Question

I have a bash script with the following lines

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

I only want it to create the _removed.gz and _added.gz files when the file is not empty.
I’ve tried to do this below but there is something wrong with my script?

    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

Answer 1

if [[ -s file ]]
then
    do_file_creation
fi

or

for f in dir/*
do
    if [[ -s $f ]]
    then
        do_file_creation
    fi
done

Use lower case or mixed case variable names.

Use if instead of [[ ]] &&

Use indentation.