int main(int argc, char *argv[])
{
try
{
libmaus2::timing::RealTimeClock rtc; rtc.start();
::libmaus2::util::ArgInfo arginfo(argc,argv);
for ( uint64_t i = 0; i < arginfo.restargs.size(); ++i )
if (
arginfo.restargs[i] == "-v"
||
arginfo.restargs[i] == "--version"
)
{
std::cerr << ::biobambam2::Licensing::license();
return EXIT_SUCCESS;
}
else if (
arginfo.restargs[i] == "-h"
||
arginfo.restargs[i] == "--help"
)
{
std::cerr << ::biobambam2::Licensing::license() << std::endl;
std::cerr << "Key=Value pairs:" << std::endl;
std::cerr << std::endl;
std::vector< std::pair<std::string,std::string> > V;
V.push_back ( std::pair<std::string,std::string> ( "I=<[stdin]>", "input filename (default: read file from standard input)" ) );
#if defined(BIOBAMBAM_LIBMAUS2_HAVE_IO_LIB)
V.push_back ( std::pair<std::string,std::string> ( std::string("inputformat=<[")+getDefaultInputFormat()+"]>", "input format: cram, bam or sam" ) );
V.push_back ( std::pair<std::string,std::string> ( "reference=<[]>", "name of reference FastA in case of inputformat=cram" ) );
#else
V.push_back ( std::pair<std::string,std::string> ( "inputformat=<[bam]>", "input format: bam" ) );
#endif
#if defined(LIBMAUS2_HAVE_REGEX_H)
V.push_back ( std::pair<std::string,std::string> ( "name=<[]>", "consider only reads with names matching the given regualr expression (default: use all reads)" ) );
#endif
::biobambam2::Licensing::printMap(std::cerr,V);
std::cerr << std::endl;
return EXIT_SUCCESS;
}
bamalignfrac(arginfo);
std::cerr << "[V] " << libmaus2::util::MemUsage() << " wall clock time " << rtc.formatTime(rtc.getElapsedSeconds()) << std::endl;
}
catch(std::exception const & ex)
{
std::cerr << ex.what() << std::endl;
return EXIT_FAILURE;
}
}
int main(int argc, char * argv[])
{
try
{
::libmaus2::util::ArgInfo arginfo(argc,argv);
::std::vector<std::string> const & inputfilenames = arginfo.restargs;
char const * fasuffixes[] = { ".fa", ".fasta", 0 };
std::string defoutname = libmaus2::util::OutputFileNameTools::endClipLcp(inputfilenames,&fasuffixes[0]) + ".fa";
while ( ::libmaus2::util::GetFileSize::fileExists(defoutname) )
defoutname += "_";
std::string const outfilename = arginfo.getValue<std::string>("outfilename",defoutname);
std::cerr << "output file name " << defoutname << std::endl;
::std::vector< ::libmaus2::fastx::FastAReader::RewriteInfo > const info = ::libmaus2::fastx::FastAReader::rewriteFiles(inputfilenames,outfilename);
for ( uint64_t i = 0; i < info.size(); ++i )
std::cerr << info[i].valid << "\t" << info[i].idlen << "\t" << info[i].seqlen << "\t" << info[i].getIdPrefix() << std::endl;
return EXIT_SUCCESS;
}
catch(std::exception const & ex)
{
std::cerr << ex.what() << std::endl;
return EXIT_FAILURE;
}
}
int main(int argc, char * argv[])
{
::libmaus::util::ArgInfo arginfo(argc,argv);
#if defined(LIBMAUS_HAVE_KMLOCAL)
return kmlocalmain(arginfo);
#else
std::cerr << "kmlocal is not available." << std::endl;
return EXIT_FAILURE;
#endif
}
int main(int argc, char * argv[])
{
try
{
::libmaus2::util::ArgInfo arginfo(argc,argv);
srand(time(0));
testIncudedBWTSingle("fischersfritzfischtfrischefische$");
testIncudedBWTSingle("jmmississiippii$");
testIncudedBWTSingle("mmississiippii$");
testIncudedBWTSingle("ababababababab$");
testIncudedBWTSingle("babbbabbba$");
testIncudedBWTSingle("abbbabbbaa$");
testIncudedBWTSingle("abbbbabbbb$");
testIncudedBWTSingle("fischfritz$");
testIncudedBWTSingle("babbbbbb$");
testIncudedBWTBinary();
testInducedBWTRandom();
}
catch(std::exception const & ex)
{
std::cerr << ex.what() << std::endl;
return EXIT_FAILURE;
}
}
int main(int argc, char * argv[])
{
try
{
::libmaus::util::ArgInfo arginfo(argc,argv);
::libmaus::util::TempFileRemovalContainer::setup();
::std::vector<std::string> const & inputfilenames = arginfo.restargs;
char const * fasuffixes[] = { ".fa", ".fasta", 0 };
std::string deftmpname = libmaus::util::OutputFileNameTools::endClipLcp(inputfilenames,&fasuffixes[0]) + ".fa.tmp";
while ( ::libmaus::util::GetFileSize::fileExists(deftmpname) )
deftmpname += "_";
std::string defoutname = libmaus::util::OutputFileNameTools::endClipLcp(inputfilenames,&fasuffixes[0]) + ".fa.recoded";
while ( ::libmaus::util::GetFileSize::fileExists(defoutname) )
defoutname += "_";
std::string const tempfilename = arginfo.getValue<std::string>("tempfilename",deftmpname);
std::string const outfilename = arginfo.getValue<std::string>("outputfilename",defoutname);
std::string const indexfilename = tempfilename + ".index";
unsigned int const addterm = arginfo.getValue<unsigned int>("addterm",0);
unsigned int const termadd = addterm ? 1 : 0;
::libmaus::util::TempFileRemovalContainer::addTempFile(tempfilename);
::libmaus::util::TempFileRemovalContainer::addTempFile(indexfilename);
std::cerr << "temp file name " << tempfilename << std::endl;
std::cerr << "output file name " << outfilename << std::endl;
/* uint64_t const numseq = */ ::libmaus::fastx::FastAReader::rewriteFiles(inputfilenames,tempfilename,indexfilename);
uint64_t curpos = 0;
::libmaus::aio::CheckedOutputStream COS(outfilename);
// 0,A,C,G,T,N
// map forward
::libmaus::autoarray::AutoArray<char> cmap(256,false);
std::fill(cmap.begin(),cmap.end(),5+termadd);
cmap['\n'] = 0 + termadd;
cmap['a'] = cmap['A'] = 1 + termadd;
cmap['c'] = cmap['C'] = 2 + termadd;
cmap['g'] = cmap['G'] = 3 + termadd;
cmap['t'] = cmap['T'] = 4 + termadd;
cmap['n'] = cmap['N'] = 5 + termadd;
// map to reverse complement
::libmaus::autoarray::AutoArray<char> rmap(256,false);
std::fill(rmap.begin(),rmap.end(),5+termadd);
rmap['\n'] = 0 + termadd;
rmap['a'] = rmap['A'] = 4 + termadd;
rmap['c'] = rmap['C'] = 3 + termadd;
rmap['g'] = rmap['G'] = 2 + termadd;
rmap['t'] = rmap['T'] = 1 + termadd;
rmap['n'] = rmap['N'] = 5 + termadd;
// reverse complement for mapped data
::libmaus::autoarray::AutoArray<char> xmap(256,false);
std::fill(xmap.begin(),xmap.end(),5+termadd);
xmap[0] = 0 + termadd;
xmap[1] = 4 + termadd;
xmap[2] = 3 + termadd;
xmap[3] = 2 + termadd;
xmap[4] = 1 + termadd;
xmap[5] = 5 + termadd;
::libmaus::autoarray::AutoArray<char> imap(256,false);
for ( uint64_t i = 0; i < imap.size(); ++i )
imap[i] = static_cast<char>(i);
::libmaus::fastx::FastAReader::RewriteInfoDecoder::unique_ptr_type infodec(new ::libmaus::fastx::FastAReader::RewriteInfoDecoder(indexfilename));
::libmaus::fastx::FastAReader::RewriteInfo info;
uint64_t maxseqlen = 0;
while ( infodec->get(info) )
maxseqlen = std::max(maxseqlen,info.seqlen);
std::cerr << "[V] max seq len " << maxseqlen << std::endl;
::libmaus::fastx::FastAReader::RewriteInfoDecoder::unique_ptr_type tinfodec(new ::libmaus::fastx::FastAReader::RewriteInfoDecoder(indexfilename));
infodec = UNIQUE_PTR_MOVE(tinfodec);
if ( maxseqlen <= 256*1024 )
{
::libmaus::aio::CheckedInputStream CIS(tempfilename);
::libmaus::autoarray::AutoArray<uint8_t> B(maxseqlen+1,false);
while ( infodec->get(info) )
{
// skip id
CIS.ignore(info.idlen+2);
// read sequence plus following terminator
CIS.read(reinterpret_cast<char *>(B.begin()), info.seqlen+1);
// map
for ( uint64_t i = 0; i < info.seqlen+1; ++i )
B[i] = cmap[B[i]];
// write
COS.write(reinterpret_cast<char const *>(B.begin()),info.seqlen+1);
// remap
for ( uint64_t i = 0; i < info.seqlen+1; ++i )
B[i] = xmap[B[i]];
// reverse
std::reverse(B.begin(),B.begin()+info.seqlen);
// write
COS.write(reinterpret_cast<char const *>(B.begin()),info.seqlen+1);
}
}
else
{
while ( infodec->get(info) )
{
// std::cerr << info.valid << "\t" << info.idlen << "\t" << info.seqlen << "\t" << info.getIdPrefix() << std::endl;
uint64_t const seqbeg = curpos + (info.idlen+2);
uint64_t const seqend = seqbeg + info.seqlen;
::libmaus::aio::CheckedInputStream CIS(tempfilename); CIS.seekg(seqbeg);
::libmaus::util::GetFileSize::copyMap(CIS,COS,cmap.begin(),seqend-seqbeg+1);
::libmaus::aio::CircularReverseWrapper CRW(tempfilename,seqend);
::libmaus::util::GetFileSize::copyMap(CRW,COS,rmap.begin(),seqend-seqbeg+1);
curpos += (info.idlen+2) + (info.seqlen+1);
}
}
if ( addterm )
COS.put(0);
return EXIT_SUCCESS;
}
catch(std::exception const & ex)
{
std::cerr << ex.what() << std::endl;
return EXIT_FAILURE;
}
}
