Object that manages the text and OCR recognition settings of the document.
public DocumentText Text { get; }
public:
property DocumentText^ Text
{
DocumentText^ get()
}
public DocumentText getText()
Text # get (LEADDocument)
The DocumentText object that manages the text and OCR recognition settings of this LEADDocument.
Refer to DocumentText for more information.
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:\LEADTOOLS23\Resources\Images";
public const string OcrLEADRuntimeDir = @"C:\LEADTOOLS23\Bin\Common\OcrLEADRuntime";
}
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.net.MalformedURLException;
import java.net.URI;
import java.net.URISyntaxException;
import java.net.URL;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.ArrayList;
import java.util.Calendar;
import java.util.List;
import java.util.concurrent.Callable;
import java.util.concurrent.ExecutorService;
import java.util.concurrent.Executors;
import java.util.concurrent.Future;
import java.util.regex.Pattern;
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.annotations.engine.*;
import leadtools.barcode.*;
import leadtools.caching.*;
import leadtools.codecs.*;
import leadtools.document.*;
import leadtools.document.DocumentMimeTypes.UserGetDocumentStatusHandler;
import leadtools.document.converter.*;
import leadtools.document.writer.*;
import leadtools.ocr.*;
public void documentTextExample() {
final String LEAD_VARS_IMAGES_DIR = "C:\\LEADTOOLS23\\Resources\\Images";
final String OCR_LEAD_RUNTIME_DIR = "C:\\LEADTOOLS23\\Bin\\Common\\OcrLEADRuntime";
LoadDocumentOptions options = new LoadDocumentOptions();
LEADDocument document = DocumentFactory.loadFromFile(combine(LEAD_VARS_IMAGES_DIR, "slice.tif"), options);
// for the TIF file we need an OCR engine
OcrEngine ocrEngine = OcrEngineManager.createEngine(OcrEngineType.LEAD);
RasterCodecs rasterCodecs = new RasterCodecs();
DocumentWriter documentWriter = new DocumentWriter();
ocrEngine.startup(rasterCodecs, documentWriter, null, OCR_LEAD_RUNTIME_DIR);
// DocumentText reference
document.getText().setOcrEngine(ocrEngine);
// Get all of the DocumentTextExtractionModes (DocumentTextExtractionMode
// reference)
DocumentTextExtractionMode[] textExtractionModes = DocumentTextExtractionMode.values();
for (DocumentTextExtractionMode modes : textExtractionModes) {
System.out.println("Text extraction mode: " + modes);
}
// get text
DocumentPage page = document.getPages().get(0);
DocumentPageText pageText = page.getText();
if (pageText != null) {
pageText.buildText();
String text = pageText.getText();
System.out.println(text);
} else {
System.out.println("Failed!");
}
assertTrue(pageText != null);
}
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