#--------------------- Import Foreign Format  ( 9/02/09) -------------------
item:Import Foreign Format
#itemmethod:cp $INPUTFILE OUTFILE.tmp; readseq -a -fGenBank -o=OUTPUTFILE OUTFILE.tmp; $RM_CMD -f OUTFILE.tmp
# FASTA files produced by NCBI have definition lines in the form
# >gi|169079|gb|M18250.1|PEADRRB Pea (P.sativum) disease resistance
# whereas most FASTA files have a definition line like
# >PEADRRB - Pea (P.sativum) disease resistance
# Many programs cannot read the NCBI style, or truncate the lines at
# unpredictable places. The command below uses sed to change the second
# pipe character to a blank so that the gi number is used as a name
# and the rest of the line is read as the definition.
# >gi|169079 |gb|M18250.1|PEADRRB Pea (P.sativum) disease resistance
# This way, at least we have the gi number, and know it is a gi number
# This should not affect any other files read by readseq, other than
# NCBI generated files.
itemmethod:cat $INPUTFILE | sed 's/^\(>gi|[0-9][0-9]*\)\(\|\)\(.*\)/\1 \3/' > OUTFILE.tmp; readseq -a -fGenBank -o=OUTPUTFILE OUTFILE.tmp; $RM_CMD -f OUTFILE.tmp
itemhelp:readseq.help
itemopen:gde_help_viewer.csh

arg:INPUTFILE
argtype:text
#@argtype:file_chooser
arglabel:Name of foreign file?

out:OUTPUTFILE
outformat:genbank