int main (int argc, char* argv[])
{
if (argc < 2)
{
std::cerr << "you must provide a bank." << std::endl;
return EXIT_FAILURE;
}
// We define a try/catch block in case some method fails
try
{
// We declare an input Bank and use it locally
IBank* inputBank = Bank::open (argv[1]);
LOCAL (inputBank);
// We create a sequence iterator for the bank with progress information
ProgressIterator<Sequence> iter (*inputBank, "Iterating sequences");
// We loop over sequences.
for (iter.first(); !iter.isDone(); iter.next())
{
// Note that we do nothing inside the sequence iterating loop
}
}
catch (Exception& e)
{
std::cerr << "EXCEPTION: " << e.getMessage() << std::endl;
}
}
int main (int argc, char* argv[])
{
/** We create a command line parser. */
OptionsParser parser ("BankStats");
parser.push_back (new OptionOneParam (STR_URI_INPUT, "bank input", true));
try
{
/** We parse the user options. */
IProperties* options = parser.parse (argc, argv);
// We get information about the bank.
u_int64_t nbSequences=0, dataSize=0, seqMaxSize=0, seqMinSize=~0;
// We declare an input Bank and use it locally
IBank* inputBank = Bank::open (options->getStr(STR_URI_INPUT));
LOCAL (inputBank);
ProgressIterator<Sequence> it (*inputBank, "iterate");
for (it.first(); !it.isDone(); it.next())
{
Data& data = it.item().getData();
nbSequences ++;
if (data.size() > seqMaxSize) { seqMaxSize = data.size(); }
if (data.size() < seqMinSize) { seqMinSize = data.size(); }
dataSize += data.size ();
}
std::cout << "data size : " << dataSize << std::endl;
std::cout << "sequence number : " << nbSequences << std::endl;
std::cout << "sequence max size : " << seqMaxSize << std::endl;
std::cout << "sequence min size : " << seqMinSize << std::endl;
}
catch (OptionFailure& e)
{
return e.displayErrors (std::cout);
}
catch (Exception& e)
{
std::cerr << "EXCEPTION: " << e.getMessage() << std::endl;
}
}
int main (int argc, char* argv[])
{
/** We create a command line parser. */
OptionsParser parser ("KmerTest");
parser.push_back (new OptionOneParam (STR_URI_INPUT, "bank input", true));
parser.push_back (new OptionOneParam (STR_KMER_SIZE, "kmer size", true));
parser.push_back (new OptionOneParam (STR_MINIMIZER_SIZE, "minimizer size", true));
parser.push_back (new OptionNoParam (STR_VERBOSE, "display kmers", false));
try
{
/** We parse the user options. */
IProperties* options = parser.parse (argc, argv);
// We get the kmer and minimizer sizes.
size_t kmerSize = options->getInt(STR_KMER_SIZE);
size_t mmerSize = options->getInt(STR_MINIMIZER_SIZE);
// We define a try/catch block in case some method fails (bad filename for instance)
u_int64_t nbKmers = 0;
bool display = options->get(STR_VERBOSE) != 0;
// We declare a Bank instance defined by a list of filenames
IBank* bank = Bank::open (options->getStr(STR_URI_INPUT));
LOCAL (bank);
// We declare a kmer model and a minimizer model
Model model (kmerSize, mmerSize);
// We get a reference on the minimizer model, which will be useful for dumping
const ModelMinimizer::Model& modelMinimizer = model.getMmersModel();
Kmer<span>::Type checksum;
size_t nbChanged = 0;
size_t nbInvalid = 0;
// We define an iterator that encapsulates the sequences iterator with progress feedback
ProgressIterator<Sequence> iter (*bank, "iterate bank");
// We loop over sequences.
for (iter.first(); !iter.isDone(); iter.next())
{
// Shortcut
Sequence& seq = iter.item();
//! [snippet1_iterate]
// We iterate the kmers (and minimizers) of the current sequence.
model.iterate (seq.getData(), [&] (const Model::Kmer& kmer, size_t idx)
{
nbKmers ++;
if (kmer.hasChanged() == true) { nbChanged++; }
if (kmer.isValid() == false) { nbInvalid++; }
checksum += kmer.minimizer().value();
});
//! [snippet1_iterate]
}
cout << "nbKmers : " << nbKmers << endl;
cout << "nbInvalid : " << nbInvalid << endl;
cout << "nbChanged : " << nbChanged << endl;
cout << "ratio : " << (nbChanged > 0 ? (double)nbKmers / (double)nbChanged : 0) << endl;
cout << "checksum : " << checksum << endl;
}
catch (OptionFailure& e)
{
return e.displayErrors (std::cout);
}
catch (Exception& e)
{
std::cerr << "EXCEPTION: " << e.getMessage() << std::endl;
}
return EXIT_SUCCESS;
}
int main (int argc, char* argv[])
{
/** We create a command line parser. */
OptionsParser parser ("BankSplitter");
parser.push_back (new OptionOneParam (STR_URI_INPUT, "bank reference", true));
parser.push_back (new OptionOneParam (STR_MAX_INPUT_SIZE, "average db size per split", true));
parser.push_back (new OptionOneParam (STR_URI_OUTPUT_DIR, "output directory", false, "."));
parser.push_back (new OptionNoParam (STR_OUTPUT_FASTQ, "fastq output", false));
parser.push_back (new OptionNoParam (STR_OUTPUT_GZ, "gzip output", false));
// We define a try/catch block in case some method fails (bad filename for instance)
try
{
/** We parse the user options. */
IProperties* options = parser.parse (argc, argv);
/** Shortcuts. */
u_int64_t maxDbSize = options->getInt(STR_MAX_INPUT_SIZE);
// We declare an input Bank
IBank* inputBank = Bank::open (options->getStr(STR_URI_INPUT));
LOCAL (inputBank);
// We get the basename of the input bank.
string inputBasename = System::file().getBaseName (options->getStr(STR_URI_INPUT));
/** We set the name of the output directory. */
stringstream ss; ss << inputBasename << "_S" << maxDbSize;
string outputDirName = ss.str();
/** We create the output directory. */
string outputDir = options->getStr(STR_URI_OUTPUT_DIR) + "/" + outputDirName;
System::file().mkdir (outputDir, S_IRWXU);
// We create the album bank.
BankAlbum album (outputDir + "/album.txt");
/** We get estimations about the bank. */
u_int64_t number, totalSize, maxSize;
inputBank->estimate (number, totalSize, maxSize);
u_int64_t estimationNbSeqToIterate = number;
// We create an iterator over the input bank
ProgressIterator<Sequence> itSeq (*inputBank, "split");
// We loop over sequences to get the exact number of sequences.
int64_t nbBanksOutput = -1;
u_int64_t nbSequences = 0;
u_int64_t dbSize = ~0;
bool isFastq = options->get(STR_OUTPUT_FASTQ) != 0;
bool isGzipped = options->get(STR_OUTPUT_GZ) != 0;
IBank* currentBank = 0;
for (itSeq.first(); !itSeq.isDone(); itSeq.next())
{
if (dbSize > maxDbSize)
{
if (currentBank != 0) { currentBank->flush(); currentBank->finalize(); }
nbBanksOutput ++;
/** We build the uri of the current bank. */
stringstream ss; ss << inputBasename << "_" << nbBanksOutput << (isFastq ? ".fastq" : ".fasta");
if (isGzipped) { ss << ".gz"; }
/** We create a new bank and put it in the album. */
currentBank = album.addBank (outputDir, ss.str(), isFastq, isGzipped);
/** We reinit the db size counter. */
dbSize = 0;
}
dbSize += itSeq->getDataSize();
/** We insert the sequence into the current output bank. */
currentBank->insert (*itSeq);
}
if (currentBank != 0) { currentBank->flush(); }
}
catch (OptionFailure& e)
{
return e.displayErrors (cout);
}
catch (Exception& e)
{
cerr << "EXCEPTION: " << e.getMessage() << endl;
}
}
