Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[release/7.0] Fix handling of backtracking stack with some loops #79361

Merged
merged 3 commits into from
Jan 4, 2023
Merged

[release/7.0] Fix handling of backtracking stack with some loops #79361

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f3e9ca1
Fix handling of backtracking stack with some loops
stephentoub Dec 7, 2022
7147262
Fix declaration of local in regex source generator
stephentoub Dec 7, 2022
d27c95a
Fix startingStackpos tracking for loop in loop
stephentoub Dec 8, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 32 additions & 6 deletions src/libraries/System.Text.RegularExpressions/gen/RegexGenerator.Emitter.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3873,10 +3873,16 @@ void EmitLoop(RegexNode node)

bool isAtomic = rm.Analysis.IsAtomicByAncestor(node);
string? startingStackpos = null;
if (isAtomic)
if (isAtomic || minIterations > 1)
{
// If the loop is atomic, constructs will need to backtrack around it, and as such any backtracking
// state pushed by the loop should be removed prior to exiting the loop. Similarly, if the loop has
// a minimum iteration count greater than 1, we might end up with at least one successful iteration
// only to find we can't iterate further, and will need to clear any pushed state from the backtracking
// stack. For both cases, we need to store the starting stack index so it can be reset to that position.
startingStackpos = ReserveName("startingStackpos");
writer.WriteLine($"int {startingStackpos} = stackpos;");
additionalDeclarations.Add($"int {startingStackpos} = 0;");
writer.WriteLine($"{startingStackpos} = stackpos;");
}

string originalDoneLabel = doneLabel;
Expand Down Expand Up @@ -4069,6 +4075,22 @@ void EmitLoop(RegexNode node)
using (EmitBlock(writer, $"if ({CountIsLessThan(iterationCount, minIterations)})"))
{
writer.WriteLine($"// All possible iterations have matched, but it's below the required minimum of {minIterations}. Fail the loop.");

// If the minimum iterations is 1, then since we're only here if there are fewer, there must be 0
// iterations, in which case there's nothing to reset. If, however, the minimum iteration count is
// greater than 1, we need to check if there was at least one successful iteration, in which case
// any backtracking state still set needs to be reset; otherwise, constructs earlier in the sequence
// trying to pop their own state will erroneously pop this state instead.
if (minIterations > 1)
{
Debug.Assert(startingStackpos is not null);
using (EmitBlock(writer, $"if ({iterationCount} != 0)"))
{
writer.WriteLine($"// Ensure any stale backtracking state is removed.");
writer.WriteLine($"stackpos = {startingStackpos};");
}
}

Goto(originalDoneLabel);
}
writer.WriteLine();
Expand Down Expand Up @@ -4124,8 +4146,10 @@ void EmitLoop(RegexNode node)
writer.WriteLine();

// Store the loop's state
EmitStackPush(iterationMayBeEmpty ?
new[] { startingPos!, iterationCount } :
EmitStackPush(
startingPos is not null && startingStackpos is not null ? new[] { startingPos, startingStackpos, iterationCount } :
startingPos is not null ? new[] { startingPos, iterationCount } :
startingStackpos is not null ? new[] { startingStackpos, iterationCount } :
new[] { iterationCount });

// Skip past the backtracking section
Expand All @@ -4136,8 +4160,10 @@ void EmitLoop(RegexNode node)
// Emit a backtracking section that restores the loop's state and then jumps to the previous done label
string backtrack = ReserveName("LoopBacktrack");
MarkLabel(backtrack, emitSemicolon: false);
EmitStackPop(iterationMayBeEmpty ?
new[] { iterationCount, startingPos! } :
EmitStackPop(
startingPos is not null && startingStackpos is not null ? new[] { iterationCount, startingStackpos, startingPos } :
startingPos is not null ? new[] { iterationCount, startingPos } :
startingStackpos is not null ? new[] { iterationCount, startingStackpos } :
new[] { iterationCount });

// We're backtracking. Check the timeout.
Expand Down
51 changes: 45 additions & 6 deletions ...raries/System.Text.RegularExpressions/src/System/Text/RegularExpressions/RegexCompiler.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4613,8 +4613,13 @@ void EmitLoop(RegexNode node)

bool isAtomic = analysis.IsAtomicByAncestor(node);
LocalBuilder? startingStackpos = null;
if (isAtomic)
if (isAtomic || minIterations > 1)
{
// If the loop is atomic, constructs will need to backtrack around it, and as such any backtracking
// state pushed by the loop should be removed prior to exiting the loop. Similarly, if the loop has
// a minimum iteration count greater than 1, we might end up with at least one successful iteration
// only to find we can't iterate further, and will need to clear any pushed state from the backtracking
// stack. For both cases, we need to store the starting stack index so it can be reset to that position.
startingStackpos = DeclareInt32();
Ldloc(stackpos);
Stloc(startingStackpos);
Expand Down Expand Up @@ -4802,7 +4807,6 @@ void EmitLoop(RegexNode node)
}
EmitUncaptureUntilPopped();


// If there's a required minimum iteration count, validate now that we've processed enough iterations.
if (minIterations > 0)
{
Expand All @@ -4821,7 +4825,7 @@ void EmitLoop(RegexNode node)
// since the only value that wouldn't meet that is 0.
if (minIterations > 1)
{
// if (iterationCount < minIterations) goto doneLabel/originalDoneLabel;
// if (iterationCount < minIterations) goto doneLabel;
Ldloc(iterationCount);
Ldc(minIterations);
BltFar(doneLabel);
Expand All @@ -4831,10 +4835,36 @@ void EmitLoop(RegexNode node)
{
// The child doesn't backtrack, which means there's no other way the matched iterations could
// match differently, so if we haven't already greedily processed enough iterations, fail the loop.
// if (iterationCount < minIterations) goto doneLabel/originalDoneLabel;
// if (iterationCount < minIterations)
// {
// if (iterationCount != 0) stackpos = startingStackpos;
// goto originalDoneLabel;
// }

Label enoughIterations = DefineLabel();
Ldloc(iterationCount);
Ldc(minIterations);
BltFar(originalDoneLabel);
Bge(enoughIterations);

// If the minimum iterations is 1, then since we're only here if there are fewer, there must be 0
// iterations, in which case there's nothing to reset. If, however, the minimum iteration count is
// greater than 1, we need to check if there was at least one successful iteration, in which case
// any backtracking state still set needs to be reset; otherwise, constructs earlier in the sequence
// trying to pop their own state will erroneously pop this state instead.
if (minIterations > 1)
{
Debug.Assert(startingStackpos is not null);

Ldloc(iterationCount);
Ldc(0);
BeqFar(originalDoneLabel);

Ldloc(startingStackpos);
Stloc(stackpos);
}
BrFar(originalDoneLabel);

MarkLabel(enoughIterations);
}
}

Expand Down Expand Up @@ -4888,11 +4918,15 @@ void EmitLoop(RegexNode node)
if (analysis.IsInLoop(node))
{
// Store the loop's state
EmitStackResizeIfNeeded(1 + (startingPos is not null ? 1 : 0));
EmitStackResizeIfNeeded(1 + (startingPos is not null ? 1 : 0) + (startingStackpos is not null ? 1 : 0));
if (startingPos is not null)
{
EmitStackPush(() => Ldloc(startingPos));
}
if (startingStackpos is not null)
{
EmitStackPush(() => Ldloc(startingStackpos));
}
EmitStackPush(() => Ldloc(iterationCount));

// Skip past the backtracking section
Expand All @@ -4911,6 +4945,11 @@ void EmitLoop(RegexNode node)
// startingPos = base.runstack[--runstack];
EmitStackPop();
Stloc(iterationCount);
if (startingStackpos is not null)
{
EmitStackPop();
Stloc(startingStackpos);
}
if (startingPos is not null)
{
EmitStackPop();
Expand Down
9 changes: 9 additions & 0 deletions src/libraries/System.Text.RegularExpressions/tests/FunctionalTests/Regex.Match.Tests.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -363,6 +363,15 @@ public static IEnumerable<object[]> Match_MemberData()
yield return ("a*(?:a[ab]*)*", "aaaababbbbbbabababababaaabbb", RegexOptions.None, 0, 28, true, "aaaa");
yield return ("a*(?:a[ab]*?)*?", "aaaababbbbbbabababababaaabbb", RegexOptions.None, 0, 28, true, "aaaa");

// Sequences of loops
yield return (@"(ver\.? |[_ ]+)?\d+(\.\d+){2,3}$", " Ver 2.0", RegexOptions.IgnoreCase, 0, 8, false, "");
yield return (@"(?:|a)?(?:\b\d){2,}", " a 0", RegexOptions.None, 0, 4, false, "");
yield return (@"(?:|a)?(\d){2,}", " a00a", RegexOptions.None, 0, 5, true, "a00");
yield return (@"^( | )?((\w\d){3,}){3,}", " 12345678901234567", RegexOptions.None, 0, 18, false, "");
yield return (@"^( | )?((\w\d){3,}){3,}", " 123456789012345678", RegexOptions.None, 0, 19, true, " 123456789012345678");
yield return (@"^( | )?((\w\d){3,}){3,}", " 123456789012345678", RegexOptions.None, 0, 20, true, " 123456789012345678");
yield return (@"^( | )?((\w\d){3,}){3,}", " 123456789012345678", RegexOptions.None, 0, 21, false, "");

// Using beginning/end of string chars \A, \Z: Actual - "\\Aaaa\\w+zzz\\Z"
yield return (@"\Aaaa\w+zzz\Z", "aaaasdfajsdlfjzzz", RegexOptions.IgnoreCase, 0, 17, true, "aaaasdfajsdlfjzzz");
yield return (@"\Aaaaaa\w+zzz\Z", "aaaa", RegexOptions.IgnoreCase, 0, 4, false, string.Empty);
Expand Down