diff --git a/Document-Processing/Data-Extraction/Smart-Data-Extractor/NET/Assemblies-Required.md b/Document-Processing/Data-Extraction/Smart-Data-Extractor/NET/Assemblies-Required.md
index 1f36509a8a..eb871b3030 100644
--- a/Document-Processing/Data-Extraction/Smart-Data-Extractor/NET/Assemblies-Required.md
+++ b/Document-Processing/Data-Extraction/Smart-Data-Extractor/NET/Assemblies-Required.md
@@ -31,6 +31,7 @@ The following assemblies need to be referenced in your application based on the
Syncfusion.PdfToImageConverter.Base
Syncfusion.SmartFormRecognizer.Base
Syncfusion.SmartTableExtractor.Base
+ Syncfusion.Markdown
@@ -47,6 +48,7 @@ The following assemblies need to be referenced in your application based on the
Syncfusion.PdfToImageConverter.Portable
Syncfusion.SmartFormRecognizer.Portable
Syncfusion.SmartTableExtractor.Portable
+ Syncfusion.Markdown
@@ -62,6 +64,7 @@ The following assemblies need to be referenced in your application based on the
Syncfusion.PdfToImageConverter.NET
Syncfusion.SmartFormRecognizer.NET
Syncfusion.SmartTableExtractor.NET
+ Syncfusion.Markdown
diff --git a/Document-Processing/Data-Extraction/Smart-Data-Extractor/NET/Features.md b/Document-Processing/Data-Extraction/Smart-Data-Extractor/NET/Features.md
index 3d6f61acb0..5ac2cc3755 100644
--- a/Document-Processing/Data-Extraction/Smart-Data-Extractor/NET/Features.md
+++ b/Document-Processing/Data-Extraction/Smart-Data-Extractor/NET/Features.md
@@ -113,7 +113,7 @@ using (FileStream inputStream = new FileStream("Input.pdf", FileMode.Open, FileA
## Extract Data as JSON from PDF Document
-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:
+To extract form fields across a PDF document using the **ExtractDataAsJson** method of the **DataExtractor** class, refer to the following code example:
{% tabs %}
@@ -129,7 +129,7 @@ using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess
{
//Initialize the Smart Data Extractor.
DataExtractor extractor = new DataExtractor();
- //Extract form data as JSON.
+ //Extract data as JSON.
string data = extractor.ExtractDataAsJson(stream);
//Save the extracted JSON data into an output file.
File.WriteAllText("Output.json", data, Encoding.UTF8);
@@ -149,7 +149,7 @@ using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess
{
//Initialize the Smart Data Extractor.
DataExtractor extractor = new DataExtractor();
- //Extract form data as JSON.
+ //Extract data as JSON.
string data = extractor.ExtractDataAsJson(stream);
//Save the extracted JSON data into an output file.
File.WriteAllText("Output.json", data, Encoding.UTF8);
@@ -159,6 +159,54 @@ using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess
{% endtabs %}
+## Extract Data as Markdown from PDF Document
+
+To extract form fields across a PDF document using the **ExtractDataAsMarkdown** method of the **DataExtractor** class, refer to the following code example:
+
+{% tabs %}
+
+{% highlight c# tabtitle="C# [Cross-platform]" %}
+
+using System.IO;
+using Syncfusion.SmartDataExtractor;
+using Syncfusion.SmartFormRecognizer;
+using System.Text;
+
+//Open the input PDF file as a stream.
+using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess.Read))
+{
+ //Initialize the Smart Data Extractor.
+ DataExtractor extractor = new DataExtractor();
+ //Extract data as Markdown.
+ string data = extractor.ExtractDataAsMarkdown(stream);
+ //Save the extracted Markdown data into an output file.
+ File.WriteAllText("Output.md", data, Encoding.UTF8);
+}
+
+{% endhighlight %}
+
+{% highlight c# tabtitle="C# [Windows-specific]" %}
+
+using System.IO;
+using Syncfusion.SmartDataExtractor;
+using Syncfusion.SmartFormRecognizer;
+using System.Text;
+
+//Open the input PDF file as a stream.
+using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess.Read))
+{
+ //Initialize the Smart Data Extractor.
+ DataExtractor extractor = new DataExtractor();
+ //Extract data as Markdown.
+ string data = extractor.ExtractDataAsMarkdown(stream);
+ //Save the extracted Markdown data into an output file.
+ File.WriteAllText("Output.md", data, Encoding.UTF8);
+}
+
+{% endhighlight %}
+
+{% endtabs %}
+
## Extract Data as JSON from an Image
To extract structured data from an image document using the **ExtractDataAsJson** method of the **DataExtractor** class, refer to the following code examples.
diff --git a/Document-Processing/Data-Extraction/Smart-Data-Extractor/NET/troubleshooting.md b/Document-Processing/Data-Extraction/Smart-Data-Extractor/NET/troubleshooting.md
index 21fd1c1629..72552ce853 100644
--- a/Document-Processing/Data-Extraction/Smart-Data-Extractor/NET/troubleshooting.md
+++ b/Document-Processing/Data-Extraction/Smart-Data-Extractor/NET/troubleshooting.md
@@ -78,18 +78,21 @@ documentation: UG
Solution |
In your MVC project file (.csproj), add the following build target to copy the native DLL from the NuGet package folder to the bin folder:
-
-
-
-
-
-
- |
-
+{% tabs %}
+{% highlight C# %}
+
+
+
+
+
+{% endhighlight %}
+{% endtabs %}
+
+
diff --git a/Document-Processing/Data-Extraction/Smart-Table-Extractor/NET/Assemblies-Required.md b/Document-Processing/Data-Extraction/Smart-Table-Extractor/NET/Assemblies-Required.md
index e88399385d..7e6565d838 100644
--- a/Document-Processing/Data-Extraction/Smart-Table-Extractor/NET/Assemblies-Required.md
+++ b/Document-Processing/Data-Extraction/Smart-Table-Extractor/NET/Assemblies-Required.md
@@ -29,6 +29,7 @@ The following assemblies need to be referenced in your application based on the
Syncfusion.OCRProcessor.Base
Syncfusion.Pdf.Base
Syncfusion.PdfToImageConverter.Base
+ Syncfusion.Markdown
@@ -43,6 +44,7 @@ The following assemblies need to be referenced in your application based on the
Syncfusion.Pdf.Imaging.Portable
Syncfusion.Pdf.Portable
Syncfusion.PdfToImageConverter.Portable
+ Syncfusion.Markdown
@@ -56,6 +58,7 @@ The following assemblies need to be referenced in your application based on the
Syncfusion.Pdf.Imaging.NET
Syncfusion.Pdf.NET
Syncfusion.PdfToImageConverter.NET
+ Syncfusion.Markdown
diff --git a/Document-Processing/Data-Extraction/Smart-Table-Extractor/NET/Features.md b/Document-Processing/Data-Extraction/Smart-Table-Extractor/NET/Features.md
index ddefb46025..cb4699cc27 100644
--- a/Document-Processing/Data-Extraction/Smart-Table-Extractor/NET/Features.md
+++ b/Document-Processing/Data-Extraction/Smart-Table-Extractor/NET/Features.md
@@ -26,19 +26,8 @@ using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess
{
// Initialize the Smart Table Extractor
TableExtractor extractor = new TableExtractor();
-
- //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 = 0.6;
-
- //Assign the configured options to the extractor.
- extractor.TableExtractionOptions = options;
-
//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);
}
@@ -56,19 +45,8 @@ using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess
{
//Initialize the Smart Table Extractor.
TableExtractor extractor = new TableExtractor();
-
- //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 = 0.6;
-
- //Assign the configured options to the extractor.
- extractor.TableExtractionOptions = options;
-
//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);
}
@@ -94,17 +72,14 @@ using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess
{
//Initialize the Smart Table Extractor.
TableExtractor extractor = new TableExtractor();
-
//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 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);
}
@@ -122,17 +97,13 @@ using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess
{
//Initialize the Smart Table Extractor.
TableExtractor extractor = new TableExtractor();
-
//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 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);
}
@@ -158,17 +129,13 @@ using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess
{
//Initialize the Smart Table Extractor.
TableExtractor extractor = new TableExtractor();
-
//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 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);
}
@@ -186,17 +153,13 @@ using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess
{
//Initialize the Smart Table Extractor.
TableExtractor extractor = new TableExtractor();
-
//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 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);
}
@@ -222,17 +185,13 @@ using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess
{
//Initialize the Smart Table Extractor.
TableExtractor extractor = new TableExtractor();
-
//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 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);
}
@@ -250,17 +209,13 @@ using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess
{
//Initialize the Smart Table Extractor.
TableExtractor extractor = new TableExtractor();
-
//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 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);
}
@@ -285,22 +240,12 @@ 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 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 a cancellation token with a timeout of 30 seconds to control the async operation.
CancellationTokenSource cts = new CancellationTokenSource(TimeSpan.FromSeconds(30));
-
//Call the asynchronous extraction API to extract table data as a JSON string.
string data = await tableExtractor.ExtractTableAsJsonAsync(stream, cts.Token);
-
//Save the extracted JSON data into an output file.
File.WriteAllText("Output.json", data, Encoding.UTF8);
}
@@ -317,21 +262,12 @@ 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 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 a cancellation token with a timeout of 30 seconds to control the async operation.
CancellationTokenSource cts = new CancellationTokenSource(TimeSpan.FromSeconds(30));
-
//Call the asynchronous extraction API to extract table data as a JSON string.
string data = await tableExtractor.ExtractTableAsJsonAsync(stream, cts.Token);
-
//Save the extracted JSON data into an output file.
File.WriteAllText("Output.json", data, Encoding.UTF8);
}
@@ -340,3 +276,49 @@ using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess
{% endtabs %}
+## Extract Table data as Markdown from a PDF Document
+
+To extract structured table data from a PDF document using the **ExtractTableAsMarkdown** method of the **TableExtractor** class, refer to the following code
+
+{% tabs %}
+
+{% highlight c# tabtitle="C# [Cross-platform]" %}
+
+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
+ TableExtractor extractor = new TableExtractor();
+ //Extract table data from the PDF document as markdown.
+ string data = extractor.ExtractTableAsMarkdown(stream);
+ //Save the extracted markdown data into an output file.
+ File.WriteAllText("Output.md", data, Encoding.UTF8);
+}
+
+{% endhighlight %}
+
+{% highlight c# tabtitle="C# [Windows-specific]" %}
+
+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
+ TableExtractor extractor = new TableExtractor();
+ //Extract table data from the PDF document as markdown.
+ string data = extractor.ExtractTableAsMarkdown(stream);
+ //Save the extracted markdown data into an output file.
+ File.WriteAllText("Output.md", data, Encoding.UTF8);
+}
+
+{% endhighlight %}
+
+{% endtabs %}
+
diff --git a/Document-Processing/Data-Extraction/Smart-Table-Extractor/NET/data-extraction-images/onnx.png b/Document-Processing/Data-Extraction/Smart-Table-Extractor/NET/data-extraction-images/onnx.png
deleted file mode 100644
index 11ff3f4822..0000000000
Binary files a/Document-Processing/Data-Extraction/Smart-Table-Extractor/NET/data-extraction-images/onnx.png and /dev/null differ
diff --git a/Document-Processing/Data-Extraction/Smart-Table-Extractor/NET/table-extraction-images/onnx-table.png b/Document-Processing/Data-Extraction/Smart-Table-Extractor/NET/table-extraction-images/onnx-table.png
new file mode 100644
index 0000000000..4e67e28200
Binary files /dev/null and b/Document-Processing/Data-Extraction/Smart-Table-Extractor/NET/table-extraction-images/onnx-table.png differ
diff --git a/Document-Processing/Data-Extraction/Smart-Table-Extractor/NET/troubleshooting.md b/Document-Processing/Data-Extraction/Smart-Table-Extractor/NET/troubleshooting.md
index 183a0e15c9..ddc7e74962 100644
--- a/Document-Processing/Data-Extraction/Smart-Table-Extractor/NET/troubleshooting.md
+++ b/Document-Processing/Data-Extraction/Smart-Table-Extractor/NET/troubleshooting.md
@@ -26,7 +26,7 @@ documentation: UG
Please refer to the below screenshot,
- 
+ 
Note: If you publish your application, ensure the runtimes/models folder and ONNX files are included in the publish output.
@@ -64,29 +64,36 @@ documentation: UG
- | Exception |
- Microsoft.ML.ONNXRuntime.ONNXRuntimeException |
-
-
- | Reason |
- The required native runtime library (ONNXRuntime.dll) is missing from your application's bin folder. |
-
-
- | Solution |
-
- In your MVC project file (.csproj), add the following build target to copy the native DLL from the NuGet package folder to the bin folder:
-
-
-
-
-
-
-
- |
-
+Exception
+ |
+Microsoft.ML.ONNXRuntime.ONNXRuntimeException
+ |
+
+
+| Reason
+ |
+The required native runtime library (ONNXRuntime.dll) is missing from your application's bin folder.
+ |
+
+
+
+| Solution
+ |
+ In your MVC project file (.csproj), add the following build target to copy the native DLL from the NuGet package folder to the bin folder:
+{% tabs %}
+{% highlight C# %}
+
+
+
+
+
+{% endhighlight %}
+{% endtabs %}
+ |
+