bin/sequence_metadata/get_unique_attributes.sh

   1 #! /usr/bin/env bash
   2
   3 # This script will return a line-separated list of unique attribute keys in the last column
   4 # of the provided gff3 file
   5
   6 # Usage ./get_unique_attributes.sh <infile>
   7
   8 if [ "$#" -ne 1 ]; then
   9     echo "Usage: $0 <infile>"
  10     exit 1
  11 fi
  12
  13 attributes=$(awk -F $'\t' '{print $9}' "$1")
  14 keys=$(echo "$attributes" | grep -o "\([^=;]\+\)=" | cut -d '=' -f 1)
  15 echo "$keys" | sort | uniq