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"]

我认为如果你指定你想要保留什么，而不是你想要删除什么，会更容易。

如果你只想要英语单词，你可以这样用:

text.match(/[a-z'\-]+/gi);

示例(运行片段):

var R=[/[a-z'\-]+/gi,/[a-z'\-\s]+/gi]; var s=document.getElementById('s'); for(var i=0;i<R.length;i++) { var o=document.createElement('option'); o.innerText=R[i]+''; o.value=i; s.appendChild(o); } var t=document.getElementById('t'); var r=document.getElementById('r'); s.onchange=function() { r.innerHTML=''; var x=s.value; if((x>=0)&&(x<R.length)) x=t.value.match(R[x]); for(i=0;i<x.length;i++) { var li=document.createElement('li'); li.innerText=x[i]; r.appendChild(li); } } <textarea id="t" style="width:70%;height:12em">even, test; spider-man But saying o'er what I have said before: My child is yet a stranger in the world; She hath not seen the change of fourteen years, Let two more summers wither in their pride, Ere we may think her ripe to be a bride. —Shakespeare, William. The Tragedy of Romeo and Juliet</textarea> <p><select id="s"> <option selected>Select a regular expression</option> <!-- option value="1">/[a-z'\-]+/gi</option> <option value="2">/[a-z'\-\s]+/gi</option --> </select></p> <ol id="r" style="display:block;width:auto;border:1px inner;overflow:scroll;height:8em;max-height:10em;"></ol> </div>

我将为这样的函数提供一个经典的实现。代码可以在几乎所有版本的JavaScript中运行，并且在某种程度上是最优的。

它不使用正则表达式，这很难维护 它没有使用JavaScript的新特性 它不使用需要更多计算机内存的多次.split() .join()调用

只是纯代码:

var text = "Create a function, that will return an array (of string), with the words inside the text";

println(getWords(text));

function getWords(text)
{
    let startWord = -1;
    let ar = [];

    for(let i = 0; i <= text.length; i++)
    {
        let c = i < text.length ? text[i] : " ";

        if (!isSeparator(c) && startWord < 0)
        {
            startWord = i;
        }

        if (isSeparator(c) && startWord >= 0)
        {
            let word = text.substring(startWord, i);
            ar.push(word);

            startWord = -1;
        }
    }

    return ar;
}

function isSeparator(c)
{
    var separators = [" ", "\t", "\n", "\r", ",", ";", ".", "!", "?", "(", ")"];
    return separators.includes(c);
}

你可以看到代码在playground中运行: https://codeguppy.com/code.html?IJI0E4OGnkyTZnoszAzf

通过。com/或。net/分割URL

url.split(/\.com\/|\.net\//)

一个简单的方法是用每个分隔符处理字符串中的每个字符，并构建一个分隔符数组:

splix = function ()
{
  u = [].slice.call(arguments); v = u.slice(1); u = u[0]; w = [u]; x = 0;

  for (i = 0; i < u.length; ++i)
  {
    for (j = 0; j < v.length; ++j)
    {
      if (u.slice(i, i + v[j].length) == v[j])
      {
        y = w[x].split(v[j]); w[x] = y[0]; w[++x] = y[1];
      };
    };
  };
  
  return w;
};

console.logg = function () { document.body.innerHTML += "<br>" + [].slice.call(arguments).join(); } splix = function() { u = [].slice.call(arguments); v = u.slice(1); u = u[0]; w = [u]; x = 0; console.logg("Processing: <code>" + JSON.stringify(w) + "</code>"); for (i = 0; i < u.length; ++i) { for (j = 0; j < v.length; ++j) { console.logg("Processing: <code>[\x22" + u.slice(i, i + v[j].length) + "\x22, \x22" + v[j] + "\x22]</code>"); if (u.slice(i, i + v[j].length) == v[j]) { y = w[x].split(v[j]); w[x] = y[0]; w[++x] = y[1]; console.logg("Currently processed: " + JSON.stringify(w) + "\n"); }; }; }; console.logg("Return: <code>" + JSON.stringify(w) + "</code>"); }; setTimeout(function() { console.clear(); splix("1.23--4", ".", "--"); }, 250); @import url("http://fonts.googleapis.com/css?family=Roboto"); body {font: 20px Roboto;}

用法:splix(字符串，分隔符…) 示例:splix("1.23- 4"， "."， "——") 返回:["1"，"23"，"4"]