[RegexDiff] MihaZupan/runtime/regex-fewerUintCasts

[MihuBot]

Job completed in 11 minutes 29 seconds.

Using arguments: regexdiff -SkipJitDiff -UploadTestAssembly -NoPRLink

Examples of GeneratedRegex source diffs

"\\s+" (24455 uses)

[GeneratedRegex("\\s+", RegexOptions.None)]

         /// <summary>Whether <see cref="s_defaultTimeout"/> is non-infinite.</summary>
         internal static readonly bool s_hasTimeout = s_defaultTimeout != Regex.InfiniteMatchTimeout;
         
-        /// <summary>Supports searching for characters in or not in "\t\n\v\f\r \u0085             \u2028\u2029  　".</summary>
-        internal static readonly SearchValues<char> s_whitespace = SearchValues.Create("\t\n\v\f\r \u0085             \u2028\u2029  　");
+        /// <summary>Supports searching for characters in or not in "\t\n\v\f\r \u0085             \u2028\u2029  　".</summary>
+        internal static readonly SearchValues<char> s_whitespace = SearchValues.Create("\t\n\v\f\r \u0085             \u2028\u2029  　");
     }
 }

"[^'\",]+'[^^']+'|[^'\",]+\"[^\"]+\"|[^,]+" (21563 uses)

[GeneratedRegex("[^'\",]+'[^^']+'|[^'\",]+\"[^\"]+\"|[^,]+", RegexOptions.None)]

  }
  
  // Match '\''.
-   if ((uint)slice.Length < 2 || slice[1] != '\'')
+   if (slice.Length < 2 || slice[1] != '\'')
  {
      goto AlternationBranch;
  }
  }
  
  // Match '"'.
-   if ((uint)slice.Length < 2 || slice[1] != '"')
+   if (slice.Length < 2 || slice[1] != '"')
  {
      goto AlternationBranch1;
  }

"(?:,\"|^\")(\"\"|[\\w\\W]*?)(?=\",|\"$)|(?:, ..." (18474 uses)

[GeneratedRegex("(?:,\"|^\")(\"\"|[\\w\\W]*?)(?=\",|\"$)|(?:,(?!\")|^(?!\"))([^,]*?)(?=$|,)|(\r\n|\n)", RegexOptions.Compiled)]

  // Branch 0
  {
      // Match ','.
-       if ((uint)slice.Length < 2 || slice[1] != ',')
+       if (slice.Length < 2 || slice[1] != ',')
      {
          goto AlternationBranch3;
      }
      }
      
      // Match '"'.
-       if ((uint)slice.Length < 2 || slice[1] != '"')
+       if (slice.Length < 2 || slice[1] != '"')
      {
          goto NegativeLookaroundMatch;
      }
  {
      case '\r':
          // Match '\n'.
-           if ((uint)slice.Length < 2 || slice[1] != '\n')
+           if (slice.Length < 2 || slice[1] != '\n')
          {
              UncaptureUntil(0);
              return false; // The input didn't match.

"\\s" (10990 uses)

[GeneratedRegex("\\s", RegexOptions.CultureInvariant)]

         /// <summary>Whether <see cref="s_defaultTimeout"/> is non-infinite.</summary>
         internal static readonly bool s_hasTimeout = s_defaultTimeout != Regex.InfiniteMatchTimeout;
         
-        /// <summary>Supports searching for characters in or not in "\t\n\v\f\r \u0085             \u2028\u2029  　".</summary>
-        internal static readonly SearchValues<char> s_whitespace = SearchValues.Create("\t\n\v\f\r \u0085             \u2028\u2029  　");
+        /// <summary>Supports searching for characters in or not in "\t\n\v\f\r \u0085             \u2028\u2029  　".</summary>
+        internal static readonly SearchValues<char> s_whitespace = SearchValues.Create("\t\n\v\f\r \u0085             \u2028\u2029  　");
     }
 }

"^\\s*(((?<ORIGIN>(((\\d+>)?[a-zA-Z]?:[^:]*)| ..." (7826 uses)

[GeneratedRegex("^\\s*(((?<ORIGIN>(((\\d+>)?[a-zA-Z]?:[^:]*)|([^:]*))):)|())(?<SUBCATEGORY>(()|([^:]*? )))(?<CATEGORY>(error|warning))( \\s*(?<CODE>[^: ]*))?\\s*:(?<TEXT>.*)$", RegexOptions.IgnoreCase | RegexOptions.Compiled)]

  {
      case 'E' or 'e':
          
-           if ((uint)slice.Length < 5 ||
+           if (slice.Length < 5 ||
              !slice.Slice(1).StartsWith("rror", StringComparison.OrdinalIgnoreCase)) // Match the string "rror" (ordinal case-insensitive)
          {
              goto CaptureBacktrack7;
          
      case 'W' or 'w':
          
-           if ((uint)slice.Length < 7 ||
+           if (slice.Length < 7 ||
              !slice.Slice(1).StartsWith("arning", StringComparison.OrdinalIgnoreCase)) // Match the string "arning" (ordinal case-insensitive)
          {
              goto CaptureBacktrack7;

"^\\s*(?<ORIGIN>(?<FILENAME>.*):(?<LOCATION>( ..." (7826 uses)

[GeneratedRegex("^\\s*(?<ORIGIN>(?<FILENAME>.*):(?<LOCATION>(?<LINE>[0-9]*):(?<COLUMN>[0-9]*))):(?<CATEGORY> error| warning):(?<TEXT>.*)", RegexOptions.IgnoreCase | RegexOptions.Compiled)]

  // Match with 2 alternative expressions.
  //{
-       if ((uint)slice.Length < 2)
+       if (slice.Length < 2)
      {
          goto CaptureBacktrack1;
      }
      {
          case 'E' or 'e':
              
-               if ((uint)slice.Length < 6 ||
+               if (slice.Length < 6 ||
                  !slice.Slice(2).StartsWith("rror", StringComparison.OrdinalIgnoreCase)) // Match the string "rror" (ordinal case-insensitive)
              {
                  goto CaptureBacktrack1;
              
          case 'W' or 'w':
              
-               if ((uint)slice.Length < 8 ||
+               if (slice.Length < 8 ||
                  !slice.Slice(2).StartsWith("arning", StringComparison.OrdinalIgnoreCase)) // Match the string "arning" (ordinal case-insensitive)
              {
                  goto CaptureBacktrack1;

"^[A-Za-z]:" (5756 uses)

[GeneratedRegex("^[A-Za-z]:", RegexOptions.Compiled)]

      return false; // The input didn't match.
  }
  
-   if ((uint)slice.Length < 2 ||
+   if (slice.Length < 2 ||
      !char.IsAsciiLetter(slice[0]) || // Match a character in the set [A-Za-z].
      slice[1] != ':') // Match ':'.
  {

"[A-z-[dDfFiIoOqQuUwWzZ]]\\d[A-z-[dDfFiIoOqQu ..." (5703 uses)

[GeneratedRegex("[A-z-[dDfFiIoOqQuUwWzZ]]\\d[A-z-[dDfFiIoOqQuU]] *\\d[A-z-[dDfFiIoOqQuU]]\\d\\b", RegexOptions.IgnoreCase | RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.CultureInvariant)]

  char ch;
  ReadOnlySpan<char> slice = inputSpan.Slice(pos);
  
-   if ((uint)slice.Length < 3 ||
+   if (slice.Length < 3 ||
      ((ch = slice[0]) < 128 ? ("\0\0\0\0綮ﭝ綯͝"[ch >> 4] & (1 << (ch & 0xF))) == 0 : !RegexRunner.CharInClass((char)ch, "\0\u0004\0A{KÅ\0 \0DEFGIJOPQRUVWXZ[defgijopqruvwxz{")) || // Match a character in the set [A-z\u212A-[DFIOQUWZdfioquwz]].
      !char.IsDigit(slice[1]) || // Match a Unicode digit.
      ((ch = slice[2]) < 128 ? ("\0\0\0\0綮\uffdd綯ߝ"[ch >> 4] & (1 << (ch & 0xF))) == 0 : !RegexRunner.CharInClass((char)ch, "\0\u0004\0A{KÅ\0\u0018\0DEFGIJOPQRUVdefgijopqruv"))) // Match a character in the set [A-z\u212A-[DFIOQUdfioqu]].
      pos += iteration;
  }
  
-   if ((uint)slice.Length < 6 ||
+   if (slice.Length < 6 ||
      !char.IsDigit(slice[3]) || // Match a Unicode digit.
      ((ch = slice[4]) < 128 ? ("\0\0\0\0綮\uffdd綯ߝ"[ch >> 4] & (1 << (ch & 0xF))) == 0 : !RegexRunner.CharInClass((char)ch, "\0\u0004\0A{KÅ\0\u0018\0DEFGIJOPQRUVdefgijopqruv")) || // Match a character in the set [A-z\u212A-[DFIOQUdfioqu]].
      !char.IsDigit(slice[5])) // Match a Unicode digit.

"\\d{5}$|\\d{5}-\\d{4}$" (5703 uses)

[GeneratedRegex("\\d{5}$|\\d{5}-\\d{4}$", RegexOptions.IgnoreCase | RegexOptions.Compiled | RegexOptions.Singleline | RegexOptions.CultureInvariant)]

  // Match a Unicode digit exactly 5 times.
  {
-       if ((uint)slice.Length < 5 ||
+       if (slice.Length < 5 ||
          !char.IsDigit(slice[0]) ||
          !char.IsDigit(slice[1]) ||
          !char.IsDigit(slice[2]) ||
      
      // Branch 1
      {
-           if ((uint)slice.Length < 10 ||
+           if (slice.Length < 10 ||
              slice[5] != '-' || // Match '-'.
              !char.IsDigit(slice[6]) || // Match a Unicode digit exactly 4 times.
              !char.IsDigit(slice[7]) ||

"^[a-f0-9]{32}$" (4920 uses)

[GeneratedRegex("^[a-f0-9]{32}$", RegexOptions.Compiled)]

  // Match a character in the set [0-9a-f] exactly 32 times.
  {
-       if ((uint)slice.Length < 32)
+       if (slice.Length < 32)
      {
          return false; // The input didn't match.
      }

For more diff examples, see https://gist.github.com/MihuBot/74fd371c36382a07aa7fb19d08c970e7

Sample source code for further analysis

const string JsonPath = "RegexResults-613.json";
if (!File.Exists(JsonPath))
{
    await using var archiveStream = await new HttpClient().GetStreamAsync("https://runtimeutils.blob.core.windows.net/artifacts/3144cd93937a4aa0a575c59ed441faae/Results.zip");
    using var archive = new ZipArchive(archiveStream, ZipArchiveMode.Read);
    archive.Entries.First(e => e.Name == "Results.json").ExtractToFile(JsonPath);
}

using FileStream jsonFileStream = File.OpenRead(JsonPath);
RegexEntry[] entries = JsonSerializer.Deserialize<RegexEntry[]>(jsonFileStream)!;
Console.WriteLine($"Working with {entries.Length} patterns");



record KnownPattern(string Pattern, RegexOptions Options, int Count);

sealed class RegexEntry
{
    public required KnownPattern Regex { get; set; }
    public required string MainSource { get; set; }
    public required string PrSource { get; set; }
    public string? FullDiff { get; set; }
    public string? ShortDiff { get; set; }
    public string[]? SearchValuesOfChar { get; set; }
    public (string[] Values, StringComparison ComparisonType)[]? SearchValuesOfString { get; set; }
}

Artifacts:

• ShortExampleDiffs.md (8 KB)
• LongExampleDiffs.md (901 KB)
• KnownPatternsProjectMain.zip (62 MB)
• Results.zip (62 MB)
• KnownPatternsProjectPr.zip (61 MB)

[MihuBot]

@MihaZupan