在Javascript中使用正则表达式标记字符串

Question

假设我有一个包含换行符和制表符的长字符串，如:

var x = "This is a long string.nt This is another one on next line.";

那么我们如何使用正则表达式将这个字符串分割成token呢?

我不想使用.split(' ')，因为我想学习Javascript的正则表达式。

更复杂的字符串可以是这样的:

var y = "This @is a #long $string. Alright, lets split this.";

现在我只想从这个字符串中提取有效的单词，不包含特殊字符和标点符号，即我想要这些:

var xwords = ["This", "is", "a", "long", "string", "This", "is", "another", "one", "on", "next", "line"];
var ywords = ["This", "is", "a", "long", "string", "Alright", "lets", "split", "this"];

Answer 1

下面是一个jsfiddle示例:http://jsfiddle.net/ayezutov/BjXw5/1/

基本上，代码非常简单:

var y = "This @is a #long $string. Alright, lets split this.";
var regex = /[^s]+/g; // This is "multiple not space characters, which should be searched not once in string"
var match = y.match(regex);
for (var i = 0; i<match.length; i++)
{
    document.write(match[i]);
    document.write('<br>');
}

:基本上，您可以展开分隔符列表:http://jsfiddle.net/ayezutov/BjXw5/2/

var regex = /[^s.,!?]+/g;

更新2:

一直都只有字母:http://jsfiddle.net/ayezutov/BjXw5/3/

var regex = /w+/g;

Answer 2

使用s+对字符串进行标记

Answer 3

exec可以遍历匹配项以删除非单词(W)字符。

var A= [], str= "This @is a #long $string. Alright, let's split this.",
rx=/W*([a-zA-Z][a-zA-Z']*)(W+|$)/g, words;
while((words= rx.exec(str))!= null){
    A.push(words[1]);
}
A.join(', ')
/*  returned value: (String)
This, is, a, long, string, Alright, let's, split, this
*/

Answer 4

var words = y.split(/[^A-Za-z0-9]+/);

Answer 5

这是一个使用regex组使用不同类型的标记对文本进行标记的解决方案。

您可以在这里测试代码https://jsfiddle.net/u3mvca6q/5/

/*
Basic Regex explanation:
/                   Regex start
(w+)               First group, words     w means ASCII letter with w     + means 1 or more letters
|                   or
(,|!)               Second group, punctuation
|                   or
(s)                Third group, white spaces
/                   Regex end
g                   "global", enables looping over the string to capture one element at a time
Regex result:
result[0] : default group : any match
result[1] : group1 : words
result[2] : group2 : punctuation , !
result[3] : group3 : whitespace
*/
var basicRegex = /(w+)|(,|!)|(s)/g;
/*
Advanced Regex explanation:
[a-zA-Zu0080-u00FF] instead of w     Supports some Unicode letters instead of ASCII letters only. Find Unicode ranges here https://apps.timwhitlock.info/js/regex
(...|.|,|!|?)                      Identify ellipsis (...) and points as separate entities
You can improve it by adding ranges for special punctuation and so on
*/
var advancedRegex = /([a-zA-Zu0080-u00FF]+)|(...|.|,|!|?)|(s)/g;
var basicString = "Hello, this is a random message!";
var advancedString = "Et en français ? Avec des caractères spéciaux ... With one point at the end.";
console.log("------------------");
var result = null;
do {
    result = basicRegex.exec(basicString)
    console.log(result);
} while(result != null)
console.log("------------------");
var result = null;
do {
    result = advancedRegex.exec(advancedString)
    console.log(result);
} while(result != null)
/*
Output:
Array [ "Hello",        "Hello",        undefined,  undefined ]
Array [ ",",            undefined,      ",",        undefined ]
Array [ " ",            undefined,      undefined,  " "       ]
Array [ "this",         "this",         undefined,  undefined ]
Array [ " ",            undefined,      undefined,  " "       ]
Array [ "is",           "is",           undefined,  undefined ]
Array [ " ",            undefined,      undefined,  " "       ]
Array [ "a",            "a",            undefined,  undefined ]
Array [ " ",            undefined,      undefined,  " "       ]
Array [ "random",       "random",       undefined,  undefined ]
Array [ " ",            undefined,      undefined,  " "       ]
Array [ "message",      "message",      undefined,  undefined ]
Array [ "!",            undefined,      "!",        undefined ]
null
*/

Answer 6

为了提取纯文字字符，我们使用w符号。这是否匹配Unicode字符取决于实现，您可以使用此参考来查看您的语言/库的情况。

请参阅Alexander Yezutov关于如何将此应用于表达式的回答(更新2)