bin/sequence_metadata/preprocess_featureprop_json.sh

   1 #! /usr/bin/env bash
   2
   3 # This shell script is called by the CXGN::Genotype::SequenceMetadata verify function and
   4 # is used to preprocess the gff3 file for the featureprop_json table.  It will:
   5 # 1) remove comment lines from the file
   6 # 2) sort the gff3 file by the seqid and start columns (1, 4)
   7
   8 # Usage: ./process_featurprop_json.sh <infile> <outfile>
   9
  10 if [ "$#" -ne 2 ]; then
  11     echo "Usage: $0 <infile> <outfile>"
  12     exit 1
  13 fi
  14
  15 grep -o '^[^#]*' "$1" | sort -t$'\t' -k1,1 -k4n,4 > "$2"