
| public static void main(String[] args) { | |
| // Step 1: Create a Document object |
documentprocessing
/ modify-html-of-an-element.java
Created
May 27, 2025 15:28
Modify HTML of an Element in Java with jsoup API
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Element div = doc.select("div").first(); // <div></div> | |
| div.html("<p>lorem ipsum</p>"); // <div><p>lorem ipsum</p></div> | |
| div.prepend("<p>First</p>"); | |
| div.append("<p>Last</p>"); | |
| // now: <div><p>First</p><p>lorem ipsum</p><p>Last</p></div> | |
| Element span = doc.select("span").first(); // <span>One</span> | |
| span.wrap("<li><a href='http://example.com/'></a></li>"); | |
| // now: <li><a href="http://example.com"><span>One</span></a></li> |
NewerOlder