www.pudn.com > charsettools_1.0.2.zip > CharsetToolkit.java

/* 
Program  CharsetToolkit.java 
 * 
Author   Keiven Ju  
 * 
Created  2003-12-12 5:03:51 
 * 
Copyright 1995-1998,2000-2003 by AKuP International, Inc.,
 
 * 
Nanjing:
 
 * Unit C, 26F Jianjiang Culture Building, No. 89 Zhongshannan Rd. Nanjing 210005 China
 
 * 
 26F, Jianjiang Building No.89,Zhongshan South Rd, Nanjing 
 * 
Taipei :
 
 * 
5F, NO.6, Alley 36, Lane 26, Rueiguang Rd,  Neihu District, Taipei City 114, Taiwan (R.O.C) 
 * 
 
 * All rights reserved.
 
 * 
 
 * This software is the confidential and proprietary information
 
 * of AKuP International, Inc. ("Confidential Information").  You
 
 * shall not disclose such Confidential Information and shall use
 
 * it only in accordance with the terms of the license agreement
 
 * you entered into with AKuP.
 
 * 
 
 * E-mail keiven.ju@akup.com  for more information.  
 */ 
package com.akup.charset; 
 
import java.io.BufferedReader; 
import java.io.BufferedWriter; 
import java.io.ByteArrayOutputStream; 
import java.io.File; 
import java.io.FileInputStream; 
import java.io.FileOutputStream; 
import java.io.IOException; 
import java.io.InputStream; 
import java.io.InputStreamReader; 
import java.io.OutputStreamWriter; 
import java.io.StringReader; 
import java.io.UnsupportedEncodingException; 
import java.util.HashMap; 
 
/**  
 * program  CharsetToolkit 
 * @author  Keiven Ju  
 * @since   1.0.0  
 * @version 1.0.0  2003-12-12 5:03:51  
 */ 
public class CharsetToolkit extends Encoding { 
	/**	Simplfied-->Traditional character equivalence hashes*/ 
	private HashMap s2thash; 
	/**	 Traditional-->Simplfied character equivalence hashes*/ 
	private HashMap t2shash; 
	/**  
	 * Constructor  
	 * @since 1.0.0 2003-12-15 
	 */ 
	public CharsetToolkit() { 
		super(); 
		init(); 
	} 
	/** 
	 * init, 
	 * @since 1.0.0  2003-12-11  
	 */ 
	private void init() { 
		String dataline; 
		// Initialize and load in the simplified/traditional character hashses 
		s2thash = new HashMap(); 
		t2shash = new HashMap(); 
		try { 
			InputStream pydata = getClass().getResourceAsStream("hcutf8.txt"); 
			//System.out.println("pydata:" + pydata); 
			//pydata = new FileInputStream(new File("hcutf8.txt")); 
			BufferedReader in = new BufferedReader(new InputStreamReader(pydata, "UTF8")); 
			while ((dataline = in.readLine()) != null) { 
				// Skip empty and commented lines 
				if (dataline.length() == 0 || dataline.charAt(0) == '#') { 
					continue; 
				} 
				// Simplified to Traditional, (one to many, but pick only one) 
				s2thash.put(dataline.substring(0, 1).intern(), dataline.substring(1, 2)); 
				// Traditional to Simplified, (many to one) 
				for (int i = 1; i < dataline.length(); i++) { 
					t2shash.put(dataline.substring(i, i + 1).intern(), dataline.substring(0, 1)); 
				} 
			} 
		} catch (Exception e) { 
			e.printStackTrace(); 
			System.err.println(e); 
		} 
	} 
 
	/** 
	 * indexCharset,µÃµ½ÐòºÅ 
	 * @param charsetname 
	 * @return int 
	 * @since 1.0.0  2003-12-15  
	 */ 
	protected int indexCharset(String charsetname) { 
		int idx = -1; 
		for (int i = 0; i < Encoding.TOTALTYPES; i++) { 
			if (Encoding.nicename[i].equalsIgnoreCase(charsetname) || Encoding.javaname[i].equalsIgnoreCase(charsetname) || Encoding.htmlname[i].equalsIgnoreCase(charsetname)) { 
				return i; 
			} 
		} 
		return idx; 
	} 
	/** 
	 * convertFile,´ÓÎļ?жÁ³ö×Ö·û´® 
	 * @param strInFile 
	 * @param srccharset 
	 * @param strOutFile 
	 * @param trgcharset 
	 * @throws IOException 
	 * @since 1.0.0  2003-12-15  
	 */ 
	public void convertFile(String strInFile, String srccharset, String strOutFile, String trgcharset) throws IOException { 
		convertFile(new File(strInFile), srccharset, new File(strOutFile), trgcharset); 
	} 
 
	/** 
	 * convertFile, 
	 * @param strInFile 
	 * @param srccharset 
	 * @param strOutFile 
	 * @param trgcharset 
	 * @throws IOException 
	 * @since 1.0.0  2003-12-15  
	 */ 
	public void convertFile(File strInFile, String srccharset, File strOutFile, String trgcharset) throws IOException { 
		if (srccharset == null || trgcharset == null) 
			return; 
		int src_code = this.indexCharset(srccharset); 
		int trg_code = this.indexCharset(trgcharset); 
 
		if (src_code * trg_code < 0) { //ÓÐÕÒ²»µ½µÄ 
			System.err.println(src_code + " " + trg_code); 
			throw new UnsupportedEncodingException(srccharset + " or " + trgcharset); 
		} 
		InputStreamReader isr = new InputStreamReader(new FileInputStream(strInFile), srccharset); 
		BufferedReader in = new BufferedReader(isr); 
 
		OutputStreamWriter osw = new OutputStreamWriter(new FileOutputStream(strOutFile), trgcharset); 
		BufferedWriter out = new BufferedWriter(osw); 
 
		String strline = null; 
		StringBuffer buffer = new StringBuffer(); 
		while ((strline = in.readLine()) != null) { 
			this.myConvertString(strline, src_code, trg_code, trgcharset, buffer); 
			out.write(buffer.toString()); 
			out.newLine(); 
			out.flush(); 
			buffer.delete(0, buffer.length()); 
		} 
		in.close(); 
		out.close(); 
	} 
 
	/** 
	 * convertString, 
	 * @param instring 
	 * @param srccharset 
	 * @param trgcharset 
	 * @return String 
	 * @since 1.0.0  2003-12-15  
	 */ 
	public String convertString(String instring, String srccharset, String trgcharset) throws IOException { 
		StringBuffer sb = new StringBuffer(); 
		int src_code = this.indexCharset(srccharset); 
		int trg_code = this.indexCharset(trgcharset); 
		this.myConvertString(instring, src_code, trg_code, trgcharset, sb); 
		return sb.toString(); 
	} 
	private boolean useZhCode = false; 
	/** 
	 * convertString, 
	 * @param instring 
	 * @param srccharset 
	 * @param trgbuffer 
	 * @param trgcharset 
	 * @since 1.0.0  2003-12-15  
	 */ 
	private void myConvertString(String instring, int src_code, int trg_code, String trgcharset, StringBuffer trgbuffer) throws IOException { 
		if (useZhCode) { 
			this.convertStringZHcode(instring, src_code, trg_code, trgbuffer); 
		} else { 
			ByteArrayOutputStream fos = new ByteArrayOutputStream(); 
			OutputStreamWriter osw = new OutputStreamWriter(fos, trgcharset); 
			osw.write(instring); 
			osw.close(); //ʱ¼ä¿ÉÒÔ¼õÉÙÒ»°?	 
			String trgstr = fos.toString(trgcharset); 
			int len = trgstr.length(); 
			int ch; 
			//char[] chs = trgstr.toCharArray();//ƵÂʸßʱ£¬ÂÔÓп?
			for (int idx = 0; idx < len; idx++) { 
				ch = trgstr.charAt(idx); //Ê?ÝÉÙʱÓп?
				//ch = chs[idx]; 
				if (ch == 0x3F) { 
					this.convertStringZHcode(instring.substring(idx, idx + 1), src_code, trg_code, trgbuffer); 
				} else { 
					trgbuffer.append((char) ch); 
				} 
			} 
		} 
	} 
	/** 
	 * convertStringZHcode, 
	 * @param dataline 
	 * @param src_cod 
	 * @param trg_cod 
	 * @param outline 
	 * @since 1.0.0  2003-12-11  
	 */ 
	private void convertStringZHcode(String dataline, int src_cod, int trg_cod, StringBuffer outline) { 
		int lineindex; 
		for (lineindex = 0; lineindex < dataline.length(); lineindex++) { 
			if ((src_cod == GB2312 || src_cod == GBK || src_cod == ISO2022CN_GB || src_cod == UNICODE || src_cod == UNICODES || src_cod == UTF8) && (trg_cod == BIG5 || trg_cod == CNS11643 || trg_cod == UNICODET || trg_cod == ISO2022CN_CNS)) { 
				if (s2thash.containsKey(dataline.substring(lineindex, lineindex + 1)) == true) { 
					outline.append(s2thash.get(dataline.substring(lineindex, lineindex + 1).intern())); 
				} else { 
					outline.append(dataline.substring(lineindex, lineindex + 1)); 
				} 
			} else if ((src_cod == BIG5 || src_cod == CNS11643 || src_cod == UNICODET || src_cod == UTF8 || src_cod == ISO2022CN_CNS || src_cod == GBK || src_cod == UNICODE) && (trg_cod == GB2312 || trg_cod == UNICODES || trg_cod == ISO2022CN_GB)) { 
				if (t2shash.containsKey(dataline.substring(lineindex, lineindex + 1)) == true) { 
					outline.append(t2shash.get(dataline.substring(lineindex, lineindex + 1).intern())); 
				} else { 
					outline.append(dataline.substring(lineindex, lineindex + 1)); 
				} 
			} else { 
				outline.append(dataline.substring(lineindex, lineindex + 1)); 
			} 
		} 
	} 
	/** 
	 * compareprint, 
	 * @param src 
	 * @param trg 
	 * @since 1.0.0  2003-12-15  
	 */ 
	public static void compareString(String src, String trg) { 
		StringBuffer srcb = new StringBuffer(src); 
		StringBuffer trgb = new StringBuffer(trg); 
		int len = Math.min(srcb.length(), trgb.length()); 
		char srch, trgh; 
		System.out.println("-----------------------------------"); 
		System.out.println("src " + "  " + "int" + "  " + "int" + "  " + "trg" + "  " + " src-trg"); 
		System.out.println("-----------------------------------"); 
		for (int i = 0; i < len; i++) { 
			srch = srcb.charAt(i); 
			trgh = trgb.charAt(i); 
			System.out.println(srch + "  " + (int) srch + "  " + (int) trgh + "  " + trgh + "  " + ((int) srch - (int) trgh)); 
		} 
	} 
	/** 
	 * Method readInput ´ÓÎļ?жÁ³ö×Ö·û´® 
	 * @param strInFile  
	 * @return String 
	 */ 
	public static String readInput(String strInFile, String charset) throws IOException { 
		if (charset == null) 
			return null; 
		StringBuffer buffer = new StringBuffer(); 
 
		FileInputStream fis = new FileInputStream(strInFile); 
		InputStreamReader isr = new InputStreamReader(fis, charset); 
		BufferedReader in = new BufferedReader(isr); 
		int ch; 
		while ((ch = in.read()) > -1) { 
			buffer.append((char) ch); 
		} 
		in.close(); 
		return buffer.toString(); 
	} 
 
	/** 
	 * writeOutput,×Ö·û´®Êä³öΪtrgcharset±àÂ?ļ?£ 
	 * @param str ´?ä³ö×Ö·û´® 
	 * @param strOutFile Êä³öÎļ?
	 * @param trgcharset Êä³öÎļ?harset 
	 * @since 1.0.0  2003-12-15  
	 */ 
	public static void writeOutput(String str, String strOutFile, String trgcharset) { 
		try { 
			FileOutputStream fos = new FileOutputStream(strOutFile); 
			OutputStreamWriter out = new OutputStreamWriter(fos, trgcharset); 
			out.write(str); 
			out.close(); 
		} catch (IOException e) { 
			e.printStackTrace(); 
		} 
	} 
 
	/** 
	 * ÊäÈ?Ö·û´®Êä³?UnicodeÏÔʾ×Ö·û´®¡£ 
	 * Method toUnicode 
	 * @param instring  
	 * @return String 
	 */ 
	public static String toUnicode(String instring) { 
		String unicode = "\\u"; 
		StringBuffer out = new StringBuffer(); 
		try { 
			StringReader in = new StringReader(instring); 
			int ch; 
			while ((ch = in.read()) > -1) { 
				if (ch < 0x200) { 
					out.append((char) ch); 
				} else { 
					out.append(unicode); 
					out.append(Integer.toHexString(ch)); 
				} 
			} 
			in.close(); 
		} catch (IOException e) { 
			e.printStackTrace(); 
			return null; 
		} 
		return out.toString(); 
	} 
 
	/** 
	 * toIEUnicode,ÄÜÖ±½ÓÔÚIEÉÏÏÔʾµÄÍòÄܱàÂ?£ 
	 * @param instring 
	 * @return String 
	 * @since 1.0.0  2003-12-11  
	 */ 
	public static String toIEUnicode(String instring) { 
		String IEUnicode = "&#x"; 
		char IEUnicoded = ';'; 
		StringBuffer out = new StringBuffer(); 
		try { 
			StringReader in = new StringReader(instring); 
			String temp = null; 
			int ch; 
			while ((ch = in.read()) > -1) { 
				if (ch < 0x200) { 
					out.append((char) ch); 
				} else { 
					out.append(IEUnicode); 
					out.append(Integer.toHexString(ch)); 
					out.append(IEUnicoded); 
				} 
			} 
			in.close(); 
		} catch (IOException e) { 
			e.printStackTrace(); 
			return null; 
		} 
		return out.toString(); 
	} 
	/** 
	 * toFixCode, 
	 * @param srcstring 
	 * @param trgcharset 
	 * @return String 
	 * @since 1.0.0  2003-12-16  
	 */ 
	public static String toFixCode(String srcstring, String trgcharset) throws IOException { 
		StringBuffer trgbuffer = new StringBuffer(); 
		ByteArrayOutputStream fos = new ByteArrayOutputStream(); 
		OutputStreamWriter osw = new OutputStreamWriter(fos, trgcharset); 
		osw.write(srcstring); 
		osw.close(); 
		String trgstr = new String(fos.toString(trgcharset)); 
		int len = trgstr.length(); 
		int ch; 
		for (int index = 0; index < len; index++) { 
			ch = trgstr.charAt(index); 
			if (ch == 0x3F) { 
				trgbuffer.append(toIEUnicode(srcstring.substring(index, index + 1))); 
				//} else if (ch < 0x200) { 
				//		trgbuffer.append((char) ch); 
			} else { 
				trgbuffer.append((char) ch); 
			} 
		} 
		return trgbuffer.toString(); 
	} 
 
	/**Input chartset file, output Unicode file. 
	 * @param chartset 
	 * @param infile  
	 * @param outfile  
	 */ 
	public static void FiletoUnicode(String chartset, String infile, String outfile) throws IOException { 
		System.out.println("Input " + chartset + " file, output " + chartset + " file."); 
		String str = readInput(infile, chartset); 
		String strunicode = toUnicode(str); 
		writeOutput(strunicode, outfile, chartset); 
		System.out.println("All of Characters in file.ok."); 
	} 
 
	/** 
	 * FiletoIEUnicode,Input GB2312 file, output Unicode file. 
	 * @param chartset ÊäÈ?Ä×Ö·û¼¯ 
	 * @param infile 
	 * @param outfile	  
	 * @since 1.0.0  2003-12-15  
	 */ 
	public static void FiletoIEUnicode(String chartset, String infile, String outfile) throws IOException { 
		System.out.println("Input " + chartset + " file, output " + chartset + " file."); 
		String str = readInput(infile, chartset); 
		String strunicode = toUnicode(str); 
		writeOutput(strunicode, outfile, chartset); 
		System.out.println("All of Characters in file.ok."); 
	} 
	/** 
	 * isUseZhCode, 
	 * @return boolean 
	 * @since 1.0.0  2003-12-17  
	 */ 
	public boolean isUseZhCode() { 
		return useZhCode; 
	} 
	/** 
	 * setUseZhCode, 
	 * @param b 
	 * @since 1.0.0  2003-12-17  
	 */ 
	public void setUseZhCode(boolean b) { 
		useZhCode = b; 
	} 
	public static void main(String[] args) { 
		try { 
			CharsetToolkit ctk = new CharsetToolkit(); 
			String gbstring = "‚킽‚µ“c’†"; 
			gbstring = readInput("AA.txt", "GB2312"); 
			String bigstring = ctk.convertString(gbstring, "GB2312", "BIG5"); 
			bigstring = toFixCode(gbstring, "BIG5"); 
			writeOutput(bigstring, "BB.txt", "Big5"); 
			compareString(gbstring, bigstring); 
		} catch (IOException e) { 
			e.printStackTrace(); 
		} 
	} 
}