PDFParseDocumentStructureOptions Enumeration

Summary

Specifies options to use when parsing a PDF document structure.

Syntax

C++/CLI

Java

Python

[SerializableAttribute()] 
[FlagsAttribute()] 
public enum PDFParseDocumentStructureOptions

public final class PDFParseDocumentStructureOptions 
    extends java.lang.Enum<PDFParseDocumentStructureOptions>

[FlagsAttribute()] 
[SerializableAttribute()] 
public enum class PDFParseDocumentStructureOptions

class PDFParseDocumentStructureOptions(Enum): 
   None = 0 
   Bookmarks = 1 
   InternalLinks = 2 
   Images = 4 
   Fonts = 8 
   EmbeddedFiles = 16 
   All = 31

Members

Value	Member	Description
0x00000000	None	Do not parse anything.
0x00000001	Bookmarks	Parse the bookmarks that constitute the document's Table of Contents (TOC). This option populates the PDFDocument.Bookmarks property.
0x00000002	InternalLinks	Parse the internal links (or jumps) between the pages found in the document. This option populates the PDFDocument.InternalLinks property.
0x00000004	Images	Parse the images found in the document. This option populates the PDFDocument.Images property.
0x00000008	Fonts	Parse the fonts found in the document. This option populates the PDFDocument.Fonts property.
0x0000001F	All	Parse bookmarks, internal links, images, fonts and embedded files.
0x00000010	EmbeddedFiles	Parse embedded files.

Remarks

The PDFParseDocumentStructureOptions enumeration is used as the type of the options parameter passed to the PDFDocument.ParseDocumentStructure method.

The structure of PDF document is its Table of Contents (TOC) which consists of the PDFBookmark objects saved in the document and the collection of the internal links (or jumps) between the pages that are found in all the pages (PDFInternalLink objects).

When a PDFDocument object is created, the value of PDFDocument.Bookmarks and PDFDocument.InternalLinks will be initialized to null. You must call the PDFDocument.ParseDocumentStructure method to parse the items of interest (determined by the PDFParseDocumentStructureOptions passed as the options parameter to the method). This is done for performance reasons and to make it possible to parse only the objects of interest.

You can parse either the bookmarks or the internal links or both of a PDF document using the PDFDocument.ParseDocumentStructure method. When the method returns, the PDFDocument will be updated as follows:

If PDFParseDocumentStructureOptions.Bookmarks is specified, then the PDFDocument.Bookmarks collection will be populated with a PDFBookmark object for each bookmark item found in the document. If no bookmarks are found in the document, PDFDocument.Bookmarks will be initialized with an empty collection (PDFDocument.Bookmarks.Count will be 0).
If PDFParseDocumentStructureOptions.InternalLinks is specified, then the PDFDocument.InternalLinks collection will be populated with a PDFInternalLink object for each internal link (or jump) item found in the document. If no internal links are found in the document, the PDFDocument.InternalLinks will be initialized with an empty collection (PDFDocument.InternalLinks.Count will be 0).

The values of PDFParseDocumentStructureOptions can be OR'ed together.

Example

Java

using Leadtools; 
using Leadtools.Codecs; 
using Leadtools.Controls; 
using Leadtools.Pdf; 
using Leadtools.Svg; 
using Leadtools.WinForms; 
 
 
public void PDFDocumentParseDocumentStructureExample() 
{ 
   string pdfFileName1 = Path.Combine(LEAD_VARS.ImagesDir, @"Leadtools.pdf"); 
   string pdfFileName2 = Path.Combine(LEAD_VARS.ImagesDir, @"Bookmarks.pdf"); 
 
   // Create a version of the source file with a few bookmarks 
   PDFFile file = new PDFFile(pdfFileName1); 
   // Load the pages 
   file.Load(); 
   List<PDFBookmark> bookmarks = new List<PDFBookmark>(); 
 
   // We will bookmarks for each page, cascading levels: 
   // Goto page 1 
   //    Goto page 2 
   //       Goto page 3 
   //          Goto page 4 
   int level = 0; 
   for (int i = 0; i < file.Pages.Count; i++) 
   { 
      PDFFilePage page = file.Pages[i]; 
 
      PDFBookmark bookmark = new PDFBookmark(); 
      bookmark.Title = "Goto page " + page.PageNumber.ToString(); 
      bookmark.BookmarkStyle = PDFBookmarkStyle.Plain; 
      bookmark.Level = level; 
      bookmark.TargetPageNumber = page.PageNumber; 
      bookmark.TargetPageFitType = PDFPageFitType.Default; 
      bookmark.TargetPosition = new PDFPoint(0, page.Height); 
      bookmark.TargetZoomPercent = 0; 
      bookmarks.Add(bookmark); 
 
      level++; 
      if (level > 8) 
      { 
         // Reset levels 
         level = 0; 
      } 
   } 
 
   file.WriteBookmarks(bookmarks, pdfFileName2); 
 
   // Create a document for the output file 
   using (PDFDocument document = new PDFDocument(pdfFileName2)) 
   { 
      // Now read the bookmarks and internal links in the document 
      document.ParseDocumentStructure(PDFParseDocumentStructureOptions.InternalLinks | PDFParseDocumentStructureOptions.Bookmarks); 
 
      Console.WriteLine("{0} bookmarks found:", document.Bookmarks.Count); 
      foreach (PDFBookmark bookmark in document.Bookmarks) 
      { 
         Console.WriteLine(" Title: {0}, Level: {1}, Target page: {2}", bookmark.Title, bookmark.Level, bookmark.TargetPageNumber); 
      } 
 
      Console.WriteLine("{0} Internal links found:", document.InternalLinks.Count); 
      foreach (PDFInternalLink internalLink in document.InternalLinks) 
      { 
         Console.WriteLine(" Source bounds: {0}, Target page: {1}", internalLink.SourceBounds, internalLink.TargetPageNumber); 
      } 
   } 
} 
 
static class LEAD_VARS 
{ 
   public const string ImagesDir = @"C:\LEADTOOLS23\Resources\Images"; 
}

 
import java.io.BufferedWriter; 
import java.io.Console; 
import java.io.File; 
import java.io.FileWriter; 
import java.io.IOException; 
import java.io.OutputStream; 
import java.io.OutputStreamWriter; 
import java.nio.Buffer; 
import java.nio.file.Files; 
import java.nio.file.Path; 
import java.nio.file.Paths; 
import java.nio.file.StandardOpenOption; 
import java.sql.Date; 
import java.text.SimpleDateFormat; 
import java.time.LocalDateTime; 
import java.util.ArrayList; 
import java.util.List; 
 
import javax.xml.validation.Schema; 
 
import org.apache.lucene.store.Directory; 
import org.junit.*; 
import org.junit.runner.JUnitCore; 
import org.junit.runner.Result; 
import org.junit.runner.notification.Failure; 
import static org.junit.Assert.*; 
 
import leadtools.*; 
import leadtools.barcode.*; 
import leadtools.codecs.*; 
import leadtools.pdf.*; 
import leadtools.svg.*; 
 
 
public void pdfDocumentParseDocumentStructureExample() { 
   String LEAD_VARS_ImagesDir = "C:\\LEADTOOLS23\\Resources\\Images"; 
   String pdfFileName1 = combine(LEAD_VARS_ImagesDir, "Leadtools.pdf"); 
   String pdfFileName2 = combine(LEAD_VARS_ImagesDir, "Bookmarks.pdf"); 
 
   // Create a version of the source file with a few bookmarks 
   PDFFile file = new PDFFile(pdfFileName1); 
   // Load the pages 
   file.load(); 
   ArrayList<PDFBookmark> bookmarks = new ArrayList<PDFBookmark>(); 
 
   // We will bookmarks for each page, cascading levels: 
   // Goto page 1 
   // Goto page 2 
   // Goto page 3 
   // Goto page 4 
   int level = 0; 
   for (int i = 0; i < file.getPageCount(); i++) { 
 
      PDFFilePage page = file.getPages().get(i); 
      PDFBookmark bookmark = new PDFBookmark(); 
      bookmark.setTitle("Goto page " + page.getPageNumber()); 
      bookmark.setBookmarkStyle(PDFBookmarkStyle.PLAIN); 
      bookmark.setLevel(level); 
      bookmark.setTargetPageNumber(page.getPageNumber()); 
      bookmark.setTargetPageFitType(PDFPageFitType.DEFAULT); 
      bookmark.setTargetPosition(new PDFPoint(0, page.getHeight())); 
      bookmark.setTargetZoomPercent(0); 
      bookmarks.add(bookmark); 
 
      level++; 
      if (level > 8) { 
         // Reset levels 
         level = 0; 
      } 
 
   } 
   file.writeBookmarks(bookmarks, pdfFileName2); 
 
   // Create a document for the output file 
   PDFDocument document = new PDFDocument(pdfFileName2); 
   // Now read the bookmarks and internal links in the document 
   document.parseDocumentStructure(PDFParseDocumentStructureOptions.INTERNAL_LINKS.getValue() 
         | PDFParseDocumentStructureOptions.BOOKMARKS.getValue()); 
 
   System.out.printf("%1s bookmarks found:%n", document.getBookmarks().size()); 
   assertTrue(document.getBookmarks().size() == 25); 
   for (PDFBookmark bookmark : document.getBookmarks()) { 
      System.out.printf(" Title: %1s, Level: %2s, Target page: %3s%n", bookmark.getTitle(), bookmark.getLevel(), 
            bookmark.getTargetPageNumber()); 
   } 
 
   System.out.printf("%1s Internal links found:%n", document.getInternalLinks().size()); 
   assertTrue(document.getInternalLinks().size() == 18); 
   for (PDFInternalLink internalLink : document.getInternalLinks()) { 
      System.out.printf(" Source bounds: %1s, Target page: %2s%n", internalLink.getSourceBounds(), 
            internalLink.getTargetPageNumber()); 
   } 
 
}

Requirements

Target Platforms

Reference

Leadtools.Pdf Namespace

Download our FREE evaluation

Help Version 23.0.2024.2.29

Leadtools.Pdf Assembly

Introduction

Getting Started

Namespaces

Leadtools.Pdf Namespace

Assemblies