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!

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"]

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

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(/[\/\\]/);

下面是在ES6中实现相同的新方法:

SplitByString(source, splitBy) { var splitter = splitBy.split("); splitter.push([源]);//推送初始值 返回分配器。reduceRight(函数(累加器，curValue) { Var k = []; 蓄电池。v => k =[…k…v.split (curValue)]); 返回k; })； ｝ Var source = "abc,def#hijk*lmn,opq#rst*uvw,xyz"; var splitBy = "，*#"; splitBy console.log (SplitByString(源));

在这个函数中请注意:

不涉及正则表达式 以源代码中显示的相同顺序返回拆分后的值

以上代码的结果为:

My refactor of @Brian answer var string = 'and this is some kind of information and another text and simple and some egample or red or text'; var separators = ['and', 'or']; function splitMulti(str, separators){ var tempChar = 't3mp'; //prevent short text separator in split down //split by regex e.g. \b(or|and)\b var re = new RegExp('\\b(' + separators.join('|') + ')\\b' , "g"); str = str.replace(re, tempChar).split(tempChar); // trim & remove empty return str.map(el => el.trim()).filter(el => el.length > 0); } console.log(splitMulti(string, separators))