User defined datatypes

.gitattributes

@@ -0,0 +1,2 @@
+*.bat text eol=crlf
+*.cmd text eol=crlf

.rat-excludes

@@ -1,5 +1,6 @@
 target
 .gitignore
+.gitattributes
 .project
 .classpath
 .mima-excludes
@@ -48,6 +49,7 @@ sbt-launch-lib.bash
 plugins.sbt
 work
 .*\.q
+.*\.qv
 golden
 test.out/*
 .*iml

LICENSE

@@ -712,18 +712,6 @@ THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
 NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
 EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
-========================================================================
-For colt:
-========================================================================
-
-Copyright (c) 1999 CERN - European Organization for Nuclear Research.
-Permission to use, copy, modify, distribute and sell this software and its documentation for any purpose is hereby granted without fee, provided that the above copyright notice appear in all copies and that both that copyright notice and this permission notice appear in supporting documentation. CERN makes no representations about the suitability of this software for any purpose. It is provided "as is" without expressed or implied warranty.
-
-Packages hep.aida.*
-
-Written by Pavel Binko, Dino Ferrero Merlino, Wolfgang Hoschek, Tony Johnson, Andreas Pfeiffer, and others. Check the FreeHEP home page for more info. Permission to use and/or redistribute this work is granted under the terms of the LGPL License, with the exception that any usage related to military applications is expressly forbidden. The software and documentation made available under the terms of this license are provided with no warranty.
-
-
 ========================================================================
 For SnapTree:
 ========================================================================

README.md

@@ -25,7 +25,7 @@ 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"](http://spark.apache.org/docs/latest/building-spark.html).
+["Building Spark with Maven"](http://spark.apache.org/docs/latest/building-with-maven.html).
 
 ## Interactive Scala Shell
 
@@ -84,7 +84,7 @@ storage systems. Because the protocols have changed in different versions of
 Hadoop, you must build Spark against the same version that your cluster runs.
 
 Please refer to the build documentation at
-["Specifying the Hadoop Version"](http://spark.apache.org/docs/latest/building-spark.html#specifying-the-hadoop-version)
+["Specifying the Hadoop Version"](http://spark.apache.org/docs/latest/building-with-maven.html#specifying-the-hadoop-version)
 for detailed guidance on building for a particular distribution of Hadoop, including
 building for particular Hive and Hive Thriftserver distributions. See also
 ["Third Party Hadoop Distributions"](http://spark.apache.org/docs/latest/hadoop-third-party-distributions.html)

bin/compute-classpath.cmd

@@ -1,117 +1,117 @@
-@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
-
-rem This script computes Spark's classpath and prints it to stdout; it's used by both the "run"
-rem script and the ExecutorRunner in standalone cluster mode.
-
-rem If we're called from spark-class2.cmd, it already set enabledelayedexpansion and setting
-rem it here would stop us from affecting its copy of the CLASSPATH variable; otherwise we
-rem need to set it here because we use !datanucleus_jars! below.
-if "%DONT_PRINT_CLASSPATH%"=="1" goto skip_delayed_expansion
-setlocal enabledelayedexpansion
-:skip_delayed_expansion
-
-set SCALA_VERSION=2.10
-
-rem Figure out where the Spark framework is installed
-set FWDIR=%~dp0..\
-
-rem Load environment variables from conf\spark-env.cmd, if it exists
-if exist "%FWDIR%conf\spark-env.cmd" call "%FWDIR%conf\spark-env.cmd"
-
-rem Build up classpath
-set CLASSPATH=%SPARK_CLASSPATH%;%SPARK_SUBMIT_CLASSPATH%
-
-if not "x%SPARK_CONF_DIR%"=="x" (
-  set CLASSPATH=%CLASSPATH%;%SPARK_CONF_DIR%
-) else (
-  set CLASSPATH=%CLASSPATH%;%FWDIR%conf
-)
-
-if exist "%FWDIR%RELEASE" (
-  for %%d in ("%FWDIR%lib\spark-assembly*.jar") do (
-    set ASSEMBLY_JAR=%%d
-  )
-) else (
-  for %%d in ("%FWDIR%assembly\target\scala-%SCALA_VERSION%\spark-assembly*hadoop*.jar") do (
-    set ASSEMBLY_JAR=%%d
-  )
-)
-
-set CLASSPATH=%CLASSPATH%;%ASSEMBLY_JAR%
-
-rem When Hive support is needed, Datanucleus jars must be included on the classpath.
-rem Datanucleus jars do not work if only included in the uber jar as plugin.xml metadata is lost.
-rem Both sbt and maven will populate "lib_managed/jars/" with the datanucleus jars when Spark is
-rem built with Hive, so look for them there.
-if exist "%FWDIR%RELEASE" (
-  set datanucleus_dir=%FWDIR%lib
-) else (
-  set datanucleus_dir=%FWDIR%lib_managed\jars
-)
-set "datanucleus_jars="
-for %%d in ("%datanucleus_dir%\datanucleus-*.jar") do (
-  set datanucleus_jars=!datanucleus_jars!;%%d
-)
-set CLASSPATH=%CLASSPATH%;%datanucleus_jars%
-
-set SPARK_CLASSES=%FWDIR%core\target\scala-%SCALA_VERSION%\classes
-set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%repl\target\scala-%SCALA_VERSION%\classes
-set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%mllib\target\scala-%SCALA_VERSION%\classes
-set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%bagel\target\scala-%SCALA_VERSION%\classes
-set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%graphx\target\scala-%SCALA_VERSION%\classes
-set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%streaming\target\scala-%SCALA_VERSION%\classes
-set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%tools\target\scala-%SCALA_VERSION%\classes
-set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%sql\catalyst\target\scala-%SCALA_VERSION%\classes
-set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%sql\core\target\scala-%SCALA_VERSION%\classes
-set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%sql\hive\target\scala-%SCALA_VERSION%\classes
-
-set SPARK_TEST_CLASSES=%FWDIR%core\target\scala-%SCALA_VERSION%\test-classes
-set SPARK_TEST_CLASSES=%SPARK_TEST_CLASSES%;%FWDIR%repl\target\scala-%SCALA_VERSION%\test-classes
-set SPARK_TEST_CLASSES=%SPARK_TEST_CLASSES%;%FWDIR%mllib\target\scala-%SCALA_VERSION%\test-classes
-set SPARK_TEST_CLASSES=%SPARK_TEST_CLASSES%;%FWDIR%bagel\target\scala-%SCALA_VERSION%\test-classes
-set SPARK_TEST_CLASSES=%SPARK_TEST_CLASSES%;%FWDIR%graphx\target\scala-%SCALA_VERSION%\test-classes
-set SPARK_TEST_CLASSES=%SPARK_TEST_CLASSES%;%FWDIR%streaming\target\scala-%SCALA_VERSION%\test-classes
-set SPARK_TEST_CLASSES=%SPARK_TEST_CLASSES%;%FWDIR%sql\catalyst\target\scala-%SCALA_VERSION%\test-classes
-set SPARK_TEST_CLASSES=%SPARK_TEST_CLASSES%;%FWDIR%sql\core\target\scala-%SCALA_VERSION%\test-classes
-set SPARK_TEST_CLASSES=%SPARK_TEST_CLASSES%;%FWDIR%sql\hive\target\scala-%SCALA_VERSION%\test-classes
-
-if "x%SPARK_TESTING%"=="x1" (
-  rem Add test clases to path - note, add SPARK_CLASSES and SPARK_TEST_CLASSES before CLASSPATH
-  rem so that local compilation takes precedence over assembled jar
-  set CLASSPATH=%SPARK_CLASSES%;%SPARK_TEST_CLASSES%;%CLASSPATH%
-)
-
-rem Add hadoop conf dir - else FileSystem.*, etc fail
-rem Note, this assumes that there is either a HADOOP_CONF_DIR or YARN_CONF_DIR which hosts
-rem the configurtion files.
-if "x%HADOOP_CONF_DIR%"=="x" goto no_hadoop_conf_dir
-  set CLASSPATH=%CLASSPATH%;%HADOOP_CONF_DIR%
-:no_hadoop_conf_dir
-
-if "x%YARN_CONF_DIR%"=="x" goto no_yarn_conf_dir
-  set CLASSPATH=%CLASSPATH%;%YARN_CONF_DIR%
-:no_yarn_conf_dir
-
-rem A bit of a hack to allow calling this script within run2.cmd without seeing output
-if "%DONT_PRINT_CLASSPATH%"=="1" goto exit
-
-echo %CLASSPATH%
-
-:exit
+@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
+
+rem This script computes Spark's classpath and prints it to stdout; it's used by both the "run"
+rem script and the ExecutorRunner in standalone cluster mode.
+
+rem If we're called from spark-class2.cmd, it already set enabledelayedexpansion and setting
+rem it here would stop us from affecting its copy of the CLASSPATH variable; otherwise we
+rem need to set it here because we use !datanucleus_jars! below.
+if "%DONT_PRINT_CLASSPATH%"=="1" goto skip_delayed_expansion
+setlocal enabledelayedexpansion
+:skip_delayed_expansion
+
+set SCALA_VERSION=2.10
+
+rem Figure out where the Spark framework is installed
+set FWDIR=%~dp0..\
+
+rem Load environment variables from conf\spark-env.cmd, if it exists
+if exist "%FWDIR%conf\spark-env.cmd" call "%FWDIR%conf\spark-env.cmd"
+
+rem Build up classpath
+set CLASSPATH=%SPARK_CLASSPATH%;%SPARK_SUBMIT_CLASSPATH%
+
+if not "x%SPARK_CONF_DIR%"=="x" (
+  set CLASSPATH=%CLASSPATH%;%SPARK_CONF_DIR%
+) else (
+  set CLASSPATH=%CLASSPATH%;%FWDIR%conf
+)
+
+if exist "%FWDIR%RELEASE" (
+  for %%d in ("%FWDIR%lib\spark-assembly*.jar") do (
+    set ASSEMBLY_JAR=%%d
+  )
+) else (
+  for %%d in ("%FWDIR%assembly\target\scala-%SCALA_VERSION%\spark-assembly*hadoop*.jar") do (
+    set ASSEMBLY_JAR=%%d
+  )
+)
+
+set CLASSPATH=%CLASSPATH%;%ASSEMBLY_JAR%
+
+rem When Hive support is needed, Datanucleus jars must be included on the classpath.
+rem Datanucleus jars do not work if only included in the uber jar as plugin.xml metadata is lost.
+rem Both sbt and maven will populate "lib_managed/jars/" with the datanucleus jars when Spark is
+rem built with Hive, so look for them there.
+if exist "%FWDIR%RELEASE" (
+  set datanucleus_dir=%FWDIR%lib
+) else (
+  set datanucleus_dir=%FWDIR%lib_managed\jars
+)
+set "datanucleus_jars="
+for %%d in ("%datanucleus_dir%\datanucleus-*.jar") do (
+  set datanucleus_jars=!datanucleus_jars!;%%d
+)
+set CLASSPATH=%CLASSPATH%;%datanucleus_jars%
+
+set SPARK_CLASSES=%FWDIR%core\target\scala-%SCALA_VERSION%\classes
+set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%repl\target\scala-%SCALA_VERSION%\classes
+set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%mllib\target\scala-%SCALA_VERSION%\classes
+set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%bagel\target\scala-%SCALA_VERSION%\classes
+set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%graphx\target\scala-%SCALA_VERSION%\classes
+set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%streaming\target\scala-%SCALA_VERSION%\classes
+set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%tools\target\scala-%SCALA_VERSION%\classes
+set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%sql\catalyst\target\scala-%SCALA_VERSION%\classes
+set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%sql\core\target\scala-%SCALA_VERSION%\classes
+set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%sql\hive\target\scala-%SCALA_VERSION%\classes
+
+set SPARK_TEST_CLASSES=%FWDIR%core\target\scala-%SCALA_VERSION%\test-classes
+set SPARK_TEST_CLASSES=%SPARK_TEST_CLASSES%;%FWDIR%repl\target\scala-%SCALA_VERSION%\test-classes
+set SPARK_TEST_CLASSES=%SPARK_TEST_CLASSES%;%FWDIR%mllib\target\scala-%SCALA_VERSION%\test-classes
+set SPARK_TEST_CLASSES=%SPARK_TEST_CLASSES%;%FWDIR%bagel\target\scala-%SCALA_VERSION%\test-classes
+set SPARK_TEST_CLASSES=%SPARK_TEST_CLASSES%;%FWDIR%graphx\target\scala-%SCALA_VERSION%\test-classes
+set SPARK_TEST_CLASSES=%SPARK_TEST_CLASSES%;%FWDIR%streaming\target\scala-%SCALA_VERSION%\test-classes
+set SPARK_TEST_CLASSES=%SPARK_TEST_CLASSES%;%FWDIR%sql\catalyst\target\scala-%SCALA_VERSION%\test-classes
+set SPARK_TEST_CLASSES=%SPARK_TEST_CLASSES%;%FWDIR%sql\core\target\scala-%SCALA_VERSION%\test-classes
+set SPARK_TEST_CLASSES=%SPARK_TEST_CLASSES%;%FWDIR%sql\hive\target\scala-%SCALA_VERSION%\test-classes
+
+if "x%SPARK_TESTING%"=="x1" (
+  rem Add test clases to path - note, add SPARK_CLASSES and SPARK_TEST_CLASSES before CLASSPATH
+  rem so that local compilation takes precedence over assembled jar
+  set CLASSPATH=%SPARK_CLASSES%;%SPARK_TEST_CLASSES%;%CLASSPATH%
+)
+
+rem Add hadoop conf dir - else FileSystem.*, etc fail
+rem Note, this assumes that there is either a HADOOP_CONF_DIR or YARN_CONF_DIR which hosts
+rem the configurtion files.
+if "x%HADOOP_CONF_DIR%"=="x" goto no_hadoop_conf_dir
+  set CLASSPATH=%CLASSPATH%;%HADOOP_CONF_DIR%
+:no_hadoop_conf_dir
+
+if "x%YARN_CONF_DIR%"=="x" goto no_yarn_conf_dir
+  set CLASSPATH=%CLASSPATH%;%YARN_CONF_DIR%
+:no_yarn_conf_dir
+
+rem A bit of a hack to allow calling this script within run2.cmd without seeing output
+if "%DONT_PRINT_CLASSPATH%"=="1" goto exit
+
+echo %CLASSPATH%
+
+:exit

bin/pyspark

@@ -50,22 +50,47 @@ fi
 
 . "$FWDIR"/bin/load-spark-env.sh
 
-# Figure out which Python executable to use
+# In Spark <= 1.1, setting IPYTHON=1 would cause the driver to be launched using the `ipython`
+# executable, while the worker would still be launched using PYSPARK_PYTHON.
+#
+# In Spark 1.2, we removed the documentation of the IPYTHON and IPYTHON_OPTS variables and added
+# PYSPARK_DRIVER_PYTHON and PYSPARK_DRIVER_PYTHON_OPTS to allow IPython to be used for the driver.
+# Now, users can simply set PYSPARK_DRIVER_PYTHON=ipython to use IPython and set
+# PYSPARK_DRIVER_PYTHON_OPTS to pass options when starting the Python driver
+# (e.g. PYSPARK_DRIVER_PYTHON_OPTS='notebook').  This supports full customization of the IPython
+# and executor Python executables.
+#
+# For backwards-compatibility, we retain the old IPYTHON and IPYTHON_OPTS variables.
+
+# Determine the Python executable to use if PYSPARK_PYTHON or PYSPARK_DRIVER_PYTHON isn't set:
+if hash python2.7 2>/dev/null; then
+  # Attempt to use Python 2.7, if installed:
+  DEFAULT_PYTHON="python2.7"
+else
+  DEFAULT_PYTHON="python"
+fi
+
+# Determine the Python executable to use for the driver:
+if [[ -n "$IPYTHON_OPTS" || "$IPYTHON" == "1" ]]; then
+  # If IPython options are specified, assume user wants to run IPython
+  # (for backwards-compatibility)
+  PYSPARK_DRIVER_PYTHON_OPTS="$PYSPARK_DRIVER_PYTHON_OPTS $IPYTHON_OPTS"
+  PYSPARK_DRIVER_PYTHON="ipython"
+elif [[ -z "$PYSPARK_DRIVER_PYTHON" ]]; then
+  PYSPARK_DRIVER_PYTHON="${PYSPARK_PYTHON:-"$DEFAULT_PYTHON"}"
+fi
+
+# Determine the Python executable to use for the executors:
 if [[ -z "$PYSPARK_PYTHON" ]]; then
-  if [[ "$IPYTHON" = "1" || -n "$IPYTHON_OPTS" ]]; then
-    # for backward compatibility
-    PYSPARK_PYTHON="ipython"
+  if [[ $PYSPARK_DRIVER_PYTHON == *ipython* && $DEFAULT_PYTHON != "python2.7" ]]; then
+    echo "IPython requires Python 2.7+; please install python2.7 or set PYSPARK_PYTHON" 1>&2
+    exit 1
   else
-    PYSPARK_PYTHON="python"
+    PYSPARK_PYTHON="$DEFAULT_PYTHON"
   fi
 fi
 export PYSPARK_PYTHON
 
-if [[ -z "$PYSPARK_PYTHON_OPTS" && -n "$IPYTHON_OPTS" ]]; then
-  # for backward compatibility
-  PYSPARK_PYTHON_OPTS="$IPYTHON_OPTS"
-fi
-
 # Add the PySpark classes to the Python path:
 export PYTHONPATH="$SPARK_HOME/python/:$PYTHONPATH"
 export PYTHONPATH="$SPARK_HOME/python/lib/py4j-0.8.2.1-src.zip:$PYTHONPATH"
@@ -93,9 +118,9 @@ if [[ -n "$SPARK_TESTING" ]]; then
   unset YARN_CONF_DIR
   unset HADOOP_CONF_DIR
   if [[ -n "$PYSPARK_DOC_TEST" ]]; then
-    exec "$PYSPARK_PYTHON" -m doctest $1
+    exec "$PYSPARK_DRIVER_PYTHON" -m doctest $1
   else
-    exec "$PYSPARK_PYTHON" $1
+    exec "$PYSPARK_DRIVER_PYTHON" $1
   fi
   exit
 fi
@@ -111,5 +136,5 @@ if [[ "$1" =~ \.py$ ]]; then
 else
   # PySpark shell requires special handling downstream
   export PYSPARK_SHELL=1
-  exec "$PYSPARK_PYTHON" $PYSPARK_PYTHON_OPTS
+  exec "$PYSPARK_DRIVER_PYTHON" $PYSPARK_DRIVER_PYTHON_OPTS
 fi

bin/pyspark2.cmd

@@ -59,7 +59,12 @@ for /f %%i in ('echo %1^| findstr /R "\.py"') do (
 )
 
 if [%PYTHON_FILE%] == [] (
-  %PYSPARK_PYTHON%
+  set PYSPARK_SHELL=1
+  if [%IPYTHON%] == [1] (
+	ipython %IPYTHON_OPTS%
+  ) else (
+	%PYSPARK_PYTHON%
+  ) 
 ) else (
   echo.
   echo WARNING: Running python applications through ./bin/pyspark.cmd is deprecated as of Spark 1.0.