5 * Created by Sarah Westcott on 1/2/09.
6 * Copyright 2009 Schloss Lab UMASS Amherst. All rights reserved.
10 #include "sharedcommand.h"
12 //**********************************************************************************************************************
14 SharedCommand::SharedCommand(){
16 globaldata = GlobalData::getInstance();
18 //getting output filename
19 filename = globaldata->inputFileName;
20 filename = getRootName(filename);
21 filename = filename + "shared";
22 openOutputFile(filename, out);
24 groupMap = globaldata->gGroupmap;
26 //fill filehandles with neccessary ofstreams
29 for (i=0; i<groupMap->getNumGroups(); i++) {
31 filehandles[groupMap->namesOfGroups[i]] = temp;
35 fileroot = getRootName(globaldata->getListFile());
37 //clears file before we start to write to it below
38 for (int i=0; i<groupMap->getNumGroups(); i++) {
39 remove((fileroot + groupMap->namesOfGroups[i] + ".rabund").c_str());
44 errorOut(e, "SharedCommand", "SharedCommand");
48 //**********************************************************************************************************************
50 int SharedCommand::execute(){
54 string errorOff = "no error";
57 read = new ReadOTUFile(globaldata->inputFileName);
58 read->read(&*globaldata);
61 input = globaldata->ginput;
62 SharedList = globaldata->gSharedList;
63 string lastLabel = SharedList->getLabel();
64 vector<SharedRAbundVector*> lookup;
66 if (SharedList->getNumSeqs() != groupMap->getNumSeqs()) {
67 mothurOut("Your group file contains " + toString(groupMap->getNumSeqs()) + " sequences and list file contains " + toString(SharedList->getNumSeqs()) + " sequences. Please correct."); mothurOutEndLine();
70 remove(filename.c_str()); //remove blank shared file you made
75 for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) {
79 globaldata->gSharedList = NULL;
84 //if the users enters label "0.06" and there is no "0.06" in their file use the next lowest label.
85 set<string> processedLabels;
86 set<string> userLabels = globaldata->labels;
89 while((SharedList != NULL) && ((globaldata->allLines == 1) || (userLabels.size() != 0))) {
92 if(globaldata->allLines == 1 || globaldata->labels.count(SharedList->getLabel()) == 1){
94 lookup = SharedList->getSharedRAbundVector();
95 mothurOut(lookup[0]->getLabel()); mothurOutEndLine();
97 printSharedData(lookup); //prints info to the .shared file
98 for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; }
100 processedLabels.insert(SharedList->getLabel());
101 userLabels.erase(SharedList->getLabel());
104 if ((anyLabelsToProcess(SharedList->getLabel(), userLabels, errorOff) == true) && (processedLabels.count(lastLabel) != 1)) {
106 SharedList = input->getSharedListVector(lastLabel); //get new list vector to process
108 lookup = SharedList->getSharedRAbundVector();
109 mothurOut(lookup[0]->getLabel()); mothurOutEndLine();
111 printSharedData(lookup); //prints info to the .shared file
112 for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; }
114 processedLabels.insert(SharedList->getLabel());
115 userLabels.erase(SharedList->getLabel());
119 lastLabel = SharedList->getLabel();
122 SharedList = input->getSharedListVector(); //get new list vector to process
125 //output error messages about any remaining user labels
126 set<string>::iterator it;
127 bool needToRun = false;
128 for (it = userLabels.begin(); it != userLabels.end(); it++) {
129 if (processedLabels.count(lastLabel) != 1) {
134 //run last label if you need to
135 if (needToRun == true) {
136 if (SharedList != NULL) { delete SharedList; }
137 SharedList = input->getSharedListVector(lastLabel); //get new list vector to process
139 lookup = SharedList->getSharedRAbundVector();
140 mothurOut(lookup[0]->getLabel()); mothurOutEndLine();
142 printSharedData(lookup); //prints info to the .shared file
143 for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; }
147 globaldata->gSharedList = NULL;
151 for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) {
158 catch(exception& e) {
159 errorOut(e, "SharedCommand", "execute");
163 //**********************************************************************************************************************
164 void SharedCommand::printSharedData(vector<SharedRAbundVector*> thislookup) {
167 //initialize bin values
168 for (int i = 0; i < thislookup.size(); i++) {
169 out << thislookup[i]->getLabel() << '\t' << thislookup[i]->getGroup() << '\t';
170 thislookup[i]->print(out);
172 RAbundVector rav = thislookup[i]->getRAbundVector();
173 openOutputFileAppend(fileroot + thislookup[i]->getGroup() + ".rabund", *(filehandles[thislookup[i]->getGroup()]));
174 rav.print(*(filehandles[thislookup[i]->getGroup()]));
175 (*(filehandles[thislookup[i]->getGroup()])).close();
179 catch(exception& e) {
180 errorOut(e, "SharedCommand", "printSharedData");
184 //**********************************************************************************************************************
185 void SharedCommand::createMisMatchFile() {
187 ofstream outMisMatch;
188 string outputMisMatchName = getRootName(globaldata->inputFileName);
190 //you have sequences in your list file that are not in your group file
191 if (SharedList->getNumSeqs() > groupMap->getNumSeqs()) {
192 outputMisMatchName += "missing.group";
193 mothurOut("For a list of names that are in your list file and not in your group file, please refer to " + outputMisMatchName + "."); mothurOutEndLine();
195 openOutputFile(outputMisMatchName, outMisMatch);
197 //go through list and if group returns "not found" output it
198 for (int i = 0; i < SharedList->getNumBins(); i++) {
200 string names = SharedList->get(i);
202 while (names.find_first_of(',') != -1) {
203 string name = names.substr(0,names.find_first_of(','));
204 names = names.substr(names.find_first_of(',')+1, names.length());
205 string group = groupMap->getGroup(name);
207 if(group == "not found") { outMisMatch << name << endl; }
211 string group = groupMap->getGroup(names);
212 if(group == "not found") { outMisMatch << names << endl; }
218 }else {//you have sequences in your group file that are not in you list file
220 outputMisMatchName += "missing.name";
221 mothurOut("For a list of names that are in your group file and not in your list file, please refer to " + outputMisMatchName + "."); mothurOutEndLine();
223 map<string, string> namesInList;
225 //go through listfile and get names
226 for (int i = 0; i < SharedList->getNumSeqs(); i++) {
228 string names = SharedList->get(i);
230 while (names.find_first_of(',') != -1) {
231 string name = names.substr(0,names.find_first_of(','));
232 names = names.substr(names.find_first_of(',')+1, names.length());
234 namesInList[name] = name;
238 namesInList[names] = names;
241 //get names of sequences in groupfile
242 vector<string> seqNames = groupMap->getNamesSeqs();
244 map<string, string>::iterator itMatch;
246 openOutputFile(outputMisMatchName, outMisMatch);
248 //loop through names in seqNames and if they aren't in namesIn list output them
249 for (int i = 0; i < seqNames.size(); i++) {
251 itMatch = namesInList.find(seqNames[i]);
253 if (itMatch == namesInList.end()) {
255 outMisMatch << seqNames[i] << endl;
262 catch(exception& e) {
263 errorOut(e, "SharedCommand", "createMisMatchFile");
268 //**********************************************************************************************************************
270 SharedCommand::~SharedCommand(){
276 //**********************************************************************************************************************