从 Asprise OCR 迁移到 IronOCR

// Asprise: native binary must exist in PATH or application directory
// aocr_x64.dll missing → DllNotFoundException at runtime, not at build
Ocr.SetUp();                              // Static init — touches native binary
Ocr ocr = new Ocr();
ocr.StartEngine("eng", Ocr.SPEED_FAST);  // Allocates native engine memory
string text = ocr.Recognize(imagePath, Ocr.RECOGNIZE_TYPE_TEXT, Ocr.OUTPUT_FORMAT_PLAINTEXT);
ocr.StopEngine();                         // Must call or native memory leaks

' Asprise: native binary must exist in PATH or application directory
' aocr_x64.dll missing → DllNotFoundException at runtime, not at build
Ocr.SetUp()                              ' Static init — touches native binary
Dim ocr As New Ocr()
ocr.StartEngine("eng", Ocr.SPEED_FAST)   ' Allocates native engine memory
Dim text As String = ocr.Recognize(imagePath, Ocr.RECOGNIZE_TYPE_TEXT, Ocr.OUTPUT_FORMAT_PLAINTEXT)
ocr.StopEngine()                         ' Must call or native memory leaks

// IronOCR: dotnet add package IronOcr — no binary sourcing, no lifecycle calls
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";
string text = new IronTesseract().Read(imagePath).Text;

' IronOCR: dotnet add package IronOcr — no binary sourcing, no lifecycle calls
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"
Dim text As String = New IronTesseract().Read(imagePath).Text

dotnet remove package asprise-ocr-api

// Before (Asprise)
using asprise.ocr;

// After (IronOCR)
using IronOcr;

Imports IronOcr

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

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

// AppStartup.cs — native binary validation before accepting any requests
public static void InitializeOcr()
{
    // Validate native library is reachable before first use
    string nativePath = RuntimeInformation.IsOSPlatform(OSPlatform.Windows)
        ? Path.Combine(AppContext.BaseDirectory, "aocr_x64.dll")
        : RuntimeInformation.IsOSPlatform(OSPlatform.Linux)
            ? "/usr/lib/libaocr.so"
            : "/usr/local/lib/libaocr.dylib";

    if (!File.Exists(nativePath))
        throw new FileNotFoundException(
            $"Asprise native binary not found: {nativePath}. " +
            "Deploy the correct platform binary before starting.");

    // Static global init — must run before any Ocr instance is created
    Ocr.SetUp();
}

Imports System
Imports System.IO
Imports System.Runtime.InteropServices

' AppStartup.vb — native binary validation before accepting any requests
Public Module AppStartup
    Public Sub InitializeOcr()
        ' Validate native library is reachable before first use
        Dim nativePath As String = If(RuntimeInformation.IsOSPlatform(OSPlatform.Windows),
                                      Path.Combine(AppContext.BaseDirectory, "aocr_x64.dll"),
                                      If(RuntimeInformation.IsOSPlatform(OSPlatform.Linux),
                                         "/usr/lib/libaocr.so",
                                         "/usr/local/lib/libaocr.dylib"))

        If Not File.Exists(nativePath) Then
            Throw New FileNotFoundException($"Asprise native binary not found: {nativePath}. " &
                                            "Deploy the correct platform binary before starting.")
        End If

        ' Static global init — must run before any Ocr instance is created
        Ocr.SetUp()
    End Sub
End Module

// Program.cs — license key assignment is the entire initialization
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

// That is it. 否 binary validation, no path configuration, no SetUp() call.
// NuGet resolved the correct native runtime during package restore.

' Program.vb — license key assignment is the entire initialization
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"

' That is it. 否 binary validation, no path configuration, no SetUp() call.
' NuGet resolved the correct native runtime during package restore.

// Asprise: structured output is an XML string — must parse manually
Ocr.SetUp();
Ocr ocr = new Ocr();
try
{
    ocr.StartEngine("eng", Ocr.SPEED_FAST);
    string xmlOutput = ocr.Recognize(
        imagePath,
        Ocr.RECOGNIZE_TYPE_TEXT,
        Ocr.OUTPUT_FORMAT_XML);   // Returns raw XML, not an object

    // Parse the XML manually to extract words and coordinates
    var doc = System.Xml.Linq.XDocument.Parse(xmlOutput);
    var words = doc.Descendants("word")
        .Select(w => new
        {
            Text       = (string)w.Attribute("text"),
            Confidence = (float)w.Attribute("confidence"),
            X          = (int)w.Attribute("x"),
            Y          = (int)w.Attribute("y"),
        })
        .ToList();

    foreach (var word in words)
        Console.WriteLine($"{word.Text} @ ({word.X},{word.Y}) conf={word.Confidence}");
}
finally
{
    ocr.StopEngine();
}

Imports System.Xml.Linq

' Asprise: structured output is an XML string — must parse manually
Ocr.SetUp()
Dim ocr As New Ocr()
Try
    ocr.StartEngine("eng", Ocr.SPEED_FAST)
    Dim xmlOutput As String = ocr.Recognize(imagePath, Ocr.RECOGNIZE_TYPE_TEXT, Ocr.OUTPUT_FORMAT_XML) ' Returns raw XML, not an object

    ' Parse the XML manually to extract words and coordinates
    Dim doc As XDocument = XDocument.Parse(xmlOutput)
    Dim words = doc.Descendants("word") _
        .Select(Function(w) New With {
            .Text = CStr(w.Attribute("text")),
            .Confidence = CSng(w.Attribute("confidence")),
            .X = CInt(w.Attribute("x")),
            .Y = CInt(w.Attribute("y"))
        }) _
        .ToList()

    For Each word In words
        Console.WriteLine($"{word.Text} @ ({word.X},{word.Y}) conf={word.Confidence}")
Next
Finally
    ocr.StopEngine()
End Try

// IronOCR: structured result is a typed object — no XML parsing
var result = new IronTesseract().Read(imagePath);

foreach (var page in result.Pages)
{
    foreach (var paragraph in page.Paragraphs)
    {
        foreach (var word in paragraph.Words)
        {
            Console.WriteLine(
                $"{word.Text} @ ({word.X},{word.Y}) conf={word.Confidence:F1}%");
        }
    }
}

Imports IronOcr

' IronOCR: structured result is a typed object — no XML parsing
Dim result = New IronTesseract().Read(imagePath)

For Each page In result.Pages
    For Each paragraph In page.Paragraphs
        For Each word In paragraph.Words
            Console.WriteLine($"{word.Text} @ ({word.X},{word.Y}) conf={word.Confidence:F1}%")
        Next
    Next
Next

// Asprise: no multi-frame TIFF support — split frames externally first
// Using an external imaging library (e.g., System.Drawing or Magick.NET)
var frameFiles = new List<string>();
using (var tiff = System.Drawing.Image.FromFile("scanned-batch.tiff"))
{
    int frameCount = tiff.GetFrameCount(System.Drawing.Imaging.FrameDimension.Page);
    for (int i = 0; i < frameCount; i++)
    {
        tiff.SelectActiveFrame(System.Drawing.Imaging.FrameDimension.Page, i);
        string framePath = $"frame_{i}.png";
        tiff.Save(framePath);
        frameFiles.Add(framePath);
    }
}

// Now process each frame individually — sequential on LITE/STANDARD
var allText = new System.Text.StringBuilder();
Ocr.SetUp();
Ocr ocr = new Ocr();
try
{
    ocr.StartEngine("eng", Ocr.SPEED_FAST);
    foreach (var framePath in frameFiles)
    {
        string pageText = ocr.Recognize(
            framePath,
            Ocr.RECOGNIZE_TYPE_TEXT,
            Ocr.OUTPUT_FORMAT_PLAINTEXT);
        allText.AppendLine(pageText);
    }
}
finally
{
    ocr.StopEngine();
    // Clean up temporary frame files
    foreach (var f in frameFiles)
        File.Delete(f);
}
Console.WriteLine(allText.ToString());

Imports System.Drawing
Imports System.Text
Imports System.IO

' Asprise: no multi-frame TIFF support — split frames externally first
' Using an external imaging library (e.g., System.Drawing or Magick.NET)
Dim frameFiles As New List(Of String)()
Using tiff As Image = Image.FromFile("scanned-batch.tiff")
    Dim frameCount As Integer = tiff.GetFrameCount(Imaging.FrameDimension.Page)
    For i As Integer = 0 To frameCount - 1
        tiff.SelectActiveFrame(Imaging.FrameDimension.Page, i)
        Dim framePath As String = $"frame_{i}.png"
        tiff.Save(framePath)
        frameFiles.Add(framePath)
    Next
End Using

' Now process each frame individually — sequential on LITE/STANDARD
Dim allText As New StringBuilder()
Ocr.SetUp()
Dim ocr As New Ocr()
Try
    ocr.StartEngine("eng", Ocr.SPEED_FAST)
    For Each framePath As String In frameFiles
        Dim pageText As String = ocr.Recognize(framePath, Ocr.RECOGNIZE_TYPE_TEXT, Ocr.OUTPUT_FORMAT_PLAINTEXT)
        allText.AppendLine(pageText)
    Next
Finally
    ocr.StopEngine()
    ' Clean up temporary frame files
    For Each f As String In frameFiles
        File.Delete(f)
    Next
End Try
Console.WriteLine(allText.ToString())

// IronOCR: multi-frame TIFF loads directly — no frame splitting, no temp files
using var input = new OcrInput();
input.LoadImageFrames("scanned-batch.tiff");  // All frames, one call

var result = new IronTesseract().Read(input);

// Access each page independently with its page number
foreach (var page in result.Pages)
    Console.WriteLine($"Page {page.PageNumber}: {page.Text}");

Imports IronOcr

' IronOCR: multi-frame TIFF loads directly — no frame splitting, no temp files
Using input As New OcrInput()
    input.LoadImageFrames("scanned-batch.tiff") ' All frames, one call

    Dim result = New IronTesseract().Read(input)

    ' Access each page independently with its page number
    For Each page In result.Pages
        Console.WriteLine($"Page {page.PageNumber}: {page.Text}")
    Next
End Using

// Asprise: no searchable PDF output — external PDF library required
// Step 1: OCR the document to get text
Ocr.SetUp();
Ocr ocr = new Ocr();
string recognizedText;
try
{
    ocr.StartEngine("eng", Ocr.SPEED_FAST);
    recognizedText = ocr.Recognize(
        "scanned-contract.jpg",
        Ocr.RECOGNIZE_TYPE_TEXT,
        Ocr.OUTPUT_FORMAT_PLAINTEXT);   // Only plain text — no position data
}
finally
{
    ocr.StopEngine();
}

// Step 2: Use an external PDF library to embed text over the image
// (iTextSharp, PdfSharp, or similar — adds another dependency and license)
// Text positioning requires coordinate data Asprise cannot provide in plain text mode
// ... 40-80 lines of PDF construction code
Console.WriteLine("Searchable PDF: not achievable with Asprise alone");

' Asprise: no searchable PDF output — external PDF library required
' Step 1: OCR the document to get text
Ocr.SetUp()
Dim ocr As New Ocr()
Dim recognizedText As String
Try
    ocr.StartEngine("eng", Ocr.SPEED_FAST)
    recognizedText = ocr.Recognize( _
        "scanned-contract.jpg", _
        Ocr.RECOGNIZE_TYPE_TEXT, _
        Ocr.OUTPUT_FORMAT_PLAINTEXT)   ' Only plain text — no position data
Finally
    ocr.StopEngine()
End Try

' Step 2: Use an external PDF library to embed text over the image
' (iTextSharp, PdfSharp, or similar — adds another dependency and license)
' Text positioning requires coordinate data Asprise cannot provide in plain text mode
' ... 40-80 lines of PDF construction code
Console.WriteLine("Searchable PDF: not achievable with Asprise alone")

// IronOCR: searchable PDF in two lines — no external PDF library
var result = new IronTesseract().Read("scanned-contract.jpg");
result.SaveAsSearchablePdf("searchable-contract.pdf");

// Batch: convert a folder of scanned images to searchable PDFs
foreach (var imagePath in Directory.GetFiles("scans", "*.jpg"))
{
    var batchResult = new IronTesseract().Read(imagePath);
    string outputPath = Path.ChangeExtension(imagePath, ".searchable.pdf");
    batchResult.SaveAsSearchablePdf(outputPath);
    Console.WriteLine($"Converted: {outputPath}");
}

Imports System.IO
Imports IronOcr

' IronOCR: searchable PDF in two lines — no external PDF library
Dim result = New IronTesseract().Read("scanned-contract.jpg")
result.SaveAsSearchablePdf("searchable-contract.pdf")

' Batch: convert a folder of scanned images to searchable PDFs
For Each imagePath In Directory.GetFiles("scans", "*.jpg")
    Dim batchResult = New IronTesseract().Read(imagePath)
    Dim outputPath As String = Path.ChangeExtension(imagePath, ".searchable.pdf")
    batchResult.SaveAsSearchablePdf(outputPath)
    Console.WriteLine($"Converted: {outputPath}")
Next

// Asprise: no async API — must offload to Task.Run
// This blocks a thread pool thread during the entire OCR operation
// On LITE/STANDARD, concurrent Task.Run calls = license violation
public async Task<string> ProcessUploadAsync(Stream fileStream, string fileName)
{
    string tempPath = Path.GetTempFileName();
    await using (var fs = new FileStream(tempPath, FileMode.Create))
        await fileStream.CopyToAsync(fs);

    // Task.Run wraps synchronous Asprise — occupies a thread pool thread
    // Two concurrent requests still violate LITE/STANDARD license
    return await Task.Run(() =>
    {
        Ocr ocr = new Ocr();
        try
        {
            ocr.StartEngine("eng", Ocr.SPEED_FAST);
            return ocr.Recognize(
                tempPath,
                Ocr.RECOGNIZE_TYPE_TEXT,
                Ocr.OUTPUT_FORMAT_PLAINTEXT);
        }
        finally
        {
            ocr.StopEngine();
            File.Delete(tempPath);
        }
    });
}

Imports System.IO
Imports System.Threading.Tasks

' Asprise: no async API — must offload to Task.Run
' This blocks a thread pool thread during the entire OCR operation
' On LITE/STANDARD, concurrent Task.Run calls = license violation
Public Async Function ProcessUploadAsync(fileStream As Stream, fileName As String) As Task(Of String)
    Dim tempPath As String = Path.GetTempFileName()
    Await Using fs As New FileStream(tempPath, FileMode.Create)
        Await fileStream.CopyToAsync(fs)
    End Using

    ' Task.Run wraps synchronous Asprise — occupies a thread pool thread
    ' Two concurrent requests still violate LITE/STANDARD license
    Return Await Task.Run(Function()
                              Dim ocr As New Ocr()
                              Try
                                  ocr.StartEngine("eng", Ocr.SPEED_FAST)
                                  Return ocr.Recognize(tempPath, Ocr.RECOGNIZE_TYPE_TEXT, Ocr.OUTPUT_FORMAT_PLAINTEXT)
                              Finally
                                  ocr.StopEngine()
                                  File.Delete(tempPath)
                              End Try
                          End Function)
End Function

// IronOCR: native async, concurrent requests permitted on all tiers
public async Task<string> ProcessUploadAsync(Stream fileStream, string fileName)
{
    using var input = new OcrInput();
    input.LoadImage(fileStream);       // Stream input directly — no temp file

    var ocr = new IronTesseract();
    var result = await ocr.ReadAsync(input);
    return result.Text;
}

Imports System.IO
Imports System.Threading.Tasks

' IronOCR: native async, concurrent requests permitted on all tiers
Public Async Function ProcessUploadAsync(fileStream As Stream, fileName As String) As Task(Of String)
    Using input As New OcrInput()
        input.LoadImage(fileStream) ' Stream input directly — no temp file

        Dim ocr As New IronTesseract()
        Dim result = Await ocr.ReadAsync(input)
        Return result.Text
    End Using
End Function

grep -rn "Ocr.SetUp\|StartEngine\|StopEngine" --include="*.cs" .

// Remove all occurrences of the engine lifecycle pattern:
// Ocr.SetUp();
// ocr.StartEngine(...);
// ocr.StopEngine();

// Replace application startup initialization with:
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

// Asprise XML parsing (remove)
var words = XDocument.Parse(xmlOutput)
    .Descendants("word")
    .Select(w => new { Text = (string)w.Attribute("text"), X = (int)w.Attribute("x") });

//IronOCRobject model (replace with)
var result = new IronTesseract().Read(imagePath);
var words = result.Pages
    .SelectMany(p => p.Paragraphs)
    .SelectMany(para => para.Words)
    .Select(w => new { w.Text, w.X });

Imports System.Xml.Linq
Imports IronOcr

' Asprise XML parsing (remove)
Dim words = XDocument.Parse(xmlOutput) _
    .Descendants("word") _
    .Select(Function(w) New With {Key .Text = CType(w.Attribute("text"), String), Key .X = CType(w.Attribute("x"), Integer)})

' IronOCR object model (replace with)
Dim result = New IronTesseract().Read(imagePath)
Dim words = result.Pages _
    .SelectMany(Function(p) p.Paragraphs) _
    .SelectMany(Function(para) para.Words) _
    .Select(Function(w) New With {w.Text, w.X})

// Remove: await Task.Run(() => { ocr.Recognize(...) });

// Replace with:
using var input = new OcrInput();
input.LoadImage(stream);
var result = await new IronTesseract().ReadAsync(input);
return result.Text;

Imports IronTesseract

Using input As New OcrInput()
    input.LoadImage(stream)
    Dim result = Await (New IronTesseract()).ReadAsync(input)
    Return result.Text
End Using

// Asprise string-based (remove)
string language = config["OcrLanguage"];  // e.g. "eng+fra"
ocr.StartEngine(language, Ocr.SPEED_FAST);

//IronOCRenum-based (replace with)
// For single language from config:
var ocr = new IronTesseract();
ocr.Language = Enum.Parse<OcrLanguage>(config["OcrLanguage"]);  // e.g. "English"
var result = ocr.Read(input);

' Asprise string-based (remove)
Dim language As String = config("OcrLanguage")  ' e.g. "eng+fra"
ocr.StartEngine(language, Ocr.SPEED_FAST)

' IronOCRenum-based (replace with)
' For single language from config:
Dim ocr As New IronTesseract()
ocr.Language = [Enum].Parse(Of OcrLanguage)(config("OcrLanguage"))  ' e.g. "English"
Dim result = ocr.Read(input)

// Remove: SemaphoreSlim _ocrLock = new SemaphoreSlim(1, 1);
// Remove: await _ocrLock.WaitAsync(); ... _ocrLock.Release();

// IronOCR: direct concurrent access, no guards needed
Parallel.ForEach(documentPaths, path =>
{
    var text = new IronTesseract().Read(path).Text;
    results[path] = text;
});

Imports System.Threading.Tasks

' IronOCR: direct concurrent access, no guards needed
Parallel.ForEach(documentPaths, Sub(path)
    Dim text = (New IronTesseract()).Read(path).Text
    results(path) = text
End Sub)

# Find all files importing asprise namespace
grep -rn "using asprise" --include="*.cs" .

# Find all engine lifecycle calls
grep -rn "SetUp\|StartEngine\|StopEngine" --include="*.cs" .

# Find all integer constant references
grep -rn "RECOGNIZE_TYPE\|OUTPUT_FORMAT\|SPEED_FAST\|SPEED_SLOW" --include="*.cs" .

# Find native binary references in project files and deployment scripts
grep -rn "aocr\|libaocr" --include="*.csproj" --include="Dockerfile" --include="*.yml" .

# Find XML output parsing code
grep -rn "OUTPUT_FORMAT_XML\|XDocument.Parse\|Descendants.*word" --include="*.cs" .

# Find Task.Run wrappers around OCR calls
grep -rn "Task.Run.*ocr\|Task.Run.*Recognize" --include="*.cs" .