对于那些希望在拆分函数中进行更多自定义的人，我编写了一个递归算法，它使用要拆分的字符列表拆分给定的字符串。在我看到上面的帖子之前，我写了这篇文章。我希望它能帮助一些沮丧的程序员。

splitString = function(string, splitters) {
    var list = [string];
    for(var i=0, len=splitters.length; i<len; i++) {
        traverseList(list, splitters[i], 0);
    }
    return flatten(list);
}

traverseList = function(list, splitter, index) {
    if(list[index]) {
        if((list.constructor !== String) && (list[index].constructor === String))
            (list[index] != list[index].split(splitter)) ? list[index] = list[index].split(splitter) : null;
        (list[index].constructor === Array) ? traverseList(list[index], splitter, 0) : null;
        (list.constructor === Array) ? traverseList(list, splitter, index+1) : null;    
    }
}

flatten = function(arr) {
    return arr.reduce(function(acc, val) {
        return acc.concat(val.constructor === Array ? flatten(val) : val);
    },[]);
}

var stringToSplit = "people and_other/things";
var splitList = [" ", "_", "/"];
splitString(stringToSplit, splitList);

上面的例子返回:["people"， "and"， "other"， "things"]

注:flatten函数取自Rosetta Code

我发现我需要这样做的主要原因之一是在/和\上拆分文件路径。这是一个有点棘手的正则表达式，所以我将它贴在这里作为参考:

var splitFilePath = filePath.split(/[\/\\]/);

在Github上查看我的简单库

如果你真的不想访问或与repo交互，下面是工作代码:

/**
 * 
 * @param {type} input The string input to be split
 * @param {type} includeTokensInOutput If true, the tokens are retained in the splitted output.
 * @param {type} tokens The tokens to be employed in splitting the original string.
 * @returns {Scanner}
 */
function Scanner(input, includeTokensInOutput, tokens) {
    this.input = input;
    this.includeTokensInOutput = includeTokensInOutput;
    this.tokens = tokens;
}

Scanner.prototype.scan = function () {
    var inp = this.input;

    var parse = [];
    this.tokens.sort(function (a, b) {
        return b.length - a.length; //ASC, For Descending order use: b - a
    });
    for (var i = 0; i < inp.length; i++) {


        for (var j = 0; j < this.tokens.length; j++) {

            var token = this.tokens[j];
            var len = token.length;
            if (len > 0 && i + len <= inp.length) {
                var portion = inp.substring(i, i + len);
                if (portion === token) {
                    if (i !== 0) {//avoid empty spaces
                        parse[parse.length] = inp.substring(0, i);
                    }
                    if (this.includeTokensInOutput) {
                        parse[parse.length] = token;
                    }
                    inp = inp.substring(i + len);
                    i = -1;
                    break;
                }

            }

        }

    }
    if (inp.length > 0) {
          parse[parse.length] = inp;
    }

    return parse;


};

用法很简单:

    var tokens = new Scanner("ABC+DE-GHIJK+LMNOP", false , new Array('+','-')).scan();

console.log(tokens); 

给:

['ABC', 'DE', 'GHIJK', 'LMNOP']

如果您希望在输出中包含分隔令牌(+和-)，将false设置为true，瞧!它仍然有效。

现在的用法是:

var tokens = new Scanner("ABC+DE-GHIJK+LMNOP", true , new Array('+','-')).scan();

and

console.log(tokens);

将:

['ABC', '+', 'DE', '-', 'GHIJK', '+', 'LMNOP']

享受吧!

传入一个regexp作为参数:

js> "Hello awesome, world!".split(/[\s,]+/)
Hello,awesome,world!

编辑补充:

你可以通过选择数组的长度减去1来获得最后一个元素:

>>> bits = "Hello awesome, world!".split(/[\s,]+/)
["Hello", "awesome", "world!"]
>>> bit = bits[bits.length - 1]
"world!"

．.． 如果模式不匹配:

>>> bits = "Hello awesome, world!".split(/foo/)
["Hello awesome, world!"]
>>> bits[bits.length - 1]
"Hello awesome, world!"

例如，如果你在String 07:05:45PM中使用了split and replace

var hour = time.replace("PM", "").split(":");

结果

[ '07', '05', '45' ]

棘手的方法:

var s = "dasdnk asd, (naks) :d skldma";
var a = s.replace('(',' ').replace(')',' ').replace(',',' ').split(' ');
console.log(a);//["dasdnk", "asd", "naks", ":d", "skldma"]