debian/README.Debian

@@ -5,10 +5,10 @@ BBMap ships with several tools featuring perfectly generic names.
 This would cause a lot of naming conflicts.  The solution is to
 install these tools into
 
-    /usr/lib/debian-med/bin
+    /usr/share/bbmap
 
 and let users add this dir to their PATH via
 
-    export PATH=/usr/lib/debian-med/bin:$PATH
+    export PATH=/usr/share/bbmap:$PATH
 
  -- Andreas Tille <tille@debian.org>  Fri, 18 Mar 2016 13:50:56 +0100

debian/bbmap.links

-usr/lib/debian-med/bin/bbmap.sh		usr/bin/bbmap.sh
-usr/lib/debian-med/bin/bloomfilter.sh	usr/bin/bloomfilter.sh
+usr/share/bbmap/bbmap.sh	usr/bin/bbmap.sh
+usr/share/bbmap/bloomfilter.sh	usr/bin/bloomfilter.sh
+usr/share/bbmap/bbnorm.sh	usr/bin/bbnorm.sh
+usr/share/bbmap/dedupe.sh	usr/bin/dedupe.sh
+usr/share/bbmap/reformat.sh	usr/bin/reformat.sh
+usr/share/bbmap/bbduk.sh	usr/bin/bbduk.sh

debian/changelog

-bbmap (38.43+dfsg-1) UNRELEASED; urgency=medium
+bbmap (38.43+dfsg-1) experimental; urgency=medium
 
-  * Initial release (Closes: #???)
+  * Initial release (Closes: #925875)
 
- -- Andreas Tille <tille@debian.org>  Mon, 25 Mar 2019 09:54:19 +0100
+ -- Andreas Tille <tille@debian.org>  Wed, 27 Mar 2019 21:58:48 +0100

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}.sh
-help2man --no-info --no-discard-stderr --help-option=" " \
-         --name="$NAME" \
-            --version-string="$VERSION" ${progname} > $MANDIR/${progname}.1
-echo $AUTHOR >> $MANDIR/${progname}.1
-
-progname=bloomfilter.sh
-help2man --no-info --no-discard-stderr --help-option=" " \
-         --name="Filters reads potentially sharing a kmer with a reference" \
-            --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/lintian-overrides

-# see https://lists.debian.org/debian-med/2018/06/msg00043.html
-bbmap: script-with-language-extension usr/bin/*

debian/manpages

-debian/*.1
+debian/mans/*.1

debian/mans/bbnorm.sh.1

+.\" DO NOT MODIFY THIS FILE!  It was generated by help2man 1.47.8.
+.TH BBNORM.SH "1" "April 2019" "bbnorm.sh 38.43" "User Commands"
+.SH NAME
+bbnorm.sh \- Kmer-based error-correction and normalization tool
+.SH SYNOPSIS
+.B bbnorm.sh
+\fI\,in=<input> out=<reads to keep> outt=<reads to toss> hist=<histogram output>\/\fR
+.SH DESCRIPTION
+Normalizes read depth based on kmer counts.
+Can also error\-correct, bin reads by kmer depth, and generate a kmer depth histogram.
+However, Tadpole has superior error\-correction to BBNorm.
+Please read bbmap/docs/guides/BBNormGuide.txt for more information.
+.SH OPTIONS
+.SS Input parameters
+.TP
+in=null
+Primary input.  Use in2 for paired reads in a second file
+.TP
+in2=null
+Second input file for paired reads in two files
+.TP
+extra=null
+Additional files to use for input (generating hash table) but not for output
+.TP
+fastareadlen=2^31
+Break up FASTA reads longer than this.  Can be useful when processing scaffolded genomes
+.TP
+tablereads=\-1
+Use at most this many reads when building the hashtable (\fB\-1\fR means all)
+.TP
+kmersample=1
+Process every nth kmer, and skip the rest
+.TP
+readsample=1
+Process every nth read, and skip the rest
+.TP
+interleaved=auto
+May be set to true or false to force the input read file to ovverride autodetection of the input file as paired interleaved.
+.TP
+qin=auto
+ASCII offset for input quality.  May be 33 (Sanger), 64 (Illumina), or auto.
+.SS Output parameters
+.TP
+out=<file>
+File for normalized or corrected reads.  Use out2 for paired reads in a second file
+.TP
+outt=<file>
+(outtoss) File for reads that were excluded from primary output
+.TP
+reads=\-1
+Only process this number of reads, then quit (\fB\-1\fR means all)
+.TP
+sampleoutput=t
+Use sampling on output as well as input (not used if sample rates are 1)
+.TP
+keepall=f
+Set to true to keep all reads (e.g. if you just want error correction).
+.TP
+zerobin=f
+Set to true if you want kmers with a count of 0 to go in the 0 bin instead of the 1 bin in histograms.
+.IP
+Default is false, to prevent confusion about how there can be 0\-count kmers.
+The reason is that based on the 'minq' and 'minprob' settings, some kmers may be excluded from the bloom filter.
+.TP
+tmpdir=
+This will specify a directory for temp files (only needed for multipass runs).  If null, they will be written to the output directory.
+.TP
+usetempdir=t
+Allows enabling/disabling of temporary directory; if disabled, temp files will be written to the output directory.
+.TP
+qout=auto
+ASCII offset for output quality.  May be 33 (Sanger), 64 (Illumina), or auto (same as input).
+.TP
+rename=f
+Rename reads based on their kmer depth.
+.SS Hashing parameters
+.TP
+k=31
+Kmer length (values under 32 are most efficient, but arbitrarily high values are supported)
+.TP
+bits=32
+Bits per cell in bloom filter; must be 2, 4, 8, 16, or 32.  Maximum kmer depth recorded is 2^cbits.  Automatically reduced to 16 in 2\-pass.
+.IP
+Large values decrease accuracy for a fixed amount of memory, so use the lowest number you can that will still capture highest\-depth kmers.
+.TP
+hashes=3
+Number of times each kmer is hashed and stored.  Higher is slower.
+.IP
+Higher is MORE accurate if there is enough memory, and LESS accurate if there is not enough memory.
+.TP
+prefilter=f
+True is slower, but generally more accurate; filters out low\-depth kmers from the main hashtable.  The prefilter is more memory\-efficient because it uses 2\-bit cells.
+.TP
+prehashes=2
+Number of hashes for prefilter.
+.TP
+prefilterbits=2
+(pbits) Bits per cell in prefilter.
+.TP
+prefiltersize=0.35
+Fraction of memory to allocate to prefilter.
+.TP
+buildpasses=1
+More passes can sometimes increase accuracy by iteratively removing low\-depth kmers
+.TP
+minq=6
+Ignore kmers containing bases with quality below this
+.TP
+minprob=0.5
+Ignore kmers with overall probability of correctness below this
+.TP
+threads=auto
+(t) Spawn exactly X hashing threads (default is number of logical processors).  Total active threads may exceed X due to I/O threads.
+.TP
+rdk=t
+(removeduplicatekmers) When true, a kmer's count will only be incremented once per read pair, even if that kmer occurs more than once.
+.SS Normalization parameters
+.TP
+fixspikes=f
+(fs) Do a slower, high\-precision bloom filter lookup of kmers that appear to have an abnormally high depth due to collisions.
+.TP
+target=100
+(tgt) Target normalization depth.  NOTE:  All depth parameters control kmer depth, not read depth.
+.IP
+For kmer depth Dk, read depth Dr, read length R, and kmer size K:
+Dr=Dk*(R/(R\-K+1))
+.TP
+maxdepth=\-1
+(max) Reads will not be downsampled when below this depth, even if they are above the target depth.
+.TP
+mindepth=5
+(min) Kmers with depth below this number will not be included when calculating the depth of a read.
+.TP
+minkmers=15
+(mgkpr) Reads must have at least this many kmers over min depth to be retained.  Aka 'mingoodkmersperread'.
+.TP
+percentile=54.0
+(dp) Read depth is by default inferred from the 54th percentile of kmer depth, but this may be changed to any number 1\-100.
+.TP
+uselowerdepth=t
+(uld) For pairs, use the depth of the lower read as the depth proxy.
+.TP
+deterministic=t
+(dr) Generate random numbers deterministically to ensure identical output between multiple runs.  May decrease speed with a huge number of threads.
+.TP
+passes=2
+(p) 1 pass is the basic mode.  2 passes (default) allows greater accuracy, error detection, better contol of output depth.
+.SS Error detection parameters
+.TP
+hdp=90.0
+(highdepthpercentile) Position in sorted kmer depth array used as proxy of a read's high kmer depth.
+.TP
+ldp=25.0
+(lowdepthpercentile) Position in sorted kmer depth array used as proxy of a read's low kmer depth.
+.TP
+tossbadreads=f
+(tbr) Throw away reads detected as containing errors.
+.TP
+requirebothbad=f
+(rbb) Only toss bad pairs if both reads are bad.
+.TP
+errordetectratio=125
+(edr) Reads with a ratio of at least this much between their high and low depth kmers will be classified as error reads.
+.TP
+highthresh=12
+(ht) Threshold for high kmer.  A high kmer at this or above are considered non\-error.
+.TP
+lowthresh=3
+(lt) Threshold for low kmer.  Kmers at this and below are always considered errors.
+.SS Error correction parameters
+.TP
+ecc=f
+Set to true to correct errors.  NOTE: Tadpole is now preferred for ecc as it does a better job.
+.TP
+ecclimit=3
+Correct up to this many errors per read.  If more are detected, the read will remain unchanged.
+.TP
+errorcorrectratio=140
+(ecr) Adjacent kmers with a depth ratio of at least this much between will be classified as an error.
+.TP
+echighthresh=22
+(echt) Threshold for high kmer.  A kmer at this or above may be considered non\-error.
+.TP
+eclowthresh=2
+(eclt) Threshold for low kmer.  Kmers at this and below are considered errors.
+.TP
+eccmaxqual=127
+Do not correct bases with quality above this value.
+.TP
+aec=f
+(aggressiveErrorCorrection) Sets more aggressive values of ecr=100, ecclimit=7, echt=16, eclt=3.
+.TP
+cec=f
+(conservativeErrorCorrection) Sets more conservative values of ecr=180, ecclimit=2, echt=30, eclt=1, sl=4, pl=4.
+.TP
+meo=f
+(markErrorsOnly) Marks errors by reducing quality value of suspected errors; does not correct anything.
+.TP
+mue=t
+(markUncorrectableErrors) Marks errors only on uncorrectable reads; requires 'ecc=t'.
+.TP
+overlap=f
+(ecco) Error correct by read overlap.
+.SS Depth binning parameters
+.TP
+lowbindepth=10
+(lbd) Cutoff for low depth bin.
+.TP
+highbindepth=80
+(hbd) Cutoff for high depth bin.
+.TP
+outlow=<file>
+Pairs in which both reads have a median below lbd go into this file.
+.TP
+outhigh=<file>
+Pairs in which both reads have a median above hbd go into this file.
+.TP
+outmid=<file>
+All other pairs go into this file.
+.SS Histogram parameters
+.TP
+hist=<file>
+Specify a file to write the input kmer depth histogram.
+.TP
+histout=<file>
+Specify a file to write the output kmer depth histogram.
+.TP
+histcol=3
+(histogramcolumns) Number of histogram columns, 2 or 3.
+.TP
+pzc=f
+(printzerocoverage) Print lines in the histogram with zero coverage.
+.TP
+histlen=1048576
+Max kmer depth displayed in histogram.  Also affects statistics displayed, but does not affect normalization.
+.SS Peak calling parameters
+.TP
+peaks=<file>
+Write the peaks to this file.  Default is stdout.
+.TP
+minHeight=2
+(h) Ignore peaks shorter than this.
+.TP
+minVolume=5
+(v) Ignore peaks with less area than this.
+.TP
+minWidth=3
+(w) Ignore peaks narrower than this.
+.TP
+minPeak=2
+(minp) Ignore peaks with an X\-value below this.
+.TP
+maxPeak=BIG
+(maxp) Ignore peaks with an X\-value above this.
+.TP
+maxPeakCount=8
+(maxpc) Print up to this many peaks (prioritizing height).
+.SS Java Parameters:
+.TP
+\fB\-Xmx\fR
+This will set Java's memory usage, overriding autodetection.
+.IP
+\fB\-Xmx20g\fR will specify 20 gigs of RAM, and \fB\-Xmx200m\fR will specify 200 megs.
+The max is typically 85% of physical memory.
+.TP
+\fB\-eoom\fR
+This flag will cause the process to exit if an
+out\-of\-memory exception occurs.
+Requires Java 8u92+.
+.TP
+\fB\-da\fR
+Disable assertions.
+.SH AUTHOR
+Written by Brian Bushnell (Last modified October 19, 2017)
+.P
+Please contact Brian Bushnell at bbushnell@lbl.gov if you encounter
+any problems, or post at: http://seqanswers.com/forums/showthread.php?t=41057
+.P
+This manpage was written by Andreas Tille for the Debian distribution and can be used for any other usage of the program.

debian/rules

@@ -3,7 +3,6 @@
 # DH_VERBOSE := 1
 
 include /usr/share/dpkg/default.mk
-PKGBINDIR    := debian/$(DEB_SOURCE)/usr/lib/debian-med/bin
 PKGSHAREDIR    := debian/$(DEB_SOURCE)/usr/share/$(DEB_SOURCE)
 
 export JAVA_HOME  := /usr/lib/jvm/default-java
@@ -28,23 +27,25 @@ override_dh_auto_build:
 override_dh_install:
 	dh_install
 	mkdir -p $(PKGSHAREDIR)
-	mkdir -p $(PKGBINDIR)
 	# cp -a calcmem.sh $(PKGSHAREDIR)/calcmem # we don't have any name space collision when keeping .sh extension
 	for scr in *.sh ; do \
 	    if [ "$${scr}" != "calcmem.sh" ] ; then \
 		sed -e 's:^CP=".DIR""current/":CP=/usr/share/java/bbmap.jar:' \
 		    -e 's:source ".DIR""/calcmem.sh":source "/usr/share/$(DEB_SOURCE)/calcmem":' \
-		    $${scr} > $(PKGBINDIR)/$${scr} ; \
+		    $${scr} > $(PKGSHAREDIR)/$${scr} ; \
 	    fi ; \
 	done
 
 override_dh_fixperms:
 	dh_fixperms
-	chmod +x $(PKGBINDIR)/*
+	chmod +x $(PKGSHAREDIR)/*
 
 override_dh_installman:
 	dh_installman
+	mkdir -p debian/$(DEB_SOURCE)/usr/share/man/man1/
+	mv debian/$(DEB_SOURCE)/usr/share/man/sh/man1/* debian/$(DEB_SOURCE)/usr/share/man/man1/
 	rename 's/\.1$$/.sh.1/' debian/$(DEB_SOURCE)/usr/share/man/man1/*.1
+	rm -rf debian/$(DEB_SOURCE)/usr/share/man/sh
 
 override_dh_installdocs:
 	dh_installdocs