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!

您可以将所有想要单独或共同用作分隔符的字符合并到一个正则表达式中，并将它们传递给split函数。例如，你可以这样写:

console.log( "dasdnk asd, (naks) :d skldma".split(/[ \(,\)]+/) );

输出将是:

["dasdnk", "asd", "naks", ":d", "skldma"]

让我们保持简单:(在你的RegEx中添加“[]+”表示“1或更多”)

这意味着“+”和“{1，}”是相同的。

var words = text.split(/[ .:;?!~,`"&|()<>{}\[\]\r\n/\\]+/); // note ' and - are kept

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"]

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

我使用regexp:

str =  'Write a program that extracts from a given text all palindromes, e.g. "ABBA", "lamal", "exe".';

var strNew = str.match(/\w+/g);

// Output: ["Write", "a", "program", "that", "extracts", "from", "a", "given", "text", "all", "palindromes", "e", "g", "ABBA", "lamal", "exe"]