From a2262cdb7aa30e9f45043f1440d4b02bc3340f9f Mon Sep 17 00:00:00 2001
From: Andrew Or <andrewor14@gmail.com>
Date: Mon, 5 May 2014 22:14:47 -0700
Subject: [PATCH] [SPARK-1735] Add the missing special profiles to
 make-distribution.sh

73b0cbcc241cca3d318ff74340e80b02f884acbd introduced a few special profiles that are not covered in the `make-distribution.sh`. This affects hadoop versions 2.2.x, 2.3.x, and 2.4.x. Without these special profiles, a java version error for protobufs is thrown at run time.

I took the opportunity to rewrite the way we construct the maven command. Previously, the only hadoop version that triggered the `yarn-alpha` profile was 0.23.x, which was inconsistent with the [docs](https://github.com/apache/spark/blob/master/docs/building-with-maven.md). This is now generalized to hadoop versions from 0.23.x to 2.1.x.

Author: Andrew Or <andrewor14@gmail.com>

Closes #660 from andrewor14/hadoop-distribution and squashes the following commits:

6740126 [Andrew Or] Generalize the yarn profile to hadoop versions 2.2+
88f192d [Andrew Or] Add the required special profiles to make-distribution.sh
---
 make-distribution.sh | 47 +++++++++++++++++++++++++-------------------
 1 file changed, 27 insertions(+), 20 deletions(-)

diff --git a/make-distribution.sh b/make-distribution.sh
index ff18d01e7a616..8a63133bc45d4 100755
--- a/make-distribution.sh
+++ b/make-distribution.sh
@@ -47,7 +47,7 @@ set -o pipefail
 VERSION=$(mvn help:evaluate -Dexpression=project.version 2>/dev/null | grep -v "INFO" | tail -n 1)
 if [ $? != 0 ]; then
     echo -e "You need Maven installed to build Spark."
-    echo -e "Download Maven from https://maven.apache.org."
+    echo -e "Download Maven from https://maven.apache.org/"
     exit -1;
 fi
 
@@ -131,27 +131,34 @@ cd $FWDIR
 
 export MAVEN_OPTS="-Xmx2g -XX:MaxPermSize=512M -XX:ReservedCodeCacheSize=512m"
 
-if [ "$SPARK_HIVE" == "true" ]; then
-  MAYBE_HIVE="-Phive"
-else
-  MAYBE_HIVE=""
-fi
-
-if [ "$SPARK_YARN" == "true" ]; then
-  if [[ "$SPARK_HADOOP_VERSION" =~ "0.23." ]]; then
-    mvn clean package -DskipTests -Pyarn-alpha -Dhadoop.version=$SPARK_HADOOP_VERSION \
-      -Dyarn.version=$SPARK_HADOOP_VERSION $MAYBE_HIVE -Phadoop-0.23
-  else
-    mvn clean package -DskipTests -Pyarn -Dhadoop.version=$SPARK_HADOOP_VERSION \
-      -Dyarn.version=$SPARK_HADOOP_VERSION $MAYBE_HIVE
-  fi
-else
-  if [[ "$SPARK_HADOOP_VERSION" =~ "0.23." ]]; then
-    mvn clean package -Phadoop-0.23 -DskipTests -Dhadoop.version=$SPARK_HADOOP_VERSION $MAYBE_HIVE
-  else
-    mvn clean package -DskipTests -Dhadoop.version=$SPARK_HADOOP_VERSION $MAYBE_HIVE
+BUILD_COMMAND="mvn clean package"
+
+# Use special profiles for hadoop versions 0.23.x, 2.2.x, 2.3.x, 2.4.x
+if [[ "$SPARK_HADOOP_VERSION" =~ ^0\.23\. ]]; then BUILD_COMMAND="$BUILD_COMMAND -Phadoop-0.23"; fi
+if [[ "$SPARK_HADOOP_VERSION" =~ ^2\.2\. ]]; then BUILD_COMMAND="$BUILD_COMMAND -Phadoop-2.2"; fi
+if [[ "$SPARK_HADOOP_VERSION" =~ ^2\.3\. ]]; then BUILD_COMMAND="$BUILD_COMMAND -Phadoop-2.3"; fi
+if [[ "$SPARK_HADOOP_VERSION" =~ ^2\.4\. ]]; then BUILD_COMMAND="$BUILD_COMMAND -Phadoop-2.4"; fi
+if [[ "$SPARK_HIVE" == "true" ]]; then BUILD_COMMAND="$BUILD_COMMAND -Phive"; fi
+if [[ "$SPARK_YARN" == "true" ]]; then
+  # For hadoop versions 0.23.x to 2.1.x, use the yarn-alpha profile
+  if [[ "$SPARK_HADOOP_VERSION" =~ ^0\.2[3-9]\. ]] ||
+     [[ "$SPARK_HADOOP_VERSION" =~ ^0\.[3-9][0-9]\. ]] ||
+     [[ "$SPARK_HADOOP_VERSION" =~ ^1\.[0-9]\. ]] ||
+     [[ "$SPARK_HADOOP_VERSION" =~ ^2\.[0-1]\. ]]; then
+    BUILD_COMMAND="$BUILD_COMMAND -Pyarn-alpha"
+  # For hadoop versions 2.2+, use the yarn profile
+  elif [[ "$SPARK_HADOOP_VERSION" =~ ^2.[2-9]. ]]; then
+    BUILD_COMMAND="$BUILD_COMMAND -Pyarn"
   fi
+  BUILD_COMMAND="$BUILD_COMMAND -Dyarn.version=$SPARK_HADOOP_VERSION"
 fi
+BUILD_COMMAND="$BUILD_COMMAND -Dhadoop.version=$SPARK_HADOOP_VERSION"
+BUILD_COMMAND="$BUILD_COMMAND -DskipTests"
+
+# Actually build the jar
+echo -e "\nBuilding with..."
+echo -e "\$ $BUILD_COMMAND\n"
+${BUILD_COMMAND}
 
 # Make directories
 rm -rf "$DISTDIR"