dev/tests/pr_public_classes.sh

0001 #!/usr/bin/env bash
0002
0003 #
0004 # Licensed to the Apache Software Foundation (ASF) under one or more
0005 # contributor license agreements.  See the NOTICE file distributed with
0006 # this work for additional information regarding copyright ownership.
0007 # The ASF licenses this file to You under the Apache License, Version 2.0
0008 # (the "License"); you may not use this file except in compliance with
0009 # the License.  You may obtain a copy of the License at
0010 #
0011 #    http://www.apache.org/licenses/LICENSE-2.0
0012 #
0013 # Unless required by applicable law or agreed to in writing, software
0014 # distributed under the License is distributed on an "AS IS" BASIS,
0015 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
0016 # See the License for the specific language governing permissions and
0017 # limitations under the License.
0018 #
0019
0020 #
0021 # This script follows the base format for testing pull requests against
0022 # another branch and returning results to be published. More details can be
0023 # found at dev/run-tests-jenkins.
0024 #
0025 # Arg1: The Github Pull Request Actual Commit
0026 # known as `ghprbActualCommit` in `run-tests-jenkins`
0027
0028 ghprbActualCommit="$1"
0029
0030 # $ghprbActualCommit is an automatic merge commit generated by GitHub; its parents are some Spark
0031 # master commit and the tip of the pull request branch.
0032
0033 # By diffing$ghprbActualCommit^...$ghprbActualCommit and filtering to examine the diffs of only
0034 # non-test files, we can get changes introduced in the PR and not anything else added to master
0035 # since the PR was branched.
0036
0037 # Handle differences between GNU and BSD sed
0038 if [[ $(uname) == "Darwin" ]]; then
0039     SED='sed -E'
0040 else
0041     SED='sed -r'
0042 fi
0043
0044 source_files=$(
0045   git diff $ghprbActualCommit^...$ghprbActualCommit --name-only  `# diff patch against master from branch point` \
0046     | grep -v -e "\/test"                               `# ignore files in test directories` \
0047     | grep -e "\.py$" -e "\.java$" -e "\.scala$"        `# include only code files` \
0048     | tr "\n" " "
0049 )
0050
0051 new_public_classes=$(
0052   git diff $ghprbActualCommit^...$ghprbActualCommit ${source_files}      `# diff patch against master from branch point` \
0053     | grep "^\+"                              `# filter in only added lines` \
0054     | $SED -e "s/^\+//g"                      `# remove the leading +` \
0055     | grep -e "trait " -e "class "            `# filter in lines with these key words` \
0056     | grep -e "{" -e "("                      `# filter in lines with these key words, too` \
0057     | grep -v -e "\@\@" -e "private"          `# exclude lines with these words` \
0058     | grep -v -e "^// " -e "^/\*" -e "^ \* "  `# exclude comment lines` \
0059     | $SED -e "s/\{.*//g"                     `# remove from the { onwards` \
0060     | $SED -e "s/\}//g"                       `# just in case, remove }; they mess the JSON` \
0061     | $SED -e "s/\"/\\\\\"/g"                 `# escape double quotes; they mess the JSON` \
0062     | $SED -e "s/^(.*)$/\`\1\`/g"             `# surround with backticks for style` \
0063     | $SED -e "s/^/  \* /g"                   `# prepend '  *' to start of line` \
0064     | $SED -e "s/$/\\\n/g"                    `# append newline to end of line` \
0065     | tr -d "\n"                              `# remove actual LF characters`
0066 )
0067
0068 if [ -z "$new_public_classes" ]; then
0069   echo " * This patch adds no public classes."
0070 else
0071   public_classes_note=" * This patch adds the following public classes _(experimental)_:"
0072   echo -e "${public_classes_note}\n${new_public_classes}"
0073 fi