[SPARK-13579][BUILD] Stop building the main Spark assembly.

This change modifies the "assembly/" module to just copy needed
dependencies to its build directory, and modifies the packaging
script to pick those up (and remove duplicate jars packages in the
examples module).

I also made some minor adjustments to dependencies to remove some
test jars from the final packaging, and remove jars that conflict with each
other when packaged separately (e.g. servlet api).

Also note that this change restores guava in applications' classpaths, even
though it's still shaded inside Spark. This is now needed for the Hadoop
libraries that are packaged with Spark, which now are not processed by
the shade plugin.

Author: Marcelo Vanzin <vanzin@cloudera.com>

Closes #11796 from vanzin/SPARK-13579.

8 files changed, 30 insertions, 32 deletions

diff --git a/dev/deps/spark-deps-hadoop-2.2 b/dev/deps/spark-deps-hadoop-2.2
index 3865a9fb16..2c24366cc3 100644
--- a/dev/deps/spark-deps-hadoop-2.2
+++ b/dev/deps/spark-deps-hadoop-2.2
@@ -12,7 +12,6 @@ asm-3.1.jar
 asm-commons-3.1.jar
 asm-tree-3.1.jar
 avro-1.7.7.jar
-avro-ipc-1.7.7-tests.jar
 avro-ipc-1.7.7.jar
 avro-mapred-1.7.7-hadoop2.jar
 bonecp-0.8.0.RELEASE.jar
@@ -61,6 +60,7 @@ grizzly-http-2.1.2.jar
 grizzly-http-server-2.1.2.jar
 grizzly-http-servlet-2.1.2.jar
 grizzly-rcm-2.1.2.jar
+guava-14.0.1.jar
 guice-3.0.jar
 guice-servlet-3.0.jar
 hadoop-annotations-2.2.0.jar
@@ -164,7 +164,6 @@ scala-parser-combinators_2.11-1.0.4.jar
 scala-reflect-2.11.8.jar
 scala-xml_2.11-1.0.2.jar
 scalap-2.11.8.jar
-servlet-api-2.5.jar
 slf4j-api-1.7.16.jar
 slf4j-log4j12-1.7.16.jar
 snappy-0.2.jar
@@ -177,7 +176,6 @@ stream-2.7.0.jar
 stringtemplate-3.2.1.jar
 super-csv-2.2.0.jar
 univocity-parsers-1.5.6.jar
-unused-1.0.0.jar
 xbean-asm5-shaded-4.4.jar
 xmlenc-0.52.jar
 xz-1.0.jar
diff --git a/dev/deps/spark-deps-hadoop-2.3 b/dev/deps/spark-deps-hadoop-2.3
index 4313799da7..e9cb0d8f3e 100644
--- a/dev/deps/spark-deps-hadoop-2.3
+++ b/dev/deps/spark-deps-hadoop-2.3
@@ -12,7 +12,6 @@ asm-3.1.jar
 asm-commons-3.1.jar
 asm-tree-3.1.jar
 avro-1.7.7.jar
-avro-ipc-1.7.7-tests.jar
 avro-ipc-1.7.7.jar
 avro-mapred-1.7.7-hadoop2.jar
 base64-2.3.8.jar
@@ -56,6 +55,7 @@ eigenbase-properties-1.1.5.jar
 geronimo-annotation_1.0_spec-1.1.1.jar
 geronimo-jaspic_1.0_spec-1.0.jar
 geronimo-jta_1.1_spec-1.1.1.jar
+guava-14.0.1.jar
 guice-3.0.jar
 guice-servlet-3.0.jar
 hadoop-annotations-2.3.0.jar
@@ -155,7 +155,6 @@ scala-parser-combinators_2.11-1.0.4.jar
 scala-reflect-2.11.8.jar
 scala-xml_2.11-1.0.2.jar
 scalap-2.11.8.jar
-servlet-api-2.5.jar
 slf4j-api-1.7.16.jar
 slf4j-log4j12-1.7.16.jar
 snappy-0.2.jar
@@ -168,7 +167,6 @@ stream-2.7.0.jar
 stringtemplate-3.2.1.jar
 super-csv-2.2.0.jar
 univocity-parsers-1.5.6.jar
-unused-1.0.0.jar
 xbean-asm5-shaded-4.4.jar
 xmlenc-0.52.jar
 xz-1.0.jar
diff --git a/dev/deps/spark-deps-hadoop-2.4 b/dev/deps/spark-deps-hadoop-2.4
index 910ea685f2..d8d1840da5 100644
--- a/dev/deps/spark-deps-hadoop-2.4
+++ b/dev/deps/spark-deps-hadoop-2.4
@@ -12,7 +12,6 @@ asm-3.1.jar
 asm-commons-3.1.jar
 asm-tree-3.1.jar
 avro-1.7.7.jar
-avro-ipc-1.7.7-tests.jar
 avro-ipc-1.7.7.jar
 avro-mapred-1.7.7-hadoop2.jar
 base64-2.3.8.jar
@@ -56,6 +55,7 @@ eigenbase-properties-1.1.5.jar
 geronimo-annotation_1.0_spec-1.1.1.jar
 geronimo-jaspic_1.0_spec-1.0.jar
 geronimo-jta_1.1_spec-1.1.1.jar
+guava-14.0.1.jar
 guice-3.0.jar
 guice-servlet-3.0.jar
 hadoop-annotations-2.4.0.jar
@@ -156,7 +156,6 @@ scala-parser-combinators_2.11-1.0.4.jar
 scala-reflect-2.11.8.jar
 scala-xml_2.11-1.0.2.jar
 scalap-2.11.8.jar
-servlet-api-2.5.jar
 slf4j-api-1.7.16.jar
 slf4j-log4j12-1.7.16.jar
 snappy-0.2.jar
@@ -169,7 +168,6 @@ stream-2.7.0.jar
 stringtemplate-3.2.1.jar
 super-csv-2.2.0.jar
 univocity-parsers-1.5.6.jar
-unused-1.0.0.jar
 xbean-asm5-shaded-4.4.jar
 xmlenc-0.52.jar
 xz-1.0.jar
diff --git a/dev/deps/spark-deps-hadoop-2.6 b/dev/deps/spark-deps-hadoop-2.6
index 0692f24e47..8beede1e38 100644
--- a/dev/deps/spark-deps-hadoop-2.6
+++ b/dev/deps/spark-deps-hadoop-2.6
@@ -16,7 +16,6 @@ asm-3.1.jar
 asm-commons-3.1.jar
 asm-tree-3.1.jar
 avro-1.7.7.jar
-avro-ipc-1.7.7-tests.jar
 avro-ipc-1.7.7.jar
 avro-mapred-1.7.7-hadoop2.jar
 base64-2.3.8.jar
@@ -61,6 +60,7 @@ geronimo-annotation_1.0_spec-1.1.1.jar
 geronimo-jaspic_1.0_spec-1.0.jar
 geronimo-jta_1.1_spec-1.1.1.jar
 gson-2.2.4.jar
+guava-14.0.1.jar
 guice-3.0.jar
 guice-servlet-3.0.jar
 hadoop-annotations-2.6.0.jar
@@ -162,7 +162,6 @@ scala-parser-combinators_2.11-1.0.4.jar
 scala-reflect-2.11.8.jar
 scala-xml_2.11-1.0.2.jar
 scalap-2.11.8.jar
-servlet-api-2.5.jar
 slf4j-api-1.7.16.jar
 slf4j-log4j12-1.7.16.jar
 snappy-0.2.jar
@@ -175,7 +174,6 @@ stream-2.7.0.jar
 stringtemplate-3.2.1.jar
 super-csv-2.2.0.jar
 univocity-parsers-1.5.6.jar
-unused-1.0.0.jar
 xbean-asm5-shaded-4.4.jar
 xercesImpl-2.9.1.jar
 xmlenc-0.52.jar
diff --git a/dev/deps/spark-deps-hadoop-2.7 b/dev/deps/spark-deps-hadoop-2.7
index e397558e05..a9d814f944 100644
--- a/dev/deps/spark-deps-hadoop-2.7
+++ b/dev/deps/spark-deps-hadoop-2.7
@@ -16,7 +16,6 @@ asm-3.1.jar
 asm-commons-3.1.jar
 asm-tree-3.1.jar
 avro-1.7.7.jar
-avro-ipc-1.7.7-tests.jar
 avro-ipc-1.7.7.jar
 avro-mapred-1.7.7-hadoop2.jar
 base64-2.3.8.jar
@@ -61,6 +60,7 @@ geronimo-annotation_1.0_spec-1.1.1.jar
 geronimo-jaspic_1.0_spec-1.0.jar
 geronimo-jta_1.1_spec-1.1.1.jar
 gson-2.2.4.jar
+guava-14.0.1.jar
 guice-3.0.jar
 guice-servlet-3.0.jar
 hadoop-annotations-2.7.0.jar
@@ -163,7 +163,6 @@ scala-parser-combinators_2.11-1.0.4.jar
 scala-reflect-2.11.8.jar
 scala-xml_2.11-1.0.2.jar
 scalap-2.11.8.jar
-servlet-api-2.5.jar
 slf4j-api-1.7.16.jar
 slf4j-log4j12-1.7.16.jar
 snappy-0.2.jar
@@ -176,7 +175,6 @@ stream-2.7.0.jar
 stringtemplate-3.2.1.jar
 super-csv-2.2.0.jar
 univocity-parsers-1.5.6.jar
-unused-1.0.0.jar
 xbean-asm5-shaded-4.4.jar
 xercesImpl-2.9.1.jar
 xmlenc-0.52.jar
diff --git a/dev/make-distribution.sh b/dev/make-distribution.sh
index dbdd42ff9e..4f7544f6ea 100755
--- a/dev/make-distribution.sh
+++ b/dev/make-distribution.sh
@@ -160,28 +160,35 @@ echo -e "\$ ${BUILD_COMMAND[@]}\n"
 
 # Make directories
 rm -rf "$DISTDIR"
-mkdir -p "$DISTDIR/lib"
+mkdir -p "$DISTDIR/jars"
 echo "Spark $VERSION$GITREVSTRING built for Hadoop $SPARK_HADOOP_VERSION" > "$DISTDIR/RELEASE"
 echo "Build flags: $@" >> "$DISTDIR/RELEASE"
 
 # Copy jars
-cp "$SPARK_HOME"/assembly/target/scala*/*assembly*hadoop*.jar "$DISTDIR/lib/"
-# This will fail if the -Pyarn profile is not provided
-# In this case, silence the error and ignore the return code of this command
-cp "$SPARK_HOME"/common/network-yarn/target/scala*/spark-*-yarn-shuffle.jar "$DISTDIR/lib/" &> /dev/null || :
+cp "$SPARK_HOME"/assembly/target/scala*/jars/* "$DISTDIR/jars/"
+
+# Only create the yarn directory if the yarn artifacts were build.
+if [ -f "$SPARK_HOME"/common/network-yarn/target/scala*/spark-*-yarn-shuffle.jar ]; then
+  mkdir "$DISTDIR"/yarn
+  cp "$SPARK_HOME"/common/network-yarn/target/scala*/spark-*-yarn-shuffle.jar "$DISTDIR/yarn"
+fi
 
 # Copy examples and dependencies
 mkdir -p "$DISTDIR/examples/jars"
 cp "$SPARK_HOME"/examples/target/scala*/jars/* "$DISTDIR/examples/jars"
 
+# Deduplicate jars that have already been packaged as part of the main Spark dependencies.
+for f in "$DISTDIR/examples/jars/"*; do
+  name=$(basename "$f")
+  if [ -f "$DISTDIR/jars/$name" ]; then
+    rm "$DISTDIR/examples/jars/$name"
+  fi
+done
+
 # Copy example sources (needed for python and SQL)
 mkdir -p "$DISTDIR/examples/src/main"
 cp -r "$SPARK_HOME"/examples/src/main "$DISTDIR/examples/src/"
 
-if [ "$SPARK_HIVE" == "1" ]; then
-  cp "$SPARK_HOME"/lib_managed/jars/datanucleus*.jar "$DISTDIR/lib/"
-fi
-
 # Copy license and ASF files
 cp "$SPARK_HOME/LICENSE" "$DISTDIR"
 cp -r "$SPARK_HOME/licenses" "$DISTDIR"
diff --git a/dev/mima b/dev/mima
index ea746e6f01..c355349045 100755
--- a/dev/mima
+++ b/dev/mima
@@ -25,8 +25,8 @@ FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
 cd "$FWDIR"
 
 SPARK_PROFILES="-Pyarn -Pspark-ganglia-lgpl -Pkinesis-asl -Phive-thriftserver -Phive"
-TOOLS_CLASSPATH="$(build/sbt "export tools/fullClasspath" | tail -n1)"
-OLD_DEPS_CLASSPATH="$(build/sbt $SPARK_PROFILES "export oldDeps/fullClasspath" | tail -n1)"
+TOOLS_CLASSPATH="$(build/sbt -DcopyDependencies=false "export tools/fullClasspath" | tail -n1)"
+OLD_DEPS_CLASSPATH="$(build/sbt -DcopyDependencies=false $SPARK_PROFILES "export oldDeps/fullClasspath" | tail -n1)"
 
 rm -f .generated-mima*
 
@@ -36,7 +36,7 @@ java \
   -cp "$TOOLS_CLASSPATH:$OLD_DEPS_CLASSPATH" \
   org.apache.spark.tools.GenerateMIMAIgnore
 
-echo -e "q\n" | build/sbt mimaReportBinaryIssues | grep -v -e "info.*Resolving"
+echo -e "q\n" | build/sbt -DcopyDependencies=false "$@" mimaReportBinaryIssues | grep -v -e "info.*Resolving"
 ret_val=$?
 
 if [ $ret_val != 0 ]; then
diff --git a/dev/run-tests.py b/dev/run-tests.py
index c2944747ee..cbe347274e 100755
--- a/dev/run-tests.py
+++ b/dev/run-tests.py
@@ -350,7 +350,7 @@ def build_spark_sbt(hadoop_version):
 def build_spark_assembly_sbt(hadoop_version):
     # Enable all of the profiles for the build:
     build_profiles = get_hadoop_profiles(hadoop_version) + modules.root.build_profile_flags
-    sbt_goals = ["assembly/assembly"]
+    sbt_goals = ["assembly/package"]
     profiles_and_goals = build_profiles + sbt_goals
     print("[info] Building Spark assembly (w/Hive 1.2.1) using SBT with these arguments: ",
           " ".join(profiles_and_goals))
@@ -371,9 +371,10 @@ def build_apache_spark(build_tool, hadoop_version):
         build_spark_sbt(hadoop_version)
 
 
-def detect_binary_inop_with_mima():
+def detect_binary_inop_with_mima(hadoop_version):
+    build_profiles = get_hadoop_profiles(hadoop_version) + modules.root.build_profile_flags
     set_title_and_block("Detecting binary incompatibilities with MiMa", "BLOCK_MIMA")
-    run_cmd([os.path.join(SPARK_HOME, "dev", "mima")])
+    run_cmd([os.path.join(SPARK_HOME, "dev", "mima")] + build_profiles)
 
 
 def run_scala_tests_maven(test_profiles):
@@ -571,8 +572,8 @@ def main():
     # backwards compatibility checks
     if build_tool == "sbt":
         # Note: compatibility tests only supported in sbt for now
-        detect_binary_inop_with_mima()
-        # Since we did not build assembly/assembly before running dev/mima, we need to
+        detect_binary_inop_with_mima(hadoop_version)
+        # Since we did not build assembly/package before running dev/mima, we need to
         # do it here because the tests still rely on it; see SPARK-13294 for details.
         build_spark_assembly_sbt(hadoop_version)