From 56b23d1838daf3757e7f6f5cac8abf3f295a2c15 Mon Sep 17 00:00:00 2001
From: Yu Yang <yuyang18@baidu.com>
Date: Mon, 7 Nov 2016 23:44:33 -0600
Subject: [PATCH] Fix macOS quick start preprocess script. (#390)

* Use `gshuf` instead of `shuf` in macOS
* Fix #388
---
 demo/quick_start/preprocess.sh | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/demo/quick_start/preprocess.sh b/demo/quick_start/preprocess.sh
index fe2acbbd748..58a72147c5e 100755
--- a/demo/quick_start/preprocess.sh
+++ b/demo/quick_start/preprocess.sh
@@ -21,14 +21,21 @@
 set -e
 
 export LC_ALL=C
+UNAME_STR=`uname`
+
+if [[ ${UNAME_STR} == 'Linux' ]]; then
+  SHUF_PROG='shuf'
+else
+  SHUF_PROG='gshuf'
+fi
 
 mkdir -p data/tmp
 python preprocess.py -i data/reviews_Electronics_5.json.gz
 # uniq and shuffle
 cd data/tmp
 echo 'uniq and shuffle...'
-cat pos_*|sort|uniq|shuf> pos.shuffed
-cat neg_*|sort|uniq|shuf> neg.shuffed
+cat pos_*|sort|uniq|${SHUF_PROG}> pos.shuffed
+cat neg_*|sort|uniq|${SHUF_PROG}> neg.shuffed
 
 min_len=`sed -n '$=' neg.shuffed`
 test_num=$((min_len/10))
@@ -42,8 +49,8 @@ head -n$train_num neg.shuffed >train.neg
 tail -n$test_num pos.shuffed >test.pos
 tail -n$test_num neg.shuffed >test.neg
 
-cat train.pos train.neg|shuf>../train.txt
-cat test.pos test.neg|shuf>../test.txt
+cat train.pos train.neg | ${SHUF_PROG} >../train.txt
+cat test.pos test.neg | ${SHUF_PROG} >../test.txt
 
 cd -
 echo 'data/train.txt' > data/train.list
-- 
GitLab