static void init_data(args_t *args) { args->aux.srs = bcf_sr_init(); // Open files for input and output, initialize structures if ( args->targets ) { if ( bcf_sr_set_targets(args->aux.srs, args->targets, args->targets_is_file, args->aux.flag&CALL_CONSTR_ALLELES ? 3 : 0)<0 ) error("Failed to read the targets: %s\n", args->targets); if ( args->aux.flag&CALL_CONSTR_ALLELES && args->flag&CF_INS_MISSED ) { args->aux.srs->targets->missed_reg_handler = print_missed_line; args->aux.srs->targets->missed_reg_data = args; } } if ( args->regions ) { if ( bcf_sr_set_regions(args->aux.srs, args->regions, args->regions_is_file)<0 ) error("Failed to read the targets: %s\n", args->regions); } int i; if ( !bcf_sr_add_reader(args->aux.srs, args->bcf_fname) ) error("Failed to open: %s\n", args->bcf_fname); if ( args->nsamples && args->nsamples != bcf_hdr_nsamples(args->aux.srs->readers[0].header) ) { args->samples_map = (int *) malloc(sizeof(int)*args->nsamples); args->aux.hdr = bcf_hdr_subset(args->aux.srs->readers[0].header, args->nsamples, args->samples, args->samples_map); for (i=0; i<args->nsamples; i++) if ( args->samples_map[i]<0 ) error("No such sample: %s\n", args->samples[i]); if ( !bcf_hdr_nsamples(args->aux.hdr) ) error("No matching sample found\n"); } else { args->aux.hdr = bcf_hdr_dup(args->aux.srs->readers[0].header); for (i=0; i<args->nsamples; i++) if ( bcf_hdr_id2int(args->aux.hdr,BCF_DT_SAMPLE,args->samples[i])<0 ) error("No such sample: %s\n", args->samples[i]); } // Reorder ploidy and family indexes to match mpileup's output and exclude samples which are not available if ( args->aux.ploidy ) { for (i=0; i<args->aux.nfams; i++) { int j; for (j=0; j<3; j++) { int k = bcf_hdr_id2int(args->aux.hdr, BCF_DT_SAMPLE, args->samples[ args->aux.fams[i].sample[j] ]); if ( k<0 ) error("No such sample: %s\n", args->samples[ args->aux.fams[i].sample[j] ]); args->aux.fams[i].sample[j] = k; } } uint8_t *ploidy = (uint8_t*) calloc(bcf_hdr_nsamples(args->aux.hdr), 1); for (i=0; i<args->nsamples; i++) // i index in -s sample list { int j = bcf_hdr_id2int(args->aux.hdr, BCF_DT_SAMPLE, args->samples[i]); // j index in the output VCF / subset VCF if ( j<0 ) { fprintf(stderr,"Warning: no such sample: \"%s\"\n", args->samples[i]); continue; } ploidy[j] = args->aux.ploidy[i]; } args->nsamples = bcf_hdr_nsamples(args->aux.hdr); for (i=0; i<args->nsamples; i++) assert( ploidy[i]==0 || ploidy[i]==1 || ploidy[i]==2 ); free(args->aux.ploidy); args->aux.ploidy = ploidy; } args->out_fh = hts_open(args->output_fname, hts_bcf_wmode(args->output_type)); if ( args->out_fh == NULL ) error("Can't write to \"%s\": %s\n", args->output_fname, strerror(errno)); if ( args->flag & CF_QCALL ) return; if ( args->flag & CF_MCALL ) mcall_init(&args->aux); if ( args->flag & CF_CCALL ) ccall_init(&args->aux); if ( args->flag&CF_GVCF ) { bcf_hdr_append(args->aux.hdr,"##INFO=<ID=END,Number=1,Type=Integer,Description=\"End position of the variant described in this record\">"); args->gvcf.rid = -1; args->gvcf.line = bcf_init1(); args->gvcf.gt = (int32_t*) malloc(2*sizeof(int32_t)*bcf_hdr_nsamples(args->aux.hdr)); for (i=0; i<bcf_hdr_nsamples(args->aux.hdr); i++) { args->gvcf.gt[2*i+0] = bcf_gt_unphased(0); args->gvcf.gt[2*i+1] = bcf_gt_unphased(0); } } bcf_hdr_remove(args->aux.hdr, BCF_HL_INFO, "QS"); bcf_hdr_remove(args->aux.hdr, BCF_HL_INFO, "I16"); bcf_hdr_append_version(args->aux.hdr, args->argc, args->argv, "bcftools_call"); bcf_hdr_write(args->out_fh, args->aux.hdr); if ( args->flag&CF_INS_MISSED ) init_missed_line(args); }
static void init_data(args_t *args) { int i; args->hdr = args->files->readers[0].header; if (args->calc_ac && args->update_info) { bcf_hdr_append(args->hdr,"##INFO=<ID=AC,Number=A,Type=Integer,Description=\"Allele count in genotypes\">"); bcf_hdr_append(args->hdr,"##INFO=<ID=AN,Number=1,Type=Integer,Description=\"Total number of alleles in called genotypes\">"); } bcf_hdr_append_version(args->hdr, args->argc, args->argv, "bcftools_view"); // setup sample data if (args->sample_names) { void *hdr_samples = khash_str2int_init(); for (i=0; i<bcf_hdr_nsamples(args->hdr); i++) khash_str2int_inc(hdr_samples, bcf_hdr_int2id(args->hdr,BCF_DT_SAMPLE,i)); void *exclude = (args->sample_names[0]=='^') ? khash_str2int_init() : NULL; int nsmpl; char **smpl = NULL; args->samples = NULL; args->n_samples = 0; smpl = hts_readlist(exclude ? &args->sample_names[1] : args->sample_names, args->sample_is_file, &nsmpl); if ( !smpl ) { error("Could not read the list: \"%s\"\n", exclude ? &args->sample_names[1] : args->sample_names); } if ( exclude ) { for (i=0; i<nsmpl; i++) { if (!khash_str2int_has_key(hdr_samples,smpl[i])) { if (args->force_samples) { fprintf(stderr, "Warn: exclude called for sample that does not exist in header: \"%s\"... skipping\n", smpl[i]); } else { error("Error: exclude called for sample that does not exist in header: \"%s\". Use \"--force-samples\" to ignore this error.\n", smpl[i]); } } khash_str2int_inc(exclude, smpl[i]); } for (i=0; i<bcf_hdr_nsamples(args->hdr); i++) { if ( exclude && khash_str2int_has_key(exclude,bcf_hdr_int2id(args->hdr,BCF_DT_SAMPLE,i)) ) continue; args->samples = (char**) realloc(args->samples, (args->n_samples+1)*sizeof(const char*)); args->samples[args->n_samples++] = strdup(bcf_hdr_int2id(args->hdr,BCF_DT_SAMPLE,i)); } khash_str2int_destroy(exclude); } else { for (i=0; i<nsmpl; i++) { if (!khash_str2int_has_key(hdr_samples,smpl[i])) { if (args->force_samples) { fprintf(stderr, "Warn: subset called for sample that does not exist in header: \"%s\"... skipping\n", smpl[i]); continue; } else { error("Error: subset called for sample that does not exist in header: \"%s\". Use \"--force-samples\" to ignore this error.\n", smpl[i]); } } args->samples = (char**) realloc(args->samples, (args->n_samples+1)*sizeof(const char*)); args->samples[args->n_samples++] = strdup(smpl[i]); } } for (i=0; i<nsmpl; i++) free(smpl[i]); free(smpl); khash_str2int_destroy(hdr_samples); if (args->n_samples == 0) { fprintf(stderr, "Warn: subsetting has removed all samples\n"); args->sites_only = 1; } } if (args->n_samples) args->imap = (int*)malloc(args->n_samples * sizeof(int)); // determine variant types to include/exclude if (args->include_types || args->exclude_types) { if (args->include_types && args->exclude_types) { fprintf(stderr, "Error: only supply one of --include-types, --exclude-types options\n"); exit(1); } char **type_list = 0; int m = 0, n = 0; const char *q, *p; for (q = p = args->include_types ? args->include_types : args->exclude_types;; ++p) { if (*p == ',' || *p == 0) { if (m == n) { m = m? m<<1 : 16; type_list = (char**)realloc(type_list, m * sizeof(char*)); } type_list[n] = (char*)calloc(p - q + 1, 1); strncpy(type_list[n++], q, p - q); q = p + 1; if (*p == 0) break; } } type_list = (char**)realloc(type_list, n * sizeof(char*)); if (args->include_types) { args->include = 0; for (i = 0; i < n; ++i) { if (strcmp(type_list[i], "snps") == 0) args->include |= VCF_SNP; else if (strcmp(type_list[i], "indels") == 0) args->include |= VCF_INDEL; else if (strcmp(type_list[i], "mnps") == 0) args->include |= VCF_MNP; else if (strcmp(type_list[i], "other") == 0) args->include |= VCF_OTHER; else { fprintf(stderr, "[E::%s] unknown type\n", type_list[i]); fprintf(stderr, "Accepted types are snps, indels, mnps, other\n"); exit(1); } } } if (args->exclude_types) { args->exclude = 0; for (i = 0; i < n; ++i) { if (strcmp(type_list[i], "snps") == 0) args->exclude |= VCF_SNP; else if (strcmp(type_list[i], "indels") == 0) args->exclude |= VCF_INDEL; else if (strcmp(type_list[i], "mnps") == 0) args->exclude |= VCF_MNP; else if (strcmp(type_list[i], "other") == 0) args->exclude |= VCF_OTHER; else { fprintf(stderr, "[E::%s] unknown type\n", type_list[i]); fprintf(stderr, "Accepted types are snps, indels, mnps, other\n"); exit(1); } } } for (i = 0; i < n; ++i) free(type_list[i]); free(type_list); } // setup output char modew[8]; strcpy(modew, "w"); if (args->clevel >= 0 && args->clevel <= 9) sprintf(modew + 1, "%d", args->clevel); if (args->output_type==FT_BCF) strcat(modew, "bu"); // uncompressed BCF else if (args->output_type & FT_BCF) strcat(modew, "b"); // compressed BCF else if (args->output_type & FT_GZ) strcat(modew,"z"); // compressed VCF args->out = hts_open(args->fn_out ? args->fn_out : "-", modew); if ( !args->out ) error("%s: %s\n", args->fn_out,strerror(errno)); // headers: hdr=full header, hsub=subset header, hnull=sites only header if (args->sites_only){ args->hnull = bcf_hdr_subset(args->hdr, 0, 0, 0); bcf_hdr_remove(args->hnull, BCF_HL_FMT, NULL); } if (args->n_samples > 0) { args->hsub = bcf_hdr_subset(args->hdr, args->n_samples, args->samples, args->imap); if ( !args->hsub ) error("Error occurred while subsetting samples\n"); if ( args->n_samples != bcf_hdr_nsamples(args->hsub) ) { int i; for (i=0; i<args->n_samples; i++) if ( args->imap[i]<0 ) error("Error: No such sample: \"%s\"\n", args->samples[i]); } } if ( args->filter_str ) args->filter = filter_init(args->hdr, args->filter_str); }
int main_vcfview(int argc, char *argv[]) { int i, c, clevel = -1, flag = 0, n_samples = -1, *imap = 0, excl_snp = 0, excl_indel = 0; char *fn_ref = 0, *fn_out = 0, moder[8], **samples = 0; bcf_hdr_t *h, *hsub = 0; htsFile *in; bcf1_t *b; while ((c = getopt(argc, argv, "l:bSt:o:T:s:GNI")) >= 0) { switch (c) { case 'l': clevel = atoi(optarg); flag |= 2; break; case 'S': flag |= 1; break; case 'b': flag |= 2; break; case 'G': n_samples = 0; break; case 't': fn_ref = optarg; flag |= 1; break; case 'o': fn_out = optarg; break; case 's': samples = hts_readlines(optarg, &n_samples); break; case 'N': excl_snp = 1; break; case 'I': excl_indel = 1; break; } } if (argc == optind) { fprintf(stderr, "\nUsage: vcfview [options] <in.bcf>|<in.vcf>|<in.vcf.gz>\n\n"); fprintf(stderr, "Options: -b output in BCF\n"); fprintf(stderr, " -S input is VCF\n"); fprintf(stderr, " -o FILE output file name [stdout]\n"); fprintf(stderr, " -l INT compression level [%d]\n", clevel); fprintf(stderr, " -t FILE list of reference names and lengths [null]\n"); fprintf(stderr, " -s FILE/STR list of samples (STR if started with ':'; FILE otherwise) [null]\n"); fprintf(stderr, " -G drop individual genotype information\n"); fprintf(stderr, " -N exclude SNPs\n"); fprintf(stderr, " -I exclude INDELs\n"); fprintf(stderr, "\n"); return 1; } strcpy(moder, "r"); if ((flag&1) == 0 && !(file_type(argv[optind])&(IS_VCF|IS_VCF_GZ))) strcat(moder, "b"); in = hts_open(argv[optind], moder, fn_ref); h = vcf_hdr_read(in); if (h == 0) { fprintf(stderr, "[E::%s] fail to read the VCF/BCF2 header\n", __func__); hts_close(in); return 1; } if (n_samples >= 0) { if (n_samples) imap = (int*)malloc(n_samples * sizeof(int)); hsub = bcf_hdr_subset(h, n_samples, samples, imap); } b = bcf_init1(); if ((flag&4) == 0) { // VCF/BCF output htsFile *out; char modew[8]; strcpy(modew, "w"); if (clevel >= 0 && clevel <= 9) sprintf(modew + 1, "%d", clevel); if (flag&2) strcat(modew, "b"); out = hts_open(fn_out? fn_out : "-", modew, 0); vcf_hdr_write(out, hsub? hsub : h); if (optind + 1 < argc && !(flag&1)) { // BAM input and has a region hts_idx_t *idx; if ((idx = bcf_index_load(argv[optind])) == 0) { fprintf(stderr, "[E::%s] fail to load the BCF index\n", __func__); return 1; } for (i = optind + 1; i < argc; ++i) { hts_itr_t *iter; if ((iter = bcf_itr_querys(idx, h, argv[i])) == 0) { fprintf(stderr, "[E::%s] fail to parse region '%s'\n", __func__, argv[i]); continue; } while (bcf_itr_next((BGZF*)in->fp, iter, b) >= 0) { if (excl_snp && bcf_is_snp(b)) continue; if (excl_indel && !bcf_is_snp(b)) continue; if (n_samples >= 0) { bcf_subset(h, b, n_samples, imap); vcf_write1(out, hsub, b); } else vcf_write1(out, h, b); } hts_itr_destroy(iter); } hts_idx_destroy(idx); } else { while (vcf_read1(in, h, b) >= 0) { if (excl_snp && bcf_is_snp(b)) continue; if (excl_indel && !bcf_is_snp(b)) continue; if (n_samples >= 0) { bcf_subset(h, b, n_samples, imap); vcf_write1(out, hsub, b); } else vcf_write1(out, h, b); } } hts_close(out); } bcf_destroy1(b); if (n_samples > 0) { for (i = 0; i < n_samples; ++i) free(samples[i]); free(samples); bcf_hdr_destroy(hsub); free(imap); } bcf_hdr_destroy(h); hts_close(in); return 0; }
static void init_data(args_t *args) { args->aux.srs = bcf_sr_init(); // Open files for input and output, initialize structures if ( args->targets ) { if ( bcf_sr_set_targets(args->aux.srs, args->targets, args->targets_is_file, args->aux.flag&CALL_CONSTR_ALLELES ? 3 : 0)<0 ) error("Failed to read the targets: %s\n", args->targets); if ( args->aux.flag&CALL_CONSTR_ALLELES && args->flag&CF_INS_MISSED ) { args->aux.srs->targets->missed_reg_handler = print_missed_line; args->aux.srs->targets->missed_reg_data = args; } } if ( args->regions ) { if ( bcf_sr_set_regions(args->aux.srs, args->regions, args->regions_is_file)<0 ) error("Failed to read the targets: %s\n", args->regions); } if ( !bcf_sr_add_reader(args->aux.srs, args->bcf_fname) ) error("Failed to open %s: %s\n", args->bcf_fname,bcf_sr_strerror(args->aux.srs->errnum)); args->aux.hdr = bcf_sr_get_header(args->aux.srs,0); int i; if ( args->samples_fname ) { set_samples(args, args->samples_fname, args->samples_is_file); if ( args->aux.flag&CALL_CONSTR_TRIO ) { if ( 3*args->aux.nfams!=args->nsamples ) error("Expected only trios in %s, sorry!\n", args->samples_fname); fprintf(stderr,"Detected %d samples in %d trio families\n", args->nsamples,args->aux.nfams); } args->nsex = ploidy_nsex(args->ploidy); args->sex2ploidy = (int*) calloc(args->nsex,sizeof(int)); args->sex2ploidy_prev = (int*) calloc(args->nsex,sizeof(int)); args->aux.ploidy = (uint8_t*) malloc(args->nsamples); for (i=0; i<args->nsamples; i++) args->aux.ploidy[i] = 2; for (i=0; i<args->nsex; i++) args->sex2ploidy_prev[i] = 2; } if ( args->samples_map ) { args->aux.hdr = bcf_hdr_subset(bcf_sr_get_header(args->aux.srs,0), args->nsamples, args->samples, args->samples_map); if ( !args->aux.hdr ) error("Error occurred while subsetting samples\n"); for (i=0; i<args->nsamples; i++) if ( args->samples_map[i]<0 ) error("No such sample: %s\n", args->samples[i]); if ( !bcf_hdr_nsamples(args->aux.hdr) ) error("No matching sample found\n"); } else { args->aux.hdr = bcf_hdr_dup(bcf_sr_get_header(args->aux.srs,0)); for (i=0; i<args->nsamples; i++) if ( bcf_hdr_id2int(args->aux.hdr,BCF_DT_SAMPLE,args->samples[i])<0 ) error("No such sample: %s\n", args->samples[i]); } args->out_fh = hts_open(args->output_fname, hts_bcf_wmode(args->output_type)); if ( args->out_fh == NULL ) error("Can't write to \"%s\": %s\n", args->output_fname, strerror(errno)); if ( args->flag & CF_QCALL ) return; if ( args->flag & CF_MCALL ) mcall_init(&args->aux); if ( args->flag & CF_CCALL ) ccall_init(&args->aux); if ( args->flag&CF_GVCF ) { bcf_hdr_append(args->aux.hdr,"##INFO=<ID=END,Number=1,Type=Integer,Description=\"End position of the variant described in this record\">"); args->gvcf.rid = -1; args->gvcf.line = bcf_init1(); args->gvcf.gt = (int32_t*) malloc(2*sizeof(int32_t)*bcf_hdr_nsamples(args->aux.hdr)); for (i=0; i<bcf_hdr_nsamples(args->aux.hdr); i++) { args->gvcf.gt[2*i+0] = bcf_gt_unphased(0); args->gvcf.gt[2*i+1] = bcf_gt_unphased(0); } } bcf_hdr_remove(args->aux.hdr, BCF_HL_INFO, "QS"); bcf_hdr_remove(args->aux.hdr, BCF_HL_INFO, "I16"); bcf_hdr_append_version(args->aux.hdr, args->argc, args->argv, "bcftools_call"); bcf_hdr_write(args->out_fh, args->aux.hdr); if ( args->flag&CF_INS_MISSED ) init_missed_line(args); }