def build_apache_spark(build_tool, hadoop_version):
    """Will build Spark against Hive v1.2.1 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 main():
    opts = parse_opts()
    # 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;",
              " 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"] = str(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",
              " 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.")

    # install SparkR
    if which("R"):
        run_cmd([os.path.join(SPARK_HOME, "R", "install-dev.sh")])
    else:
        print("Cannot install SparkR as R was not found in PATH")

    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", "hadoop2.6")
        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 = os.environ.get("HADOOP_PROFILE", "hadoop2.6")
        test_env = "local"

    print("[info] Using build tool", build_tool, "with Hadoop profile", hadoop_version,
          "under environment", test_env)

    changed_modules = None
    changed_files = None
    if test_env == "amplab_jenkins" and os.environ.get("AMP_JENKINS_PRB"):
        target_branch = os.environ["ghprbTargetBranch"]
        changed_files = identify_changed_files_from_git_commits("HEAD", target_branch=target_branch)
        changed_modules = determine_modules_for_files(changed_files)
        excluded_tags = determine_tags_to_exclude(changed_modules)
    if not changed_modules:
        changed_modules = [modules.root]
        excluded_tags = []
    print("[info] Found the following changed modules:",
          ", ".join(x.name for x in changed_modules))

    # setup environment variables
    # note - the 'root' module doesn't collect environment variables for all modules. Because the
    # environment variables should not be set if a module is not changed, even if running the 'root'
    # module. So here we should use changed_modules rather than test_modules.
    test_environ = {}
    for m in changed_modules:
        test_environ.update(m.environ)
    setup_test_environ(test_environ)

    test_modules = determine_modules_to_test(changed_modules)

    # license checks
    run_apache_rat_checks()

    # style checks
    if not changed_files or any(f.endswith(".scala")
                                or f.endswith("scalastyle-config.xml")
                                for f in changed_files):
        run_scala_style_checks()
    if not changed_files or any(f.endswith(".java")
                                or f.endswith("checkstyle.xml")
                                or f.endswith("checkstyle-suppressions.xml")
                                for f in changed_files):
        # run_java_style_checks()
        pass
    if not changed_files or any(f.endswith(".py") for f in changed_files):
        run_python_style_checks()
    if not changed_files or any(f.endswith(".R") for f in changed_files):
        run_sparkr_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()

    if any(m.should_run_build_tests for m in test_modules):
#.........这里部分代码省略.........

def main():
    opts = parse_opts()
    # 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;",
              " 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",
              " 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 Hadoop profile", hadoop_version,
          "under environment", test_env)

    changed_modules = None
    changed_files = None
    if test_env == "amplab_jenkins" and os.environ.get("AMP_JENKINS_PRB"):
        target_branch = os.environ["ghprbTargetBranch"]
        changed_files = identify_changed_files_from_git_commits("HEAD", target_branch=target_branch)
        changed_modules = determine_modules_for_files(changed_files)
    if not changed_modules:
        changed_modules = [modules.root]
    print("[info] Found the following changed modules:",
          ", ".join(x.name for x in changed_modules))

    test_modules = determine_modules_to_test(changed_modules)

    # license checks
    run_apache_rat_checks()

    # style checks
    if not changed_files or any(f.endswith(".scala") for f in changed_files):
        run_scala_style_checks()
    if not changed_files or any(f.endswith(".py") for f in changed_files):
        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, test_modules)

    modules_with_python_tests = [m for m in test_modules if m.python_test_goals]
    if modules_with_python_tests:
        run_python_tests(modules_with_python_tests, opts.parallelism)
    if any(m.should_run_r_tests for m in test_modules):
        run_sparkr_tests()