]> git.donarmstrong.com Git - mothur.git/blobdiff - mothurout.cpp
added dereplicate parameter to chimera.slayer and chimera.persues. added minnumsample...
[mothur.git] / mothurout.cpp
index 1a3bf79f50dad4e0a66e9910bb4abfe8c2cff944..468c063cb5c7e74a8d5901a1a38203f47409e2d5 100644 (file)
@@ -939,7 +939,7 @@ string MothurOut::getFullPathName(string fileName){
                                }
                        
                                for (int i = index; i >= 0; i--) {
-                                       newFileName = dirs[i] +  "\\" + newFileName;            
+                                       newFileName = dirs[i] +  "\\\\" + newFileName;          
                                }
                                
                                return newFileName;
@@ -1183,7 +1183,7 @@ string MothurOut::sortFile(string distFile, string outputDir){
 
                        string firstName, secondName;
                        float dist;
-                       while (input) {
+                       while (!input.eof()) {
                                input >> firstName >> secondName >> dist;
                                output << dist << '\t' << firstName << '\t' << secondName << endl;
                                gobble(input);
@@ -1199,16 +1199,17 @@ string MothurOut::sortFile(string distFile, string outputDir){
                
                        //read in sorted file and put distance at end again
                        ifstream input2;
+            ofstream output2;
                        openInputFile(tempOutfile, input2);
-                       openOutputFile(outfile, output);
+                       openOutputFile(outfile, output2);
                
-                       while (input2) {
+            while (!input2.eof()) {
                                input2 >> dist >> firstName >> secondName;
-                               output << firstName << '\t' << secondName << '\t' << dist << endl;
+                               output2 << firstName << '\t' << secondName << '\t' << dist << endl;
                                gobble(input2);
                        }
                        input2.close();
-                       output.close();
+                       output2.close();
                
                        //remove temp files
                        mothurRemove(tempDistFile);
@@ -1541,6 +1542,46 @@ vector<string> MothurOut::splitWhiteSpace(string input){
                exit(1);
        }
 }
+/***********************************************************************/
+vector<string> MothurOut::splitWhiteSpaceWithQuotes(string input){
+       try {
+        vector<string> pieces;
+        string rest = "";
+        
+        int pos = input.find('\'');
+        int pos2 = input.find('\"');
+        
+        if ((pos == string::npos) && (pos2 == string::npos)) { return splitWhiteSpace(input); } //no quotes to worry about
+        else {
+            for (int i = 0; i < input.length(); i++) {
+                if ((input[i] == '\'') || (input[i] == '\"') || (rest == "\'") || (rest == "\"")) { //grab everything til end or next ' or "
+                    rest += input[i];
+                    for (int j = i+1; j < input.length(); j++) {
+                        if ((input[j] == '\'') || (input[j] == '\"')) {  //then quit
+                            rest += input[j];
+                            i = j+1;
+                            j+=input.length();
+                        }else { rest += input[j]; }
+                    }
+                }else if (!isspace(input[i]))  { rest += input[i];  }
+                else {
+                    if (rest != "") { pieces.push_back(rest);  rest = ""; }
+                    while (i < input.length()) {  //gobble white space
+                        if (isspace(input[i])) { i++; }
+                        else { rest = input[i];  break; } //cout << "next piece buffer = " << nextPiece << endl;
+                    } 
+                }
+            }
+            
+            if (rest != "") { pieces.push_back(rest); }
+        }
+        return pieces;
+       }
+       catch(exception& e) {
+               errorOut(e, "MothurOut", "splitWhiteSpace");
+               exit(1);
+       }
+}
 //**********************************************************************************************************************
 int MothurOut::readTax(string namefile, map<string, string>& taxMap) {
        try {
@@ -1567,8 +1608,17 @@ int MothurOut::readTax(string namefile, map<string, string>& taxMap) {
                 if (pairDone) { 
                     //are there confidence scores, if so remove them
                     if (secondCol.find_first_of('(') != -1) {  removeConfidences(secondCol);   }
-                    taxMap[firstCol] = secondCol;
-                    if (debug) {  mothurOut("[DEBUG]: name = '" + firstCol + "' tax = '" + secondCol + "'\n");  }
+                    map<string, string>::iterator itTax = taxMap.find(firstCol);
+                    
+                    if(itTax == taxMap.end()) {
+                        bool ignore = false;
+                        if (secondCol != "") { if (secondCol[secondCol.length()-1] != ';') { mothurOut("[ERROR]: " + firstCol + " is missing the final ';', ignoring.\n"); ignore=true; }
+                        }
+                        if (!ignore) { taxMap[firstCol] = secondCol; }
+                        if (debug) {  mothurOut("[DEBUG]: name = '" + firstCol + "' tax = '" + secondCol + "'\n");  }
+                    }else {
+                        mothurOut("[ERROR]: " + firstCol + " is already in your taxonomy file, names must be unique./n"); control_pressed = true;
+                    }
                     pairDone = false; 
                 }
             }
@@ -1585,8 +1635,18 @@ int MothurOut::readTax(string namefile, map<string, string>& taxMap) {
                 if (pairDone) { 
                     //are there confidence scores, if so remove them
                     if (secondCol.find_first_of('(') != -1) {  removeConfidences(secondCol);   }
-                    taxMap[firstCol] = secondCol;
-                    if (debug) {  mothurOut("[DEBUG]: name = '" + firstCol + "' tax = '" + secondCol + "'\n");  }
+                    map<string, string>::iterator itTax = taxMap.find(firstCol);
+                    
+                    if(itTax == taxMap.end()) {
+                        bool ignore = false;
+                        if (secondCol != "") { if (secondCol[secondCol.length()-1] != ';') { mothurOut("[ERROR]: " + firstCol + " is missing the final ';', ignoring.\n"); ignore=true; }
+                        }
+                        if (!ignore) { taxMap[firstCol] = secondCol; }
+                        if (debug) {  mothurOut("[DEBUG]: name = '" + firstCol + "' tax = '" + secondCol + "'\n");  }
+                    }else {
+                        mothurOut("[ERROR]: " + firstCol + " is already in your taxonomy file, names must be unique./n"); control_pressed = true;
+                    }
+
                     pairDone = false; 
                 }
             } 
@@ -2114,6 +2174,32 @@ int MothurOut::getNumChar(string line, char c){
                exit(1);
        }
 }
+//**********************************************************************************************************************
+bool MothurOut::isSubset(vector<string> bigset, vector<string> subset) {
+       try {
+               
+        
+               if (subset.size() > bigset.size()) { return false;  }
+               
+               //check if each guy in suset is also in bigset
+               for (int i = 0; i < subset.size(); i++) {
+                       bool match = false;
+                       for (int j = 0; j < bigset.size(); j++) {
+                               if (subset[i] == bigset[j]) { match = true; break; }
+                       }
+                       
+                       //you have a guy in subset that had no match in bigset
+                       if (match == false) { return false; }
+               }
+               
+               return true;
+        
+       }
+       catch(exception& e) {
+               errorOut(e, "MothurOut", "isSubset");
+               exit(1);
+       }
+}
 /***********************************************************************/
 int MothurOut::mothurRemove(string filename){
        try {
@@ -2404,6 +2490,9 @@ void MothurOut::getNumSeqs(ifstream& file, int& numSeqs){
 //This function parses the estimator options and puts them in a vector
 void MothurOut::splitAtChar(string& estim, vector<string>& container, char symbol) {
        try {
+        
+        if (symbol == '-') { splitAtDash(estim, container); return; }
+        
                string individual = "";
                int estimLength = estim.size();
                for(int i=0;i<estimLength;i++){
@@ -2431,30 +2520,29 @@ void MothurOut::splitAtDash(string& estim, vector<string>& container) {
        try {
                string individual = "";
                int estimLength = estim.size();
+               bool prevEscape = false;
                for(int i=0;i<estimLength;i++){
-                       if(estim[i] == '-'){
-                               container.push_back(individual);
-                               individual = "";                                
+                       if(prevEscape){
+                               individual += estim[i];
+                               prevEscape = false;
                        }
                        else{
-                               individual += estim[i];
+                               if(estim[i] == '\\'){
+                                       prevEscape = true;
+                               }
+                               else if(estim[i] == '-'){
+                                       container.push_back(individual);
+                                       individual = "";
+                                       prevEscape = false;                             
+                               }
+                               else{
+                                       individual += estim[i];
+                                       prevEscape = false;
+                               }
                        }
                }
                container.push_back(individual);
-
-       
-       /*      string individual;
-               
-               while (estim.find_first_of('-') != -1) {
-                       individual = estim.substr(0,estim.find_first_of('-'));
-                       if ((estim.find_first_of('-')+1) <= estim.length()) { //checks to make sure you don't have dash at end of string
-                               estim = estim.substr(estim.find_first_of('-')+1, estim.length());
-                               container.push_back(individual);
-                       }
-               }
-               //get last one
-               container.push_back(estim); */
-       }
+       }
        catch(exception& e) {
                errorOut(e, "MothurOut", "splitAtDash");
                exit(1);
@@ -2467,29 +2555,29 @@ void MothurOut::splitAtDash(string& estim, set<string>& container) {
        try {
                string individual = "";
                int estimLength = estim.size();
+               bool prevEscape = false;
                for(int i=0;i<estimLength;i++){
-                       if(estim[i] == '-'){
-                               container.insert(individual);
-                               individual = "";                                
+                       if(prevEscape){
+                               individual += estim[i];
+                               prevEscape = false;
                        }
                        else{
-                               individual += estim[i];
+                               if(estim[i] == '\\'){
+                                       prevEscape = true;
+                               }
+                               else if(estim[i] == '-'){
+                                       container.insert(individual);
+                                       individual = "";
+                                       prevEscape = false;                             
+                               }
+                               else{
+                                       individual += estim[i];
+                                       prevEscape = false;
+                               }
                        }
                }
                container.insert(individual);
-
-       //      string individual;
-               
-       //      while (estim.find_first_of('-') != -1) {
-       //              individual = estim.substr(0,estim.find_first_of('-'));
-       //              if ((estim.find_first_of('-')+1) <= estim.length()) { //checks to make sure you don't have dash at end of string
-       //                      estim = estim.substr(estim.find_first_of('-')+1, estim.length());
-       //                      container.insert(individual);
-       //              }
-       //      }
-               //get last one
-       //      container.insert(estim);
-       
+        
        }
        catch(exception& e) {
                errorOut(e, "MothurOut", "splitAtDash");
@@ -2500,19 +2588,32 @@ void MothurOut::splitAtDash(string& estim, set<string>& container) {
 //This function parses the line options and puts them in a set
 void MothurOut::splitAtDash(string& estim, set<int>& container) {
        try {
-               string individual;
+               string individual = "";
                int lineNum;
-               
-               while (estim.find_first_of('-') != -1) {
-                       individual = estim.substr(0,estim.find_first_of('-'));
-                       if ((estim.find_first_of('-')+1) <= estim.length()) { //checks to make sure you don't have dash at end of string
-                               estim = estim.substr(estim.find_first_of('-')+1, estim.length());
-                               convert(individual, lineNum); //convert the string to int
-                               container.insert(lineNum);
+               int estimLength = estim.size();
+               bool prevEscape = false;
+               for(int i=0;i<estimLength;i++){
+                       if(prevEscape){
+                               individual += estim[i];
+                               prevEscape = false;
+                       }
+                       else{
+                               if(estim[i] == '\\'){
+                                       prevEscape = true;
+                               }
+                               else if(estim[i] == '-'){
+                                       convert(individual, lineNum); //convert the string to int
+                                       container.insert(lineNum);
+                                       individual = "";
+                                       prevEscape = false;                             
+                               }
+                               else{
+                                       individual += estim[i];
+                                       prevEscape = false;
+                               }
                        }
                }
-               //get last one
-               convert(estim, lineNum); //convert the string to int
+               convert(individual, lineNum); //convert the string to int
                container.insert(lineNum);
        }
        catch(exception& e) {
@@ -2650,6 +2751,35 @@ bool MothurOut::inUsersGroups(string groupname, vector<string> Groups) {
                exit(1);
        }       
 }
+/**************************************************************************************************/
+
+bool MothurOut::inUsersGroups(vector<int> set, vector< vector<int> > sets) {
+       try {
+               for (int i = 0; i < sets.size(); i++) {
+                       if (set == sets[i]) { return true; }
+               }
+               return false;
+       }
+       catch(exception& e) {
+               errorOut(e, "MothurOut", "inUsersGroups");
+               exit(1);
+       }       
+}
+/**************************************************************************************************/
+
+bool MothurOut::inUsersGroups(int groupname, vector<int> Groups) {
+       try {
+               for (int i = 0; i < Groups.size(); i++) {
+                       if (groupname == Groups[i]) { return true; }
+               }
+               return false;
+       }
+       catch(exception& e) {
+               errorOut(e, "MothurOut", "inUsersGroups");
+               exit(1);
+       }       
+}
+
 /**************************************************************************************************/
 //returns true if any of the strings in first vector are in second vector
 bool MothurOut::inUsersGroups(vector<string> groupnames, vector<string> Groups) {
@@ -2852,8 +2982,53 @@ int MothurOut::removeConfidences(string& tax) {
        }
 }
 /**************************************************************************************************/
-
-
+string MothurOut::removeQuotes(string tax) {
+       try {
+               
+               string taxon;
+               string newTax = "";
+               
+               for (int i = 0; i < tax.length(); i++) {
+                       
+                       if (control_pressed) { return newTax; }
+            
+            if ((tax[i] != '\'') && (tax[i] != '\"')) { newTax += tax[i]; }
+                       
+        }
+               
+               return newTax;
+       }
+       catch(exception& e) {
+               errorOut(e, "MothurOut", "removeQuotes");
+               exit(1);
+       }
+}
+/**************************************************************************************************/
+// function for calculating standard deviation
+double MothurOut::getStandardDeviation(vector<int>& featureVector){
+    try {
+        //finds sum
+        double average = 0; 
+        for (int i = 0; i < featureVector.size(); i++) { average += featureVector[i]; }
+        average /= (double) featureVector.size();
+        
+        //find standard deviation
+        double stdDev = 0;
+        for (int i = 0; i < featureVector.size(); i++) { //compute the difference of each dist from the mean, and square the result of each
+            stdDev += ((featureVector[i] - average) * (featureVector[i] - average));
+        }
+          
+        stdDev /= (double) featureVector.size(); 
+        stdDev = sqrt(stdDev);
+        
+        return stdDev;
+    }
+       catch(exception& e) {
+               errorOut(e, "MothurOut", "getStandardDeviation");
+               exit(1);
+       }
+}
+/**************************************************************************************************/