.net – 如何获得正则表达式的组名？

string[,] patterns = {
    { "one-1","cat" },{ "two-2","dog" },{ "three-3","mouse" },{ "four-4","fish" },};

var regex = buildRegex(patterns);

string[] tests = { "foo","dog","bar","fish" };
foreach (var t in tests) {
    var m = regex.Match(t);
    Console.WriteLine("{0}: {1}",t,reportMatch(regex,m));
}

产量

foo: no match
dog: two-2 = dog
bar: no match
fish: four-4 = fish

首先,我们通过转义组名并将它们与模式组合来构建一个Regex实例.任何非单词字符都替换为序列_nnn_,其中nnn是其UTF-32值.

private static Regex buildRegex(string[,] inputs)
{   
    string regex = ""; 
    for (int i = 0; i <= inputs.GetUpperBound(0); i++) {
        var part = String.Format(
            "(?<{0}>{1})",Regex.Replace(inputs[i,0],@"([W_])",new MatchEvaluator(escape)),inputs[i,1]);

        regex += (regex.Length != 0 ? "|" : "") + part;
    }   

    return new Regex(regex);
}   

private static string escape(Match m)
{
    return "_" + Char.ConvertToUtf32(m.Groups[1].Value,0) + "_";
}

对于匹配,.NET库没有给我们一个简单的方法来获取组的名称,所以我们必须采取另一种方式：对于每个组名,我们检查该组是否匹配,如果是,则取消其名称,并让调用者知道名称和捕获的子字符串.

private static string reportMatch(Regex regex,Match m)
{   
    if (!m.Success)
        return "no match";

    foreach (var name in regex.GetGroupNames()) {
        if (name != "0" && m.Groups[name].Value.Length > 0)
            return String.Format(
                       "{0} = {1}",Regex.Replace(name,@"_(d+)_",new MatchEvaluator(unescape)),m.Groups[name].Value);
    }

    return null;
}   

private static string unescape(Match m)
{   
    return Char.ConvertFromUtf32(int.Parse(m.Groups[1].Value));
}