utf8Generator.bsh

import java.util.Date;
import java.util.zip.*;
import java.io.*;
import java.lang.*;

//http://www.unicode.org/charts/
//CJK Radicals Supplement : 2E80 - 2EFF (11904 - 12031) ---------
//Ideographic descriptopn characters : 2FF0 - 2FFF (12272 - 12287) ---------
//CJK Strokes : 31C0 - 31EF (12736 - 12783) ---------
//CJK Compatibility (3300–33FF) (13056 - 13311) ---------
//CJK Extension A : 3400 - 4DBF (13312 - 19903 ) 6582 characters ---------
//CJK Unified Ideographs : 4E00 – 9FFF (19968 - 40959) 20902 characters ---------
//CJK Compatibility Ideographs (F900–FAFF) (63744 - 64255) ---------
//CJK Compatibility Forms (FE30–FE4F) (65072 - 65103) ---------
		//----------------------------------------------------------------------3 Bytes ends here
		//----------------------------------------------------------------------BMP ENDS HERE
//CJK Extension B : 20000 - 2A6DF (131072 - 173791) (4 Bytes) SMP 42711 characters ---------
//CJK Extension C : 2A700 - 2B73F (173824 - 177983) (4 Bytes) SMP 4149 characters ---------
//CJK Extension D : 2B740 - 2B81F (177984 - 178207) (4 Bytes) SMP 222 characters ---------
//CJK Compatibility ideographs Supplement : 2F800 - 2FA1F (194560 - 195103) ---------
		

try{
		BIGGEST_REPRESENTABLE_CODEPOINT = 0x10fff; //this is the hex for the numeric 1114111 i.e. the codePoints in unicode
		//Scanner input = new Scanner(System.in);
		//System.out.println("Enter in decimal code point : ");
		//String codePointStr = input.nextLine();
		//int codePoint=Integer.parseInt(codePointStr);
		for(i=1;i<195103;i++){
			int codePoint=i;
			boolean isValidcp;
			isValidcp = Character.isValidCodePoint(codePoint);
			String s = new String(Integer.toHexString(codePoint));
			FileOutputStream fos = new FileOutputStream("Hello_UTF8.txt", true);
			PrintStream out = new PrintStream(fos,true,"UTF-8");
			//PrintStream out = new PrintStream("Hello.txt","UTF-16");
			System.setOut(out);
			if ( codePoint <= 0xffff ) //Characters from 0x"0000 to 0xFFFF are part of the BMP i.e. 65536 characters
			{
				if ((Character.isDefined(codePoint)==true) && ((codePoint>=0x2e80 && codePoint<=0x2eff) || (codePoint>=0x2ff0 && codePoint<=0x2fff) || (codePoint>=0x31C0 && codePoint<=0x31EF) || (codePoint>=0x3300 && codePoint<=0x33FF) || (codePoint>=0x3400 && codePoint<=0x4DBF) || (codePoint>=0x4E00 && codePoint<=0x9FFF) || (codePoint>=0xF900 && codePoint<=0xFAFF) || (codePoint>=0xFE30 && codePoint<=0xFE4F)))
				{
					char[] ch = Character.toChars(codePoint); // This will store into the char[] UTF-16 representation of the codePoint
					//System.out.println("CodePoint: "+ codePoint + " Length: " + ch.length + " Charcter in HEX: 0x" + s + " Character: " + new String(ch));
					System.out.println("CodePoint: "+ codePoint + " Is defined: " + Character.isDefined(codePoint) + " Is Valid: " + isValidcp + " Character: " + new String(ch));
				}
			}
			else{
				if ((Character.isDefined(codePoint)==true) && ((codePoint>=0x20000 && codePoint<=0x2A6DF) || (codePoint>=0x2A700 && codePoint<=0x2B73F) || (codePoint>=0x2B740 && codePoint<=0x2B81F) || (codePoint>=0x2F800 && codePoint<=0x2FA1F)))
				{	
					StringBuilder sb = new StringBuilder();
					final int extract = codePoint - 0x10000;
					// strip out the high 10 bits and embed in high surrogate range.
					final int high = ( extract >>> 10 ) + 0xd800;
					// strip out the lowe 10 bits and embd in low  surrogate range.
					final int low = ( extract & 0x3ff ) + 0xdc00;
					// emit the surrogate pair in big endian order.
					sb.append( ( char ) high );
					sb.append( ( char ) low );
					System.out.println("CodePoint: "+ codePoint + " Is defined: " + Character.isDefined(codePoint) + " Is Valid: " + isValidcp + " Character: " + new String(sb));
				}
			}
		}
}

catch (FileNotFoundException e){
	System.out.println("File Not Found" + e);	
}
catch(java.io.UnsupportedEncodingException ex) {
     System.out.println("UnsupportedEncodingException" + e);
 } catch (java.util.zip.DataFormatException ex) {
     System.out.println("DataFormatException" + e);
}