在 Javascript 中使用正则表达式对字符串进行标记

Question

假设我有一个包含换行符和制表符的长字符串：

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

那么我们如何使用正则表达式将此字符串拆分为标记？

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

更复杂的字符串可能是这样的：

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

现在我只想从此字符串中提取有效的单词，没有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

这是您所要求的 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>');
}

更新：
基本上，您可以扩展分隔符字符列表： http://jsfiddle.net/ayezutov/BjXw5/2/

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

更新2：
始终只有字母：
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 可以循环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

这是一个使用正则表达式组来使用不同类型的标记对文本进行标记的解决方案。

您可以在此处测试代码 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-Z\u0080-\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-Z\u0080-\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 5

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

Answer 6

为了提取仅限单词的字符，我们使用 \w 符号。这是否与 Unicode 字符匹配取决于实现，您可以使用此参考 查看您的语言/库的情况。

请参阅 Alexander Yezutov 的回答（更新 2），了解如何将其应用到表达式中。