如何用 C# 在 Windows 上安装 Tesseract OCR

// Google Cloud Vision: JSON key file deployed to every server before this line works
// GOOGLE_APPLICATION_CREDENTIALS="/etc/secrets/service-account.json" must be set
// Key contains RSA private key — rotate manually, revoke if compromised
_client = ImageAnnotatorClient.Create();
var image = Image.FromFile("document.jpg");
var response = _client.DetectText(image);   // document leaves your infrastructure
string text = response[0].Description;

' Google Cloud Vision: JSON key file deployed to every server before this line works
' GOOGLE_APPLICATION_CREDENTIALS="/etc/secrets/service-account.json" must be set
' Key contains RSA private key — rotate manually, revoke if compromised
_client = ImageAnnotatorClient.Create()
Dim image = Image.FromFile("document.jpg")
Dim response = _client.DetectText(image)   ' document leaves your infrastructure
Dim text As String = response(0).Description

// IronOCR: one string at startup, no key files, no environment variables
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";
string text = new IronTesseract().Read("document.jpg").Text;  // local, no cloud

Imports IronOcr

' IronOCR: one string at startup, no key files, no environment variables
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"
Dim text As String = New IronTesseract().Read("document.jpg").Text ' local, no cloud

dotnet remove package Google.Cloud.Vision.V1
dotnet remove package Google.Cloud.Storage.V1

// Before (Google Cloud Vision)
using Google.Cloud.Vision.V1;
using Google.Cloud.Storage.V1;
using Google.Protobuf;
using Grpc.Core;

// After (IronOCR)
using IronOcr;

Imports IronOcr

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

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

IronOcr.License.LicenseKey = Environment.GetEnvironmentVariable("IRONOCR_LICENSE")
    ?? throw new InvalidOperationException("IRONOCR_LICENSE environment variable not set.");

Imports System
Imports IronOcr

IronOcr.License.LicenseKey = If(Environment.GetEnvironmentVariable("IRONOCR_LICENSE"), Throw New InvalidOperationException("IRONOCR_LICENSE environment variable not set."))

using Google.Cloud.Vision.V1;

// Prerequisites before this class can be instantiated:
// 1. GCP project created and Vision API enabled in GCP Console
// 2. Service account created with roles/cloudvision.user IAM role
// 3. JSON key file downloaded to every server that runs this code
// 4. GOOGLE_APPLICATION_CREDENTIALS env var pointing to the JSON file
// 5. JSON file excluded from source control via .gitignore
// 6. Key rotation schedule established (recommended: 90 days)
// 7. Separate credentials per environment (dev/staging/prod)

public class DocumentOcrService
{
    private readonly ImageAnnotatorClient _client;
    private readonly string _projectId;

    public DocumentOcrService(string projectId)
    {
        _projectId = projectId;
        // Throws RpcException(StatusCode.PermissionDenied) if any prerequisite is missing
        _client = ImageAnnotatorClient.Create();
    }

    public string ReadDocument(string imagePath)
    {
        var image = Image.FromFile(imagePath);
        var response = _client.DetectText(image);
        return response.Count > 0 ? response[0].Description : string.Empty;
    }
}

Imports Google.Cloud.Vision.V1

' Prerequisites before this class can be instantiated:
' 1. GCP project created and Vision API enabled in GCP Console
' 2. Service account created with roles/cloudvision.user IAM role
' 3. JSON key file downloaded to every server that runs this code
' 4. GOOGLE_APPLICATION_CREDENTIALS env var pointing to the JSON file
' 5. JSON file excluded from source control via .gitignore
' 6. Key rotation schedule established (recommended: 90 days)
' 7. Separate credentials per environment (dev/staging/prod)

Public Class DocumentOcrService
    Private ReadOnly _client As ImageAnnotatorClient
    Private ReadOnly _projectId As String

    Public Sub New(projectId As String)
        _projectId = projectId
        ' Throws RpcException(StatusCode.PermissionDenied) if any prerequisite is missing
        _client = ImageAnnotatorClient.Create()
    End Sub

    Public Function ReadDocument(imagePath As String) As String
        Dim image = Image.FromFile(imagePath)
        Dim response = _client.DetectText(image)
        Return If(response.Count > 0, response(0).Description, String.Empty)
    End Function
End Class

using IronOcr;

// Prerequisites: set the license key once at app startup
// 否 JSON files, no environment variables beyond the key, no GCP Console configuration
// 否 key rotation, no IAM roles, no per-environment credential sets

public class DocumentOcrService
{
    private readonly IronTesseract _ocr;

    public DocumentOcrService()
    {
        // IronTesseract is ready immediately — no external validation required
        _ocr = new IronTesseract();
    }

    public string ReadDocument(string imagePath)
    {
        return _ocr.Read(imagePath).Text;
    }
}

Imports IronOcr

' Prerequisites: set the license key once at app startup
' 否 JSON files, no environment variables beyond the key, no GCP Console configuration
' 否 key rotation, no IAM roles, no per-environment credential sets

Public Class DocumentOcrService
    Private ReadOnly _ocr As IronTesseract

    Public Sub New()
        ' IronTesseract is ready immediately — no external validation required
        _ocr = New IronTesseract()
    End Sub

    Public Function ReadDocument(imagePath As String) As String
        Return _ocr.Read(imagePath).Text
    End Function
End Class

using Google.Cloud.Vision.V1;
using System.Collections.Generic;

public class BatchAnnotationService
{
    private readonly ImageAnnotatorClient _client;

    public BatchAnnotationService()
    {
        _client = ImageAnnotatorClient.Create();
    }

    public List<string> BatchAnnotateImages(string[] imagePaths)
    {
        // Build one request per image with TEXT_DETECTION feature
        var requests = imagePaths.Select(path => new AnnotateImageRequest
        {
            Image = Image.FromFile(path),
            Features =
            {
                new 特征 { Type = Feature.Types.Type.TextDetection },
                new 特征 { Type = Feature.Types.Type.DocumentTextDetection }
            }
        }).ToList();

        // Single round-trip for all images in the batch
        var batchResponse = _client.BatchAnnotateImages(requests);

        // Match responses back to requests by index
        var results = new List<string>();
        for (int i = 0; i < batchResponse.Responses.Count; i++)
        {
            var response = batchResponse.Responses[i];
            if (response.Error != null)
            {
                // Per-item error in batch — must handle individually
                results.Add($"Error on {imagePaths[i]}: {response.Error.Message}");
                continue;
            }

            // Prefer DOCUMENT_TEXT_DETECTION full text if available
            var fullText = response.FullTextAnnotation?.Text
                ?? response.TextAnnotations.FirstOrDefault()?.Description
                ?? string.Empty;
            results.Add(fullText);
        }

        return results;
    }
}

Imports Google.Cloud.Vision.V1
Imports System.Collections.Generic
Imports System.Linq

Public Class BatchAnnotationService
    Private ReadOnly _client As ImageAnnotatorClient

    Public Sub New()
        _client = ImageAnnotatorClient.Create()
    End Sub

    Public Function BatchAnnotateImages(imagePaths As String()) As List(Of String)
        ' Build one request per image with TEXT_DETECTION feature
        Dim requests = imagePaths.Select(Function(path) New AnnotateImageRequest With {
            .Image = Image.FromFile(path),
            .Features = {
                New Feature With {.Type = Feature.Types.Type.TextDetection},
                New Feature With {.Type = Feature.Types.Type.DocumentTextDetection}
            }
        }).ToList()

        ' Single round-trip for all images in the batch
        Dim batchResponse = _client.BatchAnnotateImages(requests)

        ' Match responses back to requests by index
        Dim results = New List(Of String)()
        For i As Integer = 0 To batchResponse.Responses.Count - 1
            Dim response = batchResponse.Responses(i)
            If response.Error IsNot Nothing Then
                ' Per-item error in batch — must handle individually
                results.Add($"Error on {imagePaths(i)}: {response.Error.Message}")
                Continue For
            End If

            ' Prefer DOCUMENT_TEXT_DETECTION full text if available
            Dim fullText = If(response.FullTextAnnotation?.Text, response.TextAnnotations.FirstOrDefault()?.Description, String.Empty)
            results.Add(fullText)
        Next

        Return results
    End Function
End Class

using IronOcr;
using System.Collections.Concurrent;
using System.Collections.Generic;
using System.Threading.Tasks;

public class BatchAnnotationService
{
    public List<string> BatchAnnotateImages(string[] imagePaths)
    {
        var results = new ConcurrentDictionary<int, string>();

        // Parallel processing — no batch size limit, no network round-trips
        Parallel.For(0, imagePaths.Length, i =>
        {
            var ocr = new IronTesseract();   // thread-safe: one instance per thread
            results[i] = ocr.Read(imagePaths[i]).Text;
        });

        // Reconstruct in original order
        return Enumerable.Range(0, imagePaths.Length)
            .Select(i => results[i])
            .ToList();
    }

    public OcrResult BatchAsDocument(string[] imagePaths)
    {
        // Load all images into a single OcrInput for combined document output
        using var input = new OcrInput();
        foreach (var path in imagePaths)
            input.LoadImage(path);

        return new IronTesseract().Read(input);
    }
}

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

Public Class BatchAnnotationService
    Public Function BatchAnnotateImages(imagePaths As String()) As List(Of String)
        Dim results = New ConcurrentDictionary(Of Integer, String)()

        ' Parallel processing — no batch size limit, no network round-trips
        Parallel.For(0, imagePaths.Length, Sub(i)
                                               Dim ocr = New IronTesseract() ' thread-safe: one instance per thread
                                               results(i) = ocr.Read(imagePaths(i)).Text
                                           End Sub)

        ' Reconstruct in original order
        Return Enumerable.Range(0, imagePaths.Length) _
            .Select(Function(i) results(i)) _
            .ToList()
    End Function

    Public Function BatchAsDocument(imagePaths As String()) As OcrResult
        ' Load all images into a single OcrInput for combined document output
        Using input As New OcrInput()
            For Each path In imagePaths
                input.LoadImage(path)
            Next
            Return New IronTesseract().Read(input)
        End Using
    End Function
End Class

using Google.Cloud.Vision.V1;
using System.Collections.Generic;

public record WordAnnotation(string Text, int X, int Y, int Width, int Height, float Confidence);

public class WordLevelExtractor
{
    private readonly ImageAnnotatorClient _client;

    public WordLevelExtractor()
    {
        _client = ImageAnnotatorClient.Create();
    }

    public List<WordAnnotation> ExtractWordAnnotations(string imagePath)
    {
        var image = Image.FromFile(imagePath);
        var annotation = _client.DetectDocumentText(image);

        var words = new List<WordAnnotation>();

        // Navigate: Pages -> Blocks -> Paragraphs -> Words
        foreach (var page in annotation.Pages)
        {
            foreach (var block in page.Blocks)
            {
                foreach (var paragraph in block.Paragraphs)
                {
                    foreach (var word in paragraph.Words)
                    {
                        // Word.Text does not exist — must concatenate Symbols
                        var text = string.Concat(word.Symbols.Select(s => s.Text));

                        // BoundingPoly has Vertices, not X/Y/Width/Height
                        var vertices = word.BoundingBox.Vertices;
                        int x = vertices[0].X;
                        int y = vertices[0].Y;
                        int width = vertices.Count > 1 ? vertices[1].X - vertices[0].X : 0;
                        int height = vertices.Count > 2 ? vertices[2].Y - vertices[0].Y : 0;

                        words.Add(new WordAnnotation(text, x, y, width, height, word.Confidence));
                    }
                }
            }
        }

        return words;
    }
}

Imports Google.Cloud.Vision.V1
Imports System.Collections.Generic
Imports System.Linq

Public Class WordAnnotation
    Public Property Text As String
    Public Property X As Integer
    Public Property Y As Integer
    Public Property Width As Integer
    Public Property Height As Integer
    Public Property Confidence As Single

    Public Sub New(text As String, x As Integer, y As Integer, width As Integer, height As Integer, confidence As Single)
        Me.Text = text
        Me.X = x
        Me.Y = y
        Me.Width = width
        Me.Height = height
        Me.Confidence = confidence
    End Sub
End Class

Public Class WordLevelExtractor
    Private ReadOnly _client As ImageAnnotatorClient

    Public Sub New()
        _client = ImageAnnotatorClient.Create()
    End Sub

    Public Function ExtractWordAnnotations(imagePath As String) As List(Of WordAnnotation)
        Dim image = Image.FromFile(imagePath)
        Dim annotation = _client.DetectDocumentText(image)

        Dim words As New List(Of WordAnnotation)()

        ' Navigate: Pages -> Blocks -> Paragraphs -> Words
        For Each page In annotation.Pages
            For Each block In page.Blocks
                For Each paragraph In block.Paragraphs
                    For Each word In paragraph.Words
                        ' Word.Text does not exist — must concatenate Symbols
                        Dim text = String.Concat(word.Symbols.Select(Function(s) s.Text))

                        ' BoundingPoly has Vertices, not X/Y/Width/Height
                        Dim vertices = word.BoundingBox.Vertices
                        Dim x As Integer = vertices(0).X
                        Dim y As Integer = vertices(0).Y
                        Dim width As Integer = If(vertices.Count > 1, vertices(1).X - vertices(0).X, 0)
                        Dim height As Integer = If(vertices.Count > 2, vertices(2).Y - vertices(0).Y, 0)

                        words.Add(New WordAnnotation(text, x, y, width, height, word.Confidence))
                    Next
                Next
            Next
        Next

        Return words
    End Function
End Class

using IronOcr;
using System.Collections.Generic;

public record WordAnnotation(string Text, int X, int Y, int Width, int Height, double Confidence);

public class WordLevelExtractor
{
    private readonly IronTesseract _ocr;

    public WordLevelExtractor()
    {
        _ocr = new IronTesseract();
    }

    public List<WordAnnotation> ExtractWordAnnotations(string imagePath)
    {
        var result = _ocr.Read(imagePath);

        // Words are a flat collection — no hierarchy traversal, no symbol concatenation
        return result.Words.Select(w => new WordAnnotation(
            Text:       w.Text,         // direct string property
            X:          w.X,
            Y:          w.Y,
            Width:      w.Width,
            Height:     w.Height,
            Confidence: w.Confidence    // double, no conversion needed
        )).ToList();
    }
}

Imports IronOcr
Imports System.Collections.Generic

Public Class WordAnnotation
    Public Property Text As String
    Public Property X As Integer
    Public Property Y As Integer
    Public Property Width As Integer
    Public Property Height As Integer
    Public Property Confidence As Double

    Public Sub New(text As String, x As Integer, y As Integer, width As Integer, height As Integer, confidence As Double)
        Me.Text = text
        Me.X = x
        Me.Y = y
        Me.Width = width
        Me.Height = height
        Me.Confidence = confidence
    End Sub
End Class

Public Class WordLevelExtractor
    Private ReadOnly _ocr As IronTesseract

    Public Sub New()
        _ocr = New IronTesseract()
    End Sub

    Public Function ExtractWordAnnotations(imagePath As String) As List(Of WordAnnotation)
        Dim result = _ocr.Read(imagePath)

        ' Words are a flat collection — no hierarchy traversal, no symbol concatenation
        Return result.Words.Select(Function(w) New WordAnnotation(
            Text:=w.Text,         ' direct string property
            X:=w.X,
            Y:=w.Y,
            Width:=w.Width,
            Height:=w.Height,
            Confidence:=w.Confidence    ' double, no conversion needed
        )).ToList()
    End Function
End Class

using Google.Cloud.Vision.V1;
using System.Collections.Generic;
using System.Drawing;          // for TIFF frame extraction
using System.Drawing.Imaging;

public class TiffProcessingService
{
    private readonly ImageAnnotatorClient _client;

    public TiffProcessingService()
    {
        _client = ImageAnnotatorClient.Create();
    }

    public List<string> ProcessMultiPageTiff(string tiffPath)
    {
        var pageTexts = new List<string>();

        // Load TIFF and extract frames manually using System.Drawing
        using var tiff = System.Drawing.Image.FromFile(tiffPath);
        var frameDimension = new FrameDimension(tiff.FrameDimensionsList[0]);
        int frameCount = tiff.GetFrameCount(frameDimension);

        for (int i = 0; i < frameCount; i++)
        {
            tiff.SelectActiveFrame(frameDimension, i);

            // Save each frame to a temp file — Vision API does not accept TIFF frames directly
            var tempPath = Path.Combine(Path.GetTempPath(), $"tiff-frame-{i}.jpg");
            tiff.Save(tempPath, ImageFormat.Jpeg);

            // One API call per frame — each call = one unit of quota
            var visionImage = Google.Cloud.Vision.V1.Image.FromFile(tempPath);
            var response = _client.DetectText(visionImage);
            pageTexts.Add(response.FirstOrDefault()?.Description ?? string.Empty);

            File.Delete(tempPath);
        }

        // Producing a searchable PDF requires a separate library (e.g., iTextSharp)
        //Google Cloud Visionhas no PDF output capability
        return pageTexts;
    }
}

Imports Google.Cloud.Vision.V1
Imports System.Collections.Generic
Imports System.Drawing          ' for TIFF frame extraction
Imports System.Drawing.Imaging
Imports System.IO

Public Class TiffProcessingService
    Private ReadOnly _client As ImageAnnotatorClient

    Public Sub New()
        _client = ImageAnnotatorClient.Create()
    End Sub

    Public Function ProcessMultiPageTiff(tiffPath As String) As List(Of String)
        Dim pageTexts As New List(Of String)()

        ' Load TIFF and extract frames manually using System.Drawing
        Using tiff As System.Drawing.Image = System.Drawing.Image.FromFile(tiffPath)
            Dim frameDimension As New FrameDimension(tiff.FrameDimensionsList(0))
            Dim frameCount As Integer = tiff.GetFrameCount(frameDimension)

            For i As Integer = 0 To frameCount - 1
                tiff.SelectActiveFrame(frameDimension, i)

                ' Save each frame to a temp file — Vision API does not accept TIFF frames directly
                Dim tempPath As String = Path.Combine(Path.GetTempPath(), $"tiff-frame-{i}.jpg")
                tiff.Save(tempPath, ImageFormat.Jpeg)

                ' One API call per frame — each call = one unit of quota
                Dim visionImage As Google.Cloud.Vision.V1.Image = Google.Cloud.Vision.V1.Image.FromFile(tempPath)
                Dim response = _client.DetectText(visionImage)
                pageTexts.Add(If(response.FirstOrDefault()?.Description, String.Empty))

                File.Delete(tempPath)
            Next
        End Using

        ' Producing a searchable PDF requires a separate library (e.g., iTextSharp)
        ' Google Cloud Vision has no PDF output capability
        Return pageTexts
    End Function
End Class

using IronOcr;

public class TiffProcessingService
{
    private readonly IronTesseract _ocr;

    public TiffProcessingService()
    {
        _ocr = new IronTesseract();
    }

    public string ProcessMultiPageTiff(string tiffPath)
    {
        using var input = new OcrInput();
        // LoadImageFrames handles all TIFF frames in one call — no temp files, no frame loop
        input.LoadImageFrames(tiffPath);

        var result = _ocr.Read(input);
        return result.Text;
    }

    public void ProcessMultiPageTiffToSearchablePdf(string tiffPath, string outputPdfPath)
    {
        using var input = new OcrInput();
        input.LoadImageFrames(tiffPath);

        var result = _ocr.Read(input);

        //Google Cloud Visionhas no equivalent — this single call produces a searchable PDF
        result.SaveAsSearchablePdf(outputPdfPath);
    }

    public void ProcessLowQualityTiff(string tiffPath, string outputPdfPath)
    {
        using var input = new OcrInput();
        input.LoadImageFrames(tiffPath);

        // Preprocessing before OCR improves accuracy on degraded scans
        input.Deskew();
        input.DeNoise();
        input.Contrast();

        var result = _ocr.Read(input);
        result.SaveAsSearchablePdf(outputPdfPath);
    }
}

Imports IronOcr

Public Class TiffProcessingService
    Private ReadOnly _ocr As IronTesseract

    Public Sub New()
        _ocr = New IronTesseract()
    End Sub

    Public Function ProcessMultiPageTiff(tiffPath As String) As String
        Using input As New OcrInput()
            ' LoadImageFrames handles all TIFF frames in one call — no temp files, no frame loop
            input.LoadImageFrames(tiffPath)

            Dim result = _ocr.Read(input)
            Return result.Text
        End Using
    End Function

    Public Sub ProcessMultiPageTiffToSearchablePdf(tiffPath As String, outputPdfPath As String)
        Using input As New OcrInput()
            input.LoadImageFrames(tiffPath)

            Dim result = _ocr.Read(input)

            ' Google Cloud Vision has no equivalent — this single call produces a searchable PDF
            result.SaveAsSearchablePdf(outputPdfPath)
        End Using
    End Sub

    Public Sub ProcessLowQualityTiff(tiffPath As String, outputPdfPath As String)
        Using input As New OcrInput()
            input.LoadImageFrames(tiffPath)

            ' Preprocessing before OCR improves accuracy on degraded scans
            input.Deskew()
            input.DeNoise()
            input.Contrast()

            Dim result = _ocr.Read(input)
            result.SaveAsSearchablePdf(outputPdfPath)
        End Using
    End Sub
End Class

using Google.Cloud.Vision.V1;
using Grpc.Core;
using System.Collections.Generic;

public class ThrottledBatchProcessor
{
    private readonly ImageAnnotatorClient _client;
    private const int MaxRequestsPerMinute = 1800;
    private const int RetryDelayMs = 60_000;

    public ThrottledBatchProcessor()
    {
        _client = ImageAnnotatorClient.Create();
    }

    public async Task<Dictionary<string, string>> ProcessWithThrottlingAsync(
        string[] imagePaths,
        IProgress<(int completed, int total)> progress)
    {
        var results = new Dictionary<string, string>();
        int completed = 0;

        foreach (var path in imagePaths)
        {
            bool succeeded = false;
            while (!succeeded)
            {
                try
                {
                    var image = Google.Cloud.Vision.V1.Image.FromFile(path);
                    var response = _client.DetectText(image);
                    results[path] = response.FirstOrDefault()?.Description ?? string.Empty;
                    succeeded = true;
                }
                catch (RpcException ex) when (ex.StatusCode == StatusCode.ResourceExhausted)
                {
                    // Rate limit exceeded — wait and retry
                    await Task.Delay(RetryDelayMs);
                }
            }

            progress.Report((++completed, imagePaths.Length));
        }

        return results;
    }
}

Imports Google.Cloud.Vision.V1
Imports Grpc.Core
Imports System.Collections.Generic
Imports System.Threading.Tasks

Public Class ThrottledBatchProcessor
    Private ReadOnly _client As ImageAnnotatorClient
    Private Const MaxRequestsPerMinute As Integer = 1800
    Private Const RetryDelayMs As Integer = 60000

    Public Sub New()
        _client = ImageAnnotatorClient.Create()
    End Sub

    Public Async Function ProcessWithThrottlingAsync(
        imagePaths As String(),
        progress As IProgress(Of (completed As Integer, total As Integer))) As Task(Of Dictionary(Of String, String))

        Dim results As New Dictionary(Of String, String)()
        Dim completed As Integer = 0

        For Each path In imagePaths
            Dim succeeded As Boolean = False
            While Not succeeded
                Try
                    Dim image = Google.Cloud.Vision.V1.Image.FromFile(path)
                    Dim response = _client.DetectText(image)
                    results(path) = If(response.FirstOrDefault()?.Description, String.Empty)
                    succeeded = True
                Catch ex As RpcException When ex.StatusCode = StatusCode.ResourceExhausted
                    ' Rate limit exceeded — wait and retry
                    Await Task.Delay(RetryDelayMs)
                End Try
            End While

            progress.Report((Threading.Interlocked.Increment(completed), imagePaths.Length))
        Next

        Return results
    End Function
End Class

using IronOcr;
using System.Collections.Concurrent;
using System.Collections.Generic;
using System.Threading;
using System.Threading.Tasks;

public class BatchProcessor
{
    public Dictionary<string, string> ProcessBatch(
        string[] imagePaths,
        IProgress<(int completed, int total)> progress)
    {
        var results = new ConcurrentDictionary<string, string>();
        int completed = 0;

        // 无速率限制 — full parallelism, no retry logic needed
        Parallel.ForEach(imagePaths, imagePath =>
        {
            var ocr = new IronTesseract();
            results[imagePath] = ocr.Read(imagePath).Text;
            progress.Report((Interlocked.Increment(ref completed), imagePaths.Length));
        });

        return new Dictionary<string, string>(results);
    }

    public void ProcessBatchToSearchablePdfs(
        string[] imagePaths,
        string outputDirectory)
    {
        Parallel.ForEach(imagePaths, imagePath =>
        {
            var ocr = new IronTesseract();
            var result = ocr.Read(imagePath);

            var outputPath = Path.Combine(
                outputDirectory,
                Path.GetFileNameWithoutExtension(imagePath) + "-searchable.pdf");

            result.SaveAsSearchablePdf(outputPath);
        });
    }
}

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

Public Class BatchProcessor
    Public Function ProcessBatch(imagePaths As String(), progress As IProgress(Of (completed As Integer, total As Integer))) As Dictionary(Of String, String)
        Dim results = New ConcurrentDictionary(Of String, String)()
        Dim completed As Integer = 0

        ' 无速率限制 — full parallelism, no retry logic needed
        Parallel.ForEach(imagePaths, Sub(imagePath)
                                         Dim ocr = New IronTesseract()
                                         results(imagePath) = ocr.Read(imagePath).Text
                                         progress.Report((Interlocked.Increment(completed), imagePaths.Length))
                                     End Sub)

        Return New Dictionary(Of String, String)(results)
    End Function

    Public Sub ProcessBatchToSearchablePdfs(imagePaths As String(), outputDirectory As String)
        Parallel.ForEach(imagePaths, Sub(imagePath)
                                         Dim ocr = New IronTesseract()
                                         Dim result = ocr.Read(imagePath)

                                         Dim outputPath = Path.Combine(outputDirectory, Path.GetFileNameWithoutExtension(imagePath) & "-searchable.pdf")

                                         result.SaveAsSearchablePdf(outputPath)
                                     End Sub)
    End Sub
End Class

// Remove this from every deployment environment:
// GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json

// Add this once at application startup:
IronOcr.License.LicenseKey = Environment.GetEnvironmentVariable("IRONOCR_LICENSE")
    ?? throw new InvalidOperationException("IRONOCR_LICENSE environment variable is required.");

' Remove this from every deployment environment:
' GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json

' Add this once at application startup:
IronOcr.License.LicenseKey = If(Environment.GetEnvironmentVariable("IRONOCR_LICENSE"), Throw New InvalidOperationException("IRONOCR_LICENSE environment variable is required."))

# Find all Protobuf symbol concatenation patterns
grep -rn "\.Symbols\." --include="*.cs" .
grep -rn "SelectMany.*Symbols" --include="*.cs" .
grep -rn "w\.Symbols\.Select" --include="*.cs" .

// Before: symbol concatenation required by Protobuf schema
var text = string.Join("", paragraph.Words.SelectMany(w => w.Symbols).Select(s => s.Text));

// After: direct property on OcrResult.Paragraph
var text = paragraph.Text;

' Before: symbol concatenation required by Protobuf schema
Dim text = String.Join("", paragraph.Words.SelectMany(Function(w) w.Symbols).Select(Function(s) s.Text))

' After: direct property on OcrResult.Paragraph
Dim text = paragraph.Text

// Delete: StorageClient, GCS upload, AsyncBatchAnnotateFilesAsync,
//         PollUntilCompletedAsync, output download, DeleteObjectAsync

// Replace with:
public async Task<string> ProcessPdfAsync(string pdfPath)
{
    return await Task.Run(() =>
    {
        using var input = new OcrInput();
        input.LoadPdf(pdfPath);
        return new IronTesseract().Read(input).Text;
    });
}

Imports System.Threading.Tasks

Public Async Function ProcessPdfAsync(pdfPath As String) As Task(Of String)
    Return Await Task.Run(Function()
                              Using input As New OcrInput()
                                  input.LoadPdf(pdfPath)
                                  Return New IronTesseract().Read(input).Text
                              End Using
                          End Function)
End Function

// Remove: all RpcException handlers for ResourceExhausted, PermissionDenied,
//         Unavailable, DeadlineExceeded, Unauthenticated

//IronOCRerror surface:
try
{
    var result = new IronTesseract().Read(imagePath);
    if (result.Confidence < 50)
        input.DeNoise(); // add preprocessing for low-confidence results
    return result.Text;
}
catch (IOException ex)
{
    // File not found or locked
    throw new InvalidOperationException($"Cannot read: {imagePath}", ex);
}
catch (IronOcr.Exceptions.OcrException ex)
{
    // Processing failure — not a transient network error
    throw new InvalidOperationException($"OCR failed: {ex.Message}", ex);
}

Imports IronOcr
Imports System.IO

' Remove: all RpcException handlers for ResourceExhausted, PermissionDenied,
'         Unavailable, DeadlineExceeded, Unauthenticated

'IronOCRerror surface:
Try
    Dim result = New IronTesseract().Read(imagePath)
    If result.Confidence < 50 Then
        input.DeNoise() ' add preprocessing for low-confidence results
    End If
    Return result.Text
Catch ex As IOException
    ' File not found or locked
    Throw New InvalidOperationException($"Cannot read: {imagePath}", ex)
Catch ex As IronOcr.Exceptions.OcrException
    ' Processing failure — not a transient network error
    Throw New InvalidOperationException($"OCR failed: {ex.Message}", ex)
End Try

// Remove: System.Drawing frame extraction, temp file writes, per-frame API calls

// Replace with:
using var input = new OcrInput();
input.LoadImageFrames(tiffPath);   // all frames, no temp files
var result = new IronTesseract().Read(input);

Imports IronOcr

Dim input As New OcrInput()
input.LoadImageFrames(tiffPath) ' all frames, no temp files
Dim result = (New IronTesseract()).Read(input)

// Before: vertex index arithmetic
int x = word.BoundingBox.Vertices[0].X;
int y = word.BoundingBox.Vertices[0].Y;
int width  = word.BoundingBox.Vertices[1].X - word.BoundingBox.Vertices[0].X;
int height = word.BoundingBox.Vertices[2].Y - word.BoundingBox.Vertices[0].Y;

// After: direct properties
int x      = word.X;
int y      = word.Y;
int width  = word.Width;
int height = word.Height;

' Before: vertex index arithmetic
Dim x As Integer = word.BoundingBox.Vertices(0).X
Dim y As Integer = word.BoundingBox.Vertices(0).Y
Dim width As Integer = word.BoundingBox.Vertices(1).X - word.BoundingBox.Vertices(0).X
Dim height As Integer = word.BoundingBox.Vertices(2).Y - word.BoundingBox.Vertices(0).Y

' After: direct properties
Dim x As Integer = word.X
Dim y As Integer = word.Y
Dim width As Integer = word.Width
Dim height As Integer = word.Height

# Find allGoogle Cloud Visionnamespace imports
grep -rn "using Google.Cloud.Vision" --include="*.cs" .
grep -rn "using Google.Cloud.Storage" --include="*.cs" .
grep -rn "using Grpc.Core" --include="*.cs" .

# Find ImageAnnotatorClient usage
grep -rn "ImageAnnotatorClient" --include="*.cs" .

# Find GCS pipeline code
grep -rn "StorageClient\|UploadObjectAsync\|DeleteObjectAsync" --include="*.cs" .
grep -rn "AsyncBatchAnnotateFilesAsync\|PollUntilCompleted" --include="*.cs" .

# Find Protobuf symbol concatenation
grep -rn "\.Symbols\." --include="*.cs" .
grep -rn "SelectMany.*Symbols" --include="*.cs" .

# Find BoundingPoly vertex calculations
grep -rn "BoundingPoly\|BoundingBox\.Vertices" --include="*.cs" .

# Find rate limit retry handlers
grep -rn "ResourceExhausted\|StatusCode\." --include="*.cs" .

# Find environment variable references
grep -rn "GOOGLE_APPLICATION_CREDENTIALS" .