url中文参数问题，最近在一个项目中遇到的，由于要实现一个autocomplete（自动完成）的功能，在使用jquery框架时,js发送中文参数编码为utf-8，一开始通过本地的new String(q.getBytes("iso8859-1"),"utf-8")方式正确转换。上传到测试环境，却还是乱码，分析原因本地默认编码方式utf-8，webx框架解析会通过本地环境的编码方式转换。由于测试服务器设置gbk编码，而本地为utf-8，所以环境编码不同造成转换差异。
尝试在本地用多种方式调试编码转换，均未得到正确结果，分析原因，是中间转换时使用了不正确的编码格式导致(原来utf-8,转码时gbk)，js传参:使用utf-8，webx解析使用gbk。此时编码得不到正确转换。
网上搜索了一下，发现js中有个escape函数，可对中文进行unicode编码,尝试了一下，由于webx框架本身会根据web服务器的环境设置的编码进行转换(替换掉%C之类的符号)。使用escape编码后产生的是诸如：%u5c42，此时在后台可以取到原始值：%u5c42(框架未对其做任何转换处理)，再通过java中写一个unescape方法进行解码，问题解决。
附上一些关键代码及说明：
String aa="层";//未进行转换
String aa="%B2%E3";//进行url编码,gbk方式(URLEncoder.encode(aa, "gbk"))
String aa="%E5%B1%82";//进行url编码,utf-8方式(URLEncoder.encode(aa, "utf-8"))
String aa="%u5c42";//获取js中escape转换后的”层”
修改jquery.autocomplete.js中传参数的方法：
function lastWord(value) {
//alert(value);
//escape(value);
if ( !options.multiple )
return escape(value);
var words = trimWords(value);
return escape(words[words.length - 1]);;
}
String aa = rundata.getParameters().getString("q");//aa为：%25u5c42
aa =Escape.unescape(aa);//java unescape解码，aa为：%u5c42
aa =Escape.unescape(aa);//再次解码，aa为：层
以下是Escape类：
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 };
/**
* 编码
*
* @param s
* @return
*/
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 ('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();
}
/**
* 解码 说明：本方法保证 不论参数s是否经过escape()编码，均能得到正确的“解码”结果
*
* @param s
* @return
*/
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 ('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);
} else { // 对应的字符未经过编码
sbuf.append((char) ch);
}
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(unescape(stest));
System.out.println(unescape("%u5355%u4F4D26"));
}
扫一扫
1035
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
