debian/control

@@ -18,7 +18,8 @@ Homepage: https://github.com/GATB/simka
 
 Package: simka
 Architecture: any
-Depends: ${misc:Depends},
+Depends: ${shlibs:Depends},
+	 ${misc:Depends},
          libgatbcore2
 Description: comparative metagenomics method dedicated to NGS datasets
  Simka is a de novo comparative metagenomics tool. Simka represents each

debian/createmanpages

+#!/bin/sh
+MANDIR=debian/mans
+mkdir -p $MANDIR
+
+VERSION=`dpkg-parsechangelog | awk '/^Version:/ {print $2}' | sed -e 's/^[0-9]*://' -e 's/-.*//' -e 's/[+~]dfsg$//'`
+NAME=`grep "^Description:" debian/control | sed 's/^Description: *//' | head -n1`
+PROGNAME=`grep "^Package:" debian/control | sed 's/^Package: *//' | head -n1`
+
+AUTHOR=".SH AUTHOR\nThis manpage was written by $DEBFULLNAME for the Debian distribution and
+can be used for any other usage of the program.
+"
+
+progname=simka
+help2man --no-info --no-discard-stderr --help-option="-h" \
+         --name="$NAME" \
+            --version-string="$VERSION" ${progname} > $MANDIR/${progname}.1
+echo $AUTHOR >> $MANDIR/${progname}.1
+
+progname=simkaCount
+help2man --no-info --no-discard-stderr --help-option="-h" \
+         --name="$NAME" \
+            --version-string="$VERSION" ${progname} > $MANDIR/${progname}.1
+echo $AUTHOR >> $MANDIR/${progname}.1
+
+progname=simkaCountProcess
+help2man --no-info --no-discard-stderr --help-option="-h" \
+         --name="$NAME" \
+            --version-string="$VERSION" ${progname} > $MANDIR/${progname}.1
+echo $AUTHOR >> $MANDIR/${progname}.1
+
+progname=simkaMerge
+help2man --no-info --no-discard-stderr --help-option="-h" \
+         --name="$NAME" \
+            --version-string="$VERSION" ${progname} > $MANDIR/${progname}.1
+echo $AUTHOR >> $MANDIR/${progname}.1
+
+progname=simkaMinCore
+help2man --no-info --no-discard-stderr --help-option="-h" \
+         --name="$NAME" \
+            --version-string="$VERSION" ${progname} > $MANDIR/${progname}.1
+echo $AUTHOR >> $MANDIR/${progname}.1
+
+progname=simkaMin
+help2man --no-info --no-discard-stderr --help-option="-h" \
+         --name="$NAME" \
+            --version-string="$VERSION" ${progname} > $MANDIR/${progname}.1
+echo $AUTHOR >> $MANDIR/${progname}.1
+
+progname=simkaMin_update
+help2man --no-info --no-discard-stderr --help-option="-h" \
+         --name="$NAME" \
+            --version-string="$VERSION" ${progname} > $MANDIR/${progname}.1
+echo $AUTHOR >> $MANDIR/${progname}.1
+
+echo "$MANDIR/*.1" > debian/manpages
+
+cat <<EOT
+Please enhance the help2man output.
+The following web page might be helpful in doing so:
+    http://liw.fi/manpages/
+EOT
+

debian/manpages

+debian/mans/*.1

debian/mans/simka.1

+.\" DO NOT MODIFY THIS FILE!  It was generated by help2man 1.47.8.
+.TH SIMKA "1" "September 2019" "simka 1.5.1" "User Commands"
+.SH NAME
+simka \- comparative metagenomics method dedicated to NGS datasets
+.SH DESCRIPTION
+ERROR: Unknown parameter '\-h'
+ERROR: Option '\-in' is mandatory
+ERROR: Option '\-out\-tmp' is mandatory
+ERROR: Option '\-in' is mandatory
+.PP
+[Simka options]
+.TP
+\fB\-in\fR
+(1 arg) :    input file of samples. One sample per line: id1: filename1...
+.TP
+\fB\-out\fR
+(1 arg) :    output directory for result files (distance matrices)  [default './simka_results']
+.TP
+\fB\-out\-tmp\fR
+(1 arg) :    output directory for temporary files
+.TP
+\fB\-keep\-tmp\fR
+(0 arg) :    keep temporary files
+.TP
+\fB\-data\-info\fR (0 arg) :
+compute (and display) information before running Simka, such as the number of reads per dataset
+.TP
+\fB\-verbose\fR
+(1 arg) :    verbosity level  [default '1']
+.TP
+\fB\-version\fR
+(0 arg) :    version
+.TP
+\fB\-help\fR
+(0 arg) :    help
+.IP
+[distance options]
+.TP
+\fB\-simple\-dist\fR
+(0 arg) :    compute all simple distances (Chord, Hellinger...)
+.TP
+\fB\-complex\-dist\fR (0 arg) :
+compute all complex distances (Jensen\-Shannon...)
+.IP
+[kmer options]
+.TP
+\fB\-kmer\-size\fR
+(1 arg) :    size of a kmer  [default '21']
+.TP
+\fB\-abundance\-min\fR
+(1 arg) :    min abundance a kmer need to be considered  [default '2']
+.TP
+\fB\-abundance\-max\fR
+(1 arg) :    max abundance a kmer can have to be considered  [default '999999999']
+.TP
+\fB\-kmer\-shannon\-index\fR (1 arg) :
+minimal Shannon index a kmer should have to be kept. Float in [0,2]  [default '0']
+.IP
+[read options]
+.TP
+\fB\-max\-reads\fR
+(1 arg) :    maximum number of reads per sample to process. Can be \fB\-1\fR: use all reads. Can be 0: estimate it  [default '\-1']
+.TP
+\fB\-min\-read\-size\fR
+(1 arg) :    minimal size a read should have to be kept  [default '0']
+.TP
+\fB\-min\-shannon\-index\fR (1 arg) :
+minimal Shannon index a read should have to be kept. Float in [0,2]  [default '0']
+.IP
+[core options]
+.TP
+\fB\-nb\-cores\fR
+(1 arg) :    number of cores  [default '0']
+.TP
+\fB\-max\-memory\fR (1 arg) :
+max memory (MB)  [default '5000']
+.TP
+\fB\-max\-count\fR
+(1 arg) :    maximum number of simultaneous counting jobs (a higher value improve execution time but increase temporary disk usage)  [default '']
+.TP
+\fB\-max\-merge\fR
+(1 arg) :    maximum number of simultaneous merging jobs (1 job = 1 core)  [default '']
+.IP
+[cluster options]
+.TP
+\fB\-count\-cmd\fR
+(1 arg) :    command to submit counting job  [default '']
+.TP
+\fB\-merge\-cmd\fR
+(1 arg) :    command to submit merging job  [default '']
+.TP
+\fB\-count\-file\fR (1 arg) :
+filename to the couting job template  [default '']
+.TP
+\fB\-merge\-file\fR (1 arg) :
+filename to the merging job template  [default '']
+.SH AUTHOR
+This manpage was written by Shayan Doust for the Debian distribution and can be used for any other usage of the program.

debian/mans/simkaCount.1

+.\" DO NOT MODIFY THIS FILE!  It was generated by help2man 1.47.8.
+.TH SIMKACOUNT "1" "September 2019" "simkaCount 1.5.1" "User Commands"
+.SH NAME
+simkaCount \- comparative metagenomics method dedicated to NGS datasets
+.SH DESCRIPTION
+ERROR: Unknown parameter '\-h'
+ERROR: Option '\-out\-tmp\-simka' is mandatory
+ERROR: Option '\-bank\-name' is mandatory
+ERROR: Option '\-bank\-index' is mandatory
+ERROR: Option '\-min\-read\-size' is mandatory
+ERROR: Option '\-min\-shannon\-index' is mandatory
+ERROR: Option '\-max\-reads' is mandatory
+ERROR: Option '\-nb\-datasets' is mandatory
+ERROR: Option '\-nb\-partitions' is mandatory
+ERROR: Option '\-in' is mandatory
+.PP
+[SimkaCount options]
+.TP
+\fB\-nb\-cores\fR
+(1 arg) :    number of cores  [default '0']
+.TP
+\fB\-verbose\fR
+(1 arg) :    verbosity level  [default '1']
+.TP
+\fB\-version\fR
+(0 arg) :    version
+.TP
+\fB\-help\fR
+(0 arg) :    help
+.TP
+\fB\-out\-tmp\-simka\fR
+(1 arg) :    tmp output
+.TP
+\fB\-bank\-name\fR
+(1 arg) :    bank name
+.TP
+\fB\-bank\-index\fR
+(1 arg) :    bank name
+.TP
+\fB\-min\-read\-size\fR
+(1 arg) :    bank name
+.TP
+\fB\-min\-shannon\-index\fR
+(1 arg) :    bank name
+.TP
+\fB\-max\-reads\fR
+(1 arg) :    bank name
+.TP
+\fB\-nb\-datasets\fR
+(1 arg) :    bank name
+.TP
+\fB\-nb\-partitions\fR
+(1 arg) :    bank name
+.TP
+\fB\-in\fR
+(1 arg) :    reads file
+.TP
+\fB\-kmer\-size\fR
+(1 arg) :    size of a kmer  [default '31']
+.TP
+\fB\-abundance\-min\fR
+(1 arg) :    min abundance threshold for solid kmers  [default '0']
+.TP
+\fB\-abundance\-max\fR
+(1 arg) :    max abundance threshold for solid kmers  [default '2147483647']
+.TP
+\fB\-abundance\-min\-threshold\fR
+(1 arg) :    min abundance hard threshold (only used when min abundance is "auto")  [default '2']
+.TP
+\fB\-histo\-max\fR
+(1 arg) :    max number of values in kmers histogram  [default '10000']
+.TP
+\fB\-solidity\-kind\fR
+(1 arg) :    way to compute counts of several files (sum, min, max, one, all, custom)  [default 'sum']
+.TP
+\fB\-solidity\-custom\fR
+(1 arg) :    when solidity\-kind is custom, specifies list of files where kmer must be present  [default '']
+.TP
+\fB\-max\-memory\fR
+(1 arg) :    max memory (in MBytes)  [default '5000']
+.TP
+\fB\-max\-disk\fR
+(1 arg) :    max disk   (in MBytes)  [default '0']
+.TP
+\fB\-solid\-kmers\-out\fR
+(1 arg) :    output file for solid kmers (only when constructing a graph)  [default '']
+.TP
+\fB\-out\fR
+(1 arg) :    output file  [default '']
+.TP
+\fB\-out\-dir\fR
+(1 arg) :    output directory  [default '.']
+.TP
+\fB\-out\-tmp\fR
+(1 arg) :    output directory for temporary files  [default '.']
+.TP
+\fB\-out\-compress\fR
+(1 arg) :    h5 compression level (0:none, 9:best)  [default '0']
+.TP
+\fB\-storage\-type\fR
+(1 arg) :    storage type of kmer counts ('hdf5' or 'file')  [default 'hdf5']
+.TP
+\fB\-histo2D\fR
+(1 arg) :    compute the 2D histogram (with first file = genome, remaining files = reads)  [default '0']
+.TP
+\fB\-histo\fR
+(1 arg) :    output the kmer abundance histogram  [default '0']
+.IP
+[kmer count, advanced performance tweaks options]
+.TP
+\fB\-minimizer\-type\fR
+(1 arg) :    minimizer type (0=lexi, 1=freq)  [default '0']
+.TP
+\fB\-minimizer\-size\fR
+(1 arg) :    size of a minimizer  [default '10']
+.TP
+\fB\-repartition\-type\fR (1 arg) :
+minimizer repartition (0=unordered, 1=ordered)  [default '0']
+.SH AUTHOR
+This manpage was written by Shayan Doust for the Debian distribution and can be used for any other usage of the program.

debian/mans/simkaCountProcess.1

+.\" DO NOT MODIFY THIS FILE!  It was generated by help2man 1.47.8.
+.TH SIMKACOUNTPROCESS "1" "September 2019" "simkaCountProcess 1.5.1" "User Commands"
+.SH NAME
+simkaCountProcess \- comparative metagenomics method dedicated to NGS datasets
+.SH DESCRIPTION
+nohup: invalid option \fB\-\-\fR 'h'
+Try 'nohup \fB\-\-help\fR' for more information.
+nohup: invalid option \fB\-\-\fR 'h'
+Try 'nohup \fB\-\-help\fR' for more information.
+nohup: invalid option \fB\-\-\fR 'h'
+Try 'nohup \fB\-\-help\fR' for more information.
+nohup: invalid option \fB\-\-\fR 'h'
+Try 'nohup \fB\-\-help\fR' for more information.
+nohup: invalid option \fB\-\-\fR 'h'
+Try 'nohup \fB\-\-help\fR' for more information.
+.SH AUTHOR
+This manpage was written by Shayan Doust for the Debian distribution and can be used for any other usage of the program.

debian/mans/simkaMerge.1

+.\" DO NOT MODIFY THIS FILE!  It was generated by help2man 1.47.8.
+.TH SIMKAMERGE "1" "September 2019" "simkaMerge 1.5.1" "User Commands"
+.SH NAME
+simkaMerge \- comparative metagenomics method dedicated to NGS datasets
+.SH DESCRIPTION
+ERROR: Unknown parameter '\-h'
+ERROR: Option '\-nb\-cores' is mandatory
+ERROR: Option '\-kmer\-size' is mandatory
+ERROR: Option '\-in' is mandatory
+ERROR: Option '\-out\-tmp\-simka' is mandatory
+ERROR: Option '\-partition\-id' is mandatory
+ERROR: Option '\-nb\-cores' is mandatory
+ERROR: Option '\-max\-memory' is mandatory
+ERROR: Option '\-kmer\-shannon\-index' is mandatory
+.PP
+[SimkaMerge options]
+.TP
+\fB\-nb\-cores\fR
+(1 arg) :    number of cores  [default '0']
+.TP
+\fB\-verbose\fR
+(1 arg) :    verbosity level  [default '1']
+.TP
+\fB\-version\fR
+(0 arg) :    version
+.TP
+\fB\-help\fR
+(0 arg) :    help
+.TP
+\fB\-nb\-cores\fR
+(1 arg) :    nb cores
+.TP
+\fB\-kmer\-size\fR
+(1 arg) :    kmer size
+.TP
+\fB\-in\fR
+(1 arg) :    input filename
+.TP
+\fB\-out\-tmp\-simka\fR
+(1 arg) :    tmp output
+.TP
+\fB\-partition\-id\fR
+(1 arg) :    bank name
+.TP
+\fB\-nb\-cores\fR
+(1 arg) :    bank name
+.TP
+\fB\-max\-memory\fR
+(1 arg) :    bank name
+.TP
+\fB\-kmer\-shannon\-index\fR (1 arg) :
+bank name
+.TP
+\fB\-simple\-dist\fR
+(0 arg) :    compute simple distances
+.TP
+\fB\-complex\-dist\fR
+(0 arg) :    compute complex distances
+.SH AUTHOR
+This manpage was written by Shayan Doust for the Debian distribution and can be used for any other usage of the program.

debian/mans/simkaMin.1

+.\" DO NOT MODIFY THIS FILE!  It was generated by help2man 1.47.8.
+.TH SIMKAMIN "1" "September 2019" "simkaMin 1.5.1" "User Commands"
+.SH NAME
+simkaMin \- comparative metagenomics method dedicated to NGS datasets
+.SH DESCRIPTION
+.SS "[main options]:"
+.TP
+\fB\-in\fR
+(1 arg) :    input file of datasets. One sample per line: id1: filename1...
+.TP
+\fB\-out\fR
+(1 arg) :    output directory for result files (distance matrices) [Default: ./simka_results]
+.TP
+\fB\-seed\fR
+(1 arg) :    seed used for random k\-mer selection [Default: 100]
+.TP
+\fB\-bin\fR
+(1 arg) :    path to simkaMinCore program (to be specified if not in PATH, or not in standard installation directory <simkaDir>/build/bin/simkaMinCore)
+.SS "[core options]:"
+.TP
+\fB\-nb\-cores\fR
+(1 arg) :    number of cores [Default: 0]
+.TP
+\fB\-max\-memory\fR
+(1 arg) :    max memory (MB) [Default: 8000]
+.SS "[k-mer options]:"
+.TP
+\fB\-kmer\-size\fR
+(1 arg) :    size of a kmer [Default: 21]
+.TP
+\fB\-nb\-kmers\fR
+(1 arg) :    number of kmers used to compute distances [Default: 1000000]
+.TP
+\fB\-filter\fR
+(0 arg) :    filter out k\-mer seen one time (potentially erroneous)
+.SS "[read options]:"
+.TP
+\fB\-max\-reads\fR
+(1 arg) :    maximum number of reads per sample to process [Default: 0]
+.TP
+\fB\-min\-read\-size\fR
+(1 arg) :    minimal size a read should have to be kept [Default: 0]
+.TP
+\fB\-min\-shannon\-index\fR
+(1 arg) :    minimal Shannon index a read should have to be kept. Float in [0,2] [Default: 0]
+.SH AUTHOR
+This manpage was written by Shayan Doust for the Debian distribution and can be used for any other usage of the program.

debian/mans/simkaMinCore.1

+.\" DO NOT MODIFY THIS FILE!  It was generated by help2man 1.47.8.
+.TH SIMKAMINCORE "1" "September 2019" "simkaMinCore 1.5.1" "User Commands"
+.SH NAME
+simkaMinCore \- comparative metagenomics method dedicated to NGS datasets
+.SH SYNOPSIS
+.B simkaMin
+[\fI\,option\/\fR]
+.SH DESCRIPTION
+[Distance computation options]
+.TP
+sketch
+: transform datasets in small sketches of k\-mers and their abundance
+.TP
+distance
+: compute Jaccard and Bray\-Curtis distances between sketches
+.PP
+[Distance matrix manipulation options]
+.TP
+export
+: export distance matrices stored in binary format
+.PP
+[Sketch options]
+.TP
+append
+: merge multiple sketch files into a single one
+.TP
+info
+: list datasets contained in a sketch file
+.SH AUTHOR
+This manpage was written by Shayan Doust for the Debian distribution and can be used for any other usage of the program.

debian/mans/simkaMin_update.1

+.\" DO NOT MODIFY THIS FILE!  It was generated by help2man 1.47.8.
+.TH SIMKAMIN_UPDATE "1" "September 2019" "simkaMin_update 1.5.1" "User Commands"
+.SH NAME
+simkaMin_update \- comparative metagenomics method dedicated to NGS datasets
+.SH DESCRIPTION
+.SS "[main options]:"
+.TP
+\fB\-in\fR
+(1 arg) :    input file of datasets (datasets to add to existing simka results
+.TP
+\fB\-in\-to\-update\fR
+(1 arg) :    path to existing simka results to update (existing results will be overwritten)
+.TP
+\fB\-bin\fR
+(1 arg) :    path to simkaMinCore program (to be specified if not in PATH, or not in standard installation directory <simkaDir>/build/bin/simkaMinCore)
+.SS "[core options]:"
+.TP
+\fB\-nb\-cores\fR
+(1 arg) :    number of cores [Default: 0]
+.TP
+\fB\-max\-memory\fR
+(1 arg) :    max memory (MB) [Default: 8000]
+.SS "[k-mer options]:"
+.TP
+\fB\-filter\fR
+(0 arg) :    filter out k\-mer seen one time (potentially erroneous)
+.SS "[read options]:"
+.TP
+\fB\-max\-reads\fR
+(1 arg) :    maximum number of reads per sample to process [Default: 0]
+.TP
+\fB\-min\-read\-size\fR
+(1 arg) :    minimal size a read should have to be kept [Default: 0]
+.TP
+\fB\-min\-shannon\-index\fR
+(1 arg) :    minimal Shannon index a read should have to be kept. Float in [0,2] [Default: 0]
+.SH AUTHOR
+This manpage was written by Shayan Doust for the Debian distribution and can be used for any other usage of the program.

debian/rules

@@ -5,8 +5,7 @@ export LC_ALL=C.UTF-8
 
 include /usr/share/dpkg/default.mk
 
-# for hardening you might like to uncomment this:
-# export DEB_BUILD_MAINT_OPTIONS=hardening=+all
+export DEB_BUILD_MAINT_OPTIONS=hardening=+all
 
 %:
 	dh $@ --with python3
@@ -15,7 +14,7 @@ override_dh_install:
 	dh_install
 	rm -r debian/tmp/usr/example \
 		debian/tmp/usr/scripts
-	chrpath --delete debian/tmp/usr/bin/*
+	chrpath --delete debian/simka/usr/bin/*
 	for file in debian/simkamin/usr/bin/*.py; do mv "$$file" "$${file%%.py}"; done
 	mv debian/simkamin/usr/bin/simkaMin_utils debian/simkamin/usr/bin/simkaMin_utils.py
 

debian/simka.install

+debian/tmp/usr/bin/* usr/bin