繁簡體(GBBig5)字串轉化的JAVA方式實現

Big5)字串轉化的JAVA方式實現" href="http://pingyuan.itpub.net/entry/19" rel="bookmark" snap_preview_added="no">繁簡體(GB<=>Big5)字串轉化的JAVA方式實現[@more@]本文提供一個java實現中文字元繁簡體互換的zip包以及主要的原始碼實現說明。

package zeal.util;
2
3	import java.io.*;
4
5	/**
6	* 用來處理GB2312/BIG5碼字元互相轉換的類.
7	* 需要兩個碼錶檔案:
8	* /zeal/util/gb-big5.table,/zeal/util/big5-gb.table.
9	* 這兩個碼錶可以根據具體情況補充對映不正確的碼.
10	* Title: GB<=>Big5
11	* Description: Deal with the convertion
12	* between gb2312 and big5 charset Strings.
13	* Copyright: Copyright (c) 2004
14	* Company: zeali.net
15	* @author Zeal Li
16	* @version 1.0
17	*
18	* @see zeal.util.StreamConverter
19	*/
20
21	public class GB2Big5{
22	private static GB2Big5 pInstance = null;
23	private String s_big5TableFile = null;
24	private String s_gbTableFile = null;
25	private byte[] b_big5Table = null;
26	private byte[] b_gbTable = null;
27
28	/** 指定兩個碼錶檔案來進行初始化 */
29	private GB2Big5(String sgbTableFile,String sbig5TableFile)
30	throws NullPointerException{
31	s_big5TableFile = sbig5TableFile;
32	s_gbTableFile = sgbTableFile;
33	if(null == b_gbTable){
34	b_gbTable = getBytesFromFile(sgbTableFile);
35	}
36	if(null == b_big5Table){
37	b_big5Table = getBytesFromFile(sbig5TableFile);
38	}
39	if(null == b_gbTable){
40	throw
41	new NullPointerException("No gb table can be load");
42	}
43	if(null == b_big5Table){
44	throw
45	new NullPointerException("No big5 table can be load");
46	}
47	}
48
49	public static synchronized GB2Big5 getInstance(){
50	//return getInstance("d:gb-big5.table","d:big5-gb.table");
51	return getInstance("/zeal/util/gb-big5.table",
52	"/zeal/util/big5-gb.table");
53	}
54
55	public static synchronized GB2Big5 getInstance(String sgbTableFile,
56	String sbig5TableFile){
57	if(null == pInstance){
58	try{
59	pInstance = new GB2Big5(sgbTableFile,sbig5TableFile);
60	}
61	catch(Exception e){
62	System.err.println(e.toString());
63	pInstance = null;
64	}
65	}
66
67	return pInstance;
68	}
69
70	/** 把gbChar對應的big5字元替換掉，用來更新碼錶檔案.
71	* 一般當發現字元對映不正確的時候可以透過這個方法來校正. */
72	protected synchronized void resetBig5Char(String gbChar,String big5Char)
73	throws Exception{
74	byte[] Text = new String(gbChar.getBytes(),"GBK").getBytes("GBK");
75	byte[] TextBig5 = new String(big5Char.getBytes(),
76	"BIG5").getBytes("BIG5");
77	int max = Text.length - 1;
78	int h = 0;
79	int l = 0;
80	int p = 0;
81	int b = 256;
82	byte[] big = new byte[2];
83	for(int i = 0; i < max; i++){
84	h = (int) (Text[i]);
85	if(h < 0){
86	h = b + h;
87	l = (int) (Text[i + 1]);
88	if(l < 0){
89	l = b + (int) (Text[i + 1]);
90	}
91	if(h == 161 && l == 64){
92	; // do nothing
93	}
94	else{
95	p = (h - 160) * 510 + (l - 1) * 2;
96	b_gbTable[p] = TextBig5[i];
97	b_gbTable[p + 1] = TextBig5[i + 1];
98	}
99	i++;
100	}
101	}
102
103	BufferedOutputStream pWriter =
104	new BufferedOutputStream(new FileOutputStream(s_gbTableFile));
105	pWriter.write(b_gbTable,0,b_gbTable.length);
106	pWriter.close();
107	}
108
109	/** 把big5Char對應的gb字元替換掉，用來更新碼錶檔案.
110	* 一般當發現字元對映不正確的時候可以透過這個方法來校正. */
111	protected synchronized void resetGbChar(String big5Char,String gbChar)
112	throws Exception{
113	byte[] TextGb =
114	new String(gbChar.getBytes(),"GBK").getBytes("GBK");
115	byte[] Text =
116	new String(big5Char.getBytes(),"BIG5").getBytes("BIG5");
117	int max = Text.length - 1;
118	int h = 0;
119	int l = 0;
120	int p = 0;
121	int b = 256;
122	byte[] big = new byte[2];
123	for(int i = 0; i < max; i++){
124	h = (int) (Text[i]);
125	if(h < 0){
126	h = b + h;
127	l = (int) (Text[i + 1]);
128	if(l < 0){
129	l = b + (int) (Text[i + 1]);
130	}
131	if(h == 161 && l == 64){
132	; // do nothing
133	}
134	else{
135	p = (h - 160) * 510 + (l - 1) * 2;
136	b_big5Table[p] = TextGb[i];
137	b_big5Table[p + 1] = TextGb[i + 1];
138	}
139	i++;
140	}
141	}
142
143	BufferedOutputStream pWriter =
144	new BufferedOutputStream(new FileOutputStream(s_big5TableFile));
145	pWriter.write(b_big5Table,0,b_big5Table.length);
146	pWriter.close();
147	}
148
149	/** 把gb2312編碼的字串轉化成big5碼的位元組流 */
150	public byte[] gb2big5(String inStr) throws Exception{
151	if(null == inStr || inStr.length() <= 0){
152	return "".getBytes();
153	//return "";
154	}
155
156	byte[] Text =
157	new String(inStr.getBytes(),"GBK").getBytes("GBK");
158	int max = Text.length - 1;
159	int h = 0;
160	int l = 0;
161	int p = 0;
162	int b = 256;
163	byte[] big = new byte[2];
164	for(int i = 0; i < max; i++){
165	h = (int) (Text[i]);
166	if(h < 0){
167	h = b + h;
168	l = (int) (Text[i + 1]);
169	if(l < 0){
170	l = b + (int) (Text[i + 1]);
171	}
172	if(h == 161 && l == 64){
173	big[0] = big[1] = (byte) (161 - b);
174	}
175	else{
176	p = (h - 160) * 510 + (l - 1) * 2;
177	try{
178	big[0] = (byte) (b_gbTable[p] - b);
179	}
180	catch(Exception e){
181	big[0] = 45;
182	}
183	try{
184	big[1] = (byte) (b_gbTable[p + 1] - b);
185	}
186	catch(Exception e){
187	big[1] = 45;
188	}
189	}
190	Text[i] = big[0];
191	Text[i + 1] = big[1];
192	i++;
193	}
194
195	}
196
197	return Text;
198	//return new String(Text);
199	}
200
201	/** 把big5碼的字串轉化成gb2312碼的字串 */
202	public String big52gb(String inStr) throws Exception{
203	if(null == inStr || inStr.length() <= 0){
204	return "";
205	}
206
207	byte[] Text =
208	new String(inStr.getBytes(),"BIG5").getBytes("BIG5");
209	int max = Text.length - 1;
210	int h = 0;
211	int l = 0;
212	int p = 0;
213	int b = 256;
214	byte[] big = new byte[2];
215	for(int i = 0; i < max; i++){
216	h = (int) (Text[i]);
217	if(h < 0){
218	h = b + h;
219	l = (int) (Text[i + 1]);
220	if(l < 0){
221	l = b + (int) (Text[i + 1]);
222	}
223	if(h == 161 && l == 161){
224	big[0] = (byte) (161 - b);
225	big[1] = (byte) (64 - b);
226	}
227	else{
228	p = (h - 160) * 510 + (l - 1) * 2;
229	try{
230	big[0] = (byte) (b_big5Table[p] - b);
231	}
232	catch(Exception e){
233	big[0] = 45;
234	}
235	try{
236	big[1] = (byte) (b_big5Table[p + 1] - b);
237	}
238	catch(Exception e){
239	big[1] = 45;
240	}
241	}
242	Text[i] = big[0];
243	Text[i + 1] = big[1];
244	i++;
245	}
246
247	}
248
249	return new String(Text);
250	}
251
252	/** 把檔案讀入位元組陣列，讀取失敗則返回null */
253	private static byte[] getBytesFromFile(String inFileName){
254	try{
255	InputStream in =
256	GB2Big5.class.getResourceAsStream(inFileName);
257	byte[] sContent = StreamConverter.toByteArray(in);
258	in.close();
259	return sContent;
260
261	/*
262	java.io.RandomAccessFile inStream =
263	new java.io.RandomAccessFile(inFileName,"r");
264	byte[] sContent = new byte[ (int) (inStream.length())];
265	inStream.read(sContent);
266	inStream.close();
267	return sContent;
268	*/
269	}
270	catch(Exception e){
271	e.printStackTrace();
272	return null;
273	}
274	}
275
276	public static void main(String[] args) throws Exception{
277	if(args.length < 2){
278	System.out.println(
279	"Usage: zeal.util.GB2Big5 [-gb | -big5] inputstring");
280	System.exit(1);
281	return;
282	}
283
284	boolean bIsGB = true;
285	String inStr = "";
286	for(int i = 0; i < args.length; i++){
287	if(args[i].equalsIgnoreCase("-gb")){
288	bIsGB = true;
289	}
290	else if(args[i].equalsIgnoreCase("-big5")){
291	bIsGB = false;
292	}
293	else{
294	inStr = args[i];
295	}
296	}
297
298	GB2Big5 pTmp = GB2Big5.getInstance();
299
300	String outStr = "";
301	if(bIsGB){
302	outStr = pTmp.big52gb(inStr);
303	}
304	else{
305	outStr = new String(pTmp.gb2big5(inStr),"BIG5");
306	}
307
308	System.out.println("String [" + inStr +
309	"] converted into:n[" + outStr + "]");
310	}
311	}

直接呼叫GB2Big5只適用於對於少量字元的轉化，當需要對整個jsp頁面根據使用者需要進行編碼轉化
的時候，就需要使用到taglib的功能。
具體配置使用步驟如下：

1.在WEB-INF/目錄下增加GB2Big5Wrapper.tld檔案，內容如下:
xml version="1.0" encoding="ISO-8859-1"?>  
2
/td>
3
   PUBLIC "-//Sun Microsystems, Inc.//DTD JSP Tag Library 1.2//EN"  
4
          "> 
5
 
6
<taglib> 
7
   <tlib-version>1.0tlib-version> 
8
   <jsp-version>1.2jsp-version> 
9
   <short-name>zealLishort-name> 
10
   <tag> 
11
     <name>GB2Big5Wrappername> 
12
     <tag-class>zeal.util.GB2Big5Wrappertag-class> 
13
     <attribute> 
14
       <name>isbig5name>   
15
       <rtexprvalue>truertexprvalue> 
16
       <type>booleantype> 
17
     attribute> 
18
   tag> 
19
taglib>
2.在需要進行轉化的JSP頁面裡面加上:


任何你需要轉化的東西
比如test.jsp原始碼如下 => 
<%@ page  
2
contentType="text/html; charset=GBK" 
3
 
4
import="javax.servlet.http.HttpSession" 
5
import="java.util.*" 
6
import="com.zealLi.*" 
7
%>
8
String encode = request.getParameter("encode");  
9
 
10
if(null == encode || encode.length() <= 0){  
11
  encode = "BIG5";  
12
}  
13
boolean isBig5 = false;  
14
String charset = "GB2312";  
15
 
16
if(encode.equalsIgnoreCase("BIG5")){  
17
  isBig5 = true;  
18
  charset = "BIG5";  
19
}  
20
String sInfo = "中文字型繁簡體轉化的測試。";  
21
%>uri="/WEB-INF/GB2Big5Wrapper.tld" prefix="zealLi"%> 
22
<zealLi:GB2Big5Wrapper isbig5="">  
23
<html> 
24
  <head> 
25
    <title>Jsp測試頁面title> 
26
    <meta http-equiv="Content-Type" content="text/html; charset=">  
27
  head> 
28
  <body> 
29
    <%  
30
    Calendar now = Calendar.getInstance();  
31
    out.println(now.get(Calendar.YEAR) + "." +   
32
    (now.get(Calendar.MONTH)+1) + "." +   
33
    now.get(Calendar.DAY_OF_MONTH) + "<p>");  
34
    %> 
35
    <p> 
36
    <%=sInfo%> 
37
  body> 
38
html>zealLi:GB2Big5Wrapper>