diff options
| author | William Benton <willb@redhat.com> | 2014-07-15 14:11:57 -0700 |
|---|---|---|
| committer | Michael Armbrust <michael@databricks.com> | 2014-07-15 14:12:15 -0700 |
| commit | 2db77e93198742eea05d600d5a9608266db18c0a (patch) | |
| tree | e6b3fdc0e8108df9201a32235b6a97407be41473 /sql/hive | |
| parent | f2bf6511a76694c937ed042367250e9f8ef4f9af (diff) | |
| download | spark-2db77e93198742eea05d600d5a9608266db18c0a.tar.gz spark-2db77e93198742eea05d600d5a9608266db18c0a.tar.bz2 spark-2db77e93198742eea05d600d5a9608266db18c0a.zip | |
SPARK-2407: Added internal implementation of SQL SUBSTR()
This replaces the Hive UDF for SUBSTR(ING) with an implementation in Catalyst
and adds tests to verify correct operation.
Author: William Benton <willb@redhat.com>
Closes #1359 from willb/internalSqlSubstring and squashes the following commits:
ccedc47 [William Benton] Fixed too-long line.
a30a037 [William Benton] replace view bounds with implicit parameters
ec35c80 [William Benton] Adds fixes from review:
4f3bfdb [William Benton] Added internal implementation of SQL SUBSTR()
(cherry picked from commit 61de65bc69f9a5fc396b76713193c6415436d452)
Signed-off-by: Michael Armbrust <michael@databricks.com>
Diffstat (limited to 'sql/hive')
| -rw-r--r-- | sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala index 56aa27a208..300e249f5b 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala @@ -860,6 +860,7 @@ private[hive] object HiveQl { val BETWEEN = "(?i)BETWEEN".r val WHEN = "(?i)WHEN".r val CASE = "(?i)CASE".r + val SUBSTR = "(?i)SUBSTR(?:ING)?".r protected def nodeToExpr(node: Node): Expression = node match { /* Attribute References */ @@ -984,6 +985,10 @@ private[hive] object HiveQl { /* Other functions */ case Token("TOK_FUNCTION", Token(RAND(), Nil) :: Nil) => Rand + case Token("TOK_FUNCTION", Token(SUBSTR(), Nil) :: string :: pos :: Nil) => + Substring(nodeToExpr(string), nodeToExpr(pos), Literal(Integer.MAX_VALUE, IntegerType)) + case Token("TOK_FUNCTION", Token(SUBSTR(), Nil) :: string :: pos :: length :: Nil) => + Substring(nodeToExpr(string), nodeToExpr(pos), nodeToExpr(length)) /* UDFs - Must be last otherwise will preempt built in functions */ case Token("TOK_FUNCTION", Token(name, Nil) :: args) => |