diff CSP2/CSP2_env/env-d9b9114564458d9d-741b3de822f2aaca6c6caa4325c4afce/opt/bbmap-39.01-1/statswrapper.sh @ 69:33d812a61356

planemo upload commit 2e9511a184a1ca667c7be0c6321a36dc4e3d116d
author jpayne
date Tue, 18 Mar 2025 17:55:14 -0400
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/CSP2/CSP2_env/env-d9b9114564458d9d-741b3de822f2aaca6c6caa4325c4afce/opt/bbmap-39.01-1/statswrapper.sh	Tue Mar 18 17:55:14 2025 -0400
@@ -0,0 +1,74 @@
+#!/bin/bash
+
+usage(){
+echo "
+Written by Brian Bushnell
+Last modified August 1, 2017
+
+Description:  Runs stats.sh on multiple assemblies to produce one output line per file.
+
+Usage:  statswrapper.sh in=<input file>
+
+Parameters:
+in=<file>       Specify the input fasta file, or stdin.  For multiple files a, b, and c: 'statswrapper.sh in=a,b,c'.
+                'in=' may be omitted if this is the first arg, and asterisks may be used; e.g. statswrapper.sh *.fa
+gc=<file>       Writes ACGTN content per scaffold to a file.
+gchist=<file>   Filename to output scaffold gc content histogram.
+gcbins=<200>    Number of bins for gc histogram.
+n=<10>          Number of contiguous Ns to signify a break between contigs.
+k=<13>          Estimate memory usage of BBMap with this kmer length.
+minscaf=<0>     Ignore scaffolds shorter than this.
+n_=<t>          This flag will prefix the terms 'contigs' and 'scaffolds' with 'n_' in formats 3-6.
+addname=<t>     Adds a column for input file name, for formats 3-6.
+
+format=<1 through 6>   Format of the stats information.  Default is format=3.
+   format=1 uses variable units like MB and KB, and is designed for compatibility with existing tools.
+   format=2 uses only whole numbers of bases, with no commas in numbers, and is designed for machine parsing.
+   format=3 outputs stats in 2 rows of tab-delimited columns: a header row and a data row.
+   format=4 is like 3 but with scaffold data only.
+   format=5 is like 3 but with contig data only.
+   format=6 is like 3 but the header starts with a #.
+
+gcformat=<1 or 2>   Select GC output format.
+   gcformat=1:   name   start   stop   A   C   G   T   N   GC
+   gcformat=2:   name   GC
+   Note that in gcformat 1, A+C+G+T=1 even when N is nonzero.
+"
+}
+
+#This block allows symlinked shellscripts to correctly set classpath.
+pushd . > /dev/null
+DIR="${BASH_SOURCE[0]}"
+while [ -h "$DIR" ]; do
+  cd "$(dirname "$DIR")"
+  DIR="$(readlink "$(basename "$DIR")")"
+done
+cd "$(dirname "$DIR")"
+DIR="$(pwd)/"
+popd > /dev/null
+
+#DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )/"
+CP="$DIR""current/"
+
+z="-Xmx200m"
+set=0
+
+if [ -z "$1" ] || [[ $1 == -h ]] || [[ $1 == --help ]]; then
+	usage
+	exit
+fi
+
+calcXmx () {
+	source "$DIR""/calcmem.sh"
+	setEnvironment
+	parseXmx "$@"
+}
+calcXmx "$@"
+
+stats() {
+	local CMD="java $EA $EOOM $z -cp $CP jgi.AssemblyStatsWrapper format=3 $@"
+	echo $CMD >&2
+	eval $CMD
+}
+
+stats "$@"