js 玩转正则表达式之语法高亮

(\/\/.*|\/\*[\S\s]+?\*\/) // 匹配注释
((["'])(?:\\.|[^\\\n])*?\3) // 匹配字符串
\b(break|continue|do|for|in|function|if|else|return|switch|this|throw|try|catch|finally|var|while|with|case|new|typeof|instance|delete|void)\b // 匹配关键词
\b(Object|Array|String|Number|Boolean|Function|RegExp|Date|Math|window|document|navigator|location)\b // 匹配内置对象
\b(true|false)\b // 匹配布尔值
\b(null|undefined|NaN)\b // 匹配各种空值，我觉得这个和布尔值一组比较合适。
(?:[^\W\d]|\$)[\$\w]* // 匹配普通的变量名
(0[xX][0-9a-fA-F]+|\d+(?:\.\d+)?(?:[eE]\d+)?) // 匹配数字 (前者不占用，这里就会有问题)
(?:[^\)\]\}]|^)(\/(?!\*)(?:\\.|[^\\\/\n])+?\/[gim]*) // 匹配正则
[\S\s] // 其他不能匹配的任意值

(\/\/.*|\/\*[\s\S]*?\*\/) // 匹配注释没改
("(?:[^"\\]|\\[\s\S])*"|'(?:[^'\\]|\\[\s\S])*') // 匹配注释优化过
\b(true|false|null|undefined|NaN)\b // 匹配布尔和空值，这几个比较常用，分组提前
\b(var|for|if|else|return|this|while|new|function|switch|case|typeof|do|in|throw|try|catch|finally|with|instance|delete|void|break|continue)\b // 匹配关键词，关键词顺序改了下
\b(document|Date|Math|window|Object|location|navigator|Array|String|Number|Boolean|Function|RegExp)\b //内置对象，单词顺序改了下
(?:[^\W\d]|\$)[\$\w]* // 匹配普通的变量名没改
(0[xX][0-9a-fA-F]+|\d+(?:\.\d+)?(?:[eE][+-]?\d+)?|\.\d+(?:[eE][+-]?\d+)?) // 匹配数字，修复了匹配
(?:^|[^\)\]\}])(\/(?!\*)(?:\\.|[^\\\/\n])+?\/[gim]*) // 匹配正则，这个最复杂，情况很多，我暂时没实力修改
[\s\S] // 匹配其他

// 单行注释
/**
* 多行注释
* @date 2014-05-12 22:24:37
* @name 测试一下
*/
var str1 = "123\"456";
var str2 = '123\'456';
var str3 = "123\
456";

var num = 123;
var arr = [12, 12.34, .12, 1e3, 1e+3, 1e-3, 12.34e3, 12.34e+3, 12.34e-3, .1234e3];
var arr = ["12", "12.34", '.12, 1e3', '1e+3, 1e-3', '12.34e3, 12.34e+3, 12.34e-3', ".1234e3"];
var arr = [/12", "12.34/, /"12\/34"/];

for (var i=0; i<1e3; i++) {
var node = document.getElementById("a"+i);
arr.push(node);
}

function test () {
return true;
}
test();

(function(window, undefined) {
var _re_js = new RegExp('(\\/\\/.*|\\/\\*[\\s\\S]*?\\*\\/)|("(?:[^"\\\\]|\\\\[\\s\\S])*"|\'(?:[^\'\\\\]|\\\\[\\s\\S])*\')|\\b(true|false|null|undefined|NaN)\\b|\\b(var|for|if|else|return|this|while|new|function|switch|case|typeof|do|in|throw|try|catch|finally|with|instance|delete|void|break|continue)\\b|\\b(document|Date|Math|window|Object|location|navigator|Array|String|Number|Boolean|Function|RegExp)\\b|(?:[^\\W\\d]|\\$)[\\$\\w]*|(0[xX][0-9a-fA-F]+|\\d+(?:\\.\\d+)?(?:[eE][+-]?\\d+)?|\\.\\d+(?:[eE][+-]?\\d+)?)|(?:^|[^\\)\\]\\}])(\\/(?!\\*)(?:\\\\.|[^\\\\\\/\\n])+?\\/[gim]*)|[\\s\\S]', 'g');

function htmlEncode(str) {
 var i, s = {
 //"&": /&/g,
 """: /"/g,
 "'": /'/g,
 "<": //g,
 " ": /\n/g,
 " ": / /g,
 " ": /\t/g
 };
 for (i in s) {
 str = str.replace(s[i], i);
 }
 return str;
 }

window.prettify = prettify;
})(window);

<!doctype html>
<html lang="en">
<head>
 <meta charset="UTF-8">
 <title>test</title>
 <style>
 /* 高亮样式 */
 *{font-size:12px;}
 code{word-break:break-all;}

.com {color:#008000;} /* 注释 */
 .comkey {color:#FFA500;} /* 注释标记 */
 .str {color:#808080;} /* 字符串 */
 .val {color:#000080;} /* true|false|null|undefined|NaN */
 .kwd {color:#000080;font:bold 12px 'comic sans ms', sans-serif;} /* 关键词 */
 .obj {color:#000080;} /* 内置对象 */
 .num {color:#FF0000;} /* 数字 */
 .reg {color:#8000FF;} /* 正则 */
 .func {color:#A355B9;} /* 函数 */
 </style>
</head>
<body>

<code id="regdemon">
// 单行注释
/**
* 多行注释
* @date 2014-05-12 22:24:37
* @name 测试一下
*/
var str1 = "123\"456";
var str2 = '123\'456';
var str3 = "123\
456";

var num = 123;
var arr = [12, 12.34, .12, 1e3, 1e+3, 1e-3, 12.34e3, 12.34e+3, 12.34e-3, .1234e3];
var arr = ["12", "12.34", '.12, 1e3', '1e+3, 1e-3', '12.34e3, 12.34e+3, 12.34e-3', ".1234e3"];
var arr = [/12", "12.34/, /"12\/34"/];

for (var i=0; i<1e3; i++) {
var node = document.getElementById("a"+i);
arr.push(node);
}

function test () {
return true;
}
test();

(function(window, undefined) {
var _re_js = new RegExp('(\\/\\/.*|\\/\\*[\\s\\S]*?\\*\\/)|("(?:[^"\\\\]|\\\\[\\s\\S])*"|\'(?:[^\'\\\\]|\\\\[\\s\\S])*\')|\\b(true|false|null|undefined|NaN)\\b|\\b(var|for|if|else|return|this|while|new|function|switch|case|typeof|do|in|throw|try|catch|finally|with|instance|delete|void|break|continue)\\b|\\b(document|Date|Math|window|Object|location|navigator|Array|String|Number|Boolean|Function|RegExp)\\b|(?:[^\\W\\d]|\\$)[\\$\\w]*|(0[xX][0-9a-fA-F]+|\\d+(?:\\.\\d+)?(?:[eE][+-]?\\d+)?|\\.\\d+(?:[eE][+-]?\\d+)?)|(?:^|[^\\)\\]\\}])(\\/(?!\\*)(?:\\\\.|[^\\\\\\/\\n])+?\\/[gim]*)|[\\s\\S]', 'g');