Regex将所有内容转换为小写，但URL除外。

Question

给出一个免费的文本

你好，世界http://example.com/?param=FooBar快餐店

..。除了大多数常见的URL模式(因为它们是需要保留大小写的部分)之外，如何才能将所有内容转换为小写字母呢？

上面的结果将是

你好，世界http://example.com/?param=FooBar快餐店

我在用JavaScript。谢谢!

Answer 1

我会这样做：

var str = 'Hello World http://example.com/?param=FooBar Foo Bar';

str.replace(/[^\s]+/g, function (match) {
    return match.indexOf('http') === 0 ? match : match.toLowerCase();
})

http://jsfiddle.net/xMPFW/1/

根据您想要的具体程度，您可以在回调中包含一个更复杂的URL检查--如下所示：https://stackoverflow.com/a/3809435/1200182

Answer 2

这应该是可行的：

var s = 'Hello World http://example.com/?param=FooBar FOO Bar';
var r = s.replace(/([^ A-Z]*)([A-Z])/g, function($1, $2) { 
     return /https?:\/\/\S+/.test($1) ? $1 : $1.toLowerCase(); 
});
//=> hello world http://example.com/?param=Foobar foo bar

Answer 3

将字符串标记化，然后利用来自这里的URI Regex检查令牌是否是URI令牌，如果没有使其小写。

var regex = new RegExp("([A-Za-z][A-Za-z0-9+\\-.]*):(?:(//)(?:((?:[A-Za-z0-9\\-._~!$&'()*+,;=:]|%[0-9A-Fa-f]{2})*)@)?((?:\\[(?:(?:(?:(?:[0-9A-Fa-f]{1,4}:){6}|::(?:[0-9A-Fa-f]{1,4}:){5}|(?:[0-9A-Fa-f]{1,4})?::(?:[0-9A-Fa-f]{1,4}:){4}|(?:(?:[0-9A-Fa-f]{1,4}:){0,1}[0-9A-Fa-f]{1,4})?::(?:[0-9A-Fa-f]{1,4}:){3}|(?:(?:[0-9A-Fa-f]{1,4}:){0,2}[0-9A-Fa-f]{1,4})?::(?:[0-9A-Fa-f]{1,4}:){2}|(?:(?:[0-9A-Fa-f]{1,4}:){0,3}[0-9A-Fa-f]{1,4})?::[0-9A-Fa-f]{1,4}:|(?:(?:[0-9A-Fa-f]{1,4}:){0,4}[0-9A-Fa-f]{1,4})?::)(?:[0-9A-Fa-f]{1,4}:[0-9A-Fa-f]{1,4}|(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?))|(?:(?:[0-9A-Fa-f]{1,4}:){0,5}[0-9A-Fa-f]{1,4})?::[0-9A-Fa-f]{1,4}|(?:(?:[0-9A-Fa-f]{1,4}:){0,6}[0-9A-Fa-f]{1,4})?::)|[Vv][0-9A-Fa-f]+\\.[A-Za-z0-9\\-._~!$&'()*+,;=:]+)\\]|(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)|(?:[A-Za-z0-9\\-._~!$&'()*+,;=]|%[0-9A-Fa-f]{2})*))(?::([0-9]*))?((?:/(?:[A-Za-z0-9\\-._~!$&'()*+,;=:@]|%[0-9A-Fa-f]{2})*)*)|/((?:(?:[A-Za-z0-9\\-._~!$&'()*+,;=:@]|%[0-9A-Fa-f]{2})+(?:/(?:[A-Za-z0-9\\-._~!$&'()*+,;=:@]|%[0-9A-Fa-f]{2})*)*)?)|((?:[A-Za-z0-9\\-._~!$&'()*+,;=:@]|%[0-9A-Fa-f]{2})+(?:/(?:[A-Za-z0-9\\-._~!$&'()*+,;=:@]|%[0-9A-Fa-f]{2})*)*)|)(?:\\?((?:[A-Za-z0-9\\-._~!$&'()*+,;=:@/?]|%[0-9A-Fa-f]{2})*))?(?:\\#((?:[A-Za-z0-9\\-._~!$&'()*+,;=:@/?]|%[0-9A-Fa-f]{2})*))?")

var text = 'Hello World http://example.com/?param=FooBar Foo Bar';
var tokens = text.split(' ');
var lowerText = '';

for (var i = 0; i < tokens.length; i++) {
    if (i != 0)
        lowerText += ' ';
    if (!tokens[i].match(regex))
        lowerText += tokens[i].toLowerCase();
    else
        lowerText += tokens[i];
}