Github user paul-rogers commented on a diff in the pull request:
https://github.com/apache/drill/pull/1015#discussion_r149554195
--- Diff:
exec/java-exec/src/main/java/org/apache/drill/exec/expr/fn/impl/SqlPatternContainsMatcher.java
---
@@ -17,37 +17,48 @@
*/
package org.apache.drill.exec.expr.fn.impl;
-public class SqlPatternContainsMatcher implements SqlPatternMatcher {
- final String patternString;
- CharSequence charSequenceWrapper;
- final int patternLength;
-
- public SqlPatternContainsMatcher(String patternString, CharSequence
charSequenceWrapper) {
- this.patternString = patternString;
- this.charSequenceWrapper = charSequenceWrapper;
- patternLength = patternString.length();
+import io.netty.buffer.DrillBuf;
+
+public class SqlPatternContainsMatcher extends AbstractSqlPatternMatcher {
+
+ public SqlPatternContainsMatcher(String patternString) {
+ super(patternString);
}
@Override
- public int match() {
- final int txtLength = charSequenceWrapper.length();
- int patternIndex = 0;
- int txtIndex = 0;
-
- // simplePattern string has meta characters i.e % and _ and escape
characters removed.
- // so, we can just directly compare.
- while (patternIndex < patternLength && txtIndex < txtLength) {
- if (patternString.charAt(patternIndex) !=
charSequenceWrapper.charAt(txtIndex)) {
- // Go back if there is no match
- txtIndex = txtIndex - patternIndex;
- patternIndex = 0;
- } else {
- patternIndex++;
+ public int match(int start, int end, DrillBuf drillBuf) {
+
+ if (patternLength == 0) { // Everything should match for null pattern
string
+ return 1;
+ }
+
+ final int txtLength = end - start;
+
+ // no match if input string length is less than pattern length
+ if (txtLength < patternLength) {
+ return 0;
+ }
+
+ outer:
+ for (int txtIndex = 0; txtIndex < txtLength; txtIndex++) {
+
+ // boundary check
+ if (txtIndex + patternLength > txtLength) {
--- End diff --
Better:
```
int end = txtLength - patternLength;
for (int txtIndex = 0; txtIndex < end; txtIndex++) {
```
And omit the boundary check on every iteration. That is, no reason to
iterate past the last possible match, then use an if-statement to shorten the
loop. Just shorten the loop.
---
