Merge branch 'apache:trunk' into HADOOP-17715

Author: snehavarma

BUILDING.txt

@@ -51,14 +51,13 @@ Known issues:
   and run your IDE and Docker etc inside that VM.
 
 ----------------------------------------------------------------------------------
-Installing required packages for clean install of Ubuntu 14.04 LTS Desktop:
+Installing required packages for clean install of Ubuntu 18.04 LTS Desktop.
+(For Ubuntu 20.04, gcc/g++ and cmake bundled with Ubuntu can be used.
+Refer to  dev-support/docker/Dockerfile):
 
-* Oracle JDK 1.8 (preferred)
-  $ sudo apt-get purge openjdk*
-  $ sudo apt-get install software-properties-common
-  $ sudo add-apt-repository ppa:webupd8team/java
+* Open JDK 1.8
   $ sudo apt-get update
-  $ sudo apt-get install oracle-java8-installer
+  $ sudo apt-get -y install java-8-openjdk
 * Maven
   $ sudo apt-get -y install maven
 * Native libraries
@@ -86,12 +85,13 @@ Installing required packages for clean install of Ubuntu 14.04 LTS Desktop:
   $ curl -L https://sourceforge.net/projects/boost/files/boost/1.72.0/boost_1_72_0.tar.bz2/download > boost_1_72_0.tar.bz2
   $ tar --bzip2 -xf boost_1_72_0.tar.bz2 && cd boost_1_72_0
   $ ./bootstrap.sh --prefix=/usr/
-  $ ./b2 --without-python install
+  $ ./b2 --without-python
+  $ sudo ./b2 --without-python install
 
 Optional packages:
 
 * Snappy compression (only used for hadoop-mapreduce-client-nativetask)
-  $ sudo apt-get install snappy libsnappy-dev
+  $ sudo apt-get install libsnappy-dev
 * Intel ISA-L library for erasure coding
   Please refer to https://01.org/intel%C2%AE-storage-acceleration-library-open-source-version
   (OR https://github.com/01org/isa-l)
@@ -139,7 +139,7 @@ Maven build goals:
  * Compile                   : mvn compile [-Pnative]
  * Run tests                 : mvn test [-Pnative] [-Pshelltest]
  * Create JAR                : mvn package
- * Run findbugs              : mvn compile findbugs:findbugs
+ * Run spotbugs              : mvn compile spotbugs:spotbugs
  * Run checkstyle            : mvn compile checkstyle:checkstyle
  * Install JAR in M2 cache   : mvn install
  * Deploy JAR to Maven repo  : mvn deploy

LICENSE-binary

@@ -225,7 +225,7 @@ com.fasterxml.jackson.jaxrs:jackson-jaxrs-base:2.9.9
 com.fasterxml.jackson.jaxrs:jackson-jaxrs-json-provider:2.9.9
 com.fasterxml.jackson.module:jackson-module-jaxb-annotations:2.9.9
 com.fasterxml.uuid:java-uuid-generator:3.1.4
-com.fasterxml.woodstox:woodstox-core:5.0.3
+com.fasterxml.woodstox:woodstox-core:5.3.0
 com.github.davidmoten:rxjava-extras:0.8.0.17
 com.github.stephenc.jcip:jcip-annotations:1.0-1
 com.google:guice:4.0
@@ -240,7 +240,7 @@ com.google.guava:guava:20.0
 com.google.guava:guava:27.0-jre
 com.google.guava:listenablefuture:9999.0-empty-to-avoid-conflict-with-guava
 com.microsoft.azure:azure-storage:7.0.0
-com.nimbusds:nimbus-jose-jwt:4.41.1
+com.nimbusds:nimbus-jose-jwt:9.8.1
 com.squareup.okhttp:okhttp:2.7.5
 com.squareup.okio:okio:1.6.0
 com.zaxxer:HikariCP-java7:2.4.12
@@ -249,7 +249,7 @@ commons-cli:commons-cli:1.2
 commons-codec:commons-codec:1.11
 commons-collections:commons-collections:3.2.2
 commons-daemon:commons-daemon:1.0.13
-commons-io:commons-io:2.5
+commons-io:commons-io:2.8.0
 commons-lang:commons-lang:2.6
 commons-logging:commons-logging:1.1.3
 commons-net:commons-net:3.6
@@ -283,7 +283,7 @@ javax.inject:javax.inject:1
 log4j:log4j:1.2.17
 net.java.dev.jna:jna:5.2.0
 net.minidev:accessors-smart:1.2
-net.minidev:json-smart:2.3
+net.minidev:json-smart:2.4.2
 org.apache.avro:avro:1.7.7
 org.apache.commons:commons-collections4:4.2
 org.apache.commons:commons-compress:1.19
@@ -366,7 +366,7 @@ hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanage
 
 com.github.luben:zstd-jni:1.4.3-1
 dnsjava:dnsjava:2.1.7
-org.codehaus.woodstox:stax2-api:3.1.4
+org.codehaus.woodstox:stax2-api:4.2.1
 
 
 BSD 3-Clause
@@ -468,8 +468,8 @@ com.microsoft.azure:azure-cosmosdb-gateway:2.4.5
 com.microsoft.azure:azure-data-lake-store-sdk:2.3.3
 com.microsoft.azure:azure-keyvault-core:1.0.0
 com.microsoft.sqlserver:mssql-jdbc:6.2.1.jre7
-org.bouncycastle:bcpkix-jdk15on:1.60
-org.bouncycastle:bcprov-jdk15on:1.60
+org.bouncycastle:bcpkix-jdk15on:1.68
+org.bouncycastle:bcprov-jdk15on:1.68
 org.checkerframework:checker-qual:2.5.2
 org.codehaus.mojo:animal-sniffer-annotations:1.17
 org.jruby.jcodings:jcodings:1.0.13

dev-support/Jenkinsfile

@@ -35,7 +35,7 @@ pipeline {
         DOCKERFILE = "${SOURCEDIR}/dev-support/docker/Dockerfile"
         YETUS='yetus'
         // Branch or tag name.  Yetus release tags are 'rel/X.Y.Z'
-        YETUS_VERSION='6ab19e71eaf3234863424c6f684b34c1d3dcc0ce'
+        YETUS_VERSION='f9ba0170a5787a5f4662d3769804fef0226a182f'
     }
 
     parameters {
@@ -120,11 +120,11 @@ pipeline {
                         YETUS_ARGS+=("--proclimit=5500")
                         YETUS_ARGS+=("--dockermemlimit=22g")
 
-                        # -1 findbugs issues that show up prior to the patch being applied
-                        YETUS_ARGS+=("--findbugs-strict-precheck")
+                        # -1 spotbugs issues that show up prior to the patch being applied
+                        YETUS_ARGS+=("--spotbugs-strict-precheck")
 
                         # rsync these files back into the archive dir
-                        YETUS_ARGS+=("--archive-list=checkstyle-errors.xml,findbugsXml.xml")
+                        YETUS_ARGS+=("--archive-list=checkstyle-errors.xml,spotbugsXml.xml")
 
                         # URL for user-side presentation in reports and such to our artifacts
                         # (needs to match the archive bits below)
@@ -133,9 +133,6 @@ pipeline {
                         # plugins to enable
                         YETUS_ARGS+=("--plugins=all")
 
-                        # use Hadoop's bundled shelldocs
-                        YETUS_ARGS+=("--shelldocs=${WORKSPACE}/${SOURCEDIR}/dev-support/bin/shelldocs")
-
                         # don't let these tests cause -1s because we aren't really paying that
                         # much attention to them
                         YETUS_ARGS+=("--tests-filter=checkstyle")
@@ -152,9 +149,6 @@ pipeline {
                         # help keep the ASF boxes clean
                         YETUS_ARGS+=("--sentinel")
 
-                        # use emoji vote so it is easier to find the broken line
-                        YETUS_ARGS+=("--github-use-emoji-vote")
-
                         # test with Java 8 and 11
                         YETUS_ARGS+=("--java-home=/usr/lib/jvm/java-8-openjdk-amd64")
                         YETUS_ARGS+=("--multijdkdirs=/usr/lib/jvm/java-11-openjdk-amd64")
@@ -163,6 +157,10 @@ pipeline {
                         # custom javadoc goals
                         YETUS_ARGS+=("--mvn-javadoc-goals=process-sources,javadoc:javadoc-no-fork")
 
+                        # write Yetus report as GitHub comment (YETUS-1102)
+                        YETUS_ARGS+=("--github-write-comment")
+                        YETUS_ARGS+=("--github-use-emoji-vote")
+
                         "${TESTPATCHBIN}" "${YETUS_ARGS[@]}"
                         '''
                 }
@@ -174,6 +172,19 @@ pipeline {
     post {
         always {
           script {
+            // Publish status if it was missed (YETUS-1059)
+            withCredentials(
+                [usernamePassword(credentialsId: '683f5dcf-5552-4b28-9fb1-6a6b77cf53dd',
+                                  passwordVariable: 'GITHUB_TOKEN',
+                                  usernameVariable: 'GITHUB_USER')]) {
+                sh '''#!/usr/bin/env bash
+                    YETUS_ARGS+=("--github-token=${GITHUB_TOKEN}")
+                    YETUS_ARGS+=("--patch-dir=${WORKSPACE}/${PATCHDIR}")
+                    TESTPATCHBIN="${WORKSPACE}/${YETUS}/precommit/src/main/shell/github-status-recovery.sh"
+                    /usr/bin/env bash "${TESTPATCHBIN}" "${YETUS_ARGS[@]}" ${EXTRA_ARGS} || true
+                    '''
+            }
+
             // Yetus output
             archiveArtifacts "${env.PATCHDIR}/**"
             // Publish the HTML report so that it can be looked at

dev-support/bin/checkcompatibility.py

@@ -1,4 +1,4 @@
-#!/usr/bin/env python
+#!/usr/bin/env python3
 #
 # Licensed to the Apache Software Foundation (ASF) under one
 # or more contributor license agreements.  See the NOTICE file
@@ -30,33 +30,16 @@
 import shutil
 import subprocess
 import sys
-import urllib2
-try:
-  import argparse
-except ImportError:
-  sys.stderr.write("Please install argparse, e.g. via `pip install argparse`.")
-  sys.exit(2)
+import urllib.request
+import argparse
 
 # Various relative paths
 REPO_DIR = os.getcwd()
 
 def check_output(*popenargs, **kwargs):
-  r"""Run command with arguments and return its output as a byte string.
-  Backported from Python 2.7 as it's implemented as pure python on stdlib.
-  >>> check_output(['/usr/bin/python', '--version'])
-  Python 2.6.2
-  """
-  process = subprocess.Popen(stdout=subprocess.PIPE, *popenargs, **kwargs)
-  output, _ = process.communicate()
-  retcode = process.poll()
-  if retcode:
-    cmd = kwargs.get("args")
-    if cmd is None:
-      cmd = popenargs[0]
-    error = subprocess.CalledProcessError(retcode, cmd)
-    error.output = output
-    raise error
-  return output
+  """ Run command with arguments and return its output as a string. """
+  return subprocess.check_output(*popenargs, **kwargs, encoding='utf-8')
+
 
 def get_repo_dir():
   """ Return the path to the top of the repo. """
@@ -139,7 +122,7 @@ def checkout_java_acc(force):
   url = "https://github.com/lvc/japi-compliance-checker/archive/1.8.tar.gz"
   scratch_dir = get_scratch_dir()
   path = os.path.join(scratch_dir, os.path.basename(url))
-  jacc = urllib2.urlopen(url)
+  jacc = urllib.request.urlopen(url)
   with open(path, 'wb') as w:
     w.write(jacc.read())
 
@@ -192,9 +175,9 @@ def run_java_acc(src_name, src_jars, dst_name, dst_jars, annotations):
 
   if annotations is not None:
     annotations_path = os.path.join(get_scratch_dir(), "annotations.txt")
-    with file(annotations_path, "w") as f:
+    with open(annotations_path, "w") as f:
       for ann in annotations:
-        print >>f, ann
+        print(ann, file=f)
     args += ["-annotations-list", annotations_path]
 
   subprocess.check_call(args)
@@ -264,8 +247,8 @@ def main():
   parser.add_argument("--skip-build",
                       action="store_true",
                       help="Skip building the projects.")
-  parser.add_argument("src_rev", nargs=1, help="Source revision.")
-  parser.add_argument("dst_rev", nargs="?", default="HEAD",
+  parser.add_argument("src_rev", nargs=1, type=str, help="Source revision.")
+  parser.add_argument("dst_rev", nargs="?", type=str, default="HEAD",
                       help="Destination revision. " +
                       "If not specified, will use HEAD.")
 

dev-support/bin/hadoop.sh

@@ -355,6 +355,7 @@ function personality_modules
       fi
     ;;
     unit)
+      extra="-Dsurefire.rerunFailingTestsCount=2"
       if [[ "${BUILDMODE}" = full ]]; then
         ordering=mvnsrc
       elif [[ "${CHANGED_MODULES[*]}" =~ \. ]]; then
@@ -363,7 +364,7 @@ function personality_modules
 
       if [[ ${TEST_PARALLEL} = "true" ]] ; then
         if hadoop_test_parallel; then
-          extra="-Pparallel-tests"
+          extra="${extra} -Pparallel-tests"
           if [[ -n ${TEST_THREADS:-} ]]; then
             extra="${extra} -DtestsThreadCount=${TEST_THREADS}"
           fi
@@ -482,7 +483,7 @@ function personality_file_tests
   fi
 
   if [[ ${filename} =~ \.java$ ]]; then
-    add_test findbugs
+    add_test spotbugs
   fi
 }
 
@@ -550,7 +551,7 @@ function shadedclient_rebuild
   echo_and_redirect "${logfile}" \
     "${MAVEN}" "${MAVEN_ARGS[@]}" verify -fae --batch-mode -am \
       "${modules[@]}" \
-      -Dtest=NoUnitTests -Dmaven.javadoc.skip=true -Dcheckstyle.skip=true -Dfindbugs.skip=true
+      -Dtest=NoUnitTests -Dmaven.javadoc.skip=true -Dcheckstyle.skip=true -Dspotbugs.skip=true
 
   count=$("${GREP}" -c '\[ERROR\]' "${logfile}")
   if [[ ${count} -gt 0 ]]; then

dev-support/bin/test-patch

@@ -15,4 +15,4 @@
 # limitations under the License.
 
 BINDIR=$(cd -P -- "$(dirname -- "${BASH_SOURCE-0}")" >/dev/null && pwd -P)
-exec "${BINDIR}/yetus-wrapper" test-patch --project=hadoop --skip-dir=dev-support "$@"
+exec "${BINDIR}/yetus-wrapper" test-patch --project=hadoop --skip-dirs=dev-support "$@"

dev-support/bin/yetus-wrapper

@@ -77,7 +77,7 @@ WANTED="$1"
 shift
 ARGV=("$@")
 
-HADOOP_YETUS_VERSION=${HADOOP_YETUS_VERSION:-0.10.0}
+HADOOP_YETUS_VERSION=${HADOOP_YETUS_VERSION:-0.13.0}
 BIN=$(yetus_abs "${BASH_SOURCE-$0}")
 BINDIR=$(dirname "${BIN}")