int GetRAbundCommand::createRabund(CountTable& ct, ListVector*& list, RAbundVector*& rabund){
try {
rabund->setLabel(list->getLabel());
for(int i = 0; i < list->getNumBins(); i++) {
if (m->control_pressed) { return 0; }
vector<string> binNames;
string bin = list->get(i);
m->splitAtComma(bin, binNames);
int total = 0;
for (int j = 0; j < binNames.size(); j++) {
total += ct.getNumSeqs(binNames[j]);
}
rabund->push_back(total);
}
return 0;
}
catch(exception& e) {
m->errorOut(e, "GetRAbundCommand", "createRabund");
exit(1);
}
}
int DeconvoluteCommand::execute() {
try {
if (abort) { if (calledHelp) { return 0; } return 2; }
//prepare filenames and open files
map<string, string> variables;
variables["[filename]"] = outputDir + util.getRootName(util.getSimpleName(fastafile));
string outNameFile = getOutputFileName("name", variables);
string outCountFile = getOutputFileName("count", variables);
variables["[extension]"] = util.getExtension(fastafile);
string outFastaFile = getOutputFileName("fasta", variables);
map<string, string> nameMap;
map<string, string>::iterator itNames;
if (namefile != "") {
util.readNames(namefile, nameMap);
if (namefile == outNameFile){
//prepare filenames and open files
map<string, string> mvariables;
mvariables["[filename]"] = outputDir + util.getRootName(util.getSimpleName(fastafile));
mvariables["[tag]"] = "unique";
outNameFile = getOutputFileName("name", mvariables);
}
}
CountTable ct;
if (countfile != "") {
ct.readTable(countfile, true, false);
if (countfile == outCountFile){
//prepare filenames and open files
map<string, string> mvariables;
mvariables["[filename]"] = outputDir + util.getRootName(util.getSimpleName(fastafile));
mvariables["[tag]"] = "unique";
outCountFile = getOutputFileName("count", mvariables); }
}
if (m->getControl_pressed()) { return 0; }
ifstream in;
util.openInputFile(fastafile, in);
ofstream outFasta;
util.openOutputFile(outFastaFile, outFasta);
map<string, string> sequenceStrings; //sequenceString -> list of names. "atgc...." -> seq1,seq2,seq3.
map<string, string>::iterator itStrings;
set<string> nameInFastaFile; //for sanity checking
set<string>::iterator itname;
vector<string> nameFileOrder;
CountTable newCt;
int count = 0;
while (!in.eof()) {
if (m->getControl_pressed()) { in.close(); outFasta.close(); util.mothurRemove(outFastaFile); return 0; }
Sequence seq(in);
if (seq.getName() != "") {
//sanity checks
itname = nameInFastaFile.find(seq.getName());
if (itname == nameInFastaFile.end()) { nameInFastaFile.insert(seq.getName()); }
else { m->mothurOut("[ERROR]: You already have a sequence named " + seq.getName() + " in your fasta file, sequence names must be unique, please correct."); m->mothurOutEndLine(); }
itStrings = sequenceStrings.find(seq.getAligned());
if (itStrings == sequenceStrings.end()) { //this is a new unique sequence
//output to unique fasta file
seq.printSequence(outFasta);
if (namefile != "") {
itNames = nameMap.find(seq.getName());
if (itNames == nameMap.end()) { //namefile and fastafile do not match
m->mothurOut("[ERROR]: " + seq.getName() + " is in your fasta file, and not in your namefile, please correct."); m->mothurOutEndLine();
}else {
if (format == "name") { sequenceStrings[seq.getAligned()] = itNames->second; nameFileOrder.push_back(seq.getAligned());
}else { newCt.push_back(seq.getName(), util.getNumNames(itNames->second)); sequenceStrings[seq.getAligned()] = seq.getName(); nameFileOrder.push_back(seq.getAligned()); }
}
}else if (countfile != "") {
if (format == "name") {
int numSeqs = ct.getNumSeqs(seq.getName());
string expandedName = seq.getName()+"_0";
for (int i = 1; i < numSeqs; i++) { expandedName += "," + seq.getName() + "_" + toString(i); }
sequenceStrings[seq.getAligned()] = expandedName; nameFileOrder.push_back(seq.getAligned());
}else {
ct.getNumSeqs(seq.getName()); //checks to make sure seq is in table
sequenceStrings[seq.getAligned()] = seq.getName(); nameFileOrder.push_back(seq.getAligned());
}
}else {
if (format == "name") { sequenceStrings[seq.getAligned()] = seq.getName(); nameFileOrder.push_back(seq.getAligned()); }
else { newCt.push_back(seq.getName()); sequenceStrings[seq.getAligned()] = seq.getName(); nameFileOrder.push_back(seq.getAligned()); }
}
}else { //this is a dup
if (namefile != "") {
itNames = nameMap.find(seq.getName());
if (itNames == nameMap.end()) { //namefile and fastafile do not match
m->mothurOut("[ERROR]: " + seq.getName() + " is in your fasta file, and not in your namefile, please correct."); m->mothurOutEndLine();
}else {
if (format == "name") { sequenceStrings[seq.getAligned()] += "," + itNames->second; }
else { int currentReps = newCt.getNumSeqs(itStrings->second); newCt.setNumSeqs(itStrings->second, currentReps+(util.getNumNames(itNames->second))); }
}
}else if (countfile != "") {
if (format == "name") {
int numSeqs = ct.getNumSeqs(seq.getName());
string expandedName = seq.getName()+"_0";
for (int i = 1; i < numSeqs; i++) { expandedName += "," + seq.getName() + "_" + toString(i); }
sequenceStrings[seq.getAligned()] += "," + expandedName;
}else {
int num = ct.getNumSeqs(seq.getName()); //checks to make sure seq is in table
if (num != 0) { //its in the table
ct.mergeCounts(itStrings->second, seq.getName()); //merges counts and saves in uniques name
}
}
}else {
if (format == "name") { sequenceStrings[seq.getAligned()] += "," + seq.getName(); }
else { int currentReps = newCt.getNumSeqs(itStrings->second); newCt.setNumSeqs(itStrings->second, currentReps+1); }
}
}
count++;
}
util.gobble(in);
if(count % 1000 == 0) { m->mothurOutJustToScreen(toString(count) + "\t" + toString(sequenceStrings.size()) + "\n"); }
}
if(count % 1000 != 0) { m->mothurOut(toString(count) + "\t" + toString(sequenceStrings.size())); m->mothurOutEndLine(); }
in.close();
outFasta.close();
if (m->getControl_pressed()) { util.mothurRemove(outFastaFile); return 0; }
//print new names file
ofstream outNames;
if (format == "name") { util.openOutputFile(outNameFile, outNames); outputNames.push_back(outNameFile); outputTypes["name"].push_back(outNameFile); }
else { util.openOutputFile(outCountFile, outNames); outputTypes["count"].push_back(outCountFile); outputNames.push_back(outCountFile); }
if ((countfile != "") && (format == "count")) { ct.printHeaders(outNames); }
else if ((countfile == "") && (format == "count")) { newCt.printHeaders(outNames); }
for (int i = 0; i < nameFileOrder.size(); i++) {
if (m->getControl_pressed()) { outputTypes.clear(); util.mothurRemove(outFastaFile); outNames.close(); for (int j = 0; j < outputNames.size(); j++) { util.mothurRemove(outputNames[j]); } return 0; }
itStrings = sequenceStrings.find(nameFileOrder[i]);
if (itStrings != sequenceStrings.end()) {
if (format == "name") {
//get rep name
int pos = (itStrings->second).find_first_of(',');
if (pos == string::npos) { // only reps itself
outNames << itStrings->second << '\t' << itStrings->second << endl;
}else {
outNames << (itStrings->second).substr(0, pos) << '\t' << itStrings->second << endl;
}
}else {
if (countfile != "") { ct.printSeq(outNames, itStrings->second); }
else if (format == "count") { newCt.printSeq(outNames, itStrings->second); }
}
}else{ m->mothurOut("[ERROR]: mismatch in namefile print."); m->mothurOutEndLine(); m->setControl_pressed(true); }
}
outNames.close();
if (m->getControl_pressed()) { outputTypes.clear(); util.mothurRemove(outFastaFile); for (int j = 0; j < outputNames.size(); j++) { util.mothurRemove(outputNames[j]); } return 0; }
m->mothurOut("\nOutput File Names: \n");
outputNames.push_back(outFastaFile); outputTypes["fasta"].push_back(outFastaFile);
for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i] +"\n"); } m->mothurOutEndLine();
//set fasta file as new current fastafile
string currentName = "";
itTypes = outputTypes.find("fasta");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { currentName = (itTypes->second)[0]; current->setFastaFile(currentName); }
}
itTypes = outputTypes.find("name");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { currentName = (itTypes->second)[0]; current->setNameFile(currentName); }
}
itTypes = outputTypes.find("count");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { currentName = (itTypes->second)[0]; current->setCountFile(currentName); }
}
return 0;
}
catch(exception& e) {
m->errorOut(e, "DeconvoluteCommand", "execute");
exit(1);
}
}
int SeqSummaryCommand::execute(){
try{
if (abort == true) { if (calledHelp) { return 0; } return 2; }
int start = time(NULL);
//set current fasta to fastafile
m->setFastaFile(fastafile);
map<string, string> variables;
variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(fastafile));
string summaryFile = getOutputFileName("summary",variables);
long long numSeqs = 0;
long long size = 0;
long long numUniques = 0;
map<int, long long> startPosition;
map<int, long long> endPosition;
map<int, long long> seqLength;
map<int, long long> ambigBases;
map<int, long long> longHomoPolymer;
if (namefile != "") { nameMap = m->readNames(namefile); numUniques = nameMap.size(); }
else if (countfile != "") {
CountTable ct;
ct.readTable(countfile, false, false);
nameMap = ct.getNameMap();
size = ct.getNumSeqs();
numUniques = ct.getNumUniqueSeqs();
}
if (m->control_pressed) { return 0; }
vector<unsigned long long> positions;
#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
positions = m->divideFile(fastafile, processors);
for (int i = 0; i < (positions.size()-1); i++) { lines.push_back(new linePair(positions[i], positions[(i+1)])); }
#else
positions = m->setFilePosFasta(fastafile, numSeqs);
if (numSeqs < processors) { processors = numSeqs; }
//figure out how many sequences you have to process
int numSeqsPerProcessor = numSeqs / processors;
for (int i = 0; i < processors; i++) {
int startIndex = i * numSeqsPerProcessor;
if(i == (processors - 1)){ numSeqsPerProcessor = numSeqs - i * numSeqsPerProcessor; }
lines.push_back(new linePair(positions[startIndex], numSeqsPerProcessor));
}
#endif
if(processors == 1){
numSeqs = driverCreateSummary(startPosition, endPosition, seqLength, ambigBases, longHomoPolymer, fastafile, summaryFile, lines[0]);
}else{
numSeqs = createProcessesCreateSummary(startPosition, endPosition, seqLength, ambigBases, longHomoPolymer, fastafile, summaryFile);
}
if (m->control_pressed) { return 0; }
//set size
if (countfile != "") {}//already set
else if (namefile == "") { size = numSeqs; }
else { for (map<int, long long>::iterator it = startPosition.begin(); it != startPosition.end(); it++) { size += it->second; } }
if ((namefile != "") || (countfile != "")) {
string type = "count";
if (namefile != "") { type = "name"; }
if (numSeqs != numUniques) { // do fasta and name/count files match
m->mothurOut("[ERROR]: Your " + type + " file contains " + toString(numUniques) + " unique sequences, but your fasta file contains " + toString(numSeqs) + ". File mismatch detected, quitting command.\n"); m->control_pressed = true;
}
}
if (m->control_pressed) { m->mothurRemove(summaryFile); return 0; }
long long ptile0_25 = 1+(long long)(size * 0.025); //number of sequences at 2.5%
long long ptile25 = 1+(long long)(size * 0.250); //number of sequences at 25%
long long ptile50 = 1+(long long)(size * 0.500);
long long ptile75 = 1+(long long)(size * 0.750);
long long ptile97_5 = 1+(long long)(size * 0.975);
long long ptile100 = (long long)(size);
vector<int> starts; starts.resize(7,0); vector<int> ends; ends.resize(7,0); vector<int> ambigs; ambigs.resize(7,0); vector<int> lengths; lengths.resize(7,0); vector<int> homops; homops.resize(7,0);
//find means
long long meanStartPosition, meanEndPosition, meanSeqLength, meanAmbigBases, meanLongHomoPolymer;
meanStartPosition = 0; meanEndPosition = 0; meanSeqLength = 0; meanAmbigBases = 0; meanLongHomoPolymer = 0;
//minimum
if ((startPosition.begin())->first == -1) { starts[0] = 0; }
else {starts[0] = (startPosition.begin())->first; }
long long totalSoFar = 0;
//set all values to min
starts[1] = starts[0]; starts[2] = starts[0]; starts[3] = starts[0]; starts[4] = starts[0]; starts[5] = starts[0];
int lastValue = 0;
for (map<int, long long>::iterator it = startPosition.begin(); it != startPosition.end(); it++) {
int value = it->first; if (value == -1) { value = 0; }
meanStartPosition += (value*it->second);
totalSoFar += it->second;
if (((totalSoFar <= ptile0_25) && (totalSoFar > 1)) || ((lastValue < ptile0_25) && (totalSoFar > ptile0_25))){ starts[1] = value; } //save value
if (((totalSoFar <= ptile25) && (totalSoFar > ptile0_25)) || ((lastValue < ptile25) && (totalSoFar > ptile25))) { starts[2] = value; } //save value
if (((totalSoFar <= ptile50) && (totalSoFar > ptile25)) || ((lastValue < ptile50) && (totalSoFar > ptile50))) { starts[3] = value; } //save value
if (((totalSoFar <= ptile75) && (totalSoFar > ptile50)) || ((lastValue < ptile75) && (totalSoFar > ptile75))) { starts[4] = value; } //save value
if (((totalSoFar <= ptile97_5) && (totalSoFar > ptile75)) || ((lastValue < ptile97_5) && (totalSoFar > ptile97_5))) { starts[5] = value; } //save value
if ((totalSoFar <= ptile100) && (totalSoFar > ptile97_5)) { starts[6] = value; } //save value
lastValue = totalSoFar;
}
starts[6] = (startPosition.rbegin())->first;
if ((endPosition.begin())->first == -1) { ends[0] = 0; }
else {ends[0] = (endPosition.begin())->first; }
totalSoFar = 0;
//set all values to min
ends[1] = ends[0]; ends[2] = ends[0]; ends[3] = ends[0]; ends[4] = ends[0]; ends[5] = ends[0];
lastValue = 0;
for (map<int, long long>::iterator it = endPosition.begin(); it != endPosition.end(); it++) {
int value = it->first; if (value == -1) { value = 0; }
meanEndPosition += (value*it->second);
totalSoFar += it->second;
if (((totalSoFar <= ptile0_25) && (totalSoFar > 1)) || ((lastValue < ptile0_25) && (totalSoFar > ptile0_25))){ ends[1] = value; } //save value
if (((totalSoFar <= ptile25) && (totalSoFar > ptile0_25)) || ((lastValue < ptile25) && (totalSoFar > ptile25))) { ends[2] = value; } //save value
if (((totalSoFar <= ptile50) && (totalSoFar > ptile25)) || ((lastValue < ptile50) && (totalSoFar > ptile50))) { ends[3] = value; } //save value
if (((totalSoFar <= ptile75) && (totalSoFar > ptile50)) || ((lastValue < ptile75) && (totalSoFar > ptile75))) { ends[4] = value; } //save value
if (((totalSoFar <= ptile97_5) && (totalSoFar > ptile75)) || ((lastValue < ptile97_5) && (totalSoFar > ptile97_5))) { ends[5] = value; } //save value
if ((totalSoFar <= ptile100) && (totalSoFar > ptile97_5)) { ends[6] = value; } //save value
lastValue = totalSoFar;
}
ends[6] = (endPosition.rbegin())->first;
if ((seqLength.begin())->first == -1) { lengths[0] = 0; }
else {lengths[0] = (seqLength.begin())->first; }
//set all values to min
lengths[1] = lengths[0]; lengths[2] = lengths[0]; lengths[3] = lengths[0]; lengths[4] = lengths[0]; lengths[5] = lengths[0];
totalSoFar = 0;
lastValue = 0;
for (map<int, long long>::iterator it = seqLength.begin(); it != seqLength.end(); it++) {
int value = it->first;
meanSeqLength += (value*it->second);
totalSoFar += it->second;
if (((totalSoFar <= ptile0_25) && (totalSoFar > 1)) || ((lastValue < ptile0_25) && (totalSoFar > ptile0_25))){ lengths[1] = value; } //save value
if (((totalSoFar <= ptile25) && (totalSoFar > ptile0_25)) || ((lastValue < ptile25) && (totalSoFar > ptile25))) { lengths[2] = value; } //save value
if (((totalSoFar <= ptile50) && (totalSoFar > ptile25)) || ((lastValue < ptile50) && (totalSoFar > ptile50))) { lengths[3] = value; } //save value
if (((totalSoFar <= ptile75) && (totalSoFar > ptile50)) || ((lastValue < ptile75) && (totalSoFar > ptile75))) { lengths[4] = value; } //save value
if (((totalSoFar <= ptile97_5) && (totalSoFar > ptile75)) || ((lastValue < ptile97_5) && (totalSoFar > ptile97_5))) { lengths[5] = value; } //save value
if ((totalSoFar <= ptile100) && (totalSoFar > ptile97_5)) { lengths[6] = value; } //save value
lastValue = totalSoFar;
}
lengths[6] = (seqLength.rbegin())->first;
if ((ambigBases.begin())->first == -1) { ambigs[0] = 0; }
else {ambigs[0] = (ambigBases.begin())->first; }
//set all values to min
ambigs[1] = ambigs[0]; ambigs[2] = ambigs[0]; ambigs[3] = ambigs[0]; ambigs[4] = ambigs[0]; ambigs[5] = ambigs[0];
totalSoFar = 0;
lastValue = 0;
for (map<int, long long>::iterator it = ambigBases.begin(); it != ambigBases.end(); it++) {
int value = it->first;
meanAmbigBases += (value*it->second);
totalSoFar += it->second;
if (((totalSoFar <= ptile0_25) && (totalSoFar > 1)) || ((lastValue < ptile0_25) && (totalSoFar > ptile0_25))){ ambigs[1] = value; } //save value
if (((totalSoFar <= ptile25) && (totalSoFar > ptile0_25)) || ((lastValue < ptile25) && (totalSoFar > ptile25))) { ambigs[2] = value; } //save value
if (((totalSoFar <= ptile50) && (totalSoFar > ptile25)) || ((lastValue < ptile50) && (totalSoFar > ptile50))) { ambigs[3] = value; } //save value
if (((totalSoFar <= ptile75) && (totalSoFar > ptile50)) || ((lastValue < ptile75) && (totalSoFar > ptile75))) { ambigs[4] = value; } //save value
if (((totalSoFar <= ptile97_5) && (totalSoFar > ptile75)) || ((lastValue < ptile97_5) && (totalSoFar > ptile97_5))) { ambigs[5] = value; } //save value
if ((totalSoFar <= ptile100) && (totalSoFar > ptile97_5)) { ambigs[6] = value; } //save value
lastValue = totalSoFar;
}
ambigs[6] = (ambigBases.rbegin())->first;
if ((longHomoPolymer.begin())->first == -1) { homops[0] = 0; }
else {homops[0] = (longHomoPolymer.begin())->first; }
//set all values to min
homops[1] = homops[0]; homops[2] = homops[0]; homops[3] = homops[0]; homops[4] = homops[0]; homops[5] = homops[0];
totalSoFar = 0;
lastValue = 0;
for (map<int, long long>::iterator it = longHomoPolymer.begin(); it != longHomoPolymer.end(); it++) {
int value = it->first;
meanLongHomoPolymer += (it->first*it->second);
totalSoFar += it->second;
if (((totalSoFar <= ptile0_25) && (totalSoFar > 1)) || ((lastValue < ptile0_25) && (totalSoFar > ptile0_25))){ homops[1] = value; } //save value
if (((totalSoFar <= ptile25) && (totalSoFar > ptile0_25)) || ((lastValue < ptile25) && (totalSoFar > ptile25))) { homops[2] = value; } //save value
if (((totalSoFar <= ptile50) && (totalSoFar > ptile25)) || ((lastValue < ptile50) && (totalSoFar > ptile50))) { homops[3] = value; } //save value
if (((totalSoFar <= ptile75) && (totalSoFar > ptile50)) || ((lastValue < ptile75) && (totalSoFar > ptile75))) { homops[4] = value; } //save value
if (((totalSoFar <= ptile97_5) && (totalSoFar > ptile75)) || ((lastValue < ptile97_5) && (totalSoFar > ptile97_5))) { homops[5] = value; } //save value
if ((totalSoFar <= ptile100) && (totalSoFar > ptile97_5)) { homops[6] = value; } //save value
lastValue = totalSoFar;
}
homops[6] = (longHomoPolymer.rbegin())->first;
double meanstartPosition, meanendPosition, meanseqLength, meanambigBases, meanlongHomoPolymer;
meanstartPosition = meanStartPosition / (double) size; meanendPosition = meanEndPosition /(double) size; meanlongHomoPolymer = meanLongHomoPolymer / (double) size; meanseqLength = meanSeqLength / (double) size; meanambigBases = meanAmbigBases /(double) size;
if (m->control_pressed) { m->mothurRemove(summaryFile); return 0; }
m->mothurOutEndLine();
m->mothurOut("\t\tStart\tEnd\tNBases\tAmbigs\tPolymer\tNumSeqs"); m->mothurOutEndLine();
m->mothurOut("Minimum:\t" + toString(starts[0]) + "\t" + toString(ends[0]) + "\t" + toString(lengths[0]) + "\t" + toString(ambigs[0]) + "\t" + toString(homops[0]) + "\t" + toString(1)); m->mothurOutEndLine();
m->mothurOut("2.5%-tile:\t" + toString(starts[1]) + "\t" + toString(ends[1]) + "\t" + toString(lengths[1]) + "\t" + toString(ambigs[1]) + "\t" + toString(homops[1]) + "\t" + toString(ptile0_25)); m->mothurOutEndLine();
m->mothurOut("25%-tile:\t" + toString(starts[2]) + "\t" + toString(ends[2]) + "\t" + toString(lengths[2]) + "\t" + toString(ambigs[2]) + "\t" + toString(homops[2]) + "\t" + toString(ptile25)); m->mothurOutEndLine();
m->mothurOut("Median: \t" + toString(starts[3]) + "\t" + toString(ends[3]) + "\t" + toString(lengths[3]) + "\t" + toString(ambigs[3]) + "\t" + toString(homops[3]) + "\t" + toString(ptile50)); m->mothurOutEndLine();
m->mothurOut("75%-tile:\t" + toString(starts[4]) + "\t" + toString(ends[4]) + "\t" + toString(lengths[4]) + "\t" + toString(ambigs[4]) + "\t" + toString(homops[4]) + "\t" + toString(ptile75)); m->mothurOutEndLine();
m->mothurOut("97.5%-tile:\t" + toString(starts[5]) + "\t" + toString(ends[5]) + "\t" + toString(lengths[5]) + "\t" + toString(ambigs[5]) + "\t" + toString(homops[5]) + "\t" + toString(ptile97_5)); m->mothurOutEndLine();
m->mothurOut("Maximum:\t" + toString(starts[6]) + "\t" + toString(ends[6]) + "\t" + toString(lengths[6]) + "\t" + toString(ambigs[6]) + "\t" + toString(homops[6]) + "\t" + toString(ptile100)); m->mothurOutEndLine();
m->mothurOut("Mean:\t" + toString(meanstartPosition) + "\t" + toString(meanendPosition) + "\t" + toString(meanseqLength) + "\t" + toString(meanambigBases) + "\t" + toString(meanlongHomoPolymer)); m->mothurOutEndLine();
if ((namefile == "") && (countfile == "")) { m->mothurOut("# of Seqs:\t" + toString(numSeqs)); m->mothurOutEndLine(); }
else { m->mothurOut("# of unique seqs:\t" + toString(numSeqs)); m->mothurOutEndLine(); m->mothurOut("total # of seqs:\t" + toString(size)); m->mothurOutEndLine(); }
if (m->control_pressed) { m->mothurRemove(summaryFile); return 0; }
m->mothurOutEndLine();
m->mothurOut("Output File Names: "); m->mothurOutEndLine();
m->mothurOut(summaryFile); m->mothurOutEndLine(); outputNames.push_back(summaryFile); outputTypes["summary"].push_back(summaryFile);
m->mothurOutEndLine();
if ((namefile == "") && (countfile == "")) { m->mothurOut("It took " + toString(time(NULL) - start) + " secs to summarize " + toString(numSeqs) + " sequences.\n"); }
else{ m->mothurOut("It took " + toString(time(NULL) - start) + " secs to summarize " + toString(size) + " sequences.\n"); }
//set fasta file as new current fastafile
string current = "";
itTypes = outputTypes.find("summary");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setSummaryFile(current); }
}
return 0;
}
catch(exception& e) {
m->errorOut(e, "SeqSummaryCommand", "execute");
exit(1);
}
}
//**********************************************************************************************************************
int RemoveRareCommand::processList(){
try {
//you must provide a label because the names in the listfile need to be consistent
string thisLabel = "";
if (allLines) { m->mothurOut("For the listfile you must select one label, using first label in your listfile."); m->mothurOutEndLine(); }
else if (labels.size() > 1) { m->mothurOut("For the listfile you must select one label, using " + (*labels.begin()) + "."); m->mothurOutEndLine(); thisLabel = *labels.begin(); }
else { thisLabel = *labels.begin(); }
InputData input(listfile, "list");
ListVector* list = input.getListVector();
//get first one or the one we want
if (thisLabel != "") {
//use smart distancing
set<string> userLabels; userLabels.insert(thisLabel);
set<string> processedLabels;
string lastLabel = list->getLabel();
while((list != NULL) && (userLabels.size() != 0)) {
if(userLabels.count(list->getLabel()) == 1){
processedLabels.insert(list->getLabel());
userLabels.erase(list->getLabel());
break;
}
if ((m->anyLabelsToProcess(list->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) {
processedLabels.insert(list->getLabel());
userLabels.erase(list->getLabel());
delete list;
list = input.getListVector(lastLabel);
break;
}
lastLabel = list->getLabel();
delete list;
list = input.getListVector();
}
if (userLabels.size() != 0) {
m->mothurOut("Your file does not include the label " + thisLabel + ". I will use " + lastLabel + "."); m->mothurOutEndLine();
list = input.getListVector(lastLabel);
}
}
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += m->hasPath(listfile); }
map<string, string> variables;
variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(listfile));
variables["[extension]"] = m->getExtension(listfile);
variables["[tag]"] = list->getLabel();
string outputFileName = getOutputFileName("list", variables);
variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(groupfile));
variables["[extension]"] = m->getExtension(groupfile);
string outputGroupFileName = getOutputFileName("group", variables);
variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(countfile));
variables["[extension]"] = m->getExtension(countfile);
string outputCountFileName = getOutputFileName("count", variables);
ofstream out, outGroup;
m->openOutputFile(outputFileName, out);
bool wroteSomething = false;
//if groupfile is given then use it
GroupMap* groupMap;
CountTable ct;
if (groupfile != "") {
groupMap = new GroupMap(groupfile); groupMap->readMap();
SharedUtil util;
vector<string> namesGroups = groupMap->getNamesOfGroups();
util.setGroups(Groups, namesGroups);
m->openOutputFile(outputGroupFileName, outGroup);
}else if (countfile != "") {
ct.readTable(countfile, true, false);
if (ct.hasGroupInfo()) {
vector<string> namesGroups = ct.getNamesOfGroups();
SharedUtil util;
util.setGroups(Groups, namesGroups);
}
}
if (list != NULL) {
vector<string> binLabels = list->getLabels();
vector<string> newLabels;
//make a new list vector
ListVector newList;
newList.setLabel(list->getLabel());
//for each bin
for (int i = 0; i < list->getNumBins(); i++) {
if (m->control_pressed) { if (groupfile != "") { delete groupMap; outGroup.close(); m->mothurRemove(outputGroupFileName); } out.close(); m->mothurRemove(outputFileName); return 0; }
//parse out names that are in accnos file
string binnames = list->get(i);
vector<string> names;
string saveBinNames = binnames;
m->splitAtComma(binnames, names);
int binsize = names.size();
vector<string> newGroupFile;
if (groupfile != "") {
vector<string> newNames;
saveBinNames = "";
for(int k = 0; k < names.size(); k++) {
string group = groupMap->getGroup(names[k]);
if (m->inUsersGroups(group, Groups)) {
newGroupFile.push_back(names[k] + "\t" + group);
newNames.push_back(names[k]);
saveBinNames += names[k] + ",";
}
}
names = newNames; binsize = names.size();
saveBinNames = saveBinNames.substr(0, saveBinNames.length()-1);
}else if (countfile != "") {
saveBinNames = "";
binsize = 0;
for(int k = 0; k < names.size(); k++) {
if (ct.hasGroupInfo()) {
vector<string> thisSeqsGroups = ct.getGroups(names[k]);
int thisSeqsCount = 0;
for (int n = 0; n < thisSeqsGroups.size(); n++) {
if (m->inUsersGroups(thisSeqsGroups[n], Groups)) {
thisSeqsCount += ct.getGroupCount(names[k], thisSeqsGroups[n]);
}
}
binsize += thisSeqsCount;
//if you don't have any seqs from the groups the user wants, then remove you.
if (thisSeqsCount == 0) { newGroupFile.push_back(names[k]); }
else { saveBinNames += names[k] + ","; }
}else {
binsize += ct.getNumSeqs(names[k]);
saveBinNames += names[k] + ",";
}
}
saveBinNames = saveBinNames.substr(0, saveBinNames.length()-1);
}
if (binsize > nseqs) { //keep bin
newList.push_back(saveBinNames);
newLabels.push_back(binLabels[i]);
if (groupfile != "") { for(int k = 0; k < newGroupFile.size(); k++) { outGroup << newGroupFile[k] << endl; } }
else if (countfile != "") { for(int k = 0; k < newGroupFile.size(); k++) { ct.remove(newGroupFile[k]); } }
}else { if (countfile != "") { for(int k = 0; k < names.size(); k++) { ct.remove(names[k]); } } }
}
//print new listvector
if (newList.getNumBins() != 0) {
wroteSomething = true;
newList.setLabels(newLabels);
newList.printHeaders(out);
newList.print(out);
}
}
out.close();
if (groupfile != "") { outGroup.close(); outputTypes["group"].push_back(outputGroupFileName); outputNames.push_back(outputGroupFileName); }
if (countfile != "") {
if (ct.hasGroupInfo()) {
vector<string> allGroups = ct.getNamesOfGroups();
for (int i = 0; i < allGroups.size(); i++) {
if (!m->inUsersGroups(allGroups[i], Groups)) { ct.removeGroup(allGroups[i]); }
}
}
ct.printTable(outputCountFileName);
outputTypes["count"].push_back(outputCountFileName); outputNames.push_back(outputCountFileName);
}
if (wroteSomething == false) { m->mothurOut("Your file contains only rare sequences."); m->mothurOutEndLine(); }
outputTypes["list"].push_back(outputFileName); outputNames.push_back(outputFileName);
return 0;
}
catch(exception& e) {
m->errorOut(e, "RemoveRareCommand", "processList");
exit(1);
}
}
