码迷,mamicode.com
首页 > 其他好文 > 详细

中文转Punycode

时间:2016-08-09 00:03:14      阅读:233      评论:0      收藏:0      [点我收藏+]

标签:

package cn.cnnic.ops.udf;

public class GetPunycodeFromChinese {
    static int TMIN = 1;
    static int TMAX = 26;
    static int BASE = 36;
    static int INITIAL_N = 128;
    static int INITIAL_BIAS = 72;
    static int DAMP = 700;
    static int SKEW = 38;
    static char DELIMITER = ‘-‘;
    static String PUNY_PREFIX = "xn--";
    static char DOT = ‘.‘;
    static String SPLIT_DOT = "\\.";
    
    public static void main(String[] args) {
        String str = "互联网络信息中心.中国";
        GetPunycodeFromChinese gpfc = new GetPunycodeFromChinese();
        System.out.println(gpfc.evaluate(str));
    }

    /**
     * 
     * @param txt
     * @return
     */
    public String evaluate(String txt) {
        String strResult=txt;
        try {
            strResult = fromChineseToPunycode(txt.toString().trim());
        } catch (Exception e) {
            e.printStackTrace();
        }
        return strResult;
    }
    
    /**
     * 
     * @param input
     * @return
     * @throws Exception
     */
    public String fromChineseToPunycode(String input) throws Exception{
        if(input == null || input.equalsIgnoreCase("")){
            return "";
        }else if(input.indexOf(DOT) < 0){
            return PUNY_PREFIX+fromChineseToPunycodeUnit(input);
        }else if(input.indexOf(DOT) > 0){
            String[] arr = input.split(SPLIT_DOT);
            String result="";
            for(int index = 0; index<arr.length;index++){
                result = result + PUNY_PREFIX +fromChineseToPunycodeUnit(arr[index])+".";
            }
            return result.substring(0, result.length()-1);
        }
        return input;
    }
    
    /**
     * 
     * @param input
     * @return
     * @throws Exception
     */
    public String fromChineseToPunycodeUnit(String input) throws Exception {
        int n = INITIAL_N;
        int delta = 0;
        int bias = INITIAL_BIAS;
        StringBuilder output = new StringBuilder();
        int b = 0;
        for (int i = 0; i < input.length(); i++) {
            char c = input.charAt(i);
            if (isBasic(c)) {
                output.append(c);
                b++;
            }
        }
        if (b > 0) {
            output.append(DELIMITER);
        }
        int h = b;
        while (h < input.length()) {
            int m = Integer.MAX_VALUE;
            // Find the minimum code point >= n
            for (int i = 0; i < input.length(); i++) {
                int c = input.charAt(i);
                if (c >= n && c < m) {
                    m = c;
                }
            }
            if (m - n > (Integer.MAX_VALUE - delta) / (h + 1)) {
                throw new Exception("OVERFLOW");
            }
            delta = delta + (m - n) * (h + 1);
            n = m;
            for (int j = 0; j < input.length(); j++) {
                int c = input.charAt(j);
                if (c < n) {
                    delta++;
                    if (0 == delta) {
                        throw new Exception("OVERFLOW");
                    }
                }
                if (c == n) {
                    int q = delta;
                    for (int k = BASE;; k += BASE) {
                        int t;
                        if (k <= bias) {
                            t = TMIN;
                        } else if (k >= bias + TMAX) {
                            t = TMAX;
                        } else {
                            t = k - bias;
                        }
                        if (q < t) {
                            break;
                        }
                        output.append((char) digit2codepoint(t + (q - t) % (BASE - t)));
                        q = (q - t) / (BASE - t);
                    }
                    output.append((char) digit2codepoint(q));
                    bias = adapt(delta, h + 1, h == b);
                    delta = 0;
                    h++;
                }
            }
            delta++;
            n++;
        }
        return output.toString();
    }
    
    /**
     * 
     * @param delta
     * @param numpoints
     * @param first
     * @return
     */
    public int adapt(int delta, int numpoints, boolean first) {
        if (first) {
            delta = delta / DAMP;
        } else {
            delta = delta / 2;
        }
        delta = delta + (delta / numpoints);
        int k = 0;
        while (delta > ((BASE - TMIN) * TMAX) / 2) {
            delta = delta / (BASE - TMIN);
            k = k + BASE;
        }
        return k + ((BASE - TMIN + 1) * delta) / (delta + SKEW);
    }

    /**
     * 
     * @param c
     * @return
     */
    public boolean isBasic(char c) {
        return c < 0x80;
    }

    /**
     * 
     * @param d
     * @return
     * @throws Exception
     */
    public int digit2codepoint(int d) throws Exception {
        if (d < 26) {
            // 0..25 : ‘a‘..‘z‘
            return d + ‘a‘;
        } else if (d < 36) {
            // 26..35 : ‘0‘..‘9‘;
            return d - 26 + ‘0‘;
        } else {
            throw new Exception("BAD_INPUT");
        }
    }

    /**
     * 
     * @param c
     * @return
     * @throws Exception
     */
    public int codepoint2digit(int c) throws Exception {
        if (c - ‘0‘ < 10) {
            // ‘0‘..‘9‘ : 26..35
            return c - ‘0‘ + 26;
        } else if (c - ‘a‘ < 26) {
            // ‘a‘..‘z‘ : 0..25
            return c - ‘a‘;
        } else {
            throw new Exception("BAD_INPUT");
        }
    }
}

 

【参考】http://blog.csdn.net/a19881029/article/details/18262671

中文转Punycode

标签:

原文地址:http://www.cnblogs.com/zhzhang/p/5751439.html

(0)
(0)
   
举报
评论 一句话评论(0
登录后才能评论!
© 2014 mamicode.com 版权所有  联系我们:gaon5@hotmail.com
迷上了代码!