IronPDFを使用してC#で2つのPDFファイルを比較する方法

Install-Package IronPdf
dotnet add package IronPdf

IronPdf.License.LicenseKey = "YOUR-LICENSE-KEY";

IronPdf.License.LicenseKey = "YOUR-LICENSE-KEY"

using IronPdf;
using System;

// Load two PDF documents
var pdf1 = PdfDocument.FromFile("document1.pdf");
var pdf2 = PdfDocument.FromFile("document2.pdf");

// Extract text from both PDFs
string text1 = pdf1.ExtractAllText();
string text2 = pdf2.ExtractAllText();

// Compare the two documents
if (text1 == text2)
{
    Console.WriteLine("PDF files are identical");
}
else
{
    Console.WriteLine("PDFs have differences");

    // Calculate character-level similarity
    int maxLength = Math.Max(text1.Length, text2.Length);
    if (maxLength > 0)
    {
        int differences = 0;
        int minLength = Math.Min(text1.Length, text2.Length);

        for (int i = 0; i < minLength; i++)
        {
            if (text1[i] != text2[i]) differences++;
        }

        differences += Math.Abs(text1.Length - text2.Length);
        double similarity = 1.0 - (double)differences / maxLength;

        Console.WriteLine($"Similarity: {similarity:P}");
        Console.WriteLine($"Character differences: {Math.Abs(text1.Length - text2.Length)}");
    }
}

Imports IronPdf
Imports System

' Load two PDF documents
Dim pdf1 = PdfDocument.FromFile("document1.pdf")
Dim pdf2 = PdfDocument.FromFile("document2.pdf")

' Extract text from both PDFs
Dim text1 As String = pdf1.ExtractAllText()
Dim text2 As String = pdf2.ExtractAllText()

' Compare the two documents
If text1 = text2 Then
    Console.WriteLine("PDF files are identical")
Else
    Console.WriteLine("PDFs have differences")

    ' Calculate character-level similarity
    Dim maxLength As Integer = Math.Max(text1.Length, text2.Length)
    If maxLength > 0 Then
        Dim differences As Integer = 0
        Dim minLength As Integer = Math.Min(text1.Length, text2.Length)

        For i As Integer = 0 To minLength - 1
            If text1(i) <> text2(i) Then differences += 1
        Next

        differences += Math.Abs(text1.Length - text2.Length)
        Dim similarity As Double = 1.0 - CDbl(differences) / maxLength

        Console.WriteLine($"Similarity: {similarity:P}")
        Console.WriteLine($"Character differences: {Math.Abs(text1.Length - text2.Length)}")
    End If
End If

using IronPdf;
using System;
using System.Collections.Generic;

var pdf1 = PdfDocument.FromFile("document1.pdf");
var pdf2 = PdfDocument.FromFile("document2.pdf");

int maxPages = Math.Max(pdf1.PageCount, pdf2.PageCount);
var pageResults = new List<(int Page, double Similarity)>();

for (int i = 0; i < maxPages; i++)
{
    string page1Text = i < pdf1.PageCount ? pdf1.ExtractTextFromPage(i) : "";
    string page2Text = i < pdf2.PageCount ? pdf2.ExtractTextFromPage(i) : "";

    if (page1Text != page2Text)
    {
        int maxLen = Math.Max(page1Text.Length, page2Text.Length);
        double sim = maxLen == 0 ? 1.0
            : 1.0 - (double)Math.Abs(page1Text.Length - page2Text.Length) / maxLen;

        Console.WriteLine($"Page {i + 1} differs -- similarity: {sim:P}");
        pageResults.Add((i + 1, sim));
    }
}

Console.WriteLine($"\nTotal pages with differences: {pageResults.Count}");

Imports IronPdf
Imports System
Imports System.Collections.Generic

Dim pdf1 = PdfDocument.FromFile("document1.pdf")
Dim pdf2 = PdfDocument.FromFile("document2.pdf")

Dim maxPages As Integer = Math.Max(pdf1.PageCount, pdf2.PageCount)
Dim pageResults = New List(Of (Page As Integer, Similarity As Double))()

For i As Integer = 0 To maxPages - 1
    Dim page1Text As String = If(i < pdf1.PageCount, pdf1.ExtractTextFromPage(i), "")
    Dim page2Text As String = If(i < pdf2.PageCount, pdf2.ExtractTextFromPage(i), "")

    If page1Text <> page2Text Then
        Dim maxLen As Integer = Math.Max(page1Text.Length, page2Text.Length)
        Dim sim As Double = If(maxLen = 0, 1.0, 1.0 - CDbl(Math.Abs(page1Text.Length - page2Text.Length)) / maxLen)

        Console.WriteLine($"Page {i + 1} differs -- similarity: {sim:P}")
        pageResults.Add((i + 1, sim))
    End If
Next

Console.WriteLine($"\nTotal pages with differences: {pageResults.Count}")

using IronPdf;
using System;
using System.Collections.Generic;
using System.IO;

string[] pdfPaths = { "reference.pdf", "version1.pdf", "version2.pdf", "version3.pdf" };

if (pdfPaths.Length < 2)
{
    Console.WriteLine("At least 2 PDFs required for comparison");
    return;
}

var referencePdf = PdfDocument.FromFile(pdfPaths[0]);
string referenceText = referencePdf.ExtractAllText();

var results = new List<(string File, double Similarity, bool Identical)>();

for (int i = 1; i < pdfPaths.Length; i++)
{
    try
    {
        var currentPdf = PdfDocument.FromFile(pdfPaths[i]);
        string currentText = currentPdf.ExtractAllText();

        bool identical = referenceText == currentText;
        int maxLen = Math.Max(referenceText.Length, currentText.Length);
        double similarity = maxLen == 0 ? 1.0
            : 1.0 - (double)Math.Abs(referenceText.Length - currentText.Length) / maxLen;

        results.Add((Path.GetFileName(pdfPaths[i]), similarity, identical));

        string status = identical ? "identical to reference" : $"differs -- similarity: {similarity:P}";
        Console.WriteLine($"{Path.GetFileName(pdfPaths[i])}: {status}");
    }
    catch (Exception ex)
    {
        Console.WriteLine($"Error processing {pdfPaths[i]}: {ex.Message}");
    }
}

Console.WriteLine($"\nBatch complete: {results.Count} files compared");
Console.WriteLine($"Identical: {results.FindAll(r => r.Identical).Count}");
Console.WriteLine($"Different: {results.FindAll(r => !r.Identical).Count}");

Imports IronPdf
Imports System
Imports System.Collections.Generic
Imports System.IO

Module Module1
    Sub Main()
        Dim pdfPaths As String() = {"reference.pdf", "version1.pdf", "version2.pdf", "version3.pdf"}

        If pdfPaths.Length < 2 Then
            Console.WriteLine("At least 2 PDFs required for comparison")
            Return
        End If

        Dim referencePdf = PdfDocument.FromFile(pdfPaths(0))
        Dim referenceText As String = referencePdf.ExtractAllText()

        Dim results As New List(Of (File As String, Similarity As Double, Identical As Boolean))()

        For i As Integer = 1 To pdfPaths.Length - 1
            Try
                Dim currentPdf = PdfDocument.FromFile(pdfPaths(i))
                Dim currentText As String = currentPdf.ExtractAllText()

                Dim identical As Boolean = (referenceText = currentText)
                Dim maxLen As Integer = Math.Max(referenceText.Length, currentText.Length)
                Dim similarity As Double = If(maxLen = 0, 1.0, 1.0 - CDbl(Math.Abs(referenceText.Length - currentText.Length)) / maxLen)

                results.Add((Path.GetFileName(pdfPaths(i)), similarity, identical))

                Dim status As String = If(identical, "identical to reference", $"differs -- similarity: {similarity:P}")
                Console.WriteLine($"{Path.GetFileName(pdfPaths(i))}: {status}")
            Catch ex As Exception
                Console.WriteLine($"Error processing {pdfPaths(i)}: {ex.Message}")
            End Try
        Next

        Console.WriteLine($"\nBatch complete: {results.Count} files compared")
        Console.WriteLine($"Identical: {results.FindAll(Function(r) r.Identical).Count}")
        Console.WriteLine($"Different: {results.FindAll(Function(r) Not r.Identical).Count}")
    End Sub
End Module

using IronPdf;
using System;

try
{
    // Load password-protected PDFs
    var pdf1 = PdfDocument.FromFile("secure-document1.pdf", "password1");
    var pdf2 = PdfDocument.FromFile("secure-document2.pdf", "password2");

    Console.WriteLine($"PDF 1 loaded: {pdf1.PageCount} pages");
    Console.WriteLine($"PDF 2 loaded: {pdf2.PageCount} pages");

    string text1 = pdf1.ExtractAllText();
    string text2 = pdf2.ExtractAllText();

    bool identical = text1.Equals(text2);
    int maxLen = Math.Max(text1.Length, text2.Length);
    double similarity = maxLen == 0 ? 1.0
        : 1.0 - (double)Math.Abs(text1.Length - text2.Length) / maxLen;

    Console.WriteLine($"Documents are {(identical ? "identical" : "different")}");
    Console.WriteLine($"Similarity: {similarity:P}");

    // Optionally save a secured comparison report
    if (!identical)
    {
        var renderer = new ChromePdfRenderer();
        var reportPdf = renderer.RenderHtmlAsPdf(
            $"<h1>Comparison Result</h1><p>Similarity: {similarity:P}</p>");

        reportPdf.SecuritySettings.OwnerPassword = "report-owner-password";
        reportPdf.SecuritySettings.UserPassword = "report-user-password";
        reportPdf.SecuritySettings.AllowUserPrinting = true;
        reportPdf.SecuritySettings.AllowUserCopyPasteContent = false;

        reportPdf.SaveAs("comparison-report.pdf");
        Console.WriteLine("Secured report saved.");
    }
}
catch (Exception ex)
{
    Console.WriteLine($"Error handling secured PDFs: {ex.Message}");
}

Imports IronPdf
Imports System

Try
    ' Load password-protected PDFs
    Dim pdf1 = PdfDocument.FromFile("secure-document1.pdf", "password1")
    Dim pdf2 = PdfDocument.FromFile("secure-document2.pdf", "password2")

    Console.WriteLine($"PDF 1 loaded: {pdf1.PageCount} pages")
    Console.WriteLine($"PDF 2 loaded: {pdf2.PageCount} pages")

    Dim text1 As String = pdf1.ExtractAllText()
    Dim text2 As String = pdf2.ExtractAllText()

    Dim identical As Boolean = text1.Equals(text2)
    Dim maxLen As Integer = Math.Max(text1.Length, text2.Length)
    Dim similarity As Double = If(maxLen = 0, 1.0, 1.0 - CDbl(Math.Abs(text1.Length - text2.Length)) / maxLen)

    Console.WriteLine($"Documents are {(If(identical, "identical", "different"))}")
    Console.WriteLine($"Similarity: {similarity:P}")

    ' Optionally save a secured comparison report
    If Not identical Then
        Dim renderer = New ChromePdfRenderer()
        Dim reportPdf = renderer.RenderHtmlAsPdf($"<h1>Comparison Result</h1><p>Similarity: {similarity:P}</p>")

        reportPdf.SecuritySettings.OwnerPassword = "report-owner-password"
        reportPdf.SecuritySettings.UserPassword = "report-user-password"
        reportPdf.SecuritySettings.AllowUserPrinting = True
        reportPdf.SecuritySettings.AllowUserCopyPasteContent = False

        reportPdf.SaveAs("comparison-report.pdf")
        Console.WriteLine("Secured report saved.")
    End If
Catch ex As Exception
    Console.WriteLine($"Error handling secured PDFs: {ex.Message}")
End Try

using IronPdf;
using System;
using System.Collections.Generic;
using System.IO;
using System.Text;

var pdf1 = PdfDocument.FromFile("document1.pdf");
var pdf2 = PdfDocument.FromFile("document2.pdf");

var differences = new List<(int Page, double Similarity, int Len1, int Len2, int CharDiff)>();
int totalPages = Math.Max(pdf1.PageCount, pdf2.PageCount);

for (int i = 0; i < totalPages; i++)
{
    string p1 = i < pdf1.PageCount ? pdf1.ExtractTextFromPage(i) ?? "" : "";
    string p2 = i < pdf2.PageCount ? pdf2.ExtractTextFromPage(i) ?? "" : "";

    if (p1 == p2) continue;

    int maxLen = Math.Max(p1.Length, p2.Length);
    double sim = maxLen == 0 ? 1.0 : 1.0 - (double)Math.Abs(p1.Length - p2.Length) / maxLen;
    int charDiff = Math.Abs(p1.Length - p2.Length);

    differences.Add((i + 1, sim, p1.Length, p2.Length, charDiff));
}

// Build HTML report
var sb = new StringBuilder();
sb.Append(@"<html><head><style>
    body { font-family: Arial, sans-serif; margin: 20px; }
    h1 { color: #333; border-bottom: 2px solid #4CAF50; }
    .summary { background: #f0f0f0; padding: 15px; border-radius: 5px; margin-bottom: 20px; }
    table { border-collapse: collapse; width: 100%; }
    th, td { border: 1px solid #ddd; padding: 8px; text-align: left; }
    th { background: #4CAF50; color: white; }
    .ok { background: #c8e6c9; padding: 15px; border-radius: 5px; }
</style></head><body>");

sb.Append("<h1>PDF Comparison Report</h1>");
sb.Append("<div class='summary'>");
sb.Append($"<p><strong>File 1:</strong> {Path.GetFileName("document1.pdf")}</p>");
sb.Append($"<p><strong>File 2:</strong> {Path.GetFileName("document2.pdf")}</p>");
sb.Append($"<p><strong>Pages with differences:</strong> {differences.Count} of {totalPages}</p>");
sb.Append($"<p><strong>Generated:</strong> {DateTime.Now:yyyy-MM-dd HH:mm:ss}</p>");
sb.Append("</div>");

if (differences.Count > 0)
{
    sb.Append("<table><thead><tr><th>Page</th><th>Similarity</th><th>File 1 Length</th><th>File 2 Length</th><th>Char Diff</th></tr></thead><tbody>");
    foreach (var d in differences)
    {
        sb.Append($"<tr><td>{d.Page}</td><td>{d.Similarity:P}</td><td>{d.Len1}</td><td>{d.Len2}</td><td>{d.CharDiff}</td></tr>");
    }
    sb.Append("</tbody></table>");
}
else
{
    sb.Append("<p class='ok'>No differences detected -- files are identical.</p>");
}

sb.Append("</body></html>");

var renderer = new ChromePdfRenderer();
renderer.RenderingOptions.MarginTop = 25;
renderer.RenderingOptions.MarginBottom = 25;
renderer.RenderingOptions.CssMediaType = IronPdf.Rendering.PdfCssMediaType.Print;

var reportPdf = renderer.RenderHtmlAsPdf(sb.ToString());
reportPdf.MetaData.Author = "PDF Comparison Tool";
reportPdf.MetaData.Title = "PDF Comparison Report";
reportPdf.MetaData.CreationDate = DateTime.Now;

reportPdf.SaveAs("comparison-report.pdf");
Console.WriteLine("Report saved to comparison-report.pdf");

Imports IronPdf
Imports System
Imports System.Collections.Generic
Imports System.IO
Imports System.Text

Dim pdf1 = PdfDocument.FromFile("document1.pdf")
Dim pdf2 = PdfDocument.FromFile("document2.pdf")

Dim differences = New List(Of (Page As Integer, Similarity As Double, Len1 As Integer, Len2 As Integer, CharDiff As Integer))()
Dim totalPages As Integer = Math.Max(pdf1.PageCount, pdf2.PageCount)

For i As Integer = 0 To totalPages - 1
    Dim p1 As String = If(i < pdf1.PageCount, pdf1.ExtractTextFromPage(i), "")
    Dim p2 As String = If(i < pdf2.PageCount, pdf2.ExtractTextFromPage(i), "")

    If p1 = p2 Then Continue For

    Dim maxLen As Integer = Math.Max(p1.Length, p2.Length)
    Dim sim As Double = If(maxLen = 0, 1.0, 1.0 - CDbl(Math.Abs(p1.Length - p2.Length)) / maxLen)
    Dim charDiff As Integer = Math.Abs(p1.Length - p2.Length)

    differences.Add((i + 1, sim, p1.Length, p2.Length, charDiff))
Next

' Build HTML report
Dim sb = New StringBuilder()
sb.Append("<html><head><style>
    body { font-family: Arial, sans-serif; margin: 20px; }
    h1 { color: #333; border-bottom: 2px solid #4CAF50; }
    .summary { background: #f0f0f0; padding: 15px; border-radius: 5px; margin-bottom: 20px; }
    table { border-collapse: collapse; width: 100%; }
    th, td { border: 1px solid #ddd; padding: 8px; text-align: left; }
    th { background: #4CAF50; color: white; }
    .ok { background: #c8e6c9; padding: 15px; border-radius: 5px; }
</style></head><body>")

sb.Append("<h1>PDF Comparison Report</h1>")
sb.Append("<div class='summary'>")
sb.Append($"<p><strong>File 1:</strong> {Path.GetFileName("document1.pdf")}</p>")
sb.Append($"<p><strong>File 2:</strong> {Path.GetFileName("document2.pdf")}</p>")
sb.Append($"<p><strong>Pages with differences:</strong> {differences.Count} of {totalPages}</p>")
sb.Append($"<p><strong>Generated:</strong> {DateTime.Now:yyyy-MM-dd HH:mm:ss}</p>")
sb.Append("</div>")

If differences.Count > 0 Then
    sb.Append("<table><thead><tr><th>Page</th><th>Similarity</th><th>File 1 Length</th><th>File 2 Length</th><th>Char Diff</th></tr></thead><tbody>")
    For Each d In differences
        sb.Append($"<tr><td>{d.Page}</td><td>{d.Similarity:P}</td><td>{d.Len1}</td><td>{d.Len2}</td><td>{d.CharDiff}</td></tr>")
    Next
    sb.Append("</tbody></table>")
Else
    sb.Append("<p class='ok'>No differences detected -- files are identical.</p>")
End If

sb.Append("</body></html>")

Dim renderer = New ChromePdfRenderer()
renderer.RenderingOptions.MarginTop = 25
renderer.RenderingOptions.MarginBottom = 25
renderer.RenderingOptions.CssMediaType = IronPdf.Rendering.PdfCssMediaType.Print

Dim reportPdf = renderer.RenderHtmlAsPdf(sb.ToString())
reportPdf.MetaData.Author = "PDF Comparison Tool"
reportPdf.MetaData.Title = "PDF Comparison Report"
reportPdf.MetaData.CreationDate = DateTime.Now

reportPdf.SaveAs("comparison-report.pdf")
Console.WriteLine("Report saved to comparison-report.pdf")