[SPARK-25598][STREAMING][BUILD][test-maven] Remove flume connector in Spark 3

dev/create-release/release-build.sh

@@ -114,7 +114,7 @@ PUBLISH_SCALA_2_10=0
 SCALA_2_10_PROFILES="-Pscala-2.10"
 SCALA_2_11_PROFILES=
 if [[ $SPARK_VERSION > "2.3" ]]; then
-  BASE_PROFILES="$BASE_PROFILES -Pkubernetes -Pflume"
+  BASE_PROFILES="$BASE_PROFILES -Pkubernetes"
   SCALA_2_11_PROFILES="-Pkafka-0-8"
 else
   PUBLISH_SCALA_2_10=1

dev/mima

@@ -24,7 +24,7 @@ set -e
 FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
 cd "$FWDIR"
 
-SPARK_PROFILES="-Pmesos -Pkafka-0-8 -Pkubernetes -Pyarn -Pflume -Pspark-ganglia-lgpl -Pkinesis-asl -Phive-thriftserver -Phive"
+SPARK_PROFILES="-Pmesos -Pkafka-0-8 -Pkubernetes -Pyarn -Pspark-ganglia-lgpl -Pkinesis-asl -Phive-thriftserver -Phive"
 TOOLS_CLASSPATH="$(build/sbt -DcopyDependencies=false "export tools/fullClasspath" | tail -n1)"
 OLD_DEPS_CLASSPATH="$(build/sbt -DcopyDependencies=false $SPARK_PROFILES "export oldDeps/fullClasspath" | tail -n1)"
 

dev/run-tests.py

@@ -333,7 +333,6 @@ def build_spark_sbt(hadoop_version):
     build_profiles = get_hadoop_profiles(hadoop_version) + modules.root.build_profile_flags
     sbt_goals = ["test:package",  # Build test jars as some tests depend on them
                  "streaming-kafka-0-8-assembly/assembly",
-                 "streaming-flume-assembly/assembly",
                  "streaming-kinesis-asl-assembly/assembly"]
     profiles_and_goals = build_profiles + sbt_goals
 

dev/sbt-checkstyle

@@ -26,7 +26,6 @@ ERRORS=$(echo -e "q\n" \
         -Pkafka-0-8 \
         -Pkubernetes \
         -Pyarn \
-        -Pflume \
         -Phive \
         -Phive-thriftserver \
         checkstyle test:checkstyle \

dev/scalastyle

@@ -26,7 +26,6 @@ ERRORS=$(echo -e "q\n" \
         -Pkafka-0-8 \
         -Pkubernetes \
         -Pyarn \
-        -Pflume \
         -Phive \
         -Phive-thriftserver \
         -Pspark-ganglia-lgpl \

dev/sparktestsupport/modules.py

@@ -283,56 +283,6 @@ def __hash__(self):
     ]
 )
 
-streaming_flume_sink = Module(
-    name="streaming-flume-sink",
-    dependencies=[streaming],
-    source_file_regexes=[
-        "external/flume-sink",
-    ],
-    build_profile_flags=[
-        "-Pflume",
-    ],
-    environ={
-        "ENABLE_FLUME_TESTS": "1"
-    },
-    sbt_test_goals=[
-        "streaming-flume-sink/test",
-    ]
-)
-
-
-streaming_flume = Module(
-    name="streaming-flume",
-    dependencies=[streaming],
-    source_file_regexes=[
-        "external/flume",
-    ],
-    build_profile_flags=[
-        "-Pflume",
-    ],
-    environ={
-        "ENABLE_FLUME_TESTS": "1"
-    },
-    sbt_test_goals=[
-        "streaming-flume/test",
-    ]
-)
-
-
-streaming_flume_assembly = Module(
-    name="streaming-flume-assembly",
-    dependencies=[streaming_flume, streaming_flume_sink],
-    source_file_regexes=[
-        "external/flume-assembly",
-    ],
-    build_profile_flags=[
-        "-Pflume",
-    ],
-    environ={
-        "ENABLE_FLUME_TESTS": "1"
-    }
-)
-
 
 mllib_local = Module(
     name="mllib-local",
@@ -425,14 +375,12 @@ def __hash__(self):
         pyspark_core,
         streaming,
         streaming_kafka,
-        streaming_flume_assembly,
         streaming_kinesis_asl
     ],
     source_file_regexes=[
         "python/pyspark/streaming"
     ],
     environ={
-        "ENABLE_FLUME_TESTS": "1",
         "ENABLE_KAFKA_0_8_TESTS": "1"
     },
     python_test_goals=[

dev/test-dependencies.sh

@@ -29,7 +29,7 @@ export LC_ALL=C
 # TODO: This would be much nicer to do in SBT, once SBT supports Maven-style resolution.
 
 # NOTE: These should match those in the release publishing script
-HADOOP2_MODULE_PROFILES="-Phive-thriftserver -Pmesos -Pkafka-0-8 -Pkubernetes -Pyarn -Pflume -Phive"
+HADOOP2_MODULE_PROFILES="-Phive-thriftserver -Pmesos -Pkafka-0-8 -Pkubernetes -Pyarn -Phive"
 MVN="build/mvn"
 HADOOP_PROFILES=(
     hadoop-2.7

docs/building-spark.md

@@ -99,13 +99,6 @@ Note: Kafka 0.8 support is deprecated as of Spark 2.3.0.
 
 Kafka 0.10 support is still automatically built.
 
-## Building with Flume support
-
-Apache Flume support must be explicitly enabled with the `flume` profile.
-Note: Flume support is deprecated as of Spark 2.3.0.
-
-    ./build/mvn -Pflume -DskipTests clean package
-
 ## Building submodules individually
 
 It's possible to build Spark submodules using the `mvn -pl` option.

docs/streaming-custom-receivers.md

@@ -4,7 +4,7 @@ title: Spark Streaming Custom Receivers
 ---
 
 Spark Streaming can receive streaming data from any arbitrary data source beyond
-the ones for which it has built-in support (that is, beyond Flume, Kafka, Kinesis, files, sockets, etc.).
+the ones for which it has built-in support (that is, beyond Kafka, Kinesis, files, sockets, etc.).
 This requires the developer to implement a *receiver* that is customized for receiving data from
 the concerned data source. This guide walks through the process of implementing a custom receiver
 and using it in a Spark Streaming application. Note that custom receivers can be implemented