From 89e19c75e80fd9523af5eb208cc13674db7a847f Mon Sep 17 00:00:00 2001
From: Albert Chu <chu11@llnl.gov>
Date: Mon, 16 Nov 2015 16:43:42 -0800
Subject: [PATCH 1/2] Support environment variable MAHOUT_WORK_DIR to allow
 users to specify an alternate temporary directory in examples.

---
 examples/bin/classify-20newsgroups.sh    | 6 +++++-
 examples/bin/classify-wikipedia.sh       | 6 +++++-
 examples/bin/cluster-reuters.sh          | 6 +++++-
 examples/bin/cluster-syntheticcontrol.sh | 6 +++++-
 examples/bin/factorize-movielens-1M.sh   | 9 +++++++--
 examples/bin/factorize-netflix.sh        | 6 +++++-
 6 files changed, 32 insertions(+), 7 deletions(-)

diff --git a/examples/bin/classify-20newsgroups.sh b/examples/bin/classify-20newsgroups.sh
index c58e9a02f4..6d7ab45d29 100755
--- a/examples/bin/classify-20newsgroups.sh
+++ b/examples/bin/classify-20newsgroups.sh
@@ -36,7 +36,11 @@ START_PATH=`pwd`
 # Set commands for dfs
 source ${START_PATH}/set-dfs-commands.sh
 
-WORK_DIR=/tmp/mahout-work-${USER}
+if [[ -z "$MAHOUT_WORK_DIR" ]]; then
+  WORK_DIR=/tmp/mahout-work-${USER}
+else
+  WORK_DIR=$MAHOUT_WORK_DIR
+fi
 algorithm=( cnaivebayes-MapReduce naivebayes-MapReduce cnaivebayes-Spark naivebayes-Spark sgd clean)
 if [ -n "$1" ]; then
   choice=$1
diff --git a/examples/bin/classify-wikipedia.sh b/examples/bin/classify-wikipedia.sh
index 68487dcc75..686c99dacb 100755
--- a/examples/bin/classify-wikipedia.sh
+++ b/examples/bin/classify-wikipedia.sh
@@ -42,7 +42,11 @@ START_PATH=`pwd`
 # Set commands for dfs
 source ${START_PATH}/set-dfs-commands.sh
 
-WORK_DIR=/tmp/mahout-work-wiki
+if [[ -z "$MAHOUT_WORK_DIR" ]]; then
+  WORK_DIR=/tmp/mahout-work-wiki
+else
+  WORK_DIR=$MAHOUT_WORK_DIR
+fi
 algorithm=( CBayes BinaryCBayes clean)
 if [ -n "$1" ]; then
   choice=$1
diff --git a/examples/bin/cluster-reuters.sh b/examples/bin/cluster-reuters.sh
index d53aa00d2a..6c42ab9a76 100755
--- a/examples/bin/cluster-reuters.sh
+++ b/examples/bin/cluster-reuters.sh
@@ -43,7 +43,11 @@ if [ ! -e $MAHOUT ]; then
   exit 1
 fi
 
-WORK_DIR=/tmp/mahout-work-${USER}
+if [[ -z "$MAHOUT_WORK_DIR" ]]; then
+  WORK_DIR=/tmp/mahout-work-${USER}
+else
+  WORK_DIR=$MAHOUT_WORK_DIR
+fi
 
 algorithm=( kmeans fuzzykmeans lda streamingkmeans clean)
 if [ -n "$1" ]; then
diff --git a/examples/bin/cluster-syntheticcontrol.sh b/examples/bin/cluster-syntheticcontrol.sh
index eab62be39f..5e1240f553 100755
--- a/examples/bin/cluster-syntheticcontrol.sh
+++ b/examples/bin/cluster-syntheticcontrol.sh
@@ -48,7 +48,11 @@ START_PATH=`pwd`
 # Set commands for dfs
 source ${START_PATH}/set-dfs-commands.sh
 
-WORK_DIR=/tmp/mahout-work-${USER}
+if [[ -z "$MAHOUT_WORK_DIR" ]]; then
+  WORK_DIR=/tmp/mahout-work-${USER}
+else
+  WORK_DIR=$MAHOUT_WORK_DIR
+fi
 
 echo "creating work directory at ${WORK_DIR}"
 mkdir -p ${WORK_DIR}
diff --git a/examples/bin/factorize-movielens-1M.sh b/examples/bin/factorize-movielens-1M.sh
index 735e425a3f..29730e1d80 100755
--- a/examples/bin/factorize-movielens-1M.sh
+++ b/examples/bin/factorize-movielens-1M.sh
@@ -43,7 +43,12 @@ fi
 export MAHOUT_LOCAL=true
 MAHOUT="$MAHOUT_HOME/bin/mahout"
 
-WORK_DIR=/tmp/mahout-work-${USER}
+if [[ -z "$MAHOUT_WORK_DIR" ]]; then
+  WORK_DIR=/tmp/mahout-work-${USER}
+else
+  WORK_DIR=$MAHOUT_WORK_DIR
+fi
+
 echo "creating work directory at ${WORK_DIR}"
 mkdir -p ${WORK_DIR}/movielens
 
@@ -77,4 +82,4 @@ shuf ${WORK_DIR}/recommendations/part-m-00000 |head
 echo -e "\n\n"
 
 echo "removing work directory"
-rm -rf ${WORK_DIR}
\ No newline at end of file
+rm -rf ${WORK_DIR}
diff --git a/examples/bin/factorize-netflix.sh b/examples/bin/factorize-netflix.sh
index 856f775ac9..26faf66a53 100755
--- a/examples/bin/factorize-netflix.sh
+++ b/examples/bin/factorize-netflix.sh
@@ -45,7 +45,11 @@ fi
 
 MAHOUT="../../bin/mahout"
 
-WORK_DIR=/tmp/mahout-work-${USER}
+if [[ -z "$MAHOUT_WORK_DIR" ]]; then
+  WORK_DIR=/tmp/mahout-work-${USER}
+else
+  WORK_DIR=$MAHOUT_WORK_DIR
+fi
 
 START_PATH=`pwd`
 

From 599101083ab7d31600b8c93b2efd8cea4c0a30bf Mon Sep 17 00:00:00 2001
From: Albert Chu <chu11@llnl.gov>
Date: Thu, 19 Nov 2015 13:46:05 -0800
Subject: [PATCH 2/2] In examples, specify -p option to HDFS -mkdir option when
 potentially necessary.

---
 examples/bin/classify-20newsgroups.sh | 2 +-
 examples/bin/classify-wikipedia.sh    | 2 +-
 examples/bin/cluster-reuters.sh       | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/examples/bin/classify-20newsgroups.sh b/examples/bin/classify-20newsgroups.sh
index 6d7ab45d29..f47d5c5249 100755
--- a/examples/bin/classify-20newsgroups.sh
+++ b/examples/bin/classify-20newsgroups.sh
@@ -109,7 +109,7 @@ if  ( [ "x$alg" == "xnaivebayes-MapReduce" ] ||  [ "x$alg" == "xcnaivebayes-MapR
     echo "Copying 20newsgroups data to HDFS"
     set +e
     $DFSRM ${WORK_DIR}/20news-all
-    $DFS -mkdir ${WORK_DIR}
+    $DFS -mkdir -p ${WORK_DIR}
     $DFS -mkdir ${WORK_DIR}/20news-all
     set -e
     if [ $HVERSION -eq "1" ] ; then
diff --git a/examples/bin/classify-wikipedia.sh b/examples/bin/classify-wikipedia.sh
index 686c99dacb..8a7889f0a5 100755
--- a/examples/bin/classify-wikipedia.sh
+++ b/examples/bin/classify-wikipedia.sh
@@ -114,7 +114,7 @@ if [ "x$alg" == "xCBayes" ] || [ "x$alg" == "xBinaryCBayes" ] ; then
     echo "Copying wikipedia data to HDFS"
     set +e
     $DFSRM ${WORK_DIR}/wikixml
-    $DFS -mkdir ${WORK_DIR}
+    $DFS -mkdir -p ${WORK_DIR}
     set -e
     $DFS -put ${WORK_DIR}/wikixml ${WORK_DIR}/wikixml
   fi
diff --git a/examples/bin/cluster-reuters.sh b/examples/bin/cluster-reuters.sh
index 6c42ab9a76..49f6c94ccd 100755
--- a/examples/bin/cluster-reuters.sh
+++ b/examples/bin/cluster-reuters.sh
@@ -102,7 +102,7 @@ if [ ! -e ${WORK_DIR}/reuters-out-seqdir ]; then
         set +e
         $DFSRM ${WORK_DIR}/reuters-sgm
         $DFSRM ${WORK_DIR}/reuters-out
-        $DFS -mkdir ${WORK_DIR}/
+        $DFS -mkdir -p ${WORK_DIR}/
         $DFS -mkdir ${WORK_DIR}/reuters-sgm
         $DFS -mkdir ${WORK_DIR}/reuters-out
         $DFS -put ${WORK_DIR}/reuters-sgm ${WORK_DIR}/reuters-sgm