//**********************************************************************************************************************
SffInfoCommand::SffInfoCommand(){
try {
- abort = true;
- //initialize outputTypes
+ abort = true; calledHelp = true;
vector<string> tempOutNames;
outputTypes["fasta"] = tempOutNames;
outputTypes["flow"] = tempOutNames;
//**********************************************************************************************************************
vector<string> SffInfoCommand::getRequiredParameters(){
try {
- string Array[] = {"sff"};
+ string Array[] = {"sff", "sfftxt", "or"};
vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
return myArray;
}
SffInfoCommand::SffInfoCommand(string option) {
try {
- abort = false;
+ abort = false; calledHelp = false;
hasAccnos = false;
//allow user to run help
- if(option == "help") { help(); abort = true; }
+ if(option == "help") { help(); abort = true; calledHelp = true; }
else {
//valid paramters for this command
string inputDir = validParameter.validFile(parameters, "inputdir", false); if (inputDir == "not found"){ inputDir = ""; }
sffFilename = validParameter.validFile(parameters, "sff", false);
- if (sffFilename == "not found") { m->mothurOut("sff is a required parameter for the sffinfo command."); m->mothurOutEndLine(); abort = true; }
+ if (sffFilename == "not found") { sffFilename = ""; }
else {
m->splitAtDash(sffFilename, filenames);
temp = validParameter.validFile(parameters, "trim", false); if (temp == "not found"){ temp = "T"; }
trim = m->isTrue(temp);
- temp = validParameter.validFile(parameters, "sfftxt", false); if (temp == "not found"){ temp = "F"; }
- sfftxt = m->isTrue(temp);
+ temp = validParameter.validFile(parameters, "sfftxt", false);
+ if (temp == "not found") { temp = "F"; sfftxt = false; sfftxtFilename = ""; }
+ else if (m->isTrue(temp)) { sfftxt = true; sfftxtFilename = ""; }
+ else {
+ //you are a filename
+ if (inputDir != "") {
+ map<string,string>::iterator it = parameters.find("sfftxt");
+ //user has given a template file
+ if(it != parameters.end()){
+ string path = m->hasPath(it->second);
+ //if the user has not given a path then, add inputdir. else leave path alone.
+ if (path == "") { parameters["sfftxt"] = inputDir + it->second; }
+ }
+ }
+
+ sfftxtFilename = validParameter.validFile(parameters, "sfftxt", true);
+ if (sfftxtFilename == "not found") { sfftxtFilename = ""; }
+ else if (sfftxtFilename == "not open") { sfftxtFilename = ""; }
+ }
+
+ if ((sfftxtFilename == "") && (filenames.size() == 0)) { m->mothurOut("[ERROR]: you must provide a valid sff or sfftxt file."); m->mothurOutEndLine(); abort=true; }
}
}
catch(exception& e) {
void SffInfoCommand::help(){
try {
- m->mothurOut("The sffinfo command reads a sff file and extracts the sequence data.\n");
+ m->mothurOut("The sffinfo command reads a sff file and extracts the sequence data, or you can use it to parse a sfftxt file..\n");
m->mothurOut("The sffinfo command parameters are sff, fasta, qfile, accnos, flow, sfftxt, and trim. sff is required. \n");
m->mothurOut("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");
m->mothurOut("The fasta parameter allows you to indicate if you would like a fasta formatted file generated. Default=True. \n");
m->mothurOut("The qfile parameter allows you to indicate if you would like a quality file generated. Default=True. \n");
m->mothurOut("The flow parameter allows you to indicate if you would like a flowgram file generated. Default=False. \n");
m->mothurOut("The sfftxt parameter allows you to indicate if you would like a sff.txt file generated. Default=False. \n");
+ m->mothurOut("If you want to parse an existing sfftxt file into flow, fasta and quality file, enter the file name using the sfftxt parameter. \n");
m->mothurOut("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");
m->mothurOut("The accnos parameter allows you to provide a accnos file containing the names of the sequences you would like extracted. You may enter multiple files by separating them by -'s. \n");
m->mothurOut("Example sffinfo(sff=mySffFile.sff, trim=F).\n");
int SffInfoCommand::execute(){
try {
- if (abort == true) { return 0; }
+ if (abort == true) { if (calledHelp) { return 0; } return 2; }
for (int s = 0; s < filenames.size(); s++) {
m->mothurOut("It took " + toString(time(NULL) - start) + " secs to extract " + toString(numReads) + ".");
}
+ if (sfftxtFilename != "") { parseSffTxt(); }
+
if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
//report output filenames
if (sfftxt) { m->openOutputFile(sfftxtFileName, outSfftxt); outSfftxt.setf(ios::fixed, ios::floatfield); outSfftxt.setf(ios::showpoint); outputNames.push_back(sfftxtFileName); outputTypes["sfftxt"].push_back(sfftxtFileName); }
if (fasta) { m->openOutputFile(outFastaFileName, outFasta); outputNames.push_back(outFastaFileName); outputTypes["fasta"].push_back(outFastaFileName); }
if (qual) { m->openOutputFile(outQualFileName, outQual); outputNames.push_back(outQualFileName); outputTypes["qual"].push_back(outQualFileName); }
- if (flow) { m->openOutputFile(outFlowFileName, outFlow); outputNames.push_back(outFlowFileName); outputTypes["flow"].push_back(outFlowFileName); }
+ if (flow) { m->openOutputFile(outFlowFileName, outFlow); outputNames.push_back(outFlowFileName); outFlow.setf(ios::fixed, ios::floatfield); outFlow.setf(ios::showpoint); outputTypes["flow"].push_back(outFlowFileName); }
ifstream in;
in.open(input.c_str(), ios::binary);
if (header.version != "0001") { m->mothurOut("Version is not supported, only support version 0001."); m->mothurOutEndLine(); return count; }
//print common header
- if (sfftxt) { printCommonHeader(outSfftxt, header); }
-
+ if (sfftxt) { printCommonHeader(outSfftxt, header); }
+ if (flow) { outFlow << header.numFlowsPerRead << endl; }
+
//read through the sff file
while (!in.eof()) {
if (header.name.length() > header.nameLength) { header.name = header.name.substr(0, header.nameLength); }
delete[] tempBuffer;
+ //extract info from name
+ 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;
}
}
//**********************************************************************************************************************
+int SffInfoCommand::decodeName(string& timestamp, string& region, string& xy, string name) {
+ try {
+
+ string time = name.substr(0, 6);
+ unsigned int timeNum = m->fromBase36(time);
+
+ int q1 = timeNum / 60;
+ int sec = timeNum - 60 * q1;
+ int q2 = q1 / 60;
+ int minute = q1 - 60 * q2;
+ int q3 = q2 / 24;
+ int hr = q2 - 24 * q3;
+ int q4 = q3 / 32;
+ int day = q3 - 32 * q4;
+ int q5 = q4 / 13;
+ int mon = q4 - 13 * q5;
+ int year = 2000 + q5;
+
+ timestamp = toString(year) + "_" + toString(mon) + "_" + toString(day) + "_" + toString(hr) + "_" + toString(minute) + "_" + toString(sec);
+
+ region = name.substr(7, 2);
+
+ string xyNum = name.substr(9);
+ unsigned int myXy = m->fromBase36(xyNum);
+ int x = myXy >> 12;
+ int y = myXy & 4095;
+
+ xy = toString(x) + "_" + toString(y);
+
+ return 0;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "SffInfoCommand", "decodeName");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
int SffInfoCommand::printCommonHeader(ofstream& out, CommonHeader& header) {
try {
try {
out << ">" << header.name << endl;
- out << "Run Prefix: " << endl;
- out << "Region #: " << endl;
- out << "XY Location: " << endl << endl;
+ out << "Run Prefix: " << header.timestamp << endl;
+ out << "Region #: " << header.region << endl;
+ out << "XY Location: " << header.xy << endl << endl;
out << "Run Name: " << endl;
out << "Analysis Name: " << endl;
}
}
- out << ">" << header.name << endl;
+ out << ">" << header.name << " xy=" << header.xy << endl;
out << seq << endl;
return 0;
out << "0\t0\t0\t0";
}
else if((header.clipQualRight != 0) && ((header.clipQualRight-header.clipQualLeft) >= 0)){
- out << ">" << header.name << " length=" << (header.clipQualRight-header.clipQualLeft) << endl;
+ out << ">" << header.name << " xy=" << header.xy << " length=" << (header.clipQualRight-header.clipQualLeft) << endl;
for (int i = (header.clipQualLeft-1); i < (header.clipQualRight-1); i++) { out << read.qualScores[i] << '\t'; }
}
else{
- out << ">" << header.name << " length=" << (header.clipQualRight-header.clipQualLeft) << endl;
+ out << ">" << header.name << " xy=" << header.xy << " length=" << (header.clipQualRight-header.clipQualLeft) << endl;
for (int i = (header.clipQualLeft-1); i < read.qualScores.size(); i++) { out << read.qualScores[i] << '\t'; }
}
}else{
- out << ">" << header.name << " length=" << read.qualScores.size() << endl;
+ out << ">" << header.name << " xy=" << header.xy << " length=" << read.qualScores.size() << endl;
for (int i = 0; i < read.qualScores.size(); i++) { out << read.qualScores[i] << '\t'; }
}
//**********************************************************************************************************************
int SffInfoCommand::printFlowSeqData(ofstream& out, seqRead& read, Header& header) {
try {
+ if(header.clipQualRight > header.clipQualLeft){
+
+ int rightIndex = 0;
+ for (int i = 0; i < header.clipQualRight; i++) { rightIndex += read.flowIndex[i]; }
+
+ out << header.name << ' ' << rightIndex;
+ for (int i = 0; i < read.flowgram.size(); i++) { out << setprecision(2) << ' ' << (read.flowgram[i]/(float)100); }
+ out << endl;
+ }
- out << ">" << header.name << endl;
- for (int i = 0; i < read.flowgram.size(); i++) { out << setprecision(2) << (read.flowgram[i]/(float)100) << '\t'; }
- out << endl;
return 0;
}
exit(1);
}
}
-//**********************************************************************************************************************/
+//**********************************************************************************************************************
+int SffInfoCommand::parseSffTxt() {
+ try {
+
+ ifstream inSFF;
+ m->openInputFile(sfftxtFilename, inSFF);
+
+ if (outputDir == "") { outputDir += m->hasPath(sfftxtFilename); }
+
+ //output file names
+ ofstream outFasta, outQual, outFlow;
+ string outFastaFileName, outQualFileName;
+ string outFlowFileName = outputDir + m->getRootName(m->getSimpleName(sfftxtFilename)) + "flow";
+ if (trim) {
+ outFastaFileName = outputDir + m->getRootName(m->getSimpleName(sfftxtFilename)) + "fasta";
+ outQualFileName = outputDir + m->getRootName(m->getSimpleName(sfftxtFilename)) + "qual";
+ }else{
+ outFastaFileName = outputDir + m->getRootName(m->getSimpleName(sfftxtFilename)) + "raw.fasta";
+ outQualFileName = outputDir + m->getRootName(m->getSimpleName(sfftxtFilename)) + "raw.qual";
+ }
+
+ if (fasta) { m->openOutputFile(outFastaFileName, outFasta); outputNames.push_back(outFastaFileName); outputTypes["fasta"].push_back(outFastaFileName); }
+ if (qual) { m->openOutputFile(outQualFileName, outQual); outputNames.push_back(outQualFileName); outputTypes["qual"].push_back(outQualFileName); }
+ if (flow) { m->openOutputFile(outFlowFileName, outFlow); outputNames.push_back(outFlowFileName); outFlow.setf(ios::fixed, ios::floatfield); outFlow.setf(ios::showpoint); outputTypes["flow"].push_back(outFlowFileName); }
+
+ //read common header
+ string commonHeader = m->getline(inSFF);
+ string magicNumber = m->getline(inSFF);
+ string version = m->getline(inSFF);
+ string indexOffset = m->getline(inSFF);
+ string indexLength = m->getline(inSFF);
+ int numReads = parseHeaderLineToInt(inSFF);
+ string headerLength = m->getline(inSFF);
+ string keyLength = m->getline(inSFF);
+ int numFlows = parseHeaderLineToInt(inSFF);
+ string flowgramCode = m->getline(inSFF);
+ string flowChars = m->getline(inSFF);
+ string keySequence = m->getline(inSFF);
+ m->gobble(inSFF);
+
+ string seqName;
+
+ if (flow) { outFlow << numFlows << endl; }
+
+ for(int i=0;i<numReads;i++){
+
+ //sanity check
+ if (inSFF.eof()) { m->mothurOut("[ERROR]: Expected " + toString(numReads) + " but reached end of file at " + toString(i+1) + "."); m->mothurOutEndLine(); break; }
+
+ Header header;
+
+ //parse read header
+ inSFF >> seqName;
+ seqName = seqName.substr(1);
+ m->gobble(inSFF);
+ header.name = seqName;
+
+ string runPrefix = parseHeaderLineToString(inSFF); header.timestamp = runPrefix;
+ string regionNumber = parseHeaderLineToString(inSFF); header.region = regionNumber;
+ string xyLocation = parseHeaderLineToString(inSFF); header.xy = xyLocation;
+ m->gobble(inSFF);
+
+ string runName = parseHeaderLineToString(inSFF);
+ string analysisName = parseHeaderLineToString(inSFF);
+ string fullPath = parseHeaderLineToString(inSFF);
+ m->gobble(inSFF);
+
+ string readHeaderLen = parseHeaderLineToString(inSFF); convert(readHeaderLen, header.headerLength);
+ string nameLength = parseHeaderLineToString(inSFF); convert(nameLength, header.nameLength);
+ int numBases = parseHeaderLineToInt(inSFF); header.numBases = numBases;
+ string clipQualLeft = parseHeaderLineToString(inSFF); convert(clipQualLeft, header.clipQualLeft);
+ int clipQualRight = parseHeaderLineToInt(inSFF); header.clipQualRight = clipQualRight;
+ string clipAdapLeft = parseHeaderLineToString(inSFF); convert(clipAdapLeft, header.clipAdapterLeft);
+ string clipAdapRight = parseHeaderLineToString(inSFF); convert(clipAdapRight, header.clipAdapterRight);
+ m->gobble(inSFF);
+
+ seqRead read;
+
+ //parse read
+ vector<unsigned short> flowVector = parseHeaderLineToFloatVector(inSFF, numFlows); read.flowgram = flowVector;
+ vector<unsigned int> flowIndices = parseHeaderLineToIntVector(inSFF, numBases);
+
+ //adjust for print
+ vector<unsigned int> flowIndicesAdjusted; flowIndicesAdjusted.push_back(flowIndices[0]);
+ for (int j = 1; j < flowIndices.size(); j++) { flowIndicesAdjusted.push_back(flowIndices[j] - flowIndices[j-1]); }
+ read.flowIndex = flowIndicesAdjusted;
+
+ string bases = parseHeaderLineToString(inSFF); read.bases = bases;
+ vector<unsigned int> qualityScores = parseHeaderLineToIntVector(inSFF, numBases); read.qualScores = qualityScores;
+ m->gobble(inSFF);
+
+ //if you have provided an accosfile and this seq is not in it, then dont print
+ bool print = true;
+ if (seqNames.size() != 0) { if (seqNames.count(header.name) == 0) { print = false; } }
+
+ //print
+ if (print) {
+ if (fasta) { printFastaSeqData(outFasta, read, header); }
+ if (qual) { printQualSeqData(outQual, read, header); }
+ if (flow) { printFlowSeqData(outFlow, read, header); }
+ }
+
+ //report progress
+ if((i+1) % 10000 == 0){ m->mothurOut(toString(i+1)); m->mothurOutEndLine(); }
+
+ if (m->control_pressed) { break; }
+ }
+
+ //report progress
+ if (!m->control_pressed) { if((numReads) % 10000 != 0){ m->mothurOut(toString(numReads)); m->mothurOutEndLine(); } }
+
+ inSFF.close();
+
+ if (fasta) { outFasta.close(); }
+ if (qual) { outQual.close(); }
+ if (flow) { outFlow.close(); }
+
+ return 0;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "SffInfoCommand", "parseSffTxt");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+
+int SffInfoCommand::parseHeaderLineToInt(ifstream& file){
+ try {
+ int number;
+
+ while (!file.eof()) {
+
+ char c = file.get();
+ if (c == ':'){
+ file >> number;
+ break;
+ }
+
+ }
+ m->gobble(file);
+ return number;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "SffInfoCommand", "parseHeaderLineToInt");
+ exit(1);
+ }
+
+}
+
+//**********************************************************************************************************************
+
+string SffInfoCommand::parseHeaderLineToString(ifstream& file){
+ try {
+ string text;
+
+ while (!file.eof()) {
+ char c = file.get();
+
+ if (c == ':'){
+ //m->gobble(file);
+ //text = m->getline(file);
+ file >> text;
+ break;
+ }
+ }
+ m->gobble(file);
+
+ return text;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "SffInfoCommand", "parseHeaderLineToString");
+ exit(1);
+ }
+}
+
+//**********************************************************************************************************************
+
+vector<unsigned short> SffInfoCommand::parseHeaderLineToFloatVector(ifstream& file, int length){
+ try {
+ vector<unsigned short> floatVector(length);
+
+ while (!file.eof()) {
+ char c = file.get();
+ if (c == ':'){
+ float temp;
+ for(int i=0;i<length;i++){
+ file >> temp;
+ floatVector[i] = temp * 100;
+ }
+ break;
+ }
+ }
+ m->gobble(file);
+ return floatVector;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "SffInfoCommand", "parseHeaderLineToFloatVector");
+ exit(1);
+ }
+}
+
+//**********************************************************************************************************************
+
+vector<unsigned int> SffInfoCommand::parseHeaderLineToIntVector(ifstream& file, int length){
+ try {
+ vector<unsigned int> intVector(length);
+
+ while (!file.eof()) {
+ char c = file.get();
+ if (c == ':'){
+ for(int i=0;i<length;i++){
+ file >> intVector[i];
+ }
+ break;
+ }
+ }
+ m->gobble(file);
+ return intVector;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "SffInfoCommand", "parseHeaderLineToIntVector");
+ exit(1);
+ }
+}
+
+//**********************************************************************************************************************
+
+
+
+