packet

Split.js

/*
 * @name:SplitURI.js
 * @description:分割URL
 *  最小分割单元为12个字符长度，UTF8编码中可能存在4个字节编码的字符
 *  UTF8各字节字符编码最大值：
 *    单字节字符：0-127
 *    其他字节字符末字节：128-191
 *    双字节字符首字节：192-223
 *    三字节字符首字节：224-239
 *    四字节字符首字节：240-247
 *
 * @author:[email protected]
 * @date:2012-05-26
 * @param:
 *      source[String]:source String
 *      limitLength[Number]:min-length
 *      encode[Boolean]:whether use encodeURIComponent
 * @see:http://tools.ietf.org/html/rfc3629#section-3
   Char. number range  |        UTF-8 octet sequence
 *    (hexadecimal)    |              (binary)
 * --------------------+---------------------------------------------
 * 0000 0000-0000 007F | 0xxxxxxx
 * 0000 0080-0000 07FF | 110xxxxx 10xxxxxx
 * 0000 0800-0000 FFFF | 1110xxxx 10xxxxxx 10xxxxxx
 * 0001 0000-0010 FFFF | 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
 *      
 * @todo:
 * @changelog:
 */
var SplitURI = {
    c16to10:function(s16){
        var s = s16.replace(/^(0x)/i,'');

        return parseInt(s,16);
    },
    /*
     * 检测字节完整性 %xx
     */
    checkOctet:function(urlString){
        var s = urlString,
            r = /(%[0-9a-fA-F]{0,1})$/i,
            ret  = {
                "urlString":"",
                "brokenOctet":""
            };

        ret["urlString"] = s.replace(r,function(g){
            ret["brokenOctet"] = g;
            return '';
        });

        return ret;
    },
    /*
     * 检测字符完整性
    */
    checkCharacter:function(urlString,brokenCharacter){
        // 根据最后字节编码判断该字节编码是否为单字节字符，如果不是查找该字符完整的字符编码
        // 返回完整的UTF8字节编码，和尾部的字节所在字符编码片段
        var s = urlString,
            r = /(?:%([0-9a-fA-F]{2}))$/i,
            ret = {
                "urlString":"",
                "brokenCharacter":brokenCharacter || ''
            },
            isIntact = true;

        s = s.replace(r,function(g,octet){
            var n = SplitURI.c16to10(octet);

            // 判断末字节编码
            if(n<128){
                // 单字节字符
                isIntact = true;
                return g;
            }else if(n<=191){
                // 多字节字符非首字节
                isIntact = false;
            }else if(n<=247){
                // 多字节字符首字节
                isIntact = true;
            }

            // 非单字节字符编码结尾都为非完整字符编码，移除保存到ret["brokenCharacter"]
            ret["brokenCharacter"] = g + ret["brokenCharacter"];

            return '';
        });

        ret["urlString"] = s;

        if(!isIntact){
            // 继续校验末字节字符完整性
            ret = SplitURI.checkCharacter(ret["urlString"],ret["brokenCharacter"]);
        }

        return ret;
    },
    split:function(s,limitLength,encode){
        if(!limitLength || limitLength<12) return [];

        var s = !!encode ? encodeURIComponent(s) : s,
            r = /^(?:%([0-9a-fA-F]{2}))/i,
            ret = [],
            t = '',
            isIntact,
            o,
            c;

        while(s){
            isIntact = true;
            t = s.slice(0,limitLength);
            s = s.slice(limitLength);

            // 检测字节编码完整性
            o = SplitURI.checkOctet(t);
            // 编码片段存入下一个片段
            s = o["brokenOctet"] + s;

            if(s){
                s.replace(r,function(g,octet){
                    var n = SplitURI.c16to10(octet);

                    // 下一个分段不是以10******的字符编码开头
                    // 说明上一个分段是一个完整的字符编码
                    if(n>=128 && n<=191){
                        isIntact = false;
                    }

                    return '';
                })
            }

            if(isIntact){
                ret.push(o["urlString"]);
            }else{
                // o["urlString"]不是完整的字符编码
                c = SplitURI.checkCharacter(o["urlString"]);
                s = c["brokenCharacter"] + s;
                ret.push(c["urlString"]);
            }
        }

        return ret;
    }
}