Created
January 27, 2016 08:13
-
-
Save Groostav/44a31c904c3bf8c45085 to your computer and use it in GitHub Desktop.
Stack-Overflow in java regex engine
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class RegexTests{ | |
@Test | |
public void regex_can_match_massive_repition_without_stack_overflow(){ | |
Pattern pattern = Pattern.compile("([^\\r\\n]*?\\r?\\n){266959}(?<cool>.{30})"); | |
//a pattern that runs successfully is (?>[^\\r\\n]?\\r?\\n){266959}(?<cool>.{30}) | |
// note the atomic group on the front | |
// in my case, TwentyMegDocument is the first 300,000 lines or so | |
// of a wikipedia database dump (abstract-9): | |
// https://www.cs.purdue.edu/commugrate/data/wikipedia/dumps.wikimedia.org/enwiki/latest/ | |
Matcher matcher = pattern.matcher(TwentyMegDocument); | |
boolean found = matcher.find(); | |
assertThat(found).isTrue(); | |
assertThat(matcher.group("cool")).isNotNull().isNotEmpty(); | |
} | |
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
java.lang.StackOverflowError | |
at java.util.regex.Pattern$CharProperty.match(Pattern.java:3775) | |
at java.util.regex.Pattern$Curly.match0(Pattern.java:4250) | |
at java.util.regex.Pattern$Curly.match(Pattern.java:4234) | |
at java.util.regex.Pattern$GroupHead.match(Pattern.java:4658) | |
at java.util.regex.Pattern$Loop.match(Pattern.java:4772) | |
at java.util.regex.Pattern$GroupTail.match(Pattern.java:4717) | |
at java.util.regex.Pattern$BmpCharProperty.match(Pattern.java:3798) | |
at java.util.regex.Pattern$Ques.match(Pattern.java:4181) | |
at java.util.regex.Pattern$Curly.match0(Pattern.java:4272) | |
at java.util.regex.Pattern$Curly.match(Pattern.java:4234) | |
at java.util.regex.Pattern$GroupHead.match(Pattern.java:4658) | |
at java.util.regex.Pattern$Loop.match(Pattern.java:4772) | |
at java.util.regex.Pattern$GroupTail.match(Pattern.java:4717) | |
at java.util.regex.Pattern$BmpCharProperty.match(Pattern.java:3798) | |
at java.util.regex.Pattern$Ques.match(Pattern.java:4181) | |
at java.util.regex.Pattern$Curly.match0(Pattern.java:4272) | |
at java.util.regex.Pattern$Curly.match(Pattern.java:4234) | |
at java.util.regex.Pattern$GroupHead.match(Pattern.java:4658) | |
at java.util.regex.Pattern$Loop.match(Pattern.java:4772) | |
at java.util.regex.Pattern$GroupTail.match(Pattern.java:4717) | |
at java.util.regex.Pattern$BmpCharProperty.match(Pattern.java:3798) | |
... and around and around |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment