[RegexDiff X64] [danmoseley] Remove redundant Atomic wrapper and fix shared- ... #1833
Description
Job completed in 14 minutes 2 seconds (remote runner delay: 1 minute 7 seconds).
dotnet/runtime#126114
Using arguments: regexdiff
Main commit: dotnet/runtime@44cd131
PR commit: danmoseley/runtime@8d88d04
460 out of 18857 patterns have generated source code changes.
Examples of GeneratedRegex source diffs
"^\\s*\\[(([^#;]|\\\\#|\\\\;)+)\\]\\s*([#;].*)?$" (3059 uses)
[GeneratedRegex("^\\s*\\[(([^#;]|\\\\#|\\\\;)+)\\]\\s*([#;].*)?$")] /// ○ 1st capture group.<br/>
/// ○ Loop greedily at least once.<br/>
/// ○ 2nd capture group.<br/>
- /// ○ Match with 3 alternative expressions.<br/>
+ /// ○ Match with 2 alternative expressions.<br/>
/// ○ Match a character in the set [^#;].<br/>
- /// ○ Match the string "\\#".<br/>
- /// ○ Match the string "\\;".<br/>
+ /// ○ Match a sequence of expressions.<br/>
+ /// ○ Match '\\'.<br/>
+ /// ○ Match a character in the set [#;].<br/>
/// ○ Match ']'.<br/>
/// ○ Match a whitespace character greedily any number of times.<br/>
/// ○ Optional (greedy).<br/>
//{
int capture_starting_pos1 = pos;
- // Match with 3 alternative expressions.
+ // Match with 2 alternative expressions.
//{
int alternation_starting_pos = pos;
int alternation_starting_capturepos = base.Crawlpos();
// Branch 1
//{
- // Match the string "\\#".
- if (!slice.StartsWith("\\#"))
- {
- goto AlternationBranch1;
- }
-
- Utilities.StackPush(ref base.runstack!, ref stackpos, 1, alternation_starting_pos, alternation_starting_capturepos);
- pos += 2;
- slice = inputSpan.Slice(pos);
- goto AlternationMatch;
-
- AlternationBranch1:
- pos = alternation_starting_pos;
- slice = inputSpan.Slice(pos);
- UncaptureUntil(alternation_starting_capturepos);
- //}
-
- // Branch 2
- //{
- // Match the string "\\;".
- if (!slice.StartsWith("\\;"))
+ if ((uint)slice.Length < 2 ||
+ slice[0] != '\\' || // Match '\\'.
+ (((ch = slice[1]) != '#') & (ch != ';'))) // Match a character in the set [#;].
{
goto LoopIterationNoMatch;
}
- Utilities.StackPush(ref base.runstack!, ref stackpos, 2, alternation_starting_pos, alternation_starting_capturepos);
+ Utilities.StackPush(ref base.runstack!, ref stackpos, 1, alternation_starting_pos, alternation_starting_capturepos);
pos += 2;
slice = inputSpan.Slice(pos);
goto AlternationMatch;
case 0:
goto AlternationBranch;
case 1:
- goto AlternationBranch1;
- case 2:
goto LoopIterationNoMatch;
}"^(([0-9]|[1-9][0-9]|1[0-9]{2}|2[0-4][0-9]|25 ..." (1964 uses)
[GeneratedRegex("^(([0-9]|[1-9][0-9]|1[0-9]{2}|2[0-4][0-9]|25[0-5])\\.){3}([0-9]|[1-9][0-9]|1[0-9]{2}|2[0-4][0-9]|25[0-5])$|^(([a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9\\-]*[a-zA-Z0-9])\\.)*([A-Za-z0-9]|[A-Za-z0-9][A-Za-z0-9\\-]*[A-Za-z0-9])$", RegexOptions.IgnoreCase)] /// ○ Loop exactly 3 times.<br/>
/// ○ 1st capture group.<br/>
/// ○ 2nd capture group.<br/>
- /// ○ Match with 5 alternative expressions.<br/>
+ /// ○ Match with 4 alternative expressions.<br/>
/// ○ Match a character in the set [0-9].<br/>
/// ○ Match a sequence of expressions.<br/>
/// ○ Match a character in the set [1-9].<br/>
/// ○ Match a character in the set [0-9] exactly 2 times.<br/>
/// ○ Match a sequence of expressions.<br/>
/// ○ Match '2'.<br/>
- /// ○ Match a character in the set [0-4].<br/>
- /// ○ Match a character in the set [0-9].<br/>
- /// ○ Match a sequence of expressions.<br/>
- /// ○ Match the string "25".<br/>
- /// ○ Match a character in the set [0-5].<br/>
+ /// ○ Match with 2 alternative expressions.<br/>
+ /// ○ Match a sequence of expressions.<br/>
+ /// ○ Match a character in the set [0-4].<br/>
+ /// ○ Match a character in the set [0-9].<br/>
+ /// ○ Match a sequence of expressions.<br/>
+ /// ○ Match '5'.<br/>
+ /// ○ Match a character in the set [0-5].<br/>
/// ○ Match '.'.<br/>
/// ○ 3rd capture group.<br/>
- /// ○ Match with 5 alternative expressions.<br/>
+ /// ○ Match with 4 alternative expressions.<br/>
/// ○ Match a character in the set [0-9].<br/>
/// ○ Match a sequence of expressions.<br/>
/// ○ Match a character in the set [1-9].<br/>
/// ○ Match a character in the set [0-9] exactly 2 times.<br/>
/// ○ Match a sequence of expressions.<br/>
/// ○ Match '2'.<br/>
- /// ○ Match a character in the set [0-4].<br/>
- /// ○ Match a character in the set [0-9].<br/>
- /// ○ Match a sequence of expressions.<br/>
- /// ○ Match the string "25".<br/>
- /// ○ Match a character in the set [0-5].<br/>
+ /// ○ Match with 2 alternative expressions.<br/>
+ /// ○ Match a sequence of expressions.<br/>
+ /// ○ Match a character in the set [0-4].<br/>
+ /// ○ Match a character in the set [0-9].<br/>
+ /// ○ Match a sequence of expressions.<br/>
+ /// ○ Match '5'.<br/>
+ /// ○ Match a character in the set [0-5].<br/>
/// ○ Match if at the end of the string or if before an ending newline.<br/>
/// ○ Match a sequence of expressions.<br/>
/// ○ Loop greedily any number of times.<br/>
//{
int capture_starting_pos1 = pos;
- // Match with 5 alternative expressions.
+ // Match with 4 alternative expressions.
//{
int alternation_starting_pos1 = pos;
int alternation_starting_capturepos1 = base.Crawlpos();
// Branch 3
//{
- if ((uint)slice.Length < 3 ||
- slice[0] != '2' || // Match '2'.
- !char.IsBetween(slice[1], '0', '4') || // Match a character in the set [0-4].
- !char.IsAsciiDigit(slice[2])) // Match a character in the set [0-9].
- {
- goto AlternationBranch4;
- }
-
- Utilities.StackPush(ref base.runstack!, ref stackpos, 3, alternation_starting_pos1, alternation_starting_capturepos1);
- pos += 3;
- slice = inputSpan.Slice(pos);
- goto AlternationMatch1;
-
- AlternationBranch4:
- pos = alternation_starting_pos1;
- slice = inputSpan.Slice(pos);
- UncaptureUntil(alternation_starting_capturepos1);
- //}
-
- // Branch 4
- //{
- if ((uint)slice.Length < 3 ||
- !slice.StartsWith("25", StringComparison.OrdinalIgnoreCase) || // Match the string "25" (ordinal case-insensitive)
- !char.IsBetween(slice[2], '0', '5')) // Match a character in the set [0-5].
+ // Match '2'.
+ if (slice.IsEmpty || slice[0] != '2')
{
goto LoopIterationNoMatch;
}
- Utilities.StackPush(ref base.runstack!, ref stackpos, 4, alternation_starting_pos1, alternation_starting_capturepos1);
- pos += 3;
- slice = inputSpan.Slice(pos);
+ // Match with 2 alternative expressions.
+ //{
+ if ((uint)slice.Length < 2)
+ {
+ goto LoopIterationNoMatch;
+ }
+
+ switch (slice[1])
+ {
+ case '0' or '1' or '2' or '3' or '4':
+
+ // Match a character in the set [0-9].
+ if ((uint)slice.Length < 3 || !char.IsAsciiDigit(slice[2]))
+ {
+ goto LoopIterationNoMatch;
+ }
+
+ pos += 3;
+ slice = inputSpan.Slice(pos);
+ break;
+
+ case '5':
+
+ // Match a character in the set [0-5].
+ if ((uint)slice.Length < 3 || !char.IsBetween(slice[2], '0', '5'))
+ {
+ goto LoopIterationNoMatch;
+ }
+
+ pos += 3;
+ slice = inputSpan.Slice(pos);
+ break;
+
+ default:
+ goto LoopIterationNoMatch;
+ }
+ //}
+
+ Utilities.StackPush(ref base.runstack!, ref stackpos, 3, alternation_starting_pos1, alternation_starting_capturepos1);
goto AlternationMatch1;
//}
case 2:
goto AlternationBranch3;
case 3:
- goto AlternationBranch4;
- case 4:
goto LoopIterationNoMatch;
}
//{
capture_starting_pos2 = pos;
- // Match with 5 alternative expressions.
+ // Match with 4 alternative expressions.
//{
alternation_starting_pos2 = pos;
alternation_starting_capturepos2 = base.Crawlpos();
// Match a character in the set [0-9].
if (slice.IsEmpty || !char.IsAsciiDigit(slice[0]))
{
- goto AlternationBranch5;
+ goto AlternationBranch4;
}
alternation_branch = 0;
slice = inputSpan.Slice(pos);
goto AlternationMatch2;
- AlternationBranch5:
+ AlternationBranch4:
pos = alternation_starting_pos2;
slice = inputSpan.Slice(pos);
UncaptureUntil(alternation_starting_capturepos2);
!char.IsBetween(slice[0], '1', '9') || // Match a character in the set [1-9].
!char.IsAsciiDigit(slice[1])) // Match a character in the set [0-9].
{
- goto AlternationBranch6;
+ goto AlternationBranch5;
}
alternation_branch = 1;
slice = inputSpan.Slice(pos);
goto AlternationMatch2;
- AlternationBranch6:
+ AlternationBranch5:
pos = alternation_starting_pos2;
slice = inputSpan.Slice(pos);
UncaptureUntil(alternation_starting_capturepos2);
!char.IsAsciiDigit(slice[1]) || // Match a character in the set [0-9] exactly 2 times.
!char.IsAsciiDigit(slice[2]))
{
- goto AlternationBranch7;
+ goto AlternationBranch6;
}
alternation_branch = 2;
slice = inputSpan.Slice(pos);
goto AlternationMatch2;
- AlternationBranch7:
+ AlternationBranch6:
pos = alternation_starting_pos2;
slice = inputSpan.Slice(pos);
UncaptureUntil(alternation_starting_capturepos2);
// Branch 3
//{
- if ((uint)slice.Length < 3 ||
- slice[0] != '2' || // Match '2'.
- !char.IsBetween(slice[1], '0', '4') || // Match a character in the set [0-4].
- !char.IsAsciiDigit(slice[2])) // Match a character in the set [0-9].
- {
- goto AlternationBranch8;
- }
-
- alternation_branch = 3;
- pos += 3;
- slice = inputSpan.Slice(pos);
- goto AlternationMatch2;
-
- AlternationBranch8:
- pos = alternation_starting_pos2;
- slice = inputSpan.Slice(pos);
- UncaptureUntil(alternation_starting_capturepos2);
- //}
-
- // Branch 4
- //{
- if ((uint)slice.Length < 3 ||
- !slice.StartsWith("25", StringComparison.OrdinalIgnoreCase) || // Match the string "25" (ordinal case-insensitive)
- !char.IsBetween(slice[2], '0', '5')) // Match a character in the set [0-5].
+ // Match '2'.
+ if (slice.IsEmpty || slice[0] != '2')
{
goto LoopBacktrack;
}
- alternation_branch = 4;
- pos += 3;
- slice = inputSpan.Slice(pos);
+ // Match with 2 alternative expressions.
+ //{
+ if ((uint)slice.Length < 2)
+ {
+ goto LoopBacktrack;
+ }
+
+ switch (slice[1])
+ {
+ case '0' or '1' or '2' or '3' or '4':
+
+ // Match a character in the set [0-9].
+ if ((uint)slice.Length < 3 || !char.IsAsciiDigit(slice[2]))
+ {
+ goto LoopBacktrack;
+ }
+
+ pos += 3;
+ slice = inputSpan.Slice(pos);
+ break;
+
+ case '5':
+
+ // Match a character in the set [0-5].
+ if ((uint)slice.Length < 3 || !char.IsBetween(slice[2], '0', '5'))
+ {
+ goto LoopBacktrack;
+ }
+
+ pos += 3;
+ slice = inputSpan.Slice(pos);
+ break;
+
+ default:
+ goto LoopBacktrack;
+ }
+ //}
+
+ alternation_branch = 3;
goto AlternationMatch2;
//}
switch (alternation_branch)
{
case 0:
- goto AlternationBranch5;
+ goto AlternationBranch4;
case 1:
- goto AlternationBranch6;
+ goto AlternationBranch5;
case 2:
- goto AlternationBranch7;
+ goto AlternationBranch6;
case 3:
- goto AlternationBranch8;
- case 4:
goto LoopBacktrack;
}"^(?'protocol'\\w+\\:\\/\\/)?(?>(?'user'.*)@) ..." (283 uses)
[GeneratedRegex("^(?'protocol'\\w+\\:\\/\\/)?(?>(?'user'.*)@)?(?'endpoint'[^\\/:]+)(?>\\:(?'port'\\d+))?[\\/:](?'identifier'.*?)\\/?(?>\\.git)?$")] /// ○ Match a character other than '\n' lazily any number of times.<br/>
/// ○ Match '/' greedily, optionally.<br/>
/// ○ Optional (greedy).<br/>
- /// ○ Atomic group.<br/>
- /// ○ Match the string ".git".<br/>
+ /// ○ Match the string ".git".<br/>
/// ○ Match if at the end of the string or if before an ending newline.<br/>
/// </code>
/// </remarks>
int loop_iteration2 = 0;
int loop_iteration3 = 0;
int stackpos = 0;
+ int startingStackpos = 0;
ReadOnlySpan<char> slice = inputSpan.Slice(pos);
// Match if at the beginning of the string.
//}
// Optional (greedy).
- //{
+ {
+ startingStackpos = stackpos;
loop_iteration3 = 0;
LoopBody3:
pos = base.runstack![--stackpos];
UncaptureUntil(base.runstack![--stackpos]);
slice = inputSpan.Slice(pos);
- LoopEnd3:;
- //}
+ LoopEnd3:
+ stackpos = startingStackpos; // Ensure any remaining backtracking state is removed.
+ }
// Match if at the end of the string or if before an ending newline.
if (pos < inputSpan.Length - 1 || ((uint)pos < (uint)inputSpan.Length && inputSpan[pos] != '\n'))
{
- goto LoopIterationNoMatch3;
+ goto CharLoopBacktrack2;
}
// The input matched."(?<timeOfDay>凌晨|清晨|早上|早|上午|中午|下午|午后|晚上|夜里|夜晚 ..." (186 uses)
[GeneratedRegex("(?<timeOfDay>凌晨|清晨|早上|早|上午|中午|下午|午后|晚上|夜里|夜晚|半夜|夜间|深夜|傍晚|晚)", RegexOptions.ExplicitCapture | RegexOptions.Singleline)] /// ○ Match '上' atomically, optionally.<br/>
/// ○ Match a sequence of expressions.<br/>
/// ○ Match '夜'.<br/>
- /// ○ Atomic group.<br/>
- /// ○ Match a character in the set [\u665A\u91CC\u95F4].<br/>
+ /// ○ Match a character in the set [\u665A\u91CC\u95F4].<br/>
/// ○ Match the string "半夜".<br/>
/// ○ Match the string "深夜".<br/>
/// ○ Match the string "傍晚".<br/>"^(?'protocol'\\w+)?(\\:\\/\\/)?(?>(?'user'.* ..." (125 uses)
[GeneratedRegex("^(?'protocol'\\w+)?(\\:\\/\\/)?(?>(?'user'.*)@)?(?'endpoint'[^\\/:]+)(?>\\:(?'port'\\d+))?[\\/:](?'identifier'.*?)\\/?(?>\\.git)?$")] /// ○ Match a character other than '\n' lazily any number of times.<br/>
/// ○ Match '/' greedily, optionally.<br/>
/// ○ Optional (greedy).<br/>
- /// ○ Atomic group.<br/>
- /// ○ Match the string ".git".<br/>
+ /// ○ Match the string ".git".<br/>
/// ○ Match if at the end of the string or if before an ending newline.<br/>
/// </code>
/// </remarks>
int loop_iteration3 = 0;
int loop_iteration4 = 0;
int stackpos = 0;
+ int startingStackpos = 0;
ReadOnlySpan<char> slice = inputSpan.Slice(pos);
// Match if at the beginning of the string.
//}
// Optional (greedy).
- //{
+ {
+ startingStackpos = stackpos;
loop_iteration4 = 0;
LoopBody4:
pos = base.runstack![--stackpos];
UncaptureUntil(base.runstack![--stackpos]);
slice = inputSpan.Slice(pos);
- LoopEnd4:;
- //}
+ LoopEnd4:
+ stackpos = startingStackpos; // Ensure any remaining backtracking state is removed.
+ }
// Match if at the end of the string or if before an ending newline.
if (pos < inputSpan.Length - 1 || ((uint)pos < (uint)inputSpan.Length && inputSpan[pos] != '\n'))
{
- goto LoopIterationNoMatch4;
+ goto CharLoopBacktrack3;
}
// The input matched.For more diff examples, see https://gist.github.com/MihuBot/726ab2347ad8984e604bb47e9b493b8b
Sample source code for further analysis
const string JsonPath = "RegexResults-1833.json";
if (!File.Exists(JsonPath))
{
await using var archiveStream = await new HttpClient().GetStreamAsync("https://mihubot.xyz/r/FKDmJWKA");
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 (29 KB)
- LongExampleDiffs.md (909 KB)
- Results.zip (45 MB)