How to compare text in two PDF documents?

Syncfusion Essential® PDF is a .NET PDF library used to create, read, and edit PDF document. Using this library, you can compare the text in two PDF documents by text extraction. The resultant PDF document highlight the entire line of changed text.

Steps to compare the text in PDF documents programmatically:

1. Create a new Windows Forms application project.
2. Install the Syncfusion.Pdf.Base NuGet package as reference to your .NET Framework application from NuGet.org.
3. Include the following namespace in the Form1.Designer.cs file.

C#

using Syncfusion.Pdf;
using Syncfusion.Pdf.Graphics;
using Syncfusion.Pdf.Parsing;

4. Add a new button in Form1.Designer.cs to compare the PDF files as follows.

   label = new Label();
   button = new Button();
    
   // Label
   label.Location = new System.Drawing.Point(0, 40);
   label.Size = new System.Drawing.Size(426, 35);
   label.Text = "Click the button to view the compared PDF file generated by Essential PDF";
   label.TextAlign = System.Drawing.ContentAlignment.MiddleCenter;
    
   // Button
   button.Location = new System.Drawing.Point(180, 110);
   button.Size = new System.Drawing.Size(85, 26);
   button.Text = "Compare PDF";
   button.Click += new EventHandler(ComparePDF);
    
   // Create PDF
   ClientSize = new System.Drawing.Size(450, 150);
   Controls.Add(label);
   Controls.Add(button);
   Text = "Create PDF";
   

5. Add the following code in ComparePDF to compare text in two PDF documents.

    //Load the first PDF document
   PdfLoadedDocument loadedDocument = new PdfLoadedDocument("../../Data/Source1.pdf");
    
   // Load the second PDF document
   PdfLoadedDocument loadedDocument1 = new PdfLoadedDocument("../../Data/Source2.pdf");
   // Creating the list to store text data in PDF documents
   List<TextData> textData = new List<TextData>();
   List<TextData> textData1 = new List<TextData>();
   List<TextData> maxContainsData = new List<TextData>();
   List<TextData> diff = new List<TextData>();
   for (int i = 0; i < loadedDocument.Pages.Count; i++)
   {
       // Get the page from the first document
       PdfLoadedPage loadedPage = loadedDocument.Pages[i] as PdfLoadedPage;
       // Extract the text from the page of the first document 
       string extractedText = loadedPage.ExtractText(out textData);
        // Extract the text from the page of the second document 
       string extractedText1 = loadedDocument1.Pages[i].ExtractText(out textData1);
        int minCount = 0;
        // Compare the text data count
       if (textData.Count > textData1.Count)
           maxContainsData = textData;
       if (textData.Count < textData1.Count)
           maxContainsData = textData1;
        if (textData != textData1)
       {
           if (textData.Count == textData1.Count)
               minCount = textData.Count;
           else
           {
               List<int> count = new List<int>();
               count.Add(textData.Count);
               count.Add(textData1.Count);
               minCount = count.Min();
               // Add diff text to the list
               diff.Add(maxContainsData[minCount]);
           }
           for (int j = 0; j < minCount; j++)
           {
               if (textData[j].Text != textData1[j].Text && textData[j].Bounds != textData1[j].Bounds)
               {
                   // Add diff text to the list
                   diff.Add(textData[j]);
               }
           }
       }
       // Highlight the changed text
       foreach (TextData data in diff)
       {
           loadedPage.Graphics.DrawRectangle(PdfPens.Red, PdfBrushes.Transparent, data.Bounds);
       }
   }
   // Save and close the document 
   loadedDocument.Save("ComparedPDF.pdf");
   loadedDocument.Close(true);
   loadedDocument1.Close(true);
    
   //This will open the PDF file so, the result will be seen in default PDF viewer 
   System.Diagnostics.Process.Start("ComparedPDF.pdf");
   

A complete working sample can be downloaded from PDFComparisonSample.zip.

By executing the program, you will get the PDF document as follows.