This is an automated email from the ASF dual-hosted git repository.
dongjoon pushed a commit to branch branch-3.5
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/branch-3.5 by this push:
new 5de80b7f52fb [SPARK-50886][BUILD][3.5] Upgrade Avro to 1.11.4
5de80b7f52fb is described below
commit 5de80b7f52fb09df67b87a113c914644167a6976
Author: Dongjoon Hyun <[email protected]>
AuthorDate: Sat Jan 18 22:03:06 2025 -0800
[SPARK-50886][BUILD][3.5] Upgrade Avro to 1.11.4
### What changes were proposed in this pull request?
This PR aims to upgrade Avro to 1.11.4.
### Why are the changes needed?
To bring the latest bug fixes like the following.
- https://github.com/apache/avro/releases/tag/release-1.11.3
- https://github.com/apache/avro/pull/2432
- https://github.com/apache/avro/pull/2318
- https://github.com/apache/avro/pull/1720
- https://github.com/apache/avro/releases/tag/release-1.11.4
- https://github.com/apache/avro/pull/2980
### Does this PR introduce _any_ user-facing change?
Yes, this is a dependency change.
### How was this patch tested?
Pass the CIs.
### Was this patch authored or co-authored using generative AI tooling?
No.
Closes #49563 from dongjoon-hyun/SPARK-50886.
Authored-by: Dongjoon Hyun <[email protected]>
Signed-off-by: Dongjoon Hyun <[email protected]>
---
.../avro/src/main/scala/org/apache/spark/sql/avro/AvroOptions.scala | 4 ++--
dev/deps/spark-deps-hadoop-3-hive-2.3 | 6 +++---
docs/sql-data-sources-avro.md | 4 ++--
pom.xml | 6 +++++-
project/SparkBuild.scala | 3 ++-
.../scala/org/apache/spark/sql/hive/client/HiveClientSuite.scala | 2 +-
6 files changed, 15 insertions(+), 10 deletions(-)
diff --git
a/connector/avro/src/main/scala/org/apache/spark/sql/avro/AvroOptions.scala
b/connector/avro/src/main/scala/org/apache/spark/sql/avro/AvroOptions.scala
index edaaa8835cc0..5fd39393335d 100644
--- a/connector/avro/src/main/scala/org/apache/spark/sql/avro/AvroOptions.scala
+++ b/connector/avro/src/main/scala/org/apache/spark/sql/avro/AvroOptions.scala
@@ -81,14 +81,14 @@ private[sql] class AvroOptions(
/**
* Top level record name in write result, which is required in Avro spec.
- * See https://avro.apache.org/docs/1.11.2/specification/#schema-record .
+ * See https://avro.apache.org/docs/1.11.4/specification/#schema-record .
* Default value is "topLevelRecord"
*/
val recordName: String = parameters.getOrElse(RECORD_NAME, "topLevelRecord")
/**
* Record namespace in write result. Default value is "".
- * See Avro spec for details:
https://avro.apache.org/docs/1.11.2/specification/#schema-record .
+ * See Avro spec for details:
https://avro.apache.org/docs/1.11.4/specification/#schema-record .
*/
val recordNamespace: String = parameters.getOrElse(RECORD_NAMESPACE, "")
diff --git a/dev/deps/spark-deps-hadoop-3-hive-2.3
b/dev/deps/spark-deps-hadoop-3-hive-2.3
index 06e6aa199021..4feea62dfe64 100644
--- a/dev/deps/spark-deps-hadoop-3-hive-2.3
+++ b/dev/deps/spark-deps-hadoop-3-hive-2.3
@@ -21,9 +21,9 @@ arrow-memory-core/12.0.1//arrow-memory-core-12.0.1.jar
arrow-memory-netty/12.0.1//arrow-memory-netty-12.0.1.jar
arrow-vector/12.0.1//arrow-vector-12.0.1.jar
audience-annotations/0.5.0//audience-annotations-0.5.0.jar
-avro-ipc/1.11.2//avro-ipc-1.11.2.jar
-avro-mapred/1.11.2//avro-mapred-1.11.2.jar
-avro/1.11.2//avro-1.11.2.jar
+avro-ipc/1.11.4//avro-ipc-1.11.4.jar
+avro-mapred/1.11.4//avro-mapred-1.11.4.jar
+avro/1.11.4//avro-1.11.4.jar
aws-java-sdk-bundle/1.12.262//aws-java-sdk-bundle-1.12.262.jar
azure-data-lake-store-sdk/2.3.9//azure-data-lake-store-sdk-2.3.9.jar
azure-keyvault-core/1.0.0//azure-keyvault-core-1.0.0.jar
diff --git a/docs/sql-data-sources-avro.md b/docs/sql-data-sources-avro.md
index 1da75e5d7b17..a23c438af6d4 100644
--- a/docs/sql-data-sources-avro.md
+++ b/docs/sql-data-sources-avro.md
@@ -417,7 +417,7 @@ applications. Read the [Advanced Dependency
Management](https://spark.apache
Submission Guide for more details.
## Supported types for Avro -> Spark SQL conversion
-Currently Spark supports reading all [primitive
types](https://avro.apache.org/docs/1.11.2/specification/#primitive-types) and
[complex
types](https://avro.apache.org/docs/1.11.2/specification/#complex-types) under
records of Avro.
+Currently Spark supports reading all [primitive
types](https://avro.apache.org/docs/1.11.4/specification/#primitive-types) and
[complex
types](https://avro.apache.org/docs/1.11.4/specification/#complex-types) under
records of Avro.
<table>
<thead><tr><th><b>Avro type</b></th><th><b>Spark SQL
type</b></th></tr></thead>
<tr>
@@ -481,7 +481,7 @@ In addition to the types listed above, it supports reading
`union` types. The fo
3. `union(something, null)`, where something is any supported Avro type. This
will be mapped to the same Spark SQL type as that of something, with nullable
set to true.
All other union types are considered complex. They will be mapped to
StructType where field names are member0, member1, etc., in accordance with
members of the union. This is consistent with the behavior when converting
between Avro and Parquet.
-It also supports reading the following Avro [logical
types](https://avro.apache.org/docs/1.11.2/specification/#logical-types):
+It also supports reading the following Avro [logical
types](https://avro.apache.org/docs/1.11.4/specification/#logical-types):
<table>
<thead><tr><th><b>Avro logical type</b></th><th><b>Avro
type</b></th><th><b>Spark SQL type</b></th></tr></thead>
diff --git a/pom.xml b/pom.xml
index 0ccb6ac76a9b..e427f4d4ce68 100644
--- a/pom.xml
+++ b/pom.xml
@@ -158,7 +158,7 @@
-->
<codahale.metrics.version>4.2.19</codahale.metrics.version>
<!-- Should be consistent with SparkBuild.scala and docs -->
- <avro.version>1.11.2</avro.version>
+ <avro.version>1.11.4</avro.version>
<aws.kinesis.client.version>1.12.0</aws.kinesis.client.version>
<!-- Should be consistent with Kinesis client dependency -->
<aws.java.sdk.version>1.11.655</aws.java.sdk.version>
@@ -1485,6 +1485,10 @@
<artifactId>avro</artifactId>
<version>${avro.version}</version>
<exclusions>
+ <exclusion>
+ <groupId>org.apache.commons</groupId>
+ <artifactId>commons-compress</artifactId>
+ </exclusion>
<exclusion>
<groupId>commons-io</groupId>
<artifactId>commons-io</artifactId>
diff --git a/project/SparkBuild.scala b/project/SparkBuild.scala
index f8659a4f4a25..162f34415c53 100644
--- a/project/SparkBuild.scala
+++ b/project/SparkBuild.scala
@@ -1103,7 +1103,8 @@ object DependencyOverrides {
dependencyOverrides += "com.google.guava" % "guava" % guavaVersion,
dependencyOverrides += "xerces" % "xercesImpl" % "2.12.2",
dependencyOverrides += "jline" % "jline" % "2.14.6",
- dependencyOverrides += "org.apache.avro" % "avro" % "1.11.2")
+ dependencyOverrides += "org.apache.avro" % "avro" % "1.11.4",
+ dependencyOverrides += "org.apache.commons" % "commons-compress" %
"1.23.0")
}
/**
diff --git
a/sql/hive/src/test/scala/org/apache/spark/sql/hive/client/HiveClientSuite.scala
b/sql/hive/src/test/scala/org/apache/spark/sql/hive/client/HiveClientSuite.scala
index 8476c87dc283..d35cc79c6a32 100644
---
a/sql/hive/src/test/scala/org/apache/spark/sql/hive/client/HiveClientSuite.scala
+++
b/sql/hive/src/test/scala/org/apache/spark/sql/hive/client/HiveClientSuite.scala
@@ -908,7 +908,7 @@ class HiveClientSuite(version: String, allVersions:
Seq[String])
test("Decimal support of Avro Hive serde") {
val tableName = "tab1"
// TODO: add the other logical types. For details, see the link:
- // https://avro.apache.org/docs/1.11.2/specification/#logical-types
+ // https://avro.apache.org/docs/1.11.4/specification/#logical-types
val avroSchema =
"""{
| "name": "test_record",
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
