[SPARK-7017] [BUILD] [PROJECT INFRA] Refactor dev/run-tests into Python

All, this is a first attempt at refactoring `dev/run-tests` into Python. Initially I merely converted all Bash calls over to Python, then moved to a much more modular approach (more functions, moved the calls around, etc.). What is here is the initial culmination and should provide a great base to various downstream issues (e.g. SPARK-7016, modularize / parallelize testing, etc.). Would love comments / suggestions for this initial first step!

/cc srowen pwendell nchammas

Author: Brennon York <brennon.york@capitalone.com>

Closes #5694 from brennonyork/SPARK-7017 and squashes the following commits:

154ed73 [Brennon York] updated finding java binary if JAVA_HOME not set
3922a85 [Brennon York] removed necessary passed in variable
f9fbe54 [Brennon York] reverted doc test change
8135518 [Brennon York] removed the test check for documentation changes until jenkins can get updated
05d435b [Brennon York] added check for jekyll install
22edb78 [Brennon York] add check if jekyll isn't installed on the path
2dff136 [Brennon York] fixed pep8 whitespace errors
767a668 [Brennon York] fixed path joining issues, ensured docs actually build on doc changes
c42cf9a [Brennon York] unpack set operations with splat (*)
fb85a41 [Brennon York] fixed minor set bug
0379833 [Brennon York] minor doc addition to print the changed modules
aa03d9e [Brennon York] added documentation builds as a top level test component, altered high level project changes to properly execute core tests only when necessary, changed variable names for simplicity
ec1ae78 [Brennon York] minor name changes, bug fixes
b7c72b9 [Brennon York] reverting streaming context
03fdd7b [Brennon York] fixed the tuple () wraps around example lambda
705d12e [Brennon York] changed example to comply with pep3113 supporting python3
60b3d51 [Brennon York] prepend rather than append onto PATH
7d2f5e2 [Brennon York] updated python tests to remove unused variable
2898717 [Brennon York] added a change to streaming test to check if it only runs streaming tests
eb684b6 [Brennon York] fixed sbt_test_goals reference error
db7ae6f [Brennon York] reverted SPARK_HOME from start of command
1ecca26 [Brennon York] fixed merge conflicts
2fcdfc0 [Brennon York] testing targte branch dump on jenkins
1f607b1 [Brennon York] finalizing revisions to modular tests
8afbe93 [Brennon York] made error codes a global
0629de8 [Brennon York] updated to refactor and remove various small bugs, removed pep8 complaints
d90ab2d [Brennon York] fixed merge conflicts, ensured that for regular builds both core and sql tests always run
b1248dc [Brennon York] exec python rather than running python and exiting with return code
f9deba1 [Brennon York] python to python2 and removed newline
6d0a052 [Brennon York] incorporated merge conflicts with SPARK-7249
f950010 [Brennon York] removed building hive-0.12.0 per SPARK-6908
703f095 [Brennon York] fixed merge conflicts
b1ca593 [Brennon York] reverted the sparkR test
afeb093 [Brennon York] updated to make sparkR test fail
1dada6b [Brennon York] reverted pyspark test failure
9a592ec [Brennon York] reverted mima exclude issue, added pyspark test failure
d825aa4 [Brennon York] revert build break, add mima break
f041d8a [Brennon York] added space from commented import to now test build breaking
983f2a2 [Brennon York] comment out import to fail build test
2386785 [Brennon York] Merge remote-tracking branch 'upstream/master' into SPARK-7017
76335fb [Brennon York] reverted rat license issue for sparkconf
e4a96cc [Brennon York] removed the import error and added license error, fixed the way run-tests and run-tests.py report their error codes
56d3cb9 [Brennon York] changed test back and commented out import to break compile
b37328c [Brennon York] fixed typo and added default return is no error block was found in the environment
7613558 [Brennon York] updated to return the proper env variable for return codes
a5bd445 [Brennon York] reverted license, changed test in shuffle to fail
803143a [Brennon York] removed license file for SparkContext
b0b2604 [Brennon York] comment out import to see if build fails and returns properly
83e80ef [Brennon York] attempt at better python output when called from bash
c095fa6 [Brennon York] removed another wait() call
26e18e8 [Brennon York] removed unnecessary wait()
07210a9 [Brennon York] minor doc string change for java version with namedtuple update
ec03bf3 [Brennon York] added namedtuple for java version to add readability
2cb413b [Brennon York] upcased global variables, changes various calling methods from check_output to check_call
639f1e9 [Brennon York] updated with pep8 rules, fixed minor bugs, added run-tests file in bash to call the run-tests.py script
3c53a1a [Brennon York] uncomment the scala tests :)
6126c4f [Brennon York] refactored run-tests into python

5 files changed, 546 insertions, 224 deletions

diff --git a/dev/run-tests b/dev/run-tests
index d178e2a460..a00d9f0c27 100755
--- a/dev/run-tests
+++ b/dev/run-tests
@@ -17,224 +17,7 @@
 # limitations under the License.
 #
 
-# Go to the Spark project root directory
 FWDIR="$(cd "`dirname $0`"/..; pwd)"
 cd "$FWDIR"
 
-# Clean up work directory and caches
-rm -rf ./work
-rm -rf ~/.ivy2/local/org.apache.spark
-rm -rf ~/.ivy2/cache/org.apache.spark
-
-source "$FWDIR/dev/run-tests-codes.sh"
-
-CURRENT_BLOCK=$BLOCK_GENERAL
-
-function handle_error () {
-  echo "[error] Got a return code of $? on line $1 of the run-tests script."
-  exit $CURRENT_BLOCK
-}
-
-
-# Build against the right version of Hadoop.
-{
-  if [ -n "$AMPLAB_JENKINS_BUILD_PROFILE" ]; then
-    if [ "$AMPLAB_JENKINS_BUILD_PROFILE" = "hadoop1.0" ]; then
-      export SBT_MAVEN_PROFILES_ARGS="-Phadoop-1 -Dhadoop.version=1.2.1"
-    elif [ "$AMPLAB_JENKINS_BUILD_PROFILE" = "hadoop2.0" ]; then
-      export SBT_MAVEN_PROFILES_ARGS="-Phadoop-1 -Dhadoop.version=2.0.0-mr1-cdh4.1.1"
-    elif [ "$AMPLAB_JENKINS_BUILD_PROFILE" = "hadoop2.2" ]; then
-      export SBT_MAVEN_PROFILES_ARGS="-Pyarn -Phadoop-2.2"
-    elif [ "$AMPLAB_JENKINS_BUILD_PROFILE" = "hadoop2.3" ]; then
-      export SBT_MAVEN_PROFILES_ARGS="-Pyarn -Phadoop-2.3 -Dhadoop.version=2.3.0"
-    fi
-  fi
-
-  if [ -z "$SBT_MAVEN_PROFILES_ARGS" ]; then
-    export SBT_MAVEN_PROFILES_ARGS="-Pyarn -Phadoop-2.3 -Dhadoop.version=2.3.0"
-  fi
-}
-
-export SBT_MAVEN_PROFILES_ARGS="$SBT_MAVEN_PROFILES_ARGS -Pkinesis-asl"
-
-# Determine Java path and version.
-{
-  if test -x "$JAVA_HOME/bin/java"; then
-      declare java_cmd="$JAVA_HOME/bin/java"
-  else
-      declare java_cmd=java
-  fi
-
-  # We can't use sed -r -e due to OS X / BSD compatibility; hence, all the parentheses.
-  JAVA_VERSION=$(
-    $java_cmd -version 2>&1 \
-    | grep -e "^java version" --max-count=1 \
-    | sed "s/java version \"\(.*\)\.\(.*\)\.\(.*\)\"/\1\2/"
-  )
-
-  if [ "$JAVA_VERSION" -lt 18 ]; then
-    echo "[warn] Java 8 tests will not run because JDK version is < 1.8."
-  fi
-}
-
-# Only run Hive tests if there are SQL changes.
-# Partial solution for SPARK-1455.
-if [ -n "$AMPLAB_JENKINS" ]; then
-  target_branch="$ghprbTargetBranch"
-  git fetch origin "$target_branch":"$target_branch"
-
-  # AMP_JENKINS_PRB indicates if the current build is a pull request build.
-  if [ -n "$AMP_JENKINS_PRB" ]; then
-    # It is a pull request build.
-    sql_diffs=$(
-      git diff --name-only "$target_branch" \
-      | grep -e "^sql/" -e "^bin/spark-sql" -e "^sbin/start-thriftserver.sh"
-    )
-
-    non_sql_diffs=$(
-      git diff --name-only "$target_branch" \
-      | grep -v -e "^sql/" -e "^bin/spark-sql" -e "^sbin/start-thriftserver.sh"
-    )
-
-    if [ -n "$sql_diffs" ]; then
-      echo "[info] Detected changes in SQL. Will run Hive test suite."
-      _RUN_SQL_TESTS=true
-
-      if [ -z "$non_sql_diffs" ]; then
-        echo "[info] Detected no changes except in SQL. Will only run SQL tests."
-        _SQL_TESTS_ONLY=true
-      fi
-    fi
-  else
-    # It is a regular build. We should run SQL tests.
-    _RUN_SQL_TESTS=true
-  fi
-fi
-
-set -o pipefail
-trap 'handle_error $LINENO' ERR
-
-echo ""
-echo "========================================================================="
-echo "Running Apache RAT checks"
-echo "========================================================================="
-
-CURRENT_BLOCK=$BLOCK_RAT
-
-./dev/check-license
-
-echo ""
-echo "========================================================================="
-echo "Running Scala style checks"
-echo "========================================================================="
-
-CURRENT_BLOCK=$BLOCK_SCALA_STYLE
-
-./dev/lint-scala
-
-echo ""
-echo "========================================================================="
-echo "Running Python style checks"
-echo "========================================================================="
-
-CURRENT_BLOCK=$BLOCK_PYTHON_STYLE
-
-./dev/lint-python
-
-echo ""
-echo "========================================================================="
-echo "Building Spark"
-echo "========================================================================="
-
-CURRENT_BLOCK=$BLOCK_BUILD
-
-{
-  HIVE_BUILD_ARGS="$SBT_MAVEN_PROFILES_ARGS -Phive -Phive-thriftserver"
-  echo "[info] Compile with Hive 0.13.1"
-  [ -d "lib_managed" ] && rm -rf lib_managed
-  echo "[info] Building Spark with these arguments: $HIVE_BUILD_ARGS"
-
-  if [ "${AMPLAB_JENKINS_BUILD_TOOL}" == "maven" ]; then
-    build/mvn $HIVE_BUILD_ARGS clean package -DskipTests
-  else
-    echo -e "q\n" \
-      | build/sbt $HIVE_BUILD_ARGS package assembly/assembly streaming-kafka-assembly/assembly \
-      | grep -v -e "info.*Resolving" -e "warn.*Merging" -e "info.*Including"
-  fi
-}
-
-echo ""
-echo "========================================================================="
-echo "Detecting binary incompatibilities with MiMa"
-echo "========================================================================="
-
-CURRENT_BLOCK=$BLOCK_MIMA
-
-./dev/mima
-
-echo ""
-echo "========================================================================="
-echo "Running Spark unit tests"
-echo "========================================================================="
-
-CURRENT_BLOCK=$BLOCK_SPARK_UNIT_TESTS
-
-{
-  # If the Spark SQL tests are enabled, run the tests with the Hive profiles enabled.
-  # This must be a single argument, as it is.
-  if [ -n "$_RUN_SQL_TESTS" ]; then
-    SBT_MAVEN_PROFILES_ARGS="$SBT_MAVEN_PROFILES_ARGS -Phive -Phive-thriftserver"
-  fi
-
-  if [ -n "$_SQL_TESTS_ONLY" ]; then
-    # This must be an array of individual arguments. Otherwise, having one long string
-    # will be interpreted as a single test, which doesn't work.
-    SBT_MAVEN_TEST_ARGS=("catalyst/test" "sql/test" "hive/test" "hive-thriftserver/test" "mllib/test")
-  else
-    SBT_MAVEN_TEST_ARGS=("test")
-  fi
-
-  echo "[info] Running Spark tests with these arguments: $SBT_MAVEN_PROFILES_ARGS ${SBT_MAVEN_TEST_ARGS[@]}"
-
-  if [ "${AMPLAB_JENKINS_BUILD_TOOL}" == "maven" ]; then
-    build/mvn test $SBT_MAVEN_PROFILES_ARGS --fail-at-end
-  else
-    # NOTE: echo "q" is needed because sbt on encountering a build file with failure
-    # (either resolution or compilation) prompts the user for input either q, r, etc
-    # to quit or retry. This echo is there to make it not block.
-    # NOTE: Do not quote $SBT_MAVEN_PROFILES_ARGS or else it will be interpreted as a
-    # single argument!
-    # "${SBT_MAVEN_TEST_ARGS[@]}" is cool because it's an array.
-    # QUESTION: Why doesn't 'yes "q"' work?
-    # QUESTION: Why doesn't 'grep -v -e "^\[info\] Resolving"' work?
-    echo -e "q\n" \
-      | build/sbt $SBT_MAVEN_PROFILES_ARGS "${SBT_MAVEN_TEST_ARGS[@]}" \
-      | grep -v -e "info.*Resolving" -e "warn.*Merging" -e "info.*Including"
-  fi
-}
-
-echo ""
-echo "========================================================================="
-echo "Running PySpark tests"
-echo "========================================================================="
-
-CURRENT_BLOCK=$BLOCK_PYSPARK_UNIT_TESTS
-
-# add path for python 3 in jenkins
-export PATH="${PATH}:/home/anaconda/envs/py3k/bin"
-./python/run-tests
-
-echo ""
-echo "========================================================================="
-echo "Running SparkR tests"
-echo "========================================================================="
-
-CURRENT_BLOCK=$BLOCK_SPARKR_UNIT_TESTS
-
-if [ $(command -v R) ]; then
-  ./R/install-dev.sh
-  ./R/run-tests.sh
-else
-  echo "Ignoring SparkR tests as R was not found in PATH"
-fi
-
+exec python -u ./dev/run-tests.py
diff --git a/dev/run-tests-codes.sh b/dev/run-tests-codes.sh
index 154e01255b..f4b238e1b7 100644
--- a/dev/run-tests-codes.sh
+++ b/dev/run-tests-codes.sh
@@ -21,8 +21,9 @@ readonly BLOCK_GENERAL=10
 readonly BLOCK_RAT=11
 readonly BLOCK_SCALA_STYLE=12
 readonly BLOCK_PYTHON_STYLE=13
-readonly BLOCK_BUILD=14
-readonly BLOCK_MIMA=15
-readonly BLOCK_SPARK_UNIT_TESTS=16
-readonly BLOCK_PYSPARK_UNIT_TESTS=17
-readonly BLOCK_SPARKR_UNIT_TESTS=18
+readonly BLOCK_DOCUMENTATION=14
+readonly BLOCK_BUILD=15
+readonly BLOCK_MIMA=16
+readonly BLOCK_SPARK_UNIT_TESTS=17
+readonly BLOCK_PYSPARK_UNIT_TESTS=18
+readonly BLOCK_SPARKR_UNIT_TESTS=19
diff --git a/dev/run-tests-jenkins b/dev/run-tests-jenkins
index 641b0ff3c4..c4d39d95d5 100755
--- a/dev/run-tests-jenkins
+++ b/dev/run-tests-jenkins
@@ -210,6 +210,8 @@ done
       failing_test="Scala style tests"
     elif [ "$test_result" -eq "$BLOCK_PYTHON_STYLE" ]; then
       failing_test="Python style tests"
+    elif [ "$test_result" -eq "$BLOCK_DOCUMENTATION" ]; then
+      failing_test="to generate documentation"
     elif [ "$test_result" -eq "$BLOCK_BUILD" ]; then
       failing_test="to build"
     elif [ "$test_result" -eq "$BLOCK_MIMA" ]; then
diff --git a/dev/run-tests.py b/dev/run-tests.py
new file mode 100755
index 0000000000..04a7b45741
--- /dev/null
+++ b/dev/run-tests.py
@@ -0,0 +1,536 @@
+#!/usr/bin/env python2
+
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import os
+import re
+import sys
+import shutil
+import subprocess
+from collections import namedtuple
+
+SPARK_HOME = os.path.join(os.path.dirname(os.path.realpath(__file__)), "..")
+USER_HOME = os.environ.get("HOME")
+
+
+def get_error_codes(err_code_file):
+    """Function to retrieve all block numbers from the `run-tests-codes.sh`
+    file to maintain backwards compatibility with the `run-tests-jenkins`
+    script"""
+
+    with open(err_code_file, 'r') as f:
+        err_codes = [e.split()[1].strip().split('=')
+                     for e in f if e.startswith("readonly")]
+        return dict(err_codes)
+
+
+ERROR_CODES = get_error_codes(os.path.join(SPARK_HOME, "dev/run-tests-codes.sh"))
+
+
+def exit_from_command_with_retcode(cmd, retcode):
+    print "[error] running", cmd, "; received return code", retcode
+    sys.exit(int(os.environ.get("CURRENT_BLOCK", 255)))
+
+
+def rm_r(path):
+    """Given an arbitrary path properly remove it with the correct python
+    construct if it exists
+    - from: http://stackoverflow.com/a/9559881"""
+
+    if os.path.isdir(path):
+        shutil.rmtree(path)
+    elif os.path.exists(path):
+        os.remove(path)
+
+
+def run_cmd(cmd):
+    """Given a command as a list of arguments will attempt to execute the
+    command from the determined SPARK_HOME directory and, on failure, print
+    an error message"""
+
+    if not isinstance(cmd, list):
+        cmd = cmd.split()
+    try:
+        subprocess.check_call(cmd)
+    except subprocess.CalledProcessError as e:
+        exit_from_command_with_retcode(e.cmd, e.returncode)
+
+
+def is_exe(path):
+    """Check if a given path is an executable file
+    - from: http://stackoverflow.com/a/377028"""
+
+    return os.path.isfile(path) and os.access(path, os.X_OK)
+
+
+def which(program):
+    """Find and return the given program by its absolute path or 'None'
+    - from: http://stackoverflow.com/a/377028"""
+
+    fpath, fname = os.path.split(program)
+
+    if fpath:
+        if is_exe(program):
+            return program
+    else:
+        for path in os.environ.get("PATH").split(os.pathsep):
+            path = path.strip('"')
+            exe_file = os.path.join(path, program)
+            if is_exe(exe_file):
+                return exe_file
+    return None
+
+
+def determine_java_executable():
+    """Will return the path of the java executable that will be used by Spark's
+    tests or `None`"""
+
+    # Any changes in the way that Spark's build detects java must be reflected
+    # here. Currently the build looks for $JAVA_HOME/bin/java then falls back to
+    # the `java` executable on the path
+
+    java_home = os.environ.get("JAVA_HOME")
+
+    # check if there is an executable at $JAVA_HOME/bin/java
+    java_exe = which(os.path.join(java_home, "bin", "java")) if java_home else None
+    # if the java_exe wasn't set, check for a `java` version on the $PATH
+    return java_exe if java_exe else which("java")
+
+
+JavaVersion = namedtuple('JavaVersion', ['major', 'minor', 'patch', 'update'])
+
+
+def determine_java_version(java_exe):
+    """Given a valid java executable will return its version in named tuple format
+    with accessors '.major', '.minor', '.patch', '.update'"""
+
+    raw_output = subprocess.check_output([java_exe, "-version"],
+                                         stderr=subprocess.STDOUT)
+    raw_version_str = raw_output.split('\n')[0]  # eg 'java version "1.8.0_25"'
+    version_str = raw_version_str.split()[-1].strip('"')  # eg '1.8.0_25'
+    version, update = version_str.split('_')  # eg ['1.8.0', '25']
+
+    # map over the values and convert them to integers
+    version_info = [int(x) for x in version.split('.') + [update]]
+
+    return JavaVersion(major=version_info[0],
+                       minor=version_info[1],
+                       patch=version_info[2],
+                       update=version_info[3])
+
+
+def set_title_and_block(title, err_block):
+    os.environ["CURRENT_BLOCK"] = ERROR_CODES[err_block]
+    line_str = '=' * 72
+
+    print
+    print line_str
+    print title
+    print line_str
+
+
+def run_apache_rat_checks():
+    set_title_and_block("Running Apache RAT checks", "BLOCK_RAT")
+    run_cmd([os.path.join(SPARK_HOME, "dev", "check-license")])
+
+
+def run_scala_style_checks():
+    set_title_and_block("Running Scala style checks", "BLOCK_SCALA_STYLE")
+    run_cmd([os.path.join(SPARK_HOME, "dev", "lint-scala")])
+
+
+def run_python_style_checks():
+    set_title_and_block("Running Python style checks", "BLOCK_PYTHON_STYLE")
+    run_cmd([os.path.join(SPARK_HOME, "dev", "lint-python")])
+
+
+def build_spark_documentation():
+    set_title_and_block("Building Spark Documentation", "BLOCK_DOCUMENTATION")
+    os.environ["PRODUCTION"] = "1 jekyll build"
+
+    os.chdir(os.path.join(SPARK_HOME, "docs"))
+
+    jekyll_bin = which("jekyll")
+
+    if not jekyll_bin:
+        print "[error] Cannot find a version of `jekyll` on the system; please",
+        print "install one and retry to build documentation."
+        sys.exit(int(os.environ.get("CURRENT_BLOCK", 255)))
+    else:
+        run_cmd([jekyll_bin, "build"])
+
+    os.chdir(SPARK_HOME)
+
+
+def exec_maven(mvn_args=[]):
+    """Will call Maven in the current directory with the list of mvn_args passed
+    in and returns the subprocess for any further processing"""
+
+    run_cmd([os.path.join(SPARK_HOME, "build", "mvn")] + mvn_args)
+
+
+def exec_sbt(sbt_args=[]):
+    """Will call SBT in the current directory with the list of mvn_args passed
+    in and returns the subprocess for any further processing"""
+
+    sbt_cmd = [os.path.join(SPARK_HOME, "build", "sbt")] + sbt_args
+
+    sbt_output_filter = re.compile("^.*[info].*Resolving" + "|" +
+                                   "^.*[warn].*Merging" + "|" +
+                                   "^.*[info].*Including")
+
+    # NOTE: echo "q" is needed because sbt on encountering a build file
+    # with failure (either resolution or compilation) prompts the user for
+    # input either q, r, etc to quit or retry. This echo is there to make it
+    # not block.
+    echo_proc = subprocess.Popen(["echo", "\"q\n\""], stdout=subprocess.PIPE)
+    sbt_proc = subprocess.Popen(sbt_cmd,
+                                stdin=echo_proc.stdout,
+                                stdout=subprocess.PIPE)
+    echo_proc.wait()
+    for line in iter(sbt_proc.stdout.readline, ''):
+        if not sbt_output_filter.match(line):
+            print line,
+    retcode = sbt_proc.wait()
+
+    if retcode > 0:
+        exit_from_command_with_retcode(sbt_cmd, retcode)
+
+
+def get_hadoop_profiles(hadoop_version):
+    """Return a list of profiles indicating which Hadoop version to use from
+    a Hadoop version tag."""
+
+    sbt_maven_hadoop_profiles = {
+        "hadoop1.0": ["-Phadoop-1", "-Dhadoop.version=1.0.4"],
+        "hadoop2.0": ["-Phadoop-1", "-Dhadoop.version=2.0.0-mr1-cdh4.1.1"],
+        "hadoop2.2": ["-Pyarn", "-Phadoop-2.2"],
+        "hadoop2.3": ["-Pyarn", "-Phadoop-2.3", "-Dhadoop.version=2.3.0"],
+    }
+
+    if hadoop_version in sbt_maven_hadoop_profiles:
+        return sbt_maven_hadoop_profiles[hadoop_version]
+    else:
+        print "[error] Could not find", hadoop_version, "in the list. Valid options",
+        print "are", sbt_maven_hadoop_profiles.keys()
+        sys.exit(int(os.environ.get("CURRENT_BLOCK", 255)))
+
+
+def get_build_profiles(hadoop_version="hadoop2.3",
+                       enable_base_profiles=True,
+                       enable_hive_profiles=False,
+                       enable_doc_profiles=False):
+    """Returns a list of hadoop profiles to be used as looked up from the passed in hadoop profile
+    key with the option of adding on the base and hive profiles."""
+
+    base_profiles = ["-Pkinesis-asl"]
+    hive_profiles = ["-Phive", "-Phive-thriftserver"]
+    doc_profiles = []
+    hadoop_profiles = get_hadoop_profiles(hadoop_version)
+
+    build_profiles = hadoop_profiles
+
+    if enable_base_profiles:
+        build_profiles += base_profiles
+
+    if enable_hive_profiles:
+        build_profiles += hive_profiles
+
+    if enable_doc_profiles:
+        build_profiles += doc_profiles
+
+    return build_profiles
+
+
+def build_spark_maven(hadoop_version):
+    # we always build with Hive support even if we skip Hive tests in most builds
+    build_profiles = get_build_profiles(hadoop_version, enable_hive_profiles=True)
+    mvn_goals = ["clean", "package", "-DskipTests"]
+    profiles_and_goals = build_profiles + mvn_goals
+
+    print "[info] Building Spark (w/Hive 0.13.1) using Maven with these arguments:",
+    print " ".join(profiles_and_goals)
+
+    exec_maven(profiles_and_goals)
+
+
+def build_spark_sbt(hadoop_version):
+    build_profiles = get_build_profiles(hadoop_version, enable_hive_profiles=True)
+    sbt_goals = ["package",
+                 "assembly/assembly",
+                 "streaming-kafka-assembly/assembly"]
+    profiles_and_goals = build_profiles + sbt_goals
+
+    print "[info] Building Spark (w/Hive 0.13.1) using SBT with these arguments:",
+    print " ".join(profiles_and_goals)
+
+    exec_sbt(profiles_and_goals)
+
+
+def build_apache_spark(build_tool, hadoop_version):
+    """Will build Spark against Hive v0.13.1 given the passed in build tool (either `sbt` or
+    `maven`). Defaults to using `sbt`."""
+
+    set_title_and_block("Building Spark", "BLOCK_BUILD")
+
+    rm_r("lib_managed")
+
+    if build_tool == "maven":
+        build_spark_maven(hadoop_version)
+    else:
+        build_spark_sbt(hadoop_version)
+
+
+def detect_binary_inop_with_mima():
+    set_title_and_block("Detecting binary incompatibilities with MiMa", "BLOCK_MIMA")
+    run_cmd([os.path.join(SPARK_HOME, "dev", "mima")])
+
+
+def identify_changed_modules(test_env):
+    """Given the passed in environment will determine the changed modules and
+    return them as a set. If the environment is local, will simply run all tests.
+    If run under the `amplab_jenkins` environment will determine the changed files
+    as compared to the `ghprbTargetBranch` and execute the necessary set of tests
+    to provide coverage for the changed code."""
+    changed_modules = set()
+
+    if test_env == "amplab_jenkins":
+        target_branch = os.environ["ghprbTargetBranch"]
+
+        run_cmd(['git', 'fetch', 'origin', str(target_branch+':'+target_branch)])
+
+        raw_output = subprocess.check_output(['git', 'diff', '--name-only', target_branch])
+        # remove any empty strings
+        changed_files = [f for f in raw_output.split('\n') if f]
+
+        sql_files = [f for f in changed_files
+                     if any(f.startswith(p) for p in
+                            ["sql/",
+                             "bin/spark-sql",
+                             "sbin/start-thriftserver.sh",
+                             "examples/src/main/java/org/apache/spark/examples/sql/",
+                             "examples/src/main/scala/org/apache/spark/examples/sql/"])]
+        mllib_files = [f for f in changed_files
+                       if any(f.startswith(p) for p in
+                              ["examples/src/main/java/org/apache/spark/examples/mllib/",
+                               "examples/src/main/scala/org/apache/spark/examples/mllib",
+                               "data/mllib/",
+                               "mllib/"])]
+        streaming_files = [f for f in changed_files
+                           if any(f.startswith(p) for p in
+                                  ["examples/scala-2.10/",
+                                   "examples/src/main/java/org/apache/spark/examples/streaming/",
+                                   "examples/src/main/scala/org/apache/spark/examples/streaming/",
+                                   "external/",
+                                   "extras/java8-tests/",
+                                   "extras/kinesis-asl/",
+                                   "streaming/"])]
+        graphx_files = [f for f in changed_files
+                        if any(f.startswith(p) for p in
+                               ["examples/src/main/scala/org/apache/spark/examples/graphx/",
+                                "graphx/"])]
+        doc_files = [f for f in changed_files if f.startswith("docs/")]
+
+        # union together all changed top level project files
+        top_level_project_files = set().union(*[set(f) for f in [sql_files,
+                                                                 mllib_files,
+                                                                 streaming_files,
+                                                                 graphx_files,
+                                                                 doc_files]])
+        changed_core_files = set(changed_files).difference(top_level_project_files)
+
+        if changed_core_files:
+            changed_modules.add("CORE")
+        if sql_files:
+            print "[info] Detected changes in SQL. Will run Hive test suite."
+            changed_modules.add("SQL")
+        if mllib_files:
+            print "[info] Detected changes in MLlib. Will run MLlib test suite."
+            changed_modules.add("MLLIB")
+        if streaming_files:
+            print "[info] Detected changes in Streaming. Will run Streaming test suite."
+            changed_modules.add("STREAMING")
+        if graphx_files:
+            print "[info] Detected changes in GraphX. Will run GraphX test suite."
+            changed_modules.add("GRAPHX")
+        if doc_files:
+            print "[info] Detected changes in documentation. Will build spark with documentation."
+            changed_modules.add("DOCS")
+
+        return changed_modules
+    else:
+        # we aren't in the Amplab environment so simply run all tests
+        changed_modules.add("ALL")
+        return changed_modules
+
+
+def run_scala_tests_maven(test_profiles):
+    mvn_test_goals = ["test", "--fail-at-end"]
+    profiles_and_goals = test_profiles + mvn_test_goals
+
+    print "[info] Running Spark tests using Maven with these arguments:",
+    print " ".join(profiles_and_goals)
+
+    exec_maven(profiles_and_goals)
+
+
+def run_scala_tests_sbt(test_modules, test_profiles):
+    # declare the variable for reference
+    sbt_test_goals = None
+
+    if "ALL" in test_modules:
+        sbt_test_goals = ["test"]
+    else:
+        # if we only have changes in SQL, MLlib, Streaming, or GraphX then build
+        # a custom test list
+        if "SQL" in test_modules and "CORE" not in test_modules:
+            sbt_test_goals = ["catalyst/test",
+                              "sql/test",
+                              "hive/test",
+                              "hive-thriftserver/test",
+                              "mllib/test",
+                              "examples/test"]
+        if "MLLIB" in test_modules and "CORE" not in test_modules:
+            sbt_test_goals += ["mllib/test", "examples/test"]
+        if "STREAMING" in test_modules and "CORE" not in test_modules:
+            sbt_test_goals += ["streaming/test",
+                               "streaming-flume/test",
+                               "streaming-flume-sink/test",
+                               "streaming-kafka/test",
+                               "streaming-mqtt/test",
+                               "streaming-twitter/test",
+                               "streaming-zeromq/test",
+                               "examples/test"]
+        if "GRAPHX" in test_modules and "CORE" not in test_modules:
+            sbt_test_goals += ["graphx/test", "examples/test"]
+        if not sbt_test_goals:
+            sbt_test_goals = ["test"]
+
+    profiles_and_goals = test_profiles + sbt_test_goals
+
+    print "[info] Running Spark tests using SBT with these arguments:",
+    print " ".join(profiles_and_goals)
+
+    exec_sbt(profiles_and_goals)
+
+
+def run_scala_tests(build_tool, hadoop_version, test_modules):
+    """Function to properly execute all tests passed in as a set from the
+    `determine_test_suites` function"""
+    set_title_and_block("Running Spark unit tests", "BLOCK_SPARK_UNIT_TESTS")
+
+    test_modules = set(test_modules)
+
+    hive_profiles = ("SQL" in test_modules)
+    test_profiles = get_build_profiles(hadoop_version, enable_hive_profiles=hive_profiles)
+
+    if build_tool == "maven":
+        run_scala_tests_maven(test_profiles)
+    else:
+        run_scala_tests_sbt(test_modules, test_profiles)
+
+
+def run_python_tests():
+    set_title_and_block("Running PySpark tests", "BLOCK_PYSPARK_UNIT_TESTS")
+
+    run_cmd([os.path.join(SPARK_HOME, "python", "run-tests")])
+
+
+def run_sparkr_tests():
+    set_title_and_block("Running SparkR tests", "BLOCK_SPARKR_UNIT_TESTS")
+
+    if which("R"):
+        run_cmd([os.path.join(SPARK_HOME, "R", "install-dev.sh")])
+        run_cmd([os.path.join(SPARK_HOME, "R", "run-tests.sh")])
+    else:
+        print "Ignoring SparkR tests as R was not found in PATH"
+
+
+def main():
+    # Ensure the user home directory (HOME) is valid and is an absolute directory
+    if not USER_HOME or not os.path.isabs(USER_HOME):
+        print "[error] Cannot determine your home directory as an absolute path;",
+        print "ensure the $HOME environment variable is set properly."
+        sys.exit(1)
+
+    os.chdir(SPARK_HOME)
+
+    rm_r(os.path.join(SPARK_HOME, "work"))
+    rm_r(os.path.join(USER_HOME, ".ivy2", "local", "org.apache.spark"))
+    rm_r(os.path.join(USER_HOME, ".ivy2", "cache", "org.apache.spark"))
+
+    os.environ["CURRENT_BLOCK"] = ERROR_CODES["BLOCK_GENERAL"]
+
+    java_exe = determine_java_executable()
+
+    if not java_exe:
+        print "[error] Cannot find a version of `java` on the system; please",
+        print "install one and retry."
+        sys.exit(2)
+
+    java_version = determine_java_version(java_exe)
+
+    if java_version.minor < 8:
+        print "[warn] Java 8 tests will not run because JDK version is < 1.8."
+
+    if os.environ.get("AMPLAB_JENKINS"):
+        # if we're on the Amplab Jenkins build servers setup variables
+        # to reflect the environment settings
+        build_tool = os.environ.get("AMPLAB_JENKINS_BUILD_TOOL", "sbt")
+        hadoop_version = os.environ.get("AMPLAB_JENKINS_BUILD_PROFILE", "hadoop2.3")
+        test_env = "amplab_jenkins"
+        # add path for Python3 in Jenkins if we're calling from a Jenkins machine
+        os.environ["PATH"] = "/home/anaconda/envs/py3k/bin:" + os.environ.get("PATH")
+    else:
+        # else we're running locally and can use local settings
+        build_tool = "sbt"
+        hadoop_version = "hadoop2.3"
+        test_env = "local"
+
+    print "[info] Using build tool", build_tool, "with profile", hadoop_version,
+    print "under environment", test_env
+
+    # determine high level changes
+    changed_modules = identify_changed_modules(test_env)
+    print "[info] Found the following changed modules:", ", ".join(changed_modules)
+
+    # license checks
+    run_apache_rat_checks()
+
+    # style checks
+    run_scala_style_checks()
+    run_python_style_checks()
+
+    # determine if docs were changed and if we're inside the amplab environment
+    # note - the below commented out until *all* Jenkins workers can get `jekyll` installed
+    # if "DOCS" in changed_modules and test_env == "amplab_jenkins":
+    #    build_spark_documentation()
+
+    # spark build
+    build_apache_spark(build_tool, hadoop_version)
+
+    # backwards compatibility checks
+    detect_binary_inop_with_mima()
+
+    # run the test suites
+    run_scala_tests(build_tool, hadoop_version, changed_modules)
+    run_python_tests()
+    run_sparkr_tests()
+
+if __name__ == "__main__":
+    main()
diff --git a/examples/src/main/python/kmeans.py b/examples/src/main/python/kmeans.py
index 1456c87312..0ea7cfb702 100755
--- a/examples/src/main/python/kmeans.py
+++ b/examples/src/main/python/kmeans.py
@@ -68,7 +68,7 @@ if __name__ == "__main__":
         closest = data.map(
             lambda p: (closestPoint(p, kPoints), (p, 1)))
         pointStats = closest.reduceByKey(
-            lambda (p1, c1), (p2, c2): (p1 + p2, c1 + c2))
+            lambda p1_c1, p2_c2: (p1_c1[0] + p2_c2[0], p1_c1[1] + p2_c2[1]))
         newPoints = pointStats.map(
             lambda st: (st[0], st[1][0] / st[1][1])).collect()