Manages the text options of the document.
[DataContractAttribute()]
public class DocumentText
public [DataContractAttribute]
ref class DocumentText
public class DocumentText implements Serializable
class DocumentText:
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.
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";
}
Help Collections
Raster .NET | C API | C++ Class Library | HTML5 JavaScript
Document .NET | C API | C++ Class Library | HTML5 JavaScript
Medical .NET | C API | C++ Class Library | HTML5 JavaScript
Medical Web Viewer .NET
Multimedia
Direct Show .NET | C API | Filters
Media Foundation .NET | C API | Transforms
Supported Platforms
.NET, Java, Android, and iOS/macOS Assemblies
Imaging, Medical, and Document
C API/C++ Class Libraries
Imaging, Medical, and Document
HTML5 JavaScript Libraries
Imaging, Medical, and Document
Your email has been sent to support! Someone should be in touch! If your matter is urgent please come back into chat.
Chat Hours:
Monday - Friday, 8:30am to 6pm ET
Thank you for your feedback!
Please fill out the form again to start a new chat.
All agents are currently offline.
Chat Hours:
Monday - Friday
8:30AM - 6PM EST
To contact us please fill out this form and we will contact you via email.