diff options
author | Daoyuan Wang <daoyuan.wang@intel.com> | 2015-02-02 15:49:22 -0800 |
---|---|---|
committer | Michael Armbrust <michael@databricks.com> | 2015-02-02 15:49:22 -0800 |
commit | 1646f89d967913ee1f231d9606f8502d13c25804 (patch) | |
tree | 86e89b964e7cd8a596e54621544af0052abb1d83 /sql/hive/src | |
parent | 830934976e8cf9e894bd3e5758fb941cad5d2f0b (diff) | |
download | spark-1646f89d967913ee1f231d9606f8502d13c25804.tar.gz spark-1646f89d967913ee1f231d9606f8502d13c25804.tar.bz2 spark-1646f89d967913ee1f231d9606f8502d13c25804.zip |
[SPARK-4508] [SQL] build native date type to conform behavior to Hive
Store daysSinceEpoch as an Int value(4 bytes) to represent DateType, instead of using java.sql.Date(8 bytes as Long) in catalyst row. This ensures the same comparison behavior of Hive and Catalyst.
Subsumes #3381
I thinks there are already some tests in JavaSQLSuite, and for python it will not affect python's datetime class.
Author: Daoyuan Wang <daoyuan.wang@intel.com>
Closes #3732 from adrian-wang/datenative and squashes the following commits:
0ed0fdc [Daoyuan Wang] fix test data
a2fdd4e [Daoyuan Wang] getDate
c37832b [Daoyuan Wang] row to catalyst
f0005b1 [Daoyuan Wang] add date in sql parser and java type conversion
024c9a6 [Daoyuan Wang] clean some import order
d6715fc [Daoyuan Wang] refactoring Date as Primitive Int internally
374abd5 [Daoyuan Wang] spark native date type support
Diffstat (limited to 'sql/hive/src')
26 files changed, 41 insertions, 11 deletions
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala index b746942cb1..724bd28d4b 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala @@ -18,7 +18,7 @@ package org.apache.spark.sql.hive import java.io.{BufferedReader, InputStreamReader, PrintStream} -import java.sql.{Date, Timestamp} +import java.sql.Timestamp import scala.collection.JavaConversions._ import scala.language.implicitConversions @@ -409,7 +409,7 @@ private object HiveContext { toHiveStructString((key, kType)) + ":" + toHiveStructString((value, vType)) }.toSeq.sorted.mkString("{", ",", "}") case (null, _) => "NULL" - case (d: Date, DateType) => new DateWritable(d).toString + case (d: Int, DateType) => new DateWritable(d).toString case (t: Timestamp, TimestampType) => new TimestampWritable(t).toString case (bin: Array[Byte], BinaryType) => new String(bin, "UTF-8") case (decimal: java.math.BigDecimal, DecimalType()) => diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala index 82dba99900..4afa2e71d7 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala @@ -267,7 +267,8 @@ private[hive] trait HiveInspectors { val temp = new Array[Byte](writable.getLength) System.arraycopy(writable.getBytes, 0, temp, 0, temp.length) temp - case poi: WritableConstantDateObjectInspector => poi.getWritableConstantValue.get() + case poi: WritableConstantDateObjectInspector => + DateUtils.fromJavaDate(poi.getWritableConstantValue.get()) case mi: StandardConstantMapObjectInspector => // take the value from the map inspector object, rather than the input data mi.getWritableConstantValue.map { case (k, v) => @@ -304,7 +305,8 @@ private[hive] trait HiveInspectors { System.arraycopy(bw.getBytes(), 0, result, 0, bw.getLength()) result case x: DateObjectInspector if x.preferWritable() => - x.getPrimitiveWritableObject(data).get() + DateUtils.fromJavaDate(x.getPrimitiveWritableObject(data).get()) + case x: DateObjectInspector => DateUtils.fromJavaDate(x.getPrimitiveJavaObject(data)) // org.apache.hadoop.hive.serde2.io.TimestampWritable.set will reset current time object // if next timestamp is null, so Timestamp object is cloned case x: TimestampObjectInspector if x.preferWritable() => @@ -343,6 +345,9 @@ private[hive] trait HiveInspectors { case _: JavaHiveDecimalObjectInspector => (o: Any) => HiveShim.createDecimal(o.asInstanceOf[Decimal].toJavaBigDecimal) + case _: JavaDateObjectInspector => + (o: Any) => DateUtils.toJavaDate(o.asInstanceOf[Int]) + case soi: StandardStructObjectInspector => val wrappers = soi.getAllStructFieldRefs.map(ref => wrapperFor(ref.getFieldObjectInspector)) (o: Any) => { @@ -426,7 +431,7 @@ private[hive] trait HiveInspectors { case _: BinaryObjectInspector if x.preferWritable() => HiveShim.getBinaryWritable(a) case _: BinaryObjectInspector => a.asInstanceOf[Array[Byte]] case _: DateObjectInspector if x.preferWritable() => HiveShim.getDateWritable(a) - case _: DateObjectInspector => a.asInstanceOf[java.sql.Date] + case _: DateObjectInspector => DateUtils.toJavaDate(a.asInstanceOf[Int]) case _: TimestampObjectInspector if x.preferWritable() => HiveShim.getTimestampWritable(a) case _: TimestampObjectInspector => a.asInstanceOf[java.sql.Timestamp] } diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala index c368715f7c..effaa5a443 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala @@ -34,6 +34,7 @@ import org.apache.spark.SerializableWritable import org.apache.spark.broadcast.Broadcast import org.apache.spark.rdd.{EmptyRDD, HadoopRDD, RDD, UnionRDD} import org.apache.spark.sql.catalyst.expressions._ +import org.apache.spark.sql.types.DateUtils /** * A trait for subclasses that handle table scans. @@ -306,7 +307,7 @@ private[hive] object HadoopTableReader extends HiveInspectors { row.update(ordinal, oi.getPrimitiveJavaObject(value).clone()) case oi: DateObjectInspector => (value: Any, row: MutableRow, ordinal: Int) => - row.update(ordinal, oi.getPrimitiveJavaObject(value)) + row.update(ordinal, DateUtils.fromJavaDate(oi.getPrimitiveJavaObject(value))) case oi: BinaryObjectInspector => (value: Any, row: MutableRow, ordinal: Int) => row.update(ordinal, oi.getPrimitiveJavaObject(value)) diff --git a/sql/hive/src/test/resources/golden/Date cast-0-a7cd69b80c77a771a2c955db666be53d b/sql/hive/src/test/resources/golden/Date cast-0-a7cd69b80c77a771a2c955db666be53d new file mode 100644 index 0000000000..98da82fa89 --- /dev/null +++ b/sql/hive/src/test/resources/golden/Date cast-0-a7cd69b80c77a771a2c955db666be53d @@ -0,0 +1 @@ +1970-01-01 1970-01-01 1969-12-31 16:00:00 1969-12-31 16:00:00 1970-01-01 00:00:00 diff --git a/sql/hive/src/test/resources/golden/Date comparison test 1-0-bde89be08a12361073ff658fef768b7e b/sql/hive/src/test/resources/golden/Date comparison test 1-0-bde89be08a12361073ff658fef768b7e new file mode 100644 index 0000000000..27ba77ddaf --- /dev/null +++ b/sql/hive/src/test/resources/golden/Date comparison test 1-0-bde89be08a12361073ff658fef768b7e @@ -0,0 +1 @@ +true diff --git a/sql/hive/src/test/resources/golden/Date comparison test 2-0-dc1b267f1d79d49e6675afe4fd2a34a5 b/sql/hive/src/test/resources/golden/Date comparison test 2-0-dc1b267f1d79d49e6675afe4fd2a34a5 new file mode 100644 index 0000000000..27ba77ddaf --- /dev/null +++ b/sql/hive/src/test/resources/golden/Date comparison test 2-0-dc1b267f1d79d49e6675afe4fd2a34a5 @@ -0,0 +1 @@ +true diff --git a/sql/hive/src/test/resources/golden/date_1-0-50131c0ba7b7a6b65c789a5a8497bada b/sql/hive/src/test/resources/golden/date_1-0-50131c0ba7b7a6b65c789a5a8497bada new file mode 100644 index 0000000000..573541ac97 --- /dev/null +++ b/sql/hive/src/test/resources/golden/date_1-0-50131c0ba7b7a6b65c789a5a8497bada @@ -0,0 +1 @@ +0 diff --git a/sql/hive/src/test/resources/golden/date_1-0-23edf29bf7376c70d5ecf12720f4b1eb b/sql/hive/src/test/resources/golden/date_1-1-23edf29bf7376c70d5ecf12720f4b1eb index e69de29bb2..e69de29bb2 100644 --- a/sql/hive/src/test/resources/golden/date_1-0-23edf29bf7376c70d5ecf12720f4b1eb +++ b/sql/hive/src/test/resources/golden/date_1-1-23edf29bf7376c70d5ecf12720f4b1eb diff --git a/sql/hive/src/test/resources/golden/date_1-3-df16364a220ff96a6ea1cd478cbc1d0b b/sql/hive/src/test/resources/golden/date_1-10-df16364a220ff96a6ea1cd478cbc1d0b index 963bc42fde..963bc42fde 100644 --- a/sql/hive/src/test/resources/golden/date_1-3-df16364a220ff96a6ea1cd478cbc1d0b +++ b/sql/hive/src/test/resources/golden/date_1-10-df16364a220ff96a6ea1cd478cbc1d0b diff --git a/sql/hive/src/test/resources/golden/date_1-10-d964bec7e5632091ab5cb6f6786dbbf9 b/sql/hive/src/test/resources/golden/date_1-11-d964bec7e5632091ab5cb6f6786dbbf9 index 8fb5edae63..8fb5edae63 100644 --- a/sql/hive/src/test/resources/golden/date_1-10-d964bec7e5632091ab5cb6f6786dbbf9 +++ b/sql/hive/src/test/resources/golden/date_1-11-d964bec7e5632091ab5cb6f6786dbbf9 diff --git a/sql/hive/src/test/resources/golden/date_1-11-480c5f024a28232b7857be327c992509 b/sql/hive/src/test/resources/golden/date_1-12-480c5f024a28232b7857be327c992509 index 5a368ab170..5a368ab170 100644 --- a/sql/hive/src/test/resources/golden/date_1-11-480c5f024a28232b7857be327c992509 +++ b/sql/hive/src/test/resources/golden/date_1-12-480c5f024a28232b7857be327c992509 diff --git a/sql/hive/src/test/resources/golden/date_1-12-4c0ed7fcb75770d8790575b586bf14f4 b/sql/hive/src/test/resources/golden/date_1-13-4c0ed7fcb75770d8790575b586bf14f4 index edb4b1f840..edb4b1f840 100644 --- a/sql/hive/src/test/resources/golden/date_1-12-4c0ed7fcb75770d8790575b586bf14f4 +++ b/sql/hive/src/test/resources/golden/date_1-13-4c0ed7fcb75770d8790575b586bf14f4 diff --git a/sql/hive/src/test/resources/golden/date_1-13-44fc74c1993062c0a9522199ff27fea b/sql/hive/src/test/resources/golden/date_1-14-44fc74c1993062c0a9522199ff27fea index 2af0b9ed3a..2af0b9ed3a 100644 --- a/sql/hive/src/test/resources/golden/date_1-13-44fc74c1993062c0a9522199ff27fea +++ b/sql/hive/src/test/resources/golden/date_1-14-44fc74c1993062c0a9522199ff27fea diff --git a/sql/hive/src/test/resources/golden/date_1-14-4855a66124b16d1d0d003235995ac06b b/sql/hive/src/test/resources/golden/date_1-15-4855a66124b16d1d0d003235995ac06b index d8dfbf6000..d8dfbf6000 100644 --- a/sql/hive/src/test/resources/golden/date_1-14-4855a66124b16d1d0d003235995ac06b +++ b/sql/hive/src/test/resources/golden/date_1-15-4855a66124b16d1d0d003235995ac06b diff --git a/sql/hive/src/test/resources/golden/date_1-15-8bc190dba0f641840b5e1e198a14c55b b/sql/hive/src/test/resources/golden/date_1-16-8bc190dba0f641840b5e1e198a14c55b index 4f6a1bc427..4f6a1bc427 100644 --- a/sql/hive/src/test/resources/golden/date_1-15-8bc190dba0f641840b5e1e198a14c55b +++ b/sql/hive/src/test/resources/golden/date_1-16-8bc190dba0f641840b5e1e198a14c55b diff --git a/sql/hive/src/test/resources/golden/date_1-1-4ebe3571c13a8b0c03096fbd972b7f1b b/sql/hive/src/test/resources/golden/date_1-17-23edf29bf7376c70d5ecf12720f4b1eb index e69de29bb2..e69de29bb2 100644 --- a/sql/hive/src/test/resources/golden/date_1-1-4ebe3571c13a8b0c03096fbd972b7f1b +++ b/sql/hive/src/test/resources/golden/date_1-17-23edf29bf7376c70d5ecf12720f4b1eb diff --git a/sql/hive/src/test/resources/golden/date_1-16-23edf29bf7376c70d5ecf12720f4b1eb b/sql/hive/src/test/resources/golden/date_1-2-4ebe3571c13a8b0c03096fbd972b7f1b index e69de29bb2..e69de29bb2 100644 --- a/sql/hive/src/test/resources/golden/date_1-16-23edf29bf7376c70d5ecf12720f4b1eb +++ b/sql/hive/src/test/resources/golden/date_1-2-4ebe3571c13a8b0c03096fbd972b7f1b diff --git a/sql/hive/src/test/resources/golden/date_1-2-abdce0c0d14d3fc7441b7c134b02f99a b/sql/hive/src/test/resources/golden/date_1-3-26b5c291400dfde455b3c1b878b71d0 index e69de29bb2..e69de29bb2 100644 --- a/sql/hive/src/test/resources/golden/date_1-2-abdce0c0d14d3fc7441b7c134b02f99a +++ b/sql/hive/src/test/resources/golden/date_1-3-26b5c291400dfde455b3c1b878b71d0 diff --git a/sql/hive/src/test/resources/golden/date_1-6-df16364a220ff96a6ea1cd478cbc1d0b b/sql/hive/src/test/resources/golden/date_1-4-df16364a220ff96a6ea1cd478cbc1d0b index 963bc42fde..963bc42fde 100644 --- a/sql/hive/src/test/resources/golden/date_1-6-df16364a220ff96a6ea1cd478cbc1d0b +++ b/sql/hive/src/test/resources/golden/date_1-4-df16364a220ff96a6ea1cd478cbc1d0b diff --git a/sql/hive/src/test/resources/golden/date_1-4-d964bec7e5632091ab5cb6f6786dbbf9 b/sql/hive/src/test/resources/golden/date_1-5-d964bec7e5632091ab5cb6f6786dbbf9 index 8fb5edae63..8fb5edae63 100644 --- a/sql/hive/src/test/resources/golden/date_1-4-d964bec7e5632091ab5cb6f6786dbbf9 +++ b/sql/hive/src/test/resources/golden/date_1-5-d964bec7e5632091ab5cb6f6786dbbf9 diff --git a/sql/hive/src/test/resources/golden/date_1-5-5e70fc74158fbfca38134174360de12d b/sql/hive/src/test/resources/golden/date_1-6-559d01fb0b42c42f0c4927fa0f9deac4 index e69de29bb2..e69de29bb2 100644 --- a/sql/hive/src/test/resources/golden/date_1-5-5e70fc74158fbfca38134174360de12d +++ b/sql/hive/src/test/resources/golden/date_1-6-559d01fb0b42c42f0c4927fa0f9deac4 diff --git a/sql/hive/src/test/resources/golden/date_1-9-df16364a220ff96a6ea1cd478cbc1d0b b/sql/hive/src/test/resources/golden/date_1-7-df16364a220ff96a6ea1cd478cbc1d0b index 963bc42fde..963bc42fde 100644 --- a/sql/hive/src/test/resources/golden/date_1-9-df16364a220ff96a6ea1cd478cbc1d0b +++ b/sql/hive/src/test/resources/golden/date_1-7-df16364a220ff96a6ea1cd478cbc1d0b diff --git a/sql/hive/src/test/resources/golden/date_1-7-d964bec7e5632091ab5cb6f6786dbbf9 b/sql/hive/src/test/resources/golden/date_1-8-d964bec7e5632091ab5cb6f6786dbbf9 index 8fb5edae63..8fb5edae63 100644 --- a/sql/hive/src/test/resources/golden/date_1-7-d964bec7e5632091ab5cb6f6786dbbf9 +++ b/sql/hive/src/test/resources/golden/date_1-8-d964bec7e5632091ab5cb6f6786dbbf9 diff --git a/sql/hive/src/test/resources/golden/date_1-8-1d5c58095cd52ea539d869f2ab1ab67d b/sql/hive/src/test/resources/golden/date_1-9-8306558e0eabe936ac33dabaaa17fea4 index e69de29bb2..e69de29bb2 100644 --- a/sql/hive/src/test/resources/golden/date_1-8-1d5c58095cd52ea539d869f2ab1ab67d +++ b/sql/hive/src/test/resources/golden/date_1-9-8306558e0eabe936ac33dabaaa17fea4 diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveInspectorSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveInspectorSuite.scala index 2d3ff68012..09bbd5c867 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveInspectorSuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveInspectorSuite.scala @@ -18,7 +18,6 @@ package org.apache.spark.sql.hive import java.util -import java.sql.Date import java.util.{Locale, TimeZone} import org.apache.hadoop.hive.ql.udf.UDAFPercentile @@ -76,7 +75,7 @@ class HiveInspectorSuite extends FunSuite with HiveInspectors { Literal(0.asInstanceOf[Float]) :: Literal(0.asInstanceOf[Double]) :: Literal("0") :: - Literal(new Date(2014, 9, 23)) :: + Literal(new java.sql.Date(114, 8, 23)) :: Literal(Decimal(BigDecimal(123.123))) :: Literal(new java.sql.Timestamp(123123)) :: Literal(Array[Byte](1,2,3)) :: @@ -143,7 +142,6 @@ class HiveInspectorSuite extends FunSuite with HiveInspectors { case (r1: Array[Byte], r2: Array[Byte]) if r1 != null && r2 != null && r1.length == r2.length => r1.zip(r2).map { case (b1, b2) => assert(b1 === b2) } - case (r1: Date, r2: Date) => assert(r1.compareTo(r2) === 0) case (r1, r2) => assert(r1 === r2) } } diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala index 4c53b10ba9..4f67d1def6 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala @@ -253,8 +253,30 @@ class HiveQuerySuite extends HiveComparisonTest with BeforeAndAfter { createQueryTest("Cast Timestamp to Timestamp in UDF", """ - | SELECT DATEDIFF(CAST(value AS timestamp), CAST('2002-03-21 00:00:00' AS timestamp)) - | FROM src LIMIT 1 + | SELECT DATEDIFF(CAST(value AS timestamp), CAST('2002-03-21 00:00:00' AS timestamp)) + | FROM src LIMIT 1 + """.stripMargin) + + createQueryTest("Date comparison test 1", + """ + | SELECT + | CAST(CAST('1970-01-01 22:00:00' AS timestamp) AS date) == + | CAST(CAST('1970-01-01 23:00:00' AS timestamp) AS date) + | FROM src LIMIT 1 + """.stripMargin) + + createQueryTest("Date comparison test 2", + "SELECT CAST(CAST(0 AS timestamp) AS date) > CAST(0 AS timestamp) FROM src LIMIT 1") + + createQueryTest("Date cast", + """ + | SELECT + | CAST(CAST(0 AS timestamp) AS date), + | CAST(CAST(CAST(0 AS timestamp) AS date) AS string), + | CAST(0 AS timestamp), + | CAST(CAST(0 AS timestamp) AS string), + | CAST(CAST(CAST('1970-01-01 23:00:00' AS timestamp) AS date) AS timestamp) + | FROM src LIMIT 1 """.stripMargin) createQueryTest("Simple Average", |