用于MIDP的URLEncoder类

由于MIDP没有J2SE对应的java.net.URLEncoder类，因此，要向服务器发送HTTP请求，必须自己进行URL编码，参考JDK1.4.2的src代码，将其改为一个能用在MIDP环境中的URLEncoder类：

// URLEncoder.java
package com.mboker.blog.midp.http;

import java.io.*;

/**
* Encode url, just like java.net.URLEncoder.encode() in J2SE.<br>
* NOTE: This class is modified from java.net.URLEncoder class in J2SE 1.4.
*
* @author Xuefeng
*/
class URLEncoder {

private static final int MAX_BYTES_PER_CHAR = 10; // rather arbitrary limit, but safe for now

private static boolean[] dontNeedEncoding;
private static final int caseDiff = ('a' - 'A');

static {
dontNeedEncoding = new boolean[256];
for (int i='a'; i<='z'; i++) {
dontNeedEncoding[i] = true;
}
for (int i='A'; i<='Z'; i++) {
dontNeedEncoding[i] = true;
}
for (int i='0'; i<='9'; i++) {
dontNeedEncoding[i] = true;
}
dontNeedEncoding[' '] = true;
dontNeedEncoding['-'] = true;
dontNeedEncoding['_'] = true;
dontNeedEncoding['.'] = true;
dontNeedEncoding['*'] = true;
}

private URLEncoder() {}

public static String encode(String s) {
boolean wroteUnencodedChar = false;

StringBuffer out = new StringBuffer(s.length());
ByteArrayOutputStream buf = new ByteArrayOutputStream(MAX_BYTES_PER_CHAR);
OutputStreamWriter writer = new OutputStreamWriter(buf);

for (int i = 0; i < s.length(); i++) {
int c = (int) s.charAt(i);
if (c<256 && dontNeedEncoding[c]) {
out.append((char) (c==' ' ? '+' : c));
wroteUnencodedChar = true;
} else {
// convert to external encoding before hex conversion
try {
if (wroteUnencodedChar) { // Fix for 4407610
writer = new OutputStreamWriter(buf);
wroteUnencodedChar = false;
}
writer.write(c);
/*
* If this character represents the start of a Unicode
* surrogate pair, then pass in two characters. It's not
* clear what should be done if a bytes reserved in the
* surrogate pairs range occurs outside of a legal surrogate
* pair. For now, just treat it as if it were any other
* character.
*/
if (c >= 0xD800 && c <= 0xDBFF) {
if ((i + 1) < s.length()) {
int d = (int) s.charAt(i + 1);
if (d >= 0xDC00 && d <= 0xDFFF) {
writer.write(d);
i++;
}
}
}
writer.flush();
} catch (IOException e) {
buf.reset();
continue;
}
byte[] ba = buf.toByteArray();
for (int j = 0; j < ba.length; j++) {
out.append('%');
char ch = toHex((ba[j] >> 4) & 0xF);
// converting to use uppercase letter as part of
// the hex value if ch is a letter.
if (isLetter(ch)) {
ch -= caseDiff;
}
out.append(ch);
ch = toHex(ba[j] & 0xF);
if (isLetter(ch)) {
ch -= caseDiff;
}
out.append(ch);
}
buf.reset();
}
}
return out.toString();
}

private static char toHex(int digit) {
if ((digit >= 16) || (digit < 0)) {
return '\0';
}
if (digit < 10) {
return (char)('0' + digit);
}
return (char)('a' - 10 + digit);
}

private static boolean isLetter(char c) {
return (c>='a' && c<='z');
}
}

J2SE的URLEncoder依赖于java.lang.Character的许多特性，将其全部剔除并改造为基本运算，即可在MIDP环境中使用，中文测试也一切正常。