在C#中使用IronOCR保存可搜尋的PDF

Imports IronOcr

' Create the OCR engine: defaults to English with balanced speed and accuracy
Dim ocrTesseract As New IronTesseract()

' Required: without this flag the text overlay layer is not built, and SaveAsSearchablePdf produces a plain image PDF
ocrTesseract.Configuration.RenderSearchablePdf = True

' Wrap the TIFF in OcrImageInput: handles DPI detection and page layout automatically
Using imageInput As New OcrImageInput("Potter.tiff")
    ' Run OCR; returns a result containing the recognized text and spatial layout data
    Dim ocrResult As OcrResult = ocrTesseract.Read(imageInput)

    ' Write the output: the original scanned image is preserved with an invisible text layer on top
    ocrResult.SaveAsSearchablePdf("searchablePdf.pdf")
End Using

Imports IronOcr

' Create the OCR engine: defaults to English with balanced speed and accuracy
Dim ocrTesseract As New IronTesseract()

' Required: without this flag the text overlay layer is not built, and SaveAsSearchablePdf produces a plain image PDF
ocrTesseract.Configuration.RenderSearchablePdf = True

' Wrap the TIFF in OcrImageInput: handles DPI detection and page layout automatically
Using imageInput As New OcrImageInput("Potter.tiff")
    ' Run OCR; returns a result containing the recognized text and spatial layout data
    Dim ocrResult As OcrResult = ocrTesseract.Read(imageInput)

    ' Write the output: the original scanned image is preserved with an invisible text layer on top
    ocrResult.SaveAsSearchablePdf("searchablePdf.pdf")
End Using

Imports IronOcr

' Create the OCR engine. RenderSearchablePdf is false by default; no need to set it when using OcrPdfInput directly
Dim ocrTesseract As New IronTesseract()

' Load pages 1–10 (indices 0–9) only; PageIndices avoids loading and OCR-ing the full document unnecessarily
Using pdfInput As New OcrPdfInput("multi-page-scan.pdf", PageIndices:=Enumerable.Range(0, 10))
    ' Run OCR across all selected pages in order
    Dim result As OcrResult = ocrTesseract.Read(pdfInput)

    ' Write the searchable PDF; true = apply the input's image filters to the embedded page images in the output
    result.SaveAsSearchablePdf("searchable-multi-page.pdf", True)
End Using

Imports IronOcr

' Create the OCR engine. RenderSearchablePdf is false by default; no need to set it when using OcrPdfInput directly
Dim ocrTesseract As New IronTesseract()

' Load pages 1–10 (indices 0–9) only; PageIndices avoids loading and OCR-ing the full document unnecessarily
Using pdfInput As New OcrPdfInput("multi-page-scan.pdf", PageIndices:=Enumerable.Range(0, 10))
    ' Run OCR across all selected pages in order
    Dim result As OcrResult = ocrTesseract.Read(pdfInput)

    ' Write the searchable PDF; true = apply the input's image filters to the embedded page images in the output
    result.SaveAsSearchablePdf("searchable-multi-page.pdf", True)
End Using

Imports IronOcr

' Create OCR engine: filters are applied at the OcrInput level, so no configuration changes are needed here
Dim ocr As New IronTesseract()
Dim ocrInput As New OcrInput()

' Load the scanned PDF as the OCR source
ocrInput.LoadPdf("invoice.pdf")

' Convert to grayscale: removes color noise that can reduce OCR accuracy on color-printed documents
ocrInput.ToGrayScale()
' Run OCR on the preprocessed input
Dim result As OcrResult = ocr.Read(ocrInput)

' Write the searchable PDF; True = embed the grayscale-filtered image rather than the original color scan
result.SaveAsSearchablePdf("outputGrayscale.pdf", True)

Imports IronOcr

' Create OCR engine: filters are applied at the OcrInput level, so no configuration changes are needed here
Dim ocr As New IronTesseract()
Dim ocrInput As New OcrInput()

' Load the scanned PDF as the OCR source
ocrInput.LoadPdf("invoice.pdf")

' Convert to grayscale: removes color noise that can reduce OCR accuracy on color-printed documents
ocrInput.ToGrayScale()
' Run OCR on the preprocessed input
Dim result As OcrResult = ocr.Read(ocrInput)

' Write the searchable PDF; True = embed the grayscale-filtered image rather than the original color scan
result.SaveAsSearchablePdf("outputGrayscale.pdf", True)

result.SaveAsSearchablePdf("output.pdf", False, "Fonts/LiberationSerif-Regular.ttf")

result.SaveAsSearchablePdf("output.pdf", False, "Fonts/LiberationSerif-Regular.ttf")

result.SaveAsSearchablePdf("output.pdf", False, "Fonts/LiberationSerif-Regular.ttf", "MyFont")

result.SaveAsSearchablePdf("output.pdf", False, "Fonts/LiberationSerif-Regular.ttf", "MyFont")

' Return as a byte array: suited for storing in a database or sending in an HTTP response body
Dim pdfByte As Byte() = ocrResult.SaveAsSearchablePdfBytes()

' Return as a stream: suited for uploading to cloud storage or piping to another I/O operation without buffering the full file
Dim pdfStream As Stream = ocrResult.SaveAsSearchablePdfStream()

' Return as a byte array: suited for storing in a database or sending in an HTTP response body
Dim pdfByte As Byte() = ocrResult.SaveAsSearchablePdfBytes()

' Return as a stream: suited for uploading to cloud storage or piping to another I/O operation without buffering the full file
Dim pdfStream As Stream = ocrResult.SaveAsSearchablePdfStream()

Imports IronOcr
Imports System.IO

Public Class SearchablePdfExporter
    Public Async Function ProcessAndUploadPdf(inputPath As String) As Task
        Dim ocr As New IronTesseract With {
            .Configuration = { .RenderSearchablePdf = True }
        }

        ' Process the input
        Using input As New OcrImageInput(inputPath)
            Dim result = ocr.Read(input)

            ' Option 1: Save to database as byte array
            Dim pdfBytes As Byte() = result.SaveAsSearchablePdfBytes()
            ' Store pdfBytes in database BLOB field

            ' Option 2: Upload to cloud storage using stream
            Using pdfStream As Stream = result.SaveAsSearchablePdfStream()
                ' Upload stream to Azure Blob Storage, AWS S3, etc.
                Await UploadToCloudStorage(pdfStream, "searchable-output.pdf")
            End Using

            ' Option 3: Return as web response
            ' Return File(pdfBytes, "application/pdf", "searchable.pdf")
        End Using
    End Function

    Private Async Function UploadToCloudStorage(stream As Stream, fileName As String) As Task
        ' Cloud upload implementation
    End Function
End Class

Imports IronOcr
Imports System.IO

Public Class SearchablePdfExporter
    Public Async Function ProcessAndUploadPdf(inputPath As String) As Task
        Dim ocr As New IronTesseract With {
            .Configuration = { .RenderSearchablePdf = True }
        }

        ' Process the input
        Using input As New OcrImageInput(inputPath)
            Dim result = ocr.Read(input)

            ' Option 1: Save to database as byte array
            Dim pdfBytes As Byte() = result.SaveAsSearchablePdfBytes()
            ' Store pdfBytes in database BLOB field

            ' Option 2: Upload to cloud storage using stream
            Using pdfStream As Stream = result.SaveAsSearchablePdfStream()
                ' Upload stream to Azure Blob Storage, AWS S3, etc.
                Await UploadToCloudStorage(pdfStream, "searchable-output.pdf")
            End Using

            ' Option 3: Return as web response
            ' Return File(pdfBytes, "application/pdf", "searchable.pdf")
        End Using
    End Function

    Private Async Function UploadToCloudStorage(stream As Stream, fileName As String) As Task
        ' Cloud upload implementation
    End Function
End Class

Imports IronOcr
Imports System.Threading.Tasks
Imports System.Collections.Concurrent

Public Class BatchPdfProcessor
    Private ReadOnly _ocr As IronTesseract
    
    Public Sub New()
        _ocr = New IronTesseract With {
            .Configuration = {
                .RenderSearchablePdf = True,
                ' Configure for optimal performance
                .Language = OcrLanguage.English
            }
        }
    End Sub
    
    Public Async Function ProcessBatchAsync(filePaths As String()) As Task
        Dim results As New ConcurrentBag(Of (source As String, output As String))()
        
        Await Task.Run(Sub()
            Parallel.ForEach(filePaths, 
                Sub(filePath)
                    Using input As New OcrImageInput(filePath)
                        Dim result = _ocr.Read(input)
                        
                        Dim outputPath As String = Path.ChangeExtension(filePath, ".searchable.pdf")
                        result.SaveAsSearchablePdf(outputPath)
                        
                        results.Add((filePath, outputPath))
                    End Using
                End Sub)
        End Function)
        
        Console.WriteLine($"Processed {results.Count} files")
    End Function
End Class

Imports IronOcr
Imports System.Threading.Tasks
Imports System.Collections.Concurrent

Public Class BatchPdfProcessor
    Private ReadOnly _ocr As IronTesseract
    
    Public Sub New()
        _ocr = New IronTesseract With {
            .Configuration = {
                .RenderSearchablePdf = True,
                ' Configure for optimal performance
                .Language = OcrLanguage.English
            }
        }
    End Sub
    
    Public Async Function ProcessBatchAsync(filePaths As String()) As Task
        Dim results As New ConcurrentBag(Of (source As String, output As String))()
        
        Await Task.Run(Sub()
            Parallel.ForEach(filePaths, 
                Sub(filePath)
                    Using input As New OcrImageInput(filePath)
                        Dim result = _ocr.Read(input)
                        
                        Dim outputPath As String = Path.ChangeExtension(filePath, ".searchable.pdf")
                        result.SaveAsSearchablePdf(outputPath)
                        
                        results.Add((filePath, outputPath))
                    End Using
                End Sub)
        End Function)
        
        Console.WriteLine($"Processed {results.Count} files")
    End Function
End Class

Imports IronOcr

Dim advancedOcr As New IronTesseract With {
    .Configuration = New TesseractConfiguration With {
        .RenderSearchablePdf = True,
        .TesseractVariables = New Dictionary(Of String, Object) From {
            {"preserve_interword_spaces", 1},
            {"tessedit_char_whitelist", "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"}
        },
        .PageSegmentationMode = TesseractPageSegmentationMode.SingleColumn
    },
    .Language = OcrLanguage.EnglishBest
}

Imports IronOcr

Dim advancedOcr As New IronTesseract With {
    .Configuration = New TesseractConfiguration With {
        .RenderSearchablePdf = True,
        .TesseractVariables = New Dictionary(Of String, Object) From {
            {"preserve_interword_spaces", 1},
            {"tessedit_char_whitelist", "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"}
        },
        .PageSegmentationMode = TesseractPageSegmentationMode.SingleColumn
    },
    .Language = OcrLanguage.EnglishBest
}