Procesamiento de PDF por lotes en C#: Automatice Flujos de Trabajo de Documentos a Gran Escala

Imports IronPdf

IronPdf.License.LicenseKey = "KEY"

Imports IronPdf

IronPdf.License.LicenseKey = "KEY"

Imports IronPdf
Imports System
Imports System.IO
Imports System.Threading.Tasks
Imports System.Threading

' Configure paths
Dim inputFolder As String = "input/"
Dim outputFolder As String = "output/"

Directory.CreateDirectory(outputFolder)

Dim htmlFiles As String() = Directory.GetFiles(inputFolder, "*.html")
Console.WriteLine($"Found {htmlFiles.Length} HTML files to convert")

' Create renderer instance (thread-safe, can be shared)
Dim renderer As New ChromePdfRenderer()

' Track progress
Dim processed As Integer = 0
Dim failed As Integer = 0

' Process in parallel with controlled concurrency
Dim options As New ParallelOptions With {
    .MaxDegreeOfParallelism = Environment.ProcessorCount \ 2
}

Parallel.ForEach(htmlFiles, options, Sub(htmlFile)
    Try
        Dim fileName As String = Path.GetFileNameWithoutExtension(htmlFile)
        Dim outputPath As String = Path.Combine(outputFolder, $"{fileName}.pdf")

        Using pdf = renderer.RenderHtmlFileAsPdf(htmlFile)
            pdf.SaveAs(outputPath)
        End Using

        Interlocked.Increment(processed)
        Console.WriteLine($"[OK] {fileName}.pdf")
    Catch ex As Exception
        Interlocked.Increment(failed)
        Console.WriteLine($"[ERROR] {Path.GetFileName(htmlFile)}: {ex.Message}")
    End Try
End Sub)

Console.WriteLine($"\nComplete: {processed} succeeded, {failed} failed")

Imports IronPdf
Imports System
Imports System.IO
Imports System.Threading.Tasks
Imports System.Threading

' Configure paths
Dim inputFolder As String = "input/"
Dim outputFolder As String = "output/"

Directory.CreateDirectory(outputFolder)

Dim htmlFiles As String() = Directory.GetFiles(inputFolder, "*.html")
Console.WriteLine($"Found {htmlFiles.Length} HTML files to convert")

' Create renderer instance (thread-safe, can be shared)
Dim renderer As New ChromePdfRenderer()

' Track progress
Dim processed As Integer = 0
Dim failed As Integer = 0

' Process in parallel with controlled concurrency
Dim options As New ParallelOptions With {
    .MaxDegreeOfParallelism = Environment.ProcessorCount \ 2
}

Parallel.ForEach(htmlFiles, options, Sub(htmlFile)
    Try
        Dim fileName As String = Path.GetFileNameWithoutExtension(htmlFile)
        Dim outputPath As String = Path.Combine(outputFolder, $"{fileName}.pdf")

        Using pdf = renderer.RenderHtmlFileAsPdf(htmlFile)
            pdf.SaveAs(outputPath)
        End Using

        Interlocked.Increment(processed)
        Console.WriteLine($"[OK] {fileName}.pdf")
    Catch ex As Exception
        Interlocked.Increment(failed)
        Console.WriteLine($"[ERROR] {Path.GetFileName(htmlFile)}: {ex.Message}")
    End Try
End Sub)

Console.WriteLine($"\nComplete: {processed} succeeded, {failed} failed")

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

Module Program
    Sub Main()
        Dim inputFolder As String = "documents/"
        Dim outputFolder As String = "merged/"

        Directory.CreateDirectory(outputFolder)

        ' Group PDFs by prefix (e.g., "invoice-2026-01-*.pdf" -> one merged file)
        Dim pdfFiles = Directory.GetFiles(inputFolder, "*.pdf")
        Dim groups = pdfFiles _
            .GroupBy(Function(f) Path.GetFileName(f).Split("-"c).Take(3).Aggregate(Function(a, b) $"{a}-{b}")) _
            .Where(Function(g) g.Count() > 1)

        Console.WriteLine($"Found {groups.Count()} groups to merge")

        For Each group In groups
            Dim groupName As String = group.Key
            Dim filesToMerge = group.OrderBy(Function(f) f).ToList()

            Console.WriteLine($"Merging {filesToMerge.Count} files into {groupName}.pdf")

            Try
                ' Load all PDFs for this group
                Dim pdfDocs As New List(Of PdfDocument)()
                For Each filePath As String In filesToMerge
                    pdfDocs.Add(PdfDocument.FromFile(filePath))
                Next

                ' Merge all documents
                Using merged = PdfDocument.Merge(pdfDocs)
                    merged.SaveAs(Path.Combine(outputFolder, $"{groupName}-merged.pdf"))
                End Using

                ' Dispose source documents
                For Each doc In pdfDocs
                    doc.Dispose()
                Next

                Console.WriteLine($"  [OK] Created {groupName}-merged.pdf ({merged.PageCount} pages)")
            Catch ex As Exception
                Console.WriteLine($"  [ERROR] {groupName}: {ex.Message}")
            End Try
        Next

        Console.WriteLine(vbCrLf & "Merge complete")
    End Sub
End Module

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

Module Program
    Sub Main()
        Dim inputFolder As String = "documents/"
        Dim outputFolder As String = "merged/"

        Directory.CreateDirectory(outputFolder)

        ' Group PDFs by prefix (e.g., "invoice-2026-01-*.pdf" -> one merged file)
        Dim pdfFiles = Directory.GetFiles(inputFolder, "*.pdf")
        Dim groups = pdfFiles _
            .GroupBy(Function(f) Path.GetFileName(f).Split("-"c).Take(3).Aggregate(Function(a, b) $"{a}-{b}")) _
            .Where(Function(g) g.Count() > 1)

        Console.WriteLine($"Found {groups.Count()} groups to merge")

        For Each group In groups
            Dim groupName As String = group.Key
            Dim filesToMerge = group.OrderBy(Function(f) f).ToList()

            Console.WriteLine($"Merging {filesToMerge.Count} files into {groupName}.pdf")

            Try
                ' Load all PDFs for this group
                Dim pdfDocs As New List(Of PdfDocument)()
                For Each filePath As String In filesToMerge
                    pdfDocs.Add(PdfDocument.FromFile(filePath))
                Next

                ' Merge all documents
                Using merged = PdfDocument.Merge(pdfDocs)
                    merged.SaveAs(Path.Combine(outputFolder, $"{groupName}-merged.pdf"))
                End Using

                ' Dispose source documents
                For Each doc In pdfDocs
                    doc.Dispose()
                Next

                Console.WriteLine($"  [OK] Created {groupName}-merged.pdf ({merged.PageCount} pages)")
            Catch ex As Exception
                Console.WriteLine($"  [ERROR] {groupName}: {ex.Message}")
            End Try
        Next

        Console.WriteLine(vbCrLf & "Merge complete")
    End Sub
End Module

Imports IronPdf
Imports System
Imports System.IO
Imports System.Threading.Tasks

Module Program
    Sub Main()
        Dim inputFolder As String = "multipage/"
        Dim outputFolder As String = "split/"

        Directory.CreateDirectory(outputFolder)

        Dim pdfFiles As String() = Directory.GetFiles(inputFolder, "*.pdf")
        Console.WriteLine($"Found {pdfFiles.Length} PDFs to split")

        Dim options As New ParallelOptions With {
            .MaxDegreeOfParallelism = Environment.ProcessorCount \ 2
        }

        Parallel.ForEach(pdfFiles, options, Sub(pdfFile)
                                                Dim baseName As String = Path.GetFileNameWithoutExtension(pdfFile)

                                                Try
                                                    Using pdf = PdfDocument.FromFile(pdfFile)
                                                        Dim pageCount As Integer = pdf.PageCount

                                                        Console.WriteLine($"Splitting {baseName}.pdf ({pageCount} pages)")

                                                        ' Extract each page as a separate PDF
                                                        For i As Integer = 0 To pageCount - 1
                                                            Using singlePage = pdf.CopyPage(i)
                                                                Dim outputPath As String = Path.Combine(outputFolder, $"{baseName}-page-{i + 1:D3}.pdf")
                                                                singlePage.SaveAs(outputPath)
                                                            End Using
                                                        Next

                                                        Console.WriteLine($"  [OK] Created {pageCount} files from {baseName}.pdf")
                                                    End Using
                                                Catch ex As Exception
                                                    Console.WriteLine($"  [ERROR] {baseName}: {ex.Message}")
                                                End Try
                                            End Sub)

        ' Alternative: Extract page ranges instead of individual pages
        Sub SplitByRange(inputFile As String, outputFolder As String, pagesPerChunk As Integer)
            Using pdf = PdfDocument.FromFile(inputFile)
                Dim baseName As String = Path.GetFileNameWithoutExtension(inputFile)
                Dim totalPages As Integer = pdf.PageCount
                Dim chunkNumber As Integer = 1

                For startPage As Integer = 0 To totalPages - 1 Step pagesPerChunk
                    Dim endPage As Integer = Math.Min(startPage + pagesPerChunk - 1, totalPages - 1)
                    Using chunk = pdf.CopyPages(startPage, endPage)
                        chunk.SaveAs(Path.Combine(outputFolder, $"{baseName}-chunk-{chunkNumber:D3}.pdf"))
                        chunkNumber += 1
                    End Using
                Next
            End Using
        End Sub

        Console.WriteLine(vbCrLf & "Split complete")
    End Sub
End Module

Imports IronPdf
Imports System
Imports System.IO
Imports System.Threading.Tasks

Module Program
    Sub Main()
        Dim inputFolder As String = "multipage/"
        Dim outputFolder As String = "split/"

        Directory.CreateDirectory(outputFolder)

        Dim pdfFiles As String() = Directory.GetFiles(inputFolder, "*.pdf")
        Console.WriteLine($"Found {pdfFiles.Length} PDFs to split")

        Dim options As New ParallelOptions With {
            .MaxDegreeOfParallelism = Environment.ProcessorCount \ 2
        }

        Parallel.ForEach(pdfFiles, options, Sub(pdfFile)
                                                Dim baseName As String = Path.GetFileNameWithoutExtension(pdfFile)

                                                Try
                                                    Using pdf = PdfDocument.FromFile(pdfFile)
                                                        Dim pageCount As Integer = pdf.PageCount

                                                        Console.WriteLine($"Splitting {baseName}.pdf ({pageCount} pages)")

                                                        ' Extract each page as a separate PDF
                                                        For i As Integer = 0 To pageCount - 1
                                                            Using singlePage = pdf.CopyPage(i)
                                                                Dim outputPath As String = Path.Combine(outputFolder, $"{baseName}-page-{i + 1:D3}.pdf")
                                                                singlePage.SaveAs(outputPath)
                                                            End Using
                                                        Next

                                                        Console.WriteLine($"  [OK] Created {pageCount} files from {baseName}.pdf")
                                                    End Using
                                                Catch ex As Exception
                                                    Console.WriteLine($"  [ERROR] {baseName}: {ex.Message}")
                                                End Try
                                            End Sub)

        ' Alternative: Extract page ranges instead of individual pages
        Sub SplitByRange(inputFile As String, outputFolder As String, pagesPerChunk As Integer)
            Using pdf = PdfDocument.FromFile(inputFile)
                Dim baseName As String = Path.GetFileNameWithoutExtension(inputFile)
                Dim totalPages As Integer = pdf.PageCount
                Dim chunkNumber As Integer = 1

                For startPage As Integer = 0 To totalPages - 1 Step pagesPerChunk
                    Dim endPage As Integer = Math.Min(startPage + pagesPerChunk - 1, totalPages - 1)
                    Using chunk = pdf.CopyPages(startPage, endPage)
                        chunk.SaveAs(Path.Combine(outputFolder, $"{baseName}-chunk-{chunkNumber:D3}.pdf"))
                        chunkNumber += 1
                    End Using
                Next
            End Using
        End Sub

        Console.WriteLine(vbCrLf & "Split complete")
    End Sub
End Module

Imports IronPdf
Imports System
Imports System.IO
Imports System.Threading.Tasks
Imports System.Threading

Module Program
    Sub Main()
        Dim inputFolder As String = "originals/"
        Dim outputFolder As String = "compressed/"

        Directory.CreateDirectory(outputFolder)

        Dim pdfFiles As String() = Directory.GetFiles(inputFolder, "*.pdf")
        Console.WriteLine($"Found {pdfFiles.Length} PDFs to compress")

        Dim totalOriginalSize As Long = 0
        Dim totalCompressedSize As Long = 0
        Dim processed As Integer = 0

        Dim options As New ParallelOptions With {
            .MaxDegreeOfParallelism = Environment.ProcessorCount \ 2
        }

        Parallel.ForEach(pdfFiles, options, Sub(pdfFile)
                                                Dim fileName As String = Path.GetFileName(pdfFile)
                                                Dim outputPath As String = Path.Combine(outputFolder, fileName)

                                                Try
                                                    Dim originalSize As Long = New FileInfo(pdfFile).Length
                                                    Interlocked.Add(totalOriginalSize, originalSize)

                                                    Using pdf = PdfDocument.FromFile(pdfFile)
                                                        ' Apply compression with JPEG quality setting (0-100, lower = more compression)
                                                        pdf.CompressAndSaveAs(outputPath, 60)
                                                    End Using

                                                    Dim compressedSize As Long = New FileInfo(outputPath).Length
                                                    Interlocked.Add(totalCompressedSize, compressedSize)
                                                    Interlocked.Increment(processed)

                                                    Dim reduction As Double = (1 - CDbl(compressedSize) / originalSize) * 100
                                                    Console.WriteLine($"[OK] {fileName}: {originalSize \ 1024}KB → {compressedSize \ 1024}KB ({reduction:F1}% reduction)")
                                                Catch ex As Exception
                                                    Console.WriteLine($"[ERROR] {fileName}: {ex.Message}")
                                                End Try
                                            End Sub)

        Dim totalReduction As Double = (1 - CDbl(totalCompressedSize) / totalOriginalSize) * 100
        Console.WriteLine(vbCrLf & "Compression complete:")
        Console.WriteLine($"  Files processed: {processed}")
        Console.WriteLine($"  Total original: {totalOriginalSize \ 1024 \ 1024}MB")
        Console.WriteLine($"  Total compressed: {totalCompressedSize \ 1024 \ 1024}MB")
        Console.WriteLine($"  Overall reduction: {totalReduction:F1}%")
    End Sub
End Module

Imports IronPdf
Imports System
Imports System.IO
Imports System.Threading.Tasks
Imports System.Threading

Module Program
    Sub Main()
        Dim inputFolder As String = "originals/"
        Dim outputFolder As String = "compressed/"

        Directory.CreateDirectory(outputFolder)

        Dim pdfFiles As String() = Directory.GetFiles(inputFolder, "*.pdf")
        Console.WriteLine($"Found {pdfFiles.Length} PDFs to compress")

        Dim totalOriginalSize As Long = 0
        Dim totalCompressedSize As Long = 0
        Dim processed As Integer = 0

        Dim options As New ParallelOptions With {
            .MaxDegreeOfParallelism = Environment.ProcessorCount \ 2
        }

        Parallel.ForEach(pdfFiles, options, Sub(pdfFile)
                                                Dim fileName As String = Path.GetFileName(pdfFile)
                                                Dim outputPath As String = Path.Combine(outputFolder, fileName)

                                                Try
                                                    Dim originalSize As Long = New FileInfo(pdfFile).Length
                                                    Interlocked.Add(totalOriginalSize, originalSize)

                                                    Using pdf = PdfDocument.FromFile(pdfFile)
                                                        ' Apply compression with JPEG quality setting (0-100, lower = more compression)
                                                        pdf.CompressAndSaveAs(outputPath, 60)
                                                    End Using

                                                    Dim compressedSize As Long = New FileInfo(outputPath).Length
                                                    Interlocked.Add(totalCompressedSize, compressedSize)
                                                    Interlocked.Increment(processed)

                                                    Dim reduction As Double = (1 - CDbl(compressedSize) / originalSize) * 100
                                                    Console.WriteLine($"[OK] {fileName}: {originalSize \ 1024}KB → {compressedSize \ 1024}KB ({reduction:F1}% reduction)")
                                                Catch ex As Exception
                                                    Console.WriteLine($"[ERROR] {fileName}: {ex.Message}")
                                                End Try
                                            End Sub)

        Dim totalReduction As Double = (1 - CDbl(totalCompressedSize) / totalOriginalSize) * 100
        Console.WriteLine(vbCrLf & "Compression complete:")
        Console.WriteLine($"  Files processed: {processed}")
        Console.WriteLine($"  Total original: {totalOriginalSize \ 1024 \ 1024}MB")
        Console.WriteLine($"  Total compressed: {totalCompressedSize \ 1024 \ 1024}MB")
        Console.WriteLine($"  Overall reduction: {totalReduction:F1}%")
    End Sub
End Module

Imports IronPdf
Imports System
Imports System.IO
Imports System.Threading.Tasks
Imports System.Threading

Module Program
    Sub Main()
        Dim inputFolder As String = "originals/"
        Dim outputFolder As String = "pdfa-archive/"

        Directory.CreateDirectory(outputFolder)

        Dim pdfFiles As String() = Directory.GetFiles(inputFolder, "*.pdf")
        Console.WriteLine($"Found {pdfFiles.Length} PDFs to convert to PDF/A-3b")

        Dim converted As Integer = 0
        Dim failed As Integer = 0

        Dim options As New ParallelOptions With {
            .MaxDegreeOfParallelism = Environment.ProcessorCount \ 2
        }

        Parallel.ForEach(pdfFiles, options, Sub(pdfFile)
                                                Dim fileName As String = Path.GetFileName(pdfFile)
                                                Dim outputPath As String = Path.Combine(outputFolder, fileName)

                                                Try
                                                    Using pdf = PdfDocument.FromFile(pdfFile)
                                                        ' Convert to PDF/A-3b for long-term archival
                                                        pdf.SaveAsPdfA(outputPath, PdfAVersions.PdfA3b)

                                                        Interlocked.Increment(converted)
                                                        Console.WriteLine($"[OK] {fileName} → PDF/A-3b")
                                                    End Using
                                                Catch ex As Exception
                                                    Interlocked.Increment(failed)
                                                    Console.WriteLine($"[ERROR] {fileName}: {ex.Message}")
                                                End Try
                                            End Sub)

        Console.WriteLine($"{vbCrLf}Conversion complete: {converted} succeeded, {failed} failed")
    End Sub

    ' Alternative: Convert to PDF/UA for accessibility compliance
    Sub ConvertToPdfUA(inputFolder As String, outputFolder As String)
        Directory.CreateDirectory(outputFolder)
        Dim files As String() = Directory.GetFiles(inputFolder, "*.pdf")

        Parallel.ForEach(files, Sub(pdfFile)
                                    Dim fileName As String = Path.GetFileName(pdfFile)
                                    Try
                                        Using pdf = PdfDocument.FromFile(pdfFile)
                                            ' PDF/UA requires proper tagging - ensure source is well-structured
                                            pdf.SaveAsPdfUA(Path.Combine(outputFolder, fileName))
                                            Console.WriteLine($"[OK] {fileName} → PDF/UA")
                                        End Using
                                    Catch ex As Exception
                                        Console.WriteLine($"[ERROR] {fileName}: {ex.Message}")
                                    End Try
                                End Sub)
    End Sub
End Module

Imports IronPdf
Imports System
Imports System.IO
Imports System.Threading.Tasks
Imports System.Threading

Module Program
    Sub Main()
        Dim inputFolder As String = "originals/"
        Dim outputFolder As String = "pdfa-archive/"

        Directory.CreateDirectory(outputFolder)

        Dim pdfFiles As String() = Directory.GetFiles(inputFolder, "*.pdf")
        Console.WriteLine($"Found {pdfFiles.Length} PDFs to convert to PDF/A-3b")

        Dim converted As Integer = 0
        Dim failed As Integer = 0

        Dim options As New ParallelOptions With {
            .MaxDegreeOfParallelism = Environment.ProcessorCount \ 2
        }

        Parallel.ForEach(pdfFiles, options, Sub(pdfFile)
                                                Dim fileName As String = Path.GetFileName(pdfFile)
                                                Dim outputPath As String = Path.Combine(outputFolder, fileName)

                                                Try
                                                    Using pdf = PdfDocument.FromFile(pdfFile)
                                                        ' Convert to PDF/A-3b for long-term archival
                                                        pdf.SaveAsPdfA(outputPath, PdfAVersions.PdfA3b)

                                                        Interlocked.Increment(converted)
                                                        Console.WriteLine($"[OK] {fileName} → PDF/A-3b")
                                                    End Using
                                                Catch ex As Exception
                                                    Interlocked.Increment(failed)
                                                    Console.WriteLine($"[ERROR] {fileName}: {ex.Message}")
                                                End Try
                                            End Sub)

        Console.WriteLine($"{vbCrLf}Conversion complete: {converted} succeeded, {failed} failed")
    End Sub

    ' Alternative: Convert to PDF/UA for accessibility compliance
    Sub ConvertToPdfUA(inputFolder As String, outputFolder As String)
        Directory.CreateDirectory(outputFolder)
        Dim files As String() = Directory.GetFiles(inputFolder, "*.pdf")

        Parallel.ForEach(files, Sub(pdfFile)
                                    Dim fileName As String = Path.GetFileName(pdfFile)
                                    Try
                                        Using pdf = PdfDocument.FromFile(pdfFile)
                                            ' PDF/UA requires proper tagging - ensure source is well-structured
                                            pdf.SaveAsPdfUA(Path.Combine(outputFolder, fileName))
                                            Console.WriteLine($"[OK] {fileName} → PDF/UA")
                                        End Using
                                    Catch ex As Exception
                                        Console.WriteLine($"[ERROR] {fileName}: {ex.Message}")
                                    End Try
                                End Sub)
    End Sub
End Module

Imports IronPdf
Imports System
Imports System.IO
Imports System.Threading
Imports System.Collections.Concurrent

Module Program
    Sub Main()
        Dim inputFolder As String = "input/"
        Dim outputFolder As String = "output/"
        Dim errorLogPath As String = "error-log.txt"

        Directory.CreateDirectory(outputFolder)

        Dim htmlFiles As String() = Directory.GetFiles(inputFolder, "*.html")
        Dim renderer As New ChromePdfRenderer()
        Dim errorLog As New ConcurrentBag(Of String)()

        Dim processed As Integer = 0
        Dim failed As Integer = 0
        Dim retried As Integer = 0

        Const maxRetries As Integer = 3

        Dim options As New ParallelOptions With {
            .MaxDegreeOfParallelism = Environment.ProcessorCount \ 2
        }

        Parallel.ForEach(htmlFiles, options, Sub(htmlFile)
            Dim fileName As String = Path.GetFileNameWithoutExtension(htmlFile)
            Dim outputPath As String = Path.Combine(outputFolder, $"{fileName}.pdf")
            Dim attempt As Integer = 0
            Dim success As Boolean = False

            While attempt < maxRetries AndAlso Not success
                attempt += 1
                Try
                    Using pdf = renderer.RenderHtmlFileAsPdf(htmlFile)
                        pdf.SaveAs(outputPath)
                        success = True
                        Interlocked.Increment(processed)

                        If attempt > 1 Then
                            Interlocked.Increment(retried)
                            Console.WriteLine($"[OK] {fileName}.pdf (succeeded on attempt {attempt})")
                        Else
                            Console.WriteLine($"[OK] {fileName}.pdf")
                        End If
                    End Using
                Catch ex As Exception When IsTransientException(ex) AndAlso attempt < maxRetries
                    ' Transient error - wait and retry with exponential backoff
                    Dim delayMs As Integer = CInt(Math.Pow(2, attempt)) * 500
                    Console.WriteLine($"[RETRY] {fileName}: {ex.Message} (attempt {attempt}, waiting {delayMs}ms)")
                    Thread.Sleep(delayMs)
                Catch ex As Exception
                    ' Non-transient error or max retries exceeded
                    Interlocked.Increment(failed)
                    Dim errorMessage As String = $"{DateTime.Now:yyyy-MM-dd HH:mm:ss} | {fileName} | {ex.GetType().Name} | {ex.Message}"
                    errorLog.Add(errorMessage)
                    Console.WriteLine($"[ERROR] {fileName}: {ex.Message}")
                End Try
            End While
        End Sub)

        ' Write error log
        If errorLog.Count > 0 Then
            File.WriteAllLines(errorLogPath, errorLog)
        End If

        Console.WriteLine($"{vbCrLf}Batch complete:")
        Console.WriteLine($"  Processed: {processed}")
        Console.WriteLine($"  Failed: {failed}")
        Console.WriteLine($"  Retried: {retried}")
        If failed > 0 Then
            Console.WriteLine($"  Error log: {errorLogPath}")
        End If
    End Sub

    ' Helper to identify transient exceptions worth retrying
    Function IsTransientException(ex As Exception) As Boolean
        Return TypeOf ex Is IOException OrElse
               TypeOf ex Is OutOfMemoryException OrElse
               ex.Message.Contains("timeout", StringComparison.OrdinalIgnoreCase) OrElse
               ex.Message.Contains("locked", StringComparison.OrdinalIgnoreCase)
    End Function
End Module

Imports IronPdf
Imports System
Imports System.IO
Imports System.Threading
Imports System.Collections.Concurrent

Module Program
    Sub Main()
        Dim inputFolder As String = "input/"
        Dim outputFolder As String = "output/"
        Dim errorLogPath As String = "error-log.txt"

        Directory.CreateDirectory(outputFolder)

        Dim htmlFiles As String() = Directory.GetFiles(inputFolder, "*.html")
        Dim renderer As New ChromePdfRenderer()
        Dim errorLog As New ConcurrentBag(Of String)()

        Dim processed As Integer = 0
        Dim failed As Integer = 0
        Dim retried As Integer = 0

        Const maxRetries As Integer = 3

        Dim options As New ParallelOptions With {
            .MaxDegreeOfParallelism = Environment.ProcessorCount \ 2
        }

        Parallel.ForEach(htmlFiles, options, Sub(htmlFile)
            Dim fileName As String = Path.GetFileNameWithoutExtension(htmlFile)
            Dim outputPath As String = Path.Combine(outputFolder, $"{fileName}.pdf")
            Dim attempt As Integer = 0
            Dim success As Boolean = False

            While attempt < maxRetries AndAlso Not success
                attempt += 1
                Try
                    Using pdf = renderer.RenderHtmlFileAsPdf(htmlFile)
                        pdf.SaveAs(outputPath)
                        success = True
                        Interlocked.Increment(processed)

                        If attempt > 1 Then
                            Interlocked.Increment(retried)
                            Console.WriteLine($"[OK] {fileName}.pdf (succeeded on attempt {attempt})")
                        Else
                            Console.WriteLine($"[OK] {fileName}.pdf")
                        End If
                    End Using
                Catch ex As Exception When IsTransientException(ex) AndAlso attempt < maxRetries
                    ' Transient error - wait and retry with exponential backoff
                    Dim delayMs As Integer = CInt(Math.Pow(2, attempt)) * 500
                    Console.WriteLine($"[RETRY] {fileName}: {ex.Message} (attempt {attempt}, waiting {delayMs}ms)")
                    Thread.Sleep(delayMs)
                Catch ex As Exception
                    ' Non-transient error or max retries exceeded
                    Interlocked.Increment(failed)
                    Dim errorMessage As String = $"{DateTime.Now:yyyy-MM-dd HH:mm:ss} | {fileName} | {ex.GetType().Name} | {ex.Message}"
                    errorLog.Add(errorMessage)
                    Console.WriteLine($"[ERROR] {fileName}: {ex.Message}")
                End Try
            End While
        End Sub)

        ' Write error log
        If errorLog.Count > 0 Then
            File.WriteAllLines(errorLogPath, errorLog)
        End If

        Console.WriteLine($"{vbCrLf}Batch complete:")
        Console.WriteLine($"  Processed: {processed}")
        Console.WriteLine($"  Failed: {failed}")
        Console.WriteLine($"  Retried: {retried}")
        If failed > 0 Then
            Console.WriteLine($"  Error log: {errorLogPath}")
        End If
    End Sub

    ' Helper to identify transient exceptions worth retrying
    Function IsTransientException(ex As Exception) As Boolean
        Return TypeOf ex Is IOException OrElse
               TypeOf ex Is OutOfMemoryException OrElse
               ex.Message.Contains("timeout", StringComparison.OrdinalIgnoreCase) OrElse
               ex.Message.Contains("locked", StringComparison.OrdinalIgnoreCase)
    End Function
End Module

Imports IronPdf
Imports System
Imports System.IO
Imports System.Linq
Imports System.Threading.Tasks
Imports System.Threading
Imports System.Collections.Generic

Module Program
    Sub Main()
        Dim inputFolder As String = "input/"
        Dim outputFolder As String = "output/"
        Dim checkpointPath As String = "checkpoint.txt"
        Dim errorLogPath As String = "errors.txt"

        Directory.CreateDirectory(outputFolder)

        ' Load checkpoint - files already processed successfully
        Dim completedFiles As New HashSet(Of String)()
        If File.Exists(checkpointPath) Then
            completedFiles = New HashSet(Of String)(File.ReadAllLines(checkpointPath))
            Console.WriteLine($"Resuming from checkpoint: {completedFiles.Count} files already processed")
        End If

        ' Get files to process (excluding already completed)
        Dim allFiles As String() = Directory.GetFiles(inputFolder, "*.html")
        Dim filesToProcess As String() = allFiles _
            .Where(Function(f) Not completedFiles.Contains(Path.GetFileName(f))) _
            .ToArray()

        Console.WriteLine($"Files to process: {filesToProcess.Length} (skipping {completedFiles.Count} already done)")

        Dim renderer As New ChromePdfRenderer()
        Dim checkpointLock As New Object()
        Dim processed As Integer = 0
        Dim failed As Integer = 0

        Dim options As New ParallelOptions With {
            .MaxDegreeOfParallelism = Environment.ProcessorCount \ 2
        }

        Parallel.ForEach(filesToProcess, options, Sub(htmlFile)
                                                      Dim fileName As String = Path.GetFileName(htmlFile)
                                                      Dim baseName As String = Path.GetFileNameWithoutExtension(htmlFile)
                                                      Dim outputPath As String = Path.Combine(outputFolder, $"{baseName}.pdf")

                                                      Try
                                                          Using pdf = renderer.RenderHtmlFileAsPdf(htmlFile)
                                                              pdf.SaveAs(outputPath)
                                                          End Using

                                                          ' Record success in checkpoint (thread-safe)
                                                          SyncLock checkpointLock
                                                              File.AppendAllText(checkpointPath, fileName & Environment.NewLine)
                                                          End SyncLock

                                                          Interlocked.Increment(processed)
                                                          Console.WriteLine($"[OK] {baseName}.pdf")
                                                      Catch ex As Exception
                                                          Interlocked.Increment(failed)

                                                          ' Log error for review
                                                          SyncLock checkpointLock
                                                              File.AppendAllText(errorLogPath,
                                                                                  $"{DateTime.Now:yyyy-MM-dd HH:mm:ss} | {fileName} | {ex.Message}{Environment.NewLine}")
                                                          End SyncLock

                                                          Console.WriteLine($"[ERROR] {fileName}: {ex.Message}")
                                                      End Try
                                                  End Sub)

        Console.WriteLine(vbCrLf & "Batch complete:")
        Console.WriteLine($"  Newly processed: {processed}")
        Console.WriteLine($"  Failed: {failed}")
        Console.WriteLine($"  Total completed: {completedFiles.Count + processed}")
        Console.WriteLine($"  Checkpoint saved to: {checkpointPath}")
    End Sub
End Module

Imports IronPdf
Imports System
Imports System.IO
Imports System.Linq
Imports System.Threading.Tasks
Imports System.Threading
Imports System.Collections.Generic

Module Program
    Sub Main()
        Dim inputFolder As String = "input/"
        Dim outputFolder As String = "output/"
        Dim checkpointPath As String = "checkpoint.txt"
        Dim errorLogPath As String = "errors.txt"

        Directory.CreateDirectory(outputFolder)

        ' Load checkpoint - files already processed successfully
        Dim completedFiles As New HashSet(Of String)()
        If File.Exists(checkpointPath) Then
            completedFiles = New HashSet(Of String)(File.ReadAllLines(checkpointPath))
            Console.WriteLine($"Resuming from checkpoint: {completedFiles.Count} files already processed")
        End If

        ' Get files to process (excluding already completed)
        Dim allFiles As String() = Directory.GetFiles(inputFolder, "*.html")
        Dim filesToProcess As String() = allFiles _
            .Where(Function(f) Not completedFiles.Contains(Path.GetFileName(f))) _
            .ToArray()

        Console.WriteLine($"Files to process: {filesToProcess.Length} (skipping {completedFiles.Count} already done)")

        Dim renderer As New ChromePdfRenderer()
        Dim checkpointLock As New Object()
        Dim processed As Integer = 0
        Dim failed As Integer = 0

        Dim options As New ParallelOptions With {
            .MaxDegreeOfParallelism = Environment.ProcessorCount \ 2
        }

        Parallel.ForEach(filesToProcess, options, Sub(htmlFile)
                                                      Dim fileName As String = Path.GetFileName(htmlFile)
                                                      Dim baseName As String = Path.GetFileNameWithoutExtension(htmlFile)
                                                      Dim outputPath As String = Path.Combine(outputFolder, $"{baseName}.pdf")

                                                      Try
                                                          Using pdf = renderer.RenderHtmlFileAsPdf(htmlFile)
                                                              pdf.SaveAs(outputPath)
                                                          End Using

                                                          ' Record success in checkpoint (thread-safe)
                                                          SyncLock checkpointLock
                                                              File.AppendAllText(checkpointPath, fileName & Environment.NewLine)
                                                          End SyncLock

                                                          Interlocked.Increment(processed)
                                                          Console.WriteLine($"[OK] {baseName}.pdf")
                                                      Catch ex As Exception
                                                          Interlocked.Increment(failed)

                                                          ' Log error for review
                                                          SyncLock checkpointLock
                                                              File.AppendAllText(errorLogPath,
                                                                                  $"{DateTime.Now:yyyy-MM-dd HH:mm:ss} | {fileName} | {ex.Message}{Environment.NewLine}")
                                                          End SyncLock

                                                          Console.WriteLine($"[ERROR] {fileName}: {ex.Message}")
                                                      End Try
                                                  End Sub)

        Console.WriteLine(vbCrLf & "Batch complete:")
        Console.WriteLine($"  Newly processed: {processed}")
        Console.WriteLine($"  Failed: {failed}")
        Console.WriteLine($"  Total completed: {completedFiles.Count + processed}")
        Console.WriteLine($"  Checkpoint saved to: {checkpointPath}")
    End Sub
End Module

Imports IronPdf
Imports System
Imports System.IO
Imports System.Threading
Imports System.Collections.Concurrent

Module Program
    Sub Main()
        Dim inputFolder As String = "input/"
        Dim outputFolder As String = "output/"
        Dim validatedFolder As String = "validated/"
        Dim rejectedFolder As String = "rejected/"

        Directory.CreateDirectory(outputFolder)
        Directory.CreateDirectory(validatedFolder)
        Directory.CreateDirectory(rejectedFolder)

        Dim inputFiles As String() = Directory.GetFiles(inputFolder, "*.html")
        Dim renderer As New ChromePdfRenderer()

        Dim preValidationFailed As Integer = 0
        Dim processingFailed As Integer = 0
        Dim postValidationFailed As Integer = 0
        Dim succeeded As Integer = 0

        Dim options As New ParallelOptions With {
            .MaxDegreeOfParallelism = Environment.ProcessorCount \ 2
        }

        Parallel.ForEach(inputFiles, options, Sub(inputFile)
                                                  Dim fileName As String = Path.GetFileNameWithoutExtension(inputFile)
                                                  Dim outputPath As String = Path.Combine(outputFolder, $"{fileName}.pdf")

                                                  ' Pre-validation: Check input file
                                                  If Not PreValidate(inputFile) Then
                                                      Interlocked.Increment(preValidationFailed)
                                                      Console.WriteLine($"[SKIP] {fileName}: Failed pre-validation")
                                                      Return
                                                  End If

                                                  Try
                                                      ' Process
                                                      Using pdf = renderer.RenderHtmlFileAsPdf(inputFile)
                                                          pdf.SaveAs(outputPath)

                                                          ' Post-validation: Check output file
                                                          If PostValidate(outputPath) Then
                                                              ' Move to validated folder
                                                              Dim validatedPath As String = Path.Combine(validatedFolder, $"{fileName}.pdf")
                                                              File.Move(outputPath, validatedPath, overwrite:=True)
                                                              Interlocked.Increment(succeeded)
                                                              Console.WriteLine($"[OK] {fileName}.pdf (validated)")
                                                          Else
                                                              ' Move to rejected folder for manual review
                                                              Dim rejectedPath As String = Path.Combine(rejectedFolder, $"{fileName}.pdf")
                                                              File.Move(outputPath, rejectedPath, overwrite:=True)
                                                              Interlocked.Increment(postValidationFailed)
                                                              Console.WriteLine($"[REJECT] {fileName}.pdf: Failed post-validation")
                                                          End If
                                                      End Using
                                                  Catch ex As Exception
                                                      Interlocked.Increment(processingFailed)
                                                      Console.WriteLine($"[ERROR] {fileName}: {ex.Message}")
                                                  End Try
                                              End Sub)

        Console.WriteLine(vbCrLf & "Validation summary:")
        Console.WriteLine($"  Succeeded: {succeeded}")
        Console.WriteLine($"  Pre-validation failed: {preValidationFailed}")
        Console.WriteLine($"  Processing failed: {processingFailed}")
        Console.WriteLine($"  Post-validation failed: {postValidationFailed}")
    End Sub

    ' Pre-validation: Quick checks on input file
    Function PreValidate(filePath As String) As Boolean
        Try
            Dim fileInfo As New FileInfo(filePath)

            ' Check file exists and is readable
            If Not fileInfo.Exists Then Return False

            ' Check file is not empty
            If fileInfo.Length = 0 Then Return False

            ' Check file is not too large (e.g., 50MB limit)
            If fileInfo.Length > 50 * 1024 * 1024 Then Return False

            ' Quick content check - must be valid HTML
            Dim content As String = File.ReadAllText(filePath)
            If String.IsNullOrWhiteSpace(content) Then Return False
            If Not content.Contains("<html", StringComparison.OrdinalIgnoreCase) AndAlso
               Not content.Contains("<!DOCTYPE", StringComparison.OrdinalIgnoreCase) Then
                Return False
            End If

            Return True
        Catch
            Return False
        End Try
    End Function

    ' Post-validation: Verify output PDF meets requirements
    Function PostValidate(pdfPath As String) As Boolean
        Try
            Using pdf = PdfDocument.FromFile(pdfPath)
                ' Check PDF has at least one page
                If pdf.PageCount < 1 Then Return False

                ' Check file size is reasonable (not just header, not corrupted)
                Dim fileInfo As New FileInfo(pdfPath)
                If fileInfo.Length < 1024 Then Return False

                Return True
            End Using
        Catch
            Return False
        End Try
    End Function
End Module

Imports IronPdf
Imports System
Imports System.IO
Imports System.Threading
Imports System.Collections.Concurrent

Module Program
    Sub Main()
        Dim inputFolder As String = "input/"
        Dim outputFolder As String = "output/"
        Dim validatedFolder As String = "validated/"
        Dim rejectedFolder As String = "rejected/"

        Directory.CreateDirectory(outputFolder)
        Directory.CreateDirectory(validatedFolder)
        Directory.CreateDirectory(rejectedFolder)

        Dim inputFiles As String() = Directory.GetFiles(inputFolder, "*.html")
        Dim renderer As New ChromePdfRenderer()

        Dim preValidationFailed As Integer = 0
        Dim processingFailed As Integer = 0
        Dim postValidationFailed As Integer = 0
        Dim succeeded As Integer = 0

        Dim options As New ParallelOptions With {
            .MaxDegreeOfParallelism = Environment.ProcessorCount \ 2
        }

        Parallel.ForEach(inputFiles, options, Sub(inputFile)
                                                  Dim fileName As String = Path.GetFileNameWithoutExtension(inputFile)
                                                  Dim outputPath As String = Path.Combine(outputFolder, $"{fileName}.pdf")

                                                  ' Pre-validation: Check input file
                                                  If Not PreValidate(inputFile) Then
                                                      Interlocked.Increment(preValidationFailed)
                                                      Console.WriteLine($"[SKIP] {fileName}: Failed pre-validation")
                                                      Return
                                                  End If

                                                  Try
                                                      ' Process
                                                      Using pdf = renderer.RenderHtmlFileAsPdf(inputFile)
                                                          pdf.SaveAs(outputPath)

                                                          ' Post-validation: Check output file
                                                          If PostValidate(outputPath) Then
                                                              ' Move to validated folder
                                                              Dim validatedPath As String = Path.Combine(validatedFolder, $"{fileName}.pdf")
                                                              File.Move(outputPath, validatedPath, overwrite:=True)
                                                              Interlocked.Increment(succeeded)
                                                              Console.WriteLine($"[OK] {fileName}.pdf (validated)")
                                                          Else
                                                              ' Move to rejected folder for manual review
                                                              Dim rejectedPath As String = Path.Combine(rejectedFolder, $"{fileName}.pdf")
                                                              File.Move(outputPath, rejectedPath, overwrite:=True)
                                                              Interlocked.Increment(postValidationFailed)
                                                              Console.WriteLine($"[REJECT] {fileName}.pdf: Failed post-validation")
                                                          End If
                                                      End Using
                                                  Catch ex As Exception
                                                      Interlocked.Increment(processingFailed)
                                                      Console.WriteLine($"[ERROR] {fileName}: {ex.Message}")
                                                  End Try
                                              End Sub)

        Console.WriteLine(vbCrLf & "Validation summary:")
        Console.WriteLine($"  Succeeded: {succeeded}")
        Console.WriteLine($"  Pre-validation failed: {preValidationFailed}")
        Console.WriteLine($"  Processing failed: {processingFailed}")
        Console.WriteLine($"  Post-validation failed: {postValidationFailed}")
    End Sub

    ' Pre-validation: Quick checks on input file
    Function PreValidate(filePath As String) As Boolean
        Try
            Dim fileInfo As New FileInfo(filePath)

            ' Check file exists and is readable
            If Not fileInfo.Exists Then Return False

            ' Check file is not empty
            If fileInfo.Length = 0 Then Return False

            ' Check file is not too large (e.g., 50MB limit)
            If fileInfo.Length > 50 * 1024 * 1024 Then Return False

            ' Quick content check - must be valid HTML
            Dim content As String = File.ReadAllText(filePath)
            If String.IsNullOrWhiteSpace(content) Then Return False
            If Not content.Contains("<html", StringComparison.OrdinalIgnoreCase) AndAlso
               Not content.Contains("<!DOCTYPE", StringComparison.OrdinalIgnoreCase) Then
                Return False
            End If

            Return True
        Catch
            Return False
        End Try
    End Function

    ' Post-validation: Verify output PDF meets requirements
    Function PostValidate(pdfPath As String) As Boolean
        Try
            Using pdf = PdfDocument.FromFile(pdfPath)
                ' Check PDF has at least one page
                If pdf.PageCount < 1 Then Return False

                ' Check file size is reasonable (not just header, not corrupted)
                Dim fileInfo As New FileInfo(pdfPath)
                If fileInfo.Length < 1024 Then Return False

                Return True
            End Using
        Catch
            Return False
        End Try
    End Function
End Module

Imports IronPdf
Imports System
Imports System.IO
Imports System.Threading.Tasks
Imports System.Threading
Imports System.Diagnostics

Module Program
    Sub Main()
        Dim inputFolder As String = "input/"
        Dim outputFolder As String = "output/"

        Directory.CreateDirectory(outputFolder)

        Dim htmlFiles As String() = Directory.GetFiles(inputFolder, "*.html")
        Dim renderer As New ChromePdfRenderer()

        Console.WriteLine($"Processing {htmlFiles.Length} files with {Environment.ProcessorCount} CPU cores")

        Dim processed As Integer = 0
        Dim stopwatch As Stopwatch = Stopwatch.StartNew()

        ' Configure parallelism based on system resources
        ' Rule of thumb: ProcessorCount / 2 for memory-intensive operations
        Dim options As New ParallelOptions With {
            .MaxDegreeOfParallelism = Math.Max(1, Environment.ProcessorCount \ 2)
        }

        Console.WriteLine($"Max parallelism: {options.MaxDegreeOfParallelism}")

        ' Use Parallel.ForEach for CPU-bound batch operations
        Parallel.ForEach(htmlFiles, options, Sub(htmlFile)
                                                 Dim fileName As String = Path.GetFileNameWithoutExtension(htmlFile)
                                                 Dim outputPath As String = Path.Combine(outputFolder, $"{fileName}.pdf")

                                                 Try
                                                     ' Render HTML to PDF
                                                     Using pdf = renderer.RenderHtmlFileAsPdf(htmlFile)
                                                         pdf.SaveAs(outputPath)
                                                     End Using

                                                     Dim current As Integer = Interlocked.Increment(processed)

                                                     ' Progress reporting every 10 files
                                                     If current Mod 10 = 0 Then
                                                         Dim elapsed As Double = stopwatch.Elapsed.TotalSeconds
                                                         Dim rate As Double = current / elapsed
                                                         Dim remaining As Double = (htmlFiles.Length - current) / rate
                                                         Console.WriteLine($"Progress: {current}/{htmlFiles.Length} ({rate:F1} files/sec, ~{remaining:F0}s remaining)")
                                                     End If
                                                 Catch ex As Exception
                                                     Console.WriteLine($"[ERROR] {fileName}: {ex.Message}")
                                                 End Try
                                             End Sub)

        stopwatch.Stop()
        Dim totalRate As Double = processed / stopwatch.Elapsed.TotalSeconds

        Console.WriteLine(vbCrLf & "Complete:")
        Console.WriteLine($"  Files processed: {processed}/{htmlFiles.Length}")
        Console.WriteLine($"  Total time: {stopwatch.Elapsed.TotalSeconds:F1}s")
        Console.WriteLine($"  Average rate: {totalRate:F1} files/sec")
        Console.WriteLine($"  Time per file: {stopwatch.Elapsed.TotalMilliseconds / processed:F0}ms")

        ' Memory monitoring helper (call between chunks for large batches)
        CheckMemoryPressure()
    End Sub

    Sub CheckMemoryPressure()
        Const memoryThreshold As Long = 4L * 1024 * 1024 * 1024 ' 4 GB
        Dim currentMemory As Long = GC.GetTotalMemory(forceFullCollection:=False)

        If currentMemory > memoryThreshold Then
            Console.WriteLine($"Memory pressure detected ({currentMemory \ 1024 \ 1024}MB), forcing GC...")
            GC.Collect()
            GC.WaitForPendingFinalizers()
            GC.Collect()
        End If
    End Sub
End Module