java 实现PHP unserialize接口，解决中文问题

最近用java重写php diszus的接口，碰到一堆的序列化字符串，如下：

a:1:{i:220;a:4:{s:3:”uid”;s:3:”220”;s:8:”username”;s:10:”中国好男人”;s:5:”level”;s:1:”1”;s:6:”online”;i:0;}}

试了几个类库后发现对有中文的字符串都会解析成乱码，原因是PHP对中文字符的解析是两个字符，java类库中substring，deleteCharAt之类的方法都是把中文当作一个字符来操作，比如s:10:”中国好男人”，10代表“中国好男人”占的字符数，所以，坑了。。。。所以只能自己改造下，其实也很简单，网上找了两段代码：

package com.ewt360.bbsapi.common.util.PHPHelper;

import java.util.HashMap;

/**
 * Since i have to declare the return type of a function, and i have no idea
 * ahead of time what value is being unserialized, this helper class is a hack
 * so that i can return any variable type as PHPValue and deal with it later.
 *
 * @author Scott Hurring [scott at hurring dot com]
 * @version v0.01a ALPHA!!
 * @licence GNU GPL
 */
public class PHPValue {
    /**
     * The raw object given to us by unserialize()
     */
    private Object obj = null;
    private HashMap hobj = new HashMap();

    /**
     * The toString() value of the Object passed into PHPValue
     */
    public String value = "";

    /**
     * Is the PHPValue one of the following?
     */
    public boolean isNull = false;
    public boolean isInteger = false;
    public boolean isDouble = false;
    public boolean isString = false;
    public boolean isHashMap = false;

    /**
     * Pass in an object, and PHPValue: 1. Attempts to try and figure out what
     * it is 2. Stringifies it 3. Sets a boolean flag to let everyone know what
     * we think it is.
     *
     */
    public PHPValue(Object o) {
        obj = o;

        if (obj == null) {
            isNull = true;
            value = "";
        } else if (obj.getClass().toString().equals("class java.lang.Integer")) {
            isInteger = true;
            value = ((Integer) obj).toString();
        } else if (obj.getClass().toString().equals("class java.lang.Double")) {
            isDouble = true;
            value = ((Double) obj).toString();
        } else if (obj.getClass().toString().equals("class java.util.HashMap")) {
            isHashMap = true;
            value = obj.toString();
        } else if (obj.getClass().toString().equals("class java.lang.String")) {
            isString = true;
            value = obj.toString();
        } else {
            value = obj.toString();
        }

        // debug
        if (obj != null) {
            // System.out.println("PHPValue: '" + obj.getClass() + "' = " +
            // value);
        }

    }

    /**
     * Convert PHPValue into a double
     *
     * @return double
     */
    public double toDouble() {
        if (isDouble) {
            return Double.parseDouble(value);
        } else {
            return 0.0;
        }
    }

    /**
     * Convert PHPValue into an integer
     *
     * @return int
     */
    public int toInteger() {
        if (isInteger) {
            return Integer.parseInt(value);
        } else {
            return 0;
        }
    }

    /**
     * PHPValue's string-ified value
     *
     * @return String
     */
    public String toString() {
        if (!isNull) {
            return value;
        } else {
            return "";
        }
    }

    /**
     * Cast PHPValue into HashMap
     *
     * @return HashMap
     */
    public HashMap toHashMap() {
        return (HashMap) obj;
    }

    /**
     * Return the raw object
     *
     * @return double
     */
    public Object toObject() {
        return obj;
    }

}

这个不变，主要改下面的类

package com.ewt360.bbsapi.common.util.PHPHelper;
import java.util.regex.*;
import java.util.*;

public class PHPSerialize {
    /**
     * To store partially decomposed serialized string
     */
    private StringBuffer sb;

    /** Creates a new instance of phpserialize */
    public PHPSerialize() {
    }

    /**
     * Unserializes a single value into a PHPValue
     *
     * @param s
     *            s String to unserialize
     * @return PHPValue
     */
    public PHPValue unserialize(String s) {
        sb = new StringBuffer(s);
        PHPValue phpvalue = getNext();
        // println("value = " + phpvalue.toString());
        return phpvalue;
    }

    /**
     * Get the next token in the serialized string
     *
     *
     */
    private PHPValue getNext() {
        // println("getNext = "+ sb.toString());
        PHPValue phpvalue;
        Object value = new Object();
        // Current character
        String c;
        // What type of value is this
        String what = "";
        // Consume & throw away characters
        int consumeChars = 0;
        // Length of the string/array
        int len = -1;
        // Buffer to read in string
        StringBuffer tmp = new StringBuffer();
        // length of sb is constantly changing.
        while (sb.length() > 0) {
            c = sb.substring(0, 1);
            sb = sb.deleteCharAt(0);
            // println(c +"\twhat="+what+"\ttmp="+tmp.toString());
            // Ignore chars
            if (consumeChars-- > 0) {
                continue;
            }
            /**
             * This is a hackish pseudo state machine 'what' is the state
             *
             */
            if (what.equals("array_length")) {
                if (c.equals(":")) {
                    len = Integer.parseInt(tmp.toString());
                    tmp.delete(0, tmp.length());
                    // println("\tarray_length="+ len);
                    what = "array_value";
                }
                if (len == -1) {
                    tmp.append(c);
                }
            } else if (what.equals("array_value")) {
                // value = new PHPValue( new HashMap() );
                HashMap hash = new HashMap();
                for (int i = 0; i < len; i++) {
                    PHPValue hashKey = getNext();
                    PHPValue hashValue = getNext();
                    // Force the keys of the HashMap to be type String
                    hash.put(hashKey.value, hashValue);
                }
                value = hash;
                // return new PHPValue(value);
                what = "set";
            } else if (what.equals("string_length")) {
                if (c.equals(":")) {
                    len = Integer.parseInt(tmp.toString());
                    tmp.delete(0, tmp.length());
                    // println("\tstring_length="+ len);
                    what = "string_value";
                    consumeChars = 1;
                }
                if (len == -1) {
                    tmp.append(c);
                }
            } else if (what.equals("string_value")) {
                if (len > 0) {
                    tmp.append(c);
                } else {
                    value = tmp.toString();
                    what = "set";
                    // println("\tstring_value="+ value);
                }
                //主要就是这里了
                if(c.getBytes().length > 1){
                    len = len - 2;
                }
                else{
                    len--;
                }
            } else if (what.equals("integer")) {
                if (c.equals(";")) {
                    value = tmp.toString();
                    what = "set";
                } else {
                    tmp.append(c);
                }
            } else if (what.equals("double")) {
                if (c.equals(";")) {
                    value = tmp.toString();
                    what = "set";
                } else {
                    tmp.append(c);
                }
            } else if (what.equals("null")) {
                if (c.equals(";")) {
                    value = null;
                    what = "set";
                } else {
                    // Bad
                }
            }
            // What kind of variable is coming up next
            else {
                if (c.equals("a")) {
                    what = "array_length";
                } else if (c.equals("s")) {
                    what = "string_length";
                } else if (c.equals("i")) {
                    what = "integer";
                } else if (c.equals("d")) {
                    what = "double";
                } else if (c.equals("n")) {
                    what = "null";
                    // do NOT consume the next char ";"
                    continue;
                } else {
                    continue;
                }

                // Consume the ":" after variable type declaration
                consumeChars = 1;
                continue;
            }

            if (what.equals("set")) {
                return new PHPValue(value);
            }

        }

        return new PHPValue(value);
    }

}

原代码：

修改后：