#!/bin/bash

root=`dirname $0`

url38="ftp://ftp.ncbi.nlm.nih.gov/genbank/genomes/Eukaryotes/vertebrates_mammals/Homo_sapiens/GRCh38/seqs_for_alignment_pipelines/GCA_000001405.15_GRCh38_full_analysis_set.fna.gz"
url37d5="ftp://ftp.ncbi.nlm.nih.gov/1000genomes/ftp/technical/reference/phase2_reference_assembly_sequence/hs37d5.fa.gz"

if [ $# -eq 0 ]; then
	echo "Usage: $0 <hs38|hs38a|hs38d6|hs37|hs37d5>"
	exit 1;
fi

if [ $1 == "hs38d6" ]; then
	(wget -O- $url38 | gzip -dc; cat $root/resource-GRCh38/hs38d6-extra.fa) > $1.fa
	[ ! -f $1.fa.alt ] && cp $root/resource-GRCh38/hs38d6.fa.alt $1.fa.alt
elif [ $1 == "hs38a" ]; then
	wget -O- $url38 | gzip -dc > $1.fa
	[ ! -f $1.fa.alt ] && grep _alt $root/resource-GRCh38/hs38d6.fa.alt > $1.fa.alt
elif [ $1 == "hs38" ]; then
	wget -O- $url38 | gzip -dc | awk '/^>/{f=/_alt/?0:1}f' > $1.fa
elif [ $1 == "hs37d5" ]; then
	wget -O- $url37d5 | gzip -dc > $1.fa 2>/dev/null
elif [ $1 == "hs37" ]; then
	wget -O- $url37d5 | gzip -dc 2>/dev/null | awk '/^>/{f=/>hs37d5/?0:1}f' > $1.fa
else
	echo "ERROR: unknown genome build"
fi

[ ! -f $1.fa.bwt ] && echo -e "\nPlease run 'bwa index $1.fa'...\n"