// Constructor
Input(int argc, char **argv)
: ec_(false), shortestOnly_(false), distances_(false), suppressRef_(false),
overlaps_(true), delim_("|"), refFile_(""), nonRefFile_(""), chr_("all") {
typedef Ext::UserError UE;
if ( 1 == argc )
throw(NoInput());
int argcntr = 1;
bool outoption = false; // may choose up to one type of non-default output option
// [Process-Flags]
std::string next = "";
while ( argcntr < argc ) {
next = argv[argcntr];
if ( next == "--help" )
throw(HelpException());
else if ( next == "--version" )
throw(VersionException());
else if ( next == "--ec" || next == "--header" )
ec_ = true;
else if ( next == "--no-overlaps" )
overlaps_ = false;
else if ( next == "--delim" ) {
Ext::Assert<UE>(++argcntr < argc, "No value given for --delim.");
delim_ = argv[argcntr];
}
else if ( next == "--chrom" ) {
Ext::Assert<UE>(++argcntr < argc, "No value given for --chrome.");
chr_ = argv[argcntr];
}
else if ( next == "--closest" ) {
Ext::Assert<UE>(!outoption, "Multiple output options not allowed.");
shortestOnly_ = true;
outoption = true;
}
else if ( next == "--dist" )
distances_ = true;
else if ( next == "--no-ref" )
suppressRef_ = true;
else if ( next == "--help" )
throw(HelpException());
else if ( next == "--shortest" ) { // silently supported for bckwd compatibility
Ext::Assert<UE>(!outoption, "Multiple output options not allowed.");
shortestOnly_ = true;
outoption = true;
} else { // the rest are two input files?
Ext::Assert<UE>(argcntr + 2 == argc, "Unknown option: " + next + ".");
break;
}
++argcntr;
} // while
Ext::Assert<UE>(argcntr + 2 == argc, "Not enough input files given.");
refFile_ = argv[argcntr++];
nonRefFile_ = argv[argcntr];
Ext::Assert<UE>(refFile_.find("--") != 0, "Option given where file expected: " + refFile_ + ".");
Ext::Assert<UE>(nonRefFile_.find("--") != 0, "Option given where file expected: " + nonRefFile_ + ".");
}
Input::Input(int argc, char** argv) : _niters(1), _nstates(1), _nsymbols(0),
_verbose(false), _read_params(false),
_seed(std::time(NULL)) {
for ( int i = 1; i < argc; ++i ) {
if ( std::string(argv[i]) == "--help" )
throw(Help());
else if ( std::string(argv[i]) == "--version" )
throw(Version());
} // for
if ( argc == 1 )
throw(NoInput());
if ( argc < 4 )
throw("Wrong number of args: see --help");
const std::string ints = "0123456789";
int nextc = 1;
const std::string todo = argv[nextc++];
std::string next = argv[nextc++];
if ( todo == "train" || todo == "train-and-decode" ) {
if ( (argc < 5) || (argc > 7) )
throw("Wrong number of args for '" + todo + ". See --help");
_operation = Ops::TRAIN;
if ( todo == "train-and-decode" )
_operation = Ops::TRAIN_AND_DECODE;
int count = argc;
while ( next.find_first_of("--seed") == 0 || next.find_first_of("--verbose") == 0 ) {
if ( --count == 0 )
break;
if ( next == "--verbose" ) {
_verbose = true;
} else {
auto v = split(next, "=");
if ( v.size() != 2 )
throw("Bad number. Expect a +integer for " + next + ". See --help");
if ( v[1].find_first_not_of(ints) != std::string::npos )
throw("Bad number. Expect a +integer for " + next + ". See --help");
_seed = std::atoi(v[1].c_str());
std::srand(_seed);
}
if ( nextc != argc )
next = argv[nextc++];
else
break;
} // while
if ( count != 5 )
throw("Wrong number (or order) of arguments for " + todo + ". See --help");
if ( next.find_first_not_of(ints) != std::string::npos )
throw("Bad argument: expect a +integer for <number-states>. See --help");
_nstates = std::atoi(next.c_str());
next = argv[nextc++];
if ( next.find_first_not_of(ints) != std::string::npos )
throw("Bad argument - expect a +integer for <number-iterations>. See --help");
_niters = std::atoi(next.c_str());
} else if ( todo == "probability" ) {
if ( argc != 4 )
throw("Wrong number of args for '" + todo + ". See --help");
_operation = Ops::PROB;
_params = next;
std::ifstream f(_params.c_str());
if (!f)
throw("Input file not found: " + _params);
read_parameters();
} else if ( todo == "decode" ) {
if ( argc != 4 )
throw("Wrong number of args for '" + todo + ". See --help");
_operation = Ops::DECODE;
_params = next;
std::ifstream f(_params.c_str());
if (!f)
throw("Input file not found: " + _params);
read_parameters();
} else {
throw("Unknown operation: '" + todo + "'. See --help.");
}
if ( _niters <= 0 || _niters > _MAXITER )
throw("Bad number of '" + todo + "' iterations");
else if ( _nstates <= 0 || _nstates > _MAXSTATES )
throw("Bad number of '" + todo + "' states");
_src = argv[nextc++];
std::ifstream f(_src.c_str());
if (!f)
throw("Input file not found: " + _src);
read_data(); // read observations; get _nsymbols from the data
if ( todo == "train" || todo == "train-and-decode" ) {
initialize_parameters(); // only after read_data() due to _nsymbols
if ( _nsymbols == 0 )
throw("Didn't find any data");
}
}
