Commit 0b801687 authored by Steffen Möller's avatar Steffen Möller
Browse files

New upstream version 1.7

parent 0b1efffb

.appveyor.yml

+0 −4
Original line number Diff line number Diff line
@@ -5,10 +5,6 @@ version: 'vers.{build}' 


# branches to build

branches:

    # Whitelist

    only:

      - develop



    # Blacklist

    except:

      - gh-pages

Makefile

+7 −4
Original line number Diff line number Diff line
@@ -175,8 +175,9 @@ cram_sam_header_h = cram/sam_header.h cram/string_alloc.h cram/pooled_alloc.h $( 
cram_samtools_h = cram/cram_samtools.h $(htslib_sam_h) $(cram_sam_header_h)

cram_structs_h = cram/cram_structs.h $(htslib_thread_pool_h) cram/string_alloc.h $(htslib_khash_h)

cram_open_trace_file_h = cram/open_trace_file.h cram/mFILE.h

hfile_internal_h = hfile_internal.h $(htslib_hfile_h)

hts_internal_h = hts_internal.h $(htslib_hts_h)

hfile_internal_h = hfile_internal.h $(htslib_hfile_h) $(textutils_internal_h)

hts_internal_h = hts_internal.h $(htslib_hts_h) $(textutils_internal_h)

textutils_internal_h = textutils_internal.h $(htslib_kstring_h)

thread_pool_internal_h = thread_pool_internal.h $(htslib_thread_pool_h)
@@ -195,6 +196,7 @@ config.h: 
	echo '/* Default config.h generated by Makefile */' > $@

	echo '#define HAVE_LIBBZ2 1' >> $@

	echo '#define HAVE_LIBLZMA 1' >> $@

	echo '#define HAVE_LZMA_H 1' >> $@

	echo '#define HAVE_FSEEKO 1' >> $@

	echo '#define HAVE_DRAND48 1' >> $@
@@ -293,8 +295,9 @@ hfile.o hfile.pico: hfile.c config.h $(htslib_hfile_h) $(hfile_internal_h) $(hts 
hfile_gcs.o hfile_gcs.pico: hfile_gcs.c config.h $(htslib_hts_h) $(htslib_kstring_h) $(hfile_internal_h)

hfile_libcurl.o hfile_libcurl.pico: hfile_libcurl.c config.h $(hfile_internal_h) $(htslib_hts_h) $(htslib_kstring_h)

hfile_net.o hfile_net.pico: hfile_net.c config.h $(hfile_internal_h) $(htslib_knetfile_h)

hfile_s3.o hfile_s3.pico: hfile_s3.c config.h $(hts_internal_h) $(hfile_internal_h) $(htslib_hts_h) $(htslib_kstring_h)

hfile_s3.o hfile_s3.pico: hfile_s3.c config.h $(hfile_internal_h) $(htslib_hts_h) $(htslib_kstring_h)

hts.o hts.pico: hts.c config.h $(htslib_hts_h) $(htslib_bgzf_h) $(cram_h) $(hfile_internal_h) $(htslib_hfile_h) version.h $(hts_internal_h) $(htslib_khash_h) $(htslib_kseq_h) $(htslib_ksort_h)

hts_os.o hts_os.pico: hts_os.c config.h os/rand.c

vcf.o vcf.pico: vcf.c config.h $(htslib_vcf_h) $(htslib_bgzf_h) $(htslib_tbx_h) $(htslib_hfile_h) $(hts_internal_h) $(htslib_khash_str2int_h) $(htslib_kstring_h) $(htslib_khash_h) $(htslib_kseq_h) $(htslib_hts_endian_h)

sam.o sam.pico: sam.c config.h $(htslib_sam_h) $(htslib_bgzf_h) $(cram_h) $(hts_internal_h) $(htslib_hfile_h) $(htslib_khash_h) $(htslib_kseq_h) $(htslib_kstring_h) $(htslib_hts_endian_h)

tbx.o tbx.pico: tbx.c config.h $(htslib_tbx_h) $(htslib_bgzf_h) $(hts_internal_h) $(htslib_khash_h)
@@ -317,7 +320,7 @@ cram/cram_decode.o cram/cram_decode.pico: cram/cram_decode.c config.h $(cram_h) 
cram/cram_encode.o cram/cram_encode.pico: cram/cram_encode.c config.h $(cram_h) $(cram_os_h) $(htslib_hts_h) $(htslib_hts_endian_h)

cram/cram_external.o cram/cram_external.pico: cram/cram_external.c config.h $(htslib_hfile_h) $(cram_h)

cram/cram_index.o cram/cram_index.pico: cram/cram_index.c config.h $(htslib_bgzf_h) $(htslib_hfile_h) $(hts_internal_h) $(cram_h) $(cram_os_h)

cram/cram_io.o cram/cram_io.pico: cram/cram_io.c config.h $(cram_h) $(cram_os_h) $(htslib_hts_h) $(cram_open_trace_file_h) cram/rANS_static.h $(htslib_hfile_h) $(htslib_bgzf_h) $(htslib_faidx_h) $(hts_internal_h)

cram/cram_io.o cram/cram_io.pico: cram/cram_io.c config.h os/lzma_stub.h $(cram_h) $(cram_os_h) $(htslib_hts_h) $(cram_open_trace_file_h) cram/rANS_static.h $(htslib_hfile_h) $(htslib_bgzf_h) $(htslib_faidx_h) $(hts_internal_h)

cram/cram_samtools.o cram/cram_samtools.pico: cram/cram_samtools.c config.h $(cram_h) $(htslib_sam_h)

cram/cram_stats.o cram/cram_stats.pico: cram/cram_stats.c config.h $(cram_h) $(cram_os_h)

cram/files.o cram/files.pico: cram/files.c config.h $(cram_misc_h)

NEWS

+42 −0
Original line number Diff line number Diff line 
Noteworthy changes in release 1.7 (26th January 2018)

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~



* BAM: HTSlib now supports BAMs which include CIGARs with more than 

  65535 operations as per HTS-Specs 18th November (dab57f4 and 2f915a8).



* BCF/VCF:

  - Removed the need for long double in pileup calculations.

  - Sped up the synced reader in some situations.

  - Bug fixing: removed memory leak in bcf_copy.



* CRAM:

  - Added support for HTS_IDX_START in cram iterators.

  - Easier to build when lzma header files are absent.

  - Bug fixing: a region query with REQUIRED_FIELDS option to

    disable sequence retrieval now gives correct results.

  - Bug fixing: stop queries to regions starting after the last

    read on a chromosome from incorrectly reporting errors

    (#651, #653; reported by Imran Haque and @egafni via pysam).



* Multi-region iterator: The new structure takes a list of regions and

  iterates over all, deduplicating reads in the process, and producing a 

  full list of file offset intervals. This is usually much faster than 

  repeatedly using the old single-region iterator on a series of regions.



* Curl improvements:

  - Add Bearer token support via HTS_AUTH_LOCATION env (#600).

  - Use CURL_CA_BUNDLE environment variable to override the CA (#622; 

    thanks to Garret Kelly & David Alexander).

  - Speed up (removal of excessive waiting) for both http(s) and ftp.

  - Avoid repeatedly reconnecting by removal of unnecessary seeks.

  - Bug fixing: double free when libcurl_open fails.



* BGZF block caching, if enabled, now performs far better (#629; reported

  by Ram Yalamanchili).



* Added an hFILE layer for in-memory I/O buffers (#590; thanks to Thomas 

  Hickman).



* Tidied up the drand48 support (intended for systems that do not

  provide this function).



Noteworthy changes in release 1.6 (28th September 2017)

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

bcf_sr_sort.c

+34 −21
Original line number Diff line number Diff line
@@ -327,6 +327,20 @@ char *grp_create_key(sr_sort_t *srt) 
    }

    return ret;

}

int bcf_sr_sort_set_active(sr_sort_t *srt, int idx)

{

    hts_expand(int,idx+1,srt->mactive,srt->active);

    srt->nactive = 1;

    srt->active[srt->nactive - 1] = idx;

    return 0;

}

int bcf_sr_sort_add_active(sr_sort_t *srt, int idx)

{

    hts_expand(int,idx+1,srt->mactive,srt->active);

    srt->nactive++;

    srt->active[srt->nactive - 1] = idx;

    return 0;

}

static void bcf_sr_sort_set(bcf_srs_t *readers, sr_sort_t *srt, const char *chr, int min_pos)

{

    if ( !srt->grp_str2int )
@@ -357,11 +371,11 @@ static void bcf_sr_sort_set(bcf_srs_t *readers, sr_sort_t *srt, const char *chr, 
    memset(&grp,0,sizeof(grp_t));



    // group VCFs into groups, each with a unique combination of variants in the duplicate lines

    int ireader,ivar,irec,igrp,ivset;

    for (ireader=0; ireader<readers->nreaders; ireader++)

    int ireader,ivar,irec,igrp,ivset,iact;

    for (ireader=0; ireader<readers->nreaders; ireader++) srt->vcf_buf[ireader].nrec = 0;

    for (iact=0; iact<srt->nactive; iact++)

    {

        srt->vcf_buf[ireader].nrec = 0;



        ireader = srt->active[iact];

        bcf_sr_t *reader = &readers->readers[ireader];

        int rid   = bcf_hdr_name2id(reader->header, chr);

        grp.nvar  = 0;
@@ -546,23 +560,8 @@ static void bcf_sr_sort_set(bcf_srs_t *readers, sr_sort_t *srt, const char *chr, 
int bcf_sr_sort_next(bcf_srs_t *readers, sr_sort_t *srt, const char *chr, int min_pos)

{

    int i,j;

    if ( readers->nreaders == 1 )

    {

        srt->nsr = 1;

        if ( !srt->msr )

        {

            srt->vcf_buf = (vcf_buf_t*) calloc(1,sizeof(vcf_buf_t));   // first time here

            srt->msr = 1;

        }

        bcf_sr_t *reader = &readers->readers[0];

        assert( reader->buffer[1]->pos==min_pos );

        bcf1_t *tmp = reader->buffer[0];

        for (j=1; j<=reader->nbuffer; j++) reader->buffer[j-1] = reader->buffer[j];

        reader->buffer[ reader->nbuffer ] = tmp;

        reader->nbuffer--;

        readers->has_line[0] = 1;

        return 1;

    }

    assert( srt->nactive>0 );



    if ( srt->nsr != readers->nreaders )

    {

        srt->sr = readers;
@@ -575,6 +574,19 @@ int bcf_sr_sort_next(bcf_srs_t *readers, sr_sort_t *srt, const char *chr, int mi 
        srt->nsr = readers->nreaders;

        srt->chr = NULL;

    }

    if ( srt->nactive == 1 )

    {

        if ( readers->nreaders>1 )

            memset(readers->has_line, 0, readers->nreaders*sizeof(*readers->has_line));

        bcf_sr_t *reader = &readers->readers[srt->active[0]];

        assert( reader->buffer[1]->pos==min_pos );

        bcf1_t *tmp = reader->buffer[0];

        for (j=1; j<=reader->nbuffer; j++) reader->buffer[j-1] = reader->buffer[j];

        reader->buffer[ reader->nbuffer ] = tmp;

        reader->nbuffer--;

        readers->has_line[srt->active[0]] = 1;

        return 1;

    }

    if ( !srt->chr || srt->pos!=min_pos || strcmp(srt->chr,chr) ) bcf_sr_sort_set(readers, srt, chr, min_pos);



    if ( !srt->vcf_buf[0].nrec ) return 0;
@@ -629,6 +641,7 @@ sr_sort_t *bcf_sr_sort_init(sr_sort_t *srt) 
}

void bcf_sr_sort_destroy(sr_sort_t *srt)

{

    free(srt->active);

    if ( srt->var_str2int ) khash_str2int_destroy_free(srt->var_str2int);

    if ( srt->grp_str2int ) khash_str2int_destroy_free(srt->grp_str2int);

    int i;

bcf_sr_sort.h

+3 −0
Original line number Diff line number Diff line
@@ -92,11 +92,14 @@ typedef struct 
    const char *chr;

    int pos, nsr, msr;

    int pair;

    int nactive, mactive, *active;  // list of readers with lines at the current pos

}

sr_sort_t;



sr_sort_t *bcf_sr_sort_init(sr_sort_t *srt);

int bcf_sr_sort_next(bcf_srs_t *readers, sr_sort_t *srt, const char *chr, int pos);

int bcf_sr_sort_set_active(sr_sort_t *srt, int i);

int bcf_sr_sort_add_active(sr_sort_t *srt, int i);

void bcf_sr_sort_destroy(sr_sort_t *srt);

void bcf_sr_sort_remove_reader(bcf_srs_t *readers, sr_sort_t *srt, int i);