Merge remote-tracking branch 'upstream/master' into SPARK-3278

Author: zapletal-martin

.gitignore

@@ -5,6 +5,7 @@
 *.ipr
 *.iml
 *.iws
+*.pyc
 .idea/
 .idea_modules/
 sbt/*.jar
@@ -49,9 +50,12 @@ dependency-reduced-pom.xml
 checkpoint
 derby.log
 dist/
-spark-*-bin.tar.gz
+dev/create-release/*txt
+dev/create-release/*final
+spark-*-bin-*.tgz
 unit-tests.log
 /lib/
+ec2/lib/
 rat-results.txt
 scalastyle.txt
 scalastyle-output.xml

.rat-excludes

@@ -64,3 +64,4 @@ dist/*
 logs
 .*scalastyle-output.xml
 .*dependency-reduced-pom.xml
+known_translations

LICENSE

@@ -646,7 +646,8 @@ THE SOFTWARE.
 
 ========================================================================
 For Scala Interpreter classes (all .scala files in repl/src/main/scala
-except for Main.Scala, SparkHelper.scala and ExecutorClassLoader.scala):
+except for Main.Scala, SparkHelper.scala and ExecutorClassLoader.scala),
+and for SerializableMapWrapper in JavaUtils.scala:
 ========================================================================
 
 Copyright (c) 2002-2013 EPFL

README.md

@@ -26,7 +26,7 @@ To build Spark and its example programs, run:
 
 (You do not need to do this if you downloaded a pre-built package.)
 More detailed documentation is available from the project site, at
-["Building Spark with Maven"](http://spark.apache.org/docs/latest/building-with-maven.html).
+["Building Spark with Maven"](http://spark.apache.org/docs/latest/building-spark.html).
 
 ## Interactive Scala Shell
 

assembly/pom.xml

@@ -169,16 +169,6 @@
   </build>
 
   <profiles>
-    <profile>
-      <id>yarn-alpha</id>
-      <dependencies>
-        <dependency>
-          <groupId>org.apache.spark</groupId>
-          <artifactId>spark-yarn-alpha_${scala.binary.version}</artifactId>
-          <version>${project.version}</version>
-        </dependency>
-      </dependencies>
-    </profile>
     <profile>
       <id>yarn</id>
       <dependencies>

bin/beeline.cmd

@@ -0,0 +1,21 @@
+@echo off
+
+rem
+rem Licensed to the Apache Software Foundation (ASF) under one or more
+rem contributor license agreements.  See the NOTICE file distributed with
+rem this work for additional information regarding copyright ownership.
+rem The ASF licenses this file to You under the Apache License, Version 2.0
+rem (the "License"); you may not use this file except in compliance with
+rem the License.  You may obtain a copy of the License at
+rem
+rem    http://www.apache.org/licenses/LICENSE-2.0
+rem
+rem Unless required by applicable law or agreed to in writing, software
+rem distributed under the License is distributed on an "AS IS" BASIS,
+rem WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+rem See the License for the specific language governing permissions and
+rem limitations under the License.
+rem
+
+set SPARK_HOME=%~dp0..
+cmd /V /E /C %SPARK_HOME%\bin\spark-class.cmd org.apache.hive.beeline.BeeLine %*

bin/compute-classpath.sh

@@ -25,7 +25,11 @@ FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
 
 . "$FWDIR"/bin/load-spark-env.sh
 
-CLASSPATH="$SPARK_CLASSPATH:$SPARK_SUBMIT_CLASSPATH"
+if [ -n "$SPARK_CLASSPATH" ]; then
+  CLASSPATH="$SPARK_CLASSPATH:$SPARK_SUBMIT_CLASSPATH"
+else
+  CLASSPATH="$SPARK_SUBMIT_CLASSPATH"
+fi
 
 # Build up classpath
 if [ -n "$SPARK_CONF_DIR" ]; then
@@ -68,14 +72,14 @@ else
   assembly_folder="$ASSEMBLY_DIR"
 fi
 
-num_jars="$(ls "$assembly_folder" | grep "spark-assembly.*hadoop.*\.jar" | wc -l)"
+num_jars="$(ls "$assembly_folder" | grep "spark-assembly.*hadoop.*\.jar$" | wc -l)"
 if [ "$num_jars" -eq "0" ]; then
   echo "Failed to find Spark assembly in $assembly_folder"
   echo "You need to build Spark before running this program."
   exit 1
 fi
 if [ "$num_jars" -gt "1" ]; then
-  jars_list=$(ls "$assembly_folder" | grep "spark-assembly.*hadoop.*.jar")
+  jars_list=$(ls "$assembly_folder" | grep "spark-assembly.*hadoop.*.jar$")
   echo "Found multiple Spark assembly jars in $assembly_folder:"
   echo "$jars_list"
   echo "Please remove all but one jar."
@@ -108,7 +112,7 @@ else
   datanucleus_dir="$FWDIR"/lib_managed/jars
 fi
 
-datanucleus_jars="$(find "$datanucleus_dir" 2>/dev/null | grep "datanucleus-.*\\.jar")"
+datanucleus_jars="$(find "$datanucleus_dir" 2>/dev/null | grep "datanucleus-.*\\.jar$")"
 datanucleus_jars="$(echo "$datanucleus_jars" | tr "\n" : | sed s/:$//g)"
 
 if [ -n "$datanucleus_jars" ]; then

bin/spark-shell

@@ -45,6 +45,13 @@ source "$FWDIR"/bin/utils.sh
 SUBMIT_USAGE_FUNCTION=usage
 gatherSparkSubmitOpts "$@"
 
+# SPARK-4161: scala does not assume use of the java classpath,
+# so we need to add the "-Dscala.usejavacp=true" flag mnually. We
+# do this specifically for the Spark shell because the scala REPL
+# has its own class loader, and any additional classpath specified
+# through spark.driver.extraClassPath is not automatically propagated.
+SPARK_SUBMIT_OPTS="$SPARK_SUBMIT_OPTS -Dscala.usejavacp=true"
+
 function main() {
   if $cygwin; then
     # Workaround for issue involving JLine and Cygwin

bin/spark-shell2.cmd

@@ -19,4 +19,23 @@ rem
 
 set SPARK_HOME=%~dp0..
 
-cmd /V /E /C %SPARK_HOME%\bin\spark-submit.cmd --class org.apache.spark.repl.Main %* spark-shell
+echo "%*" | findstr " --help -h" >nul
+if %ERRORLEVEL% equ 0 (
+  call :usage
+  exit /b 0
+)
+
+call %SPARK_HOME%\bin\windows-utils.cmd %*
+if %ERRORLEVEL% equ 1 (
+  call :usage
+  exit /b 1
+)
+
+cmd /V /E /C %SPARK_HOME%\bin\spark-submit.cmd --class org.apache.spark.repl.Main %SUBMISSION_OPTS% spark-shell %APPLICATION_OPTS%
+
+exit /b 0
+
+:usage
+echo "Usage: .\bin\spark-shell.cmd [options]" >&2
+%SPARK_HOME%\bin\spark-submit --help 2>&1 | findstr /V "Usage" 1>&2
+exit /b 0

bin/spark-sql

@@ -23,6 +23,8 @@
 # Enter posix mode for bash
 set -o posix
 
+# NOTE: This exact class name is matched downstream by SparkSubmit.
+# Any changes need to be reflected there.
 CLASS="org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver"
 
 # Figure out where Spark is installed