deva2han.cs

using System;
using System.Collections;
using System.IO;
using System.Text;
using System.Text.RegularExpressions;

namespace CST.Conversion
{
    class Deva2Han
    {
        static void Main(string[] args)
        {
            try
            {
                if (args.Length < 2)
                {
                    PrintUsage();
                    return;
                }

                FileInfo fi = new FileInfo(args[0]);
                if (!fi.Exists)
                {
                    Console.WriteLine("Input file does not exist.");
                    return;
                }

                DirectoryInfo di = new DirectoryInfo(args[1]);
                if (!di.Exists) di.Create();

                Deva2Han d2h = new Deva2Han();
                d2h.InputFilePath = args[0];
                d2h.OutputFilePath = Path.Combine(di.FullName, fi.Name);
                
                d2h.ConvertFile();
                Console.WriteLine("Transliteration to Hanzi (Sino-Pali) Complete: " + d2h.OutputFilePath);
            }
            catch (Exception ex)
            {
                Console.WriteLine("Error: " + ex.Message);
            }
        }

        static void PrintUsage()
        {
            Console.WriteLine("Transliterates Unicode Devanagari to Unicode Chinese (Mahayana Standard)");
            Console.WriteLine("Syntax: deva2han <inputfile> <outputdirectory>");
        }

        private Hashtable deva2Han;

        public Deva2Han()
        {
            deva2Han = new Hashtable();

            // === VOWELS (Independent & Dependent) ===
            deva2Han['\x0905'] = "阿"; // a
            deva2Han['\x0906'] = "阿"; // aa
            deva2Han['\x0907'] = "伊"; // i
            deva2Han['\x0908'] = "伊"; // ii
            deva2Han['\x0909'] = "優"; // u
            deva2Han['\x090A'] = "優"; // uu
            deva2Han['\x090F'] = "翳"; // e
            deva2Han['\x0913'] = "摩"; // o (Namo -> 那摩)

            deva2Han['\x093E'] = "";   // aa sign
            deva2Han['\x093F'] = "伊"; // i sign
            deva2Han['\x0940'] = "伊"; // ii sign
            deva2Han['\x0941'] = "優"; // u sign
            deva2Han['\x0942'] = "優"; // uu sign
            deva2Han['\x0947'] = "翳"; // e sign
            deva2Han['\x094B'] = "摩"; // o sign

            // === CONSONANTS ===
            deva2Han['\x0915'] = "迦"; // ka
            deva2Han['\x0916'] = "佉"; // kha
            deva2Han['\x0917'] = "伽"; // ga
            deva2Han['\x0918'] = "伽"; // gha
            deva2Han['\x0919'] = "哦"; // nga

            deva2Han['\x091A'] = "遮"; // ca
            deva2Han['\x091B'] = "車"; // cha
            deva2Han['\x091C'] = "闍"; // ja
            deva2Han['\x091D'] = "闍"; // jha
            deva2Han['\x091E'] = "若"; // nya

            deva2Han['\x091F'] = "吒"; // Ta
            deva2Han['\x0920'] = "他"; // Tha
            deva2Han['\x0921'] = "茶"; // Da
            deva2Han['\x0922'] = "荼"; // Dha
            deva2Han['\x0923'] = "拏"; // Na

            deva2Han['\x0924'] = "多"; // ta
            deva2Han['\x0925'] = "他"; // tha
            deva2Han['\x0926'] = "陀"; // da
            deva2Han['\x0927'] = "馱"; // dha
            deva2Han['\x0928'] = "那"; // na

            deva2Han['\x092A'] = "波"; // pa
            deva2Han['\x092B'] = "頗"; // pha
            deva2Han['\x092C'] = "婆"; // ba
            deva2Han['\x092D'] = "梵"; // bha
            deva2Han['\x092E'] = "摩"; // ma

            deva2Han['\x092F'] = "也"; // ya
            deva2Han['\x0930'] = "羅"; // ra
            deva2Han['\x0932'] = "羅"; // la
            deva2Han['\x0935'] = "縛"; // va
            deva2Han['\x0938'] = "薩"; // sa
            deva2Han['\x0939'] = "訶"; // ha

            // === SPECIAL & PUNCTUATION ===
            deva2Han['\x0902'] = "南"; // Anusvara (ใช้ 南 เพื่อเสียงปิดปากในพยางค์ท้าย)
            deva2Han['\x094D'] = "";   // Virama
            deva2Han['a'] = "";        // Inherent a
            deva2Han['\x0964'] = "。"; // Danda
            deva2Han['\x0965'] = "॥"; // Double Danda
            deva2Han['\x0970'] = ".";
        }

        public string InputFilePath { get; set; }
        public string OutputFilePath { get; set; }

        public void ConvertFile()
        {
            string devStr = File.ReadAllText(InputFilePath, Encoding.UTF8);

            // Change Stylesheet link
            devStr = devStr.Replace("tipitaka-deva.xsl", "tipitaka-han.xsl");

            // XML Tag Protection: แยกประมวลผลเฉพาะ Text ระหว่าง Tag
            string processedStr = Regex.Replace(devStr, "(<[^>]+>)|([^<]+)", m =>
            {
                if (m.Groups[1].Success) return m.Groups[1].Value;
                return ConvertText(m.Groups[2].Value);
            });

            File.WriteAllText(OutputFilePath, processedStr, Encoding.UTF8);
        }

        private string ConvertText(string text)
        {
            if (string.IsNullOrEmpty(text)) return text;

            // 1. จัดการตัวสะกดซ้อน (Double Consonants) เช่น ss -> s
            // ในอักษรจีนนิยมแทนเสียงพยัญชนะซ้อนด้วยอักษรตัวเดียวเพื่อความกระชับ
            text = Regex.Replace(text, "([\x0915-\x0939])\x094D\\1", "$1");

            // 2. เติมสระ 'a' หลังพยัญชนะเดี่ยว (Alphabetization)
            text = Regex.Replace(text, "([\x0915-\x0939])([^\x093E-\x094Da])", "$1a$2");
            text = Regex.Replace(text, "([\x0915-\x0939])([^\x093E-\x094Da])", "$1a$2");

            StringBuilder sb = new StringBuilder();
            foreach (char c in text)
            {
                if (deva2Han.ContainsKey(c))
                    sb.Append(deva2Han[c]);
                else
                    sb.Append(c);
            }

            return sb.ToString();
        }
    }
}