static int query_chroms(char *fname)
{
const char **seq;
int i, nseq, ftype = file_type(fname);
if ( ftype & IS_TXT || !ftype )
{
tbx_t *tbx = tbx_index_load(fname);
if ( !tbx ) error("Could not load .tbi index of %s\n", fname);
seq = tbx_seqnames(tbx, &nseq);
for (i=0; i<nseq; i++)
printf("%s\n", seq[i]);
free(seq);
tbx_destroy(tbx);
}
else if ( ftype==IS_BCF )
{
htsFile *fp = hts_open(fname,"r");
if ( !fp ) error("Could not read %s\n", fname);
bcf_hdr_t *hdr = bcf_hdr_read(fp);
if ( !hdr ) error("Could not read the header: %s\n", fname);
hts_close(fp);
hts_idx_t *idx = bcf_index_load(fname);
if ( !idx ) error("Could not load .csi index of %s\n", fname);
seq = bcf_index_seqnames(idx, hdr, &nseq);
for (i=0; i<nseq; i++)
printf("%s\n", seq[i]);
free(seq);
bcf_hdr_destroy(hdr);
hts_idx_destroy(idx);
}
else if ( ftype==IS_BAM ) // todo: BAM
error("BAM: todo\n");
return 0;
}
int vcf_index_stats(char *fname, int stats)
{
char *fn_out = NULL;
FILE *out;
out = fn_out ? fopen(fn_out, "w") : stdout;
const char **seq;
int i, nseq;
tbx_t *tbx = NULL;
hts_idx_t *idx = NULL;
htsFile *fp = hts_open(fname,"r");
if ( !fp ) { fprintf(stderr,"Could not read %s\n", fname); return 1; }
bcf_hdr_t *hdr = bcf_hdr_read(fp);
if ( !hdr ) { fprintf(stderr,"Could not read the header: %s\n", fname); return 1; }
if ( hts_get_format(fp)->format==vcf )
{
tbx = tbx_index_load(fname);
if ( !tbx ) { fprintf(stderr,"Could not load TBI index: %s\n", fname); return 1; }
}
else if ( hts_get_format(fp)->format==bcf )
{
idx = bcf_index_load(fname);
if ( !idx ) { fprintf(stderr,"Could not load CSI index: %s\n", fname); return 1; }
}
else
{
fprintf(stderr,"Could not detect the file type as VCF or BCF: %s\n", fname);
return 1;
}
seq = tbx ? tbx_seqnames(tbx, &nseq) : bcf_index_seqnames(idx, hdr, &nseq);
uint64_t sum = 0;
for (i=0; i<nseq; i++)
{
uint64_t records, v;
hts_idx_get_stat(tbx ? tbx->idx : idx, i, &records, &v);
sum+=records;
if (stats&2 || !records) continue;
bcf_hrec_t *hrec = bcf_hdr_get_hrec(hdr, BCF_HL_CTG, "ID", seq[i], NULL);
int hkey = hrec ? bcf_hrec_find_key(hrec, "length") : -1;
fprintf(out,"%s\t%s\t%" PRIu64 "\n", seq[i], hkey<0?".":hrec->vals[hkey], records);
}
if (!sum)
{
// No counts found.
// Is this because index version has no stored count data, or no records?
bcf1_t *rec = bcf_init1();
if (bcf_read1(fp, hdr, rec) >= 0)
{
fprintf(stderr,"%s index of %s does not contain any count metadata. Please re-index with a newer version of bcftools or tabix.\n", tbx ? "TBI" : "CSI", fname);
return 1;
}
bcf_destroy1(rec);
}
if (stats&2) fprintf(out, "%" PRIu64 "\n", sum);
free(seq);
fclose(out);
hts_close(fp);
bcf_hdr_destroy(hdr);
if (tbx)
tbx_destroy(tbx);
if (idx)
hts_idx_destroy(idx);
return 0;
}
int main(int argc, char* argv[]) {
namespace po = boost::program_options;
std::string file;
std::string output;
try
{
// Declare the supported options.
po::options_description desc("Allowed options");
desc.add_options()
("help,h", "produce help message")
("version", "Show version")
("input-file", po::value< std::string >(), "The input files")
("output-file", po::value<std::string>(), "The output file name.")
;
po::positional_options_description popts;
popts.add("input-file", 1);
popts.add("output-file", 1);
po::options_description cmdline_options;
cmdline_options
.add(desc)
;
po::variables_map vm;
po::store(po::command_line_parser(argc, argv).
options(cmdline_options).positional(popts).run(), vm);
po::notify(vm);
if (vm.count("version"))
{
std::cout << "vcfhdr2json version " << HAPLOTYPES_VERSION << "\n";
return 0;
}
if (vm.count("help"))
{
std::cout << desc << "\n";
return 1;
}
if (vm.count("input-file"))
{
file = vm["input-file"].as< std::string > ();
}
if (vm.count("output-file"))
{
output = vm["output-file"].as< std::string >();
}
if(file.size() == 0)
{
std::cerr << "Please specify an input file.\n";
return 1;
}
if (output == "")
{
std::cerr << "Please specify an output file.\n";
return 1;
}
}
catch (po::error & e)
{
std::cerr << e.what() << "\n";
return 1;
}
try
{
Json::StyledWriter writer;
htsFile * fp = bcf_open(file.c_str(), "r");
bcf_hdr_t * hdr = bcf_hdr_read(fp);
Json::Value root;
Json::Value a;
for (int i = 0; i < bcf_hdr_nsamples(hdr); ++i)
{
a.append(hdr->samples[i]);
}
root["samples"] = a;
Json::Value fields;
for (int i = 0; i < hdr->nhrec; i++)
{
Json::Value field;
field["key"] = hdr->hrec[i]->key;
if (!hdr->hrec[i]->value)
{
Json::Value values;
for (int j = 0; j < hdr->hrec[i]->nkeys; j++)
{
values[hdr->hrec[i]->keys[j]] = hdr->hrec[i]->vals[j];
}
field["values"] = values;
}
else
{
field["value"] = hdr->hrec[i]->value;
}
fields.append(field);
}
root["fields"] = fields;
tbx_t * tbx_idx = tbx_index_load(file.c_str());
if ( !tbx_idx )
{
hts_idx_t * csi_idx = bcf_index_load(file.c_str());
if(!csi_idx)
{
root["tabix"] = Json::Value::null;
}
else
{
root["tabix"] = Json::Value();
root["tabix"]["chromosomes"] = Json::Value();
int count = 0;
const char ** tbx_names = bcf_index_seqnames(csi_idx, hdr, &count);
for (int i = 0; i < count; ++i)
{
root["tabix"]["chromosomes"].append(tbx_names[i]);
}
free(tbx_names);
hts_idx_destroy(csi_idx);
}
}
else
{
root["tabix"] = Json::Value();
root["tabix"]["chromosomes"] = Json::Value();
int count = 0;
const char ** tbx_names = tbx_seqnames(tbx_idx, &count);
for (int i = 0; i < count; ++i)
{
root["tabix"]["chromosomes"].append(tbx_names[i]);
}
free(tbx_names);
tbx_destroy(tbx_idx);
}
std::ofstream out(output.c_str());
out << writer.write(root);
bcf_close(fp);
bcf_hdr_destroy(hdr);
}
catch(std::runtime_error & e)
{
std::cerr << e.what() << std::endl;
return 1;
}
catch(std::logic_error & e)
{
std::cerr << e.what() << std::endl;
return 1;
}
return 0;
}
int convert(int argc, char **argv)
{
if (argc < 2) return convert_help();
int c;
char *in=NULL, *out=NULL, *bim=NULL, *vid=NULL, *tmp_dir=NULL, *ped=NULL;
uint32_t num_fields, num_records, col = 2;
int i_is_set = 0,
o_is_set = 0,
f_is_set = 0,
b_is_set = 0,
v_is_set = 0,
t_is_set = 0,
p_is_set = 0,
r_is_set = 0;
while((c = getopt (argc, argv, "hi:o:f:r:b:v:t:p:c:")) != -1) {
switch (c) {
case 'c':
col = atoi(optarg);
break;
case 'p':
p_is_set = 1;
ped = optarg;
break;
case 't':
t_is_set = 1;
tmp_dir = optarg;
break;
case 'v':
v_is_set = 1;
vid = optarg;
break;
case 'b':
b_is_set = 1;
bim = optarg;
break;
case 'i':
i_is_set = 1;
in = optarg;
break;
case 'o':
o_is_set = 1;
out = optarg;
break;
case 'f':
f_is_set = 1;
num_fields = atoi(optarg);
break;
case 'r':
r_is_set = 1;
num_records = atoi(optarg);
break;
case 'h':
convert_help();
return 1;
case '?':
if ( (optopt == 'i') ||
(optopt == 'f') ||
(optopt == 'r') ||
(optopt == 't') ||
(optopt == 's') ||
(optopt == 'p') ||
(optopt == 'c') ||
(optopt == 'o') )
fprintf (stderr, "Option -%c requires an argument.\n",
optopt);
else if (isprint (optopt))
fprintf (stderr, "Unknown option `-%c'.\n", optopt);
else
fprintf (stderr, "Unknown option character `\\x%x'.\n", optopt);
default:
convert_help();
return 1;
}
}
char *type = argv[0];
if (i_is_set == 0) {
printf("Input file is not set\n");
return convert_help();
}
if (strcmp(type, "bcf") == 0) {
if ( (f_is_set == 0) || (r_is_set == 0) ) {
fprintf(stderr,"Attempting to autodetect num of records "
"and fields from %s\n", in);
//Try and auto detect the sizes, need the index
tbx_t *tbx = NULL;
hts_idx_t *idx = NULL;
htsFile *fp = hts_open(in,"rb");
if ( !fp ) {
fprintf(stderr,"Could not read %s\n", in);
return 1;
}
bcf_hdr_t *hdr = bcf_hdr_read(fp);
if ( !hdr ) {
fprintf(stderr,"Could not read the header: %s\n", in);
return 1;
}
if (hts_get_format(fp)->format==vcf) {
tbx = tbx_index_load(in);
if ( !tbx ) {
fprintf(stderr,"Could not load TBI index: %s\n", in);
return 1;
}
} else if ( hts_get_format(fp)->format==bcf ) {
idx = bcf_index_load(in);
if ( !idx ) {
fprintf(stderr,"Could not load CSI index: %s\n", in);
return 1;
}
} else {
fprintf(stderr,
"Could not detect the file type as VCF or BCF: %s\n",
in);
return 1;
}
num_fields = hdr->n[BCF_DT_SAMPLE];
num_records = 0;
const char **seq;
int nseq;
seq = tbx ? tbx_seqnames(tbx, &nseq) :
bcf_index_seqnames(idx, hdr, &nseq);
int i;
uint32_t sum = 0;
for (i = 0; i < nseq; ++i) {
uint64_t records, v;
hts_idx_get_stat(tbx ? tbx->idx: idx, i, &records, &v);
num_records += records;
}
fprintf(stderr, "Number of records:%u\tNumber of fields:%u\n",
num_records, num_fields);
free(seq);
hts_close(fp);
bcf_hdr_destroy(hdr);
if (idx)
hts_idx_destroy(idx);
if (tbx)
tbx_destroy(tbx);
}
if (o_is_set == 0) {
out = (char*)malloc(strlen(in) + 5); // 5 for ext and \0
strcpy(out,in);
strcat(out, ".gqt");
}
if (b_is_set == 0) {
bim = (char*)malloc(strlen(in) + 5); // 5 for ext and \0
strcpy(bim,in);
strcat(bim, ".bim");
}
if (v_is_set == 0) {
vid = (char*)malloc(strlen(in) + 5); // 5 for ext and \0
strcpy(vid,in);
strcat(vid, ".vid");
}
if (t_is_set == 0) {
tmp_dir = (char*)malloc(3*sizeof(char)); // "./\0"
strcpy(tmp_dir,"./");
}
int r = bcf_wahbm(in, out, bim, vid, tmp_dir, num_fields, num_records);
return r;
}
if (strcmp(type, "ped") == 0) {
if (o_is_set == 0) {
if (p_is_set == 1) {
out = (char*)malloc(strlen(ped) + 4); // 4 for ext and \0
strcpy(out,ped);
strcat(out, ".db");
} else {
out = (char*)malloc(strlen(in) + 4); // 4 for ext and \0
strcpy(out,in);
strcat(out, ".db");
}
}
fprintf(stderr, "Creating sample database %s\n", out);
return ped_ped(in, ped, col, out);
}
return convert_help();
}