Skip to content

Use searchInterruptible for Joni regexp matching #16109

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

Merged
rschlussel merged 1 commit into from
May 24, 2021
Merged

Use searchInterruptible for Joni regexp matching #16109

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
22 changes: 17 additions & 5 deletions presto-main/src/main/java/com/facebook/presto/operator/scalar/JoniRegexpFunctions.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,7 @@
import java.nio.charset.StandardCharsets;

import static com.facebook.presto.common.type.VarcharType.VARCHAR;
import static com.facebook.presto.spi.StandardErrorCode.GENERIC_USER_ERROR;
import static com.facebook.presto.spi.StandardErrorCode.INVALID_FUNCTION_ARGUMENT;
import static java.lang.Math.toIntExact;
import static java.lang.String.format;
Expand All @@ -63,7 +64,8 @@ public static boolean regexpLike(@SqlType("varchar(x)") Slice source, @SqlType(J
offset = 0;
matcher = pattern.matcher(source.getBytes());
}
return matcher.search(offset, offset + source.length(), Option.DEFAULT) != -1;

return getMatchingOffset(matcher, offset, offset + source.length()) != -1;
}

@Description("removes substrings matching a regular expression")
Expand Down Expand Up @@ -93,7 +95,7 @@ public static Slice regexpReplace(@SqlType("varchar(x)") Slice source, @SqlType(
int lastEnd = 0;
int nextStart = 0; // nextStart is the same as lastEnd, unless the last match was zero-width. In such case, nextStart is lastEnd + 1.
while (true) {
int offset = matcher.search(nextStart, source.length(), Option.DEFAULT);
int offset = getMatchingOffset(matcher, nextStart, source.length());
if (offset == -1) {
break;
}
Expand Down Expand Up @@ -215,7 +217,7 @@ public static Block regexpExtractAll(@SqlType("varchar(x)") Slice source, @SqlTy

int nextStart = 0;
while (true) {
int offset = matcher.search(nextStart, source.length(), Option.DEFAULT);
int offset = getMatchingOffset(matcher, nextStart, source.length());
if (offset == -1) {
break;
}
Expand Down Expand Up @@ -260,7 +262,7 @@ public static Slice regexpExtract(@SqlType("varchar(x)") Slice source, @SqlType(
validateGroup(groupIndex, matcher.getEagerRegion());
int group = toIntExact(groupIndex);

int offset = matcher.search(0, source.length(), Option.DEFAULT);
int offset = getMatchingOffset(matcher, 0, source.length());
if (offset == -1) {
return null;
}
Expand Down Expand Up @@ -288,7 +290,7 @@ public static Block regexpSplit(@SqlType("varchar(x)") Slice source, @SqlType(Jo
int lastEnd = 0;
int nextStart = 0;
while (true) {
int offset = matcher.search(nextStart, source.length(), Option.DEFAULT);
int offset = getMatchingOffset(matcher, nextStart, source.length());
if (offset == -1) {
break;
}
Expand All @@ -307,6 +309,16 @@ public static Block regexpSplit(@SqlType("varchar(x)") Slice source, @SqlType(Jo
return blockBuilder.build();
}

private static int getMatchingOffset(Matcher matcher, int at, int range)
{
try {
return matcher.searchInterruptible(at, range, Option.DEFAULT);
}
catch (InterruptedException interruptedException) {
throw new PrestoException(GENERIC_USER_ERROR, "Regexp matching interrupted");
}
}

private static void validateGroup(long group, Region region)
{
if (group < 0) {
Expand Down