merging with upstream

.github/workflows/ci.yaml

@@ -0,0 +1,46 @@
+name: CI
+
+on:
+  push:
+    branches:
+    - master
+  pull_request:
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        compiler: [gcc, clang]
+
+    steps:
+    - name: Checkout bwa
+      uses: actions/checkout@v3
+
+    - name: Compile with ${{ matrix.compiler }}
+      run:  make CC=${{ matrix.compiler }}
+
+  build-aarch64:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        compiler: [gcc, clang]
+
+    steps:
+    - name: Checkout bwa
+      uses: actions/checkout@v3
+
+    - name: Compile with ${{ matrix.compiler }}
+      uses: uraimo/run-on-arch-action@v2
+      with:
+        arch: aarch64
+        distro: ubuntu20.04
+        githubToken: ${{ github.token }}
+        dockerRunArgs: |
+          --volume "${PWD}:/bwa"
+        install: |
+          apt-get update -q -y
+          apt-get install -q -y make ${{ matrix.compiler }} zlib1g-dev
+        run: |
+          cd /bwa
+          make CC=${{ matrix.compiler }}

Makefile

@@ -25,15 +25,15 @@ endif
 .SUFFIXES:.c .o .cc
 
 .c.o:
-		$(CC) -c $(CFLAGS) $(DFLAGS) $(INCLUDES) $< -o $@
+		$(CC) -c $(CFLAGS) $(DFLAGS) $(INCLUDES) $(CPPFLAGS) $< -o $@
 
 all:$(PROG)
 
 bwa:libbwa.a $(AOBJS) main.o
-		$(CC) $(CFLAGS) $(DFLAGS) $(AOBJS) main.o -o $@ -L. -lbwa $(LIBS)
+		$(CC) $(CFLAGS) $(LDFLAGS) $(AOBJS) main.o -o $@ -L. -lbwa $(LIBS)
 
 bwamem-lite:libbwa.a example.o
-		$(CC) $(CFLAGS) $(DFLAGS) example.o -o $@ -L. -lbwa $(LIBS)
+		$(CC) $(CFLAGS) $(LDFLAGS) example.o -o $@ -L. -lbwa $(LIBS)
 
 libbwa.a:$(LOBJS)
 		$(AR) -csru $@ $(LOBJS)
@@ -42,7 +42,7 @@ clean:
 		rm -f gmon.out *.o a.out $(PROG) *~ *.a
 
 depend:
-	( LC_ALL=C ; export LC_ALL; makedepend -Y -- $(CFLAGS) $(DFLAGS) -- *.c )
+	( LC_ALL=C ; export LC_ALL; makedepend -Y -- $(CFLAGS) $(DFLAGS) $(CPPFLAGS) -- *.c )
 
 # DO NOT DELETE THIS LINE -- make depend depends on it.
 
@@ -80,7 +80,7 @@ fastmap.o: bwa.h bntseq.h bwt.h bwamem.h kvec.h malloc_wrap.h utils.h kseq.h
 is.o: malloc_wrap.h
 kopen.o: malloc_wrap.h
 kstring.o: kstring.h malloc_wrap.h
-ksw.o: ksw.h malloc_wrap.h
+ksw.o: ksw.h neon_sse.h scalar_sse.h malloc_wrap.h
 main.o: kstring.h malloc_wrap.h utils.h
 malloc_wrap.o: malloc_wrap.h
 maxk.o: bwa.h bntseq.h bwt.h bwamem.h kseq.h malloc_wrap.h

NEWS.md

@@ -1,7 +1,35 @@
+Release 0.7.17 (23 October 2017)
+--------------------------------
+
+This release adds option -q to preserve the mapping quality of split alignment
+with a lower alignment score than the primary alignment. Option -5
+automatically applies -q as well.
+
+(0.7.17: 23 October 2017, r1188)
+
+
+
+Release 0.7.16 (30 July 2017)
+-----------------------------
+
+This release added a couple of minor features and incorporated multiple pull
+requests, including:
+
+ * Added option -5, which is useful to some Hi-C pipelines.
+
+ * Fixed an error with samtools sorting (#129). Updated download link for
+   GRCh38 (#123). Fixed README MarkDown formatting (#70). Addressed multiple
+   issues via a collected pull request #139 by @jmarshall. Avoid malformatted
+   SAM header when -R is used with TAB (#84). Output mate CIGAR (#138).
+
+(0.7.16: 30 July 2017, r1180)
+
+
+
 Release 0.7.15 (31 May 2016)
 ----------------------------
 
-Fixed a long existing bug which potentially leads underestimated insert size
+Fixed a long existing bug which potentially leads to underestimated insert size
 upper bound. This bug should have little effect in practice.
 
 (0.7.15: 31 May 2016, r1140)

README.md

@@ -1,14 +1,26 @@
-[![Build Status](https://travis-ci.org/lh3/bwa.svg?branch=dev)](https://travis-ci.org/lh3/bwa)
-[![Build Status](https://drone.io/github.com/lh3/bwa/status.png)](https://drone.io/github.com/lh3/bwa/latest)
-##Getting started
+[![Build Status](https://github.com/lh3/bwa/actions/workflows/ci.yaml/badge.svg)](https://github.com/lh3/bwa/actions)
+[![SourceForge Downloads](https://img.shields.io/sourceforge/dt/bio-bwa.svg?label=SF%20downloads)](https://sourceforge.net/projects/bio-bwa/files/?source=navbar)
+[![GitHub Downloads](https://img.shields.io/github/downloads/lh3/bwa/total.svg?style=flat&label=GitHub%20downloads)](https://github.com/lh3/bwa/releases)
+[![BioConda Install](https://img.shields.io/conda/dn/bioconda/bwa.svg?style=flag&label=BioConda%20install)](https://anaconda.org/bioconda/bwa)
+
+**Note: [minimap2][minimap2] has replaced BWA-MEM for __PacBio and Nanopore__ read
+alignment.** It retains all major BWA-MEM features, but is ~50 times as fast,
+more versatile, more accurate and produces better base-level alignment.
+A beta version of [BWA-MEM2][bwa-mem2] has been released for short-read mapping.
+BWA-MEM2 is about twice as fast as BWA-MEM and outputs near identical alignments.
+
+[minimap2]: https://github.com/lh3/minimap2
+[bwa-mem2]: https://github.com/bwa-mem2/bwa-mem2
+
+## Getting started
 
 	git clone https://github.com/lh3/bwa.git
 	cd bwa; make
 	./bwa index ref.fa
 	./bwa mem ref.fa read-se.fq.gz | gzip -3 > aln-se.sam.gz
 	./bwa mem ref.fa read1.fq read2.fq | gzip -3 > aln-pe.sam.gz
 
-##Introduction
+## Introduction
 
 BWA is a software package for mapping DNA sequences against a large reference
 genome, such as the human genome. It consists of three algorithms:
@@ -24,7 +36,7 @@ reference genome (the **index** command). Alignment algorithms are invoked with
 different sub-commands: **aln/samse/sampe** for BWA-backtrack,
 **bwasw** for BWA-SW and **mem** for the BWA-MEM algorithm.
 
-##Availability
+## Availability
 
 BWA is released under [Apache 2.0][1]. The latest source code is [freely
 available at github][2]. Released packages can [be downloaded][3] at
@@ -37,7 +49,7 @@ In addition to BWA, this self-consistent package also comes with bwa-associated
 and 3rd-party tools for proper BAM-to-FASTQ conversion, mapping to ALT contigs,
 adapter triming, duplicate marking, HLA typing and associated data files.
 
-##Seeking helps
+## Seeking help
 
 The detailed usage is described in the man page available together with the
 source code. You can use `man ./bwa.1` to view the man page in a terminal. The
@@ -46,7 +58,7 @@ have questions about BWA, you may [sign up the mailing list][6] and then send
 the questions to [[email protected]][7]. You may also ask questions
 in forums such as [BioStar][8] and [SEQanswers][9].
 
-##Citing BWA
+## Citing BWA
 
 * Li H. and Durbin R. (2009) Fast and accurate short read alignment with
  Burrows-Wheeler transform. *Bioinformatics*, **25**, 1754-1760. [PMID:
@@ -63,7 +75,7 @@ in forums such as [BioStar][8] and [SEQanswers][9].
 Please note that the last reference is a preprint hosted at [arXiv.org][13]. I
 do not have plan to submit it to a peer-reviewed journal in the near future.
 
-##Frequently asked questions (FAQs)
+## Frequently asked questions (FAQs)
 
 1. [What types of data does BWA work with?](#type)
 2. [Why does a read appear multiple times in the output SAM?](#multihit)
@@ -73,7 +85,7 @@ do not have plan to submit it to a peer-reviewed journal in the near future.
 6. [Does BWA work with ALT contigs in the GRCh38 release?](#altctg)
 7. [Can I just run BWA-MEM against GRCh38+ALT without post-processing?](#postalt)
 
-####<a name="type"></a>1. What types of data does BWA work with?
+#### <a name="type"></a>1. What types of data does BWA work with?
 
 BWA works with a variety types of DNA sequence data, though the optimal
 algorithm and setting may vary. The following list gives the recommended
@@ -108,42 +120,42 @@ errors given longer query sequences as the chance of missing all seeds is small.
 As is shown above, with non-default settings, BWA-MEM works with Oxford Nanopore
 reads with a sequencing error rate over 20%.
 
-####<a name="multihit"></a>2. Why does a read appear multiple times in the output SAM?
+#### <a name="multihit"></a>2. Why does a read appear multiple times in the output SAM?
 
 BWA-SW and BWA-MEM perform local alignments. If there is a translocation, a gene
 fusion or a long deletion, a read bridging the break point may have two hits,
 occupying two lines in the SAM output. With the default setting of BWA-MEM, one
 and only one line is primary and is soft clipped; other lines are tagged with
 0x800 SAM flag (supplementary alignment) and are hard clipped.
 
-####<a name="4gb"></a>3. Does BWA work on reference sequences longer than 4GB in total?
+#### <a name="4gb"></a>3. Does BWA work on reference sequences longer than 4GB in total?
 
 Yes. Since 0.6.x, all BWA algorithms work with a genome with total length over
 4GB. However, individual chromosome should not be longer than 2GB.
 
-####<a name="pe0"></a>4. Why can one read in a pair has high mapping quality but the other has zero?
+#### <a name="pe0"></a>4. Why can one read in a pair have a high mapping quality but the other has zero?
 
 This is correct. Mapping quality is assigned for individual read, not for a read
 pair. It is possible that one read can be mapped unambiguously, but its mate
 falls in a tandem repeat and thus its accurate position cannot be determined.
 
-####<a name="endref"></a>5. How can a BWA-backtrack alignment stands out of the end of a chromosome?
+#### <a name="endref"></a>5. How can a BWA-backtrack alignment stand out of the end of a chromosome?
 
 Internally BWA concatenates all reference sequences into one long sequence. A
 read may be mapped to the junction of two adjacent reference sequences. In this
 case, BWA-backtrack will flag the read as unmapped (0x4), but you will see
 position, CIGAR and all the tags. A similar issue may occur to BWA-SW alignment
 as well. BWA-MEM does not have this problem.
 
-####<a name="altctg"></a>6. Does BWA work with ALT contigs in the GRCh38 release?
+#### <a name="altctg"></a>6. Does BWA work with ALT contigs in the GRCh38 release?
 
 Yes, since 0.7.11, BWA-MEM officially supports mapping to GRCh38+ALT.
 BWA-backtrack and BWA-SW don't properly support ALT mapping as of now. Please
 see [README-alt.md][18] for details. Briefly, it is recommended to use
 [bwakit][17], the binary release of BWA, for generating the reference genome
 and for mapping.
 
-####<a name="postalt"></a>7. Can I just run BWA-MEM against GRCh38+ALT without post-processing?
+#### <a name="postalt"></a>7. Can I just run BWA-MEM against GRCh38+ALT without post-processing?
 
 If you are not interested in hits to ALT contigs, it is okay to run BWA-MEM
 without post-processing. The alignments produced this way are very close to

bntseq.c

@@ -1,6 +1,8 @@
 /* The MIT License
 
-   Copyright (c) 2008 Genome Research Ltd (GRL).
+   Copyright (c) 2018-     Dana-Farber Cancer Institute
+                 2009-2018 Broad Institute, Inc.
+                 2008-2009 Genome Research Ltd. (GRL)
 
    Permission is hereby granted, free of charge, to any person obtaining
    a copy of this software and associated documentation files (the
@@ -22,9 +24,6 @@
    CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
    SOFTWARE.
 */
-
-/* Contact: Heng Li <[email protected]> */
-
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -197,7 +196,13 @@ bntseq_t *bns_restore(const char *prefix)
 				}
 				while (c != '\n' && c != EOF) c = fgetc(fp);
 				i = 0;
-			} else str[i++] = c; // FIXME: potential segfault here
+			} else {
+				if (i >= 1022) {
+					fprintf(stderr, "[E::%s] sequence name longer than 1023 characters. Abort!\n", __func__);
+					exit(1);
+				}
+				str[i++] = c;
+			}
 		}
 		kh_destroy(str, h);
 		fclose(fp);
@@ -299,9 +304,9 @@ int64_t bns_fasta2bntseq(gzFile fp_fa, const char *prefix, int for_only)
 	// read sequences
 	while (kseq_read(seq) >= 0) pac = add1(seq, bns, pac, &m_pac, &m_seqs, &m_holes, &q);
 	if (!for_only) { // add the reverse complemented sequence
-		m_pac = (bns->l_pac * 2 + 3) / 4 * 4;
-		pac = realloc(pac, m_pac/4);
-		memset(pac + (bns->l_pac+3)/4, 0, (m_pac - (bns->l_pac+3)/4*4) / 4);
+		int64_t ll_pac = (bns->l_pac * 2 + 3) / 4 * 4;
+		if (ll_pac > m_pac) pac = realloc(pac, ll_pac/4);
+		memset(pac + (bns->l_pac+3)/4, 0, (ll_pac - (bns->l_pac+3)/4*4) / 4);
 		for (l = bns->l_pac - 1; l >= 0; --l, ++bns->l_pac)
 			_set_pac(pac, bns->l_pac, 3-_get_pac(pac, l));
 	}

bntseq.h

@@ -1,6 +1,8 @@
 /* The MIT License
 
-   Copyright (c) 2008 Genome Research Ltd (GRL).
+   Copyright (c) 2018-     Dana-Farber Cancer Institute
+                 2009-2018 Broad Institute, Inc.
+                 2008-2009 Genome Research Ltd. (GRL)
 
    Permission is hereby granted, free of charge, to any person obtaining
    a copy of this software and associated documentation files (the
@@ -23,8 +25,6 @@
    SOFTWARE.
 */
 
-/* Contact: Heng Li <[email protected]> */
-
 #ifndef BWT_BNTSEQ_H
 #define BWT_BNTSEQ_H