Github user liancheng commented on a diff in the pull request:
https://github.com/apache/spark/pull/224#discussion_r10928264
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringOperations.scala
---
@@ -20,10 +20,114 @@ package catalyst
package expressions
import org.apache.spark.sql.catalyst.types.BooleanType
+import java.util.regex.Pattern
-case class Like(left: Expression, right: Expression) extends
BinaryExpression {
- def dataType = BooleanType
- def nullable = left.nullable // Right cannot be null.
+import catalyst.types.StringType
+import catalyst.types.BooleanType
+import catalyst.trees.TreeNode
+
+import catalyst.errors.`package`.TreeNodeException
+import org.apache.spark.sql.catalyst.types.DataType
+
+
+/**
+ * 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")
+ }
+
+ protected def pattern(str: String) = if(cache == null) compile(str) else
cache
+
+ protected def filter: PartialFunction[(Row, (String, String)), Any] = {
--- End diff --
Return type of the partial function can be `Boolean`, same as above.
---
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.
---
