Add multi-language support

.gitattributes

@@ -2,62 +2,4 @@
 # Set default behavior to automatically normalize line endings.
 ###############################################################################
 * text=auto
-
-###############################################################################
-# Set default behavior for command prompt diff.
-#
-# This is need for earlier builds of msysgit that does not have it on by
-# default for csharp files.
-# Note: This is only used by command line
-###############################################################################
-#*.cs     diff=csharp
-
-###############################################################################
-# Set the merge driver for project and solution files
-#
-# Merging from the command prompt will add diff markers to the files if there
-# are conflicts (Merging from VS is not affected by the settings below, in VS
-# the diff markers are never inserted). Diff markers may cause the following 
-# file extensions to fail to load in VS. An alternative would be to treat
-# these files as binary and thus will always conflict and require user
-# intervention with every merge. To do so, just uncomment the entries below
-###############################################################################
-#*.sln       merge=binary
-#*.csproj    merge=binary
-#*.vbproj    merge=binary
-#*.vcxproj   merge=binary
-#*.vcproj    merge=binary
-#*.dbproj    merge=binary
-#*.fsproj    merge=binary
-#*.lsproj    merge=binary
-#*.wixproj   merge=binary
-#*.modelproj merge=binary
-#*.sqlproj   merge=binary
-#*.wwaproj   merge=binary
-
-###############################################################################
-# behavior for image files
-#
-# image files are treated as binary by default.
-###############################################################################
-#*.jpg   binary
-#*.png   binary
-#*.gif   binary
-
-###############################################################################
-# diff behavior for common document formats
-# 
-# Convert binary document formats to text before diffing them. This feature
-# is only available from the command line. Turn it on by uncommenting the 
-# entries below.
-###############################################################################
-#*.doc   diff=astextplain
-#*.DOC   diff=astextplain
-#*.docx  diff=astextplain
-#*.DOCX  diff=astextplain
-#*.dot   diff=astextplain
-#*.DOT   diff=astextplain
-#*.pdf   diff=astextplain
-#*.PDF   diff=astextplain
-#*.rtf   diff=astextplain
-#*.RTF   diff=astextplain
+*.bat text eol=crlf

TestCharacterRanges.cs

@@ -0,0 +1,58 @@
+using System;
+using WFInfo.LanguageProcessing;
+using WFInfo.Settings;
+
+namespace WFInfo.Test
+{
+    /// <summary>
+    /// Simple test to verify character range generation works correctly
+    /// </summary>
+    public class TestCharacterRanges
+    {
+        public static void TestCharacterRanges()
+        {
+            Console.WriteLine("Testing character range generation...");
+
+            // Create a mock settings object
+            var settings = new TestApplicationSettings();
+
+            try
+            {
+                // Test Japanese processor
+                var japaneseProcessor = new JapaneseLanguageProcessor(settings);
+                var japaneseWhitelist = japaneseProcessor.CharacterWhitelist;
+                Console.WriteLine($"Japanese whitelist length: {japaneseWhitelist.Length}");
+
+                // Test Korean processor  
+                var koreanProcessor = new KoreanLanguageProcessor(settings);
+                var koreanWhitelist = koreanProcessor.CharacterWhitelist;
+                Console.WriteLine($"Korean whitelist length: {koreanWhitelist.Length}");
+
+                // Test Chinese processors
+                var simplifiedProcessor = new SimplifiedChineseLanguageProcessor(settings);
+                var simplifiedWhitelist = simplifiedProcessor.CharacterWhitelist;
+                Console.WriteLine($"Simplified Chinese whitelist length: {simplifiedWhitelist.Length}");
+
+                var traditionalProcessor = new TraditionalChineseLanguageProcessor(settings);
+                var traditionalWhitelist = traditionalProcessor.CharacterWhitelist;
+                Console.WriteLine($"Traditional Chinese whitelist length: {traditionalWhitelist.Length}");
+
+                Console.WriteLine("All character range tests passed!");
+            }
+            catch (Exception ex)
+            {
+                Console.WriteLine($"Error testing character ranges: {ex.Message}");
+                throw;
+            }
+        }
+    }
+
+    /// <summary>
+    /// Mock application settings for testing
+    /// </summary>
+    public class TestApplicationSettings : IReadOnlyApplicationSettings
+    {
+        public string Locale => "en";
+        // Add other required properties as needed
+    }
+}

WFInfo/CustomEntrypoint.cs

@@ -14,6 +14,7 @@
 using System.Linq;
 using System.CodeDom;
 using Tesseract;
+using WFInfo.Tests;
 
 namespace WFInfo
 {
@@ -83,6 +84,41 @@ public static void Main()
 
             Directory.CreateDirectory(appPath);
 
+            // Check for test execution arguments
+            // Usage: WFInfo.exe [--test] map.json [output.json]
+            string[] args = Environment.GetCommandLineArgs().Skip(1).ToArray();
+            bool isTestMode = false;
+
+            if (args.Length >= 1 && (args[0].Equals("--test", StringComparison.OrdinalIgnoreCase) ||
+                                     args[0].Equals("-test", StringComparison.OrdinalIgnoreCase) ||
+                                     args[0].Equals("--map", StringComparison.OrdinalIgnoreCase)))
+            {
+                isTestMode = true;
+                args = args.Skip(1).ToArray(); // strip flag
+            }
+            else if (args.Length >= 1 && args[0].EndsWith(".json", StringComparison.OrdinalIgnoreCase))
+            {
+                isTestMode = true;
+            }
+
+            if (isTestMode)
+            {
+                try
+                {
+                    Console.WriteLine("WFInfo OCR Test Runner");
+                    Console.WriteLine("=======================");
+                    TestProgram.RunTests(args).GetAwaiter().GetResult();
+                    return;
+                }
+                catch (Exception ex)
+                {
+                    Console.WriteLine($"Test execution failed: {ex.Message}");
+                    Console.WriteLine(ex.StackTrace);
+                    Environment.Exit(1);
+                    return;
+                }
+            }
+
             string thisprocessname = Process.GetCurrentProcess().ProcessName;
             string version = Assembly.GetExecutingAssembly().GetName().Version.ToString();
             if (Process.GetProcesses().Count(p => p.ProcessName == thisprocessname) > 1)