Lots more stuff

src/Nadeko.Common/Extensions/EnumerableExtensions.cs

@@ -37,7 +37,9 @@ public static class EnumerableExtensions
     /// </returns>
     public static string Join<T>(this IEnumerable<T> data, string separator, Func<T, string>? func = null)
         => string.Join(separator, data.Select(func ?? (x => x?.ToString() ?? string.Empty)));
-
+    
+    
+    // todo have 2 different shuffles
     /// <summary>
     ///     Randomize element order by performing the Fisher-Yates shuffle
     /// </summary>

src/Nadeko.Common/Extensions/StringExtensions.cs

@@ -0,0 +1,139 @@
+using NadekoBot.Common.Yml;
+using System.Text;
+using System.Text.RegularExpressions;
+using Humanizer;
+using Nadeko.Common;
+
+namespace NadekoBot.Extensions;
+
+public static class StringExtensions
+{
+    private static readonly HashSet<char> _lettersAndDigits = new(Enumerable.Range(48, 10)
+                                                                            .Concat(Enumerable.Range(65, 26))
+                                                                            .Concat(Enumerable.Range(97, 26))
+                                                                            .Select(x => (char)x));
+
+    private static readonly Regex _filterRegex = new(@"discord(?:\.gg|\.io|\.me|\.li|(?:app)?\.com\/invite)\/(\w+)",
+        RegexOptions.Compiled | RegexOptions.IgnoreCase);
+
+    private static readonly Regex _codePointRegex =
+        new(@"(\\U(?<code>[a-zA-Z0-9]{8})|\\u(?<code>[a-zA-Z0-9]{4})|\\x(?<code>[a-zA-Z0-9]{2}))",
+            RegexOptions.Compiled);
+
+    public static string PadBoth(this string str, int length)
+    {
+        var spaces = length - str.Length;
+        var padLeft = (spaces / 2) + str.Length;
+        return str.PadLeft(padLeft, ' ').PadRight(length, ' ');
+    }
+
+    public static string StripHtml(this string input)
+        => Regex.Replace(input, "<.*?>", string.Empty);
+
+    public static string? TrimTo(this string? str, int maxLength, bool hideDots = false)
+        => hideDots ? str?.Truncate(maxLength, string.Empty) : str?.Truncate(maxLength);
+
+    public static string ToTitleCase(this string str)
+    {
+        var tokens = str.Split(new[] { " " }, StringSplitOptions.RemoveEmptyEntries);
+        for (var i = 0; i < tokens.Length; i++)
+        {
+            var token = tokens[i];
+            tokens[i] = token[..1].ToUpperInvariant() + token[1..];
+        }
+
+        return tokens.Join(" ").Replace(" Of ", " of ").Replace(" The ", " the ");
+    }
+
+    //http://www.dotnetperls.com/levenshtein
+    public static int LevenshteinDistance(this string s, string t)
+    {
+        var n = s.Length;
+        var m = t.Length;
+        var d = new int[n + 1, m + 1];
+
+        // Step 1
+        if (n == 0)
+            return m;
+
+        if (m == 0)
+            return n;
+
+        // Step 2
+        for (var i = 0; i <= n; d[i, 0] = i++)
+        {
+        }
+
+        for (var j = 0; j <= m; d[0, j] = j++)
+        {
+        }
+
+        // Step 3
+        for (var i = 1; i <= n; i++)
+            //Step 4
+        for (var j = 1; j <= m; j++)
+        {
+            // Step 5
+            var cost = t[j - 1] == s[i - 1] ? 0 : 1;
+
+            // Step 6
+            d[i, j] = Math.Min(Math.Min(d[i - 1, j] + 1, d[i, j - 1] + 1), d[i - 1, j - 1] + cost);
+        }
+
+        // Step 7
+        return d[n, m];
+    }
+
+    public static async Task<Stream> ToStream(this string str)
+    {
+        var ms = new MemoryStream();
+        var sw = new StreamWriter(ms);
+        await sw.WriteAsync(str);
+        await sw.FlushAsync();
+        ms.Position = 0;
+        return ms;
+    }
+
+    public static bool IsDiscordInvite(this string str)
+        => _filterRegex.IsMatch(str);
+
+    public static string Unmention(this string str)
+        => str.Replace("@", "ම", StringComparison.InvariantCulture);
+
+    public static string SanitizeMentions(this string str, bool sanitizeRoleMentions = false)
+    {
+        str = str.Replace("@everyone", "@everyοne", StringComparison.InvariantCultureIgnoreCase)
+                 .Replace("@here", "@һere", StringComparison.InvariantCultureIgnoreCase);
+        if (sanitizeRoleMentions)
+            str = str.SanitizeRoleMentions();
+
+        return str;
+    }
+
+    public static string SanitizeRoleMentions(this string str)
+        => str.Replace("<@&", "<ම&", StringComparison.InvariantCultureIgnoreCase);
+
+    public static string SanitizeAllMentions(this string str)
+        => str.SanitizeMentions().SanitizeRoleMentions();
+
+    public static string ToBase64(this string plainText)
+    {
+        var plainTextBytes = Encoding.UTF8.GetBytes(plainText);
+        return Convert.ToBase64String(plainTextBytes);
+    }
+
+    public static string GetInitials(this string txt, string glue = "")
+        => txt.Split(' ').Select(x => x.FirstOrDefault()).Join(glue);
+
+    public static bool IsAlphaNumeric(this string txt)
+        => txt.All(c => _lettersAndDigits.Contains(c));
+
+    public static string UnescapeUnicodeCodePoints(this string input)
+        => _codePointRegex.Replace(input,
+            me =>
+            {
+                var str = me.Groups["code"].Value;
+                var newString = YamlHelper.UnescapeUnicodeCodePoint(str);
+                return newString;
+            });
+}

src/Nadeko.Common/Nadeko.Common.csproj

@@ -7,6 +7,7 @@
     </PropertyGroup>
 
     <ItemGroup>
+        <PackageReference Include="Humanizer.Core" Version="2.14.1" />
         <PackageReference Include="Microsoft.Extensions.Caching.Memory" Version="7.0.0" />
         <PackageReference Include="NonBlocking" Version="2.1.1" />
         <PackageReference Include="OneOf" Version="3.0.223" />

src/Nadeko.Common/YamlHelper.cs

@@ -0,0 +1,48 @@
+#nullable disable
+namespace NadekoBot.Common.Yml;
+
+public static class YamlHelper
+{
+    // https://github.com/aaubry/YamlDotNet/blob/0f4cc205e8b2dd8ef6589d96de32bf608a687c6f/YamlDotNet/Core/Scanner.cs#L1687
+    /// <summary>
+    ///     This is modified code from yamldotnet's repo which handles parsing unicode code points
+    ///     it is needed as yamldotnet doesn't support unescaped unicode characters
+    /// </summary>
+    /// <param name="point">Unicode code point</param>
+    /// <returns>Actual character</returns>
+    public static string UnescapeUnicodeCodePoint(this string point)
+    {
+        var character = 0;
+
+        // Scan the character value.
+
+        foreach (var c in point)
+        {
+            if (!IsHex(c))
+                return point;
+
+            character = (character << 4) + AsHex(c);
+        }
+
+        // Check the value and write the character.
+
+        if (character is (>= 0xD800 and <= 0xDFFF) or > 0x10FFFF)
+            return point;
+
+        return char.ConvertFromUtf32(character);
+    }
+
+    public static bool IsHex(char c)
+        => c is (>= '0' and <= '9') or (>= 'A' and <= 'F') or (>= 'a' and <= 'f');
+
+    public static int AsHex(char c)
+    {
+        if (c <= '9')
+            return c - '0';
+
+        if (c <= 'F')
+            return c - 'A' + 10;
+
+        return c - 'a' + 10;
+    }
+}