//**********************************************************************************************************************
-SharedCommand::SharedCommand(){
+SharedCommand::SharedCommand(string o) : outputDir(o) {
try {
globaldata = GlobalData::getInstance();
//getting output filename
filename = globaldata->inputFileName;
- filename = getRootName(filename);
+ if (outputDir == "") { outputDir += hasPath(filename); }
+
+ filename = outputDir + getRootName(getSimpleName(filename));
filename = filename + "shared";
+
openOutputFile(filename, out);
+ pickedGroups = false;
groupMap = globaldata->gGroupmap;
+ //if hte user has not specified any groups then use them all
+ if (globaldata->Groups.size() == 0) {
+ groups = groupMap->namesOfGroups;
+ }else{ //they have specified groups
+ groups = globaldata->Groups;
+ pickedGroups = true;
+ }
+
//fill filehandles with neccessary ofstreams
int i;
ofstream* temp;
- for (i=0; i<groupMap->getNumGroups(); i++) {
+ for (i=0; i<groups.size(); i++) {
temp = new ofstream;
- filehandles[groupMap->namesOfGroups[i]] = temp;
+ filehandles[groups[i]] = temp;
}
//set fileroot
- fileroot = getRootName(globaldata->getListFile());
+ fileroot = outputDir + getRootName(getSimpleName(globaldata->getListFile()));
//clears file before we start to write to it below
- for (int i=0; i<groupMap->getNumGroups(); i++) {
- remove((fileroot + groupMap->namesOfGroups[i] + ".rabund").c_str());
+ for (int i=0; i<groups.size(); i++) {
+ remove((fileroot + groups[i] + ".rabund").c_str());
+ outputNames.push_back((fileroot + groups[i] + ".rabund"));
}
}
catch(exception& e) {
- errorOut(e, "SharedCommand", "SharedCommand");
+ m->errorOut(e, "SharedCommand", "SharedCommand");
exit(1);
}
}
//lookup.clear();
string errorOff = "no error";
-
+ //errorOff = "";
+
//read in listfile
read = new ReadOTUFile(globaldata->inputFileName);
read->read(&*globaldata);
string lastLabel = SharedList->getLabel();
vector<SharedRAbundVector*> lookup;
- if (SharedList->getNumSeqs() != groupMap->getNumSeqs()) {
- mothurOut("Your group file contains " + toString(groupMap->getNumSeqs()) + " sequences and list file contains " + toString(SharedList->getNumSeqs()) + " sequences. Please correct."); mothurOutEndLine();
+ if (m->control_pressed) {
+ delete input; delete SharedList; globaldata->ginput = NULL; globaldata->gSharedList = NULL;
+ for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { delete it3->second; }
+ out.close(); remove(filename.c_str());
+ for (int i=0; i<groups.size(); i++) { remove((fileroot + groups[i] + ".rabund").c_str()); }
+ return 1;
+ }
+
+ if ((globaldata->Groups.size() == 0) && (SharedList->getNumSeqs() != groupMap->getNumSeqs())) { //if the user has not specified any groups and their files don't match exit with error
+ m->mothurOut("Your group file contains " + toString(groupMap->getNumSeqs()) + " sequences and list file contains " + toString(SharedList->getNumSeqs()) + " sequences. Please correct."); m->mothurOutEndLine();
+
+ out.close();
+ remove(filename.c_str()); //remove blank shared file you made
createMisMatchFile();
for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) {
delete it3->second;
}
+ delete input;
+ globaldata->ginput = NULL;
delete SharedList;
globaldata->gSharedList = NULL;
return 1;
}
- //if the users enters label "0.06" and there is no "0.06" in their file use the next lowest label.
- set<string> processedLabels;
- set<string> userLabels = globaldata->labels;
+ //if user has specified groups make new groupfile for them
+ if (globaldata->Groups.size() != 0) { //make new group file
+ string groups = "";
+ for (int i = 0; i < globaldata->Groups.size(); i++) {
+ groups += globaldata->Groups[i] + ".";
+ }
+
+ string newGroupFile = outputDir + getRootName(getSimpleName(globaldata->inputFileName)) + groups + "groups";
+ ofstream outGroups;
+ openOutputFile(newGroupFile, outGroups);
+ vector<string> names = groupMap->getNamesSeqs();
+ string groupName;
+ for (int i = 0; i < names.size(); i++) {
+ groupName = groupMap->getGroup(names[i]);
+ if (isValidGroup(groupName, globaldata->Groups)) {
+ outGroups << names[i] << '\t' << groupName << endl;
+ }
+ }
+ outGroups.close();
+ }
+ //if the users enters label "0.06" and there is no "0.06" in their file use the next lowest label.
+ set<string> processedLabels;
+ set<string> userLabels = globaldata->labels;
+
while((SharedList != NULL) && ((globaldata->allLines == 1) || (userLabels.size() != 0))) {
-
-
+ if (m->control_pressed) {
+ delete input; delete SharedList; globaldata->ginput = NULL; globaldata->gSharedList = NULL;
+ for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { delete it3->second; }
+ out.close(); remove(filename.c_str());
+ for (int i=0; i<groups.size(); i++) { remove((fileroot + groups[i] + ".rabund").c_str()); }
+ return 1;
+ }
+
if(globaldata->allLines == 1 || globaldata->labels.count(SharedList->getLabel()) == 1){
lookup = SharedList->getSharedRAbundVector();
- mothurOut(lookup[0]->getLabel()); mothurOutEndLine();
+ m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine();
+ if (pickedGroups) { //check for otus with no seqs in them
+ eliminateZeroOTUS(lookup);
+ }
+
+ if (m->control_pressed) {
+ delete input; delete SharedList; globaldata->ginput = NULL; globaldata->gSharedList = NULL;
+ for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; }
+ for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { delete it3->second; }
+ out.close(); remove(filename.c_str());
+ for (int i=0; i<groups.size(); i++) { remove((fileroot + groups[i] + ".rabund").c_str()); }
+ return 1;
+ }
printSharedData(lookup); //prints info to the .shared file
for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; }
}
if ((anyLabelsToProcess(SharedList->getLabel(), userLabels, errorOff) == true) && (processedLabels.count(lastLabel) != 1)) {
+ string saveLabel = SharedList->getLabel();
+
delete SharedList;
SharedList = input->getSharedListVector(lastLabel); //get new list vector to process
lookup = SharedList->getSharedRAbundVector();
- mothurOut(lookup[0]->getLabel()); mothurOutEndLine();
+ m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine();
+ if (pickedGroups) { //check for otus with no seqs in them
+ eliminateZeroOTUS(lookup);
+ }
+
+
+ if (m->control_pressed) {
+ delete input; delete SharedList; globaldata->ginput = NULL; globaldata->gSharedList = NULL;
+ for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; }
+ for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { delete it3->second; }
+ out.close(); remove(filename.c_str());
+ for (int i=0; i<groups.size(); i++) { remove((fileroot + groups[i] + ".rabund").c_str()); }
+ return 1;
+ }
printSharedData(lookup); //prints info to the .shared file
for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; }
processedLabels.insert(SharedList->getLabel());
userLabels.erase(SharedList->getLabel());
+
+ //restore real lastlabel to save below
+ SharedList->setLabel(saveLabel);
}
SharedList = input->getSharedListVector(lastLabel); //get new list vector to process
lookup = SharedList->getSharedRAbundVector();
- mothurOut(lookup[0]->getLabel()); mothurOutEndLine();
+ m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine();
+ if (pickedGroups) { //check for otus with no seqs in them
+ eliminateZeroOTUS(lookup);
+ }
+
+ if (m->control_pressed) {
+ delete input; globaldata->ginput = NULL;
+ for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { delete it3->second; }
+ out.close(); remove(filename.c_str());
+ for (int i=0; i<groups.size(); i++) { remove((fileroot + groups[i] + ".rabund").c_str()); }
+ return 1;
+ }
printSharedData(lookup); //prints info to the .shared file
for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; }
}
+ //change format to shared to speed up commands
+ globaldata->setFormat("sharedfile");
+ globaldata->setListFile("");
+ globaldata->setGroupFile("");
+ globaldata->setSharedFile(filename);
+
+ if (m->control_pressed) {
+ delete input; globaldata->ginput = NULL;
+ remove(filename.c_str());
+ for (int i=0; i<groups.size(); i++) { remove((fileroot + groups[i] + ".rabund").c_str()); }
+ return 1;
+ }
+
+ m->mothurOutEndLine();
+ m->mothurOut("Output File Names: "); m->mothurOutEndLine();
+ for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
+ m->mothurOut(filename); m->mothurOutEndLine();
+ m->mothurOutEndLine();
+
return 0;
}
catch(exception& e) {
- errorOut(e, "SharedCommand", "execute");
+ m->errorOut(e, "SharedCommand", "execute");
exit(1);
}
}
//initialize bin values
for (int i = 0; i < thislookup.size(); i++) {
+//cout << "in printData " << thislookup[i]->getLabel() << '\t' << thislookup[i]->getGroup() << endl;
out << thislookup[i]->getLabel() << '\t' << thislookup[i]->getGroup() << '\t';
thislookup[i]->print(out);
}
catch(exception& e) {
- errorOut(e, "SharedCommand", "printSharedData");
+ m->errorOut(e, "SharedCommand", "printSharedData");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+int SharedCommand::eliminateZeroOTUS(vector<SharedRAbundVector*>& thislookup) {
+ try {
+
+ vector<SharedRAbundVector*> newLookup;
+ for (int i = 0; i < thislookup.size(); i++) {
+ SharedRAbundVector* temp = new SharedRAbundVector();
+ temp->setLabel(thislookup[i]->getLabel());
+ temp->setGroup(thislookup[i]->getGroup());
+ newLookup.push_back(temp);
+ }
+
+ //for each bin
+ for (int i = 0; i < thislookup[0]->getNumBins(); i++) {
+ if (m->control_pressed) { for (int j = 0; j < newLookup.size(); j++) { delete newLookup[j]; } return 0; }
+
+ //look at each sharedRabund and make sure they are not all zero
+ bool allZero = true;
+ for (int j = 0; j < thislookup.size(); j++) {
+ if (thislookup[j]->getAbundance(i) != 0) { allZero = false; break; }
+ }
+
+ //if they are not all zero add this bin
+ if (!allZero) {
+ for (int j = 0; j < thislookup.size(); j++) {
+ newLookup[j]->push_back(thislookup[j]->getAbundance(i), thislookup[j]->getGroup());
+ }
+ }
+ //else{ cout << "bin # " << i << " is all zeros" << endl; }
+ }
+
+ for (int j = 0; j < thislookup.size(); j++) { delete thislookup[j]; }
+ thislookup = newLookup;
+
+ return 0;
+
+ }
+ catch(exception& e) {
+ m->errorOut(e, "SharedCommand", "eliminateZeroOTUS");
exit(1);
}
}
//**********************************************************************************************************************
-void SharedCommand::createMisMatchFile() {
+int SharedCommand::createMisMatchFile() {
try {
ofstream outMisMatch;
- string outputMisMatchName = getRootName(globaldata->inputFileName);
+ string outputMisMatchName = outputDir + getRootName(getSimpleName(globaldata->inputFileName));
//you have sequences in your list file that are not in your group file
if (SharedList->getNumSeqs() > groupMap->getNumSeqs()) {
outputMisMatchName += "missing.group";
- mothurOut("For a list of names that are in your list file and not in your group file, please refer to " + outputMisMatchName + "."); mothurOutEndLine();
+ m->mothurOut("For a list of names that are in your list file and not in your group file, please refer to " + outputMisMatchName + "."); m->mothurOutEndLine();
openOutputFile(outputMisMatchName, outMisMatch);
+ map<string, string> listNames;
+ map<string, string>::iterator itList;
+
//go through list and if group returns "not found" output it
for (int i = 0; i < SharedList->getNumBins(); i++) {
+ if (m->control_pressed) { outMisMatch.close(); remove(outputMisMatchName.c_str()); return 0; }
string names = SharedList->get(i);
string group = groupMap->getGroup(name);
if(group == "not found") { outMisMatch << name << endl; }
+
+ itList = listNames.find(name);
+ if (itList != listNames.end()) { m->mothurOut(name + " is in your list file more than once. Sequence names must be unique. please correct."); m->mothurOutEndLine(); }
+ else { listNames[name] = name; }
}
-
+
//get last name
string group = groupMap->getGroup(names);
- if(group == "not found") { outMisMatch << names << endl; }
+ if(group == "not found") { outMisMatch << names << endl; }
+
+ itList = listNames.find(names);
+ if (itList != listNames.end()) { m->mothurOut(names + " is in your list file more than once. Sequence names must be unique. please correct."); m->mothurOutEndLine(); }
+ else { listNames[names] = names; }
+
}
outMisMatch.close();
}else {//you have sequences in your group file that are not in you list file
outputMisMatchName += "missing.name";
- mothurOut("For a list of names that are in your group file and not in your list file, please refer to " + outputMisMatchName + "."); mothurOutEndLine();
+ m->mothurOut("For a list of names that are in your group file and not in your list file, please refer to " + outputMisMatchName + "."); m->mothurOutEndLine();
map<string, string> namesInList;
+ map<string, string>::iterator itList;
//go through listfile and get names
- for (int i = 0; i < SharedList->getNumSeqs(); i++) {
+ for (int i = 0; i < SharedList->getNumBins(); i++) {
+ if (m->control_pressed) { return 0; }
+
string names = SharedList->get(i);
-
+
while (names.find_first_of(',') != -1) {
string name = names.substr(0,names.find_first_of(','));
names = names.substr(names.find_first_of(',')+1, names.length());
+ itList = namesInList.find(name);
+ if (itList != namesInList.end()) { m->mothurOut(name + " is in your list file more than once. Sequence names must be unique. please correct."); m->mothurOutEndLine(); }
+
namesInList[name] = name;
+
}
+ itList = namesInList.find(names);
+ if (itList != namesInList.end()) { m->mothurOut(names + " is in your list file more than once. Sequence names must be unique. please correct."); m->mothurOutEndLine(); }
+
//get last name
namesInList[names] = names;
}
//loop through names in seqNames and if they aren't in namesIn list output them
for (int i = 0; i < seqNames.size(); i++) {
+ if (m->control_pressed) { outMisMatch.close(); remove(outputMisMatchName.c_str()); return 0; }
itMatch = namesInList.find(seqNames[i]);
}
outMisMatch.close();
}
-
+
+ return 0;
}
catch(exception& e) {
- errorOut(e, "SharedCommand", "createMisMatchFile");
+ m->errorOut(e, "SharedCommand", "createMisMatchFile");
exit(1);
}
}
}
//**********************************************************************************************************************
+
+bool SharedCommand::isValidGroup(string groupname, vector<string> groups) {
+ try {
+ for (int i = 0; i < groups.size(); i++) {
+ if (groupname == groups[i]) { return true; }
+ }
+
+ return false;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "SharedCommand", "isValidGroup");
+ exit(1);
+ }
+}
+/************************************************************/
+
+