debian/changelog

-minia (3.2.0-1) UNRELEASED; urgency=medium
+minia (3.2.0-1) unstable; urgency=medium
 
-  * Switch from legacy version to version 2.x at GibHub
-  * Add myself as Uploader
   * New upstream version
+  * Add myself as Uploader
   * debhelper 12
   * Point Vcs fields to salsa.debian.org
   * Standards-Version: 4.3.0
@@ -13,8 +12,10 @@ minia (3.2.0-1) UNRELEASED; urgency=medium
   * Build-Depends: libboost-dev, libhdf5-dev
   * Versioned Build-Depends: libgatbcore-dev (>= 1.4.1+git20181225.44d5a44~)
   * Do not set rpath
+  * Add rudimentary manpages
+  * Rewrite autopkgtest
 
- -- Andreas Tille <tille@debian.org>  Mon, 21 Jan 2019 09:01:19 +0100
+ -- Andreas Tille <tille@debian.org>  Fri, 25 Jan 2019 22:29:11 +0100
 
 minia (1.6906-2) unstable; urgency=medium
 

debian/control

@@ -22,6 +22,8 @@ Depends: ${misc:Depends},
          ${shlibs:Depends},
          zlib1g,
          bc
+Recommends: samtools
+Suggests: bandage
 Description: short-read biological sequence assembler
  Short-read DNA sequence assembler based on a de Bruijn graph,
  capable of assembling a human genome on a desktop computer in a day.

debian/createmanpages

+#!/bin/sh
+MANDIR=debian
+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 $DEBFULLNAME for the Debian distribution and
+can be used for any other usage of the program.
+"
+
+# If program name is different from package name or title should be
+# different from package short description change this here
+progname=${PROGNAME}
+help2man --no-info --no-discard-stderr --help-option=" " \
+         --name="$NAME" \
+            --version-string="$VERSION" ${progname} > $MANDIR/${progname}.1
+echo $AUTHOR >> $MANDIR/${progname}.1
+
+progname=merci
+help2man --no-info --no-discard-stderr --help-option=" " \
+         --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/*.1

debian/merci.1

+.\" DO NOT MODIFY THIS FILE!  It was generated by help2man 1.47.8.
+.TH MERCI "1" "January 2019" "merci 3.2.0" "User Commands"
+.SH NAME
+merci \- short-read biological sequence assembler
+.SH DESCRIPTION
+.PP
+[merci options]
+.IP
+[assembly options]
+.TP
+\fB\-verbose\fR
+(1 arg) :    verbosity level  [default '1']
+.TP
+\fB\-nb\-cores\fR
+(1 arg) :    number of threads  [default '0']
+.TP
+\fB\-kmer\-size\fR (1 arg) :
+kmer size
+.TP
+\fB\-assembly\fR
+(1 arg) :    assembly to improve
+.TP
+\fB\-reads\fR
+(1 arg) :    input reads (fasta/fastq/compressed)
+.SH AUTHOR
+This manpage was written by Andreas Tille for the Debian distribution and can be used for any other usage of the program.

debian/minia.1

+.\" DO NOT MODIFY THIS FILE!  It was generated by help2man 1.47.8.
+.TH MINIA "1" "January 2019" "minia 3.2.0" "User Commands"
+.SH NAME
+minia \- short-read biological sequence assembler
+.SH DESCRIPTION
+Specifiy \fB\-in\fR
+.PP
+[minia options]
+.IP
+[assembly options]
+.TP
+\fB\-in\fR
+(1 arg) :    input reads (fasta/fastq/compressed) or hdf5 file  [default '']
+.TP
+\fB\-keep\-isolated\fR (0 arg) :
+keep short (<= max(2k, 150 bp)) isolated output sequences
+.TP
+\fB\-traversal\fR
+(1 arg) :    traversal type ('contig', 'unitig')  [default 'contig']
+.TP
+\fB\-fasta\-line\fR
+(1 arg) :    number of nucleotides per line in fasta output (0 means one line)  [default '0']
+.IP
+[graph simplifications options]
+.TP
+\fB\-no\-bulge\-removal\fR
+(0 arg) :    ask to not perform bulge removal
+.TP
+\fB\-no\-tip\-removal\fR
+(0 arg) :    ask to not perform tip removal
+.TP
+\fB\-no\-ec\-removal\fR
+(0 arg) :    ask to not perform erroneous connection removal
+.TP
+\fB\-tip\-len\-topo\-kmult\fR
+(1 arg) :    remove all tips of length <= k * X bp  [default '2.500000']
+.TP
+\fB\-tip\-len\-rctc\-kmult\fR
+(1 arg) :    remove tips that pass coverage criteria, of length <= k * X bp  [default '10.000000']
+.TP
+\fB\-tip\-rctc\-cutoff\fR
+(1 arg) :    tip relative coverage coefficient: mean coverage of neighbors >  X * tip coverage  [default '2.000000']
+.TP
+\fB\-bulge\-len\-kmult\fR
+(1 arg) :    bulges shorter than k*X bp are candidate to be removed  [default '3.000000']
+.TP
+\fB\-bulge\-len\-kadd\fR
+(1 arg) :    bulges shorter than k+X bp are candidate to be removed  [default '100']
+.TP
+\fB\-bulge\-altpath\-kadd\fR
+(1 arg) :    explore up to k+X nodes to find alternative path  [default '50']
+.TP
+\fB\-bulge\-altpath\-covmult\fR (1 arg) :
+bulges of coverage <= X*cov_altpath will be removed  [default '1']
+.TP
+\fB\-ec\-len\-kmult\fR
+(1 arg) :    EC shorter than k*X bp are candidates to be removed  [default '9.000000']
+.TP
+\fB\-ec\-rctc\-cutoff\fR
+(1 arg) :    EC relative coverage coefficient (similar in spirit as tip)  [default '4.000000']
+.TP
+\fB\-no\-mphf\fR
+(0 arg) :    don't construct the MPHF
+.IP
+[kmer count options]
+.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 '2']
+.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']
+.IP
+[bloom options]
+.TP
+\fB\-bloom\fR
+(1 arg) :    bloom type ('basic', 'cache', 'neighbor')  [default 'neighbor']
+.TP
+\fB\-debloom\fR
+(1 arg) :    debloom type ('none', 'original' or 'cascading')  [default 'cascading']
+.TP
+\fB\-debloom\-impl\fR (1 arg) :
+debloom impl ('basic', 'minimizer')  [default 'minimizer']
+.IP
+[branching options]
+.TP
+\fB\-branching\-nodes\fR (1 arg) :
+branching type ('none' or 'stored')  [default 'stored']
+.TP
+\fB\-topology\-stats\fR
+(1 arg) :    topological information level (0 for none)  [default '0']
+.IP
+[general options]
+.TP
+\fB\-config\-only\fR
+(0 arg) :    dump config only
+.TP
+\fB\-nb\-cores\fR
+(1 arg) :    number of cores  [default '0']
+.TP
+\fB\-verbose\fR
+(1 arg) :    verbosity level  [default '1']
+.TP
+\fB\-integer\-precision\fR (1 arg) :
+integers precision (0 for optimized value)  [default '0']
+.TP
+[debug
+options]
+.TP
+\fB\-redo\-bcalm\fR
+(0 arg) :    debug function, redo the bcalm algo
+.TP
+\fB\-skip\-bcalm\fR
+(0 arg) :    same, but       skip     bcalm
+.TP
+\fB\-redo\-bglue\fR
+(0 arg) :    same, but       redo     bglue
+.TP
+\fB\-skip\-bglue\fR
+(0 arg) :    same, but       skip     bglue
+.TP
+\fB\-redo\-links\fR
+(0 arg) :    same, but       redo     links
+.TP
+\fB\-skip\-links\fR
+(0 arg) :    same, but       skip     links
+.TP
+\fB\-nb\-glue\-partitions\fR (1 arg) :
+number of glue partitions (automatically calculated by default)  [default '0']
+.SH AUTHOR
+This manpage was written by Andreas Tille for the Debian distribution and can be used for any other usage of the program.

debian/patches/fix_path_in_tests.patch

+Author: Andreas Tille <tille@debian.org>
+Last-Update: Mon, 21 Jan 2019 09:01:19 +0100
+Description: Make sure tools in tests will be found
+
+--- a/test/simple_test.sh
++++ b/test/simple_test.sh
+@@ -9,8 +9,12 @@ elif [ -f "../build/bin/minia" ]
+ then
+  bindir="../build/bin"
+ else
+- echo "could not find a compiled Minia binary"
+- exit 1
++ if which minia >/dev/null ; then
++   bindir=$(dirname $(which minia))
++ else
++   echo "could not find a compiled Minia binary"
++   exit 1
++ fi
+ fi
+ 
+ verbose="0"
+--- a/test/10k_test.sh
++++ b/test/10k_test.sh
+@@ -5,14 +5,15 @@ t=2
+ traversal=contig
+ 
+ set -x
+-../build/minia -in "$file".fa -kmer-size "$k" -abundance-min $t -traversal $traversal -nb-cores 1
++minia -in "$file".fa -kmer-size "$k" -abundance-min $t -traversal $traversal -nb-cores 1
+ set +x
+ 
+ echo "legacy: ~/gatb-pipeline/minia/minia-legacy -in "$file".fa -kmer-size "$k" -no-length-cutoff -abundance-min $t -traversal $traversal"
+ 
+ # running tigops
+-echo "tigops, bandage:"
+-echo "../../tigops/build/tigops fasta2fastg -tigs "$file".contigs.fa -out "$file".contigs.fastg -kmer-size $k -rename"
++echo "To run tigops this project needs to be packaged: https://github.com/GATB/tigops"
++echo "tigops fasta2fastg -tigs "$file".contigs.fa -out "$file".contigs.fastg -kmer-size $k -rename"
+ 
+-echo "~/tools/bandage/Bandage/Bandage $file.contigs.fastg"
++echo "Make sure you do  'apt install bandage'  to run this command"
++echo "Bandage $file.contigs.fastg"
+ 
+--- a/test/test_ERR039477.sh
++++ b/test/test_ERR039477.sh
+@@ -9,8 +9,12 @@ elif [ -f "../build/bin/minia" ]
+ then
+  bindir="../build/bin"
+ else
+- echo "could not find a compiled Minia binary"
+- exit 1
++ if which minia >/dev/null ; then
++   bindir=$(dirname $(which minia))
++ else
++   echo "could not find a compiled Minia binary"
++   exit 1
++ fi
+ fi
+ 
+ ################################################################################
+--- a/test/buchnera_test.sh
++++ b/test/buchnera_test.sh
+@@ -1,10 +1,11 @@
+ file=buchnera
+ k=22
+ 
+-../build/minia -in buchnera -abundance-min 2 -kmer-size $k
++minia -in buchnera -abundance-min 2 -kmer-size $k
+ 
+-echo "tigops, bandage:"
+-echo "../../tigops/build/tigops fasta2fastg -tigs "$file".contigs.fa -out "$file".contigs.fastg -kmer-size $k -rename"
++echo "To run tigops this project needs to be packaged: https://github.com/GATB/tigops"
++echo "tigops fasta2fastg -tigs "$file".contigs.fa -out "$file".contigs.fastg -kmer-size $k -rename"
+ 
+-echo "~/tools/bandage/Bandage/Bandage $file.contigs.fastg"
++echo "Make sure you do  'apt install bandage'  to run this command"
++echo "Bandage $file.contigs.fastg"
+ 

debian/patches/series

@@ -2,3 +2,4 @@ use_debian_packaged_gatb-core.patch
 link_libraries.patch
 no_install_to_wrong_dir.patch
 skip-rpath.patch
+fix_path_in_tests.patch

debian/tests/control

 Tests: run-unit-test
-Depends: @
+Depends: @, samtools, python
 Restrictions: allow-stderr

debian/tests/run-unit-test

@@ -9,9 +9,17 @@ fi
 
 cd $AUTOPKGTEST_TMP
 
-cp -a /usr/share/doc/${pkg}/read50x_ref10K_e001.fasta* .
+cp -a /usr/share/doc/${pkg}/test/* .
 gunzip -r *
 
-minia read50x_ref10K_e001.fasta 31 3 10000 minia_assembly_k31_m3
+echo "************ Run simple_test.sh ****************"
+bash simple_test.sh
+echo "************ Run 10k_test.sh ****************"
+sh 10k_test.sh
+echo "************ Run buchnera_test.sh ****************"
+sh buchnera_test.sh
 
-minia read50x_ref10K_e001.fasta 29 4 10000 minia_assembly_k33_m4
+echo "************ Run buchnera_simulate_reads.sh ****************"
+sh buchnera_simulate_reads.sh
+echo "************ Run 1seq_90bp_simulate_reads.sh ****************"
+sh 1seq_90bp_simulate_reads.sh