OCR de TIFFs de más de 2 GB con LibTiff.NET

dotnet add package BitMiracle.LibTiff.NET

/// <summary>
/// Splits a multi-page TIFF into single-page TIFF byte streams without ever
/// holding the whole file in memory. Each page is copied at the raw
/// (still-encoded) strip/tile level, so pixel data and compression are
/// preserved exactly - there is no decode/re-encode step.
///
/// This is the chunking step only. It produces sub-2 GB single-page byte
/// arrays; feeding them to IronOCR (which is where the AnyBitmap 2 GB
/// single-buffer limit lives) is the consumer's job - see TiffOcrExample.
/// </summary>
public static class TiffPageSplitter
{
    // Tags that describe how a page's raw strip/tile data is encoded.
    // With a raw copy nothing is re-encoded, so every one of these must be
    // carried over verbatim or the copied bytes become uninterpretable.
    // Extend this list if your TIFFs carry tags not covered here
    // (e.g. ICC profiles, EXTRASAMPLES for alpha channels).
    private static readonly TiffTag[] ScalarIntTags =
    {
        TiffTag.IMAGEWIDTH,
        TiffTag.IMAGELENGTH,
        TiffTag.BITSPERSAMPLE,
        TiffTag.SAMPLESPERPIXEL,
        TiffTag.COMPRESSION,
        TiffTag.PHOTOMETRIC,
        TiffTag.FILLORDER,
        TiffTag.PLANARCONFIG,
        TiffTag.ORIENTATION,
        TiffTag.RESOLUTIONUNIT,
        TiffTag.PREDICTOR,      // required for LZW / Deflate raw copies
        TiffTag.SAMPLEFORMAT,
        TiffTag.T4OPTIONS,      // CCITT Group 3
        TiffTag.T6OPTIONS,      // CCITT Group 4
        TiffTag.SUBFILETYPE,
    };

    private static readonly TiffTag[] ScalarDoubleTags =
    {
        TiffTag.XRESOLUTION,    // DPI directly affects OCR accuracy
        TiffTag.YRESOLUTION,
    };

    /// <summary>
    /// Lazily yields each page of <paramref name="inputPath"/> as a standalone
    /// single-page TIFF. The source file stays open for the lifetime of the
    /// enumeration and only one page is materialised at a time, so peak memory
    /// is roughly one page rather than the whole file.
    /// </summary>
    public static IEnumerable<byte[]> SplitTiffToPages(string inputPath)
    {
        using (Tiff input = Tiff.Open(inputPath, "r"))
        {
            if (input == null)
                throw new InvalidOperationException($"Could not open TIFF: {inputPath}");

            int pageCount = input.NumberOfDirectories();
            for (int page = 0; page < pageCount; page++)
            {
                input.SetDirectory((short)page);
                yield return ExtractCurrentPage(input);
            }
        }
    }

    private static byte[] ExtractCurrentPage(Tiff input)
    {
        using (var ms = new MemoryStream())
        {
            // Default TiffStream operates on the MemoryStream passed as clientData.
            using (Tiff output = Tiff.ClientOpen("InMemory", "w", ms, new TiffStream()))
            {
                if (output == null)
                    throw new InvalidOperationException("Could not create in-memory TIFF.");

                CopyTags(input, output);

                if (input.IsTiled())
                    CopyRawTiles(input, output);
                else
                    CopyRawStrips(input, output);

                output.WriteDirectory();
            }

            return ms.ToArray();
        }
    }

    private static void CopyTags(Tiff input, Tiff output)
    {
        foreach (TiffTag tag in ScalarIntTags)
        {
            FieldValue[] v = input.GetField(tag);
            if (v != null && v.Length > 0)
                output.SetField(tag, v[0].ToInt());
        }
        foreach (TiffTag tag in ScalarDoubleTags)
        {
            FieldValue[] v = input.GetField(tag);
            if (v != null && v.Length > 0)
                output.SetField(tag, v[0].ToDouble());
        }
        // Strip vs tile layout must match the raw data exactly, otherwise the
        // raw bytes won't line up with the declared boundaries.
        if (input.IsTiled())
        {
            output.SetField(TiffTag.TILEWIDTH, input.GetField(TiffTag.TILEWIDTH)[0].ToInt());
            output.SetField(TiffTag.TILELENGTH, input.GetField(TiffTag.TILELENGTH)[0].ToInt());
        }
        else
        {
            FieldValue[] rps = input.GetField(TiffTag.ROWSPERSTRIP);
            if (rps != null && rps.Length > 0)
                output.SetField(TiffTag.ROWSPERSTRIP, rps[0].ToInt());
        }

        // Palette images: the colour map is required to interpret pixel indices.
        FieldValue[] cmap = input.GetField(TiffTag.COLORMAP);
        if (cmap != null && cmap.Length >= 3)
            output.SetField(TiffTag.COLORMAP,
                cmap[0].ToShortArray(), cmap[1].ToShortArray(), cmap[2].ToShortArray());
    }

    private static void CopyRawStrips(Tiff input, Tiff output)
    {
        int stripCount = input.NumberOfStrips();
        int[] byteCounts = input.GetField(TiffTag.STRIPBYTECOUNTS)[0].ToIntArray();
        for (int strip = 0; strip < stripCount; strip++)
        {
            byte[] buffer = new byte[byteCounts[strip]];
            int read = input.ReadRawStrip(strip, buffer, 0, buffer.Length);
            output.WriteRawStrip(strip, buffer, read);
        }
    }

    private static void CopyRawTiles(Tiff input, Tiff output)
    {
        int tileCount = input.NumberOfTiles();
        int[] byteCounts = input.GetField(TiffTag.TILEBYTECOUNTS)[0].ToIntArray();
        for (int tile = 0; tile < tileCount; tile++)
        {
            byte[] buffer = new byte[byteCounts[tile]];
            int read = input.ReadRawTile(tile, buffer, 0, buffer.Length);
            output.WriteRawTile(tile, buffer, read);
        }
    }

    /// <summary>
    /// Lazily yields multi-page TIFF chunks (the equivalent of the old
    /// Magick.NET 100-pages-per-chunk approach). A new chunk is started when
    /// adding the next page would push the chunk past
    /// <paramref name="maxChunkBytes"/>, or when <paramref name="maxPagesPerChunk"/>
    /// is reached - whichever comes first.
    ///
    /// Size is the real guard: page count alone can exceed the 2 GB AnyBitmap
    /// limit on large pages. The byte total here is the encoded (compressed)
    /// size, which is a cheap proxy - validate the cap against your actual
    /// pages, since decoded size can be much larger than encoded.
    /// </summary>
    public static IEnumerable<byte[]> SplitTiffToChunks(
        string inputPath,
        int maxPagesPerChunk = 100,
        long maxChunkBytes = 1_500_000_000L)
    {
        using (Tiff input = Tiff.Open(inputPath, "r"))
        {
            if (input == null)
                throw new InvalidOperationException($"Could not open TIFF: {inputPath}");
            int pageCount = input.NumberOfDirectories();
            int page = 0;
            while (page < pageCount)
            {
                using (var ms = new MemoryStream())
                {
                    using (Tiff output = Tiff.ClientOpen("InMemory", "w", ms, new TiffStream()))
                    {
                        if (output == null)
                            throw new InvalidOperationException("Could not create in-memory TIFF.");

                        int pagesInChunk = 0;
                        long chunkBytes = 0;

                        while (page < pageCount && pagesInChunk < maxPagesPerChunk)
                        {
                            input.SetDirectory((short)page);
                            long pageBytes = RawPageByteSize(input);
                            // Stop before exceeding the cap, but always allow at
                            // least one page so a single large page still goes through.
                            if (pagesInChunk > 0 && chunkBytes + pageBytes > maxChunkBytes)
                                break;
                            CopyTags(input, output);
                            if (input.IsTiled())
                                CopyRawTiles(input, output);
                            else
                                CopyRawStrips(input, output);

                            output.WriteDirectory(); // finalise this page as one directory in the chunk
                            chunkBytes += pageBytes;
                            pagesInChunk++;
                            page++;
                        }
                    }

                    yield return ms.ToArray();
                }
            }
        }
    }

    private static long RawPageByteSize(Tiff page)
    {
        TiffTag tag = page.IsTiled() ? TiffTag.TILEBYTECOUNTS : TiffTag.STRIPBYTECOUNTS;
        int[] counts = page.GetField(tag)[0].ToIntArray();
        long total = 0;
        foreach (int c in counts)
            total += c;
        return total;
    }
}

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

''' <summary>
''' Splits a multi-page TIFF into single-page TIFF byte streams without ever
''' holding the whole file in memory. Each page is copied at the raw
''' (still-encoded) strip/tile level, so pixel data and compression are
''' preserved exactly - there is no decode/re-encode step.
'''
''' This is the chunking step only. It produces sub-2 GB single-page byte
''' arrays; feeding them to IronOCR (which is where the AnyBitmap 2 GB
''' single-buffer limit lives) is the consumer's job - see TiffOcrExample.
''' </summary>
Public NotInheritable Class TiffPageSplitter

    ' Tags that describe how a page's raw strip/tile data is encoded.
    ' With a raw copy nothing is re-encoded, so every one of these must be
    ' carried over verbatim or the copied bytes become uninterpretable.
    ' Extend this list if your TIFFs carry tags not covered here
    ' (e.g. ICC profiles, EXTRASAMPLES for alpha channels).
    Private Shared ReadOnly ScalarIntTags As TiffTag() = {
        TiffTag.IMAGEWIDTH,
        TiffTag.IMAGELENGTH,
        TiffTag.BITSPERSAMPLE,
        TiffTag.SAMPLESPERPIXEL,
        TiffTag.COMPRESSION,
        TiffTag.PHOTOMETRIC,
        TiffTag.FILLORDER,
        TiffTag.PLANARCONFIG,
        TiffTag.ORIENTATION,
        TiffTag.RESOLUTIONUNIT,
        TiffTag.PREDICTOR,      ' required for LZW / Deflate raw copies
        TiffTag.SAMPLEFORMAT,
        TiffTag.T4OPTIONS,      ' CCITT Group 3
        TiffTag.T6OPTIONS,      ' CCITT Group 4
        TiffTag.SUBFILETYPE
    }

    Private Shared ReadOnly ScalarDoubleTags As TiffTag() = {
        TiffTag.XRESOLUTION,    ' DPI directly affects OCR accuracy
        TiffTag.YRESOLUTION
    }

    ''' <summary>
    ''' Lazily yields each page of <paramref name="inputPath"/> as a standalone
    ''' single-page TIFF. The source file stays open for the lifetime of the
    ''' enumeration and only one page is materialised at a time, so peak memory
    ''' is roughly one page rather than the whole file.
    ''' </summary>
    Public Shared Iterator Function SplitTiffToPages(inputPath As String) As IEnumerable(Of Byte())
        Using input As Tiff = Tiff.Open(inputPath, "r")
            If input Is Nothing Then
                Throw New InvalidOperationException($"Could not open TIFF: {inputPath}")
            End If

            Dim pageCount As Integer = input.NumberOfDirectories()
            For page As Integer = 0 To pageCount - 1
                input.SetDirectory(CShort(page))
                Yield ExtractCurrentPage(input)
            Next
        End Using
    End Function

    Private Shared Function ExtractCurrentPage(input As Tiff) As Byte()
        Using ms As New MemoryStream()
            ' Default TiffStream operates on the MemoryStream passed as clientData.
            Using output As Tiff = Tiff.ClientOpen("InMemory", "w", ms, New TiffStream())
                If output Is Nothing Then
                    Throw New InvalidOperationException("Could not create in-memory TIFF.")
                End If

                CopyTags(input, output)

                If input.IsTiled() Then
                    CopyRawTiles(input, output)
                Else
                    CopyRawStrips(input, output)
                End If

                output.WriteDirectory()
            End Using

            Return ms.ToArray()
        End Using
    End Function

    Private Shared Sub CopyTags(input As Tiff, output As Tiff)
        For Each tag As TiffTag In ScalarIntTags
            Dim v As FieldValue() = input.GetField(tag)
            If v IsNot Nothing AndAlso v.Length > 0 Then
                output.SetField(tag, v(0).ToInt())
            End If
        Next
        For Each tag As TiffTag In ScalarDoubleTags
            Dim v As FieldValue() = input.GetField(tag)
            If v IsNot Nothing AndAlso v.Length > 0 Then
                output.SetField(tag, v(0).ToDouble())
            End If
        Next
        ' Strip vs tile layout must match the raw data exactly, otherwise the
        ' raw bytes won't line up with the declared boundaries.
        If input.IsTiled() Then
            output.SetField(TiffTag.TILEWIDTH, input.GetField(TiffTag.TILEWIDTH)(0).ToInt())
            output.SetField(TiffTag.TILELENGTH, input.GetField(TiffTag.TILELENGTH)(0).ToInt())
        Else
            Dim rps As FieldValue() = input.GetField(TiffTag.ROWSPERSTRIP)
            If rps IsNot Nothing AndAlso rps.Length > 0 Then
                output.SetField(TiffTag.ROWSPERSTRIP, rps(0).ToInt())
            End If
        End If

        ' Palette images: the colour map is required to interpret pixel indices.
        Dim cmap As FieldValue() = input.GetField(TiffTag.COLORMAP)
        If cmap IsNot Nothing AndAlso cmap.Length >= 3 Then
            output.SetField(TiffTag.COLORMAP,
                cmap(0).ToShortArray(), cmap(1).ToShortArray(), cmap(2).ToShortArray())
        End If
    End Sub

    Private Shared Sub CopyRawStrips(input As Tiff, output As Tiff)
        Dim stripCount As Integer = input.NumberOfStrips()
        Dim byteCounts As Integer() = input.GetField(TiffTag.STRIPBYTECOUNTS)(0).ToIntArray()
        For strip As Integer = 0 To stripCount - 1
            Dim buffer As Byte() = New Byte(byteCounts(strip) - 1) {}
            Dim read As Integer = input.ReadRawStrip(strip, buffer, 0, buffer.Length)
            output.WriteRawStrip(strip, buffer, read)
        Next
    End Sub

    Private Shared Sub CopyRawTiles(input As Tiff, output As Tiff)
        Dim tileCount As Integer = input.NumberOfTiles()
        Dim byteCounts As Integer() = input.GetField(TiffTag.TILEBYTECOUNTS)(0).ToIntArray()
        For tile As Integer = 0 To tileCount - 1
            Dim buffer As Byte() = New Byte(byteCounts(tile) - 1) {}
            Dim read As Integer = input.ReadRawTile(tile, buffer, 0, buffer.Length)
            output.WriteRawTile(tile, buffer, read)
        Next
    End Sub

    ''' <summary>
    ''' Lazily yields multi-page TIFF chunks (the equivalent of the old
    ''' Magick.NET 100-pages-per-chunk approach). A new chunk is started when
    ''' adding the next page would push the chunk past
    ''' <paramref name="maxChunkBytes"/>, or when <paramref name="maxPagesPerChunk"/>
    ''' is reached - whichever comes first.
    '''
    ''' Size is the real guard: page count alone can exceed the 2 GB AnyBitmap
    ''' limit on large pages. The byte total here is the encoded (compressed)
    ''' size, which is a cheap proxy - validate the cap against your actual
    ''' pages, since decoded size can be much larger than encoded.
    ''' </summary>
    Public Shared Iterator Function SplitTiffToChunks(
        inputPath As String,
        Optional maxPagesPerChunk As Integer = 100,
        Optional maxChunkBytes As Long = 1500000000L) As IEnumerable(Of Byte())
        Using input As Tiff = Tiff.Open(inputPath, "r")
            If input Is Nothing Then
                Throw New InvalidOperationException($"Could not open TIFF: {inputPath}")
            End If
            Dim pageCount As Integer = input.NumberOfDirectories()
            Dim page As Integer = 0
            While page < pageCount
                Using ms As New MemoryStream()
                    Using output As Tiff = Tiff.ClientOpen("InMemory", "w", ms, New TiffStream())
                        If output Is Nothing Then
                            Throw New InvalidOperationException("Could not create in-memory TIFF.")
                        End If

                        Dim pagesInChunk As Integer = 0
                        Dim chunkBytes As Long = 0

                        While page < pageCount AndAlso pagesInChunk < maxPagesPerChunk
                            input.SetDirectory(CShort(page))
                            Dim pageBytes As Long = RawPageByteSize(input)
                            ' Stop before exceeding the cap, but always allow at
                            ' least one page so a single large page still goes through.
                            If pagesInChunk > 0 AndAlso chunkBytes + pageBytes > maxChunkBytes Then
                                Exit While
                            End If
                            CopyTags(input, output)
                            If input.IsTiled() Then
                                CopyRawTiles(input, output)
                            Else
                                CopyRawStrips(input, output)
                            End If

                            output.WriteDirectory() ' finalise this page as one directory in the chunk
                            chunkBytes += pageBytes
                            pagesInChunk += 1
                            page += 1
                        End While
                    End Using

                    Yield ms.ToArray()
                End Using
            End While
        End Using
    End Function

    Private Shared Function RawPageByteSize(page As Tiff) As Long
        Dim tag As TiffTag = If(page.IsTiled(), TiffTag.TILEBYTECOUNTS, TiffTag.STRIPBYTECOUNTS)
        Dim counts As Integer() = page.GetField(tag)(0).ToIntArray()
        Dim total As Long = 0
        For Each c As Integer In counts
            total += c
        Next
        Return total
    End Function
End Class

var inputPath = "2gb_benchmark1200.tiff";
var ocr = new IronTesseract();
int chunk = 0;
foreach (byte[] chunkBytes in TiffPageSplitter.SplitTiffToChunks(inputPath, maxPagesPerChunk: 100))
{
    using (var ocrInput = new OcrInput())
    {
        ocrInput.LoadImage(chunkBytes); // loads every page in the chunk
        var result = ocr.Read(ocrInput);
        Console.WriteLine($"Chunk {chunk}: {result.Text?.Length ?? 0} chars");
    }
    chunk++;
}

Imports IronOcr

Dim inputPath As String = "2gb_benchmark1200.tiff"
Dim ocr As New IronTesseract()
Dim chunk As Integer = 0

For Each chunkBytes As Byte() In TiffPageSplitter.SplitTiffToChunks(inputPath, maxPagesPerChunk:=100)
    Using ocrInput As New OcrInput()
        ocrInput.LoadImage(chunkBytes) ' loads every page in the chunk
        Dim result = ocr.Read(ocrInput)
        Console.WriteLine($"Chunk {chunk}: {If(result.Text?.Length, 0)} chars")
    End Using
    chunk += 1
Next