Cancelling a long running regex match?

Question

Say I\'m running a service where users can submit a regex to search through lots of data. If the user submits a regex that is very slow (ie. takes minutes for Matcher.find()

Answer 1

With a little variation it is possible to avoid using additional threads for this:

public class RegularExpressionUtils {

    // demonstrates behavior for regular expression running into catastrophic backtracking for given input
    public static void main(String[] args) {
        Matcher matcher = createMatcherWithTimeout(
                "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx", "(x+x+)+y", 2000);
        System.out.println(matcher.matches());
    }

    public static Matcher createMatcherWithTimeout(String stringToMatch, String regularExpression, int timeoutMillis) {
        Pattern pattern = Pattern.compile(regularExpression);
        return createMatcherWithTimeout(stringToMatch, pattern, timeoutMillis);
    }

    public static Matcher createMatcherWithTimeout(String stringToMatch, Pattern regularExpressionPattern, int timeoutMillis) {
        CharSequence charSequence = new TimeoutRegexCharSequence(stringToMatch, timeoutMillis, stringToMatch,
                regularExpressionPattern.pattern());
        return regularExpressionPattern.matcher(charSequence);
    }

    private static class TimeoutRegexCharSequence implements CharSequence {

        private final CharSequence inner;

        private final int timeoutMillis;

        private final long timeoutTime;

        private final String stringToMatch;

        private final String regularExpression;

        public TimeoutRegexCharSequence(CharSequence inner, int timeoutMillis, String stringToMatch, String regularExpression) {
            super();
            this.inner = inner;
            this.timeoutMillis = timeoutMillis;
            this.stringToMatch = stringToMatch;
            this.regularExpression = regularExpression;
            timeoutTime = System.currentTimeMillis() + timeoutMillis;
        }

        public char charAt(int index) {
            if (System.currentTimeMillis() > timeoutTime) {
                throw new RuntimeException("Timeout occurred after " + timeoutMillis + "ms while processing regular expression '"
                                + regularExpression + "' on input '" + stringToMatch + "'!");
            }
            return inner.charAt(index);
        }

        public int length() {
            return inner.length();
        }

        public CharSequence subSequence(int start, int end) {
            return new TimeoutRegexCharSequence(inner.subSequence(start, end), timeoutMillis, stringToMatch, regularExpression);
        }

        @Override
        public String toString() {
            return inner.toString();
        }
    }

}

Thanks a lot to dawce for pointing me to this solution in answer to an unnecessary complicated question !