PGYI fkey checker

checkfkey.sh

#!/usr/bin/env bash

# checks pgyi dataset for fkey integrity
# will print out any offending records
# usage: bash ./fkeycheck.sh <csv_data_folder>
# example: bash ./fkeycheck.sh ./examples/pgyi/data

wd=$1

plot=$wd/plot.csv
plot_measurement=$wd/plot_measurement.csv
trees=$wd/trees.csv
trees_measurement=$wd/trees_measurement.csv
treatment=$wd/treatment.csv
disturbance=$wd/disturbance.csv
regeneration=$wd/regeneration.csv
photo_avi=$wd/photo_avi.csv

plot_childs=($plot_measurement $trees $treatment $disturbance $regeneration $photo_avi)

check(){
    awk -F, "NR==FNR{ k[$2]=1; next; } NF{ if(!k[$4]) print; }" $1 $3
}

for child in "${plot_childs[@]}"
do
    check $plot '$1 $2' $child '$1 $2'
done

check $trees '$1 $2 $3' $trees_measurement '$1 $2 $4'