Java：转换汉字为unicode形式的字符串和转换unicode形式字符串转换成汉字

is_two

转自：http://www.blogjava.net/jjshcc/archive/2011/05/11/349991.html[size=13.333333969116211px]/* 输出
[size=13.333333969116211px]Original:       黄   彪彪
[size=13.333333969116211px]to unicode:     \u9EC4\ \t\u5F6A\u5F6A
[size=13.333333969116211px]from unicode:   黄   彪彪
[size=13.333333969116211px]使用命令转换: native2ascii -encoding utf-8 a.txt a.txt
[size=13.333333969116211px]Java的properties属性文件会把字符先转换成unicode的形式存储.
[size=13.333333969116211px]*/
[size=13.333333969116211px] 
[size=13.333333969116211px]import java.io.UnsupportedEncodingException;
[size=13.333333969116211px] 
[size=13.333333969116211px]public class UnicodeConverter {
[size=13.333333969116211px]    public static void main(String[] args) throws UnsupportedEncodingException {
[size=13.333333969116211px]        String s = "黄 \t彪\u5F6A";
[size=13.333333969116211px]        System.out.println("Original:\t\t" + s);
[size=13.333333969116211px] 
[size=13.333333969116211px]        s = toEncodedUnicode(s, true);
[size=13.333333969116211px]        System.out.println("to unicode:\t\t" + s);
[size=13.333333969116211px] 
[size=13.333333969116211px]        s = fromEncodedUnicode(s.toCharArray(), 0, s.length());
[size=13.333333969116211px]        System.out.println("from unicode:\t" + s);
[size=13.333333969116211px]    }
[size=13.333333969116211px] 
[size=13.333333969116211px]    private static final char[] hexDigit = { '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A',
[size=13.333333969116211px]            'B', 'C', 'D', 'E', 'F' };
[size=13.333333969116211px] 
[size=13.333333969116211px]    private static char toHex(int nibble) {
[size=13.333333969116211px]        return hexDigit[(nibble & 0xF)];
[size=13.333333969116211px]    }
 
[size=13.333333969116211px] /**
[size=13.333333969116211px]     * 将字符串编码成 Unicode 形式的字符串. 如 "黄" to "\u9EC4"
[size=13.333333969116211px]     * Converts unicodes to encoded \\uxxxx and escapes
[size=13.333333969116211px]     * special characters with a preceding slash
[size=13.333333969116211px]     *
[size=13.333333969116211px]     * @param theString
[size=13.333333969116211px]     *        待转换成Unicode编码的字符串。
[size=13.333333969116211px]     * @param escapeSpace
[size=13.333333969116211px]     *        是否忽略空格，为true时在空格后面是否加个反斜杠。
[size=13.333333969116211px]     * @return 返回转换后Unicode编码的字符串。
[size=13.333333969116211px]     */
[size=13.333333969116211px]    public static String toEncodedUnicode(String theString, boolean escapeSpace) {
[size=13.333333969116211px]        int len = theString.length();
[size=13.333333969116211px]        int bufLen = len * 2;
[size=13.333333969116211px]        if (bufLen < 0) {
[size=13.333333969116211px]            bufLen = Integer.MAX_VALUE;
[size=13.333333969116211px]        }
[size=13.333333969116211px]        StringBuffer outBuffer = new StringBuffer(bufLen);
[size=13.333333969116211px] 
[size=13.333333969116211px]        for (int x = 0; x < len; x++) {
[size=13.333333969116211px]            char aChar = theString.charAt(x);
[size=13.333333969116211px]            // Handle common case first, selecting largest block that
[size=13.333333969116211px]            // avoids the specials below
[size=13.333333969116211px]            if ((aChar > 61) && (aChar < 127)) {
[size=13.333333969116211px]                if (aChar == '\\') {
[size=13.333333969116211px]                    outBuffer.append('\\');
[size=13.333333969116211px]                    outBuffer.append('\\');
[size=13.333333969116211px]                    continue;
[size=13.333333969116211px]                }
[size=13.333333969116211px]                outBuffer.append(aChar);
[size=13.333333969116211px]                continue;
[size=13.333333969116211px]            }
[size=13.333333969116211px] 
[size=13.333333969116211px]            switch (aChar) {
[size=13.333333969116211px]            case ' ':
[size=13.333333969116211px]                if (x == 0 || escapeSpace) outBuffer.append('\\');
[size=13.333333969116211px]                outBuffer.append(' ');
[size=13.333333969116211px]                break;
[size=13.333333969116211px]            case '\t':
[size=13.333333969116211px]                outBuffer.append('\\');
[size=13.333333969116211px]                outBuffer.append('t');
[size=13.333333969116211px]                break;
[size=13.333333969116211px]            case '\n':
[size=13.333333969116211px]                outBuffer.append('\\');
[size=13.333333969116211px]                outBuffer.append('n');
[size=13.333333969116211px]                break;
[size=13.333333969116211px]            case '\r':
[size=13.333333969116211px]                outBuffer.append('\\');
[size=13.333333969116211px]                outBuffer.append('r');
[size=13.333333969116211px]                break;
[size=13.333333969116211px]            case '\f':
[size=13.333333969116211px]                outBuffer.append('\\');
[size=13.333333969116211px]                outBuffer.append('f');
[size=13.333333969116211px]                break;
[size=13.333333969116211px]            case '=': // Fall through
[size=13.333333969116211px]            case ':': // Fall through
[size=13.333333969116211px]            case '#': // Fall through
[size=13.333333969116211px]            case '!':
[size=13.333333969116211px]                outBuffer.append('\\');
[size=13.333333969116211px]                outBuffer.append(aChar);
[size=13.333333969116211px]                break;
[size=13.333333969116211px]            default:
[size=13.333333969116211px]                if ((aChar < 0x0020) || (aChar > 0x007e)) {
[size=13.333333969116211px]                    // 每个unicode有16位，每四位对应的16进制从高位保存到低位
[size=13.333333969116211px]                    outBuffer.append('\\');
[size=13.333333969116211px]                    outBuffer.append('u');
[size=13.333333969116211px]                    outBuffer.append(toHex((aChar >> 12) & 0xF));
[size=13.333333969116211px]                    outBuffer.append(toHex((aChar >> 8) & 0xF));
[size=13.333333969116211px]                    outBuffer.append(toHex((aChar >> 4) & 0xF));
[size=13.333333969116211px]                    outBuffer.append(toHex(aChar & 0xF));
[size=13.333333969116211px]                } else {
[size=13.333333969116211px]                    outBuffer.append(aChar);
[size=13.333333969116211px]                }
[size=13.333333969116211px]            }
[size=13.333333969116211px]        }
[size=13.333333969116211px]        return outBuffer.toString();
[size=13.333333969116211px]    }
 
[size=13.333333969116211px] /**
[size=13.333333969116211px]     * 从 Unicode 形式的字符串转换成对应的编码的特殊字符串。 如 "\u9EC4" to "黄".
[size=13.333333969116211px]     * Converts encoded \\uxxxx to unicode chars
[size=13.333333969116211px]     * and changes special saved chars to their original forms
[size=13.333333969116211px]     *
[size=13.333333969116211px]     * @param in
[size=13.333333969116211px]     *        Unicode编码的字符数组。
[size=13.333333969116211px]     * @param off
[size=13.333333969116211px]     *        转换的起始偏移量。
[size=13.333333969116211px]     * @param len
[size=13.333333969116211px]     *        转换的字符长度。
[size=13.333333969116211px]     * @param convtBuf
[size=13.333333969116211px]     *        转换的缓存字符数组。
[size=13.333333969116211px]     * @return 完成转换，返回编码前的特殊字符串。
[size=13.333333969116211px]     */
[size=13.333333969116211px]    public static String fromEncodedUnicode(char[] in, int off, int len) {
[size=13.333333969116211px]        char aChar;
[size=13.333333969116211px]        char[] out = new char[len]; // 只短不长
[size=13.333333969116211px]        int outLen = 0;
[size=13.333333969116211px]        int end = off + len;
[size=13.333333969116211px] 
[size=13.333333969116211px]        while (off < end) {
[size=13.333333969116211px]            aChar = in[off++];
[size=13.333333969116211px]            if (aChar == '\\') {
[size=13.333333969116211px]                aChar = in[off++];
[size=13.333333969116211px]                if (aChar == 'u') {
[size=13.333333969116211px]                    // Read the xxxx
[size=13.333333969116211px]                    int value = 0;
[size=13.333333969116211px]                    for (int i = 0; i < 4; i++) {
[size=13.333333969116211px]                        aChar = in[off++];
[size=13.333333969116211px]                        switch (aChar) {
[size=13.333333969116211px]                        case '0':
[size=13.333333969116211px]                        case '1':
[size=13.333333969116211px]                        case '2':
[size=13.333333969116211px]                        case '3':
[size=13.333333969116211px]                        case '4':
[size=13.333333969116211px]                        case '5':
[size=13.333333969116211px]                        case '6':
[size=13.333333969116211px]                        case '7':
[size=13.333333969116211px]                        case '8':
[size=13.333333969116211px]                        case '9':
[size=13.333333969116211px]                            value = (value << 4) + aChar - '0';
[size=13.333333969116211px]                            break;
[size=13.333333969116211px]                        case 'a':
[size=13.333333969116211px]                        case 'b':
[size=13.333333969116211px]                        case 'c':
[size=13.333333969116211px]                        case 'd':
[size=13.333333969116211px]                        case 'e':
[size=13.333333969116211px]                        case 'f':
[size=13.333333969116211px]                            value = (value << 4) + 10 + aChar - 'a';
[size=13.333333969116211px]                            break;
[size=13.333333969116211px]                        case 'A':
[size=13.333333969116211px]                        case 'B':
[size=13.333333969116211px]                        case 'C':
[size=13.333333969116211px]                        case 'D':
[size=13.333333969116211px]                        case 'E':
[size=13.333333969116211px]                        case 'F':
[size=13.333333969116211px]                            value = (value << 4) + 10 + aChar - 'A';
[size=13.333333969116211px]                            break;
[size=13.333333969116211px]                        default:
[size=13.333333969116211px]                            throw new IllegalArgumentException("Malformed \\uxxxx encoding.");
[size=13.333333969116211px]                        }
[size=13.333333969116211px]                    }
[size=13.333333969116211px]                    out[outLen++] = (char) value;
[size=13.333333969116211px]                } else {
[size=13.333333969116211px]                    if (aChar == 't') {
[size=13.333333969116211px]                        aChar = '\t';
[size=13.333333969116211px]                    } else if (aChar == 'r') {
[size=13.333333969116211px]                        aChar = '\r';
[size=13.333333969116211px]                    } else if (aChar == 'n') {
[size=13.333333969116211px]                        aChar = '\n';
[size=13.333333969116211px]                    } else if (aChar == 'f') {
[size=13.333333969116211px]                        aChar = '\f';
[size=13.333333969116211px]                    }
[size=13.333333969116211px]                    out[outLen++] = aChar;
[size=13.333333969116211px]                }
[size=13.333333969116211px]            } else {
[size=13.333333969116211px]                out[outLen++] = (char) aChar;
[size=13.333333969116211px]            }
[size=13.333333969116211px]        }
[size=13.333333969116211px]        return new String(out, 0, outLen);
[size=13.333333969116211px]    }
[size=13.333333969116211px]}