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

OCR/.NET MVC/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 MVC/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 = 17.14.36616.10 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", "{40EBF01A-F47E-433F-9C5F-1E118D6BE123}"
+EndProject
+Global
+	GlobalSection(SolutionConfigurationPlatforms) = preSolution
+		Debug|Any CPU = Debug|Any CPU
+		Release|Any CPU = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(ProjectConfigurationPlatforms) = postSolution
+		{40EBF01A-F47E-433F-9C5F-1E118D6BE123}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{40EBF01A-F47E-433F-9C5F-1E118D6BE123}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{40EBF01A-F47E-433F-9C5F-1E118D6BE123}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{40EBF01A-F47E-433F-9C5F-1E118D6BE123}.Release|Any CPU.Build.0 = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(SolutionProperties) = preSolution
+		HideSolutionNode = FALSE
+	EndGlobalSection
+	GlobalSection(ExtensibilityGlobals) = postSolution
+		SolutionGuid = {82BE2249-6CF6-4098-8CFB-FE96ABAEE376}
+	EndGlobalSection
+EndGlobal

OCR/.NET MVC/OCR-with-Tesseract-in-Docker-on-Linux/OCR-with-Tesseract-in-Docker-on-Linux/Controllers/HomeController.cs

@@ -0,0 +1,184 @@
+using Microsoft.AspNetCore.Mvc;
+using OCR_with_Tesseract_in_Docker_on_Linux.Models;
+using Syncfusion.Drawing;
+using Syncfusion.OCRProcessor;
+using Syncfusion.Pdf.Graphics;
+using Syncfusion.Pdf.Parsing;
+using System.Diagnostics;
+using System.Xml.Linq;
+
+namespace OCR_with_Tesseract_in_Docker_on_Linux.Controllers
+{
+    public class HomeController : Controller
+    {
+        private readonly ILogger<HomeController> _logger;
+
+        public HomeController(ILogger<HomeController> logger)
+        {
+            _logger = logger;
+        }
+
+        public IActionResult Index()
+        {
+            return View();
+        }
+
+        public IActionResult Privacy()
+        {
+            return View();
+        }
+        public IActionResult PerformOCR()
+        {
+            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();
+                    //Set the position as '0'
+                    stream.Position = 0;
+                    //Download the PDF document in the browser
+                    FileStreamResult fileStreamResult = new FileStreamResult(stream, "application/pdf");
+                    fileStreamResult.FileDownloadName = "Sample.pdf";
+                    return fileStreamResult;
+                }
+            }
+
+        }
+        [ResponseCache(Duration = 0, Location = ResponseCacheLocation.None, NoStore = true)]
+        public IActionResult Error()
+        {
+            return View(new ErrorViewModel { RequestId = Activity.Current?.Id ?? HttpContext.TraceIdentifier });
+        }
+    }
+    // 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 (MemoryStream tempMemStream = new MemoryStream())
+            {
+                stream.CopyTo(tempMemStream);
+                tempMemStream.Position = 0;
+                PdfTiffImage 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 (FileStream tempFileStream = new FileStream(tempImageFile, FileMode.Create, FileAccess.Write))
+            {
+                stream.Position = 0;
+                stream.CopyTo(tempFileStream);
+            }
+
+            ProcessStartInfo startInfo = new ProcessStartInfo
+            {
+                FileName = "tesseract",
+                Arguments = $"\"{tempImageFile}\" \"{tempImageFile}\" -l eng hocr",
+                RedirectStandardError = true,
+                UseShellExecute = false,
+                CreateNoWindow = true
+            };
+
+            string hocrText = null;
+            using (Process process = new Process { StartInfo = startInfo })
+            {
+                process.Start();
+                string errorOutput = process.StandardError.ReadToEnd();
+                process.WaitForExit();
+
+                if (process.ExitCode != 0)
+                    throw new Exception($"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 MVC/OCR-with-Tesseract-in-Docker-on-Linux/OCR-with-Tesseract-in-Docker-on-Linux/Dockerfile

@@ -0,0 +1,30 @@
+# 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 MVC/OCR-with-Tesseract-in-Docker-on-Linux/OCR-with-Tesseract-in-Docker-on-Linux/Models/ErrorViewModel.cs

@@ -0,0 +1,9 @@
+namespace OCR_with_Tesseract_in_Docker_on_Linux.Models
+{
+    public class ErrorViewModel
+    {
+        public string? RequestId { get; set; }
+
+        public bool ShowRequestId => !string.IsNullOrEmpty(RequestId);
+    }
+}

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

@@ -0,0 +1,17 @@
+<Project Sdk="Microsoft.NET.Sdk.Web">
+
+  <PropertyGroup>
+    <TargetFramework>net8.0</TargetFramework>
+    <Nullable>enable</Nullable>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <RootNamespace>OCR_with_Tesseract_in_Docker_on_Linux</RootNamespace>
+    <UserSecretsId>16743565-eaf2-4e18-8eb6-e6ba08388c1f</UserSecretsId>
+    <DockerDefaultTargetOS>Linux</DockerDefaultTargetOS>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Microsoft.VisualStudio.Azure.Containers.Tools.Targets" Version="1.22.1" />
+    <PackageReference Include="Syncfusion.PDF.OCR.Net.Core" Version="31.2.3" />
+  </ItemGroup>
+
+</Project>

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

@@ -0,0 +1,9 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="Current" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+  <PropertyGroup>
+    <ActiveDebugProfile>IIS Express</ActiveDebugProfile>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|AnyCPU'">
+    <DebuggerFlavor>ProjectDebugger</DebuggerFlavor>
+  </PropertyGroup>
+</Project>

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

@@ -0,0 +1,27 @@
+var builder = WebApplication.CreateBuilder(args);
+
+// Add services to the container.
+builder.Services.AddControllersWithViews();
+
+var app = builder.Build();
+
+// Configure the HTTP request pipeline.
+if (!app.Environment.IsDevelopment())
+{
+    app.UseExceptionHandler("/Home/Error");
+    // The default HSTS value is 30 days. You may want to change this for production scenarios, see https://aka.ms/aspnetcore-hsts.
+    app.UseHsts();
+}
+
+app.UseHttpsRedirection();
+app.UseStaticFiles();
+
+app.UseRouting();
+
+app.UseAuthorization();
+
+app.MapControllerRoute(
+    name: "default",
+    pattern: "{controller=Home}/{action=Index}/{id?}");
+
+app.Run();

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

@@ -0,0 +1,49 @@
+{
+  "profiles": {
+    "http": {
+      "commandName": "Project",
+      "launchBrowser": true,
+      "environmentVariables": {
+        "ASPNETCORE_ENVIRONMENT": "Development"
+      },
+      "dotnetRunMessages": true,
+      "applicationUrl": "http://localhost:5294"
+    },
+    "https": {
+      "commandName": "Project",
+      "launchBrowser": true,
+      "environmentVariables": {
+        "ASPNETCORE_ENVIRONMENT": "Development"
+      },
+      "dotnetRunMessages": true,
+      "applicationUrl": "https://localhost:7239;http://localhost:5294"
+    },
+    "IIS Express": {
+      "commandName": "IISExpress",
+      "launchBrowser": true,
+      "environmentVariables": {
+        "ASPNETCORE_ENVIRONMENT": "Development"
+      }
+    },
+    "Container (Dockerfile)": {
+      "commandName": "Docker",
+      "launchBrowser": true,
+      "launchUrl": "{Scheme}://{ServiceHost}:{ServicePort}",
+      "environmentVariables": {
+        "ASPNETCORE_HTTPS_PORTS": "8081",
+        "ASPNETCORE_HTTP_PORTS": "8080"
+      },
+      "publishAllPorts": true,
+      "useSSL": true
+    }
+  },
+  "$schema": "http://json.schemastore.org/launchsettings.json",
+  "iisSettings": {
+    "windowsAuthentication": false,
+    "anonymousAuthentication": true,
+    "iisExpress": {
+      "applicationUrl": "http://localhost:25397",
+      "sslPort": 44375
+    }
+  }
+}