This is an automated email from the ASF dual-hosted git repository.
yumwang pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new a7683af [SPARK-26346][BUILD][SQL] Upgrade Parquet to 1.11.1
a7683af is described below
commit a7683afdf498c3ee09466dfa9635edacb5cc8f0c
Author: Yuming Wang <yumw...@ebay.com>
AuthorDate: Fri Jan 29 08:07:49 2021 +0800
[SPARK-26346][BUILD][SQL] Upgrade Parquet to 1.11.1
### What changes were proposed in this pull request?
This PR upgrade Parquet to 1.11.1.
Parquet 1.11.1 new features:
- [PARQUET-1201](https://issues.apache.org/jira/browse/PARQUET-1201) -
Column indexes
- [PARQUET-1253](https://issues.apache.org/jira/browse/PARQUET-1253) -
Support for new logical type representation
- [PARQUET-1388](https://issues.apache.org/jira/browse/PARQUET-1388) -
Nanosecond precision time and timestamp - parquet-mr
More details:
https://github.com/apache/parquet-mr/blob/apache-parquet-1.11.1/CHANGES.md
### Why are the changes needed?
Support column indexes to improve query performance.
### Does this PR introduce any user-facing change?
No.
### How was this patch tested?
Existing test.
Closes #26804 from wangyum/SPARK-26346.
Authored-by: Yuming Wang <yumw...@ebay.com>
Signed-off-by: Yuming Wang <yumw...@ebay.com>
---
dev/deps/spark-deps-hadoop-2.7-hive-2.3 | 12 ++++++------
dev/deps/spark-deps-hadoop-3.2-hive-2.3 | 12 ++++++------
pom.xml | 6 +++++-
.../datasources/parquet/ParquetSchemaSuite.scala | 22 +++++++++++-----------
.../apache/spark/sql/streaming/StreamSuite.scala | 4 +++-
.../apache/spark/sql/hive/StatisticsSuite.scala | 2 +-
6 files changed, 32 insertions(+), 26 deletions(-)
diff --git a/dev/deps/spark-deps-hadoop-2.7-hive-2.3
b/dev/deps/spark-deps-hadoop-2.7-hive-2.3
index 2c468b8..179ab36 100644
--- a/dev/deps/spark-deps-hadoop-2.7-hive-2.3
+++ b/dev/deps/spark-deps-hadoop-2.7-hive-2.3
@@ -202,12 +202,12 @@ orc-shims/1.6.7//orc-shims-1.6.7.jar
oro/2.0.8//oro-2.0.8.jar
osgi-resource-locator/1.0.3//osgi-resource-locator-1.0.3.jar
paranamer/2.8//paranamer-2.8.jar
-parquet-column/1.10.1//parquet-column-1.10.1.jar
-parquet-common/1.10.1//parquet-common-1.10.1.jar
-parquet-encoding/1.10.1//parquet-encoding-1.10.1.jar
-parquet-format/2.4.0//parquet-format-2.4.0.jar
-parquet-hadoop/1.10.1//parquet-hadoop-1.10.1.jar
-parquet-jackson/1.10.1//parquet-jackson-1.10.1.jar
+parquet-column/1.11.1//parquet-column-1.11.1.jar
+parquet-common/1.11.1//parquet-common-1.11.1.jar
+parquet-encoding/1.11.1//parquet-encoding-1.11.1.jar
+parquet-format-structures/1.11.1//parquet-format-structures-1.11.1.jar
+parquet-hadoop/1.11.1//parquet-hadoop-1.11.1.jar
+parquet-jackson/1.11.1//parquet-jackson-1.11.1.jar
protobuf-java/2.5.0//protobuf-java-2.5.0.jar
py4j/0.10.9.1//py4j-0.10.9.1.jar
pyrolite/4.30//pyrolite-4.30.jar
diff --git a/dev/deps/spark-deps-hadoop-3.2-hive-2.3
b/dev/deps/spark-deps-hadoop-3.2-hive-2.3
index 894fd6a..83c32c4 100644
--- a/dev/deps/spark-deps-hadoop-3.2-hive-2.3
+++ b/dev/deps/spark-deps-hadoop-3.2-hive-2.3
@@ -172,12 +172,12 @@ orc-shims/1.6.7//orc-shims-1.6.7.jar
oro/2.0.8//oro-2.0.8.jar
osgi-resource-locator/1.0.3//osgi-resource-locator-1.0.3.jar
paranamer/2.8//paranamer-2.8.jar
-parquet-column/1.10.1//parquet-column-1.10.1.jar
-parquet-common/1.10.1//parquet-common-1.10.1.jar
-parquet-encoding/1.10.1//parquet-encoding-1.10.1.jar
-parquet-format/2.4.0//parquet-format-2.4.0.jar
-parquet-hadoop/1.10.1//parquet-hadoop-1.10.1.jar
-parquet-jackson/1.10.1//parquet-jackson-1.10.1.jar
+parquet-column/1.11.1//parquet-column-1.11.1.jar
+parquet-common/1.11.1//parquet-common-1.11.1.jar
+parquet-encoding/1.11.1//parquet-encoding-1.11.1.jar
+parquet-format-structures/1.11.1//parquet-format-structures-1.11.1.jar
+parquet-hadoop/1.11.1//parquet-hadoop-1.11.1.jar
+parquet-jackson/1.11.1//parquet-jackson-1.11.1.jar
protobuf-java/2.5.0//protobuf-java-2.5.0.jar
py4j/0.10.9.1//py4j-0.10.9.1.jar
pyrolite/4.30//pyrolite-4.30.jar
diff --git a/pom.xml b/pom.xml
index 84ec92e..05a2e04 100644
--- a/pom.xml
+++ b/pom.xml
@@ -136,7 +136,7 @@
<kafka.version>2.6.0</kafka.version>
<!-- After 10.15.1.3, the minimum required version is JDK9 -->
<derby.version>10.14.2.0</derby.version>
- <parquet.version>1.10.1</parquet.version>
+ <parquet.version>1.11.1</parquet.version>
<orc.version>1.6.7</orc.version>
<jetty.version>9.4.34.v20201102</jetty.version>
<jakartaservlet.version>4.0.3</jakartaservlet.version>
@@ -2290,6 +2290,10 @@
<groupId>commons-pool</groupId>
<artifactId>commons-pool</artifactId>
</exclusion>
+ <exclusion>
+ <groupId>javax.annotation</groupId>
+ <artifactId>javax.annotation-api</artifactId>
+ </exclusion>
</exclusions>
</dependency>
<dependency>
diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaSuite.scala
index e97c6cd..fcc08ee 100644
---
a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaSuite.scala
+++
b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaSuite.scala
@@ -251,7 +251,7 @@ class ParquetSchemaInferenceSuite extends ParquetSchemaTest
{
"""
|message root {
| optional group _1 (MAP) {
- | repeated group map (MAP_KEY_VALUE) {
+ | repeated group key_value (MAP_KEY_VALUE) {
| required int32 key;
| optional binary value (UTF8);
| }
@@ -267,7 +267,7 @@ class ParquetSchemaInferenceSuite extends ParquetSchemaTest
{
"""
|message root {
| optional group _1 (MAP) {
- | repeated group map (MAP_KEY_VALUE) {
+ | repeated group key_value (MAP_KEY_VALUE) {
| required group key {
| optional binary _1 (UTF8);
| optional binary _2 (UTF8);
@@ -300,7 +300,7 @@ class ParquetSchemaInferenceSuite extends ParquetSchemaTest
{
"""
|message root {
| optional group _1 (MAP_KEY_VALUE) {
- | repeated group map {
+ | repeated group key_value {
| required int32 key;
| optional group value {
| optional binary _1 (UTF8);
@@ -740,7 +740,7 @@ class ParquetSchemaSuite extends ParquetSchemaTest {
nullable = true))),
"""message root {
| optional group f1 (MAP_KEY_VALUE) {
- | repeated group map {
+ | repeated group key_value {
| required int32 num;
| required binary str (UTF8);
| }
@@ -759,7 +759,7 @@ class ParquetSchemaSuite extends ParquetSchemaTest {
nullable = true))),
"""message root {
| optional group f1 (MAP) {
- | repeated group map (MAP_KEY_VALUE) {
+ | repeated group key_value (MAP_KEY_VALUE) {
| required int32 key;
| required binary value (UTF8);
| }
@@ -797,7 +797,7 @@ class ParquetSchemaSuite extends ParquetSchemaTest {
nullable = true))),
"""message root {
| optional group f1 (MAP_KEY_VALUE) {
- | repeated group map {
+ | repeated group key_value {
| required int32 num;
| optional binary str (UTF8);
| }
@@ -816,7 +816,7 @@ class ParquetSchemaSuite extends ParquetSchemaTest {
nullable = true))),
"""message root {
| optional group f1 (MAP) {
- | repeated group map (MAP_KEY_VALUE) {
+ | repeated group key_value (MAP_KEY_VALUE) {
| required int32 key;
| optional binary value (UTF8);
| }
@@ -857,7 +857,7 @@ class ParquetSchemaSuite extends ParquetSchemaTest {
nullable = true))),
"""message root {
| optional group f1 (MAP) {
- | repeated group map (MAP_KEY_VALUE) {
+ | repeated group key_value (MAP_KEY_VALUE) {
| required int32 key;
| required binary value (UTF8);
| }
@@ -893,7 +893,7 @@ class ParquetSchemaSuite extends ParquetSchemaTest {
nullable = true))),
"""message root {
| optional group f1 (MAP) {
- | repeated group map (MAP_KEY_VALUE) {
+ | repeated group key_value (MAP_KEY_VALUE) {
| required int32 key;
| optional binary value (UTF8);
| }
@@ -1447,7 +1447,7 @@ class ParquetSchemaSuite extends ParquetSchemaTest {
parquetSchema =
"""message root {
| required group f0 (MAP) {
- | repeated group map (MAP_KEY_VALUE) {
+ | repeated group key_value (MAP_KEY_VALUE) {
| required int32 key;
| required group value {
| required int32 value_f0;
@@ -1472,7 +1472,7 @@ class ParquetSchemaSuite extends ParquetSchemaTest {
expectedSchema =
"""message root {
| required group f0 (MAP) {
- | repeated group map (MAP_KEY_VALUE) {
+ | repeated group key_value (MAP_KEY_VALUE) {
| required int32 key;
| required group value {
| required int64 value_f1;
diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamSuite.scala
index 440fe99..c4e43d2 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamSuite.scala
@@ -214,7 +214,9 @@ class StreamSuite extends StreamTest {
.start(outputDir.getAbsolutePath)
try {
query.processAllAvailable()
- val outputDf =
spark.read.parquet(outputDir.getAbsolutePath).as[Long]
+ // Parquet write page-level CRC checksums will change the file
size and
+ // affect the data order when reading these files. Please see
PARQUET-1746 for details.
+ val outputDf =
spark.read.parquet(outputDir.getAbsolutePath).sort('a).as[Long]
checkDataset[Long](outputDf, (0L to 10L).toArray: _*)
} finally {
query.stop()
diff --git
a/sql/hive/src/test/scala/org/apache/spark/sql/hive/StatisticsSuite.scala
b/sql/hive/src/test/scala/org/apache/spark/sql/hive/StatisticsSuite.scala
index 5357f4b..c91ee92 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/StatisticsSuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/StatisticsSuite.scala
@@ -1528,7 +1528,7 @@ class StatisticsSuite extends
StatisticsCollectionTestBase with TestHiveSingleto
Seq(tbl, ext_tbl).foreach { tblName =>
sql(s"INSERT INTO $tblName VALUES (1, 'a', '2019-12-13')")
- val expectedSize = 601
+ val expectedSize = 651
// analyze table
sql(s"ANALYZE TABLE $tblName COMPUTE STATISTICS NOSCAN")
var tableStats = getTableStats(tblName)
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org
