Github user marmbrus commented on a diff in the pull request:
https://github.com/apache/spark/pull/224#discussion_r11002548
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringOperations.scala
---
@@ -19,11 +19,113 @@ package org.apache.spark.sql
package catalyst
package expressions
+import java.util.regex.Pattern
+
+import org.apache.spark.sql.catalyst.types.DataType
+import org.apache.spark.sql.catalyst.types.StringType
import org.apache.spark.sql.catalyst.types.BooleanType
+import org.apache.spark.sql.catalyst.trees.TreeNode
+import org.apache.spark.sql.catalyst.errors.`package`.TreeNodeException
+
+
+/**
+ * Thrown when an invalid RegEx string is found.
+ */
+class InvalidRegExException[TreeType <: TreeNode[_]](tree: TreeType,
reason: String) extends
+ errors.TreeNodeException(tree, s"$reason", null)
+
+trait StringRegexExpression {
+ self: BinaryExpression =>
+
+ type EvaluatedType = Any
+
+ def escape(v: String): String
+ def nullable: Boolean = true
+ def dataType: DataType = BooleanType
+
+ // try cache the pattern for Literal
+ private lazy val cache: Pattern = right match {
+ case x @ Literal(value: String, StringType) => compile(value)
+ case _ => null
+ }
+
+ protected def compile(str: Any): Pattern = str match {
+ // TODO or let it be null if couldn't compile the regex?
+ case x: String if(x != null) => Pattern.compile(escape(x))
+ case x: String => null
+ case _ => throw new InvalidRegExException(this, "$str can not be
compiled to regex pattern")
--- End diff --
Is the right thing to do throwing an exception, or should we just return
null? I'm not sure what Hive's semantics are.
---
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.
---
