Mercurial > repos > rliterman > csp2
diff CSP2/CSP2_env/env-d9b9114564458d9d-741b3de822f2aaca6c6caa4325c4afce/opt/bbmap-39.01-1/shuffle2.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/shuffle2.sh Tue Mar 18 17:55:14 2025 -0400 @@ -0,0 +1,80 @@ +#!/bin/bash + +usage(){ +echo " +Written by Brian Bushnell +Last modified August 11, 2021 + +Description: Reorders reads randomly, keeping pairs together. +Unlike Shuffle, Shuffle2 can write temp files to handle large datasets. + +Usage: shuffle2.sh in=<file> out=<file> + +Standard parameters: +in=<file> The 'in=' flag is needed if the input file is not the first parameter. 'in=stdin' will pipe from standard in. +in2=<file> Use this if 2nd read of pairs are in a different file. +out=<file> The 'out=' flag is needed if the output file is not the second parameter. 'out=stdout' will pipe to standard out. +out2=<file> Use this to write 2nd read of pairs to a different file. +overwrite=t (ow) Set to false to force the program to abort rather than overwrite an existing file. +ziplevel=2 (zl) Set to 1 (lowest) through 9 (max) to change compression level; lower compression is faster. +int=auto (interleaved) Set to t or f to override interleaving autodetection. + +Processing parameters: +shuffle Randomly reorders reads (default). +seed=-1 Set to a positive number for deterministic shuffling. + +Java Parameters: +-Xmx This will set Java's memory usage, overriding autodetection. + -Xmx20g will specify 20 gigs of RAM, and -Xmx200m will specify 200 megs. + The max is typically 85% of physical memory. +-eoom This flag will cause the process to exit if an out-of-memory + exception occurs. Requires Java 8u92+. +-da Disable assertions. + +Please contact Brian Bushnell at bbushnell@lbl.gov if you encounter any problems. +" +} + +#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="-Xmx2g" +z2="-Xms2g" +set=0 + +if [ -z "$1" ] || [[ $1 == -h ]] || [[ $1 == --help ]]; then + usage + exit +fi + +calcXmx () { + source "$DIR""/calcmem.sh" + setEnvironment + parseXmx "$@" + if [[ $set == 1 ]]; then + return + fi + freeRam 2000m 84 + z="-Xmx${RAM}m" + z2="-Xms${RAM}m" +} +calcXmx "$@" + +shuffle() { + local CMD="java $EA $EOOM $z -cp $CP sort.Shuffle2 $@" + echo $CMD >&2 + eval $CMD +} + +shuffle "$@"