[RegexDiff X64] MihaZupan/runtime/regex-fewerUintCasts #625

MihuBot · 2024-09-05T03:16:32Z

Job completed in 20 minutes 42 seconds.

Using arguments: regexdiff -NoPRLink

Examples of GeneratedRegex source diffs

8625 out of 18885 patterns have generated source code changes.

"[^'\",]+'[^^']+'|[^'\",]+\"[^\"]+\"|[^,]+" (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*(((?<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.
      }

"^((([a-z]|\\d|[!#\\$%&'\\*\\+\\-\\/=\\?\\^_` ..." (4566 uses)

[GeneratedRegex("^((([a-z]|\\d|[!#\\$%&'\\*\\+\\-\\/=\\?\\^_`{\\|}~]|[\\u00A0-\\uD7FF\\uF900-\\uFDCF\\uFDF0-\\uFFEF])+(\\.([a-z]|\\d|[!#\\$%&'\\*\\+\\-\\/=\\?\\^_`{\\|}~]|[\\u00A0-\\uD7FF\\uF900-\\uFDCF\\uFDF0-\\uFFEF])+)*)|((\\x22)((((\\x20|\\x09)*(\\x0d\\x0a))?(\\x20|\\x09)+)?(([\\x01-\\x08\\x0b\\x0c\\x0e-\\x1f\\x7f]|\\x21|[\\x23-\\x5b]|[\\x5d-\\x7e]|[\\u00A0-\\uD7FF\\uF900-\\uFDCF\\uFDF0-\\uFFEF])|(\\\\([\\x01-\\x09\\x0b\\x0c\\x0d-\\x7f]|[\\u00A0-\\uD7FF\\uF900-\\uFDCF\\uFDF0-\\uFFEF]))))*(((\\x20|\\x09)*(\\x0d\\x0a))?(\\x20|\\x09)+)?(\\x22)))@((([a-z]|\\d|[\\u00A0-\\uD7FF\\uF900-\\uFDCF\\uFDF0-\\uFFEF])|(([a-z]|\\d|[\\u00A0-\\uD7FF\\uF900-\\uFDCF\\uFDF0-\\uFFEF])([a-z]|\\d|-|\\.|_|~|[\\u00A0-\\uD7FF\\uF900-\\uFDCF\\uFDF0-\\uFFEF])*([a-z]|\\d|[\\u00A0-\\uD7FF\\uF900-\\uFDCF\\uFDF0-\\uFFEF])))\\.)+(([a-z]|[\\u00A0-\\uD7FF\\uF900-\\uFDCF\\uFDF0-\\uFFEF])|(([a-z]|[\\u00A0-\\uD7FF\\uF900-\\uFDCF\\uFDF0-\\uFFEF])([a-z]|\\d|-|\\.|_|~|[\\u00A0-\\uD7FF\\uF900-\\uFDCF\\uFDF0-\\uFFEF])*([a-z]|[\\u00A0-\\uD7FF\\uF900-\\uFDCF\\uFDF0-\\uFFEF])))\\.?$", RegexOptions.IgnoreCase | RegexOptions.ExplicitCapture | RegexOptions.Compiled)]

  // Branch 1
  //{
-       if ((uint)slice.Length < 2 ||
+       if (slice.Length < 2 ||
          slice[0] != '\\' || // Match '\\'.
          ((ch = slice[1]) < 128 ? ("ﯾ\uffff\uffff\uffff\uffff\uffff\uffff\uffff"[ch >> 4] & (1 << (ch & 0xF))) == 0 : !RegexRunner.CharInClass((char)ch, "\0\n\0\u0001\n\v\u0080 \ud800豈\ufdd0ﷰ\ufff0"))) // Match a character in the set [\u0001-\t\v-\u007F\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF].
      {

"xmlns=\"[^\"]*\"\\s*" (4166 uses)

[GeneratedRegex("xmlns=\"[^\"]*\"\\s*", RegexOptions.None)]

  }
  
  // Match '"'.
-   if ((uint)slice.Length < 8 || slice[7] != '"')
+   if (slice.Length < 8 || slice[7] != '"')
  {
      return false; // The input didn't match.
  }

For more diff examples, see https://gist.github.com/MihuBot/075613d3f28b6a1867e2d865fbc96b4b

Total bytes of base: 54137458
Total bytes of diff: 54153509
Total bytes of delta: 16051 (0.03 % of base)
Total relative delta: -58.17
    diff is a regression.
    relative diff is an improvement.

For a list of JIT diff regressions, see Regressions.md
For a list of JIT diff improvements, see Improvements.md

Sample source code for further analysis

const string JsonPath = "RegexResults-625.json";
if (!File.Exists(JsonPath))
{
    await using var archiveStream = await new HttpClient().GetStreamAsync("https://runtimeutils.blob.core.windows.net/artifacts/EcdZFMOAAAE/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 Name, string Values)[]? SearchValuesOfChar { get; set; }
    public (string[] Values, StringComparison ComparisonType)[]? SearchValuesOfString { get; set; }
}

Artifacts:

The text was updated successfully, but these errors were encountered:

MihuBot · 2024-09-05T03:37:15Z

@MihaZupan

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[RegexDiff X64] MihaZupan/runtime/regex-fewerUintCasts #625

[RegexDiff X64] MihaZupan/runtime/regex-fewerUintCasts #625

MihuBot commented Sep 5, 2024 •

edited

Loading

MihuBot commented Sep 5, 2024

[RegexDiff X64] MihaZupan/runtime/regex-fewerUintCasts #625

[RegexDiff X64] MihaZupan/runtime/regex-fewerUintCasts #625

Comments

MihuBot commented Sep 5, 2024 • edited Loading

MihuBot commented Sep 5, 2024

MihuBot commented Sep 5, 2024 •

edited

Loading