]> git.donarmstrong.com Git - mothur.git/blobdiff - mothurout.cpp
added code to format fast files for uchime. started work on sff.multiple command
[mothur.git] / mothurout.cpp
index eacad376e1e91a519feff3c8e57727662042599b..1a3bf79f50dad4e0a66e9910bb4abfe8c2cff944 100644 (file)
@@ -43,6 +43,7 @@ set<string> MothurOut::getCurrentTypes()  {
         types.insert("tree");
         types.insert("flow");
         types.insert("biom");
+        types.insert("count");
         types.insert("processors");
 
                return types;
@@ -78,6 +79,7 @@ void MothurOut::printCurrentFiles()  {
                if (treefile != "")                     {  mothurOut("tree=" + treefile); mothurOutEndLine();                           }
                if (flowfile != "")                     {  mothurOut("flow=" + flowfile); mothurOutEndLine();                           }
         if (biomfile != "")                    {  mothurOut("biom=" + biomfile); mothurOutEndLine();                           }
+        if (counttablefile != "")      {  mothurOut("count=" + counttablefile); mothurOutEndLine();    }
                if (processors != "1")          {  mothurOut("processors=" + processors); mothurOutEndLine();           }
                
        }
@@ -112,6 +114,7 @@ bool MothurOut::hasCurrentFiles()  {
                if (treefile != "")                     {  return true;                 }
                if (flowfile != "")                     {  return true;                 }
         if (biomfile != "")                    {  return true;                 }
+        if (counttablefile != "")      {  return true;                 }
                if (processors != "1")          {  return true;                 }
                
                return hasCurrent;
@@ -147,6 +150,7 @@ void MothurOut::clearCurrentFiles()  {
                taxonomyfile = "";      
                flowfile = "";
         biomfile = "";
+        counttablefile = "";
                processors = "1";
        }
        catch(exception& e) {
@@ -1048,6 +1052,9 @@ int MothurOut::openInputFile(string fileName, ifstream& fileHandle){
 
 int MothurOut::renameFile(string oldName, string newName){
        try {
+        
+        if (oldName == newName) { return 0; }
+        
                ifstream inTest;
                int exist = openInputFile(newName, inTest, "");
                inTest.close();
@@ -1291,16 +1298,6 @@ vector<unsigned long long> MothurOut::setFilePosEachLine(string filename, int& n
                        positions.push_back(0);
                
                        while(!in.eof()){
-                               //unsigned long long lastpos = in.tellg();
-                               //input = getline(in); 
-                               //if (input.length() != 0) {
-                                       //unsigned long long pos = in.tellg(); 
-                                       //if (pos != -1) { positions.push_back(pos - input.length() - 1);       }
-                                       //else {  positions.push_back(lastpos);  }
-                               //}
-                               //gobble(in); //has to be here since windows line endings are 2 characters and mess up the positions
-                               
-                               
                                //getline counting reads
                                char d = in.get(); count++;
                                while ((d != '\n') && (d != '\r') && (d != '\f') && (d != in.eof()))    {
@@ -1503,7 +1500,7 @@ vector<string> MothurOut::splitWhiteSpace(string& rest, char buffer[], int size)
         for (int i = 0; i < size; i++) {
             if (!isspace(buffer[i]))  { rest += buffer[i];  }
             else {
-                pieces.push_back(rest);  rest = "";
+                if (rest != "") { pieces.push_back(rest);  rest = ""; }
                 while (i < size) {  //gobble white space
                     if (isspace(buffer[i])) { i++; }
                     else { rest = buffer[i];  break; } //cout << "next piece buffer = " << nextPiece << endl;
@@ -1527,7 +1524,7 @@ vector<string> MothurOut::splitWhiteSpace(string input){
         for (int i = 0; i < input.length(); i++) {
             if (!isspace(input[i]))  { rest += input[i];  }
             else {
-                pieces.push_back(rest);  rest = "";
+                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;
@@ -1547,7 +1544,6 @@ vector<string> MothurOut::splitWhiteSpace(string input){
 //**********************************************************************************************************************
 int MothurOut::readTax(string namefile, map<string, string>& taxMap) {
        try {
-               
         //open input file
                ifstream in;
                openInputFile(namefile, in);
@@ -1578,6 +1574,23 @@ int MothurOut::readTax(string namefile, map<string, string>& taxMap) {
             }
                }
                in.close();
+        
+        if (rest != "") {
+            vector<string> pieces = splitWhiteSpace(rest);
+            
+            for (int i = 0; i < pieces.size(); i++) {
+                if (columnOne) {  firstCol = pieces[i]; columnOne=false; }
+                else  { secondCol = pieces[i]; pairDone = true; columnOne=true; }
+                
+                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");  }
+                    pairDone = false; 
+                }
+            } 
+        }
                
                return taxMap.size();
 
@@ -1590,7 +1603,6 @@ int MothurOut::readTax(string namefile, map<string, string>& taxMap) {
 /**********************************************************************************************************************/
 int MothurOut::readNames(string namefile, map<string, string>& nameMap, bool redund) { 
        try {
-               
                //open input file
                ifstream in;
                openInputFile(namefile, in);
@@ -1621,6 +1633,76 @@ int MothurOut::readNames(string namefile, map<string, string>& nameMap, bool red
             }
                }
                in.close();
+        
+        if (rest != "") {
+            vector<string> pieces = splitWhiteSpace(rest);
+            
+            for (int i = 0; i < pieces.size(); i++) {
+                if (columnOne) {  firstCol = pieces[i]; columnOne=false; }
+                else  { secondCol = pieces[i]; pairDone = true; columnOne=true; }
+                
+                if (pairDone) { 
+                    //parse names into vector
+                    vector<string> theseNames;
+                    splitAtComma(secondCol, theseNames);
+                    for (int i = 0; i < theseNames.size(); i++) {  nameMap[theseNames[i]] = firstCol;  }
+                    pairDone = false; 
+                }
+            }  
+        }
+               
+               return nameMap.size();
+               
+       }
+       catch(exception& e) {
+               errorOut(e, "MothurOut", "readNames");
+               exit(1);
+       }
+}
+/**********************************************************************************************************************/
+int MothurOut::readNames(string namefile, map<string, string>& nameMap, int flip) { 
+       try {
+               //open input file
+               ifstream in;
+               openInputFile(namefile, in);
+        
+        string rest = "";
+        char buffer[4096];
+        bool pairDone = false;
+        bool columnOne = true;
+        string firstCol, secondCol;
+        
+               while (!in.eof()) {
+                       if (control_pressed) { break; }
+                       
+            in.read(buffer, 4096);
+            vector<string> pieces = splitWhiteSpace(rest, buffer, in.gcount());
+            
+            for (int i = 0; i < pieces.size(); i++) {
+                if (columnOne) {  firstCol = pieces[i]; columnOne=false; }
+                else  { secondCol = pieces[i]; pairDone = true; columnOne=true; }
+                
+                if (pairDone) { 
+                    nameMap[secondCol] = firstCol;
+                    pairDone = false; 
+                }
+            }
+               }
+               in.close();
+        
+        if (rest != "") {
+            vector<string> pieces = splitWhiteSpace(rest);
+            
+            for (int i = 0; i < pieces.size(); i++) {
+                if (columnOne) {  firstCol = pieces[i]; columnOne=false; }
+                else  { secondCol = pieces[i]; pairDone = true; columnOne=true; }
+                
+                if (pairDone) { 
+                    nameMap[secondCol] = firstCol;
+                    pairDone = false; 
+                }
+            } 
+        }
                
                return nameMap.size();
                
@@ -1633,7 +1715,7 @@ int MothurOut::readNames(string namefile, map<string, string>& nameMap, bool red
 /**********************************************************************************************************************/
 int MothurOut::readNames(string namefile, map<string, string>& nameMap, map<string, int>& nameCount) { 
        try {
-               nameMap.clear(); nameCount.clear();
+               nameMap.clear(); nameCount.clear();
                //open input file
                ifstream in;
                openInputFile(namefile, in);
@@ -1666,6 +1748,24 @@ int MothurOut::readNames(string namefile, map<string, string>& nameMap, map<stri
                }
                in.close();
                
+        if (rest != "") {
+            vector<string> pieces = splitWhiteSpace(rest);
+            
+            for (int i = 0; i < pieces.size(); i++) {
+                if (columnOne) {  firstCol = pieces[i]; columnOne=false; }
+                else  { secondCol = pieces[i]; pairDone = true; columnOne=true; }
+                
+                if (pairDone) { 
+                    //parse names into vector
+                    vector<string> theseNames;
+                    splitAtComma(secondCol, theseNames);
+                    for (int i = 0; i < theseNames.size(); i++) {  nameMap[theseNames[i]] = firstCol;  }
+                    nameCount[firstCol] = theseNames.size();
+                    pairDone = false; 
+                }
+            }
+
+        }
                return nameMap.size();
                
        }
@@ -1677,7 +1777,6 @@ int MothurOut::readNames(string namefile, map<string, string>& nameMap, map<stri
 /**********************************************************************************************************************/
 int MothurOut::readNames(string namefile, map<string, string>& nameMap) { 
        try {
-               
                //open input file
                ifstream in;
                openInputFile(namefile, in);
@@ -1702,6 +1801,17 @@ int MothurOut::readNames(string namefile, map<string, string>& nameMap) {
             }
                }
                in.close();
+        
+        if (rest != "") {
+            vector<string> pieces = splitWhiteSpace(rest);
+            
+            for (int i = 0; i < pieces.size(); i++) {
+                if (columnOne) {  firstCol = pieces[i]; columnOne=false; }
+                else  { secondCol = pieces[i]; pairDone = true; columnOne=true; }
+                
+                if (pairDone) { nameMap[firstCol] = secondCol; pairDone = false; }
+            }
+        }
                
                return nameMap.size();
                
@@ -1713,8 +1823,7 @@ int MothurOut::readNames(string namefile, map<string, string>& nameMap) {
 }
 /**********************************************************************************************************************/
 int MothurOut::readNames(string namefile, map<string, vector<string> >& nameMap) { 
-       try {
-               
+       try {        
                //open input file
                ifstream in;
                openInputFile(namefile, in);
@@ -1745,6 +1854,22 @@ int MothurOut::readNames(string namefile, map<string, vector<string> >& nameMap)
                }
                in.close();
         
+        if (rest != "") {
+            vector<string> pieces = splitWhiteSpace(rest);
+            
+            for (int i = 0; i < pieces.size(); i++) {
+                if (columnOne) {  firstCol = pieces[i]; columnOne=false; }
+                else  { secondCol = pieces[i]; pairDone = true; columnOne=true; }
+                
+                if (pairDone) { 
+                    vector<string> temp;
+                    splitAtComma(secondCol, temp);
+                    nameMap[firstCol] = temp;
+                    pairDone = false;  
+                } 
+            }
+        }
+        
                return nameMap.size();
        }
        catch(exception& e) {
@@ -1755,7 +1880,6 @@ int MothurOut::readNames(string namefile, map<string, vector<string> >& nameMap)
 /**********************************************************************************************************************/
 map<string, int> MothurOut::readNames(string namefile) { 
        try {
-               
                map<string, int> nameMap;
                
                //open input file
@@ -1786,6 +1910,20 @@ map<string, int> MothurOut::readNames(string namefile) {
             }
                }
         in.close();
+        
+        if (rest != "") {
+            vector<string> pieces = splitWhiteSpace(rest);
+            for (int i = 0; i < pieces.size(); i++) {
+                if (columnOne) {  firstCol = pieces[i]; columnOne=false; }
+                else  { secondCol = pieces[i]; pairDone = true; columnOne=true; }
+                
+                if (pairDone) { 
+                    int num = getNumNames(secondCol);
+                    nameMap[firstCol] = num;
+                    pairDone = false;  
+                } 
+            }
+        }
                
                return nameMap;
                
@@ -1838,6 +1976,29 @@ int MothurOut::readNames(string namefile, vector<seqPriorityNode>& nameVector, m
                }
         in.close();
         
+        if (rest != "") {
+            vector<string> pieces = splitWhiteSpace(rest);
+            
+            for (int i = 0; i < pieces.size(); i++) {
+                if (columnOne) {  firstCol = pieces[i]; columnOne=false; }
+                else  { secondCol = pieces[i]; pairDone = true; columnOne=true; }
+                
+                if (pairDone) { 
+                    int num = getNumNames(secondCol);
+                    
+                    map<string, string>::iterator it = fastamap.find(firstCol);
+                    if (it == fastamap.end()) {
+                        error = 1;
+                        mothurOut("[ERROR]: " + firstCol + " is not in your fastafile, but is in your namesfile, please correct."); mothurOutEndLine();
+                    }else {
+                        seqPriorityNode temp(num, it->second, firstCol);
+                        nameVector.push_back(temp);
+                    }
+                    
+                    pairDone = false;  
+                } 
+            }
+        }
                return error;
        }
        catch(exception& e) {
@@ -1848,7 +2009,7 @@ int MothurOut::readNames(string namefile, vector<seqPriorityNode>& nameVector, m
 //**********************************************************************************************************************
 set<string> MothurOut::readAccnos(string accnosfile){
        try {
-               set<string> names;
+               set<string> names;
                ifstream in;
                openInputFile(accnosfile, in);
                string name;
@@ -1866,6 +2027,10 @@ set<string> MothurOut::readAccnos(string accnosfile){
         }
                in.close();     
                
+        if (rest != "") {
+            vector<string> pieces = splitWhiteSpace(rest);
+            for (int i = 0; i < pieces.size(); i++) {  names.insert(pieces[i]);  } 
+        }
                return names;
        }
        catch(exception& e) {
@@ -1893,6 +2058,11 @@ int MothurOut::readAccnos(string accnosfile, vector<string>& names){
             for (int i = 0; i < pieces.size(); i++) {  names.push_back(pieces[i]);  }
         }
                in.close();     
+        
+        if (rest != "") {
+            vector<string> pieces = splitWhiteSpace(rest);
+            for (int i = 0; i < pieces.size(); i++) {  names.push_back(pieces[i]);  }
+        }
                
                return 0;
        }
@@ -1983,6 +2153,28 @@ bool MothurOut::mothurConvert(string item, int& num){
                exit(1);
        }
 }
+/***********************************************************************/
+bool MothurOut::mothurConvert(string item, intDist& num){
+       try {
+               bool error = false;
+               
+               if (isNumeric1(item)) {
+                       convert(item, num);
+               }else {
+                       num = 0;
+                       error = true;
+                       mothurOut("[ERROR]: cannot convert " + item + " to an integer."); mothurOutEndLine();
+                       commandInputsConvertError = true;
+               }
+               
+               return error;
+       }
+       catch(exception& e) {
+               errorOut(e, "MothurOut", "mothurConvert");
+               exit(1);
+       }
+}
+
 /***********************************************************************/
 bool MothurOut::isNumeric1(string stringToCheck){
        try {