←Select platform

EmptyPageMode Property

Summary

Determines how empty pages are treated during the conversion.

Syntax
C#
C++/CLI
Java
Python
public DocumentConverterEmptyPageMode EmptyPageMode { get; set; } 
public:  
   property DocumentConverterEmptyPageMode^ EmptyPageMode 
   { 
      DocumentConverterEmptyPageMode^ get() 
      void set(DocumentConverterEmptyPageMode^ value) 
   } 
public DocumentConverterEmptyPageMode getEmptyPageMode() 
public void setEmptyPageMode(DocumentConverterEmptyPageMode value) 
EmptyPageMode # get and set (DocumentConverterOptions)

Property Value

Determines how empty pages are treated during the conversion. Default value is DocumentConverterEmptyPageMode.None.

Remarks

This option controls how the document converter treats empty pages during the conversion as follows:

Value Description

DocumentConverterEmptyPageMode.None

Do not do anything special. No detection is performed and empty pages will be added to the output document and the result is guaranteed to have the same number of pages as the input. This is the default behavior.

DocumentConverterEmptyPageMode.Skip

Empty pages are skipped and not added to the final document. If the user instructs the converter to use the annotations during conversion, then any page that is empty but has an annotation container with objects is considered none-empty and is added to the output document.

DocumentConverterEmptyPageMode.SkipIgnoreAnnotations

Similar to Empty with the annotations ignored. Empty pages are skipped even if they have annotations.

The document converter uses the following to detect if a page is empty:

  • If raster conversion is used, a BlankPageDetectorCommand image processing command with the options from DocumentConverterPreprocessor.BlankPageDetectorCommandFlags is run on the raster image to detect if the page is empty. The user can select other options that the default of BlankPageDetectorCommandFlags.None which only detects if the page is fully empty, for example, using margins and ignoring noise or bleed through.

  • If SVG conversion is used, the converter will enumerate all the elements in the page's SVG document object. The page is considered empty if it does not contain any elements besides the root <svg> element.

Example

This example creates a test document of four pages with the second page empty (all white). It will then use the document converter to generate an output document with and without skipping empty pages.

C#
Java
using Leadtools; 
using Leadtools.Codecs; 
using Leadtools.Document.Writer; 
using Leadtools.Svg; 
using LeadtoolsExamples.Common; 
using Leadtools.Document; 
using Leadtools.Caching; 
using Leadtools.Annotations.Engine; 
using Leadtools.Ocr; 
using Leadtools.Document.Converter; 
using Leadtools.Annotations.Rendering; 
 
public static void Run() 
{ 
   var inputDocumentFile = @"C:\LEADTOOLS22\Resources\Images\EmptyPageTestInput.tif"; 
   var outputDocumentFile1 = @"C:\LEADTOOLS22\Resources\Images\NoSkipping.tif"; 
   var outputDocumentFile2 = @"C:\LEADTOOLS22\Resources\Images\SkippingEmptyPages.tif"; 
 
   // Create a multi-page TIF file that is 4 pages with the second page empty 
   CreateTestDocumentFile(inputDocumentFile); 
 
   using (DocumentConverter documentConverter = new DocumentConverter()) 
   { 
      documentConverter.Diagnostics.EnableTrace = true; 
 
      // Make sure the options are set to not skip empty pages 
      documentConverter.Options.EmptyPageMode = DocumentConverterEmptyPageMode.None; 
 
      // Create a job to convert the input document to the first output file and run it 
      var jobData = DocumentConverterJobs.CreateJobData(inputDocumentFile, outputDocumentFile1, RasterImageFormat.CcittGroup4); 
      jobData.JobName = "No skipping empty pages"; 
      var job = documentConverter.Jobs.CreateJob(jobData); 
      documentConverter.Jobs.RunJob(job); 
 
      // Now, tell the document converter to skip empty pagess 
      documentConverter.Options.EmptyPageMode = DocumentConverterEmptyPageMode.SkipIgnoreAnnotations; 
      // And create a job to convert the input document to the second output file and run it 
      jobData = DocumentConverterJobs.CreateJobData(inputDocumentFile, outputDocumentFile2, RasterImageFormat.CcittGroup4); 
      jobData.JobName = "Skipping empty pages"; 
      job = documentConverter.Jobs.CreateJob(jobData); 
      documentConverter.Jobs.RunJob(job); 
 
      Console.WriteLine("Finished, checking the number of pages"); 
 
      // Show the number of pages in the first and second document, should report 4 and 3 
      using (var rasterCodecs = new RasterCodecs()) 
      { 
         var pageCount = rasterCodecs.GetTotalPages(outputDocumentFile1); 
         Console.WriteLine("First job did not skip any pages and produced {0} pages, should be 4", pageCount); 
         pageCount = rasterCodecs.GetTotalPages(outputDocumentFile2); 
         Console.WriteLine("Second job skipped the empty pages and produced {0} pages, should be 3", pageCount); 
      } 
   } 
} 
 
private static void CreateTestDocumentFile(string fileName) 
{ 
   var pageTemplateFile = @"C:\LEADTOOLS22\Resources\Images\Ocr{0}.tif"; 
 
   using (var rasterCodecs = new RasterCodecs()) 
   { 
      rasterCodecs.Options.RasterizeDocument.Load.Resolution = 300; 
 
      CodecsSavePageMode savePageMode = CodecsSavePageMode.Overwrite; 
 
      for (var pageNumber = 1; pageNumber <= 4; pageNumber++) 
      { 
         if (pageNumber != 2) 
         { 
            using (var rasterImage = rasterCodecs.Load(string.Format(pageTemplateFile, pageNumber), 1)) 
            { 
               // Add it to the output document 
               rasterCodecs.Save(rasterImage, fileName, RasterImageFormat.CcittGroup4, 1, 1, 1, -1, savePageMode); 
               savePageMode = CodecsSavePageMode.Append; 
 
               if (pageNumber == 1) 
               { 
                  // Save an empty page (all white) the same size as the previous page 
                  using (var emptyPage = RasterImage.Create( 
                     rasterImage.Width, 
                     rasterImage.Height, 
                     rasterImage.BitsPerPixel, 
                     rasterImage.XResolution, 
                     RasterColor.FromKnownColor(RasterKnownColor.White))) 
                  { 
                     rasterCodecs.Save(emptyPage, fileName, RasterImageFormat.CcittGroup4, 1, 1, 1, -1, savePageMode); 
                  } 
               } 
            } 
         } 
      } 
   } 
} 
 
import static org.junit.Assert.assertTrue; 
 
import java.io.File; 
import java.io.FileOutputStream; 
import java.io.IOException; 
import java.net.URI; 
import java.util.concurrent.Executors; 
import java.util.logging.ConsoleHandler; 
import java.util.logging.Handler; 
import java.util.logging.Level; 
import java.util.logging.Logger; 
 
import org.junit.*; 
import org.junit.runner.JUnitCore; 
import org.junit.runner.Result; 
import org.junit.runner.notification.Failure; 
 
import leadtools.*; 
import leadtools.annotations.rendering.AnnJavaRenderingEngine; 
import leadtools.caching.FileCache; 
import leadtools.codecs.*; 
import leadtools.document.DocumentFactory; 
import leadtools.document.DownloadDocumentOptions; 
import leadtools.document.LEADDocument; 
import leadtools.document.LoadDocumentOptions; 
import leadtools.document.LoadFromCacheOptions; 
import leadtools.document.UploadDocumentOptions; 
import leadtools.document.converter.DocumentConverter; 
import leadtools.document.converter.DocumentConverterEmptyPageMode; 
import leadtools.document.converter.DocumentConverterJob; 
import leadtools.document.converter.DocumentConverterJobData; 
import leadtools.document.converter.DocumentConverterJobError; 
import leadtools.document.converter.DocumentConverterJobErrorMode; 
import leadtools.document.converter.DocumentConverterJobStatus; 
import leadtools.document.converter.DocumentConverterJobs; 
import leadtools.document.writer.DocumentFormat; 
import leadtools.document.writer.DocumentWriter; 
import leadtools.ocr.OcrEngine; 
import leadtools.ocr.OcrEngineManager; 
import leadtools.ocr.OcrEngineType; 
 
 
public void documentConverterEmptyPageMode() { 
   String LEAD_VARS_ImagesDir = "C:\\LEADTOOLS23\\Resources\\Images"; 
   String inFile = combine(LEAD_VARS_ImagesDir, "EmptyPageTestInput.tif"); 
   String outFile = combine(LEAD_VARS_ImagesDir, "NoSkipping.tif"); 
   String outFile2 = combine(LEAD_VARS_ImagesDir, "SkippingEmptyPages.tif"); 
 
   createTestDocumentFile(inFile); 
 
   DocumentConverter documentConverter = new DocumentConverter(); 
   documentConverter.getDiagnostics().setEnableTrace(true); 
   // Make sure the options are set to not skip empty pages 
   documentConverter.getOptions().setEmptyPageMode(DocumentConverterEmptyPageMode.NONE); 
 
   // Create a job to convert the input document to the first output file and run it 
   DocumentConverterJobData jobData = DocumentConverterJobs.createJobData(inFile, outFile, 
         RasterImageFormat.CCITT_GROUP4); 
   jobData.setJobName("No Skipping empty pages"); 
   DocumentConverterJob job = documentConverter.getJobs().createJob(jobData); 
   documentConverter.getJobs().runJob(job); 
 
   // Now, tell the document converter to skip empty pagess 
   documentConverter.getOptions().setEmptyPageMode(DocumentConverterEmptyPageMode.SKIP_IGNORE_ANNOTATIONS); 
   // And create a job to convert the input document to the second output file and run it 
   jobData = DocumentConverterJobs.createJobData(inFile, outFile2, RasterImageFormat.CCITT_GROUP4); 
   jobData.setJobName("Skipping empty pages"); 
   job = documentConverter.getJobs().createJob(jobData); 
   documentConverter.getJobs().runJob(job); 
   assertTrue(job.getStatus() == DocumentConverterJobStatus.SUCCESS); 
   System.out.println("Finished, checking number of pages"); 
 
   RasterCodecs codecs = new RasterCodecs(); 
   int pageCount = codecs.getTotalPages(outFile); 
   System.out 
         .println(String.format("First job did not skip any pages and produced %s pages, should be 4", pageCount)); 
   pageCount = codecs.getTotalPages(outFile2); 
   System.out 
         .println(String.format("Second job skipped the empty pages and produced %s pages, should be 3", pageCount)); 
} 
 
public static void createTestDocumentFile(String fileName) { 
   String pageTemplateFile = "C:\\LEADTOOLS23\\Resources\\Images\\Ocr%s.tif"; 
   RasterCodecs codecs = new RasterCodecs(); 
   codecs.getOptions().getRasterizeDocument().getLoad().setResolution(300); 
   CodecsSavePageMode savePageMode = CodecsSavePageMode.OVERWRITE; 
   for (int i = 1; i <= 4; i++) { 
      if (i != 2) { 
         RasterImage rasterImage = codecs.load(String.format(pageTemplateFile, i), 1); 
         codecs.save(rasterImage, fileName, RasterImageFormat.CCITT_GROUP4, 1, 1, 1, -1, savePageMode); 
         savePageMode = CodecsSavePageMode.APPEND; 
 
         if (i == 1) { 
            RasterImage emptyPage = RasterImage.create(rasterImage.getWidth(), rasterImage.getHeight(), 
                  rasterImage.getBitsPerPixel(), rasterImage.getXResolution(), 
                  RasterColor.fromKnownColor(RasterKnownColor.WHITE)); 
            codecs.save(emptyPage, fileName, RasterImageFormat.CCITT_GROUP4, 1, 1, 1, -1, savePageMode); 
         } 
      } 
   } 
}
Requirements

Target Platforms

Help Version 23.0.2024.2.29
Products | Support | Contact Us | Intellectual Property Notices
© 1991-2024 LEAD Technologies, Inc. All Rights Reserved.

Leadtools.Document.Converter Assembly
Introduction
Getting Started
Namespaces
Leadtools.Document.Converter Namespace
Assemblies
Products | Support | Contact Us | Intellectual Property Notices
© 1991-2023 LEAD Technologies, Inc. All Rights Reserved.