解決ajax提交中文、URL中文參數(shù)傳遞后的亂碼問(wèn)題的解決辦法
在開(kāi)發(fā)中，經(jīng)常遇到用ajax提交數(shù)據(jù)，或者我們用url傳遞參數(shù)，如果是中文，我們就會(huì)遇到非常頭疼的亂碼問(wèn)題。（
Java樂(lè)園）
比如：當(dāng)我門(mén)用下邊的對(duì)象及方法(ajax)
xh = new ActiveXObject("Microsoft.XMLHTTP")
xh.onreadystatechange = getReady
xh.open("POST","/test/zhongwen.jsp",false)
向服務(wù)器端傳送中文數(shù)據(jù)時(shí),zhongwen.jsp得到parameter的值就會(huì)是亂碼。
或者我們?cè)趗rl后面?zhèn)鬟f參數(shù),比如: http://locathost:8080/test/chinese.jsp?name=中文, 這個(gè)時(shí)候，我們?cè)诜?wù)器段得到的數(shù)據(jù)就會(huì)亂碼
那么我們?cè)趺唇鉀Q這個(gè)問(wèn)題呢？
不要緊張，辦法是有的，方法如下：
首先在頁(yè)面用js的escape方法去轉(zhuǎn)碼
其次server端獲取轉(zhuǎn)碼后的數(shù)據(jù)后，就用下邊這個(gè)類(lèi)Escape的unescape方法解碼
類(lèi)Escape
JAVA代碼如下：
package test;
/**
* JavaScript escape/unescape 編碼的 Java 實(shí)現(xiàn)
* author jackyz
* keep this copyright info while using this method by free
*/
public class Escape {
private final static String[] hex = {
"00","01","02","03","04","05","06","07","08","09","0A","0B","0C","0D","0E","0F",
"10","11","12","13","14","15","16","17","18","19","1A","1B","1C","1D","1E","1F",
"20","21","22","23","24","25","26","27","28","29","2A","2B","2C","2D","2E","2F",
"30","31","32","33","34","35","36","37","38","39","3A","3B","3C","3D","3E","3F",
"40","41","42","43","44","45","46","47","48","49","4A","4B","4C","4D","4E","4F",
"50","51","52","53","54","55","56","57","58","59","5A","5B","5C","5D","5E","5F",
"60","61","62","63","64","65","66","67","68","69","6A","6B","6C","6D","6E","6F",
"70","71","72","73","74","75","76","77","78","79","7A","7B","7C","7D","7E","7F",
"80","81","82","83","84","85","86","87","88","89","8A","8B","8C","8D","8E","8F",
"90","91","92","93","94","95","96","97","98","99","9A","9B","9C","9D","9E","9F",
"A0","A1","A2","A3","A4","A5","A6","A7","A8","A9","AA","AB","AC","AD","AE","AF",
"B0","B1","B2","B3","B4","B5","B6","B7","B8","B9","BA","BB","BC","BD","BE","BF",
"C0","C1","C2","C3","C4","C5","C6","C7","C8","C9","CA","CB","CC","CD","CE","CF",
"D0","D1","D2","D3","D4","D5","D6","D7","D8","D9","DA","DB","DC","DD","DE","DF",
"E0","E1","E2","E3","E4","E5","E6","E7","E8","E9","EA","EB","EC","ED","EE","EF",
"F0","F1","F2","F3","F4","F5","F6","F7","F8","F9","FA","FB","FC","FD","FE","FF"
};
private final static byte[] val = {
0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07,0x08,0x09,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
0x3F,0x0A,0x0B,0x0C,0x0D,0x0E,0x0F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
0x3F,0x0A,0x0B,0x0C,0x0D,0x0E,0x0F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F
};
public static String escape(String s) {
StringBuffer sbuf = new StringBuffer();
int len = s.length();
for (int i = 0; i < len; i++) {
int ch = s.charAt(i);
if (ch == ' ') { // space : map to '+'
sbuf.append('+');
} else if ('A' <= ch && ch <= 'Z') { // 'A'..'Z' : as it was
sbuf.append((char)ch);
} else if ('a' <= ch && ch <= 'z') { // 'a'..'z' : as it was
sbuf.append((char)ch);
} else if ('0' <= ch && ch <= '9') { // '0'..'9' : as it was
sbuf.append((char)ch);
} else if (ch == '-' || ch == '_' // unreserved : as it was
|| ch == '.' || ch == '!'
|| ch == '~' || ch == '*'
|| ch == '"'' || ch == '('
|| ch == ')') {
sbuf.append((char)ch);
} else if (ch <= 0x007F) { // other ASCII : map to %XX
sbuf.append('%');
sbuf.append(hex[ch]);
} else { // unicode : map to %uXXXX
sbuf.append('%');
sbuf.append('u');
sbuf.append(hex[(ch >>> 8)]);
sbuf.append(hex[(0x00FF & ch)]);
}
}
return sbuf.toString();
}
public static String unescape(String s) {
StringBuffer sbuf = new StringBuffer();
int i = 0;
int len = s.length();
while (i < len) {
int ch = s.charAt(i);
if (ch == '+') { // + : map to ' '
sbuf.append(' ');
} else if ('A' <= ch && ch <= 'Z') { // 'A'..'Z' : as it was
sbuf.append((char)ch);
} else if ('a' <= ch && ch <= 'z') { // 'a'..'z' : as it was
sbuf.append((char)ch);
} else if ('0' <= ch && ch <= '9') { // '0'..'9' : as it was
sbuf.append((char)ch);
} else if (ch == '-' || ch == '_' // unreserved : as it was
|| ch == '.' || ch == '!'
|| ch == '~' || ch == '*'
|| ch == '"'' || ch == '('
|| ch == ')') {
sbuf.append((char)ch);
} else if (ch == '%') {
int cint = 0;
if ('u' != s.charAt(i+1)) { // %XX : map to ascii(XX)
cint = (cint << 4) | val[s.charAt(i+1)];
cint = (cint << 4) | val[s.charAt(i+2)];
i+=2;
} else { // %uXXXX : map to unicode(XXXX)
cint = (cint << 4) | val[s.charAt(i+2)];
cint = (cint << 4) | val[s.charAt(i+3)];
cint = (cint << 4) | val[s.charAt(i+4)];
cint = (cint << 4) | val[s.charAt(i+5)];
i+=5;
}
sbuf.append((char)cint);
}
i++;
}
return sbuf.toString();
}
public static void main(String[] args) {
String stest = "中文1234 abcd[]()<+>,.~""";
System.out.println(stest);
System.out.println(escape(stest));
System.out.println(Escape.unescape(escape(stest)));
String s = "你好";
String s1="%u4F60%u597D";
System.out.println(escape(s));
System.out.println(Escape.unescape(s1));
}
}
######### 執(zhí)行后答案：
中文1234 abcd[]()<+>,.~"
%u4E2D%u65871234+abcd%5B%5D()%3C%2B%3E%2C.~%5C
中文1234 abcd[]()<+>,.~"
%u4F60%u597D
你好
解碼后就可以得到與頁(yè)面提交的數(shù)據(jù)一致的數(shù)據(jù)了。
我們來(lái)看看為什么要采取這種方法呢？
Java 的 URLEncoder.encode 方法與 JavaScript 的 unescape 方法已經(jīng)不能兼容了。
現(xiàn)
在瀏覽器的主流版本中 JavaScript 已經(jīng)開(kāi)始使用 Unicode 作為字符串的內(nèi)碼進(jìn)行編碼。即, Unicode 字符 escape 之
后的樣子類(lèi)似于 %uABCD 而 java 的 URLEncoder.encode 方法得到的結(jié)果是 %AB%CD ,轉(zhuǎn)換出來(lái)的結(jié)果必定是亂碼
了。
在此應(yīng)該感謝寫(xiě)Escape類(lèi)的哥們，希望此帖對(duì)大家使用ajax有所幫助。