980096: Offline Text Extraction from Scanned PDFs Using Tesseract 5 and Syncfusion

OCR/.NET/OCR-with-Tesseract-in-Docker-on-Linux/.dockerignore

@@ -0,0 +1,30 @@
+**/.classpath
+**/.dockerignore
+**/.env
+**/.git
+**/.gitignore
+**/.project
+**/.settings
+**/.toolstarget
+**/.vs
+**/.vscode
+**/*.*proj.user
+**/*.dbmdl
+**/*.jfm
+**/azds.yaml
+**/bin
+**/charts
+**/docker-compose*
+**/Dockerfile*
+**/node_modules
+**/npm-debug.log
+**/obj
+**/secrets.dev.yaml
+**/values.dev.yaml
+LICENSE
+README.md
+!**/.gitignore
+!.git/HEAD
+!.git/config
+!.git/packed-refs
+!.git/refs/heads/**

OCR/.NET/OCR-with-Tesseract-in-Docker-on-Linux/OCR-with-Tesseract-in-Docker-on-Linux.sln

@@ -0,0 +1,25 @@
+
+Microsoft Visual Studio Solution File, Format Version 12.00
+# Visual Studio Version 17
+VisualStudioVersion = 17.14.36408.4 d17.14
+MinimumVisualStudioVersion = 10.0.40219.1
+Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "OCR-with-Tesseract-in-Docker-on-Linux", "OCR-with-Tesseract-in-Docker-on-Linux\OCR-with-Tesseract-in-Docker-on-Linux.csproj", "{92C3B623-ED53-4127-8161-975BCD7AA532}"
+EndProject
+Global
+	GlobalSection(SolutionConfigurationPlatforms) = preSolution
+		Debug|Any CPU = Debug|Any CPU
+		Release|Any CPU = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(ProjectConfigurationPlatforms) = postSolution
+		{92C3B623-ED53-4127-8161-975BCD7AA532}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{92C3B623-ED53-4127-8161-975BCD7AA532}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{92C3B623-ED53-4127-8161-975BCD7AA532}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{92C3B623-ED53-4127-8161-975BCD7AA532}.Release|Any CPU.Build.0 = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(SolutionProperties) = preSolution
+		HideSolutionNode = FALSE
+	EndGlobalSection
+	GlobalSection(ExtensibilityGlobals) = postSolution
+		SolutionGuid = {BEF3B3F0-759C-4D53-BF94-8EB1E0E7D2FE}
+	EndGlobalSection
+EndGlobal

OCR/.NET/OCR-with-Tesseract-in-Docker-on-Linux/OCR-with-Tesseract-in-Docker-on-Linux/Dockerfile

@@ -0,0 +1,29 @@
+# See https://aka.ms/customizecontainer to learn how to customize your debug container and how Visual Studio uses this Dockerfile to build your images for faster debugging.
+
+# This stage is used when running from VS in fast mode (Default for Debug configuration)
+FROM mcr.microsoft.com/dotnet/runtime:8.0 AS 
+RUN apt-get update && apt-get install -y tesseract-ocr
+USER $APP_UID
+WORKDIR /app
+
+
+# This stage is used to build the service project
+FROM mcr.microsoft.com/dotnet/sdk:8.0 AS build
+ARG BUILD_CONFIGURATION=Release
+WORKDIR /src
+COPY ["OCR-with-Tesseract-in-Docker-on-Linux/OCR-with-Tesseract-in-Docker-on-Linux.csproj", "OCR-with-Tesseract-in-Docker-on-Linux/"]
+RUN dotnet restore "./OCR-with-Tesseract-in-Docker-on-Linux/OCR-with-Tesseract-in-Docker-on-Linux.csproj"
+COPY . .
+WORKDIR "/src/OCR-with-Tesseract-in-Docker-on-Linux"
+RUN dotnet build "./OCR-with-Tesseract-in-Docker-on-Linux.csproj" -c $BUILD_CONFIGURATION -o /app/build
+
+# This stage is used to publish the service project to be copied to the final stage
+FROM build AS publish
+ARG BUILD_CONFIGURATION=Release
+RUN dotnet publish "./OCR-with-Tesseract-in-Docker-on-Linux.csproj" -c $BUILD_CONFIGURATION -o /app/publish /p:UseAppHost=false
+
+# This stage is used in production or when running from VS in regular mode (Default when not using the Debug configuration)
+FROM base AS final
+WORKDIR /app
+COPY --from=publish /app/publish .
+ENTRYPOINT ["dotnet", "OCR-with-Tesseract-in-Docker-on-Linux.dll"]

OCR/.NET/OCR-with-Tesseract-in-Docker-on-Linux/OCR-with-Tesseract-in-Docker-on-Linux/OCR-with-Tesseract-in-Docker-on-Linux.csproj

@@ -0,0 +1,24 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>net8.0</TargetFramework>
+    <RootNamespace>OCR-with-Tesseract-in-Docker-on-Linux</RootNamespace>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <Nullable>enable</Nullable>
+    <DockerDefaultTargetOS>Linux</DockerDefaultTargetOS>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Microsoft.VisualStudio.Azure.Containers.Tools.Targets" Version="1.22.1" />
+    <PackageReference Include="SkiaSharp.NativeAssets.Linux.NoDependencies" Version="*" />
+    <PackageReference Include="Syncfusion.PDF.OCR.Net.Core" Version="*" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <None Update="Data\Input.pdf">
+      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
+    </None>
+  </ItemGroup>
+
+</Project>

OCR/.NET/OCR-with-Tesseract-in-Docker-on-Linux/OCR-with-Tesseract-in-Docker-on-Linux/OCR-with-Tesseract-in-Docker-on-Linux.user

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="Current" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+  <PropertyGroup>
+    <ActiveDebugProfile>Container (Dockerfile)</ActiveDebugProfile>
+  </PropertyGroup>
+</Project>

OCR/.NET/OCR-with-Tesseract-in-Docker-on-Linux/OCR-with-Tesseract-in-Docker-on-Linux/Program.cs

@@ -0,0 +1,154 @@
+using Syncfusion.Drawing;
+using Syncfusion.OCRProcessor;
+using Syncfusion.Pdf;
+using Syncfusion.Pdf.Graphics;
+using Syncfusion.Pdf.Parsing;
+using System.Diagnostics;
+using System.Xml.Linq;
+
+// Main application logic
+class Program
+{
+    static void Main(string[] args)
+    {
+        string docPath = Path.GetFullPath(@"Data/Input.pdf");
+        //Initialize the OCR processor.
+        using (OCRProcessor processor = new OCRProcessor())
+        {
+            FileStream fileStream = new FileStream(docPath, FileMode.Open, FileAccess.Read);
+            //Load a PDF document
+            PdfLoadedDocument lDoc = new PdfLoadedDocument(fileStream);
+            //Set OCR language to process
+            processor.Settings.Language = Languages.English;
+            IOcrEngine tesseractEngine = new Tesseract5OCREngine();
+            processor.ExternalEngine = tesseractEngine;
+            //Process OCR by providing the PDF document.
+            processor.PerformOCR(lDoc);
+            //Create memory stream
+            using (MemoryStream stream = new MemoryStream())
+            {
+                //Save the document to memory stream
+                lDoc.Save(stream);
+                lDoc.Close();
+            }
+        }
+    }
+}
+
+// Tesseract5OcrEngine implementation
+class Tesseract5OCREngine : IOcrEngine
+{
+    private float imageHeight;
+    private float imageWidth;
+
+    public OCRLayoutResult PerformOCR(Stream stream)
+    {
+        if (stream == null || !stream.CanRead)
+            throw new ArgumentException("Input stream is null or not readable for OCR.", nameof(stream));
+
+        stream.Position = 0;
+
+        using (var tempMemStream = new MemoryStream())
+        {
+            stream.CopyTo(tempMemStream);
+            tempMemStream.Position = 0;
+            var pdfTiffImage = new PdfTiffImage(tempMemStream);
+            imageHeight = pdfTiffImage.Height;
+            imageWidth = pdfTiffImage.Width;
+        }
+
+        string tempImageFile = Path.GetTempFileName();
+        string tempHocrFile = tempImageFile + ".hocr";
+
+        // Write stream to temp image file
+        using (var tempFileStream = new FileStream(tempImageFile, FileMode.Create, FileAccess.Write))
+        {
+            stream.Position = 0;
+            stream.CopyTo(tempFileStream);
+        }
+
+        var startInfo = new ProcessStartInfo
+        {
+            FileName = "tesseract",
+            Arguments = $"\"{tempImageFile}\" \"{tempImageFile}\" -l eng hocr",
+            RedirectStandardError = true,
+            UseShellExecute = false,
+            CreateNoWindow = true
+        };
+
+        string hocrText = null;
+        using (var process = new Process { StartInfo = startInfo })
+        {
+            process.Start();
+            string errorOutput = process.StandardError.ReadToEnd();
+            process.WaitForExit();
+
+            if (process.ExitCode != 0)
+                throw new Exception($"Tesseract process failed with exit code {process.ExitCode}. Error: {errorOutput}");
+
+            if (!File.Exists(tempHocrFile))
+                throw new Exception("HOCR output file not found. Tesseract might have failed or not produced output.");
+
+            hocrText = File.ReadAllText(tempHocrFile);
+        }
+
+        // Clean up temp files
+        if (File.Exists(tempImageFile)) File.Delete(tempImageFile);
+        if (File.Exists(tempHocrFile)) File.Delete(tempHocrFile);
+
+        if (string.IsNullOrEmpty(hocrText))
+            throw new Exception("HOCR text could not be generated or was empty.");
+
+        var ocrLayoutResult = new OCRLayoutResult();
+        BuildOCRLayoutResult(ocrLayoutResult, hocrText, imageWidth, imageHeight);
+        ocrLayoutResult.ImageWidth = imageWidth;
+        ocrLayoutResult.ImageHeight = imageHeight;
+
+        return ocrLayoutResult;
+    }
+
+    void BuildOCRLayoutResult(OCRLayoutResult ocr, string hOcrText, float imageWidth, float imageHeight)
+    {
+        var doc = XDocument.Parse(hOcrText, LoadOptions.None);
+        var ns = "http://www.w3.org/1999/xhtml";
+
+        foreach (var pageElement in doc.Descendants(ns + "div").Where(d => d.Attribute("class")?.Value == "ocr_page"))
+        {
+            Page ocrPage = new Page();
+
+            foreach (var lineElement in pageElement.Descendants(ns + "span")
+                .Where(s => s.Attribute("class")?.Value == "ocr_line" || s.Attribute("class")?.Value == "ocr_header"))
+            {
+                Line ocrLine = new Line();
+
+                foreach (var wordElement in lineElement.Descendants(ns + "span")
+                    .Where(s => s.Attribute("class")?.Value == "ocrx_word"))
+                {
+                    Word ocrWord = new Word { Text = wordElement.Value };
+                    String title = wordElement.Attribute("title")?.Value;
+
+                    if (title != null)
+                    {
+                        String bboxString = title.Split(';')[0].Replace("bbox", "").Trim();
+                        int[] coords = bboxString.Split(' ', StringSplitOptions.RemoveEmptyEntries).Select(int.Parse).ToArray();
+
+                        if (coords.Length == 4)
+                        {
+                            float x = coords[0];
+                            float y = coords[1];
+                            float width = coords[2] - coords[0];
+                            float height = coords[3] - coords[1];
+                            ocrWord.Rectangle = new RectangleF(x, y, width, height);
+                        }
+                    }
+
+                    ocrLine.Add(ocrWord);
+                }
+
+                ocrPage.Add(ocrLine);
+            }
+
+            ocr.Add(ocrPage);
+        }
+    }
+}

OCR/.NET/OCR-with-Tesseract-in-Docker-on-Linux/OCR-with-Tesseract-in-Docker-on-Linux/Properties/launchSettings.json

@@ -0,0 +1,10 @@
+{
+  "profiles": {
+    "OCR-with-Tesseract-in-Docker-on-Linux": {
+      "commandName": "Project"
+    },
+    "Container (Dockerfile)": {
+      "commandName": "Docker"
+    }
+  }
+}