Github user liancheng commented on a diff in the pull request:
https://github.com/apache/spark/pull/8956#discussion_r42174368
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilters.scala
---
@@ -48,6 +48,34 @@ private[sql] object ParquetFilters {
override def inverseCanDrop(statistics: Statistics[T]): Boolean = false
}
+ object StringFilter extends Enumeration {
+ type Mode = Value
+ val STARTS_WITH, ENDS_WITH, CONTAINS = Value
+ }
+
+ case class StringFilter(
+ v: java.lang.String,
+ mode: StringFilter.Mode) extends UserDefinedPredicate[Binary] with
Serializable {
+
+ private val compare = mode match {
+ case StringFilter.STARTS_WITH =>
+ (x: java.lang.String) => x.startsWith(v)
+ case StringFilter.ENDS_WITH =>
+ (x: java.lang.String) => x.endsWith(v)
+ case StringFilter.CONTAINS =>
+ (x: java.lang.String) => x.contains(v)
+ }
+
+ override def keep(value: Binary): Boolean = {
+ val str = value.toStringUsingUTF8()
--- End diff --
Nit: remove `()`
---
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]
