Merge branch 'apache:master' into asautins/explode-lazy

Author: asautins

.github/workflows/build_and_test.yml

@@ -522,9 +522,9 @@ jobs:
           - >-
             pyspark-pandas-slow
           - >-
-            pyspark-pandas-connect-part0, pyspark-pandas-connect-part3
+            pyspark-pandas-connect
           - >-
-            pyspark-pandas-connect-part1, pyspark-pandas-connect-part2
+            pyspark-pandas-slow-connect
         exclude:
           # Always run if pyspark == 'true', even infra-image is skip (such as non-master job)
           # In practice, the build will run in individual PR, but not against the individual commit
@@ -538,10 +538,8 @@ jobs:
           # in Apache Spark repository.
           - modules: ${{ fromJson(needs.precondition.outputs.required).pyspark-pandas != 'true' && 'pyspark-pandas' }}
           - modules: ${{ fromJson(needs.precondition.outputs.required).pyspark-pandas != 'true' && 'pyspark-pandas-slow' }}
-          - modules: ${{ fromJson(needs.precondition.outputs.required).pyspark-pandas != 'true' && 'pyspark-pandas-connect-part0' }}
-          - modules: ${{ fromJson(needs.precondition.outputs.required).pyspark-pandas != 'true' && 'pyspark-pandas-connect-part1' }}
-          - modules: ${{ fromJson(needs.precondition.outputs.required).pyspark-pandas != 'true' && 'pyspark-pandas-connect-part2' }}
-          - modules: ${{ fromJson(needs.precondition.outputs.required).pyspark-pandas != 'true' && 'pyspark-pandas-connect-part3' }}
+          - modules: ${{ fromJson(needs.precondition.outputs.required).pyspark-pandas != 'true' && 'pyspark-pandas-connect' }}
+          - modules: ${{ fromJson(needs.precondition.outputs.required).pyspark-pandas != 'true' && 'pyspark-pandas-slow-connect' }}
     env:
       MODULES_TO_TEST: ${{ matrix.modules }}
       HADOOP_PROFILE: ${{ inputs.hadoop }}

.github/workflows/build_python_connect.yml

@@ -96,7 +96,7 @@ jobs:
           # Several tests related to catalog requires to run them sequencially, e.g., writing a table in a listener.
           ./python/run-tests --parallelism=1 --python-executables=python3 --modules pyspark-connect,pyspark-ml-connect
           # None of tests are dependent on each other in Pandas API on Spark so run them in parallel
-          ./python/run-tests --parallelism=1 --python-executables=python3 --modules pyspark-pandas-connect-part0,pyspark-pandas-connect-part1,pyspark-pandas-connect-part2,pyspark-pandas-connect-part3
+          ./python/run-tests --parallelism=1 --python-executables=python3 --modules pyspark-pandas-connect,pyspark-pandas-slow-connect
 
           # Stop Spark Connect server.
           ./sbin/stop-connect-server.sh

.github/workflows/python_hosted_runner_test.yml

@@ -82,13 +82,9 @@ jobs:
           - >-
             pyspark-pandas-slow
           - >-
-            pyspark-pandas-connect-part0
+            pyspark-pandas-connect
           - >-
-            pyspark-pandas-connect-part1
-          - >-
-            pyspark-pandas-connect-part2
-          - >-
-            pyspark-pandas-connect-part3
+            pyspark-pandas-slow-connect
     env:
       MODULES_TO_TEST: ${{ matrix.modules }}
       PYTHON_TO_TEST: python${{inputs.python}}