Documentation(1018996): Add sample for Different Form Recognizer Options in SmartFormRecognizer

Data-Extraction/Smart-Data-Extractor/Apply-Confidence-threshold/.NET/Apply-Confidence-Threshold-to-Extract-data.slnx

@@ -0,0 +1,3 @@
+<Solution>
+  <Project Path="Apply-Confidence-Threshold-to-Extract-data/Apply-Confidence-Threshold-to-Extract-data.csproj" />
+</Solution>

Data-Extraction/Smart-Data-Extractor/Apply-Confidence-threshold/.NET/Apply-Confidence-Threshold-to-Extract-data/Apply-Confidence-Threshold-to-Extract-data.csproj

@@ -0,0 +1,24 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>net10.0</TargetFramework>
+    <RootNamespace>Apply_Confidence_Threshold_to_Extract_data</RootNamespace>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <Nullable>enable</Nullable>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Syncfusion.SmartDataExtractor.Net.Core" Version="*" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <None Update="Data\Input.pdf">
+      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
+    </None>
+    <None Update="Output\.gitkeep">
+      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
+    </None>
+  </ItemGroup>
+
+</Project>

Data-Extraction/Smart-Data-Extractor/Apply-Confidence-threshold/.NET/Apply-Confidence-Threshold-to-Extract-data/Program.cs

@@ -0,0 +1,33 @@
+using System.IO;
+using Syncfusion.Pdf.Parsing;
+using Syncfusion.SmartDataExtractor;
+
+namespace ApplyConfidenceThresholdToExtractData
+{
+	class Program
+	{
+		static void Main(string[] args)
+		{
+			// Load the input PDF file.
+			using (FileStream stream = new FileStream(@"Data\Input.pdf", FileMode.Open, FileAccess.Read))
+			{
+				// Initialize the Smart Data Extractor.
+				DataExtractor extractor = new DataExtractor();
+
+				// Apply confidence threshold to extract the data.
+				// Only elements with confidence >= 0.75 will be included in the results.
+				// Default confidence threshold value is 0.6.
+				extractor.ConfidenceThreshold = 0.75;
+
+				// Extract data and return as a loaded PDF document.
+				PdfLoadedDocument pdf = extractor.ExtractDataAsPdfDocument(stream);
+
+				// Save the extracted output as a new PDF file.
+				pdf.Save(@"Output\Output.pdf");
+
+				// Close the document to release resources.
+				pdf.Close(true);
+			}
+		}
+	}
+}

Data-Extraction/Smart-Data-Extractor/Different-form-recognizer-options/.NET/Different-form-recognizer-options.slnx

@@ -0,0 +1,3 @@
+<Solution>
+  <Project Path="Different-form-recognizer-options/Different-form-recognizer-options.csproj" />
+</Solution>

Data-Extraction/Smart-Data-Extractor/Different-form-recognizer-options/.NET/Different-form-recognizer-options/Different-form-recognizer-options.csproj

@@ -0,0 +1,24 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>net10.0</TargetFramework>
+    <RootNamespace>Different_form_recognizer_options</RootNamespace>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <Nullable>enable</Nullable>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Syncfusion.SmartDataExtractor.Net.Core" Version="*" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <None Update="Data\Input.pdf">
+      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
+    </None>
+    <None Update="Output\.gitkeep">
+      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
+    </None>
+  </ItemGroup>
+
+</Project>

Data-Extraction/Smart-Data-Extractor/Different-form-recognizer-options/.NET/Different-form-recognizer-options/Program.cs

@@ -0,0 +1,56 @@
+using System.IO;
+using Syncfusion.Pdf.Parsing;
+using Syncfusion.SmartDataExtractor;
+using Syncfusion.SmartFormRecognizer;
+
+namespace DifferentFormRecognizerOptions
+{
+	class Program
+	{
+		static void Main(string[] args)
+		{
+			// Open the input PDF file as a stream.
+			using (FileStream stream = new FileStream(@"Data\Input.pdf", FileMode.Open, FileAccess.Read))
+			{
+				// Initialize the Smart Data Extractor.
+				DataExtractor extractor = new DataExtractor();
+
+				// Enable form detection in the document to identify form fields.
+				extractor.EnableFormDetection = true;
+
+				// Configure form recognition options for advanced detection.
+				FormRecognizeOptions formOptions = new FormRecognizeOptions();
+
+				// Recognize forms across pages 1 to 5 in the document.
+				formOptions.PageRange = new int[,] { { 1, 5 } };
+
+				// Set confidence threshold for form recognition to filter results.
+				formOptions.ConfidenceThreshold = 0.6;
+
+				// Enable detection of signatures within the document.
+				formOptions.DetectSignatures = true;
+
+				// Enable detection of textboxes within the document.
+				formOptions.DetectTextboxes = true;
+
+				// Enable detection of checkboxes within the document.
+				formOptions.DetectCheckboxes = true;
+
+				// Enable detection of radio buttons within the document.
+				formOptions.DetectRadioButtons = true;
+
+				// Assign the configured form recognition options to the extractor.
+				extractor.FormRecognizeOptions = formOptions;
+
+				// Extract form data and return as a loaded PDF document.
+				PdfLoadedDocument pdf = extractor.ExtractDataAsPdfDocument(stream);
+
+				// Save the extracted output as a new PDF file.
+				pdf.Save(@"Output\Output.pdf");
+
+				// Close the document to release resources.
+				pdf.Close(true);
+			}
+		}
+	}
+}

Data-Extraction/Smart-Data-Extractor/Different-table-extraction-options/.NET/Different-table-extraction-options.slnx

@@ -0,0 +1,3 @@
+<Solution>
+  <Project Path="Different-table-extraction-options/Different-table-extraction-options.csproj" />
+</Solution>

Data-Extraction/Smart-Data-Extractor/Different-table-extraction-options/.NET/Different-table-extraction-options/Different-table-extraction-options.csproj

@@ -0,0 +1,24 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>net10.0</TargetFramework>
+    <RootNamespace>Different_table_extraction_options</RootNamespace>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <Nullable>enable</Nullable>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Syncfusion.SmartDataExtractor.Net.Core" Version="*" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <None Update="Data\Input.pdf">
+      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
+    </None>
+    <None Update="Output\.gitkeep">
+      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
+    </None>
+  </ItemGroup>
+
+</Project>

Data-Extraction/Smart-Data-Extractor/Different-table-extraction-options/.NET/Different-table-extraction-options/Program.cs

@@ -0,0 +1,47 @@
+using System.IO;
+using Syncfusion.Pdf.Parsing;
+using Syncfusion.SmartDataExtractor;
+using Syncfusion.SmartTableExtractor;
+
+namespace DifferentTableExtractionOptions
+{
+	class Program
+	{
+		static void Main(string[] args)
+		{
+			// Load the input PDF file.
+			using (FileStream stream = new FileStream(@"Data\Input.pdf", FileMode.Open, FileAccess.Read))
+			{
+				// Initialize the Smart Data Extractor.
+				DataExtractor extractor = new DataExtractor();
+
+				// Enable table detection and set confidence threshold.
+				extractor.EnableTableDetection = true;
+
+				// Configure table extraction options.
+				TableExtractionOptions tableOptions = new TableExtractionOptions();
+
+				// Extract tables across pages 1 to 5.
+				tableOptions.PageRange = new int[,] { { 1, 5 } };
+
+				// Set confidence threshold for table extraction.
+				tableOptions.ConfidenceThreshold = 0.6;
+
+				// Enable detection of borderless tables.
+				tableOptions.DetectBorderlessTables = true;
+
+				// Assign the table extraction options to the extractor.
+				extractor.TableExtractionOptions = tableOptions;
+
+				// Extract data and return as a loaded PDF document.
+				PdfLoadedDocument pdf = extractor.ExtractDataAsPdfDocument(stream);
+
+				// Save the extracted output as a new PDF file.
+				pdf.Save(@"Output\Output.pdf");
+
+				// Close the document to release resources.
+				pdf.Close(true);
+			}
+		}
+	}
+}

Data-Extraction/Smart-Data-Extractor/Disable-Form-detection/.NET/Disable-Form-detection.slnx

@@ -0,0 +1,3 @@
+<Solution>
+  <Project Path="Disable-Form-detection/Disable-Form-detection.csproj" />
+</Solution>

Data-Extraction/Smart-Data-Extractor/Disable-Form-detection/.NET/Disable-Form-detection/Disable-Form-detection.csproj

@@ -0,0 +1,24 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>net10.0</TargetFramework>
+    <RootNamespace>Disable_Form_detection</RootNamespace>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <Nullable>enable</Nullable>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Syncfusion.SmartDataExtractor.Net.Core" Version="*" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <None Update="Data\Input.pdf">
+      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
+    </None>
+    <None Update="Output\.gitkeep">
+      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
+    </None>
+  </ItemGroup>
+
+</Project>

Data-Extraction/Smart-Data-Extractor/Disable-Form-detection/.NET/Disable-Form-detection/Program.cs

@@ -0,0 +1,33 @@
+using System.IO;
+using Syncfusion.Pdf.Parsing;
+using Syncfusion.SmartDataExtractor;
+using Syncfusion.SmartFormRecognizer;
+
+namespace FormDetection
+{
+	class Program
+	{
+		static void Main(string[] args)
+		{
+			// Open the input PDF file as a stream.
+			using (FileStream stream = new FileStream(@"Data\Input.pdf", FileMode.Open, FileAccess.Read))
+			{
+				// Initialize the Smart Data Extractor.
+				DataExtractor extractor = new DataExtractor();
+
+				// Enable or disable form detection in the document to identify form fields.
+				// By default this property is true.
+				extractor.EnableFormDetection = false;
+
+				// Extract form data and return as a loaded PDF document.
+				PdfLoadedDocument pdf = extractor.ExtractDataAsPdfDocument(stream);
+
+				// Save the extracted output as a new PDF file.
+				pdf.Save(@"Output\Output.pdf");
+
+				// Close the document to release resources.
+				pdf.Close(true);
+			}
+		}
+	}
+}

Data-Extraction/Smart-Data-Extractor/Disable-Table-detection/.NET/Disable-Table-detection.slnx

@@ -0,0 +1,3 @@
+<Solution>
+  <Project Path="Disable-Table-detection/Disable-Table-detection.csproj" />
+</Solution>

Data-Extraction/Smart-Data-Extractor/Disable-Table-detection/.NET/Disable-Table-detection/Disable-Table-detection.csproj

@@ -0,0 +1,24 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>net10.0</TargetFramework>
+    <RootNamespace>Disable_Table_detection</RootNamespace>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <Nullable>enable</Nullable>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Syncfusion.SmartDataExtractor.Net.Core" Version="*" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <None Update="Data\Input.pdf">
+      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
+    </None>
+    <None Update="Output\.gitkeep">
+      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
+    </None>
+  </ItemGroup>
+
+</Project>

Data-Extraction/Smart-Data-Extractor/Disable-Table-detection/.NET/Disable-Table-detection/Program.cs

@@ -0,0 +1,32 @@
+using System.IO;
+using Syncfusion.Pdf.Parsing;
+using Syncfusion.SmartDataExtractor;
+
+namespace DisableTableDetection
+{
+	class Program
+	{
+		static void Main(string[] args)
+		{
+			// Load the input PDF file.
+			using (FileStream stream = new FileStream(@"Data\Input.pdf", FileMode.Open, FileAccess.Read))
+			{
+				// Initialize the Smart Data Extractor.
+				DataExtractor extractor = new DataExtractor();
+
+				// Enable or disable table detection and set confidence threshold.
+				// By default this property is true.
+				extractor.EnableTableDetection = false;
+
+				// Extract data and return as a loaded PDF document.
+				PdfLoadedDocument pdf = extractor.ExtractDataAsPdfDocument(stream);
+
+				// Save the extracted output as a new PDF file.
+				pdf.Save(@"Output\Output.pdf");
+
+				// Close the document to release resources.
+				pdf.Close(true);
+			}
+		}
+	}
+}

Data-Extraction/Smart-Data-Extractor/Extract-data-as-JSON-from-PDF/.NET/Extract-data-as-JSON-from-PDF-document.slnx

@@ -0,0 +1,3 @@
+<Solution>
+  <Project Path="Extract-data-as-JSON-from-PDF-document/Extract-data-as-JSON-from-PDF-document.csproj" />
+</Solution>

Data-Extraction/Smart-Data-Extractor/Extract-data-as-JSON-from-PDF/.NET/Extract-data-as-JSON-from-PDF-document/Extract-data-as-JSON-from-PDF-document.csproj

@@ -0,0 +1,24 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>net10.0</TargetFramework>
+    <RootNamespace>Extract_data_as_JSON_from_PDF_document</RootNamespace>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <Nullable>enable</Nullable>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Syncfusion.SmartDataExtractor.Net.Core" Version="*" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <None Update="Data\Input.pdf">
+      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
+    </None>
+    <None Update="Output\.gitkeep">
+      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
+    </None>
+  </ItemGroup>
+
+</Project>