debian/README.source

+The cwl/ directory was generated thusly:
+
+All binaries were called with --write-ctd and those CTDs were converted to CWL
+using https://github.com/WorkflowConversion/CTDConverter

debian/changelog

-lambda-align (1.0.2-2) UNRELEASED; urgency=medium
+lambda-align (1.0.3-1) unstable; urgency=medium
 
+  [ Steffen Moeller ]
   * Added ref to OMICtools registry.
 
- -- Steffen Moeller <moeller@debian.org>  Fri, 30 Jun 2017 19:04:18 +0200
+  [ Michael R. Crusoe ]
+  * New upstream release fixes Seqan 2.4.0 compat
+  * Include CWL descriptions
+  * Run the unit tests and make them available as AutoPkgTests
+
+ -- Michael R. Crusoe <michael.crusoe@gmail.com>  Sat, 17 Feb 2018 12:19:04 -0800
 
 lambda-align (1.0.2-1) unstable; urgency=medium
 

debian/control

 Source: lambda-align
+Maintainer: Debian Med Packaging Team <debian-med-packaging@lists.alioth.debian.org>
+Uploaders: Sascha Steinbiss <satta@debian.org>,
+           Michael R. Crusoe <michael.crusoe@gmail.com>
 Section: science
 Priority: optional
-Maintainer: Debian Med Packaging Team <debian-med-packaging@lists.alioth.debian.org>
-Uploaders: Sascha Steinbiss <satta@debian.org>
 Build-Depends: debhelper (>= 10),
-               libseqan2-dev (>= 2.2.0+dfsg-2~),
+               libseqan2-dev,
                cmake,
                zlib1g-dev,
-               libbz2-dev
-Standards-Version: 4.0.0
+               libbz2-dev,
+               openssl
+Standards-Version: 4.1.3
 Vcs-Browser: https://anonscm.debian.org/cgit/debian-med/lambda-align.git
 Vcs-Git: https://anonscm.debian.org/git/debian-med/lambda-align.git
 Homepage: https://seqan.github.io/lambda
 
 Package: lambda-align
 Architecture: any
-Depends: ${shlibs:Depends}, ${misc:Depends}
+Depends: ${shlibs:Depends},
+         ${misc:Depends}
+Suggests: cwl-runner
 Description: Local Aligner for Massive Biological DatA
  Lambda is a local biosequence aligner optimized for many query sequences
  and searches in protein space. It is compatible to the de facto standard tool

debian/cwl/lambda.cwl

+#!/usr/bin/env cwl-runner
+
+# This CWL file was automatically generated using CTDConverter.
+# Visit https://github.com/WorkflowConversion/CTDConverter for more information.
+
+baseCommand: lambda
+class: CommandLineTool
+cwlVersion: v1.0
+doc: "Lambda is a local aligner optimized for many query sequences and searches in\
+  \ protein space. It is compatible to BLAST, but much faster than BLAST and many\
+  \ other comparable tools.\nDetailed information is available in the wiki: <https://github.com/seqan/lambda/wiki>\n\
+  \n\n\nFor more information, visit http://www.seqan.de"
+inputs:
+- default: 'false'
+  doc: Display the help message with advanced options.
+  id: param_full-help
+  inputBinding:
+    prefix: -full-help
+  label: Display the help message with advanced options.
+  type:
+  - 'null'
+  - string
+- default: '1'
+  doc: 'Turn this option off to disable version update notifications of the application. '
+  id: param_version-check
+  inputBinding:
+    prefix: -version-check
+  label: 'Turn this option off to disable version update notifications of the application. '
+  type:
+  - 'null'
+  - string
+- default: 'false'
+  doc: Display long copyright information.
+  id: param_copyright
+  inputBinding:
+    prefix: -copyright
+  label: Display long copyright information.
+  type:
+  - 'null'
+  - string
+- default: '1'
+  doc: 'Display more/less diagnostic output during operation: 0 [only errors]; 1 [default];
+    2 [+run-time, options and statistics].'
+  id: param_verbosity
+  inputBinding:
+    prefix: -verbosity
+  label: 'Display more/less diagnostic output during operation: 0 [only errors]; 1
+    [default]; 2 [+run-time, options and statistics].'
+  type:
+  - 'null'
+  - int
+- doc: Query sequences.
+  id: param_query
+  inputBinding:
+    prefix: -query
+  label: Query sequences.
+  type: File
+- doc: Path to original database sequences (a precomputed index with .sa or .fm needs
+    to exist!).
+  id: param_database
+  inputBinding:
+    prefix: -database
+  label: Path to original database sequences (a precomputed index with .sa or .fm
+    needs to exist!).
+  type: File
+- default: fm
+  doc: database index is in this format.
+  id: param_db-index-type
+  inputBinding:
+    prefix: -db-index-type
+  label: database index is in this format.
+  type:
+  - 'null'
+  - string
+- default: output.m8
+  doc: Filename for output output file
+  id: param_output_filename
+  inputBinding:
+    prefix: -output
+  label: Filename for output output file
+  type:
+  - 'null'
+  - string
+- default: std
+  doc: Print specified column combination and/or order (.m8 and .m9 outputs only);
+    call -oc help for more details.
+  id: param_output-columns
+  inputBinding:
+    prefix: -output-columns
+  label: Print specified column combination and/or order (.m8 and .m9 outputs only);
+    call -oc help for more details.
+  type:
+  - 'null'
+  - string
+- default: '0'
+  doc: Output only matches above this threshold (checked before e-value check).
+  id: param_percent-identity
+  inputBinding:
+    prefix: -percent-identity
+  label: Output only matches above this threshold (checked before e-value check).
+  type:
+  - 'null'
+  - int
+- default: '0.1'
+  doc: Output only matches that score below this threshold.
+  id: param_e-value
+  inputBinding:
+    prefix: -e-value
+  label: Output only matches that score below this threshold.
+  type:
+  - 'null'
+  - double
+- default: '500'
+  doc: Print at most this number of matches per query.
+  id: param_num-matches
+  inputBinding:
+    prefix: -num-matches
+  label: Print at most this number of matches per query.
+  type:
+  - 'null'
+  - int
+- default: 'off'
+  doc: BAM files require all subject names to be written to the header. For SAM this
+    is not required, so Lambda does not automatically do it to save space (especially
+    for protein database this is a lot!). If you still want them with SAM, e.g. for
+    better BAM compatibility, use this option.
+  id: param_sam-with-refheader
+  inputBinding:
+    prefix: -sam-with-refheader
+  label: BAM files require all subject names to be written to the header. For SAM
+    this is not required, so Lambda does not automatically do it to save space (especially
+    for protein database this is a lot!). If you still want them with SAM, e.g. for
+    better BAM compatibility, use this option.
+  type:
+  - 'null'
+  - string
+- default: uniq
+  doc: Write matching DNA subsequence into SAM/BAM file (BLASTN). For BLASTX and TBLASTX
+    the matching protein sequence is "untranslated" and positions retransformed to
+    the original sequence. For BLASTP and TBLASTN there is no DNA sequence so a "*"
+    is written to the SEQ column. The matching protein sequence can be written as
+    an optional tag, see --sam-bam-tags. If set to uniq than the sequence is omitted
+    iff it is identical to the previous match's subsequence.
+  id: param_sam-bam-seq
+  inputBinding:
+    prefix: -sam-bam-seq
+  label: Write matching DNA subsequence into SAM/BAM file (BLASTN). For BLASTX and
+    TBLASTX the matching protein sequence is "untranslated" and positions retransformed
+    to the original sequence. For BLASTP and TBLASTN there is no DNA sequence so a
+    "*" is written to the SEQ column. The matching protein sequence can be written
+    as an optional tag, see --sam-bam-tags. If set to uniq than the sequence is omitted
+    iff it is identical to the previous match's subsequence.
+  type:
+  - 'null'
+  - string
+- default: AS NM ZE ZI ZF
+  doc: Write the specified optional columns to the SAM/BAM file. Call --sam-bam-tags
+    help for more details.
+  id: param_sam-bam-tags
+  inputBinding:
+    prefix: -sam-bam-tags
+  label: Write the specified optional columns to the SAM/BAM file. Call --sam-bam-tags
+    help for more details.
+  type:
+  - 'null'
+  - string
+- default: hard
+  doc: Whether to hard-clip or soft-clip the regions beyond the local match. Soft-clipping
+    retains the full sequence in the output file, but obviously uses more space.
+  id: param_sam-bam-clip
+  inputBinding:
+    prefix: -sam-bam-clip
+  label: Whether to hard-clip or soft-clip the regions beyond the local match. Soft-clipping
+    retains the full sequence in the output file, but obviously uses more space.
+  type:
+  - 'null'
+  - string
+- default: '8'
+  doc: number of threads to run concurrently.
+  id: param_threads
+  inputBinding:
+    prefix: -threads
+  label: number of threads to run concurrently.
+  type:
+  - 'null'
+  - int
+- default: none
+  doc: controls double-indexing.
+  id: param_query-index-type
+  inputBinding:
+    prefix: -query-index-type
+  label: controls double-indexing.
+  type:
+  - 'null'
+  - string
+- default: blastx
+  doc: Blast Operation Mode.
+  id: param_program
+  inputBinding:
+    prefix: -program
+  label: Blast Operation Mode.
+  type:
+  - 'null'
+  - string
+- default: '1'
+  doc: The translation table to use for nucl -> amino acid translation(not for BlastN,
+    BlastP). See https://www.ncbi.nlm.nih.gov/Taxonomy/Utils/wprintgc.cgi?mode=c for
+    ids (default is generic). Six frames are generated.
+  id: param_genetic-code
+  inputBinding:
+    prefix: -genetic-code
+  label: The translation table to use for nucl -> amino acid translation(not for BlastN,
+    BlastP). See https://www.ncbi.nlm.nih.gov/Taxonomy/Utils/wprintgc.cgi?mode=c for
+    ids (default is generic). Six frames are generated.
+  type:
+  - 'null'
+  - int
+- default: murphy10
+  doc: Alphabet Reduction for seeding phase (ignored for BLASTN).
+  id: param_alphabet-reduction
+  inputBinding:
+    prefix: -alphabet-reduction
+  label: Alphabet Reduction for seeding phase (ignored for BLASTN).
+  type:
+  - 'null'
+  - string
+- default: '10'
+  doc: Length of the seeds (default = 14 for BLASTN).
+  id: param_seed-length
+  inputBinding:
+    prefix: -seed-length
+  label: Length of the seeds (default = 14 for BLASTN).
+  type:
+  - 'null'
+  - int
+- default: '10'
+  doc: Offset for seeding (if unset = seed-length, non-overlapping; default = 5 for
+    BLASTN).
+  id: param_seed-offset
+  inputBinding:
+    prefix: -seed-offset
+  label: Offset for seeding (if unset = seed-length, non-overlapping; default = 5
+    for BLASTN).
+  type:
+  - 'null'
+  - int
+- default: '1'
+  doc: maximum seed distance.
+  id: param_seed-delta
+  inputBinding:
+    prefix: -seed-delta
+  label: maximum seed distance.
+  type:
+  - 'null'
+  - int
+- default: '2'
+  doc: evaluate score of a region NUM times the size of the seed before extension
+    (0 -> no pre-scoring, 1 -> evaluate seed, n-> area around seed, as well; default
+    = 1 if no reduction is used).
+  id: param_pre-scoring
+  inputBinding:
+    prefix: -pre-scoring
+  label: evaluate score of a region NUM times the size of the seed before extension
+    (0 -> no pre-scoring, 1 -> evaluate seed, n-> area around seed, as well; default
+    = 1 if no reduction is used).
+  type:
+  - 'null'
+  - int
+- default: '2.0'
+  doc: minimum average score per position in pre-scoring region.
+  id: param_pre-scoring-threshold
+  inputBinding:
+    prefix: -pre-scoring-threshold
+  label: minimum average score per position in pre-scoring region.
+  type:
+  - 'null'
+  - double
+- default: 'on'
+  doc: filter hits that will likely duplicate a match already found.
+  id: param_filter-putative-duplicates
+  inputBinding:
+    prefix: -filter-putative-duplicates
+  label: filter hits that will likely duplicate a match already found.
+  type:
+  - 'null'
+  - string
+- default: 'on'
+  doc: If the maximum number of matches per query are found already, stop searching
+    if the remaining realm looks unfeasable.
+  id: param_filter-putative-abundant
+  inputBinding:
+    prefix: -filter-putative-abundant
+  label: If the maximum number of matches per query are found already, stop searching
+    if the remaining realm looks unfeasable.
+  type:
+  - 'null'
+  - string
+- default: '62'
+  doc: use '45' for Blosum45; '62' for Blosum62 (default); '80' for Blosum80; [ignored
+    for BlastN]
+  id: param_scoring-scheme
+  inputBinding:
+    prefix: -scoring-scheme
+  label: use '45' for Blosum45; '62' for Blosum62 (default); '80' for Blosum80; [ignored
+    for BlastN]
+  type:
+  - 'null'
+  - int
+- default: '-1'
+  doc: Score per gap character (default = -2 for BLASTN).
+  id: param_score-gap
+  inputBinding:
+    prefix: -score-gap
+  label: Score per gap character (default = -2 for BLASTN).
+  type:
+  - 'null'
+  - int
+- default: '-11'
+  doc: Additional cost for opening gap (default = -5 for BLASTN).
+  id: param_score-gap-open
+  inputBinding:
+    prefix: -score-gap-open
+  label: Additional cost for opening gap (default = -5 for BLASTN).
+  type:
+  - 'null'
+  - int
+- default: '2'
+  doc: Match score [only BLASTN])
+  id: param_score-match
+  inputBinding:
+    prefix: -score-match
+  label: Match score [only BLASTN])
+  type:
+  - 'null'
+  - int
+- default: '-3'
+  doc: Mismatch score [only BLASTN]
+  id: param_score-mismatch
+  inputBinding:
+    prefix: -score-mismatch
+  label: Mismatch score [only BLASTN]
+  type:
+  - 'null'
+  - int
+- default: '30'
+  doc: Stop Banded extension if score x below the maximum seen (-1 means no xdrop).
+  id: param_x-drop
+  inputBinding:
+    prefix: -x-drop
+  label: Stop Banded extension if score x below the maximum seen (-1 means no xdrop).
+  type:
+  - 'null'
+  - int
+- default: '-3'
+  doc: Size of the DP-band used in extension (-3 means log2 of query length; -2 means
+    sqrt of query length; -1 means full dp; n means band of size 2n+1)
+  id: param_band
+  inputBinding:
+    prefix: -band
+  label: Size of the DP-band used in extension (-3 means log2 of query length; -2
+    means sqrt of query length; -1 means full dp; n means band of size 2n+1)
+  type:
+  - 'null'
+  - int
+label: the Local Aligner for Massive Biological DatA
+outputs:
+- doc: File to hold reports on hits (.m* are blastall -m* formats; .m8 is tab-seperated,
+    .m9 is tab-seperated with with comments, .m0 is pairwise format).
+  id: param_output
+  label: File to hold reports on hits (.m* are blastall -m* formats; .m8 is tab-seperated,
+    .m9 is tab-seperated with with comments, .m0 is pairwise format).
+  outputBinding:
+    glob: $(inputs.param_output_filename)
+  type:
+  - 'null'
+  - File

debian/cwl/lambda_indexer.cwl

+#!/usr/bin/env cwl-runner
+
+# This CWL file was automatically generated using CTDConverter.
+# Visit https://github.com/WorkflowConversion/CTDConverter for more information.
+
+baseCommand: lambda_indexer
+class: CommandLineTool
+cwlVersion: v1.0
+doc: "Lambda is a local aligner optimized for many query sequences and searches in\
+  \ protein space. It is compatible to BLAST, but much faster than BLAST and many\
+  \ other comparable tools.\nDetailed information is available in the wiki: <https://github.com/seqan/lambda/wiki>\n\
+  This is the indexer_binary for creating lambda-compatible databases.\n\n\n\nFor\
+  \ more information, visit http://www.seqan.de"
+inputs:
+- default: 'false'
+  doc: Display the help message with advanced options.
+  id: param_full-help
+  inputBinding:
+    prefix: -full-help
+  label: Display the help message with advanced options.
+  type:
+  - 'null'
+  - string
+- default: '1'
+  doc: 'Turn this option off to disable version update notifications of the application. '
+  id: param_version-check
+  inputBinding:
+    prefix: -version-check
+  label: 'Turn this option off to disable version update notifications of the application. '
+  type:
+  - 'null'
+  - string
+- default: 'false'
+  doc: Display long copyright information.
+  id: param_copyright
+  inputBinding:
+    prefix: -copyright
+  label: Display long copyright information.
+  type:
+  - 'null'
+  - string
+- default: '1'
+  doc: 'Display more/less diagnostic output during operation: 0 [only errors]; 1 [default];
+    2 [+run-time, options and statistics].'
+  id: param_verbosity
+  inputBinding:
+    prefix: -verbosity
+  label: 'Display more/less diagnostic output during operation: 0 [only errors]; 1
+    [default]; 2 [+run-time, options and statistics].'
+  type:
+  - 'null'
+  - int
+- doc: Database sequences.
+  id: param_database
+  inputBinding:
+    prefix: -database
+  label: Database sequences.
+  type: File
+- doc: SEG intervals for database(optional).
+  id: param_segfile
+  inputBinding:
+    prefix: -segfile
+  label: SEG intervals for database(optional).
+  type:
+  - 'null'
+  - File
+- default: fm
+  doc: Suffix array or full-text minute space.
+  id: param_db-index-type
+  inputBinding:
+    prefix: -db-index-type
+  label: Suffix array or full-text minute space.
+  type:
+  - 'null'
+  - string
+- default: 'on'
+  doc: Truncate IDs at first whitespace. This saves a lot of space and is irrelevant
+    for all LAMBDA output formats other than BLAST Pairwise (.m0).
+  id: param_truncate-ids
+  inputBinding:
+    prefix: -truncate-ids
+  label: Truncate IDs at first whitespace. This saves a lot of space and is irrelevant
+    for all LAMBDA output formats other than BLAST Pairwise (.m0).
+  type:
+  - 'null'
+  - string
+- default: blastx
+  doc: Blast Operation Mode.
+  id: param_program
+  inputBinding:
+    prefix: -program
+  label: Blast Operation Mode.
+  type:
+  - 'null'
+  - string
+- default: '1'
+  doc: The translation table to use (not for BlastN, BlastP). See https://www.ncbi.nlm.nih.gov/Taxonomy/Utils/wprintgc.cgi?mode=c
+    for ids (default is generic).
+  id: param_genetic-code
+  inputBinding:
+    prefix: -genetic-code
+  label: The translation table to use (not for BlastN, BlastP). See https://www.ncbi.nlm.nih.gov/Taxonomy/Utils/wprintgc.cgi?mode=c
+    for ids (default is generic).
+  type:
+  - 'null'
+  - int
+- default: murphy10
+  doc: Alphabet Reduction for seeding phase (ignored for BLASTN).
+  id: param_alphabet-reduction
+  inputBinding:
+    prefix: -alphabet-reduction
+  label: Alphabet Reduction for seeding phase (ignored for BLASTN).
+  type:
+  - 'null'
+  - string
+- default: radixsort
+  doc: Algorithm for SA construction (also used for FM; see Memory  Requirements below!).
+  id: param_algorithm
+  inputBinding:
+    prefix: -algorithm
+  label: Algorithm for SA construction (also used for FM; see Memory  Requirements
+    below!).
+  type:
+  - 'null'
+  - string
+- default: '8'
+  doc: number of threads to run concurrently (ignored if a == skew7ext).
+  id: param_threads
+  inputBinding:
+    prefix: -threads
+  label: number of threads to run concurrently (ignored if a == skew7ext).
+  type:
+  - 'null'
+  - int
+- default: /home/mcrusoe/debian/lambda-align
+  doc: temporary directory used by skew, defaults to working directory.
+  id: param_tmp-dir
+  inputBinding:
+    prefix: -tmp-dir
+  label: temporary directory used by skew, defaults to working directory.
+  type:
+  - 'null'
+  - string
+label: indexer for creating lambda-compatible databases

debian/lintian-overrides

-# The term 'iff' actually exists and means 'if anf only if'.
-lambda-align: spelling-error-in-binary usr/bin/lambda iff if
-lambda-align: spelling-error-in-binary usr/bin/lambda_indexer iff if
-lambda-align: spelling-error-in-manpage usr/share/man/man1/lambda.1.gz iff if

debian/patches/force-link-rt-pthread.patch

@@ -2,9 +2,9 @@ Description: enforce linking of -lrt -lpthread
  This patch makes sure that these get linked even though they might
  be missing in $SEQAN_LIBRARIES (until this is fixed in libseqan2-dev).
 Author: Sascha Steinbiss <satta@debian.org>
---- a/src/CMakeLists.txt
-+++ b/src/CMakeLists.txt
-@@ -207,8 +207,8 @@
+--- lambda-align.orig/src/CMakeLists.txt
++++ lambda-align/src/CMakeLists.txt
+@@ -208,8 +208,8 @@
                  radix_inplace.h)
  
  # Add dependencies found by find_package (SeqAn).

debian/rules

@@ -25,3 +25,6 @@ override_dh_installman:
 
 override_dh_auto_configure:
 	dh_auto_configure -- -DLAMBDA_NATIVE_BUILD=OFF -DLAMBDA_MMAPPED_DB=ON -DCMAKE_BUILD_TYPE=Release
+
+override_dh_auto_test:
+	cd build/tests && ctest --parallel $(shell nproc)

debian/tests/control

+Tests: run-tests
+Depends: lambda-align, openssl, gzip, coreutils, diffutils
+Restrictions: allow-stderr

debian/tests/run-tests

+#!/bin/sh -e
+
+mkdir build
+cd build
+cmake ../
+for binary in $(dpkg -L lambda-align); do ln -s ${binary} bin/; done
+ctest  --parallel $(nproc)
+

src/holders.hpp

@@ -385,7 +385,16 @@ public:
                             ArrayGaps>;
     using TAlignRow1 = Gaps<typename Infix<typename Value<typename TGlobalHolder::TTransSubjSeqs>::Type>::Type,
                             ArrayGaps>;
+#if (SEQAN_VERSION_MINOR < 4)
     using TDPContext =  DPContext<typename Value<typename TGlobalHolder::TScoreScheme>::Type, TScoreExtension>;
+#else
+    using TCellValue  = int16_t;
+    using TDPCell     = DPCell_<TCellValue, TScoreExtension>;
+    using TTraceValue = typename TraceBitMap_<TCellValue>::Type;
+    using TScoreHost  = String<TDPCell, Alloc<OverAligned> >;
+    using TTraceHost  = String<TTraceValue, Alloc<OverAligned> >;
+    using TDPContext  = DPContext<TDPCell, TTraceValue, TScoreHost, TTraceHost>;
+#endif
     using TAliExtContext = AliExtContext_<TAlignRow0, TAlignRow1, TDPContext>;
 
     TAliExtContext      alignContext;

src/options.hpp

@@ -420,14 +420,14 @@ parseCommandLine(LambdaOptions & options, int argc, char const ** argv)
         "Query sequences.",
         ArgParseArgument::INPUT_FILE,
         "IN"));
-    setValidValues(parser, "query", toCString(concat(getFileExtensions(SeqFileIn()), ' ')));
+    setValidValues(parser, "query", getFileExtensions(SeqFileIn()));
     setRequired(parser, "q");
 
     addOption(parser, ArgParseOption("d", "database",
         "Path to original database sequences (a precomputed index with .sa or .fm needs to exist!).",
         ArgParseArgument::INPUT_FILE,
         "IN"));
-    setValidValues(parser, "database", toCString(concat(getFileExtensions(SeqFileIn()), ' ')));
+    setValidValues(parser, "database", getFileExtensions(SeqFileIn()));
     setRequired(parser, "d");
 
     addOption(parser, ArgParseOption("di", "db-index-type",
@@ -1048,7 +1048,7 @@ parseCommandLine(LambdaIndexerOptions & options, int argc, char const ** argv)
         ArgParseArgument::INPUT_FILE,
         "IN"));
     setRequired(parser, "database");
-    setValidValues(parser, "database", toCString(concat(getFileExtensions(SeqFileIn()), ' ')));
+    setValidValues(parser, "database", getFileExtensions(SeqFileIn()));
 
     addOption(parser, ArgParseOption("s",
         "segfile",