Merge pull request #251 from SyncfusionExamples/1022877-DataExtraction_MDSamples

Documentation (1022877) – Added PDF to Markdown Extraction Samples

Author: GowthamrajKumar25

Data-Extraction/Getting-Started/ASP.NETCore/Recognize_Forms/Recognize_Forms/Data/Input.pdf

@@ -0,0 +1,37 @@
+# Extract Structured Data from PDF
+
+The Syncfusion® [Smart Data Extractor](https://www.syncfusion.com/document-sdk/net-pdf-data-extraction) is a .NET library used to extract document structures such as hierarchies, text blocks, images, headers, and footers from PDFs and scanned images by analyzing visual layout patterns like lines, boxes, and alignment. It returns structured JSON with per-field confidence scores
+
+## Steps to Extract Structured Data from PDF Files
+
+Step 1: **Create a new project:** Begin by setting up a new C# Console Application project.
+
+Step 2: **Install the NuGet package:** Add the [Syncfusion.SmartDataExtractor.Net.Core](https://www.nuget.org/packages/Syncfusion.SmartDataExtractor.Net.Core) package to your project from [NuGet.org](https://www.nuget.org/).
+
+Step 3: **Include necessary namespaces:** Add these namespaces in your Program.cs file:
+
+```csharp
+using System.IO;
+using System.Text;
+using Syncfusion.SmartDataExtractor;
+
+```
+
+Step 4: Add the following code snippet in Program.cs file to extract data from PDF.
+
+```csharp
+// Open the input PDF file as a stream.
+using (FileStream stream = new FileStream(Path.GetFullPath("Input.pdf"), FileMode.Open, FileAccess.ReadWrite))
+{
+	// Initialize the Smart Data Extractor.
+	DataExtractor extractor = new DataExtractor();
+	// Extract form data as JSON.
+	string data = extractor.ExtractDataAsJson(stream);
+	// Save the extracted JSON data into an output file.
+	File.WriteAllText(Path.GetFullPath(@"Output.json"), data, Encoding.UTF8);
+}
+
+```
+For a complete working example, download it from [GitHub](https://github.com/SyncfusionExamples/PDF-Examples/tree/master/Data-Extraction/Smart-Data-Extractor/Extract-data-as-JSON-from-PDF/.NET).
+
+More information about Extract data from PDF can be refer in this [documentation](https://help.syncfusion.com/document-processing/data-extraction/smart-data-extractor/overview)section.

Data-Extraction/Getting-Started/Console/.NETFramework/Recognize_Forms/Recognize_Forms/Data/Input.pdf

@@ -0,0 +1,22 @@
+
+Microsoft Visual Studio Solution File, Format Version 12.00
+# Visual Studio Version 18
+VisualStudioVersion = 18.5.11716.220 stable
+MinimumVisualStudioVersion = 10.0.40219.1
+Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "Extract-data-as-MD-from-PDF", "Extract-data-as-MD-from-PDF\Extract-data-as-MD-from-PDF.csproj", "{29872D0F-18F6-6AB7-0892-D538C0E179BA}"
+EndProject
+Global
+	GlobalSection(SolutionConfigurationPlatforms) = preSolution
+		Debug|Any CPU = Debug|Any CPU
+		Release|Any CPU = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(ProjectConfigurationPlatforms) = postSolution
+		{29872D0F-18F6-6AB7-0892-D538C0E179BA}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{29872D0F-18F6-6AB7-0892-D538C0E179BA}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{29872D0F-18F6-6AB7-0892-D538C0E179BA}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{29872D0F-18F6-6AB7-0892-D538C0E179BA}.Release|Any CPU.Build.0 = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(SolutionProperties) = preSolution
+		HideSolutionNode = FALSE
+	EndGlobalSection
+EndGlobal

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

@@ -0,0 +1,24 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>net8.0</TargetFramework>
+    <RootNamespace>Extract_data_as_MD_from_PDF</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/Extract-data-as-MD-from-PDF/.NET/Extract-data-as-MD-from-PDF.sln

@@ -0,0 +1,13 @@
+using Syncfusion.SmartDataExtractor;
+using System.Text;
+
+//Open the input PDF file as a stream.
+using (FileStream stream = new FileStream(Path.GetFullPath(@"Data\Input.pdf"), FileMode.Open, FileAccess.ReadWrite))
+{
+	//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(Path.GetFullPath(@"Output\Output.md"), data, Encoding.UTF8);
+}

Data-Extraction/Smart-Data-Extractor/Extract-data-as-MD-from-PDF/.NET/Extract-data-as-MD-from-PDF/Data/Input.pdf

@@ -0,0 +1,35 @@
+# Extract Structured Data from PDF as Markdown
+
+The Syncfusion® [Smart Data Extractor](https://www.syncfusion.com/document-sdk/net-pdf-data-extraction) is a .NET library that extracts document structures such as hierarchies, text blocks, images, headers, and footers from PDFs and scanned images by analyzing visual layout patterns like lines, boxes, and alignment.
+
+## Steps to Extract Data as Markdown from PDF Files
+
+Step 1: **Create a new project:** Begin by setting up a new C# Console Application project.
+
+Step 2: **Install the NuGet package:** Add the [Syncfusion.SmartDataExtractor.Net.Core](https://www.nuget.org/packages/Syncfusion.SmartDataExtractor.Net.Core) package to your project from [NuGet.org](https://www.nuget.org/).
+
+Step 3: **Include necessary namespaces:** Add these namespaces in your Program.cs file:
+
+```csharp
+using System.IO;
+using System.Text;
+using Syncfusion.SmartDataExtractor;
+
+```
+
+Step 4: Add the following code snippet in Program.cs file to extract data from PDF.
+
+```csharp
+//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);
+}
+
+```
+More information about Extract data from PDF can be refer in this [documentation](https://help.syncfusion.com/document-processing/data-extraction/smart-data-extractor/overview)section.

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

@@ -0,0 +1,34 @@
+# Recognize Form Data from PDF using C#
+
+The Syncfusion® [Smart Form Recognizer](https://www.syncfusion.com/document-sdk/net-pdf-data-extraction) is a .NET C# library that detects form regions and extracts text fields, checkboxes, radio buttons, and signatures by interpreting visual patterns such as boxes and selection markers. The extracted results are returned as normalized JSON with confidence scores, enabling applications to automatically process form data. 
+
+## Steps to Recognize Form Data from PDF Files
+
+Step 1: **Create a new project:** Begin by setting up a new C# Console Application project.
+
+Step 2:  **Install the NuGet package:** Add the [Syncfusion.SmartFormRecognizer.Net.Core](https://www.nuget.org/packages/Syncfusion.SmartFormRecognizer.Net.Core) package to your project from [NuGet.org](https://www.nuget.org/).
+
+Step 3: **Include necessary namespaces:** Add these namespaces in your Program.cs file:
+
+```csharp
+using System.IO;
+using Syncfusion.SmartFormRecognizer;
+```
+
+Step 4: Add the following code snippet in Program.cs file to extract data from PDF.
+
+```csharp
+// Read the input PDF file as stream.
+using (FileStream inputStream = new FileStream(Path.GetFullPath(@"Input.pdf"), FileMode.Open, FileAccess.ReadWrite))
+{
+	// Initialize the Form Recognizer.
+	FormRecognizer smartFormRecognizer = new FormRecognizer();
+	// Recognize the form and get the output as JSON string.
+	string outputJson = smartFormRecognizer.RecognizeFormAsJson(inputStream);
+	// Save the output JSON to file.
+	File.WriteAllText(Path.GetFullPath(@"Output.json"),outputJson);
+}
+```
+For a complete working example, download it from [GitHub](https://github.com/SyncfusionExamples/PDF-Examples/tree/master/Data-Extraction/Smart-Form-Recognizer/Recognize-forms-using-JSON/.NET). 
+
+More information about SmartFormRecognizer can be refer in this [documentation](https://help.syncfusion.com/document-processing/data-extraction/smart-form-recognizer/overview)section.