Merge branch 'apache:master' into master

.github/labeler.yml

@@ -17,145 +17,218 @@
 # under the License.
 #
 
-#
-# Pull Request Labeler Github Action Configuration: https://github.com/marketplace/actions/labeler
-#
-# Note that we currently cannot use the negatioon operator (i.e. `!`) for miniglob matches as they
-# would match any file that doesn't touch them. What's needed is the concept of `any `, which takes a
-# list of constraints / globs and then matches all of the constraints for either `any` of the files or
-# `all` of the files in the change set.
-#
-# However, `any`/`all` are not supported in a released version and testing off of the `main` branch
-# resulted in some other errors when testing.
-#
-# An issue has been opened upstream requesting that a release be cut that has support for all/any:
-# - https://github.com/actions/labeler/issues/111
-#
-# While we wait for this issue to be handled upstream, we can remove
-# the negated / `!` matches for now and at least have labels again.
-#
 INFRA:
- - ".github/**/*"
- - "appveyor.yml"
- - "tools/**/*"
- - "dev/create-release/**/*"
- - ".asf.yaml"
- - ".gitattributes"
- - ".gitignore"
- - "dev/github_jira_sync.py"
- - "dev/merge_spark_pr.py"
- - "dev/run-tests-jenkins*"
+ - changed-files:
+ - any-glob-to-any-file: [
+ '.github/**/*',
+ 'appveyor.yml',
+ 'tools/**/*',
+ 'dev/create-release/**/*',
+ '.asf.yaml',
+ '.gitattributes',
+ '.gitignore',
+ 'dev/merge_spark_pr.py',
+ 'dev/run-tests-jenkins*'
+ ]
+
 BUILD:
- # Can be supported when a stable release with correct all/any is released
- #- any: ['dev/**/*', '!dev/github_jira_sync.py', '!dev/merge_spark_pr.py', '!dev/.rat-excludes']
- - "dev/**/*"
- - "build/**/*"
- - "project/**/*"
- - "assembly/**/*"
- - "**/*pom.xml"
- - "bin/docker-image-tool.sh"
- - "bin/find-spark-home*"
- - "scalastyle-config.xml"
- # These can be added in the above `any` clause (and the /dev/**/* glob removed) when
- # `any`/`all` support is released
- # - "!dev/github_jira_sync.py"
- # - "!dev/merge_spark_pr.py"
- # - "!dev/run-tests-jenkins*"
- # - "!dev/.rat-excludes"
+  - changed-files:
+  - all-globs-to-any-file: [
+  'dev/**/*',
+  '!dev/merge_spark_pr.py',
+  '!dev/run-tests-jenkins*'
+  ]
+  - any-glob-to-any-file: [
+  'build/**/*',
+  'project/**/*',
+  'assembly/**/*',
+  '**/*pom.xml',
+  'bin/docker-image-tool.sh',
+  'bin/find-spark-home*',
+  'scalastyle-config.xml'
+  ]
+
 DOCS:
- - "docs/**/*"
- - "**/README.md"
- - "**/CONTRIBUTING.md"
+ - changed-files:
+ - any-glob-to-any-file: [
+ 'docs/**/*',
+ '**/README.md',
+ '**/CONTRIBUTING.md',
+ 'python/docs/**/*'
+ ]
+
 EXAMPLES:
- - "examples/**/*"
- - "bin/run-example*"
-# CORE needs to be updated when all/any are released upstream.
+ - changed-files:
+ - any-glob-to-any-file: [
+ 'examples/**/*',
+ 'bin/run-example*'
+ ]
+
 CORE:
- # - any: ["core/**/*", "!**/*UI.scala", "!**/ui/**/*"] # If any file matches all of the globs defined in the list started by `any`, label is applied.
- - "core/**/*"
- - "common/kvstore/**/*"
- - "common/network-common/**/*"
- - "common/network-shuffle/**/*"
- - "python/pyspark/*.py"
- - "python/pyspark/tests/**/*.py"
+ - changed-files:
+ - all-globs-to-any-file: [
+ 'core/**/*',
+ '!**/*UI.scala',
+ '!**/ui/**/*'
+ ]
+ - any-glob-to-any-file: [
+ 'common/kvstore/**/*',
+ 'common/network-common/**/*',
+ 'common/network-shuffle/**/*',
+ 'python/pyspark/*.py',
+ 'python/pyspark/tests/**/*.py'
+ ]
+
 SPARK SUBMIT:
- - "bin/spark-submit*"
+ - changed-files:
+ - any-glob-to-any-file: [
+ 'bin/spark-submit*'
+ ]
+
 SPARK SHELL:
- - "repl/**/*"
- - "bin/spark-shell*"
+ - changed-files:
+ - any-glob-to-any-file: [
+ 'repl/**/*',
+ 'bin/spark-shell*'
+ ]
+
 SQL:
-#- any: ["**/sql/**/*", "!python/pyspark/sql/avro/**/*", "!python/pyspark/sql/streaming/**/*", "!python/pyspark/sql/tests/streaming/test_streaming.py"]
- - "**/sql/**/*"
- - "common/unsafe/**/*"
- #- "!python/pyspark/sql/avro/**/*"
- #- "!python/pyspark/sql/streaming/**/*"
- #- "!python/pyspark/sql/tests/streaming/test_streaming.py"
- - "bin/spark-sql*"
- - "bin/beeline*"
- - "sbin/*thriftserver*.sh"
- - "**/*SQL*.R"
- - "**/DataFrame.R"
- - "**/*WindowSpec.R"
- - "**/*catalog.R"
- - "**/*column.R"
- - "**/*functions.R"
- - "**/*group.R"
- - "**/*schema.R"
- - "**/*types.R"
+ - changed-files:
+ - all-globs-to-any-file: [
+ '**/sql/**/*',
+ '!python/pyspark/sql/avro/**/*',
+ '!python/pyspark/sql/streaming/**/*',
+ '!python/pyspark/sql/tests/streaming/test_streaming*.py'
+ ]
+ - any-glob-to-any-file: [
+ 'common/unsafe/**/*',
+ 'bin/spark-sql*',
+ 'bin/beeline*',
+ 'sbin/*thriftserver*.sh',
+ '**/*SQL*.R',
+ '**/DataFrame.R',
+ '**/*WindowSpec.R',
+ '**/*catalog.R',
+ '**/*column.R',
+ '**/*functions.R',
+ '**/*group.R',
+ '**/*schema.R',
+ '**/*types.R'
+ ]
+
 AVRO:
- - "connector/avro/**/*"
- - "python/pyspark/sql/avro/**/*"
+ - changed-files:
+ - any-glob-to-any-file: [
+ 'connector/avro/**/*',
+ 'python/pyspark/sql/avro/**/*'
+ ]
+
 DSTREAM:
- - "streaming/**/*"
- - "data/streaming/**/*"
- - "connector/kinesis*"
- - "connector/kafka*"
- - "python/pyspark/streaming/**/*"
+ - changed-files:
+ - any-glob-to-any-file: [
+ 'streaming/**/*',
+ 'data/streaming/**/*',
+ 'connector/kinesis*',
+ 'connector/kafka*',
+ 'python/pyspark/streaming/**/*'
+ ]
+
 GRAPHX:
- - "graphx/**/*"
- - "data/graphx/**/*"
+ - changed-files:
+ - any-glob-to-any-file: [
+ 'graphx/**/*',
+ 'data/graphx/**/*'
+ ]
+
 ML:
- - "**/ml/**/*"
- - "**/*mllib_*.R"
+ - changed-files:
+ - any-glob-to-any-file: [
+ '**/ml/**/*',
+ '**/*mllib_*.R'
+ ]
+
 MLLIB:
- - "**/spark/mllib/**/*"
- - "mllib-local/**/*"
- - "python/pyspark/mllib/**/*"
+ - changed-files:
+ - any-glob-to-any-file: [
+ '**/spark/mllib/**/*',
+ 'mllib-local/**/*',
+ 'python/pyspark/mllib/**/*'
+ ]
+
 STRUCTURED STREAMING:
- - "**/sql/**/streaming/**/*"
- - "connector/kafka-0-10-sql/**/*"
- - "python/pyspark/sql/streaming/**/*"
- - "python/pyspark/sql/tests/streaming/test_streaming.py"
- - "**/*streaming.R"
+ - changed-files:
+ - any-glob-to-any-file: [
+ '**/sql/**/streaming/**/*',
+ 'connector/kafka-0-10-sql/**/*',
+ 'python/pyspark/sql/streaming/**/*',
+ 'python/pyspark/sql/tests/streaming/test_streaming*.py',
+ '**/*streaming.R'
+ ]
+
 PYTHON:
- - "bin/pyspark*"
- - "**/python/**/*"
+ - changed-files:
+ - any-glob-to-any-file: [
+ 'bin/pyspark*',
+ '**/python/**/*'
+ ]
+
 PANDAS API ON SPARK:
- - "python/pyspark/pandas/**/*"
+ - changed-files:
+ - any-glob-to-any-file: [
+ 'python/pyspark/pandas/**/*'
+ ]
+
 R:
- - "**/r/**/*"
- - "**/R/**/*"
- - "bin/sparkR*"
+ - changed-files:
+ - any-glob-to-any-file: [
+ '**/r/**/*',
+ '**/R/**/*',
+ 'bin/sparkR*'
+ ]
+
 YARN:
- - "resource-managers/yarn/**/*"
-MESOS:
- - "resource-managers/mesos/**/*"
- - "sbin/*mesos*.sh"
+ - changed-files:
+ - any-glob-to-any-file: [
+ 'resource-managers/yarn/**/*'
+ ]
+
 KUBERNETES:
- - "resource-managers/kubernetes/**/*"
+ - changed-files:
+ - any-glob-to-any-file: [
+ 'resource-managers/kubernetes/**/*'
+ ]
+
 WINDOWS:
- - "**/*.cmd"
- - "R/pkg/tests/fulltests/test_Windows.R"
+ - changed-files:
+ - any-glob-to-any-file: [
+ '**/*.cmd',
+ 'R/pkg/tests/fulltests/test_Windows.R'
+ ]
+
 WEB UI:
- - "**/ui/**/*"
- - "**/*UI.scala"
+ - changed-files:
+ - any-glob-to-any-file: [
+ '**/ui/**/*',
+ '**/*UI.scala'
+ ]
+
 DEPLOY:
- - "sbin/**/*"
+ - changed-files:
+ - any-glob-to-any-file: [
+ 'sbin/**/*'
+ ]
+
 CONNECT:
- - "connector/connect/**/*"
- - "**/sql/sparkconnect/**/*"
- - "python/pyspark/sql/**/connect/**/*"
- - "python/pyspark/ml/**/connect/**/*"
+ - changed-files:
+ - any-glob-to-any-file: [
+ 'connector/connect/**/*',
+ 'python/pyspark/sql/**/connect/**/*',
+ 'python/pyspark/ml/**/connect/**/*'
+ ]
+
 PROTOBUF:
- - "connector/protobuf/**/*"
- - "python/pyspark/sql/protobuf/**/*"
+ - changed-files:
+ - any-glob-to-any-file: [
+ 'connector/protobuf/**/*',
+ 'python/pyspark/sql/protobuf/**/*'
+ ]