[RegexDiff X64] [stephentoub] Remove positive lookarounds that wrap only zer ... #1301
Description
Job completed in 17 minutes 48 seconds (remote runner delay: 54 seconds).
dotnet/runtime#118091
Using arguments: regexdiff
173 out of 18857 patterns have generated source code changes.
Examples of GeneratedRegex source diffs
"(((?<=\\W|^)-\\s*)|(?<=\\b))\\d+\\s*(B|b|m|t ..." (540 uses)
[GeneratedRegex("(((?<=\\W|^)-\\s*)|(?<=\\b))\\d+\\s*(B|b|m|t|g)(?=\\b)", RegexOptions.Singleline)] /// ○ Match a whitespace character atomically any number of times.<br/>
/// ○ 3rd capture group.<br/>
/// ○ Match a character in the set [Bbgmt].<br/>
- /// ○ Zero-width positive lookahead.<br/>
- /// ○ Match if at a word boundary.<br/>
+ /// ○ Match if at a word boundary.<br/>
/// </code>
/// </remarks>
[global::System.CodeDom.Compiler.GeneratedCodeAttribute("System.Text.RegularExpressions.Generator", "42.42.42.42")]
base.Capture(3, capture_starting_pos2, pos);
}
- // Zero-width positive lookahead.
+ // Match if at a word boundary.
+ if (!Utilities.IsBoundary(inputSpan, pos))
{
- slice = inputSpan.Slice(pos);
- int positivelookahead_starting_pos = pos;
-
- if (Utilities.s_hasTimeout)
- {
- base.CheckTimeout();
- }
-
- // Match if at a word boundary.
- if (!Utilities.IsBoundary(inputSpan, pos))
- {
- goto CaptureBacktrack;
- }
-
- pos = positivelookahead_starting_pos;
- slice = inputSpan.Slice(pos);
+ goto CaptureBacktrack;
}
// The input matched."(((?<!\\d+\\s*)-\\s*)|((?<=\\b)(?<!\\d+,)))( ..." (338 uses)
[GeneratedRegex("(((?<!\\d+\\s*)-\\s*)|((?<=\\b)(?<!\\d+,)))(\\d+(,\\d+)?)\\^([+-]*[1-9]\\d*)(?=\\b)", RegexOptions.IgnoreCase | RegexOptions.Singleline)] /// ○ Match a character in the set [+\-] atomically any number of times.<br/>
/// ○ Match a character in the set [1-9].<br/>
/// ○ Match a Unicode digit greedily any number of times.<br/>
- /// ○ Zero-width positive lookahead.<br/>
- /// ○ Match if at a word boundary.<br/>
+ /// ○ Match if at a word boundary.<br/>
/// </code>
/// </remarks>
[global::System.CodeDom.Compiler.GeneratedCodeAttribute("System.Text.RegularExpressions.Generator", "42.42.42.42")]
CaptureSkipBacktrack2:;
//}
- // Zero-width positive lookahead.
+ // Match if at a word boundary.
+ if (!Utilities.IsBoundary(inputSpan, pos))
{
- slice = inputSpan.Slice(pos);
- int positivelookahead_starting_pos = pos;
-
- if (Utilities.s_hasTimeout)
- {
- base.CheckTimeout();
- }
-
- // Match if at a word boundary.
- if (!Utilities.IsBoundary(inputSpan, pos))
- {
- goto CaptureBacktrack2;
- }
-
- pos = positivelookahead_starting_pos;
- slice = inputSpan.Slice(pos);
+ goto CaptureBacktrack2;
}
// The input matched."(((?<!\\d+\\s*)-\\s*)|((?<=\\b)(?<!\\d+,)))( ..." (338 uses)
[GeneratedRegex("(((?<!\\d+\\s*)-\\s*)|((?<=\\b)(?<!\\d+,)))(\\d+(,\\d+)?)e([+-]*[1-9]\\d*)(?=\\b)", RegexOptions.IgnoreCase | RegexOptions.Singleline)] /// ○ Match a character in the set [+\-] atomically any number of times.<br/>
/// ○ Match a character in the set [1-9].<br/>
/// ○ Match a Unicode digit greedily any number of times.<br/>
- /// ○ Zero-width positive lookahead.<br/>
- /// ○ Match if at a word boundary.<br/>
+ /// ○ Match if at a word boundary.<br/>
/// </code>
/// </remarks>
[global::System.CodeDom.Compiler.GeneratedCodeAttribute("System.Text.RegularExpressions.Generator", "42.42.42.42")]
CaptureSkipBacktrack2:;
//}
- // Zero-width positive lookahead.
+ // Match if at a word boundary.
+ if (!Utilities.IsBoundary(inputSpan, pos))
{
- slice = inputSpan.Slice(pos);
- int positivelookahead_starting_pos = pos;
-
- if (Utilities.s_hasTimeout)
- {
- base.CheckTimeout();
- }
-
- // Match if at a word boundary.
- if (!Utilities.IsBoundary(inputSpan, pos))
- {
- goto CaptureBacktrack2;
- }
-
- pos = positivelookahead_starting_pos;
- slice = inputSpan.Slice(pos);
+ goto CaptureBacktrack2;
}
// The input matched."(((?<!\\d+\\s*)-\\s*)|((?<=\\b)(?<!\\d+\\,)) ..." (326 uses)
[GeneratedRegex("(((?<!\\d+\\s*)-\\s*)|((?<=\\b)(?<!\\d+\\,)))\\d+,\\d+\\s*(K|k|M|G|T)(?=\\b)", RegexOptions.Singleline)] /// ○ Match a whitespace character atomically any number of times.<br/>
/// ○ 4th capture group.<br/>
/// ○ Match a character in the set [GKMTk].<br/>
- /// ○ Zero-width positive lookahead.<br/>
- /// ○ Match if at a word boundary.<br/>
+ /// ○ Match if at a word boundary.<br/>
/// </code>
/// </remarks>
[global::System.CodeDom.Compiler.GeneratedCodeAttribute("System.Text.RegularExpressions.Generator", "42.42.42.42")]
base.Capture(4, capture_starting_pos3, pos);
}
- // Zero-width positive lookahead.
+ // Match if at a word boundary.
+ if (!Utilities.IsBoundary(inputSpan, pos))
{
- slice = inputSpan.Slice(pos);
- int positivelookahead_starting_pos = pos;
-
- if (Utilities.s_hasTimeout)
- {
- base.CheckTimeout();
- }
-
- // Match if at a word boundary.
- if (!Utilities.IsBoundary(inputSpan, pos))
- {
- goto CaptureBacktrack;
- }
-
- pos = positivelookahead_starting_pos;
- slice = inputSpan.Slice(pos);
+ goto CaptureBacktrack;
}
// The input matched."(((?<=\\W|^)-\\s*)|(?<=\\b))\\d+\\s*(k|M|T|G ..." (325 uses)
[GeneratedRegex("(((?<=\\W|^)-\\s*)|(?<=\\b))\\d+\\s*(k|M|T|G)(?=\\b)", RegexOptions.Singleline)] /// ○ Match a whitespace character atomically any number of times.<br/>
/// ○ 3rd capture group.<br/>
/// ○ Match a character in the set [GMTk].<br/>
- /// ○ Zero-width positive lookahead.<br/>
- /// ○ Match if at a word boundary.<br/>
+ /// ○ Match if at a word boundary.<br/>
/// </code>
/// </remarks>
[global::System.CodeDom.Compiler.GeneratedCodeAttribute("System.Text.RegularExpressions.Generator", "42.42.42.42")]
base.Capture(3, capture_starting_pos2, pos);
}
- // Zero-width positive lookahead.
+ // Match if at a word boundary.
+ if (!Utilities.IsBoundary(inputSpan, pos))
{
- slice = inputSpan.Slice(pos);
- int positivelookahead_starting_pos = pos;
-
- if (Utilities.s_hasTimeout)
- {
- base.CheckTimeout();
- }
-
- // Match if at a word boundary.
- if (!Utilities.IsBoundary(inputSpan, pos))
- {
- goto CaptureBacktrack;
- }
-
- pos = positivelookahead_starting_pos;
- slice = inputSpan.Slice(pos);
+ goto CaptureBacktrack;
}
// The input matched."(((?<!\\d+\\s*)-\\s*)|((?<=\\b)(?<!\\d+,)))( ..." (252 uses)
[GeneratedRegex("(((?<!\\d+\\s*)-\\s*)|((?<=\\b)(?<!\\d+,)))(\\d+(,\\d+)?)\\^([+-]*[1-9]\\d*)(?=\\b)", RegexOptions.ExplicitCapture | RegexOptions.Singleline)] /// ○ Match a character in the set [+\-] atomically any number of times.<br/>
/// ○ Match a character in the set [1-9].<br/>
/// ○ Match a Unicode digit greedily any number of times.<br/>
- /// ○ Zero-width positive lookahead.<br/>
- /// ○ Match if at a word boundary.<br/>
+ /// ○ Match if at a word boundary.<br/>
/// </code>
/// </remarks>
[global::System.CodeDom.Compiler.GeneratedCodeAttribute("System.Text.RegularExpressions.Generator", "42.42.42.42")]
CharLoopEnd2:
//}
- // Zero-width positive lookahead.
+ // Match if at a word boundary.
+ if (!Utilities.IsBoundary(inputSpan, pos))
{
- slice = inputSpan.Slice(pos);
- int positivelookahead_starting_pos = pos;
-
- if (Utilities.s_hasTimeout)
- {
- base.CheckTimeout();
- }
-
- // Match if at a word boundary.
- if (!Utilities.IsBoundary(inputSpan, pos))
- {
- goto CharLoopBacktrack2;
- }
-
- pos = positivelookahead_starting_pos;
- slice = inputSpan.Slice(pos);
+ goto CharLoopBacktrack2;
}
// The input matched."(((?<!\\d+\\s*)-\\s*)|((?<=\\b)(?<!\\d+,)))( ..." (252 uses)
[GeneratedRegex("(((?<!\\d+\\s*)-\\s*)|((?<=\\b)(?<!\\d+,)))(\\d+(,\\d+)?)e([+-]*[1-9]\\d*)(?=\\b)", RegexOptions.ExplicitCapture | RegexOptions.Singleline)] /// ○ Match a character in the set [+\-] atomically any number of times.<br/>
/// ○ Match a character in the set [1-9].<br/>
/// ○ Match a Unicode digit greedily any number of times.<br/>
- /// ○ Zero-width positive lookahead.<br/>
- /// ○ Match if at a word boundary.<br/>
+ /// ○ Match if at a word boundary.<br/>
/// </code>
/// </remarks>
[global::System.CodeDom.Compiler.GeneratedCodeAttribute("System.Text.RegularExpressions.Generator", "42.42.42.42")]
CharLoopEnd2:
//}
- // Zero-width positive lookahead.
+ // Match if at a word boundary.
+ if (!Utilities.IsBoundary(inputSpan, pos))
{
- slice = inputSpan.Slice(pos);
- int positivelookahead_starting_pos = pos;
-
- if (Utilities.s_hasTimeout)
- {
- base.CheckTimeout();
- }
-
- // Match if at a word boundary.
- if (!Utilities.IsBoundary(inputSpan, pos))
- {
- goto CharLoopBacktrack2;
- }
-
- pos = positivelookahead_starting_pos;
- slice = inputSpan.Slice(pos);
+ goto CharLoopBacktrack2;
}
// The input matched."(((?<!\\d+\\s*)-\\s*)|(?<=\\b))\\d+\\s*(K|k| ..." (215 uses)
[GeneratedRegex("(((?<!\\d+\\s*)-\\s*)|(?<=\\b))\\d+\\s*(K|k|M|T|G)(?=\\b)", RegexOptions.Singleline)] /// ○ Match a whitespace character atomically any number of times.<br/>
/// ○ 3rd capture group.<br/>
/// ○ Match a character in the set [GKMTk].<br/>
- /// ○ Zero-width positive lookahead.<br/>
- /// ○ Match if at a word boundary.<br/>
+ /// ○ Match if at a word boundary.<br/>
/// </code>
/// </remarks>
[global::System.CodeDom.Compiler.GeneratedCodeAttribute("System.Text.RegularExpressions.Generator", "42.42.42.42")]
base.Capture(3, capture_starting_pos2, pos);
}
- // Zero-width positive lookahead.
+ // Match if at a word boundary.
+ if (!Utilities.IsBoundary(inputSpan, pos))
{
- slice = inputSpan.Slice(pos);
- int positivelookahead_starting_pos = pos;
-
- if (Utilities.s_hasTimeout)
- {
- base.CheckTimeout();
- }
-
- // Match if at a word boundary.
- if (!Utilities.IsBoundary(inputSpan, pos))
- {
- goto CaptureBacktrack;
- }
-
- pos = positivelookahead_starting_pos;
- slice = inputSpan.Slice(pos);
+ goto CaptureBacktrack;
}
// The input matched."(((?<!\\d+\\s*)-\\s*)|((?<=\\b)(?<!\\d+[\\., ..." (200 uses)
[GeneratedRegex("(((?<!\\d+\\s*)-\\s*)|((?<=\\b)(?<!\\d+[\\.,])))(\\d+([\\.,]\\d+)?)\\^([+-]*[1-9]\\d*)(?=\\b)", RegexOptions.ExplicitCapture | RegexOptions.Singleline)] /// ○ Match a character in the set [+\-] atomically any number of times.<br/>
/// ○ Match a character in the set [1-9].<br/>
/// ○ Match a Unicode digit greedily any number of times.<br/>
- /// ○ Zero-width positive lookahead.<br/>
- /// ○ Match if at a word boundary.<br/>
+ /// ○ Match if at a word boundary.<br/>
/// </code>
/// </remarks>
[global::System.CodeDom.Compiler.GeneratedCodeAttribute("System.Text.RegularExpressions.Generator", "42.42.42.42")]
CharLoopEnd2:
//}
- // Zero-width positive lookahead.
+ // Match if at a word boundary.
+ if (!Utilities.IsBoundary(inputSpan, pos))
{
- slice = inputSpan.Slice(pos);
- int positivelookahead_starting_pos = pos;
-
- if (Utilities.s_hasTimeout)
- {
- base.CheckTimeout();
- }
-
- // Match if at a word boundary.
- if (!Utilities.IsBoundary(inputSpan, pos))
- {
- goto CharLoopBacktrack2;
- }
-
- pos = positivelookahead_starting_pos;
- slice = inputSpan.Slice(pos);
+ goto CharLoopBacktrack2;
}
// The input matched."(((?<!\\d+\\s*)-\\s*)|((?<=\\b)(?<!\\d+[\\., ..." (200 uses)
[GeneratedRegex("(((?<!\\d+\\s*)-\\s*)|((?<=\\b)(?<!\\d+[\\.,])))(\\d+([\\.,]\\d+)?)e([+-]*[1-9]\\d*)(?=\\b)", RegexOptions.ExplicitCapture | RegexOptions.Singleline)] /// ○ Match a character in the set [+\-] atomically any number of times.<br/>
/// ○ Match a character in the set [1-9].<br/>
/// ○ Match a Unicode digit greedily any number of times.<br/>
- /// ○ Zero-width positive lookahead.<br/>
- /// ○ Match if at a word boundary.<br/>
+ /// ○ Match if at a word boundary.<br/>
/// </code>
/// </remarks>
[global::System.CodeDom.Compiler.GeneratedCodeAttribute("System.Text.RegularExpressions.Generator", "42.42.42.42")]
CharLoopEnd2:
//}
- // Zero-width positive lookahead.
+ // Match if at a word boundary.
+ if (!Utilities.IsBoundary(inputSpan, pos))
{
- slice = inputSpan.Slice(pos);
- int positivelookahead_starting_pos = pos;
-
- if (Utilities.s_hasTimeout)
- {
- base.CheckTimeout();
- }
-
- // Match if at a word boundary.
- if (!Utilities.IsBoundary(inputSpan, pos))
- {
- goto CharLoopBacktrack2;
- }
-
- pos = positivelookahead_starting_pos;
- slice = inputSpan.Slice(pos);
+ goto CharLoopBacktrack2;
}
// The input matched.For more diff examples, see https://gist.github.com/MihuBot/262e88321889757cdd1ba8ed32fc4fd4
JIT assembly changes
Total bytes of base: 54186495
Total bytes of diff: 54183740
Total bytes of delta: -2755 (-0.01 % of base)
Total relative delta: -0.28
diff is an improvement.
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-1301.json";
if (!File.Exists(JsonPath))
{
await using var archiveStream = await new HttpClient().GetStreamAsync("https://mihubot.xyz/r/E2myvU9A");
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, new JsonSerializerOptions { IncludeFields = true })!;
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:
- ShortExampleDiffs.md (18 KB)
- LongExampleDiffs.md (426 KB)
- Results.zip (42 MB)
- JitAnalyzeSummary.txt (58 KB)
- JitDiffRegressions.md (870 KB)
- LongJitDiffRegressions.md (4 MB)
- jit-diffs.zip (391 MB)
- JitDiffImprovements.md (897 KB)
- LongJitDiffImprovements.md (9 MB)