From e6d1406abd55bc24477eb8c6ee72c31e7110435e Mon Sep 17 00:00:00 2001 From: jeanlyn Date: Wed, 25 Mar 2015 17:47:45 -0700 Subject: [SPARK-5498][SQL]fix query exception when partition schema does not match table schema In hive,the schema of partition may be difference from the table schema.When we use spark-sql to query the data of partition which schema is difference from the table schema,we will get the exceptions as the description of the [jira](https://issues.apache.org/jira/browse/SPARK-5498) .For example: * We take a look of the schema for the partition and the table ```sql DESCRIBE partition_test PARTITION (dt='1'); id int None name string None dt string None # Partition Information # col_name data_type comment dt string None ``` ``` DESCRIBE partition_test; OK id bigint None name string None dt string None # Partition Information # col_name data_type comment dt string None ``` * run the sql ```sql SELECT * FROM partition_test where dt='1'; ``` we will get the cast exception `java.lang.ClassCastException: org.apache.spark.sql.catalyst.expressions.MutableLong cannot be cast to org.apache.spark.sql.catalyst.expressions.MutableInt` Author: jeanlyn Closes #4289 from jeanlyn/schema and squashes the following commits: 9c8da74 [jeanlyn] fix style b41d6b9 [jeanlyn] fix compile errors 07d84b6 [jeanlyn] Merge branch 'master' into schema 535b0b6 [jeanlyn] reduce conflicts d6c93c5 [jeanlyn] fix bug 1e8b30c [jeanlyn] fix code style 0549759 [jeanlyn] fix code style c879aa1 [jeanlyn] clean the code 2a91a87 [jeanlyn] add more test case and clean the code 12d800d [jeanlyn] fix code style 63d170a [jeanlyn] fix compile problem 7470901 [jeanlyn] reduce conflicts afc7da5 [jeanlyn] make getConvertedOI compatible between 0.12.0 and 0.13.1 b1527d5 [jeanlyn] fix type mismatch 10744ca [jeanlyn] Insert a space after the start of the comment 3b27af3 [jeanlyn] SPARK-5498:fix bug when query the data when partition schema does not match table schema --- .../src/main/scala/org/apache/spark/sql/hive/Shim13.scala | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'sql/hive/v0.13.1') diff --git a/sql/hive/v0.13.1/src/main/scala/org/apache/spark/sql/hive/Shim13.scala b/sql/hive/v0.13.1/src/main/scala/org/apache/spark/sql/hive/Shim13.scala index f9fcbdae15..7577309900 100644 --- a/sql/hive/v0.13.1/src/main/scala/org/apache/spark/sql/hive/Shim13.scala +++ b/sql/hive/v0.13.1/src/main/scala/org/apache/spark/sql/hive/Shim13.scala @@ -17,6 +17,7 @@ package org.apache.spark.sql.hive +import java.util import java.util.{ArrayList => JArrayList} import java.util.Properties import java.rmi.server.UID @@ -38,7 +39,7 @@ import org.apache.hadoop.hive.ql.processors.CommandProcessorFactory import org.apache.hadoop.hive.serde.serdeConstants import org.apache.hadoop.hive.serde2.typeinfo.{TypeInfo, DecimalTypeInfo, TypeInfoFactory} import org.apache.hadoop.hive.serde2.objectinspector.primitive.{HiveDecimalObjectInspector, PrimitiveObjectInspectorFactory} -import org.apache.hadoop.hive.serde2.objectinspector.{PrimitiveObjectInspector, ObjectInspector} +import org.apache.hadoop.hive.serde2.objectinspector.{ObjectInspectorConverters, PrimitiveObjectInspector, ObjectInspector} import org.apache.hadoop.hive.serde2.{Deserializer, ColumnProjectionUtils} import org.apache.hadoop.hive.serde2.{io => hiveIo} import org.apache.hadoop.hive.serde2.avro.AvroGenericRecordWritable @@ -400,7 +401,11 @@ private[hive] object HiveShim { Decimal(hdoi.getPrimitiveJavaObject(data).bigDecimalValue(), hdoi.precision(), hdoi.scale()) } } - + + def getConvertedOI(inputOI: ObjectInspector, outputOI: ObjectInspector): ObjectInspector = { + ObjectInspectorConverters.getConvertedOI(inputOI, outputOI) + } + /* * Bug introduced in hive-0.13. AvroGenericRecordWritable has a member recordReaderID that * is needed to initialize before serialization. -- cgit v1.2.3