use getopts to parse input

README.md

@@ -16,25 +16,22 @@ gnuplot (www.gnuplot.info/)
 
 ## usage:
 ```
-${SRC_DIR}/recursive_gmconvert.sh MAP_NAME THRESHOLD n N i0 SERIAL
+${SRC_DIR}/recursive_gmconvert.sh -f map_filename -t threshold -n num_gaussians -N num_iterations [-i first_iteration] [-s]
 ```
-
-`MAP_NAME`: the file name of the input EM map
-
-`THRESHOLD`: the density threshold
-
-`n`: number of gaussians per sub-process. 2 or 4 is a good guess.
-
-`N`: number recursion levels.
-
-`i0`: initial recursion level (default: 1)
-
-`SERIAL`: if set to 1, uses the serial implementation (default: 0)
+Required arguments:
+`-f map_filename`: the file name of the input EM map
+`-t threshold`: the density threshold
+`-n num_gaussians`: number of gaussians per sub-process
+`-N num_iterations`: number of recursion levels
+Optional arguments:
+`-i first_iteration`: initial recursion level (defaults to 1)
+`-s`: enable serial mode
+`-h`: display this message
 
 The script creates a sub-directory (called `i`) for each recursion level `i`, and the output files are called `i/i.gmm` and `i_imp.gmm`.
 `i/i.gmm` contains the gmm in `gmconvert` format, and `i_imp.gmm` contains the gmm in `IMP` format (the conversion is handeld by `gmconvert2imp.sh`), which can be read in IMP using `IMP.isd.gmm_tools.decorate_gmm_from_text` function.
 
-Unless you set SERIAL to 1, all the scripts assume that you are running a cluster with the `slurm` queuing system.
+Unless you enable serial mode (`-s` flag), all the scripts assume that you are running a cluster with the `slurm` queuing system.
 
 ## References
 
@@ -54,4 +51,4 @@ http://www.cell.com/biophysj/fulltext/S0006-3495%2808%2978604-1
 
 G. Tang, L. Peng, P.R. Baldwin, D.S. Mann, W. Jiang, I. Rees & S.J. Ludtke. 
 
-(2007) J Struct Biol. 157, 38-46. PMID: 16859925 
\ No newline at end of file
+(2007) J Struct Biol. 157, 38-46. PMID: 16859925 

recursive_gmconvert.sh

 #!/bin/zsh
 
-profile_cmd="time"
-
-map_name=$1
-threshold=$2
-n_gaussians=$3
-N=$4
-MaxArraySize=100000
-
-get_max_jobs(){
-	echo ${MaxArraySize}
+usage() {
+	echo >&2 \
+	"usage: recursive_gmconvert.sh -f map_filename -t threshold -n num_gaussians -N num_iterations [-i first_iteration] [-s]
+Required arguments:
+-f map_filename: the file name of the input EM map
+-t threshold: the density threshold
+-n num_gaussians: number of gaussians per sub-process
+-N num_iterations: number of recursion levels
+Optional arguments:
+-i first_iteration: initial recursion level (defaults to 1)
+-s: enable serial mode
+-h: display this message"
 }
 
+#defaults
+map_name=
+threshold=
+n_gaussians=
+N=
 i0=1
-if [ -n "$5" ]
-then
-	i0=$5
-fi
+serial=0
 
-echo $i0
+while getopts f:t:n:N:i:sh opt
+do
+    case "$opt" in
+      f)  map_name="$OPTARG";;
+			t)  threshold="$OPTARG";;
+			n)  n_gaussians="$OPTARG";;
+			N)  N="$OPTARG";;
+			i)  i0="$OPTARG";;
+			s)  serial=1;;
+			h)  usage
+					exit ;;
+      \?)	# unknown flag
+      	  echo >&2 \
+					usage
+				  exit 1;;
+    esac
+done
 
-serial=0
-if [ -n "$6" ]
-then 
-	serial=$6
+#check that necessary options were set
+if [[ ! -e "$map_name" ]] || [[ -z "$threshold" ]] || [[ -z "$n_gaussians" ]] || [[ -z "$N" ]]
+then
+	usage
+	exit 1
 fi
 
+MaxArraySize=100000
+get_max_jobs(){
+	echo ${MaxArraySize}
+}
+profile_cmd="time"
+
 bindir=${0:h}
 impdir=~/imp-fast/
 gmconvert=${bindir}/gmconvert/gmconvert
@@ -40,7 +67,10 @@ do
 	n_jobs=1
 	if ((i==1))
 	then
-		${gmconvert} -imap ${map_name} -zth ${threshold} -oimap threshold.map -ogmm /dev/null -ng 0
+		if [[ ! -e threshold.map ]]
+		then
+			${gmconvert} -imap ${map_name} -zth ${threshold} -oimap threshold.map -ogmm /dev/null -ng 0
+	  fi
 		echo ${profile_cmd} ${gmconvert} -imap ${map_name} -ogmm $n/${n}_0.gmm -ng ${n_gaussians} -zth ${threshold}
 		echo ${gmconvert}  -igmm $n/${n}_0.gmm -imap ${map_name} -omap /dev/null
 	else