Github user ppadma commented on a diff in the pull request:
https://github.com/apache/drill/pull/1072#discussion_r158032627
--- Diff:
exec/java-exec/src/main/java/org/apache/drill/exec/expr/fn/impl/SqlPatternContainsMatcher.java
---
@@ -19,44 +19,283 @@
import io.netty.buffer.DrillBuf;
-public class SqlPatternContainsMatcher extends AbstractSqlPatternMatcher {
+/** SQL Pattern Contains implementation */
+public final class SqlPatternContainsMatcher extends
AbstractSqlPatternMatcher {
+ private final MatcherFcn matcherFcn;
public SqlPatternContainsMatcher(String patternString) {
super(patternString);
+
+ // Pattern matching is 1) a CPU intensive operation and 2) pattern and
input dependent. The conclusion is
+ // that there is no single implementation that can do it all well. So,
we use multiple implementations
+ // chosen based on the pattern length.
+ if (patternLength == 1) {
+ matcherFcn = new Matcher1();
+ } else if (patternLength == 2) {
+ matcherFcn = new Matcher2();
+ } else if (patternLength == 3) {
+ matcherFcn = new Matcher3();
+ } else if (patternLength < 10) {
+ matcherFcn = new MatcherN();
+ } else {
+ matcherFcn = new BoyerMooreMatcher();
+ }
}
@Override
public int match(int start, int end, DrillBuf drillBuf) {
+ return matcherFcn.match(start, end, drillBuf);
+ }
+
+
//--------------------------------------------------------------------------
+ // Inner Data Structure
+ //
--------------------------------------------------------------------------
+
+ /** Abstract matcher class to allow us pick the most efficient
implementation */
+ private abstract class MatcherFcn {
+ protected final byte[] patternArray;
+
+ protected MatcherFcn() {
+ assert patternByteBuffer.hasArray();
--- End diff --
is this true for null pattern ?
---
