Added the contents

Author: VenkateshwaranSF5013

Document-Processing/Data-Extraction/Smart-Data-Extractor/NET/Features.md

@@ -129,6 +129,66 @@ using (FileStream stream = new FileStream("Image.png", FileMode.Open, FileAccess
 
 {% endtabs %}  
 
+## Extract Data as Stream
+
+To extract structured data from a PDF document and return the output as a stream using the **ExtractDataAsPdfStream** method of the **DataExtractor** class, refer to the following example.
+
+{% tabs %} 
+
+{% highlight c# tabtitle="C# [Cross-platform]" %}
+
+using System.IO;
+using Syncfusion.SmartDataExtractor;
+
+//Open the input PDF file as a stream.
+using (FileStream inputStream = new FileStream("Input.pdf", FileMode.Open, FileAccess.Read, FileShare.Read))
+{
+    //Initialize the Smart Data Extractor.
+    DataExtractor extractor = new DataExtractor();
+    extractor.EnableFormDetection = true;
+    extractor.EnableTableDetection = true;
+    extractor.ConfidenceThreshold = 0.6;
+
+    //Extract data and return as a PDF stream.
+    Stream pdfStream = extractor.ExtractDataAsPdfStream(inputStream);
+
+    //Save the extracted PDF stream into an output file.
+    using (FileStream outputStream = new FileStream("Output.pdf", FileMode.Create, FileAccess.Write))
+    {
+        pdfStream.CopyTo(outputStream);
+    }
+}
+ 
+{% endhighlight %}
+
+{% highlight c# tabtitle="C# [Windows-specific]" %}
+
+using System.IO;
+using Syncfusion.SmartDataExtractor;
+
+//Open the input PDF file as a stream.
+using (FileStream inputStream = new FileStream("Input.pdf", FileMode.Open, FileAccess.Read, FileShare.Read))
+{
+    //Initialize the Smart Data Extractor.
+    DataExtractor extractor = new DataExtractor();
+    extractor.EnableFormDetection = true;
+    extractor.EnableTableDetection = true;
+    extractor.ConfidenceThreshold = 0.6;
+
+    //Extract data and return as a PDF stream.
+    Stream pdfStream = extractor.ExtractDataAsPdfStream(inputStream);
+
+    //Save the extracted PDF stream into an output file.
+    using (FileStream outputStream = new FileStream("Output.pdf", FileMode.Create, FileAccess.Write))
+    {
+        pdfStream.CopyTo(outputStream);
+    }
+}
+ 			
+{% endhighlight %}
+
+{% endtabs %}
+
 ## Extract Form Data as JSON
 
 To extract form fields across a PDF document using the **ExtractDataAsJson** method of the **DataExtractor** class with form recognition options, refer to the following code example:

Document-Processing/Data-Extraction/Smart-Table-Extractor/NET/Features.md

@@ -27,16 +27,19 @@ using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess
     // Initialize the Smart Table Extractor
     TableExtractor extractor = new TableExtractor();
 
-    // Set all three options together
+    //Configure table extraction options such as border-less table detection, page range, and confidence threshold.
     TableExtractionOptions options = new TableExtractionOptions();
     options.DetectBorderlessTables = true;
     options.PageRange = new int[,] { { 1, 5 } };
     options.ConfidenceThreshold = 0.75;
 
+    //Assign the configured options to the extractor.
     extractor.TableExtractionOptions = options;
 
-    // Extract and save
+    //Extract table data from the PDF document as JSON string.
     string data = extractor.ExtractTableAsJson(stream);
+
+    //Save the extracted JSON data into an output file.
     File.WriteAllText("Output.json", data, Encoding.UTF8);
 }
 
@@ -51,19 +54,22 @@ using Syncfusion.SmartTableExtractor;
 //Open the input PDF file as a stream.
 using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess.Read))
 {
-    // Initialize the Smart Table Extractor
+    //Initialize the Smart Table Extractor.
     TableExtractor extractor = new TableExtractor();
 
-    // Set all three options together
+    //Configure table extraction options such as border-less table detection, page range, and confidence threshold.
     TableExtractionOptions options = new TableExtractionOptions();
     options.DetectBorderlessTables = true;
     options.PageRange = new int[,] { { 1, 5 } };
     options.ConfidenceThreshold = 0.75;
 
+    //Assign the configured options to the extractor.
     extractor.TableExtractionOptions = options;
 
-    // Extract and save
+    //Extract table data from the PDF document as JSON string.
     string data = extractor.ExtractTableAsJson(stream);
+
+    //Save the extracted JSON data into an output file.
     File.WriteAllText("Output.json", data, Encoding.UTF8);
 }
 
@@ -83,19 +89,23 @@ using System.IO;
 using System.Text;
 using Syncfusion.SmartTableExtractor;
 
+//Open the input PDF file as a stream.
 using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess.Read))
 {
-    // Initialize the Smart Table Extractor
+    //Initialize the Smart Table Extractor.
     TableExtractor extractor = new TableExtractor();
 
-    // Set DetectBorderlessTables
+    //Configure the table extraction option to detect border-less tables in the document.
     TableExtractionOptions options = new TableExtractionOptions();
     options.DetectBorderlessTables = true;
 
+    //Assign the configured options to the extractor.
     extractor.TableExtractionOptions = options;
 
-    // Extract and save
+    //Extract table data from the PDF document as a JSON string.
     string data = extractor.ExtractTableAsJson(stream);
+
+    //Save the extracted JSON data into an output file.
     File.WriteAllText("Output.json", data, Encoding.UTF8);
 }
 
@@ -107,27 +117,31 @@ using System.IO;
 using System.Text;
 using Syncfusion.SmartTableExtractor;
 
+//Open the input PDF file as a stream.
 using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess.Read))
 {
-    // Initialize the Smart Table Extractor
+    //Initialize the Smart Table Extractor.
     TableExtractor extractor = new TableExtractor();
 
-    // Set DetectBorderlessTables
+    //Configure the table extraction option to detect border-less tables in the document.
     TableExtractionOptions options = new TableExtractionOptions();
     options.DetectBorderlessTables = true;
 
+    //Assign the configured options to the extractor.
     extractor.TableExtractionOptions = options;
 
-    // Extract and save
+    //Extract table data from the PDF document as a JSON string.
     string data = extractor.ExtractTableAsJson(stream);
+
+    //Save the extracted JSON data into an output file.
     File.WriteAllText("Output.json", data, Encoding.UTF8);
 }
 
 {% endhighlight %}
 
 {% endtabs %}  
 
-## Extract Tables Within a Specific Page Range
+## Extract Tables within a Specific Page Range
 
 To extract structured table data from a specific range of pages in a PDF document using the **ExtractTableAsJson** method of the **TableExtractor** class, refer to the following code example: 
 
@@ -139,19 +153,23 @@ using System.IO;
 using System.Text;
 using Syncfusion.SmartTableExtractor;
 
+//Open the input PDF file as a stream.
 using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess.Read))
 {
-    // Initialize the Smart Table Extractor
+    //Initialize the Smart Table Extractor.
     TableExtractor extractor = new TableExtractor();
 
-    // Set the PageRange
+    //Configure table extraction options to specify the page range for detection.
     TableExtractionOptions options = new TableExtractionOptions();
     options.PageRange = new int[,] { { 2, 4 } };
 
+    //Assign the configured options to the extractor.
     extractor.TableExtractionOptions = options;
 
-    // Extract and save
+    //Extract table data from the specified page range as a JSON string.
     string data = extractor.ExtractTableAsJson(stream);
+
+    //Save the extracted JSON data into an output file.
     File.WriteAllText("Output.json", data, Encoding.UTF8);
 }
 			
@@ -163,19 +181,23 @@ using System.IO;
 using System.Text;
 using Syncfusion.SmartTableExtractor;
 
+//Open the input PDF file as a stream.
 using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess.Read))
 {
-    // Initialize the Smart Table Extractor
+    //Initialize the Smart Table Extractor.
     TableExtractor extractor = new TableExtractor();
 
-    // Set only PageRange
+    //Configure table extraction options to specify the page range for detection.
     TableExtractionOptions options = new TableExtractionOptions();
     options.PageRange = new int[,] { { 2, 4 } };
 
+    //Assign the configured options to the extractor.
     extractor.TableExtractionOptions = options;
 
-    // Extract and save
+    //Extract table data from the specified page range as a JSON string.
     string data = extractor.ExtractTableAsJson(stream);
+
+    //Save the extracted JSON data into an output file.
     File.WriteAllText("Output.json", data, Encoding.UTF8);
 }
 
@@ -195,19 +217,23 @@ using System.IO;
 using System.Text;
 using Syncfusion.SmartTableExtractor;
 
+//Open the input PDF file as a stream.
 using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess.Read))
 {
-    // Initialize the Smart Table Extractor
+    //Initialize the Smart Table Extractor.
     TableExtractor extractor = new TableExtractor();
 
-    // Set ConfidenceThreshold
+    //Configure table extraction options to set the confidence threshold for detection.
     TableExtractionOptions options = new TableExtractionOptions();
     options.ConfidenceThreshold = 0.6;
 
+    //Assign the configured options to the extractor.
     extractor.TableExtractionOptions = options;
 
-    // Extract and save
+    //Extract table data from the PDF document as a JSON string.
     string data = extractor.ExtractTableAsJson(stream);
+
+    //Save the extracted JSON data into an output file.
     File.WriteAllText("Output.json", data, Encoding.UTF8);
 }
 
@@ -219,19 +245,23 @@ using System.IO;
 using System.Text;
 using Syncfusion.SmartTableExtractor;
 
+//Open the input PDF file as a stream.
 using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess.Read))
 {
-    // Initialize the Smart Table Extractor
+    //Initialize the Smart Table Extractor.
     TableExtractor extractor = new TableExtractor();
 
-    // Set ConfidenceThreshold
+    //Configure table extraction options to set the confidence threshold for detection.
     TableExtractionOptions options = new TableExtractionOptions();
     options.ConfidenceThreshold = 0.6;
 
+    //Assign the configured options to the extractor.
     extractor.TableExtractionOptions = options;
 
-    // Extract and save
+    //Extract table data from the PDF document as a JSON string.
     string data = extractor.ExtractTableAsJson(stream);
+
+    //Save the extracted JSON data into an output file.
     File.WriteAllText("Output.json", data, Encoding.UTF8);
 }
 
@@ -252,27 +282,29 @@ using System.Text;
 using System.Threading;
 using Syncfusion.SmartTableExtractor;
 
+//Open the input PDF file as a stream.
 using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess.Read))
 {
-    // Declare and configure the extractor and options
+    //Declare and configure the table extraction options with border-less table detection and confidence threshold.
     TableExtractionOptions extractionOptions = new TableExtractionOptions();
     extractionOptions.DetectBorderlessTables = true;
     extractionOptions.ConfidenceThreshold = 0.6;
 
+    //Initialize the Smart Table Extractor and assign the configured options.
     TableExtractor tableExtractor = new TableExtractor();
+    //Assign the configured table extraction options to the extractor.
     tableExtractor.TableExtractionOptions = extractionOptions;
 
-    // Create cancellation token with timeout
-    var cts = new CancellationTokenSource(TimeSpan.FromSeconds(30));
+    //Create a cancellation token with a timeout of 30 seconds to control the async operation.
+    CancellationTokenSource cts = new CancellationTokenSource(TimeSpan.FromSeconds(30));
 
-    // Call the async extraction API
+    //Call the asynchronous extraction API to extract table data as a JSON string.
     string data = await tableExtractor.ExtractTableAsJsonAsync(stream, cts.Token);
 
-    // Save the extracted data as JSON
+    //Save the extracted JSON data into an output file.
     File.WriteAllText("Output.json", data, Encoding.UTF8);
 }
 
-
 {% endhighlight %}
 
 {% highlight c# tabtitle="C# [Windows-specific]" %}
@@ -282,27 +314,28 @@ using System.Text;
 using System.Threading;
 using Syncfusion.SmartTableExtractor;
 
+//Open the input PDF file as a stream.
 using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess.Read))
 {
-    // Declare and configure the extractor and options
+    //Declare and configure the table extraction options with border-less table detection and confidence threshold.
     TableExtractionOptions extractionOptions = new TableExtractionOptions();
     extractionOptions.DetectBorderlessTables = true;
     extractionOptions.ConfidenceThreshold = 0.6;
 
+    //Initialize the Smart Table Extractor and assign the configured options.
     TableExtractor tableExtractor = new TableExtractor();
     tableExtractor.TableExtractionOptions = extractionOptions;
 
-    // Create cancellation token with timeout
-    var cts = new CancellationTokenSource(TimeSpan.FromSeconds(30));
+    //Create a cancellation token with a timeout of 30 seconds to control the async operation.
+    CancellationTokenSource cts = new CancellationTokenSource(TimeSpan.FromSeconds(30));
 
-    // Call the async extraction API
+    //Call the asynchronous extraction API to extract table data as a JSON string.
     string data = await tableExtractor.ExtractTableAsJsonAsync(stream, cts.Token);
 
-    // Save the extracted data as JSON
+    //Save the extracted JSON data into an output file.
     File.WriteAllText("Output.json", data, Encoding.UTF8);
 }
 
-
 {% endhighlight %}
 
 {% endtabs %}