.gitignore

-# This file is used to ignore files which are generated
-# ----------------------------------------------------------------------------
-
-*~
-*.autosave
-*.a
-*.core
-*.moc
-*.o
-*.obj
-*.orig
-*.rej
-*.so
-*.so.*
-*_pch.h.cpp
-*_resource.rc
-*.qm
-.#*
-*.*#
-core
-!core/
-tags
 .DS_Store
-.directory
-*.debug
-Makefile*
-*.prl
-*.app
-moc_*.cpp
-ui_*.h
-qrc_*.cpp
-Thumbs.db
-*.res
-*.rc
-/.qmake.cache
-/.qmake.stash
-
-# qtcreator generated files
-*.pro.user*
-CMakeLists.txt.user
-
-# xemacs temporary files
-*.flc
-
-# Vim temporary files
-.*.swp
-
-# Visual Studio generated files
-*.ib_pdb_index
-*.idb
-*.ilk
-*.pdb
-*.sln
-*.suo
-*.vcproj
-*vcproj.*.*.user
-*.ncb
-*.sdf
-*.opensdf
-*.vcxproj
-*vcxproj.*
+/build*
 
-.vscode
-
-# MinGW generated files
-*.Debug
-*.Release
-
-# Python byte code
+# cram
 *.pyc
 
-# Binaries
-# --------
-*.dll
-*.exe
-
-# Generated directories
-bin
-build
-lib
-
 # Meson WrapDB stuff
-subprojects/packagecache/
-subprojects/googletest*
-
-# generated Doxyfile
-*Doxyfile
+/subprojects/*
+!/subprojects/*.wrap

CHANGELOG.md

@@ -3,13 +3,85 @@
 All notable changes to this project will be documented in this file.
 This project adheres to [Semantic Versioning](http://semver.org/).
 
-**NOTE:** The current series (0.y.z) is under initial development. Anything may
-change at any time. The public API should not be considered stable yet. Once we
-lock down a version 1.0.0, this will define a reference point & compatibility
-guarantees will be maintained within each major version series.
-
 ## Active
 
+### Added
+ - CCSRecord API to work with the minimally required data for CCS
+ - TextFileReader & TextFileWriter for generic line files (plain text or gzipped)
+ - BedReader & BedWriter for BED format support
+
+## [1.0.6] - 2019-06-14
+
+### Added
+ - IFastaWriter & IFastqWriter abstract base classes
+
+## [1.0.5] - 2019-06-11
+
+### Changed
+ - BAM tag lookup improvements under the hood.
+
+## [1.0.4] - 2019-06-07
+
+### Added
+ - General-purpose BgzipWriter
+ - BgzipFastaWriter and BgzipFastqWriter
+ - Read-only view to read indices passing a PbiFilter
+ - IPD field to SimpleRead
+
+## [1.0.3] - 2019-05-20
+
+### Added
+ - IndexedFastqReader for random access to FASTQ subregions
+
+### Fixed
+ - MappedSimpleRead clipping: on disjoint aligned/requested regions and on requests larger
+   than available sequence.
+
+## [1.0.2] - 2019-05-10
+
+### Added
+ - Range-for iteration on FastaReader & FastqReader
+
+## [1.0.1] - 2019-05-09
+
+### Added
+ - SimpleRead & MappedSimpleRead for htslib-free processing.
+
+### Fixed
+ - Incorrect type displayed in SAM output (pure-text) for floating-point values.
+
+## [1.0.0] - 2019-04-22
+
+### Changed
+ - C++14 is now a *hard* minimum.
+
+### Removed
+ - Headers emulating C++14 features for C++11.
+
+### Fixed
+ - Inconsistent whitelist/blacklist filters in DataSet XML.
+
+## [0.25.0] - 2019-04-11
+
+### Changed
+ - Requires C++14 at minimum.
+
+### Fixed
+ - Reading BioSample(s) elements from DataSet XML.
+
+## [0.24.0] - 2019-04-05
+
+### Added
+ - Built-in support for dataset elements: BioSample(s) & DNABarcode(s).
+ - BaiIndexCache for reusing data from *.bai files(s).
+ - Support in GenomicIntervalQuery for new BaiIndexCache.
+
+## [0.23.1] - 2019-03-21
+
+### Added
+ - Streamable BamReader (via stdin).
+ - Enabled range-for on BamReader, compatible with the other *Query inputs.
+
 ## [0.23.0] - 2019-03-11
 
 ### Added

bamboo_build.sh

@@ -45,7 +45,7 @@ unset BOOST_LIBRARYDIR
 
 # in order to make shared libraries consumable
 # by conda and other package managers
-export LDFLAGS="-static-libstdc++ -static-libgcc"
+export LDFLAGS=${LDFLAGS:-"-fuse-ld=gold -static-libstdc++ -static-libgcc"}
 
 source scripts/ci/setup.sh
 source scripts/ci/build.sh

debian/changelog

+pbbam (1.0.6+dfsg-1) UNRELEASED; urgency=medium
+
+  * Drop <!nocheck> option from python3-cram
+    Closes: #934467
+  * New upstream version
+  * Standards-Version: 4.4.1
+  * Remove patch debug_tests.patch that is missing from
+    debian/patches/series.
+  * debian/copyright: use spaces rather than tabs to start continuation
+    lines.
+  * Remove obsolete fields Contact, Name from debian/upstream/metadata.
+  * Build-Depends: cmake, libpbcopper-dev (>= 1.3.0)
+
+  TODO: ...  -Wl,--as-needed -Wl,--no-undefined -shared -fPIC -Wl,--start-group -Wl,-soname,libpbbam.so.1.0.6 -g -O2 -fdebug-prefix-map=/build/pbbam-1.0.6+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -Wl,-z,relro -Wl,-z,now -pthread /usr/lib/x86_64-linux-gnu/libz.so /usr/lib/x86_64-linux-gnu/libhts.so -lpbcopper -Wl,--end-group
+    FAILED: src/libpbbam.so.1.0.6 
+    c++  -o src/libpbbam.so.1.0.6 'src/25a6634@@pbbam@sha/AlignmentPrinter.cpp.o' 'src/25a6634@@pbbam@sha/BaiIndexCache.cpp.o' 'src/25a6634@@pbbam@sha/BaiIndexedBamReader.cpp.o' 'src/25a6634@@pbbam@sha/BamFile.cpp.o' 'src/25a6634@@pbbam@sha/BamFileMerger.cpp.o' 'src/25a6634@@pbbam@sha/BamHeader.cpp.o' 'src/25a6634@@pbbam@sha/BamReader.cpp.o' 'src/25a6634@@pbbam@sha/BamRecord.cpp.o' 'src/25a6634@@pbbam@sha/BamRecordBuilder.cpp.o' 'src/25a6634@@pbbam@sha/BamRecordImpl.cpp.o' 'src/25a6634@@pbbam@sha/BamRecordTags.cpp.o' 'src/25a6634@@pbbam@sha/BamRecordView.cpp.o' 'src/25a6634@@pbbam@sha/BamTagCodec.cpp.o' 'src/25a6634@@pbbam@sha/BamWriter.cpp.o' 'src/25a6634@@pbbam@sha/BarcodeQuery.cpp.o' 'src/25a6634@@pbbam@sha/BgzipFastaWriter.cpp.o' 'src/25a6634@@pbbam@sha/BgzipFastqWriter.cpp.o' 'src/25a6634@@pbbam@sha/BgzipWriter.cpp.o' 'src/25a6634@@pbbam@sha/ChemistryTable.cpp.o' 'src/25a6634@@pbbam@sha/Compare.cpp.o' 'src/25a6634@@pbbam@sha/CompositeFastaReader.cpp.o' 'src/25a6634@@pbbam@sha/Config.cpp.o' 'src/25a6634@@pbbam@sha/DataSet.cpp.o' 'src/25a6634@@pbbam@sha/DataSetBaseTypes.cpp.o' 'src/25a6634@@pbbam@sha/DataSetElement.cpp.o' 'src/25a6634@@pbbam@sha/DataSetIO.cpp.o' 'src/25a6634@@pbbam@sha/DataSetTypes.cpp.o' 'src/25a6634@@pbbam@sha/DataSetXsd.cpp.o' 'src/25a6634@@pbbam@sha/EntireFileQuery.cpp.o' 'src/25a6634@@pbbam@sha/FaiIndex.cpp.o' 'src/25a6634@@pbbam@sha/FaiZmwChunker.cpp.o' 'src/25a6634@@pbbam@sha/FastaCache.cpp.o' 'src/25a6634@@pbbam@sha/FastaReader.cpp.o' 'src/25a6634@@pbbam@sha/FastaSequence.cpp.o' 'src/25a6634@@pbbam@sha/FastaSequenceQuery.cpp.o' 'src/25a6634@@pbbam@sha/FastaWriter.cpp.o' 'src/25a6634@@pbbam@sha/FastqReader.cpp.o' 'src/25a6634@@pbbam@sha/FastqSequence.cpp.o' 'src/25a6634@@pbbam@sha/FastqWriter.cpp.o' 'src/25a6634@@pbbam@sha/FileProducer.cpp.o' 'src/25a6634@@pbbam@sha/FileUtils.cpp.o' 'src/25a6634@@pbbam@sha/FofnReader.cpp.o' 'src/25a6634@@pbbam@sha/FormatUtils.cpp.o' 'src/25a6634@@pbbam@sha/GenomicIntervalQuery.cpp.o' 'src/25a6634@@pbbam@sha/IFastaWriter.cpp.o' 'src/25a6634@@pbbam@sha/IFastqWriter.cpp.o' 'src/25a6634@@pbbam@sha/IndexedBamWriter.cpp.o' 'src/25a6634@@pbbam@sha/IndexedFastaReader.cpp.o' 'src/25a6634@@pbbam@sha/IndexedFastqBgzfReader.cpp.o' 'src/25a6634@@pbbam@sha/IndexedFastqReader.cpp.o' 'src/25a6634@@pbbam@sha/IndexedFastqTextReader.cpp.o' 'src/25a6634@@pbbam@sha/IndexedFastqReaderImpl.cpp.o' 'src/25a6634@@pbbam@sha/IRecordWriter.cpp.o' 'src/25a6634@@pbbam@sha/KSeqReader.cpp.o' 'src/25a6634@@pbbam@sha/MD5.cpp.o' 'src/25a6634@@pbbam@sha/MemoryUtils.cpp.o' 'src/25a6634@@pbbam@sha/PbiBuilder.cpp.o' 'src/25a6634@@pbbam@sha/PbiFile.cpp.o' 'src/25a6634@@pbbam@sha/PbiFilter.cpp.o' 'src/25a6634@@pbbam@sha/PbiFilterQuery.cpp.o' 'src/25a6634@@pbbam@sha/PbiFilterTypes.cpp.o' 'src/25a6634@@pbbam@sha/PbiIndexedBamReader.cpp.o' 'src/25a6634@@pbbam@sha/PbiIndexIO.cpp.o' 'src/25a6634@@pbbam@sha/PbiRawData.cpp.o' 'src/25a6634@@pbbam@sha/ProgramInfo.cpp.o' 'src/25a6634@@pbbam@sha/QNameQuery.cpp.o' 'src/25a6634@@pbbam@sha/ReadAccuracyQuery.cpp.o' 'src/25a6634@@pbbam@sha/ReadGroupInfo.cpp.o' 'src/25a6634@@pbbam@sha/RecordType.cpp.o' 'src/25a6634@@pbbam@sha/SamTagCodec.cpp.o' 'src/25a6634@@pbbam@sha/SamWriter.cpp.o' 'src/25a6634@@pbbam@sha/SequenceInfo.cpp.o' 'src/25a6634@@pbbam@sha/StringUtilities.cpp.o' 'src/25a6634@@pbbam@sha/SubreadLengthQuery.cpp.o' 'src/25a6634@@pbbam@sha/Tag.cpp.o' 'src/25a6634@@pbbam@sha/TagCollection.cpp.o' 'src/25a6634@@pbbam@sha/TextFileReader.cpp.o' 'src/25a6634@@pbbam@sha/TextFileWriter.cpp.o' 'src/25a6634@@pbbam@sha/Validator.cpp.o' 'src/25a6634@@pbbam@sha/ValidationErrors.cpp.o' 'src/25a6634@@pbbam@sha/ValidationException.cpp.o' 'src/25a6634@@pbbam@sha/Version.cpp.o' 'src/25a6634@@pbbam@sha/VirtualZmwBamRecord.cpp.o' 'src/25a6634@@pbbam@sha/VirtualZmwCompositeReader.cpp.o' 'src/25a6634@@pbbam@sha/VirtualZmwReader.cpp.o' 'src/25a6634@@pbbam@sha/VirtualRegion.cpp.o' 'src/25a6634@@pbbam@sha/VirtualRegionTypeMap.cpp.o' 'src/25a6634@@pbbam@sha/XmlReader.cpp.o' 'src/25a6634@@pbbam@sha/XmlWriter.cpp.o' 'src/25a6634@@pbbam@sha/WhitelistedZmwReadStitcher.cpp.o' 'src/25a6634@@pbbam@sha/ZmwChunkedFastaReader.cpp.o' 'src/25a6634@@pbbam@sha/ZmwChunkedFastqReader.cpp.o' 'src/25a6634@@pbbam@sha/ZmwChunkedFastxBgzfReader.cpp.o' 'src/25a6634@@pbbam@sha/ZmwChunkedFastxReaderImpl.cpp.o' 'src/25a6634@@pbbam@sha/ZmwChunkedFastxTextReader.cpp.o' 'src/25a6634@@pbbam@sha/ZmwGroupQuery.cpp.o' 'src/25a6634@@pbbam@sha/ZmwReadStitcher.cpp.o' 'src/25a6634@@pbbam@sha/ZmwQuery.cpp.o' 'src/25a6634@@pbbam@sha/ZmwTypeMap.cpp.o' 'src/25a6634@@pbbam@sha/bed_BedReader.cpp.o' 'src/25a6634@@pbbam@sha/bed_BedWriter.cpp.o' 'src/25a6634@@pbbam@sha/ccs_CCSPbiBuilder.cpp.o' 'src/25a6634@@pbbam@sha/ccs_CCSRecordFormat.cpp.o' 'src/25a6634@@pbbam@sha/ccs_CCSRecordReader.cpp.o' 'src/25a6634@@pbbam@sha/ccs_CCSRecordWriter.cpp.o' 'src/25a6634@@pbbam@sha/vcf_VcfFile.cpp.o' 'src/25a6634@@pbbam@sha/vcf_VcfFormat.cpp.o' 'src/25a6634@@pbbam@sha/vcf_VcfHeader.cpp.o' 'src/25a6634@@pbbam@sha/vcf_VcfHeaderTypes.cpp.o' 'src/25a6634@@pbbam@sha/vcf_VcfQuery.cpp.o' 'src/25a6634@@pbbam@sha/vcf_VcfReader.cpp.o' 'src/25a6634@@pbbam@sha/vcf_VcfSort.cpp.o' 'src/25a6634@@pbbam@sha/vcf_VcfVariant.cpp.o' 'src/25a6634@@pbbam@sha/vcf_VcfWriter.cpp.o' 'src/25a6634@@pbbam@sha/pugixml_pugixml.cpp.o' -Wl,--as-needed -Wl,--no-undefined -shared -fPIC -Wl,--start-group -Wl,-soname,libpbbam.so.1.0.6 -g -O2 -fdebug-prefix-map=/build/pbbam-1.0.6+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -Wl,-z,relro -Wl,-z,now -pthread /usr/lib/x86_64-linux-gnu/libz.so /usr/lib/x86_64-linux-gnu/libhts.so -lpbcopper -Wl,--end-group
+    /usr/bin/ld: cannot find -lpbcopper
+    collect2: error: ld returned 1 exit status
+
+ -- Andreas Tille <tille@debian.org>  Fri, 13 Dec 2019 21:50:03 +0100
+
 pbbam (0.23.0+dfsg-1) unstable; urgency=medium
 
   * Afif removed himself from Uploaders

debian/control

@@ -8,15 +8,17 @@ Build-Depends: debhelper-compat (= 12),
                d-shlibs,
                meson,
                pkg-config,
+               cmake,
 # swig3.0,
                libboost-dev,
                zlib1g-dev,
                libssl-dev,
                libhts-dev,
+               libpbcopper-dev (>= 1.3.0),
+               python3-cram,
                libgtest-dev <!nocheck>,
-               python3-cram <!nocheck>,
                samtools <!nocheck>
-Standards-Version: 4.4.0
+Standards-Version: 4.4.1
 Vcs-Browser: https://salsa.debian.org/med-team/pbbam
 Vcs-Git: https://salsa.debian.org/med-team/pbbam.git
 Homepage: http://pbbam.readthedocs.org/en/latest/index.html

debian/patches/debug_tests.patch

-Description: Only debug code to track down bug #909071 i386 (no solution yet)
-Bug-Debian: https://bugs.debian.org/909071
-Author: Andreas Tille <tille@debian.org>
-Last-Update:  Tue, 18 Sep 2018 08:40:19 +0200
-
---- a/tests/src/cram/pbmerge_pacbio_ordering.t.in
-+++ b/tests/src/cram/pbmerge_pacbio_ordering.t.in
-@@ -13,6 +13,8 @@ Setup:
- 
- Sanity Check:
- 
-+  $ ls -l $HQREGION_BAM
-+  $ echo "DEBUG: $BAM2SAM --header-only $HQREGION_BAM"
-   $ $BAM2SAM --header-only $HQREGION_BAM
-   @HD\tVN:1.1\tSO:unknown\tpb:3.0.1 (esc)
-   @RG\tID:ca75d884\tPL:PACBIO\tDS:READTYPE=HQREGION;DeletionQV=dq;DeletionTag=dt;InsertionQV=iq;MergeQV=mq;SubstitutionQV=sq;SubstitutionTag=st;Ipd:Frames=ip;PulseWidth:Frames=pw;PkMid=pm;PkMean=pa;LabelQV=pq;AltLabel=pt;AltLabelQV=pv;PulseMergeQV=pg;PulseCall=pc;PrePulseFrames=pd;PulseCallWidth=px;BINDINGKIT=100372700;SEQUENCINGKIT=100356200;BASECALLERVERSION=0.1;FRAMERATEHZ=100.000000\tPU:ArminsFakeMovie (esc)
-@@ -20,9 +22,11 @@ Sanity Check:
-   @PG\tID:bazFormat-0.3.0\tPN:bazFormat\tVN:0.3.0 (esc)
-   @PG\tID:bazwriter-0.15.0\tPN:bazwriter\tVN:0.15.0 (esc)
- 
-+  $ echo "DEBUG: $BAM2SAM --no-header $HQREGION_BAM | cut -f 1"
-   $ $BAM2SAM --no-header $HQREGION_BAM | cut -f 1
-   ArminsFakeMovie/100000/2659_7034
- 
-+  $ $echo "DEBUG: BAM2SAM --header-only $SCRAPS_BAM"
-   $ $BAM2SAM --header-only $SCRAPS_BAM
-   @HD\tVN:1.1\tSO:unknown\tpb:3.0.1 (esc)
-   @RG\tID:e83fc9c6\tPL:PACBIO\tDS:READTYPE=SCRAP;DeletionQV=dq;DeletionTag=dt;InsertionQV=iq;MergeQV=mq;SubstitutionQV=sq;SubstitutionTag=st;Ipd:Frames=ip;PulseWidth:Frames=pw;PkMid=pm;PkMean=pa;LabelQV=pq;AltLabel=pt;AltLabelQV=pv;PulseMergeQV=pg;PulseCall=pc;PrePulseFrames=pd;PulseCallWidth=px;BINDINGKIT=100372700;SEQUENCINGKIT=100356200;BASECALLERVERSION=0.1;FRAMERATEHZ=100.000000\tPU:ArminsFakeMovie (esc)
-@@ -30,6 +34,7 @@ Sanity Check:
-   @PG\tID:bazFormat-0.3.0\tPN:bazFormat\tVN:0.3.0 (esc)
-   @PG\tID:bazwriter-0.15.0\tPN:bazwriter\tVN:0.15.0 (esc)
- 
-+  $ echo "DEBUG: $BAM2SAM --no-header $SCRAPS_BAM | cut -f 1"
-   $ $BAM2SAM --no-header $SCRAPS_BAM | cut -f 1
-   ArminsFakeMovie/100000/0_2659
-   ArminsFakeMovie/100000/3025_3047
---- a/tests/src/cram/pbmerge_aligned_ordering.t.in
-+++ b/tests/src/cram/pbmerge_aligned_ordering.t.in
-@@ -51,7 +51,10 @@ Sanity Check:
- 
- Normal Merge:
- 
-+  $ echo "DEBUG: $PBMERGE $INPUT_1 $INPUT_2 > $MERGED_BAM"
-   $ $PBMERGE $INPUT_1 $INPUT_2 > $MERGED_BAM
-+  $ if [ ! -f $MERGED_BAM ] ; then echo "FIX 1: File $MERGED_BAM does not exists - no idea why. Try again creating it after 5s."; $PBMERGE $INPUT_1 $INPUT_2 > $MERGED_BAM ; fi
-+  $ if [ ! -f $MERGED_BAM ] ; then echo "FIX 1: File $MERGED_BAM does not exists - even after trying again."; exit ; else echo echo "File $MERGED_BAM was created now" ; fi
- 
-   $ $BAM2SAM --header-only $MERGED_BAM
-   @HD\tVN:1.3.1\tSO:coordinate\tpb:3.0.1 (esc)
-@@ -60,6 +63,7 @@ Normal Merge:
-   @PG\tID:BLASR\tVN:1.3.1.141565\tCL:/home/UNIXHOME/yli/for_the_people/blasr_bam_out/blasr m140905_042212_sidney_c100564852550000001823085912221377_s1_X0.1.bax.h5 lambdaNEB.fa -out tmp.bam -bam -bestn 10 -minMatch 12 -nproc 8 -minSubreadLength 50 -minReadLength 50 -randomSeed 1 -clipping subread  (esc)
-   @PG\tID:pbmerge-@PacBioBAM_VERSION@\tPN:pbmerge\tVN:@PacBioBAM_VERSION@ (esc)
- 
-+  $ echo "DEBUG: $BAM2SAM --no-header $MERGED_BAM | cut -f 1,3,4 | head -n 20"
-   $ $BAM2SAM --no-header $MERGED_BAM | cut -f 1,3,4 | head -n 20
-   m140905_042212_sidney_c100564852550000001823085912221377_s1_X0/49050/48_1132\tlambda_NEB3011\t1 (esc)
-   m140905_042212_sidney_c100564852550000001823085912221377_s1_X0/32328/387_1134\tlambda_NEB3011\t303 (esc)
-@@ -86,8 +90,15 @@ Normal Merge:
- 
- Shuffle Input:
- 
-+  $ echo DEBUG: PATH = $PATH
-+  $ which pbmerge
-+  $ echo "DEBUG: $PBMERGE $INPUT_2 $INPUT_2 > $MERGED_BAM"
-   $ $PBMERGE $INPUT_2 $INPUT_2 > $MERGED_BAM
-+  $ if [ ! -f $MERGED_BAM ] ; then echo "FIX 2: File $MERGED_BAM does not exists - no idea why. Try again creating it after 5s."; $PBMERGE $INPUT_1 $INPUT_2 > $MERGED_BAM ; fi
-+  $ if [ ! -f $MERGED_BAM ] ; then echo "FIX 2: File $MERGED_BAM does not exists - even after trying again."; exit ; else echo echo "File $MERGED_BAM was created now" ; fi
- 
-+  $ echo "DEBUG: $BAM2SAM --header-only $MERGED_BAM"
-+  $ echo "DEBUG: That is the problematic command"
-   $ $BAM2SAM --header-only $MERGED_BAM
-   @HD\tVN:1.3.1\tSO:coordinate\tpb:3.0.1 (esc)
-   @SQ\tSN:lambda_NEB3011\tLN:48502\tM5:a1319ff90e994c8190a4fe6569d0822a (esc)
-@@ -95,6 +106,7 @@ Shuffle Input:
-   @PG\tID:BLASR\tVN:1.3.1.141565\tCL:/home/UNIXHOME/yli/for_the_people/blasr_bam_out/blasr m140905_042212_sidney_c100564852550000001823085912221377_s1_X0.1.bax.h5 lambdaNEB.fa -out tmp.bam -bam -bestn 10 -minMatch 12 -nproc 8 -minSubreadLength 50 -minReadLength 50 -randomSeed 1 -clipping subread  (esc)
-   @PG\tID:pbmerge-@PacBioBAM_VERSION@\tPN:pbmerge\tVN:@PacBioBAM_VERSION@ (esc)
- 
-+  $ echo "DEBUG: $BAM2SAM --no-header $MERGED_BAM | cut -f 1,3,4 | head -n 20"
-   $ $BAM2SAM --no-header $MERGED_BAM | cut -f 1,3,4 | head -n 20
-   m140905_042212_sidney_c100564852550000001823085912221377_s1_X0/32328/387_1134\tlambda_NEB3011\t303 (esc)
-   m140905_042212_sidney_c100564852550000001823085912221377_s1_X0/6469/9936_10187\tlambda_NEB3011\t2171 (esc)
-@@ -130,6 +142,7 @@ Explicit Output Filename (also enables P
-   @PG\tID:BLASR\tVN:1.3.1.141565\tCL:/home/UNIXHOME/yli/for_the_people/blasr_bam_out/blasr m140905_042212_sidney_c100564852550000001823085912221377_s1_X0.1.bax.h5 lambdaNEB.fa -out tmp.bam -bam -bestn 10 -minMatch 12 -nproc 8 -minSubreadLength 50 -minReadLength 50 -randomSeed 1 -clipping subread  (esc)
-   @PG\tID:pbmerge-@PacBioBAM_VERSION@\tPN:pbmerge\tVN:@PacBioBAM_VERSION@ (esc)
- 
-+  $ echo "DEBUG: $BAM2SAM --no-header $MERGED_BAM | cut -f 1,3,4 | head -n 20"
-   $ $BAM2SAM --no-header $MERGED_BAM | cut -f 1,3,4 | head -n 20
-   m140905_042212_sidney_c100564852550000001823085912221377_s1_X0/49050/48_1132\tlambda_NEB3011\t1 (esc)
-   m140905_042212_sidney_c100564852550000001823085912221377_s1_X0/32328/387_1134\tlambda_NEB3011\t303 (esc)
-@@ -169,6 +182,7 @@ Explicit Output Filename (with disabled
-   @PG\tID:BLASR\tVN:1.3.1.141565\tCL:/home/UNIXHOME/yli/for_the_people/blasr_bam_out/blasr m140905_042212_sidney_c100564852550000001823085912221377_s1_X0.1.bax.h5 lambdaNEB.fa -out tmp.bam -bam -bestn 10 -minMatch 12 -nproc 8 -minSubreadLength 50 -minReadLength 50 -randomSeed 1 -clipping subread  (esc)
-   @PG\tID:pbmerge-@PacBioBAM_VERSION@\tPN:pbmerge\tVN:@PacBioBAM_VERSION@ (esc)
- 
-+  $ echo "DEBUG: $BAM2SAM --no-header $MERGED_BAM | cut -f 1,3,4 | head -n 20"
-   $ $BAM2SAM --no-header $MERGED_BAM | cut -f 1,3,4 | head -n 20
-   m140905_042212_sidney_c100564852550000001823085912221377_s1_X0/49050/48_1132\tlambda_NEB3011\t1 (esc)
-   m140905_042212_sidney_c100564852550000001823085912221377_s1_X0/32328/387_1134\tlambda_NEB3011\t303 (esc)

debian/upstream/metadata

-Name: pbbam
-Contact: Pacific Biosciences <devnet@pacificbiosciences.com>

docs/source/conf.py

@@ -103,9 +103,9 @@ author = u'Derek Barnett'
 # built documents.
 #
 # The short X.Y version.
-version = '0.23.0'
+version = '1.0.6'
 # The full version, including alpha/beta/rc tags.
-release = '0.23.0'
+release = '1.0.6'
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

include/meson.build

@@ -7,6 +7,7 @@ if not meson.is_subproject()
     files([
       'pbbam/Accuracy.h',
       'pbbam/AlignmentPrinter.h',
+      'pbbam/BaiIndexCache.h',
       'pbbam/BaiIndexedBamReader.h',
       'pbbam/BamFile.h',
       'pbbam/BamFileMerger.h',
@@ -20,6 +21,9 @@ if not meson.is_subproject()
       'pbbam/BamTagCodec.h',
       'pbbam/BamWriter.h',
       'pbbam/BarcodeQuery.h',
+      'pbbam/BgzipFastaWriter.h',
+      'pbbam/BgzipFastqWriter.h',
+      'pbbam/BgzipWriter.h',
       'pbbam/Cigar.h',
       'pbbam/CigarOperation.h',
       'pbbam/ClipType.h',
@@ -31,6 +35,7 @@ if not meson.is_subproject()
       'pbbam/DataSetTypes.h',
       'pbbam/DataSetXsd.h',
       'pbbam/EntireFileQuery.h',
+      'pbbam/FaiIndex.h',
       'pbbam/FastaCache.h',
       'pbbam/FastaReader.h',
       'pbbam/FastaSequence.h',
@@ -39,16 +44,19 @@ if not meson.is_subproject()
       'pbbam/FastqReader.h',
       'pbbam/FastqSequence.h',
       'pbbam/FastqWriter.h',
+      'pbbam/FormatUtils.h',
       'pbbam/FrameEncodingType.h',
       'pbbam/Frames.h',
       'pbbam/GenomicInterval.h',
       'pbbam/GenomicIntervalQuery.h',
+      'pbbam/IFastaWriter.h',
+      'pbbam/IFastqWriter.h',
       'pbbam/IndexedBamWriter.h',
       'pbbam/IndexedFastaReader.h',
+      'pbbam/IndexedFastqReader.h',
       'pbbam/Interval.h',
       'pbbam/IRecordWriter.h',
       'pbbam/LocalContextFlags.h',
-      'pbbam/MakeUnique.h',
       'pbbam/MD5.h',
       'pbbam/MoveAppend.h',
       'pbbam/Orientation.h',
@@ -73,11 +81,14 @@ if not meson.is_subproject()
       'pbbam/SamTagCodec.h',
       'pbbam/SamWriter.h',
       'pbbam/SequenceInfo.h',
+      'pbbam/SNR.h',
       'pbbam/Strand.h',
       'pbbam/StringUtilities.h',
       'pbbam/SubreadLengthQuery.h',
       'pbbam/Tag.h',
       'pbbam/TagCollection.h',
+      'pbbam/TextFileReader.h',
+      'pbbam/TextFileWriter.h',
       'pbbam/Unused.h',
       'pbbam/Validator.h',
       'pbbam/ZmwGroupQuery.h',
@@ -86,6 +97,22 @@ if not meson.is_subproject()
       'pbbam/ZmwTypeMap.h']),
     subdir : 'pbbam')
 
+  install_headers(
+    files([
+      'pbbam/bed/BedReader.h',
+      'pbbam/bed/BedWriter.h']),
+    subdir : 'pbbam/bed')
+
+  install_headers(
+    files([
+      'pbbam/ccs/CCSHeader.h',
+      'pbbam/ccs/CCSPbiBuilder.h',
+      'pbbam/ccs/CCSRecord.h',
+      'pbbam/ccs/CCSRecordFormat.h',
+      'pbbam/ccs/CCSRecordReader.h',
+      'pbbam/ccs/CCSRecordWriter.h']),
+    subdir : 'pbbam/ccs')
+
   install_headers(
     files([
       'pbbam/exception/BundleChemistryMappingException.h',
@@ -100,7 +127,6 @@ if not meson.is_subproject()
       'pbbam/internal/DataSetBaseTypes.h',
       'pbbam/internal/DataSetElement.h',
       'pbbam/internal/DataSetElement.inl',
-      'pbbam/internal/Interval.inl',
       'pbbam/internal/PbiBasicTypes.inl',
       'pbbam/internal/PbiFilter.inl',
       'pbbam/internal/PbiFilterTypes.inl',

include/pbbam/Accuracy.h

@@ -9,46 +9,12 @@
 
 #include "pbbam/Config.h"
 
+#include <pbcopper/data/Accuracy.h>
+
 namespace PacBio {
 namespace BAM {
 
-/// \brief The Accuracy class represents the expected accuracy of a BamRecord.
-///
-/// Values are clamped to fall within [0,1].
-///
-class PBBAM_EXPORT Accuracy
-{
-public:
-    static const float MIN;  ///< Minimum valid accuracy value [0.0]
-    static const float MAX;  ///< Maximum valid accuracy value [1.0]
-
-public:
-    /// \name Constructors & Related Methods
-    /// \{
-
-    /// Constructs an Accuracy object from a floating-point number.
-    ///
-    /// \note This is not an \b explicit ctor, to make it as easy as
-    ///       possible to use in numeric operations. We really just want
-    ///       to make sure that the acceptable range is respected.
-    ///
-    Accuracy(float accuracy);
-
-    Accuracy(const Accuracy&);
-    Accuracy(Accuracy&&);
-    Accuracy& operator=(const Accuracy&);
-    Accuracy& operator=(Accuracy&&);
-    ~Accuracy();
-
-    /// \}
-
-public:
-    /// \returns Accuracy as float primitive
-    operator float() const;
-
-private:
-    float accuracy_;
-};
+using Accuracy PBBAM_DEPRECATED = Data::Accuracy;
 
 }  // namespace BAM
 }  // namespace PacBio

include/pbbam/AlignmentPrinter.h

@@ -7,6 +7,8 @@
 #ifndef ALIGNMENTPRINTER_H
 #define ALIGNMENTPRINTER_H
 
+#include "pbbam/Config.h"
+
 #include <memory>
 #include <string>
 
@@ -39,13 +41,6 @@ public:
     ///
     AlignmentPrinter(const IndexedFastaReader& ifr);
 
-    AlignmentPrinter() = delete;
-    AlignmentPrinter(const AlignmentPrinter&) = delete;
-    AlignmentPrinter(AlignmentPrinter&&);
-    AlignmentPrinter& operator=(const AlignmentPrinter&) = delete;
-    AlignmentPrinter& operator=(AlignmentPrinter&&);
-    ~AlignmentPrinter();
-
     /// \}
 
 public:

include/pbbam/BaiIndexCache.h

+// File Description
+/// \file BaiIndexCache.h
+/// \brief Defines the BaiIndexCache class.
+//
+// Author: Derek Barnett
+
+#ifndef BAIINDEXCACHE_H
+#define BAIINDEXCACHE_H
+
+#include "pbbam/Config.h"
+
+#include <memory>
+#include <string>
+#include <vector>
+
+#include <htslib/hts.h>
+
+#include "pbbam/Position.h"
+
+namespace PacBio {
+namespace BAM {
+
+class BamFile;
+class DataSet;
+
+///
+/// \brief Caches contents of *.bai file for re-use by multiple readers.
+///
+class BaiIndexCacheData
+{
+public:
+    explicit BaiIndexCacheData(const BamFile& bamFile);
+    explicit BaiIndexCacheData(const std::string& bamFilename);
+
+    ~BaiIndexCacheData();
+
+    /// \note This is very much an internal method and should not be considered
+    ///       public API. Exposed here only because of implementation details
+    ///       (definition of htslib-related custom deleters) and may be removed.
+    ///
+    /// \note Does not own the returned pointer; caller is responsible.
+    ///
+    hts_itr_t* IteratorForInterval(const int32_t refId, const Position start,
+                                   const Position stop) const;
+
+private:
+    struct BaiIndexCacheDataPrivate;
+    std::unique_ptr<BaiIndexCacheDataPrivate> d_;
+};
+
+using BaiIndexCache = std::shared_ptr<std::vector<std::shared_ptr<BaiIndexCacheData>>>;
+
+BaiIndexCache MakeBaiIndexCache(const DataSet& dataset);
+BaiIndexCache MakeBaiIndexCache(const std::vector<BamFile>& bamFiles);
+BaiIndexCache MakeBaiIndexCache(const BamFile& bamFile);
+
+}  // namespace BAM
+}  // namespace PacBio
+
+#endif  // BAIINDEXCACHE_H

include/pbbam/BaiIndexedBamReader.h

@@ -7,6 +7,13 @@
 #ifndef BAIINDEXEDBAMREADER_H
 #define BAIINDEXEDBAMREADER_H
 
+#include "pbbam/Config.h"
+
+#include <memory>
+
+#include <htslib/sam.h>
+
+#include "pbbam/BaiIndexCache.h"
 #include "pbbam/BamFile.h"
 #include "pbbam/BamReader.h"
 #include "pbbam/GenomicInterval.h"
@@ -33,6 +40,7 @@ public:
     ///         for reading, or if the interval is invalid
     ///
     explicit BaiIndexedBamReader(std::string filename);
+    BaiIndexedBamReader(std::string filename, const std::shared_ptr<BaiIndexCacheData>& index);
 
     /// \brief Constructs %BAM reader, that can be queried on genomic interval.
     ///
@@ -42,6 +50,7 @@ public:
     ///         for reading, or if the interval is invalid
     ///
     explicit BaiIndexedBamReader(BamFile bamFile);
+    BaiIndexedBamReader(BamFile bamFile, const std::shared_ptr<BaiIndexCacheData>& index);
 
     /// \brief Constructs %BAM reader, bounded by a genomic interval.
     ///
@@ -54,6 +63,8 @@ public:
     ///         for reading, or if the interval is invalid
     ///
     BaiIndexedBamReader(const GenomicInterval& interval, std::string filename);
+    BaiIndexedBamReader(const GenomicInterval& interval, std::string filename,
+                        const std::shared_ptr<BaiIndexCacheData>& index);
 
     /// \brief Constructs %BAM reader, bounded by a genomic interval.
     ///
@@ -66,6 +77,8 @@ public:
     ///         for reading, or if the interval is invalid
     ///
     BaiIndexedBamReader(const GenomicInterval& interval, BamFile bamFile);
+    BaiIndexedBamReader(const GenomicInterval& interval, BamFile bamFile,
+                        const std::shared_ptr<BaiIndexCacheData>& index);
 
     /// \}
 
@@ -73,6 +86,9 @@ public:
     /// \name Random-Access
     /// \{
 
+    /// \returns the underlying BamFile
+    const BamFile& File() const;
+
     /// \returns the current GenomicInterval in use by this reader
     const GenomicInterval& Interval() const;
 

include/pbbam/BamFile.h

@@ -7,11 +7,12 @@
 #ifndef BAMFILE_H
 #define BAMFILE_H
 
+#include "pbbam/Config.h"
+
 #include <cstdint>
 #include <string>
 
 #include "pbbam/BamHeader.h"
-#include "pbbam/Config.h"
 
 namespace PacBio {
 namespace BAM {
@@ -36,9 +37,9 @@ public:
     BamFile(std::string filename);
 
     BamFile(const BamFile& other);
-    BamFile(BamFile&& other);
+    BamFile(BamFile&& other) noexcept;
     BamFile& operator=(const BamFile& other);
-    BamFile& operator=(BamFile&& other);
+    BamFile& operator=(BamFile&& other) noexcept;
     ~BamFile();
 
     /// \}

include/pbbam/BamFileMerger.h

@@ -3,10 +3,13 @@
 #ifndef BAMFILEMERGER_H
 #define BAMFILEMERGER_H
 
-#include <pbbam/ProgramInfo.h>
+#include "pbbam/Config.h"
+
 #include <string>
 #include <vector>
 
+#include <pbbam/ProgramInfo.h>
+
 namespace PacBio {
 namespace BAM {
 

include/pbbam/BamHeader.h

@@ -7,6 +7,8 @@
 #ifndef BAMHEADER_H
 #define BAMHEADER_H
 
+#include "pbbam/Config.h"
+
 #include <cstddef>
 #include <cstdint>
 #include <memory>
@@ -14,7 +16,6 @@
 #include <string>
 #include <vector>
 
-#include "pbbam/Config.h"
 #include "pbbam/ProgramInfo.h"
 #include "pbbam/ReadGroupInfo.h"
 #include "pbbam/SequenceInfo.h"
@@ -53,11 +54,6 @@ public:
     BamHeader(const std::string& samHeaderText);
 
     BamHeader();
-    BamHeader(const BamHeader&);
-    BamHeader(BamHeader&&);
-    BamHeader& operator=(const BamHeader&);
-    BamHeader& operator=(BamHeader&&);
-    ~BamHeader();
 
     /// \brief Detaches underlying data from the shared-pointer, returning a
     ///        independent copy of the header contents.

include/pbbam/BamReader.h

@@ -7,6 +7,8 @@
 #ifndef BAMREADER_H
 #define BAMREADER_H
 
+#include "pbbam/Config.h"
+
 #include <cstdint>
 #include <memory>
 #include <string>
@@ -16,8 +18,8 @@
 #include "pbbam/BamFile.h"
 #include "pbbam/BamHeader.h"
 #include "pbbam/BamRecord.h"
-#include "pbbam/Config.h"
 #include "pbbam/GenomicInterval.h"
+#include "pbbam/internal/QueryBase.h"
 
 namespace PacBio {
 namespace BAM {
@@ -28,12 +30,15 @@ namespace BAM {
 /// records. Derived classes may implement other access schemes (e.g. genomic
 /// region, PBI-enabled record filtering).
 ///
-class PBBAM_EXPORT BamReader
+class PBBAM_EXPORT BamReader : public internal::IQuery
 {
 public:
     /// \name Constructors & Related Methods
     /// \{
 
+    /// \brief Opens BAM for streaming from stdin
+    BamReader();
+
     /// \brief Opens BAM file for reading.
     ///
     /// \param[in] fn %BAM filename
@@ -56,9 +61,6 @@ public:
     /// \name BAM File Attributes
     /// \{
 
-    /// \returns the underlying BamFile
-    const BamFile& File() const;
-
     /// \returns %BAM filename
     const std::string& Filename() const;
 

include/pbbam/BamRecord.h

@@ -7,6 +7,8 @@
 #ifndef BAMRECORD_H
 #define BAMRECORD_H
 
+#include "pbbam/Config.h"
+
 #include <cstddef>
 #include <cstdint>
 #include <memory>
@@ -14,6 +16,9 @@
 #include <utility>
 #include <vector>
 
+#include <pbcopper/data/MappedRead.h>
+#include <pbcopper/data/Read.h>
+
 #include "pbbam/Accuracy.h"
 #include "pbbam/BamHeader.h"
 #include "pbbam/BamRecordImpl.h"
@@ -61,9 +66,9 @@ public:
     BamRecord(BamHeader header);
     BamRecord(BamRecordImpl impl);
     BamRecord(const BamRecord& other);
-    BamRecord(BamRecord&& other);
+    BamRecord(BamRecord&& other) noexcept;
     BamRecord& operator=(const BamRecord& other);
-    BamRecord& operator=(BamRecord&& other);
+    BamRecord& operator=(BamRecord&& other) noexcept;
     virtual ~BamRecord();
 
     /// \}
@@ -101,6 +106,10 @@ public:
     ///
     Position QueryEnd() const;
 
+    /// \returns the number of frames from start of movie to the last base of read
+    ///
+    int32_t QueryEndFrameNumber() const;
+
     /// \returns the record's query start position, or 0 if not stored
     ///
     /// \note QueryStart is in polymerase read coordinates, NOT genomic
@@ -108,6 +117,10 @@ public:
     ///
     Position QueryStart() const;
 
+    /// \returns the number of frames from start of movie to the first base of read
+    ///
+    int32_t QueryStartFrameNumber() const;
+
     /// \returns this record's expected read accuracy [0, 1000]
     Accuracy ReadAccuracy() const;
 
@@ -371,9 +384,15 @@ public:
     /// \returns true if this record has QueryEnd data
     bool HasQueryEnd() const;
 
+    /// \returns true if this record has QueryEnd data
+    bool HasQueryEndFrameNumber() const;
+
     /// \returns true if this record has QueryStart data
     bool HasQueryStart() const;
 
+    /// \returns true if this record has QueryStartFrameNumber data
+    bool HasQueryStartFrameNumber() const;
+
     /// \returns true if this record has ScrapRegionType data (only in SCRAP)
     bool HasScrapRegionType() const;
 
@@ -791,6 +810,13 @@ public:
     ///
     BamRecord& QueryEnd(const PacBio::BAM::Position pos);
 
+    /// \brief Sets this record's query end frame number
+    ///
+    /// \param[in] frame number
+    /// \returns reference to this record
+    ///
+    BamRecord& QueryEndFrameNumber(const int32_t frameNumber);
+
     /// \brief Sets this record's query start position.
     ///
     /// \note Changing this will modify the name of non-CCS records.
@@ -800,6 +826,13 @@ public:
     ///
     BamRecord& QueryStart(const PacBio::BAM::Position pos);
 
+    /// \brief Sets this record's query start frame number
+    ///
+    /// \param[in] frame number
+    /// \returns reference to this record
+    ///
+    BamRecord& QueryStartFrameNumber(const int32_t frameNumber);
+
     /// \brief Sets this record's expected read accuracy [0, 1000]
     ///
     /// \param[in] accuracy
@@ -1131,6 +1164,24 @@ public:
 
     /// \}
 
+public:
+    /// \name [Mapped]Read conversion
+    /// \{
+
+    ///
+    /// \return Data::Read representation of this record
+    ///
+    Data::Read ToRead() const;
+
+    ///
+    /// \return Data::MappedRead representation of this record
+    ///
+    /// \throws std::runtime_error if record is unmapped
+    ///
+    Data::MappedRead ToMappedRead() const;
+
+    /// \}
+
 public:
     /// \name Clipping & Mapping
     /// \{
@@ -1193,18 +1244,8 @@ private:
     void ClipFields(const size_t clipPos, const size_t clipLength);
 
     BamRecord& ClipToQuery(const PacBio::BAM::Position start, const PacBio::BAM::Position end);
-    BamRecord& ClipToQueryForward(const PacBio::BAM::Position start,
-                                  const PacBio::BAM::Position end);
-    BamRecord& ClipToQueryReverse(const PacBio::BAM::Position start,
-                                  const PacBio::BAM::Position end);
     BamRecord& ClipToReference(const PacBio::BAM::Position start, const PacBio::BAM::Position end,
                                const bool exciseFlankingInserts);
-    BamRecord& ClipToReferenceForward(const PacBio::BAM::Position start,
-                                      const PacBio::BAM::Position end,
-                                      const bool exciseFlankingInserts);
-    BamRecord& ClipToReferenceReverse(const PacBio::BAM::Position start,
-                                      const PacBio::BAM::Position end,
-                                      const bool exciseFlankingInserts);
 
 private:
     ///\internal

include/pbbam/BamRecordBuilder.h

@@ -7,11 +7,13 @@
 #ifndef BAMRECORDBUILDER_H
 #define BAMRECORDBUILDER_H
 
+#include "pbbam/Config.h"
+
 #include <cstdint>
 #include <string>
+
 #include "pbbam/BamHeader.h"
 #include "pbbam/BamRecord.h"
-#include "pbbam/Config.h"
 
 namespace PacBio {
 namespace BAM {
@@ -47,12 +49,6 @@ public:
     ///
     BamRecordBuilder(const BamRecord& prototype);
 
-    BamRecordBuilder(const BamRecordBuilder&);
-    BamRecordBuilder(BamRecordBuilder&&);
-    BamRecordBuilder& operator=(const BamRecordBuilder&);
-    BamRecordBuilder& operator=(BamRecordBuilder&&);
-    ~BamRecordBuilder();
-
     /// \}
 
 public: