[RegexDiff X64] [danmoseley] Improve regex optimizer through investigation o ... #1826
Description
Job completed in 14 minutes 16 seconds (remote runner delay: 1 minute 17 seconds).
dotnet/runtime#125289
Using arguments: regexdiff
Main commit: dotnet/runtime@fdbedda
PR commit: danmoseley/runtime@1c43564
214 out of 18857 patterns have generated source code changes.
Examples of GeneratedRegex source diffs
"\\b(prima(\\s+(di|del(l['aoei])?|degli|dei)) ..." (212 uses)
[GeneratedRegex("\\b(prima(\\s+(di|del(l['aoei])?|degli|dei))?|entro\\s*(l['aoe]|il?|gli|i)?|(non\\s+dopo\\s+(il?|l[oae']|gli)|non\\s+più\\s+tardi\\s+(di|del(l['aoei])?|degli|dei)|termina(no)?(\\s+con)?(\\s+(il?|l[oae']|gli))?|precedente\\s+a((l(l['aoe])?)|gli|i)?|fino\\s+a((l(l['aoe])?)|gli|i)?))\\b", RegexOptions.ExplicitCapture | RegexOptions.Singleline)] /// ○ Match 'i'.<br/>
/// ○ Match a sequence of expressions.<br/>
/// ○ Match the string "non".<br/>
+ /// ○ Match a whitespace character atomically at least once.<br/>
/// ○ Match with 2 alternative expressions.<br/>
/// ○ Match a sequence of expressions.<br/>
- /// ○ Match a whitespace character atomically at least once.<br/>
/// ○ Match the string "dopo".<br/>
/// ○ Match a whitespace character atomically at least once.<br/>
/// ○ Match with 3 alternative expressions.<br/>
/// ○ Match a character in the set ['aeo].<br/>
/// ○ Match the string "gli".<br/>
/// ○ Match a sequence of expressions.<br/>
- /// ○ Match a whitespace character atomically at least once.<br/>
/// ○ Match the string "più".<br/>
/// ○ Match a whitespace character atomically at least once.<br/>
/// ○ Match the string "tardi".<br/>
goto AlternationBranch8;
}
+ // Match a whitespace character atomically at least once.
+ {
+ pos += 3;
+ slice = inputSpan.Slice(pos);
+ int iteration2 = 0;
+ while ((uint)iteration2 < (uint)slice.Length && char.IsWhiteSpace(slice[iteration2]))
+ {
+ iteration2++;
+ }
+
+ if (iteration2 == 0)
+ {
+ goto AlternationBranch8;
+ }
+
+ slice = slice.Slice(iteration2);
+ pos += iteration2;
+ }
+
// Match with 2 alternative expressions.
//{
alternation_starting_pos4 = pos;
// Branch 0
//{
- // Match a whitespace character atomically at least once.
- {
- pos += 3;
- slice = inputSpan.Slice(pos);
- int iteration2 = 0;
- while ((uint)iteration2 < (uint)slice.Length && char.IsWhiteSpace(slice[iteration2]))
- {
- iteration2++;
- }
-
- if (iteration2 == 0)
- {
- goto AlternationBranch9;
- }
-
- slice = slice.Slice(iteration2);
- pos += iteration2;
- }
-
// Match the string "dopo".
if (!slice.StartsWith("dopo"))
{
// Branch 1
//{
+ // Match the string "più".
+ if (!slice.StartsWith("più"))
+ {
+ goto AlternationBranch8;
+ }
+
// Match a whitespace character atomically at least once.
{
pos += 3;
pos += iteration4;
}
- // Match the string "più".
- if (!slice.StartsWith("più"))
+ // Match the string "tardi".
+ if (!slice.StartsWith("tardi"))
{
goto AlternationBranch8;
}
// Match a whitespace character atomically at least once.
{
- pos += 3;
+ pos += 5;
slice = inputSpan.Slice(pos);
int iteration5 = 0;
while ((uint)iteration5 < (uint)slice.Length && char.IsWhiteSpace(slice[iteration5]))
pos += iteration5;
}
- // Match the string "tardi".
- if (!slice.StartsWith("tardi"))
- {
- goto AlternationBranch8;
- }
-
- // Match a whitespace character atomically at least once.
- {
- pos += 5;
- slice = inputSpan.Slice(pos);
- int iteration6 = 0;
- while ((uint)iteration6 < (uint)slice.Length && char.IsWhiteSpace(slice[iteration6]))
- {
- iteration6++;
- }
-
- if (iteration6 == 0)
- {
- goto AlternationBranch8;
- }
-
- slice = slice.Slice(iteration6);
- pos += iteration6;
- }
-
// Match 'd'.
if (slice.IsEmpty || slice[0] != 'd')
{
// Match a whitespace character atomically at least once.
{
- int iteration7 = 0;
- while ((uint)iteration7 < (uint)slice.Length && char.IsWhiteSpace(slice[iteration7]))
+ int iteration6 = 0;
+ while ((uint)iteration6 < (uint)slice.Length && char.IsWhiteSpace(slice[iteration6]))
{
- iteration7++;
+ iteration6++;
}
- if (iteration7 == 0)
+ if (iteration6 == 0)
{
goto LoopIterationNoMatch5;
}
- slice = slice.Slice(iteration7);
- pos += iteration7;
+ slice = slice.Slice(iteration6);
+ pos += iteration6;
}
// Match the string "con".
// Match a whitespace character atomically at least once.
{
- int iteration8 = 0;
- while ((uint)iteration8 < (uint)slice.Length && char.IsWhiteSpace(slice[iteration8]))
+ int iteration7 = 0;
+ while ((uint)iteration7 < (uint)slice.Length && char.IsWhiteSpace(slice[iteration7]))
{
- iteration8++;
+ iteration7++;
}
- if (iteration8 == 0)
+ if (iteration7 == 0)
{
goto LoopIterationNoMatch6;
}
- slice = slice.Slice(iteration8);
- pos += iteration8;
+ slice = slice.Slice(iteration7);
+ pos += iteration7;
}
// Match with 3 alternative expressions.
{
pos += 10;
slice = inputSpan.Slice(pos);
- int iteration9 = 0;
- while ((uint)iteration9 < (uint)slice.Length && char.IsWhiteSpace(slice[iteration9]))
+ int iteration8 = 0;
+ while ((uint)iteration8 < (uint)slice.Length && char.IsWhiteSpace(slice[iteration8]))
{
- iteration9++;
+ iteration8++;
}
- if (iteration9 == 0)
+ if (iteration8 == 0)
{
goto AlternationBranch18;
}
- slice = slice.Slice(iteration9);
- pos += iteration9;
+ slice = slice.Slice(iteration8);
+ pos += iteration8;
}
// Match 'a'.
{
pos += 4;
slice = inputSpan.Slice(pos);
- int iteration10 = 0;
- while ((uint)iteration10 < (uint)slice.Length && char.IsWhiteSpace(slice[iteration10]))
+ int iteration9 = 0;
+ while ((uint)iteration9 < (uint)slice.Length && char.IsWhiteSpace(slice[iteration9]))
{
- iteration10++;
+ iteration9++;
}
- if (iteration10 == 0)
+ if (iteration9 == 0)
{
return false; // The input didn't match.
}
- slice = slice.Slice(iteration10);
- pos += iteration10;
+ slice = slice.Slice(iteration9);
+ pos += iteration9;
}
// Match 'a'."\\b(1\\s*:\\s*1)|(one (on )?one|one\\s*-\\s* ..." (182 uses)
[GeneratedRegex("\\b(1\\s*:\\s*1)|(one (on )?one|one\\s*-\\s*one|one\\s*:\\s*one)\\b", RegexOptions.IgnoreCase | RegexOptions.Singleline)] /// ○ Match a character in the set [Oo].<br/>
/// ○ Match a character in the set [Nn].<br/>
/// ○ Match a character in the set [Ee].<br/>
- /// ○ Match with 3 alternative expressions.<br/>
+ /// ○ Match with 2 alternative expressions.<br/>
/// ○ Match a sequence of expressions.<br/>
/// ○ Match ' '.<br/>
/// ○ Optional (greedy).<br/>
/// ○ Match a character in the set [Ee].<br/>
/// ○ Match a sequence of expressions.<br/>
/// ○ Match a whitespace character atomically any number of times.<br/>
- /// ○ Match '-'.<br/>
- /// ○ Match a whitespace character atomically any number of times.<br/>
- /// ○ Match a character in the set [Oo].<br/>
- /// ○ Match a character in the set [Nn].<br/>
- /// ○ Match a character in the set [Ee].<br/>
- /// ○ Match a sequence of expressions.<br/>
- /// ○ Match a whitespace character atomically any number of times.<br/>
- /// ○ Match ':'.<br/>
- /// ○ Match a whitespace character atomically any number of times.<br/>
- /// ○ Match a character in the set [Oo].<br/>
- /// ○ Match a character in the set [Nn].<br/>
- /// ○ Match a character in the set [Ee].<br/>
+ /// ○ Match with 2 alternative expressions.<br/>
+ /// ○ Match a sequence of expressions.<br/>
+ /// ○ Match '-'.<br/>
+ /// ○ Match a whitespace character atomically any number of times.<br/>
+ /// ○ Match a character in the set [Oo].<br/>
+ /// ○ Match a character in the set [Nn].<br/>
+ /// ○ Match a character in the set [Ee].<br/>
+ /// ○ Match a sequence of expressions.<br/>
+ /// ○ Match ':'.<br/>
+ /// ○ Match a whitespace character atomically any number of times.<br/>
+ /// ○ Match a character in the set [Oo].<br/>
+ /// ○ Match a character in the set [Nn].<br/>
+ /// ○ Match a character in the set [Ee].<br/>
/// ○ Match if at a word boundary.<br/>
/// </code>
/// </remarks>
return false; // The input didn't match.
}
- // Match with 3 alternative expressions.
+ // Match with 2 alternative expressions.
//{
alternation_starting_pos1 = pos;
alternation_starting_capturepos1 = base.Crawlpos();
pos += iteration2;
}
- // Match '-'.
- if (slice.IsEmpty || slice[0] != '-')
- {
- goto AlternationBranch2;
- }
-
- // Match a whitespace character atomically any number of times.
- {
- int iteration3 = 1;
- while ((uint)iteration3 < (uint)slice.Length && char.IsWhiteSpace(slice[iteration3]))
+ // Match with 2 alternative expressions.
+ //{
+ if (slice.IsEmpty)
{
- iteration3++;
+ UncaptureUntil(0);
+ return false; // The input didn't match.
}
- slice = slice.Slice(iteration3);
- pos += iteration3;
- }
-
- if ((uint)slice.Length < 3 ||
- !slice.StartsWith("one", StringComparison.OrdinalIgnoreCase)) // Match the string "one" (ordinal case-insensitive)
- {
- goto AlternationBranch2;
- }
+ switch (slice[0])
+ {
+ case '-':
+
+ // Match a whitespace character atomically any number of times.
+ {
+ int iteration3 = 1;
+ while ((uint)iteration3 < (uint)slice.Length && char.IsWhiteSpace(slice[iteration3]))
+ {
+ iteration3++;
+ }
+
+ slice = slice.Slice(iteration3);
+ pos += iteration3;
+ }
+
+ if ((uint)slice.Length < 3 ||
+ !slice.StartsWith("one", StringComparison.OrdinalIgnoreCase)) // Match the string "one" (ordinal case-insensitive)
+ {
+ UncaptureUntil(0);
+ return false; // The input didn't match.
+ }
+
+ pos += 3;
+ slice = inputSpan.Slice(pos);
+ break;
+
+ case ':':
+
+ // Match a whitespace character atomically any number of times.
+ {
+ int iteration4 = 1;
+ while ((uint)iteration4 < (uint)slice.Length && char.IsWhiteSpace(slice[iteration4]))
+ {
+ iteration4++;
+ }
+
+ slice = slice.Slice(iteration4);
+ pos += iteration4;
+ }
+
+ if ((uint)slice.Length < 3 ||
+ !slice.StartsWith("one", StringComparison.OrdinalIgnoreCase)) // Match the string "one" (ordinal case-insensitive)
+ {
+ UncaptureUntil(0);
+ return false; // The input didn't match.
+ }
+
+ pos += 3;
+ slice = inputSpan.Slice(pos);
+ break;
+
+ default:
+ UncaptureUntil(0);
+ return false; // The input didn't match.
+ }
+ //}
alternation_branch = 1;
- pos += 3;
- slice = inputSpan.Slice(pos);
- goto AlternationMatch1;
-
- AlternationBranch2:
- pos = alternation_starting_pos1;
- slice = inputSpan.Slice(pos);
- UncaptureUntil(alternation_starting_capturepos1);
- //}
-
- // Branch 2
- //{
- // Match a whitespace character atomically any number of times.
- {
- int iteration4 = 3;
- while ((uint)iteration4 < (uint)slice.Length && char.IsWhiteSpace(slice[iteration4]))
- {
- iteration4++;
- }
-
- slice = slice.Slice(iteration4);
- pos += iteration4;
- }
-
- // Match ':'.
- if (slice.IsEmpty || slice[0] != ':')
- {
- UncaptureUntil(0);
- return false; // The input didn't match.
- }
-
- // Match a whitespace character atomically any number of times.
- {
- int iteration5 = 1;
- while ((uint)iteration5 < (uint)slice.Length && char.IsWhiteSpace(slice[iteration5]))
- {
- iteration5++;
- }
-
- slice = slice.Slice(iteration5);
- pos += iteration5;
- }
-
- if ((uint)slice.Length < 3 ||
- !slice.StartsWith("one", StringComparison.OrdinalIgnoreCase)) // Match the string "one" (ordinal case-insensitive)
- {
- UncaptureUntil(0);
- return false; // The input didn't match.
- }
-
- alternation_branch = 2;
- pos += 3;
- slice = inputSpan.Slice(pos);
goto AlternationMatch1;
//}
case 0:
goto LoopIterationNoMatch;
case 1:
- goto AlternationBranch2;
- case 2:
UncaptureUntil(0);
return false; // The input didn't match.
}"(?<till>zu|bis\\s*zum|zum|bis|bis\\s*hin(\\s ..." (136 uses)
[GeneratedRegex("(?<till>zu|bis\\s*zum|zum|bis|bis\\s*hin(\\s*zum)?|--|-|—|——)", RegexOptions.IgnoreCase | RegexOptions.Singleline)] /// ○ Match a character in the set [Bb].<br/>
/// ○ Match a character in the set [Ii].<br/>
/// ○ Match a character in the set [Ss].<br/>
- /// ○ Match an empty string.<br/>
/// ○ Match the string "--".<br/>
/// ○ Match a character in the set [\-\u2014].<br/>
/// ○ Match the string "——".<br/>
goto AlternationBranch3;
}
-
pos += 3;
slice = inputSpan.Slice(pos);
goto AlternationMatch;For more diff examples, see https://gist.github.com/MihuBot/08ae4323ca7f212b9eeeaea972deb8fd
Sample source code for further analysis
const string JsonPath = "RegexResults-1826.json";
if (!File.Exists(JsonPath))
{
await using var archiveStream = await new HttpClient().GetStreamAsync("https://mihubot.xyz/r/FJerkLNA");
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 (27 KB)
- LongExampleDiffs.md (911 KB)
- Results.zip (43 MB)