#!/bin/bash -e
wget --no-verbose ftp://ftp.ensembl.org/pub/
grep Link index.html |awk -F'"' '{print $2}' > getlist.tmp
rm -f index.html*
for i in `cat getlist.tmp ` ; do wget --no-verbose $i/data/mysql/ ; done
grep core index*|awk -F'"' '{print $2}' | awk -F'/' '{print $8}' | awk -F_ '{print $1"_"$2,$3"_"$4"_"$5,"/cluster/store8/ensembl/"$1"_"$2"_"$4"_"$5}' |sort  > loadScript.tmp
#extract ucsc databases
hgsql hgcentraltest -N -B -e "select max(name), scientificName from dbDb where active = 1 group by organism" | awk '{print tolower($2"_"$3),$1}' |sort >dbdb.tmp
echo '#!/bin/bash -e' > loadScript
join loadScript.tmp dbdb.tmp | awk '{print "hgLoadEnsembl",$1,$2,$3,$4}' >> loadScript    
chmod +x loadScript

#rm -f index*
echo "edit loadScript to add database name"
