void Options::parse(int argc, char** argv) {
bool isLevelNotSet = true;
for (int argx = 1; argx < argc; argx++) {
// Handle Starting Level Option
if ( strcmp(argv[argx], "--level") == 0
|| strcmp(argv[argx], "-l") == 0) {
// Confirm that a level number has been provided.
if (argx + 1 >= argc || !isPositiveInt(argv[argx + 1])) {
die("You must provide a level number.");
}
// Confirm that the provided level is within range and is thus
// valid.
startingLevelNum = atoi(argv[++argx]);
if (startingLevelNum < 1 || startingLevelNum > LevelManager::GetTotal()) {
die("Invalid level.");
}
isLevelNotSet = false;
// Handle Help Flags.
} else if ( strcmp(argv[argx], "--help") == 0
|| strcmp(argv[argx], "-h") == 0) {
showHelp();
// Handle Version Flags.
} else if ( strcmp(argv[argx], "--version") == 0
|| strcmp(argv[argx], "-v") == 0 ) {
showVersion();
// Initial Mode will be the Editor.
} else if ( strcmp(argv[argx], "--editor") == 0
|| strcmp(argv[argx], "-e") == 0 ) {
initialState = EDIT;
// Initial Mode will be the Editor.
} else if ( strcmp(argv[argx], "--new") == 0
|| strcmp(argv[argx], "-n") == 0 ) {
createNewLevel = true;
} else {
die("Unrecognized option: " + std::string(argv[argx]));
}
}
if (initialState == EDIT && isLevelNotSet && !createNewLevel) {
die("You must provide a level number to edit or specify -n.");
}
}
void SimpleVCF::init(const vector<string> & fields, CoreVCF * corevcf_){ //string line){
unresolvedGT=false;
homozygousREF=false;
heterozygous=false;
homozygousALT=false;
indexGenotype=-1;
indexGenotypeQual=-1;
indexDepth=-1;
indexPL=-1;
typeOfData=1;
// fields=allTokens(line,'\t');
// corevcf = corevcf_;
int fieldIndex = corevcf->getFieldIndexAndIncrease();
// cerr<<"fieldIndex "<<fieldIndex<<endl;
//FORMAT FIELDS
rawFormatNames = fields[ corevcf->getFieldIndexINFO()+1 ];
rawFormatValues = fields[fieldIndex];
// cerr<<"rawFormatNames "<<rawFormatNames<<endl;
// cerr<<"rawFormatValues "<<rawFormatValues<<endl;
formatFieldNames = allTokens(rawFormatNames ,':');
formatFieldValues = allTokens(rawFormatValues,':');
if(rawFormatValues == "./."){
unresolvedGT=true;
observedPL=false;
observedGL=false;
haploidCall=false;
}else{
if(formatFieldNames.size() != formatFieldValues.size()){
cerr<<"SimpleVCF: for line "<<vectorToString(fields,"\t")<<" the format field does not have as many fields as the values"<<endl;
exit(1);
}
observedPL=false;
observedGL=false;
haploidCall=false;
for(unsigned int i=0;i<formatFieldNames.size();i++){
// cerr<<"formatFieldNames["<<i<<"] "<<formatFieldNames[i]<<" = "<<formatFieldValues[i]<<endl;
if(formatFieldNames[i] == "GT"){
indexGenotype =i;
formatFieldGT= formatFieldValues[i];
bool determinedGenotype=false;
//Taken from http://www.broadinstitute.org/gatk/guide/topic?name=intro
if(formatFieldGT == "./."){ determinedGenotype=true; unresolvedGT=true; }
if(formatFieldGT == "0"){ determinedGenotype=true; homozygousREF=true; haploidCall=true; }
if(formatFieldGT == "1"){ determinedGenotype=true; homozygousALT=true; haploidCall=true; }
if(formatFieldGT == "0/0"){ determinedGenotype=true; homozygousREF=true; }
if(formatFieldGT == "0|0"){ determinedGenotype=true; homozygousREF=true; }
if(formatFieldGT == "0/1"){ determinedGenotype=true; heterozygous=true; }
if(formatFieldGT == "0|1"){ determinedGenotype=true; heterozygous=true; }
if(formatFieldGT == "1|0"){ determinedGenotype=true; heterozygous=true; }
if(formatFieldGT == "1/1"){ determinedGenotype=true; homozygousALT=true; }
if(formatFieldGT == "1|1"){ determinedGenotype=true; homozygousALT=true; }
if(formatFieldGT == "1/2"){ determinedGenotype=true; heterozygousALT=true; } //has first alt and second alt
if(formatFieldGT == "1|2"){ determinedGenotype=true; heterozygousALT=true; } //has first alt and second alt
if(formatFieldGT == "2/1"){ determinedGenotype=true; heterozygousALT=true; } //has first alt and second alt
if(formatFieldGT == "2|1"){ determinedGenotype=true; heterozygousALT=true; } //has first alt and second alt
if(formatFieldGT == "0|2"){ determinedGenotype=true; heterozygous2ndALT=true; } //has ref and second alt
if(formatFieldGT == "0/2"){ determinedGenotype=true; heterozygous2ndALT=true; } //has ref and second alt
if(formatFieldGT == "2/0"){ determinedGenotype=true; heterozygous2ndALT=true; } //has ref and second alt
if(formatFieldGT == "2|0"){ determinedGenotype=true; heterozygous2ndALT=true; } //has ref and second alt
if(formatFieldGT == "2/2"){ determinedGenotype=true; homozygous2ndALT=true; } //twice the second alt
if(formatFieldGT == "2|2"){ determinedGenotype=true; homozygous2ndALT=true; } //twice the second alt
//for more than 3
if(!determinedGenotype){
vector<string> fieldsOfGT = allTokens(formatFieldGT ,'/');
if(fieldsOfGT.size() == 2){
// int alleleCFirst = destringify<int> (fieldsOfGT[0]);
// int alleleC2nd = destringify<int> (fieldsOfGT[1]);
if(isPositiveInt(fieldsOfGT[0]) &&
isPositiveInt(fieldsOfGT[1]) ){
determinedGenotype=true; unresolvedGT=true;
}
}else{
vector<string> fieldsOfGT = allTokens(formatFieldGT ,'|');
if(fieldsOfGT.size() == 2){
// int alleleCFirst = destringify<int> (fieldsOfGT[0]);
// int alleleC2nd = destringify<int> (fieldsOfGT[1]);
if(isPositiveInt(fieldsOfGT[0]) &&
isPositiveInt(fieldsOfGT[1]) ){
determinedGenotype=true; unresolvedGT=true;
}
}else{
}
}
}
// if(formatFieldGT == "0/3" ||
// formatFieldGT == "3/3" ||
// formatFieldGT == "3/3" ||
// ){ determinedGenotype=true; unresolvedGT=true;
if(!determinedGenotype){
cerr<<"SimpleVCF: unable to determine genotype for line "<<vectorToString(fields,"\t")<<" field=#"<<formatFieldGT<<"#"<<endl;
exit(1);
}
continue;
}
if(formatFieldNames[i] == "GQ"){
if(formatFieldValues[i] == "."){
indexGenotypeQual =i;
formatFieldGQ=0.0;
}else{
indexGenotypeQual =i;
formatFieldGQ=destringify<float>(formatFieldValues[i]);
}
continue; }
if(formatFieldNames[i] == "DP"){ indexDepth =i; formatFieldDP=destringify<int> (formatFieldValues[i]); continue;}
if(formatFieldNames[i] == "GL"){
observedGL=true;
if(observedPL){
cerr<<"SimpleVCF: cannot observed both GL and PL "<<vectorToString(fields,"\t")<<""<<endl;
exit(1);
}
indexPL = i;
formatFieldGL = formatFieldValues[i];
vector<string> glfields = allTokens(formatFieldGL,',');
if(glfields.size() == 2){ //haploid calls (e.g. X for a male)
if(!haploidCall){
cerr<<"SimpleVCF: cannot observed 2 GL fields for a non-haploid record "<<vectorToString(fields,"\t")<<""<<endl;
exit(1);
}
formatFieldPLHomoRef = int(-10.0*destringify<double>(glfields[0]));
formatFieldPLHetero = -1000000; //very unlikely
formatFieldPLHomoAlt = int(-10.0*destringify<double>(glfields[1]));
}else{
if(glfields.size() == 3){ //biallelic
formatFieldPLHomoRef = int(-10.0*destringify<double>(glfields[0]));
formatFieldPLHetero = int(-10.0*destringify<double>(glfields[1]));
formatFieldPLHomoAlt = int(-10.0*destringify<double>(glfields[2]));
}else{
if(glfields.size() == 6){ //triallelic
//according to VCF docs it has the following order AA,AB,BB,AC,BC,CC
formatFieldPLHomoRef = int(-10.0*destringify<double>(glfields[0])); //r-r
formatFieldPLHetero1 = int(-10.0*destringify<double>(glfields[1])); //r-a1
formatFieldPLHomoAlt1 = int(-10.0*destringify<double>(glfields[2])); //a1-a1
formatFieldPLHetero2 = int(-10.0*destringify<double>(glfields[3])); //r-a2
formatFieldPLHetero12 = int(-10.0*destringify<double>(glfields[4])); //a1-a2
formatFieldPLHomoAlt2 = int(-10.0*destringify<double>(glfields[5])); //a2-a2
}else{
cerr<<"SimpleVCF: for line "<<vectorToString(fields,"\t")<<" the GL field does not have 3 or 6 fields"<<endl;
exit(1);
}
}
}
}
if(formatFieldNames[i] == "PL"){
observedPL=true;
if(observedGL){
cerr<<"SimpleVCF: cannot observed both GL and PL "<<vectorToString(fields,"\t")<<""<<endl;
exit(1);
}
indexPL = i;
if(formatFieldValues[i] == "."){
formatFieldPL = formatFieldValues[i];
unresolvedGT=true;
continue;
}
formatFieldPL = formatFieldValues[i];
vector<string> plfields = allTokens(formatFieldPL,',');
if(plfields.size() == 3){ //biallelic
formatFieldPLHomoRef = destringify<int>(plfields[0]);
formatFieldPLHetero = destringify<int>(plfields[1]);
formatFieldPLHomoAlt = destringify<int>(plfields[2]);
}else{
if(plfields.size() == 6){ //triallelic
//according to VCF docs it has the following order AA,AB,BB,AC,BC,CC
formatFieldPLHomoRef = destringify<int>(plfields[0]); //r-r
formatFieldPLHetero1 = destringify<int>(plfields[1]); //r-a1
formatFieldPLHomoAlt1 = destringify<int>(plfields[2]); //a1-a1
formatFieldPLHetero2 = destringify<int>(plfields[3]); //r-a2
formatFieldPLHetero12 = destringify<int>(plfields[4]); //a1-a2
formatFieldPLHomoAlt2 = destringify<int>(plfields[5]); //a2-a2
}else{
cerr<<"SimpleVCF: for line "<<vectorToString(fields,"\t")<<" the PL field does not have 3 or 6 fields"<<endl;
exit(1);
}
}
continue;
}
//To uncomment the fields to get these fields
if(formatFieldNames[i] == "A"){
vector<string> adfield = allTokens( formatFieldValues[i] ,',');
for(unsigned int j=0;j<adfield.size();j++){
countA.push_back( destringify<int>( adfield[j]) );
}
continue;
}
if(formatFieldNames[i] == "C"){
vector<string> adfield = allTokens( formatFieldValues[i] ,',');
for(unsigned int j=0;j<adfield.size();j++){
countC.push_back( destringify<int>( adfield[j]) );
}
continue;
}
if(formatFieldNames[i] == "G"){
vector<string> adfield = allTokens( formatFieldValues[i] ,',');
for(unsigned int j=0;j<adfield.size();j++){
countG.push_back( destringify<int>( adfield[j]) );
}
continue;
}
if(formatFieldNames[i] == "T"){
vector<string> adfield = allTokens( formatFieldValues[i] ,',');
for(unsigned int j=0;j<adfield.size();j++){
countT.push_back( destringify<int>( adfield[j]) );
}
continue;
}
}
}
// cout<<getADforA()<<endl;
// cout<<getADforC()<<endl;
// cout<<getADforG()<<endl;
// cout<<getADforT()<<endl;
// cerr<<"end"<<endl;
}
