#!/bin/bash
read -p "Enter a directory: " user_directory
read -p "Enter a file type: " user_type
read -p "Enter the parameter of interest: " user_parameter
found_files=$(find $user_directory -name $user_type -print | xargs)
file_list=$(grep -H $user_parameter $found_files -R | cut -d: -f1)
for f in $file_list
do
        #Remove the portion of the header with 0-5 columns
        awk -F',' 'NF>5' $f > /datashare/script_output_temp/${f##*/}"_modified.csv"
done
file_list2=$(find /datashare/script_output_temp -name *.csv -print | xargs)
read -p "Threshold value for parameter: " user_threshold
#Search the first line for the parameter and return that column number
for f in $file_list2
do
        #echo "Processing " $f
        #units=$(awk -F',' -v col=$user_parameter 'NR==1{for(i=1;i<=NF;i++){if($i==col){c=i;break}}} NR==2{print $c}' $f)
        #awk -F',' -v col=$user_parameter 'NR==1{for(i=1;i<=NF;i++){if($i==col){c=i;break}}} NR==2{print $c}' $f > /datashare/script_output_temp/units.dat
        sed -i '2d' $f
        awk -F',' -v col=$user_parameter 'NR==1{for(i=1;i<=NF;i++){if($i==col){break}}}END{if($i>=$user_threshold){print FILENAME}}' $f >> /datashare/script_output_temp/list.csv
        #echo $col_num
        #awk '{if($col_num>=$user_threshold){print FILENAME}}' $f >> /datashare/script_output_temp/list.csv
done
sort -u /datashare/script_output_temp/list.csv > /datashare/script_output_temp/list.dat