#!/bin/sh
pg=`basename $0`

TMP=/tmp/NCBI_assemblies.tmp/
WEB=/www/data/assemblies
URL=ftp://ftp.ncbi.nlm.nih.gov/genomes/GENOME_REPORTS/eukaryotes.txt

usage() {
    echo USAGE :
    echo "       Generate assembly metrics of NCBI assemblies"
    echo "         First argument is the keyword for assembly selection"
    exit 1
}

NAME=
len=0

while [ $1 ]
do
        case $1 in
                "-h")
                        usage ;;
                *)
                if [ "$NAME" = "" ]
                        then NAME=$1
	        fi
    	esac
    	shift
done

if [ "$NAME" = "" ]; then
    echo "[Error] Need to provide a keyword for the assembly selection : Plants, Insects, Mammals, ...";
    echo "See $pg -h for more details."
    exit 0;
fi;

echo "Create and move to temporary directory..."
mkdir -p $TMP
cd $TMP

echo "Download assembly file from NCBI : $URL ..."
curl $URL > $TMP/eukaryotes.txt
cat $TMP/eukaryotes.txt | awk 'BEGIN { FS="\t"; } { OFS="\t"; gsub (" ", "", $6); print $0; }' | grep $NAME > $TMP/eukaryotes.$NAME.txt
dos2unix $TMP/eukaryotes.$NAME.txt

echo "Download new assemblies and compute stats..."
if [ ! -f $TMP/$NAME.known ] 
    then touch $TMP/$NAME.known
fi
assembly_stats.pl -list $TMP/eukaryotes.$NAME.txt -prev $TMP/$NAME.known -outdir $TMP/${NAME}_genomes -force
dos2unix $TMP/${NAME}_genomes/assembly_stats

echo "Generate json file..."
cat $TMP/${NAME}_genomes/assembly_stats | grep -v \" | awk 'BEGIN { FS=";"; print "["; first=1; } $22!="" { if(!first) { print "  ,"; } first=0;  i=1; while(i<=NF) { if($i=="") { $i="-1"; } i++; } print "  {"; print "    \"organism\": \""$1"\","; print "    \"assemblyID\": \""$2"\","; print "    \"cumulativeSize\": "$3","; print "    \"numberOfScaffolds\": "$4","; print "    \"maxScaffoldSize\": "$5","; print "    \"MinScaffoldSize\": "$6","; print "    \"avgScaffoldSize\": "$7","; print "    \"scaffoldN50\": "$8","; print "    \"scaffoldL50\": "$9","; print "    \"scaffoldN80\": "$10","; print "    \"scaffoldL80\": "$11","; print "    \"scaffoldN90\": "$12","; print "    \"scaffoldL90\": "$13","; print "    \"nbN\": "$14","; print "    \"percentN\": "$15","; print "    \"cumulativeSizeContig\": "$16","; print "    \"numberOfContigs\": "$17","; print "    \"maxContigSize\": "$18","; print "    \"minContigSize\": "$19","; print "    \"avgContigSize\": "$20","; print "    \"contigN50\": "$21","; print "    \"contigL50\": "$22","; print "    \"contigN80\": "$23","; print "    \"contigL80\": "$24","; print "    \"contigN90\": "$25","; print "    \"contigL90\": "$26","; print "    \"updateDate\": \""$27"\","; print "    \"url\": \""$28"\","; print "    \"bioP\": \""$29"\","; print "    \"group\": \""$30"\","; print "    \"subGroup\": \""$31"\","; print "    \"gSize\": "$32","; print "    \"modifyDate\": \""$33"\","; print "    \"status\": \""$34"\","; print "    \"center\": \""$35"\","; print "    \"bioS\": \""$36"\""; print "  }"; } END { print "]"; }'  | sed "s/%//" > $TMP/${NAME}_genomes/assembly_stats.json

echo "Update files..."
cp $TMP/${NAME}_genomes/assembly_stats.json $WEB/$NAME-assembly-stats.json
cp $TMP/${NAME}_genomes/assembly_stats $WEB/${NAME}.known
cp $TMP/${NAME}_genomes/assembly_stats $TMP/${NAME}.known