1
0
mirror of https://github.com/golang/go synced 2024-11-12 04:50:21 -07:00

regexp: skip backtracker for long programs

This update makes maxBacktrackLen return 0 if
len(prog.Inst) > maxBacktrackProg. This prevents an attempt to
backtrack against a nil bitstate.

Fixes #10319

Change-Id: Icdbeb2392782ccf66f9d0a70ea57af22fb93f01b
Reviewed-on: https://go-review.googlesource.com/8473
Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
This commit is contained in:
Matthew Brennan 2015-04-03 20:09:53 -04:00 committed by Brad Fitzpatrick
parent 957255f5ab
commit a513088396
2 changed files with 22 additions and 1 deletions

View File

@ -47,6 +47,9 @@ var notBacktrack *bitState = nil
// maxBitStateLen returns the maximum length of a string to search with // maxBitStateLen returns the maximum length of a string to search with
// the backtracker using prog. // the backtracker using prog.
func maxBitStateLen(prog *syntax.Prog) int { func maxBitStateLen(prog *syntax.Prog) int {
if !shouldBacktrack(prog) {
return 0
}
return maxBacktrackVector / len(prog.Inst) return maxBacktrackVector / len(prog.Inst)
} }
@ -54,7 +57,7 @@ func maxBitStateLen(prog *syntax.Prog) int {
// or notBacktrack if the size of the prog exceeds the maximum size that // or notBacktrack if the size of the prog exceeds the maximum size that
// the backtracker will be run for. // the backtracker will be run for.
func newBitState(prog *syntax.Prog) *bitState { func newBitState(prog *syntax.Prog) *bitState {
if len(prog.Inst) > maxBacktrackProg { if !shouldBacktrack(prog) {
return notBacktrack return notBacktrack
} }
return &bitState{ return &bitState{
@ -62,6 +65,12 @@ func newBitState(prog *syntax.Prog) *bitState {
} }
} }
// shouldBacktrack reports whether the program is too
// long for the backtracker to run.
func shouldBacktrack(prog *syntax.Prog) bool {
return len(prog.Inst) <= maxBacktrackProg
}
// reset resets the state of the backtracker. // reset resets the state of the backtracker.
// end is the end position in the input. ncap and reqcap are the number // end is the end position in the input. ncap and reqcap are the number
// of the machine's capture registers and the number of user-requested // of the machine's capture registers and the number of user-requested

View File

@ -713,3 +713,15 @@ func TestLongest(t *testing.T) {
t.Errorf("longest match was %q, want %q", g, w) t.Errorf("longest match was %q, want %q", g, w)
} }
} }
// TestProgramTooLongForBacktrace tests that a regex which is too long
// for the backtracker still executes properly.
func TestProgramTooLongForBacktrack(t *testing.T) {
longRegex := MustCompile(`(one|two|three|four|five|six|seven|eight|nine|ten|eleven|twelve|thirteen|fourteen|fifteen|sixteen|seventeen|eighteen|nineteen|twenty|twentyone|twentytwo|twentythree|twentyfour|twentyfive|twentysix|twentyseven|twentyeight|twentynine|thirty|thirtyone|thirtytwo|thirtythree|thirtyfour|thirtyfive|thirtysix|thirtyseven|thirtyeight|thirtynine|forty|fortyone|fortytwo|fortythree|fortyfour|fortyfive|fortysix|fortyseven|fortyeight|fortynine|fifty|fiftyone|fiftytwo|fiftythree|fiftyfour|fiftyfive|fiftysix|fiftyseven|fiftyeight|fiftynine|sixty|sixtyone|sixtytwo|sixtythree|sixtyfour|sixtyfive|sixtysix|sixtyseven|sixtyeight|sixtynine|seventy|seventyone|seventytwo|seventythree|seventyfour|seventyfive|seventysix|seventyseven|seventyeight|seventynine|eighty|eightyone|eightytwo|eightythree|eightyfour|eightyfive|eightysix|eightyseven|eightyeight|eightynine|ninety|ninetyone|ninetytwo|ninetythree|ninetyfour|ninetyfive|ninetysix|ninetyseven|ninetyeight|ninetynine|onehundred)`)
if !longRegex.MatchString("two") {
t.Errorf("longRegex.MatchString(\"two\") was false, want true")
}
if longRegex.MatchString("xxx") {
t.Errorf("longRegex.MatchString(\"xxx\") was true, want false")
}
}