Merge remote-tracking branch 'upstream/master'

Author: beliefer

.github/workflows/build_and_test.yml

@@ -23,7 +23,7 @@ jobs:
       fail-fast: false
       matrix:
         java:
-          - 1.8
+          - 8
         hadoop:
           - hadoop3.2
         hive:
@@ -49,26 +49,26 @@ jobs:
         include:
           # Hive tests
           - modules: hive
-            java: 1.8
+            java: 8
             hadoop: hadoop3.2
             hive: hive2.3
             included-tags: org.apache.spark.tags.SlowHiveTest
             comment: "- slow tests"
           - modules: hive
-            java: 1.8
+            java: 8
             hadoop: hadoop3.2
             hive: hive2.3
             excluded-tags: org.apache.spark.tags.SlowHiveTest
             comment: "- other tests"
           # SQL tests
           - modules: sql
-            java: 1.8
+            java: 8
             hadoop: hadoop3.2
             hive: hive2.3
             included-tags: org.apache.spark.tags.ExtendedSQLTest
             comment: "- slow tests"
           - modules: sql
-            java: 1.8
+            java: 8
             hadoop: hadoop3.2
             hive: hive2.3
             excluded-tags: org.apache.spark.tags.ExtendedSQLTest
@@ -101,24 +101,18 @@ jobs:
           build/zinc-*
           build/scala-*
           build/*.jar
+          ~/.sbt
         key: build-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }}
         restore-keys: |
           build-
-    - name: Cache Maven local repository
-      uses: actions/cache@v2
-      with:
-        path: ~/.m2/repository
-        key: ${{ matrix.java }}-${{ matrix.hadoop }}-maven-${{ hashFiles('**/pom.xml') }}
-        restore-keys: |
-          ${{ matrix.java }}-${{ matrix.hadoop }}-maven-
     - name: Cache Coursier local repository
       uses: actions/cache@v2
       with:
         path: ~/.cache/coursier
         key: ${{ matrix.java }}-${{ matrix.hadoop }}-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
         restore-keys: |
           ${{ matrix.java }}-${{ matrix.hadoop }}-coursier-
-    - name: Install JDK ${{ matrix.java }}
+    - name: Install Java ${{ matrix.java }}
       uses: actions/setup-java@v1
       with:
         java-version: ${{ matrix.java }}
@@ -139,11 +133,9 @@ jobs:
     # Run the tests.
     - name: Run tests
       run: |
-        # Hive tests become flaky when running in parallel as it's too intensive.
-        if [[ "$MODULES_TO_TEST" == "hive" ]]; then export SERIAL_SBT_TESTS=1; fi
-        mkdir -p ~/.m2
+        # Hive and SQL tests become flaky when running in parallel as it's too intensive.
+        if [[ "$MODULES_TO_TEST" == "hive" ]] || [[ "$MODULES_TO_TEST" == "sql" ]]; then export SERIAL_SBT_TESTS=1; fi
         ./dev/run-tests --parallelism 2 --modules "$MODULES_TO_TEST" --included-tags "$INCLUDED_TAGS" --excluded-tags "$EXCLUDED_TAGS"
-        rm -rf ~/.m2/repository/org/apache/spark
     - name: Upload test results to report
       if: always()
       uses: actions/upload-artifact@v2
@@ -196,16 +188,10 @@ jobs:
           build/zinc-*
           build/scala-*
           build/*.jar
+          ~/.sbt
         key: build-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }}
         restore-keys: |
           build-
-    - name: Cache Maven local repository
-      uses: actions/cache@v2
-      with:
-        path: ~/.m2/repository
-        key: pyspark-maven-${{ hashFiles('**/pom.xml') }}
-        restore-keys: |
-          pyspark-maven-
     - name: Cache Coursier local repository
       uses: actions/cache@v2
       with:
@@ -228,24 +214,22 @@ jobs:
     # Run the tests.
     - name: Run tests
       run: |
-        mkdir -p ~/.m2
         ./dev/run-tests --parallelism 2 --modules "$MODULES_TO_TEST"
-        rm -rf ~/.m2/repository/org/apache/spark
     - name: Upload test results to report
       if: always()
       uses: actions/upload-artifact@v2
       with:
-        name: test-results-${{ matrix.modules }}--1.8-hadoop3.2-hive2.3
+        name: test-results-${{ matrix.modules }}--8-hadoop3.2-hive2.3
         path: "**/target/test-reports/*.xml"
     - name: Upload unit tests log files
       if: failure()
       uses: actions/upload-artifact@v2
       with:
-        name: unit-tests-log-${{ matrix.modules }}--1.8-hadoop3.2-hive2.3
+        name: unit-tests-log-${{ matrix.modules }}--8-hadoop3.2-hive2.3
         path: "**/target/unit-tests.log"
 
   sparkr:
-    name: Build modules - sparkr
+    name: "Build modules: sparkr"
     runs-on: ubuntu-20.04
     container:
       image: dongjoon/apache-spark-github-action-image:20201025
@@ -272,16 +256,10 @@ jobs:
           build/zinc-*
           build/scala-*
           build/*.jar
+          ~/.sbt
         key: build-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }}
         restore-keys: |
           build-
-    - name: Cache Maven local repository
-      uses: actions/cache@v2
-      with:
-        path: ~/.m2/repository
-        key: sparkr-maven-${{ hashFiles('**/pom.xml') }}
-        restore-keys: |
-          sparkr-maven-
     - name: Cache Coursier local repository
       uses: actions/cache@v2
       with:
@@ -291,18 +269,16 @@ jobs:
           sparkr-coursier-
     - name: Run tests
       run: |
-        mkdir -p ~/.m2
         # The followings are also used by `r-lib/actions/setup-r` to avoid
         # R issues at docker environment
         export TZ=UTC
         export _R_CHECK_SYSTEM_CLOCK_=FALSE
         ./dev/run-tests --parallelism 2 --modules sparkr
-        rm -rf ~/.m2/repository/org/apache/spark
     - name: Upload test results to report
       if: always()
       uses: actions/upload-artifact@v2
       with:
-        name: test-results-sparkr--1.8-hadoop3.2-hive2.3
+        name: test-results-sparkr--8-hadoop3.2-hive2.3
         path: "**/target/test-reports/*.xml"
 
   # Static analysis, and documentation build
@@ -312,17 +288,37 @@ jobs:
     steps:
     - name: Checkout Spark repository
       uses: actions/checkout@v2
+    # Cache local repositories. Note that GitHub Actions cache has a 2G limit.
+    - name: Cache Scala, SBT, Maven and Zinc
+      uses: actions/cache@v2
+      with:
+        path: |
+          build/apache-maven-*
+          build/zinc-*
+          build/scala-*
+          build/*.jar
+          ~/.sbt
+        key: build-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }}
+        restore-keys: |
+          build-
+    - name: Cache Coursier local repository
+      uses: actions/cache@v2
+      with:
+        path: ~/.cache/coursier
+        key: docs-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
+        restore-keys: |
+          docs-coursier-
     - name: Cache Maven local repository
       uses: actions/cache@v2
       with:
         path: ~/.m2/repository
-        key: docs-maven-repo-${{ hashFiles('**/pom.xml') }}
+        key: docs-maven-${{ hashFiles('**/pom.xml') }}
         restore-keys: |
           docs-maven-
-    - name: Install JDK 1.8
+    - name: Install Java 8
       uses: actions/setup-java@v1
       with:
-        java-version: 1.8
+        java-version: 8
     - name: Install Python 3.6
       uses: actions/setup-python@v2
       with:
@@ -373,8 +369,8 @@ jobs:
         cd docs
         jekyll build
 
-  java11:
-    name: Java 11 build
+  java-11:
+    name: Java 11 build with Maven
     runs-on: ubuntu-20.04
     steps:
     - name: Checkout Spark repository
@@ -394,12 +390,12 @@ jobs:
       run: |
         export MAVEN_OPTS="-Xmx2g -XX:ReservedCodeCacheSize=1g -Dorg.slf4j.simpleLogger.defaultLogLevel=WARN"
         export MAVEN_CLI_OPTS="--no-transfer-progress"
-        mkdir -p ~/.m2
+        # It uses Maven's 'install' intentionally, see https://github.com/apache/spark/pull/26414.
         ./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
 
   scala-213:
-    name: Scala 2.13 build
+    name: Scala 2.13 build with SBT
     runs-on: ubuntu-20.04
     steps:
     - name: Checkout Spark repository
@@ -411,11 +407,32 @@ jobs:
         key: scala-213-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
         restore-keys: |
           scala-213-coursier-
-    - name: Install Java 11
+    - name: Install Java 8
       uses: actions/setup-java@v1
       with:
-        java-version: 11
+        java-version: 8
     - name: Build with SBT
       run: |
         ./dev/change-scala-version.sh 2.13
         ./build/sbt -Pyarn -Pmesos -Pkubernetes -Phive -Phive-thriftserver -Phadoop-cloud -Pkinesis-asl -Djava.version=11 -Pscala-2.13 compile test:compile
+
+  hadoop-2:
+    name: Hadoop 2 build with SBT
+    runs-on: ubuntu-20.04
+    steps:
+    - name: Checkout Spark repository
+      uses: actions/checkout@v2
+    - name: Cache Coursier local repository
+      uses: actions/cache@v2
+      with:
+        path: ~/.cache/coursier
+        key: hadoop-2-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
+        restore-keys: |
+          hadoop-2-coursier-
+    - name: Install Java 8
+      uses: actions/setup-java@v1
+      with:
+        java-version: 8
+    - name: Build with SBT
+      run: |
+        ./build/sbt -Pyarn -Pmesos -Pkubernetes -Phive -Phive-thriftserver -Phadoop-cloud -Pkinesis-asl -Phadoop-2.7 compile test:compile

R/pkg/NAMESPACE

@@ -292,6 +292,7 @@ exportMethods("%<=>%",
               "floor",
               "format_number",
               "format_string",
+              "from_avro",
               "from_csv",
               "from_json",
               "from_unixtime",
@@ -416,6 +417,7 @@ exportMethods("%<=>%",
               "timestamp_seconds",
               "toDegrees",
               "toRadians",
+              "to_avro",
               "to_csv",
               "to_date",
               "to_json",

R/pkg/R/functions.R

@@ -361,6 +361,50 @@ NULL
 #' }
 NULL
 
+#' Avro processing functions for Column operations
+#'
+#' Avro processing functions defined for \code{Column}.
+#'
+#' @param x Column to compute on.
+#' @param jsonFormatSchema character Avro schema in JSON string format
+#' @param ... additional argument(s) passed as parser options.
+#' @name column_avro_functions
+#' @rdname column_avro_functions
+#' @family avro functions
+#' @note Avro is built-in but external data source module since Spark 2.4.
+#'   Please deploy the application as per
+#'   \href{https://spark.apache.org/docs/latest/sql-data-sources-avro.html#deploying}{
+#'     the deployment section
+#'   } of "Apache Avro Data Source Guide".
+#' @examples
+#' \dontrun{
+#' df <- createDataFrame(iris)
+#' schema <- paste(
+#'   c(
+#'     '{"type": "record", "namespace": "example.avro", "name": "Iris", "fields": [',
+#'     '{"type": ["double", "null"], "name": "Sepal_Length"},',
+#'     '{"type": ["double", "null"], "name": "Sepal_Width"},',
+#'     '{"type": ["double", "null"], "name": "Petal_Length"},',
+#'     '{"type": ["double", "null"], "name": "Petal_Width"},',
+#'     '{"type": ["string", "null"], "name": "Species"}]}'
+#'   ),
+#'   collapse="\\n"
+#' )
+#'
+#' df_serialized <- select(
+#'   df,
+#'   alias(to_avro(alias(struct(column("*")), "fields")), "payload")
+#' )
+#'
+#' df_deserialized <- select(
+#'   df_serialized,
+#'   from_avro(df_serialized$payload, schema)
+#' )
+#'
+#' head(df_deserialized)
+#' }
+NULL
+
 #' @details
 #' \code{lit}: A new Column is created to represent the literal value.
 #' If the parameter is a Column, it is returned unchanged.
@@ -4547,3 +4591,60 @@ setMethod("vector_to_array",
             )
             column(jc)
           })
+
+#' @details
+#' \code{from_avro} Converts a binary column of Avro format into its corresponding catalyst value.
+#' The specified schema must match the read data, otherwise the behavior is undefined:
+#' it may fail or return arbitrary result.
+#' To deserialize the data with a compatible and evolved schema, the expected Avro schema can be
+#' set via the option avroSchema.
+#'
+#' @rdname column_avro_functions
+#' @aliases from_avro from_avro,Column-method
+#' @note from_avro since 3.1.0
+setMethod("from_avro",
+          signature(x = "characterOrColumn"),
+          function(x, jsonFormatSchema, ...) {
+            x <- if (is.character(x)) {
+              column(x)
+            } else {
+              x
+            }
+
+            options <- varargsToStrEnv(...)
+            jc <- callJStatic(
+              "org.apache.spark.sql.avro.functions", "from_avro",
+              x@jc,
+              jsonFormatSchema,
+              options
+            )
+            column(jc)
+          })
+
+#' @details
+#' \code{to_avro} Converts a column into binary of Avro format.
+#'
+#' @rdname column_avro_functions
+#' @aliases to_avro to_avro,Column-method
+#' @note to_avro since 3.1.0
+setMethod("to_avro",
+          signature(x = "characterOrColumn"),
+          function(x, jsonFormatSchema = NULL) {
+            x <- if (is.character(x)) {
+              column(x)
+            } else {
+              x
+            }
+
+            jc <- if (is.null(jsonFormatSchema)) {
+              callJStatic("org.apache.spark.sql.avro.functions", "to_avro", x@jc)
+            } else {
+              callJStatic(
+                "org.apache.spark.sql.avro.functions",
+                "to_avro",
+                x@jc,
+                jsonFormatSchema
+              )
+            }
+            column(jc)
+          })