Skip to content

Commit e65600c

Browse files
manuzhangandygrove
andcommitted
build: Add spark-4.1 profile and shims
Co-authored-by: Andy Grove <[email protected]>
1 parent 0ae6515 commit e65600c

File tree

39 files changed

+3983
-23
lines changed

39 files changed

+3983
-23
lines changed

.github/workflows/pr_build_linux.yml

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -98,6 +98,11 @@ jobs:
9898
java_version: "17"
9999
maven_opts: "-Pspark-4.0"
100100
scan_impl: "native_comet"
101+
102+
- name: "Spark 4.1, JDK 17"
103+
java_version: "17"
104+
maven_opts: "-Pspark-4.1"
105+
scan_impl: "native_comet"
101106
suite:
102107
- name: "fuzz"
103108
value: |

.github/workflows/spark_sql_test.yml

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -50,7 +50,7 @@ jobs:
5050
strategy:
5151
matrix:
5252
os: [ubuntu-24.04]
53-
spark-version: [{short: '3.4', full: '3.4.3', java: 11}, {short: '3.5', full: '3.5.7', java: 11}, {short: '4.0', full: '4.0.1', java: 17}]
53+
spark-version: [{short: '3.4', full: '3.4.3', java: 11}, {short: '3.5', full: '3.5.7', java: 11}, {short: '4.0', full: '4.0.1', java: 17}, {short: '4.1', full: '4.1.0', java: 17}]
5454
module:
5555
- {name: "catalyst", args1: "catalyst/test", args2: ""}
5656
- {name: "sql_core-1", args1: "", args2: sql/testOnly * -- -l org.apache.spark.tags.ExtendedSQLTest -l org.apache.spark.tags.SlowSQLTest}
@@ -59,10 +59,12 @@ jobs:
5959
- {name: "sql_hive-1", args1: "", args2: "hive/testOnly * -- -l org.apache.spark.tags.ExtendedHiveTest -l org.apache.spark.tags.SlowHiveTest"}
6060
- {name: "sql_hive-2", args1: "", args2: "hive/testOnly * -- -n org.apache.spark.tags.ExtendedHiveTest"}
6161
- {name: "sql_hive-3", args1: "", args2: "hive/testOnly * -- -n org.apache.spark.tags.SlowHiveTest"}
62-
# Skip sql_hive-1 for Spark 4.0 due to https://github.com/apache/datafusion-comet/issues/2946
62+
# Skip sql_hive-1 for Spark 4.0+ due to https://github.com/apache/datafusion-comet/issues/2946
6363
exclude:
6464
- spark-version: {short: '4.0', full: '4.0.1', java: 17}
6565
module: {name: "sql_hive-1", args1: "", args2: "hive/testOnly * -- -l org.apache.spark.tags.ExtendedHiveTest -l org.apache.spark.tags.SlowHiveTest"}
66+
- spark-version: {short: '4.1', full: '4.1.0', java: 17}
67+
module: { name: "sql_hive-1", args1: "", args2: "hive/testOnly * -- -l org.apache.spark.tags.ExtendedHiveTest -l org.apache.spark.tags.SlowHiveTest" }
6668
fail-fast: false
6769
name: spark-sql-${{ matrix.module.name }}/${{ matrix.os }}/spark-${{ matrix.spark-version.full }}/java-${{ matrix.spark-version.java }}
6870
runs-on: ${{ matrix.os }}

common/src/main/spark-4.0/org/apache/comet/shims/CometTypeShim.scala renamed to common/src/main/spark-4.x/org/apache/comet/shims/CometTypeShim.scala

File renamed without changes.

common/src/main/spark-4.0/org/apache/comet/shims/ShimBatchReader.scala renamed to common/src/main/spark-4.x/org/apache/comet/shims/ShimBatchReader.scala

File renamed without changes.

common/src/main/spark-4.0/org/apache/comet/shims/ShimCometConf.scala renamed to common/src/main/spark-4.x/org/apache/comet/shims/ShimCometConf.scala

File renamed without changes.

common/src/main/spark-4.0/org/apache/comet/shims/ShimFileFormat.scala renamed to common/src/main/spark-4.x/org/apache/comet/shims/ShimFileFormat.scala

File renamed without changes.

common/src/main/spark-4.0/org/apache/spark/sql/comet/shims/ShimTaskMetrics.scala renamed to common/src/main/spark-4.x/org/apache/spark/sql/comet/shims/ShimTaskMetrics.scala

File renamed without changes.

dev/diffs/4.1.0.diff

Lines changed: 3740 additions & 0 deletions
Large diffs are not rendered by default.

docs/source/user-guide/latest/installation.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -50,6 +50,7 @@ use only and should not be used in production yet.
5050
| Spark Version | Java Version | Scala Version | Comet Tests in CI | Spark SQL Tests in CI |
5151
| ------------- | ------------ | ------------- | ----------------- | --------------------- |
5252
| 4.0.1 | 17 | 2.13 | Yes | Yes |
53+
| 4.1.0 | 17 | 2.13 | Yes | Yes |
5354

5455
Note that Comet may not fully work with proprietary forks of Apache Spark such as the Spark versions offered by
5556
Cloud Service Providers.

pom.xml

Lines changed: 23 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -642,8 +642,29 @@ under the License.
642642
<parquet.version>1.15.2</parquet.version>
643643
<semanticdb.version>4.13.6</semanticdb.version>
644644
<slf4j.version>2.0.16</slf4j.version>
645-
<shims.majorVerSrc>spark-4.0</shims.majorVerSrc>
646-
<shims.minorVerSrc>not-needed-yet</shims.minorVerSrc>
645+
<shims.majorVerSrc>spark-4.x</shims.majorVerSrc>
646+
<shims.minorVerSrc>spark-4.0</shims.minorVerSrc>
647+
<!-- Use jdk17 by default -->
648+
<java.version>17</java.version>
649+
<maven.compiler.source>${java.version}</maven.compiler.source>
650+
<maven.compiler.target>${java.version}</maven.compiler.target>
651+
</properties>
652+
</profile>
653+
654+
<profile>
655+
<!-- FIXME: this is WIP. Tests may fail https://github.com/apache/datafusion-comet/issues/551 -->
656+
<id>spark-4.1</id>
657+
<properties>
658+
<!-- Use Scala 2.13 by default -->
659+
<scala.version>2.13.17</scala.version>
660+
<scala.binary.version>2.13</scala.binary.version>
661+
<spark.version>4.1.0</spark.version>
662+
<spark.version.short>4.1</spark.version.short>
663+
<parquet.version>1.16.0</parquet.version>
664+
<semanticdb.version>4.13.9</semanticdb.version>
665+
<slf4j.version>2.0.17</slf4j.version>
666+
<shims.majorVerSrc>spark-4.x</shims.majorVerSrc>
667+
<shims.minorVerSrc>spark-4.1</shims.minorVerSrc>
647668
<!-- Use jdk17 by default -->
648669
<java.version>17</java.version>
649670
<maven.compiler.source>${java.version}</maven.compiler.source>

0 commit comments

Comments
 (0)