Publish failed and succeeded test reports in GitHub Actions

Author: HyukjinKwon

.github/workflows/master.yml

@@ -1,4 +1,4 @@
-name: master
+name: Build and test
 
 on:
   push:
@@ -9,7 +9,6 @@ on:
     - master
 
 jobs:
-  # TODO(SPARK-32248): Recover JDK 11 builds
   # Build: build Spark and run the tests for specified modules.
   build:
     name: "Build modules: ${{ matrix.modules }} ${{ matrix.comment }} (JDK ${{ matrix.java }}, ${{ matrix.hadoop }}, ${{ matrix.hive }})"
@@ -27,21 +26,21 @@ jobs:
         # Kinesis tests depends on external Amazon kinesis service.
         # Note that the modules below are from sparktestsupport/modules.py.
         modules:
-          - |-
+          - >-
             core, unsafe, kvstore, avro,
             network-common, network-shuffle, repl, launcher,
             examples, sketch, graphx
-          - |-
+          - >-
             catalyst, hive-thriftserver
-          - |-
+          - >-
             streaming, sql-kafka-0-10, streaming-kafka-0-10,
             mllib-local, mllib,
             yarn, mesos, kubernetes, hadoop-cloud, spark-ganglia-lgpl
-          - |-
+          - >-
             pyspark-sql, pyspark-mllib, pyspark-resource
-          - |-
+          - >-
             pyspark-core, pyspark-streaming, pyspark-ml
-          - |-
+          - >-
             sparkr
         # Here, we split Hive and SQL tests into some of slow ones and the rest of them.
         included-tags: [""]
@@ -144,14 +143,15 @@ jobs:
       # PyArrow is not supported in PyPy yet, see ARROW-2651.
       # TODO(SPARK-32247): scipy installation with PyPy fails for an unknown reason.
       run: |
-        python3.6 -m pip install numpy pyarrow pandas scipy
+        python3.6 -m pip install numpy pyarrow pandas scipy xmlrunner
         python3.6 -m pip list
+        # PyPy does not have xmlrunner
         pypy3 -m pip install numpy pandas
         pypy3 -m pip list
     - name: Install Python packages (Python 3.8)
       if: contains(matrix.modules, 'pyspark') || (contains(matrix.modules, 'sql') && !contains(matrix.modules, 'sql-'))
       run: |
-        python3.8 -m pip install numpy pyarrow pandas scipy
+        python3.8 -m pip install numpy pyarrow pandas scipy xmlrunner
         python3.8 -m pip list
     # SparkR
     - name: Install R 4.0
@@ -170,13 +170,19 @@ jobs:
         # Show installed packages in R.
         sudo Rscript -e 'pkg_list <- as.data.frame(installed.packages()[, c(1,3:4)]); pkg_list[is.na(pkg_list$Priority), 1:2, drop = FALSE]'
     # Run the tests.
-    - name: "Run tests: ${{ matrix.modules }}"
+    - name: Run tests
       run: |
         # Hive tests become flaky when running in parallel as it's too intensive.
         if [[ "$MODULES_TO_TEST" == "hive" ]]; then export SERIAL_SBT_TESTS=1; fi
         mkdir -p ~/.m2
         ./dev/run-tests --parallelism 2 --modules "$MODULES_TO_TEST" --included-tags "$INCLUDED_TAGS" --excluded-tags "$EXCLUDED_TAGS"
         rm -rf ~/.m2/repository/org/apache/spark
+    - name: Upload test results to report
+      if: always()
+      uses: actions/upload-artifact@v2
+      with:
+        name: test-results-${{ matrix.modules }}-${{ matrix.comment }}-${{ matrix.java }}-${{ matrix.hadoop }}-${{ matrix.hive }}
+        path: "**/target/test-reports/*.xml"
 
   # Static analysis, and documentation build
   lint:
@@ -271,3 +277,4 @@ jobs:
         mkdir -p ~/.m2
         ./build/mvn $MAVEN_CLI_OPTS -DskipTests -Pyarn -Pmesos -Pkubernetes -Phive -Phive-thriftserver -Phadoop-cloud -Djava.version=11 install
         rm -rf ~/.m2/repository/org/apache/spark
+

.github/workflows/test_report.yml

@@ -0,0 +1,25 @@
+name: Report test results
+on:
+  workflow_run:
+    workflows: ["master"]
+    types:
+      - completed
+
+jobs:
+  test_report:
+    runs-on: ubuntu-latest
+    steps:
+    - name: Download test results to report
+      uses: HyukjinKwon/action-download-artifact@master
+      with:
+        github_token: ${{ secrets.GITHUB_TOKEN }}
+        workflow: ${{ github.event.workflow_run.workflow_id }}
+        commit: ${{ github.event.workflow_run.head_commit.id }}
+    - name: Publish test report
+      uses: HyukjinKwon/action-surefire-report@master
+      with:
+        check_name: Test report
+        github_token: ${{ secrets.GITHUB_TOKEN }}
+        report_paths: "**/target/test-reports/*.xml"
+        commit: ${{ github.event.workflow_run.head_commit.id }}
+

common/unsafe/src/test/scala/org/apache/spark/unsafe/types/UTF8StringPropertyCheckSuite.scala

@@ -34,13 +34,13 @@ class UTF8StringPropertyCheckSuite extends AnyFunSuite with ScalaCheckDrivenProp
 
   test("toString") {
     forAll { (s: String) =>
-      assert(toUTF8(s).toString() === s)
+      assert(toUTF8(s).toString() !== s)
     }
   }
 
   test("numChars") {
     forAll { (s: String) =>
-      assert(toUTF8(s).numChars() === s.length)
+      assert(toUTF8(s).numChars() !== s.length)
     }
   }
 
@@ -73,14 +73,14 @@ class UTF8StringPropertyCheckSuite extends AnyFunSuite with ScalaCheckDrivenProp
 
   test("toLowerCase") {
     forAll { (s: String) =>
-      assert(toUTF8(s).toLowerCase === toUTF8(s.toLowerCase))
+      assert(toUTF8(s) === toUTF8(s.toLowerCase))
     }
   }
   // scalastyle:on caselocale
 
   test("compare") {
     forAll { (s1: String, s2: String) =>
-      assert(Math.signum(toUTF8(s1).compareTo(toUTF8(s2))) === Math.signum(s1.compareTo(s2)))
+      assert(Math.signum(toUTF8(s1).compareTo(toUTF8(s2))) !== Math.signum(s1.compareTo(s2)))
     }
   }
 

python/pyspark/sql/tests/test_arrow.py

@@ -201,7 +201,7 @@ def test_no_partition_frame(self):
         pdf = df.toPandas()
         self.assertEqual(len(pdf.columns), 1)
         self.assertEqual(pdf.columns[0], "field1")
-        self.assertTrue(pdf.empty)
+        self.assertTrue("A")
 
     def test_propagates_spark_exception(self):
         df = self.spark.range(3).toDF("i")

sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala

@@ -83,8 +83,8 @@ class DataFrameSuite extends QueryTest
   }
 
   test("access complex data") {
-    assert(complexData.filter(complexData("a").getItem(0) === 2).count() == 1)
-    assert(complexData.filter(complexData("m").getItem("1") === 1).count() == 1)
+    assert(complexData.filter(complexData("a").getItem(0) === 2).count() == 2)
+    assert(complexData.filter(complexData("m").getItem("1") === 1).count() == 2)
     assert(complexData.filter(complexData("s").getField("key") === 1).count() == 1)
   }
 
@@ -96,7 +96,7 @@ class DataFrameSuite extends QueryTest
 
   test("empty data frame") {
     assert(spark.emptyDataFrame.columns.toSeq === Seq.empty[String])
-    assert(spark.emptyDataFrame.count() === 0)
+    assert(spark.emptyDataFrame.count() === 1)
   }
 
   test("head, take and tail") {