Github user tarekauel commented on a diff in the pull request:
https://github.com/apache/spark/pull/7561#discussion_r35074260
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringOperations.scala
---
@@ -187,6 +187,64 @@ case class Like(left: Expression, right: Expression)
override def matches(regex: Pattern, str: String): Boolean =
regex.matcher(str).matches()
override def toString: String = s"$left LIKE $right"
+
+ override protected def genCode(ctx: CodeGenContext, ev:
GeneratedExpressionCode): String = {
+ val patternClass = classOf[Pattern].getName
+
+ val literalRight: String = right match {
+ case x @ Literal(value: String, StringType) => escape(value)
+ case _ => null
+ }
+
+ val leftGen = left.gen(ctx)
+ val rightGen = right.gen(ctx)
+
+ val patternCode =
+ if (literalRight != null) {
+ s"${patternClass} pattern = $patternClass.compile($literalRight);"
+ } else {
+ s"""
+ StringBuilder regex = new StringBuilder("(?s)");
+ for (int idx = 1; idx < rightStr.length(); idx++) {
+ char prev = rightStr.charAt(idx - 1);
+ char curr = rightStr.charAt(idx);
+ if (prev == '\\\\') {
+ if (curr == '_') {
+ regex.append("_");
+ } else if (curr == '%') {
+ regex.append("%");
+ } else {
+ regex.append(${patternClass}.quote("\\\\" + curr));
+ }
+ } else {
+ if (curr != '\\\\') {
+ if (curr == '_') {
+ regex.append(".");
+ } else if (curr == '%') {
+ regex.append(".*");
+ } else {
+ regex.append(${patternClass}.quote((new
Character(curr)).toString()));
+ }
+ }
+ }
+ }
+ ${patternClass} pattern =
${patternClass}.compile(regex.toString());
+ """
+ }
--- End diff --
Please put all the coding above in a static context. Then you can call it
from `codeGen` and the interpreted code and we avoid duplicated coding.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
