[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.

1 files changed, 2 insertions, 202 deletions

diff --git a/dev/run-tests-jenkins b/dev/run-tests-jenkins
index d3b05fa6df..e79accf9e9 100755
--- a/dev/run-tests-jenkins
+++ b/dev/run-tests-jenkins
@@ -22,207 +22,7 @@
 # Environment variables are populated by the code here:
 #+ https://github.com/jenkinsci/ghprb-plugin/blob/master/src/main/java/org/jenkinsci/plugins/ghprb/GhprbTrigger.java#L139
 
-# Go to the Spark project root directory
-FWDIR="$(cd `dirname $0`/..; pwd)"
+FWDIR="$(cd "`dirname $0`"/..; pwd)"
 cd "$FWDIR"
 
-source "$FWDIR/dev/run-tests-codes.sh"
-
-COMMENTS_URL="https://api.github.com/repos/apache/spark/issues/$ghprbPullId/comments"
-PULL_REQUEST_URL="https://github.com/apache/spark/pull/$ghprbPullId"
-
-# Important Environment Variables
-# ---
-# $ghprbActualCommit
-#+  This is the hash of the most recent commit in the PR.
-#+  The merge-base of this and master is the commit from which the PR was branched.
-# $sha1
-#+  If the patch merges cleanly, this is a reference to the merge commit hash
-#+    (e.g. "origin/pr/2606/merge").
-#+  If the patch does not merge cleanly, it is equal to $ghprbActualCommit.
-#+  The merge-base of this and master in the case of a clean merge is the most recent commit
-#+    against master.
-
-COMMIT_URL="https://github.com/apache/spark/commit/${ghprbActualCommit}"
-# GitHub doesn't auto-link short hashes when submitted via the API, unfortunately. :(
-SHORT_COMMIT_HASH="${ghprbActualCommit:0:7}"
-
-# format: http://linux.die.net/man/1/timeout
-# must be less than the timeout configured on Jenkins (currently 300m)
-TESTS_TIMEOUT="250m"
-
-# Array to capture all tests to run on the pull request. These tests are held under the
-#+ dev/tests/ directory.
-#
-# To write a PR test:
-#+  * the file must reside within the dev/tests directory
-#+  * be an executable bash script
-#+  * accept three arguments on the command line, the first being the Github PR long commit
-#+    hash, the second the Github SHA1 hash, and the final the current PR hash
-#+  * and, lastly, return string output to be included in the pr message output that will
-#+    be posted to Github
-PR_TESTS=(
-  "pr_merge_ability"
-  "pr_public_classes"
-# DISABLED (pwendell) "pr_new_dependencies"
-)
-
-function post_message () {
-  local message=$1
-  local data="{\"body\": \"$message\"}"
-  local HTTP_CODE_HEADER="HTTP Response Code: "
-
-  echo "Attempting to post to Github..."
-
-  local curl_output=$(
-    curl `#--dump-header -` \
-      --silent \
-      --user x-oauth-basic:$GITHUB_OAUTH_KEY \
-      --request POST \
-      --data "$data" \
-      --write-out "${HTTP_CODE_HEADER}%{http_code}\n" \
-      --header "Content-Type: application/json" \
-      "$COMMENTS_URL" #> /dev/null #| "$FWDIR/dev/jq" .id #| head -n 8
-  )
-  local curl_status=${PIPESTATUS[0]}
-
-  if [ "$curl_status" -ne 0 ]; then
-      echo "Failed to post message to GitHub." >&2
-      echo " > curl_status: ${curl_status}" >&2
-      echo " > curl_output: ${curl_output}" >&2
-      echo " > data: ${data}" >&2
-      # exit $curl_status
-  fi
-
-  local api_response=$(
-    echo "${curl_output}" \
-    | grep -v -e "^${HTTP_CODE_HEADER}"
-  )
-
-  local http_code=$(
-    echo "${curl_output}" \
-    | grep -e "^${HTTP_CODE_HEADER}" \
-    | sed -r -e "s/^${HTTP_CODE_HEADER}//g"
-  )
-
-  if [ -n "$http_code" ] && [ "$http_code" -ne "201" ]; then
-      echo " > http_code: ${http_code}." >&2
-      echo " > api_response: ${api_response}" >&2
-      echo " > data: ${data}" >&2
-  fi
-
-  if [ "$curl_status" -eq 0 ] && [ "$http_code" -eq "201" ]; then
-    echo " > Post successful."
-  fi
-}
-
-# post start message
-{
-  start_message="\
-  [Test build ${BUILD_DISPLAY_NAME} has started](${BUILD_URL}consoleFull) for \
-  PR $ghprbPullId at commit [\`${SHORT_COMMIT_HASH}\`](${COMMIT_URL})."
-
-  post_message "$start_message"
-}
-
-# Environment variable to capture PR test output
-pr_message=""
-# Ensure we save off the current HEAD to revert to
-current_pr_head="`git rev-parse HEAD`"
-
-echo "HEAD:  `git rev-parse HEAD`"
-echo "\$ghprbActualCommit: $ghprbActualCommit"
-echo "\$sha1:  $sha1"
-echo "\$ghprbPullTitle: $ghprbPullTitle"
-
-# Run pull request tests
-for t in "${PR_TESTS[@]}"; do
-  this_test="${FWDIR}/dev/tests/${t}.sh"
-  # Ensure the test can be found and is a file
-  if [ -f "${this_test}" ]; then
-    echo "Running test: $t"
-    this_mssg="$(bash "${this_test}" "${ghprbActualCommit}" "${sha1}" "${current_pr_head}")"
-    # Check if this is the merge test as we submit that note *before* and *after*
-    # the tests run
-    [ "$t" == "pr_merge_ability" ] && merge_note="${this_mssg}"
-    pr_message="${pr_message}\n${this_mssg}"
-    # Ensure, after each test, that we're back on the current PR
-    git checkout -f "${current_pr_head}" &>/dev/null
-  else
-    echo "Cannot find test ${this_test}."
-  fi
-done
-
-# run tests
-{
-  # Marks this build is a pull request build.
-  export AMP_JENKINS_PRB=true
-  if [[ $ghprbPullTitle == *"test-maven"* ]]; then
-    export AMPLAB_JENKINS_BUILD_TOOL="maven"
-  fi
-  if [[ $ghprbPullTitle == *"test-hadoop1.0"* ]]; then
-    export AMPLAB_JENKINS_BUILD_PROFILE="hadoop1.0"
-  elif [[ $ghprbPullTitle == *"test-hadoop2.0"* ]]; then
-    export AMPLAB_JENKINS_BUILD_PROFILE="hadoop2.0"
-  elif [[ $ghprbPullTitle == *"test-hadoop2.2"* ]]; then
-    export AMPLAB_JENKINS_BUILD_PROFILE="hadoop2.2"
-  elif [[ $ghprbPullTitle == *"test-hadoop2.3"* ]]; then
-    export AMPLAB_JENKINS_BUILD_PROFILE="hadoop2.3"
-  fi
-
-  timeout "${TESTS_TIMEOUT}" ./dev/run-tests
-  test_result="$?"
-
-  if [ "$test_result" -eq "124" ]; then
-    fail_message="**[Test build ${BUILD_DISPLAY_NAME} timed out](${BUILD_URL}console)** \
-    for PR $ghprbPullId at commit [\`${SHORT_COMMIT_HASH}\`](${COMMIT_URL}) \
-    after a configured wait of \`${TESTS_TIMEOUT}\`."
-
-    post_message "$fail_message"
-    exit $test_result
-  elif [ "$test_result" -eq "0" ]; then
-    test_result_note=" * This patch **passes all tests**."
-  else
-    if [ "$test_result" -eq "$BLOCK_GENERAL" ]; then
-      failing_test="some tests"
-    elif [ "$test_result" -eq "$BLOCK_RAT" ]; then
-      failing_test="RAT tests"
-    elif [ "$test_result" -eq "$BLOCK_SCALA_STYLE" ]; then
-      failing_test="Scala style tests"
-    elif [ "$test_result" -eq "$BLOCK_PYTHON_STYLE" ]; then
-      failing_test="Python style tests"
-    elif [ "$test_result" -eq "$BLOCK_R_STYLE" ]; then
-      failing_test="R 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
-      failing_test="MiMa tests"
-    elif [ "$test_result" -eq "$BLOCK_SPARK_UNIT_TESTS" ]; then
-      failing_test="Spark unit tests"
-    elif [ "$test_result" -eq "$BLOCK_PYSPARK_UNIT_TESTS" ]; then
-      failing_test="PySpark unit tests"
-    elif [ "$test_result" -eq "$BLOCK_SPARKR_UNIT_TESTS" ]; then
-      failing_test="SparkR unit tests"
-    else
-      failing_test="some tests"
-    fi
-
-    test_result_note=" * This patch **fails $failing_test**."
-  fi
-}
-
-# post end message
-{
-  result_message="\
-  [Test build ${BUILD_DISPLAY_NAME} has finished](${BUILD_URL}console) for \
-  PR $ghprbPullId at commit [\`${SHORT_COMMIT_HASH}\`](${COMMIT_URL})."
-
-  result_message="${result_message}\n${test_result_note}"
-  result_message="${result_message}${pr_message}"
-
-  post_message "$result_message"
-}
-
-exit $test_result
+exec python -u ./dev/run-tests-jenkins.py "$@"