From 9dd635eb5df52835b3b7f4f2b9c789da9e813c71 Mon Sep 17 00:00:00 2001 From: witgo <witgo@qq.com> Date: Tue, 15 Jul 2014 10:46:17 -0700 Subject: [PATCH] SPARK-2480: Resolve sbt warnings "NOTE: SPARK_YARN is deprecated, please use -Pyarn flag" Author: witgo <witgo@qq.com> Closes #1404 from witgo/run-tests and squashes the following commits: f703aee [witgo] fix Note: implicit method fromPairDStream is not applicable here because it comes after the application point and it lacks an explicit result type 2944f51 [witgo] Remove "NOTE: SPARK_YARN is deprecated, please use -Pyarn flag" ef59c70 [witgo] fix Note: implicit method fromPairDStream is not applicable here because it comes after the application point and it lacks an explicit result type 6cefee5 [witgo] Remove "NOTE: SPARK_YARN is deprecated, please use -Pyarn flag" --- dev/run-tests | 7 +++---- dev/scalastyle | 6 +++--- docs/hadoop-third-party-distributions.md | 4 ++-- docs/sql-programming-guide.md | 2 +- 4 files changed, 9 insertions(+), 10 deletions(-) diff --git a/dev/run-tests b/dev/run-tests index edd17b53b3..51e4def0f8 100755 --- a/dev/run-tests +++ b/dev/run-tests @@ -21,8 +21,7 @@ FWDIR="$(cd `dirname $0`/..; pwd)" cd $FWDIR -export SPARK_HADOOP_VERSION=2.3.0 -export SPARK_YARN=true +export SBT_MAVEN_PROFILES="-Pyarn -Phadoop-2.3 -Dhadoop.version=2.3.0" # Remove work directory rm -rf ./work @@ -66,8 +65,8 @@ echo "=========================================================================" # (either resolution or compilation) prompts the user for input either q, r, # etc to quit or retry. This echo is there to make it not block. if [ -n "$_RUN_SQL_TESTS" ]; then - echo -e "q\n" | SPARK_HIVE=true sbt/sbt clean package assembly/assembly test | \ - grep -v -e "info.*Resolving" -e "warn.*Merging" -e "info.*Including" + echo -e "q\n" | SBT_MAVEN_PROFILES="$SBT_MAVEN_PROFILES -Phive" sbt/sbt clean package \ + assembly/assembly test | grep -v -e "info.*Resolving" -e "warn.*Merging" -e "info.*Including" else echo -e "q\n" | sbt/sbt clean package assembly/assembly test | \ grep -v -e "info.*Resolving" -e "warn.*Merging" -e "info.*Including" diff --git a/dev/scalastyle b/dev/scalastyle index 0e8fd5cc8d..a02d06912f 100755 --- a/dev/scalastyle +++ b/dev/scalastyle @@ -17,12 +17,12 @@ # limitations under the License. # -echo -e "q\n" | SPARK_HIVE=true sbt/sbt scalastyle > scalastyle.txt +echo -e "q\n" | sbt/sbt -Phive scalastyle > scalastyle.txt # Check style with YARN alpha built too -echo -e "q\n" | SPARK_HADOOP_VERSION=0.23.9 SPARK_YARN=true sbt/sbt yarn-alpha/scalastyle \ +echo -e "q\n" | sbt/sbt -Pyarn -Phadoop-0.23 -Dhadoop.version=0.23.9 yarn-alpha/scalastyle \ >> scalastyle.txt # Check style with YARN built too -echo -e "q\n" | SPARK_HADOOP_VERSION=2.2.0 SPARK_YARN=true sbt/sbt yarn/scalastyle \ +echo -e "q\n" | sbt/sbt -Pyarn -Phadoop-2.2 -Dhadoop.version=2.2.0 yarn/scalastyle \ >> scalastyle.txt ERRORS=$(cat scalastyle.txt | grep -e "\<error\>") diff --git a/docs/hadoop-third-party-distributions.md b/docs/hadoop-third-party-distributions.md index 32403bc695..ab1023b8f1 100644 --- a/docs/hadoop-third-party-distributions.md +++ b/docs/hadoop-third-party-distributions.md @@ -48,9 +48,9 @@ the _exact_ Hadoop version you are running to avoid any compatibility errors. </tr> </table> -In SBT, the equivalent can be achieved by setting the SPARK_HADOOP_VERSION flag: +In SBT, the equivalent can be achieved by setting the the `hadoop.version` property: - SPARK_HADOOP_VERSION=1.0.4 sbt/sbt assembly + sbt/sbt -Dhadoop.version=1.0.4 assembly # Linking Applications to the Hadoop Version diff --git a/docs/sql-programming-guide.md b/docs/sql-programming-guide.md index 522c83884e..38728534a4 100644 --- a/docs/sql-programming-guide.md +++ b/docs/sql-programming-guide.md @@ -474,7 +474,7 @@ anotherPeople = sqlContext.jsonRDD(anotherPeopleRDD) Spark SQL also supports reading and writing data stored in [Apache Hive](http://hive.apache.org/). However, since Hive has a large number of dependencies, it is not included in the default Spark assembly. -In order to use Hive you must first run '`SPARK_HIVE=true sbt/sbt assembly/assembly`' (or use `-Phive` for maven). +In order to use Hive you must first run '`sbt/sbt -Phive assembly/assembly`' (or use `-Phive` for maven). This command builds a new assembly jar that includes Hive. Note that this Hive assembly jar must also be present on all of the worker nodes, as they will need access to the Hive serialization and deserialization libraries (SerDes) in order to acccess data stored in Hive. -- GitLab