for file in $diff_file_list
do
# replace any ? with $current_date and replace any % with $file
formatted_output_filename=$(echo $output_filename | sed "s|?|$current_date|g" | sed "s|%|_$file|g")
$pig_bin_dir/pig -param preceding=$hdfs_hadoop_pre_dir/$file -param current=$hdfs_hadoop_cur_dir/$file -param output_added=$hdfs_hadoop_delta_dir/${file}_added -param output_removed=$hdfs_hadoop_delta_dir/${file}_removed -param delimiter=$delimiter diff.pig
[ $? -ne 0 ] && die "diff of data between $previous_date and $current_date using pig failed. exiting `basename $0` script"
$hadoop_bin_dir/hadoop dfs -cat $hdfs_hadoop_delta_dir/${file}_added/* | gzip > $file_output_dir/${formatted_output_filename}_added.gz
$hadoop_bin_dir/hadoop dfs -cat $hdfs_hadoop_delta_dir/${file}_removed/* | gzip > $file_output_dir/${formatted_output_filename}_removed.gz
[ $? -ne 0 ] && die "there was a problem gzipping ${formatted_output_filename}. exiting `basename $0` script"
[ $post_diff_script ] && ./$post_diff_script $source $previous_date $current_date
done
我只希望它来创建_removed.gz和_added.gz文件时,文件不为空bash脚本。 我试过在下面做这个,但是我的脚本有问题吗?
for file in $diff_file_list
do
# replace any ? with $current_date and replace any % with $file
formatted_output_filename=$(echo $output_filename | sed "s|?|$current_date|g" | sed "s|%|_$file|g")
$pig_bin_dir/pig -param preceding=$hdfs_hadoop_pre_dir/$file -param current=$hdfs_hadoop_cur_dir/$file -param output_added=$hdfs_hadoop_delta_dir/${file}_added -param output_removed=$hdfs_hadoop_delta_dir/${file}_removed -param delimiter=$delimiter diff.pig
[ $? -ne 0 ] && die "diff of data between $previous_date and $current_date using pig failed. exiting `basename $0` script"
if [[ -s $hdfs_hadoop_delta_dir/${file}_added/* ]] ; then
echo "$hdfs_hadoop_delta_dir/${file}_added/* has data."
$hadoop_bin_dir/hadoop dfs -cat $hdfs_hadoop_delta_dir/${file}_added/* | gzip > $file_output_dir/${formatted_output_filename}_added.gz
$hadoop_bin_dir/hadoop dfs -cat $hdfs_hadoop_delta_dir/${file}_removed/* | gzip > $file_output_dir/${formatted_output_filename}_removed.gz
else
echo "$hdfs_hadoop_delta_dir/${file}_added/*is empty."
fi ;
[ $? -ne 0 ] && die "there was a problem gzipping ${formatted_output_filename}. exiting `basename $0` script"
[ $post_diff_script ] && ./$post_diff_script $source $previous_date $current_date
done
我的眼睛受伤... –
是的,你的脚本在向我大喊。 – trojanfoe
一些笔记。首先,尽管'[x] && y'起作用,但将它写为'if [x];那么y; fi'。另外,尝试在多行中打破很长的一行。这也有助于对齐某些东西,例如,许多'-param'选项发送到'pig'(在你分成多行后)。最后,当你说“有什么问题”时,你应该更具体。究竟发生了什么? – Shahbaz