[SPARK-7018][BUILD] Refactor dev/run-tests-jenkins into Python

This commit refactors the `run-tests-jenkins` script into Python. This refactoring was done by brennonyork in #7401; this PR contains a few minor edits from joshrosen in order to bring it up to date with other recent changes.

From the original PR description (by brennonyork):

Currently a few things are left out that, could and I think should, be smaller JIRA's after this.

1. There are still a few areas where we use environment variables where we don't need to (like `CURRENT_BLOCK`). I might get around to fixing this one in lieu of everything else, but wanted to point that out.
2. The PR tests are still written in bash. I opted to not change those and just rewrite the runner into Python. This is a great follow-on JIRA IMO.
3. All of the linting scripts are still in bash as well and would likely do to just add those in as follow-on JIRA's as well.

Closes #7401.

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

Closes #9161 from JoshRosen/run-tests-jenkins-refactoring.

2 files changed, 49 insertions, 2 deletions

diff --git a/dev/sparktestsupport/__init__.py b/dev/sparktestsupport/__init__.py
index 12696d98fb..8ab6d9e37c 100644
--- a/dev/sparktestsupport/__init__.py
+++ b/dev/sparktestsupport/__init__.py
@@ -19,3 +19,17 @@ import os
 
 SPARK_HOME = os.path.abspath(os.path.join(os.path.dirname(os.path.realpath(__file__)), "../../"))
 USER_HOME = os.environ.get("HOME")
+ERROR_CODES = {
+    "BLOCK_GENERAL": 10,
+    "BLOCK_RAT": 11,
+    "BLOCK_SCALA_STYLE": 12,
+    "BLOCK_PYTHON_STYLE": 13,
+    "BLOCK_R_STYLE": 14,
+    "BLOCK_DOCUMENTATION": 15,
+    "BLOCK_BUILD": 16,
+    "BLOCK_MIMA": 17,
+    "BLOCK_SPARK_UNIT_TESTS": 18,
+    "BLOCK_PYSPARK_UNIT_TESTS": 19,
+    "BLOCK_SPARKR_UNIT_TESTS": 20,
+    "BLOCK_TIMEOUT": 124
+}
diff --git a/dev/sparktestsupport/shellutils.py b/dev/sparktestsupport/shellutils.py
index 12bd0bf3a4..d280e79707 100644
--- a/dev/sparktestsupport/shellutils.py
+++ b/dev/sparktestsupport/shellutils.py
@@ -22,6 +22,36 @@ import subprocess
 import sys
 
 
+if sys.version_info >= (2, 7):
+    subprocess_check_output = subprocess.check_output
+    subprocess_check_call = subprocess.check_call
+else:
+    # SPARK-8763
+    # backported from subprocess module in Python 2.7
+    def subprocess_check_output(*popenargs, **kwargs):
+        if 'stdout' in kwargs:
+            raise ValueError('stdout argument not allowed, it will be overridden.')
+        process = subprocess.Popen(stdout=subprocess.PIPE, *popenargs, **kwargs)
+        output, unused_err = process.communicate()
+        retcode = process.poll()
+        if retcode:
+            cmd = kwargs.get("args")
+            if cmd is None:
+                cmd = popenargs[0]
+            raise subprocess.CalledProcessError(retcode, cmd, output=output)
+        return output
+
+    # backported from subprocess module in Python 2.7
+    def subprocess_check_call(*popenargs, **kwargs):
+        retcode = call(*popenargs, **kwargs)
+        if retcode:
+            cmd = kwargs.get("args")
+            if cmd is None:
+                cmd = popenargs[0]
+            raise CalledProcessError(retcode, cmd)
+        return 0
+
+
 def exit_from_command_with_retcode(cmd, retcode):
     print("[error] running", ' '.join(cmd), "; received return code", retcode)
     sys.exit(int(os.environ.get("CURRENT_BLOCK", 255)))
@@ -39,7 +69,7 @@ def rm_r(path):
         os.remove(path)
 
 
-def run_cmd(cmd):
+def run_cmd(cmd, return_output=False):
     """
     Given a command as a list of arguments will attempt to execute the command
     and, on failure, print an error message and exit.
@@ -48,7 +78,10 @@ def run_cmd(cmd):
     if not isinstance(cmd, list):
         cmd = cmd.split()
     try:
-        subprocess.check_call(cmd)
+        if return_output:
+            return subprocess_check_output(cmd)
+        else:
+            return subprocess_check_call(cmd)
     except subprocess.CalledProcessError as e:
         exit_from_command_with_retcode(e.cmd, e.returncode)