CommandParameter psff("sff", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(psff);
CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(paccnos);
CommandParameter psfftxt("sfftxt", "String", "", "", "", "", "",false,false); parameters.push_back(psfftxt);
- CommandParameter pflow("flow", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(pflow);
+ CommandParameter pflow("flow", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pflow);
CommandParameter ptrim("trim", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(ptrim);
CommandParameter pfasta("fasta", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pfasta);
CommandParameter pqfile("name", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pqfile);
helpString += "The sff parameter allows you to enter the sff file you would like to extract data from. You may enter multiple files by separating them by -'s.\n";
helpString += "The fasta parameter allows you to indicate if you would like a fasta formatted file generated. Default=True. \n";
helpString += "The qfile parameter allows you to indicate if you would like a quality file generated. Default=True. \n";
- helpString += "The flow parameter allows you to indicate if you would like a flowgram file generated. Default=False. \n";
+ helpString += "The flow parameter allows you to indicate if you would like a flowgram file generated. Default=True. \n";
helpString += "The sfftxt parameter allows you to indicate if you would like a sff.txt file generated. Default=False. \n";
helpString += "If you want to parse an existing sfftxt file into flow, fasta and quality file, enter the file name using the sfftxt parameter. \n";
helpString += "The trim parameter allows you to indicate if you would like a sequences and quality scores trimmed to the clipQualLeft and clipQualRight values. Default=True. \n";
//erase from file list
filenames.erase(filenames.begin()+i);
i--;
- }
+ }else { m->setSFFFile(filenames[i]); }
}
}
temp = validParameter.validFile(parameters, "fasta", false); if (temp == "not found"){ temp = "T"; }
fasta = m->isTrue(temp);
- temp = validParameter.validFile(parameters, "flow", false); if (temp == "not found"){ temp = "F"; }
+ temp = validParameter.validFile(parameters, "flow", false); if (temp == "not found"){ temp = "T"; }
flow = m->isTrue(temp);
temp = validParameter.validFile(parameters, "trim", false); if (temp == "not found"){ temp = "T"; }
}
if ((sfftxtFilename == "") && (filenames.size() == 0)) {
- //if there is a current fasta file, use it
+ //if there is a current sff file, use it
string filename = m->getSFFFile();
if (filename != "") { filenames.push_back(filename); m->mothurOut("Using " + filename + " as input file for the sff parameter."); m->mothurOutEndLine(); }
else { m->mothurOut("[ERROR]: you must provide a valid sff or sfftxt file."); m->mothurOutEndLine(); abort=true; }
//**********************************************************************************************************************
int SffInfoCommand::execute(){
try {
-
if (abort == true) { if (calledHelp) { return 0; } return 2; }
for (int s = 0; s < filenames.size(); s++) {
- if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
+ if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
int start = time(NULL);
+ filenames[s] = m->getFullPathName(filenames[s]);
m->mothurOut("Extracting info from " + filenames[s] + " ..." ); m->mothurOutEndLine();
string accnos = "";
if (sfftxtFilename != "") { parseSffTxt(); }
- if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
+ if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
//set fasta file as new current fastafile
string current = "";
ofstream outSfftxt, outFasta, outQual, outFlow;
string outFastaFileName, outQualFileName;
+ string rootName = outputDir + m->getRootName(m->getSimpleName(input));
+ if(rootName.find_last_of(".") == rootName.npos){ rootName += "."; }
+
string sfftxtFileName = outputDir + m->getRootName(m->getSimpleName(input)) + "sff.txt";
string outFlowFileName = outputDir + m->getRootName(m->getSimpleName(input)) + "flow";
if (trim) {
//read data
seqRead read;
readSeqData(in, read, header.numFlowsPerRead, readheader.numBases);
-
+ bool okay = sanityCheck(readheader, read);
+ if (!okay) { break; }
+
//if you have provided an accosfile and this seq is not in it, then dont print
if (seqNames.size() != 0) { if (seqNames.count(readheader.name) == 0) { print = false; } }
//read offset
char buffer2 [8];
in.read(buffer2, 8);
- header.indexOffset = be_int8(*(unsigned long int *)(&buffer2));
+ header.indexOffset = be_int8(*(unsigned long long *)(&buffer2));
//read index length
char buffer3 [4];
delete[] tempBuffer2;
/* Pad to 8 chars */
- unsigned long int spotInFile = in.tellg();
- unsigned long int spot = (spotInFile + 7)& ~7; // ~ inverts
+ unsigned long long spotInFile = in.tellg();
+ unsigned long long spot = (spotInFile + 7)& ~7; // ~ inverts
in.seekg(spot);
}else{
decodeName(header.timestamp, header.region, header.xy, header.name);
/* Pad to 8 chars */
- unsigned long int spotInFile = in.tellg();
- unsigned long int spot = (spotInFile + 7)& ~7;
+ unsigned long long spotInFile = in.tellg();
+ unsigned long long spot = (spotInFile + 7)& ~7;
in.seekg(spot);
}else{
in.read(buffer, 2);
read.flowgram[i] = be_int2(*(unsigned short *)(&buffer));
}
-
+
//read flowIndex
read.flowIndex.resize(numBases);
for (int i = 0; i < numBases; i++) {
}
/* Pad to 8 chars */
- unsigned long int spotInFile = in.tellg();
- unsigned long int spot = (spotInFile + 7)& ~7;
+ unsigned long long spotInFile = in.tellg();
+ unsigned long long spot = (spotInFile + 7)& ~7;
in.seekg(spot);
}else{
exit(1);
}
}
-
+//**********************************************************************************************************************
+bool SffInfoCommand::sanityCheck(Header& header, seqRead& read) {
+ try {
+ bool okay = true;
+ string message = "[WARNING]: Your sff file may be corrupted! Sequence: " + header.name + "\n";
+
+ if (header.clipQualLeft > read.bases.length()) {
+ okay = false; message += "Clip Qual Left = " + toString(header.clipQualLeft) + ", but we only read " + toString(read.bases.length()) + " bases.\n";
+ }
+ if (header.clipQualRight > read.bases.length()) {
+ okay = false; message += "Clip Qual Right = " + toString(header.clipQualRight) + ", but we only read " + toString(read.bases.length()) + " bases.\n";
+ }
+ if (header.clipQualLeft > read.qualScores.size()) {
+ okay = false; message += "Clip Qual Left = " + toString(header.clipQualLeft) + ", but we only read " + toString(read.qualScores.size()) + " quality scores.\n";
+ }
+ if (header.clipQualRight > read.qualScores.size()) {
+ okay = false; message += "Clip Qual Right = " + toString(header.clipQualRight) + ", but we only read " + toString(read.qualScores.size()) + " quality scores.\n";
+ }
+
+ if (okay == false) {
+ m->mothurOut(message); m->mothurOutEndLine();
+ }
+
+ return okay;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "SffInfoCommand", "sanityCheck");
+ exit(1);
+ }
+}
//**********************************************************************************************************************
int SffInfoCommand::printSffTxtSeqData(ofstream& out, seqRead& read, Header& header) {
try {
-
out << "Flowgram: ";
for (int i = 0; i < read.flowgram.size(); i++) { out << setprecision(2) << (read.flowgram[i]/(float)100) << '\t'; }
//**********************************************************************************************************************
int SffInfoCommand::printFastaSeqData(ofstream& out, seqRead& read, Header& header) {
try {
-
string seq = read.bases;
- if (trim) {
+ if (trim) {
if(header.clipQualRight < header.clipQualLeft){
seq = "NNNN";
}
//output file names
ofstream outFasta, outQual, outFlow;
string outFastaFileName, outQualFileName;
- string outFlowFileName = outputDir + m->getRootName(m->getSimpleName(sfftxtFilename)) + "flow";
+ string fileRoot = m->getRootName(m->getSimpleName(sfftxtFilename));
+ if (fileRoot.length() > 0) {
+ //rip off last .
+ fileRoot = fileRoot.substr(0, fileRoot.length()-1);
+ fileRoot = m->getRootName(fileRoot);
+ }
+
+ string outFlowFileName = outputDir + fileRoot + "flow";
if (trim) {
- outFastaFileName = outputDir + m->getRootName(m->getSimpleName(sfftxtFilename)) + "fasta";
- outQualFileName = outputDir + m->getRootName(m->getSimpleName(sfftxtFilename)) + "qual";
+ outFastaFileName = outputDir + fileRoot + "fasta";
+ outQualFileName = outputDir + fileRoot + "qual";
}else{
- outFastaFileName = outputDir + m->getRootName(m->getSimpleName(sfftxtFilename)) + "raw.fasta";
- outQualFileName = outputDir + m->getRootName(m->getSimpleName(sfftxtFilename)) + "raw.qual";
+ outFastaFileName = outputDir + fileRoot + "raw.fasta";
+ outQualFileName = outputDir + fileRoot + "raw.qual";
}
if (fasta) { m->openOutputFile(outFastaFileName, outFasta); outputNames.push_back(outFastaFileName); outputTypes["fasta"].push_back(outFastaFileName); }