Github user JoshRosen commented on a diff in the pull request:
https://github.com/apache/spark/pull/5694#discussion_r32359302
--- Diff: dev/run-tests.py ---
@@ -0,0 +1,506 @@
+#!/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 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(["./dev/check-license"])
+
+
+def run_scala_style_checks():
+ set_title_and_block("Running Scala style checks", "BLOCK_SCALA_STYLE")
+ run_cmd(["./dev/lint-scala"])
+
+
+def run_python_style_checks():
+ set_title_and_block("Running Python style checks",
"BLOCK_PYTHON_STYLE")
+ run_cmd(["./dev/lint-python"])
+
+
+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(["./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 = ["./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"],
+ }
+
+ try:
+ hadoop_profiles = sbt_maven_hadoop_profiles[hadoop_version]
+ except KeyError:
+ print "[error] Could not find", hadoop_version, "in the list.
Valid options",
+ print "are 'hadoop1.0', 'hadoop2.0', 'hadoop2.2', and 'hadoop2.3'."
+ sys.exit(int(os.environ.get("CURRENT_BLOCK", 255)))
+
+ return hadoop_profiles
+
+
+def get_build_profiles(hadoop_version="hadoop2.3",
+ base_profiles=True,
+ hive_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"]
+ hadoop_profiles = get_hadoop_profiles(hadoop_version)
+
+ build_profiles = hadoop_profiles
+ # first, check and add the base profiles
+ if base_profiles:
+ build_profiles = build_profiles + base_profiles
+ # second, check and add the hive profiles
+ if hive_profiles:
+ build_profiles = build_profiles + hive_profiles
+
+ return build_profiles
+
+
+def build_spark_maven(hadoop_version):
+ build_profiles = get_build_profiles(hadoop_version, hive_profiles=True)
--- End diff --
Maybe add a comment on the previous line to explain that we always build
with Hive support, even if we end up skipping the Hive tests in most PRB builds?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
