DocumentText Class

Summary

Manages the text options of the document.

Syntax

C++/CLI

Java

Python

[DataContractAttribute()] 
public class DocumentText

public [DataContractAttribute] 
   ref class DocumentText

public class DocumentText implements Serializable

class DocumentText:

Remarks

DocumentText manages the text of the document and can be accessed through the Text property of LEADDocument.

The text of a document page can be extracted using the DocumentPage.GetText method. This will return a DocumentPageText instance that contains the text characters found in the page with location and size properties. Furthermore, DocumentPageText supports building the words or the text as string for easy processing.

The framework can use either SVG or OCR technologies to extract the text data. Which method to use can be controlled using the TextExtractionMode property.

For more information, refer to Parsing Text with the Document Library.

Example

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 DocumentTextExample() 
{ 
   var options = new LoadDocumentOptions(); 
   using (var document = DocumentFactory.LoadFromFile(Path.Combine(LEAD_VARS.ImagesDir, "slice.tif"), options)) 
   { 
      //for the TIF file we need an OCR engine 
      var ocrEngine = OcrEngineManager.CreateEngine(OcrEngineType.LEAD); 
      var rasterCodecs = new RasterCodecs(); 
      var documentWriter = new DocumentWriter(); 
      ocrEngine.Startup(rasterCodecs, documentWriter, null, LEAD_VARS.OcrLEADRuntimeDir); 
 
      // DocumentText reference 
      document.Text.OcrEngine = ocrEngine; 
 
      // 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}"); 
      } 
 
      // get text  
      var page = document.Pages[0]; 
      var pageText = page.GetText(); 
      if (pageText != null) 
      { 
         pageText.BuildText(); 
         var text = pageText.Text; 
 
         Console.WriteLine(text); 
      } 
      else 
      { 
         Console.WriteLine("Failed!"); 
      } 
   } 
} 
 
static class LEAD_VARS 
{ 
   public const string ImagesDir = @"C:\LEADTOOLS22\Resources\Images"; 
   public const string OcrLEADRuntimeDir = @"C:\LEADTOOLS22\Bin\Common\OcrLEADRuntime"; 
}

Requirements

Target Platforms

Reference

DocumentText Members

Leadtools.Document Namespace

Download our FREE evaluation

Help Version 22.0.2023.4.21

Leadtools.Document Assembly

Introduction

Getting Started

Namespaces

Leadtools.Document Namespace

Assemblies