cgivre commented on code in PR #2762:
URL: https://github.com/apache/drill/pull/2762#discussion_r1115197954
##########
exec/java-exec/src/main/java/org/apache/drill/exec/expr/fn/impl/StringFunctions.java:
##########
@@ -293,6 +293,115 @@ public void eval() {
}
}
+ /*
+ * This function returns the capturing groups from a regex.
+ */
+ @FunctionTemplate(name = "regexp_extract", scope = FunctionScope.SIMPLE,
+ outputWidthCalculatorType =
OutputWidthCalculatorType.CUSTOM_FIXED_WIDTH_DEFAULT)
+ public static class RegexpExtract implements DrillSimpleFunc {
+
+ @Param VarCharHolder input;
+ @Param(constant=true) VarCharHolder pattern;
+ @Inject
+ DrillBuf buffer;
+ @Workspace
+ java.util.regex.Matcher matcher;
+ @Workspace
+ org.apache.drill.exec.expr.fn.impl.CharSequenceWrapper charSequenceWrapper;
+ @Output
+ ComplexWriter out;
+
+ @Override
+ public void setup() {
+ matcher =
java.util.regex.Pattern.compile(org.apache.drill.exec.expr.fn.impl.StringFunctionHelpers.toStringFromUTF8(pattern.start,
pattern.end, pattern.buffer)).matcher("");
+ charSequenceWrapper = new
org.apache.drill.exec.expr.fn.impl.CharSequenceWrapper();
+ matcher.reset(charSequenceWrapper);
+ }
+
+ @Override
+ public void eval() {
+ charSequenceWrapper.setBuffer(input.start, input.end, input.buffer);
+
+ // Reusing same charSequenceWrapper, no need to pass it in.
+ matcher.reset();
+ boolean result = matcher.find();
+
+ // Start the list here. If there are no matches, we return an empty
list.
+ org.apache.drill.exec.vector.complex.writer.BaseWriter.ListWriter
listWriter = out.rootAsList();
+ listWriter.startList();
+
+ if (result) {
+ org.apache.drill.exec.vector.complex.writer.VarCharWriter
varCharWriter = listWriter.varChar();
+ String extractedResult;
+ for(int i = 1; i <= matcher.groupCount(); i++) {
+ extractedResult = matcher.group(i);
Review Comment:
Fixed.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: dev-unsubscr...@drill.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
