重写Jeff的代码，使其更简洁

    public static string RemapInternationalCharToAscii(char c)
    {
        var s = c.ToString().ToLowerInvariant();

        var mappings = new Dictionary<string, string>
        {
            { "a", "àåáâäãåą" },
            { "c", "çćčĉ" },
            { "d", "đ" },
            { "e", "èéêëę" },
            { "g", "ğĝ" },
            { "h", "ĥ" },
            { "i", "ìíîïı" },
            { "j", "ĵ" },
            { "l", "ł" },
            { "n", "ñń" },
            { "o", "òóôõöøőð" },
            { "r", "ř" },
            { "s", "śşšŝ" },
            { "ss", "ß" },
            { "th", "Þ" },
            { "u", "ùúûüŭů" },
            { "y", "ýÿ" },
            { "z", "żźž" }
        };

        foreach(var mapping in mappings)
        {
            if (mapping.Value.Contains(s))
                return mapping.Key;
        }

        return string.Empty;
    }

为了更好地衡量，这里是WordPress中的PHP函数…我认为WordPress是使用花哨链接的最受欢迎的平台之一。

    function sanitize_title_with_dashes($title) {
            $title = strip_tags($title);
            // Preserve escaped octets.
            $title = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '---$1---', $title);
            // Remove percent signs that are not part of an octet.
            $title = str_replace('%', '', $title);
            // Restore octets.
            $title = preg_replace('|---([a-fA-F0-9][a-fA-F0-9])---|', '%$1', $title);
            $title = remove_accents($title);
            if (seems_utf8($title)) {
                    if (function_exists('mb_strtolower')) {
                            $title = mb_strtolower($title, 'UTF-8');
                    }
                    $title = utf8_uri_encode($title, 200);
            }
            $title = strtolower($title);
            $title = preg_replace('/&.+?;/', '', $title); // kill entities
            $title = preg_replace('/[^%a-z0-9 _-]/', '', $title);
            $title = preg_replace('/\s+/', '-', $title);
            $title = preg_replace('|-+|', '-', $title);
            $title = trim($title, '-');
            return $title;
    }

这个函数以及一些支持函数可以在wp-includes/formatting.php中找到。

您可以使用以下帮助器方法。它可以转换Unicode字符。

public static string ConvertTextToSlug(string s)
{
    StringBuilder sb = new StringBuilder();

    bool wasHyphen = true;

    foreach (char c in s)
    {
        if (char.IsLetterOrDigit(c))
        {
            sb.Append(char.ToLower(c));
            wasHyphen = false;
        }
        else
            if (char.IsWhiteSpace(c) && !wasHyphen)
            {
                sb.Append('-');
                wasHyphen = true;
            }
    }

    // Avoid trailing hyphens
    if (wasHyphen && sb.Length > 0)
        sb.Length--;

    return sb.ToString().Replace("--","-");
}

重写Jeff的代码，使其更简洁

    public static string RemapInternationalCharToAscii(char c)
    {
        var s = c.ToString().ToLowerInvariant();

        var mappings = new Dictionary<string, string>
        {
            { "a", "àåáâäãåą" },
            { "c", "çćčĉ" },
            { "d", "đ" },
            { "e", "èéêëę" },
            { "g", "ğĝ" },
            { "h", "ĥ" },
            { "i", "ìíîïı" },
            { "j", "ĵ" },
            { "l", "ł" },
            { "n", "ñń" },
            { "o", "òóôõöøőð" },
            { "r", "ř" },
            { "s", "śşšŝ" },
            { "ss", "ß" },
            { "th", "Þ" },
            { "u", "ùúûüŭů" },
            { "y", "ýÿ" },
            { "z", "żźž" }
        };

        foreach(var mapping in mappings)
        {
            if (mapping.Value.Contains(s))
                return mapping.Key;
        }

        return string.Empty;
    }

我知道这是一个非常老的问题，但由于大多数浏览器现在都支持unicode url，我在XRegex中找到了一个很好的解决方案，它可以转换除字母以外的所有内容(在所有语言中都是'-')。

这可以在几种编程语言中实现。

模式是\\p{^L}+，然后你只需要用它来替换所有非字母到'-'。

node.js中xregex模块的工作示例。

var text = 'This ! can @ have # several $ letters % from different languages such as עברית or Español';

var slugRegEx = XRegExp('((?!\\d)\\p{^L})+', 'g');

var slug = XRegExp.replace(text, slugRegEx, '-').toLowerCase();

console.log(slug) ==> "this-can-have-several-letters-from-different-languages-such-as-עברית-or-español"

下面是Jeff代码的我的版本。我做了以下修改:

The hyphens were appended in such a way that one could be added, and then need removing as it was the last character in the string. That is, we never want “my-slug-”. This means an extra string allocation to remove it on this edge case. I’ve worked around this by delay-hyphening. If you compare my code to Jeff’s the logic for this is easy to follow. His approach is purely lookup based and missed a lot of characters I found in examples while researching on Stack Overflow. To counter this, I first peform a normalisation pass (AKA collation mentioned in Meta Stack Overflow question Non US-ASCII characters dropped from full (profile) URL), and then ignore any characters outside the acceptable ranges. This works most of the time... ... For when it doesn’t I’ve also had to add a lookup table. As mentioned above, some characters don’t map to a low ASCII value when normalised. Rather than drop these I’ve got a manual list of exceptions that is doubtless full of holes, but it is better than nothing. The normalisation code was inspired by Jon Hanna’s great post in Stack Overflow question How can I remove accents on a string?. The case conversion is now also optional. public static class Slug { public static string Create(bool toLower, params string[] values) { return Create(toLower, String.Join("-", values)); } /// <summary> /// Creates a slug. /// References: /// http://www.unicode.org/reports/tr15/tr15-34.html /// https://meta.stackexchange.com/questions/7435/non-us-ascii-characters-dropped-from-full-profile-url/7696#7696 /// https://stackoverflow.com/questions/25259/how-do-you-include-a-webpage-title-as-part-of-a-webpage-url/25486#25486 /// https://stackoverflow.com/questions/3769457/how-can-i-remove-accents-on-a-string /// </summary> /// <param name="toLower"></param> /// <param name="normalised"></param> /// <returns></returns> public static string Create(bool toLower, string value) { if (value == null) return ""; var normalised = value.Normalize(NormalizationForm.FormKD); const int maxlen = 80; int len = normalised.Length; bool prevDash = false; var sb = new StringBuilder(len); char c; for (int i = 0; i < len; i++) { c = normalised[i]; if ((c >= 'a' && c <= 'z') || (c >= '0' && c <= '9')) { if (prevDash) { sb.Append('-'); prevDash = false; } sb.Append(c); } else if (c >= 'A' && c <= 'Z') { if (prevDash) { sb.Append('-'); prevDash = false; } // Tricky way to convert to lowercase if (toLower) sb.Append((char)(c | 32)); else sb.Append(c); } else if (c == ' ' || c == ',' || c == '.' || c == '/' || c == '\\' || c == '-' || c == '_' || c == '=') { if (!prevDash && sb.Length > 0) { prevDash = true; } } else { string swap = ConvertEdgeCases(c, toLower); if (swap != null) { if (prevDash) { sb.Append('-'); prevDash = false; } sb.Append(swap); } } if (sb.Length == maxlen) break; } return sb.ToString(); } static string ConvertEdgeCases(char c, bool toLower) { string swap = null; switch (c) { case 'ı': swap = "i"; break; case 'ł': swap = "l"; break; case 'Ł': swap = toLower ? "l" : "L"; break; case 'đ': swap = "d"; break; case 'ß': swap = "ss"; break; case 'ø': swap = "o"; break; case 'Þ': swap = "th"; break; } return swap; } }

关于更多的细节，单元测试，以及为什么Facebook的URL方案比堆栈溢出更聪明的解释，我在我的博客上有一个扩展版本。