←Select platform

DocumentWord Structure

Summary

Contains the properties of a text word found in the page.

Syntax
C#
C++/CLI
Java
Python
[SerializableAttribute()] 
[DataContractAttribute()] 
public struct DocumentWord 
public [SerializableAttribute,  
   DataContractAttribute] 
   value class DocumentWord sealed 
public class DocumentWord implements Serializable 
class DocumentWord: 
Remarks

The DocumentWord structure is used as the type for the Words list.

Example
C#
using Leadtools; 
using Leadtools.Codecs; 
using Leadtools.Document.Writer; 
 
using Leadtools.Document; 
using Leadtools.Caching; 
using Leadtools.Annotations.Engine; 
using Leadtools.Ocr; 
using Leadtools.Barcode; 
using Leadtools.Document.Converter; 
 
public void DocumentPageTextExample() 
{ 
   var options = new LoadDocumentOptions(); 
   using (var document = DocumentFactory.LoadFromFile(Path.Combine(LEAD_VARS.ImagesDir, "Leadtools.doc"), options)) 
   { 
      // Get page text  
      var page = document.Pages[0]; 
            
      // Get all of the DocumentTextExtractionModes (DocumentTextExtractionMode reference) 
      DocumentTextExtractionMode[] textExtractionModes = (DocumentTextExtractionMode[])Enum.GetValues(typeof(DocumentTextExtractionMode)); 
      foreach (var modes in textExtractionModes) 
      { 
         Console.WriteLine($"Text extraction mode: {modes}"); 
      } 
 
      // Text extraction mode. Auto is default 
      document.Text.TextExtractionMode = DocumentTextExtractionMode.Auto; 
 
      // DocumentPageText reference 
      var pageText = page.GetText(); 
      if (pageText != null) 
      { 
         pageText.BuildText(); 
         var characters = pageText.Characters; 
         var text = pageText.Text; 
 
         Console.WriteLine(text); 
         Console.WriteLine($"Total number of characters: {characters.Count}"); 
 
         pageText.BuildWords(); 
         Console.WriteLine($"Total number of words: {pageText.Words.Count}"); 
         // Get each word 
         foreach (DocumentWord word in pageText.Words) 
         { 
            Console.WriteLine($"Bounds: {word.Bounds} | First character index: {word.FirstCharacterIndex} " + 
               $"| Last character index: {word.LastCharacterIndex} | Value: {word.Value}"); 
         } 
      } 
      else 
      { 
         Console.WriteLine("Failed!"); 
      } 
 
   } 
} 
 
static class LEAD_VARS 
{ 
   public const string ImagesDir = @"C:\LEADTOOLS22\Resources\Images"; 
} 
Requirements

Target Platforms

See Also

Reference

Leadtools.Document Namespace

Help Version 22.0.2023.4.21
Products | Support | Contact Us | Intellectual Property Notices
© 1991-2023 LEAD Technologies, Inc. All Rights Reserved.

Leadtools.Document Assembly

Products | Support | Contact Us | Intellectual Property Notices
© 1991-2023 LEAD Technologies, Inc. All Rights Reserved.