X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=mothurout.cpp;h=1f1c96b6f203e4f1fa8b1dca2e018c735caa6b9f;hp=df1a1c0615be21cd53ab51b0a82cfaab3871e847;hb=b25ede2ad307ae76f8a610443e0ec3ec69621ce7;hpb=763d07b1c215b1bdc9d5d63431f78cfecc60acf5 diff --git a/mothurout.cpp b/mothurout.cpp index df1a1c0..1f1c96b 100644 --- a/mothurout.cpp +++ b/mothurout.cpp @@ -18,8 +18,47 @@ MothurOut* MothurOut::getInstance() { return _uniqueInstance; } /*********************************************************************************************/ +set MothurOut::getCurrentTypes() { + try { + + set types; + types.insert("fasta"); + types.insert("summary"); + types.insert("accnos"); + types.insert("column"); + types.insert("design"); + types.insert("group"); + types.insert("list"); + types.insert("name"); + types.insert("oligos"); + types.insert("order"); + types.insert("ordergroup"); + types.insert("phylip"); + types.insert("qfile"); + types.insert("relabund"); + types.insert("sabund"); + types.insert("rabund"); + types.insert("sff"); + types.insert("shared"); + types.insert("taxonomy"); + types.insert("tree"); + types.insert("flow"); + types.insert("biom"); + types.insert("count"); + types.insert("processors"); + + return types; + } + catch(exception& e) { + errorOut(e, "MothurOut", "getCurrentTypes"); + exit(1); + } +} +/*********************************************************************************************/ void MothurOut::printCurrentFiles() { try { + + if (accnosfile != "") { mothurOut("accnos=" + accnosfile); mothurOutEndLine(); } if (columnfile != "") { mothurOut("column=" + columnfile); mothurOutEndLine(); } if (designfile != "") { mothurOut("design=" + designfile); mothurOutEndLine(); } @@ -40,7 +79,10 @@ void MothurOut::printCurrentFiles() { if (taxonomyfile != "") { mothurOut("taxonomy=" + taxonomyfile); mothurOutEndLine(); } 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(); } + if (summaryfile != "") { mothurOut("summary=" + summaryfile); mothurOutEndLine(); } } catch(exception& e) { @@ -73,6 +115,9 @@ bool MothurOut::hasCurrentFiles() { if (taxonomyfile != "") { return true; } if (treefile != "") { return true; } if (flowfile != "") { return true; } + if (biomfile != "") { return true; } + if (counttablefile != "") { return true; } + if (summaryfile != "") { return true; } if (processors != "1") { return true; } return hasCurrent; @@ -107,6 +152,9 @@ void MothurOut::clearCurrentFiles() { accnosfile = ""; taxonomyfile = ""; flowfile = ""; + biomfile = ""; + counttablefile = ""; + summaryfile = ""; processors = "1"; } catch(exception& e) { @@ -114,6 +162,81 @@ void MothurOut::clearCurrentFiles() { exit(1); } } +/***********************************************************************/ +string MothurOut::findProgramPath(string programName){ + try { + + string envPath = getenv("PATH"); + string pPath = ""; + + //delimiting path char + char delim; +#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) + delim = ':'; +#else + delim = ';'; +#endif + + //break apart path variable by ':' + vector dirs; + splitAtChar(envPath, dirs, delim); + + if (debug) { mothurOut("[DEBUG]: dir's in path: \n"); } + + //get path related to mothur + for (int i = 0; i < dirs.size(); i++) { + + if (debug) { mothurOut("[DEBUG]: " + dirs[i] + "\n"); } + + //to lower so we can find it + string tempLower = ""; + for (int j = 0; j < dirs[i].length(); j++) { tempLower += tolower(dirs[i][j]); } + + //is this mothurs path? + if (tempLower.find(programName) != -1) { pPath = dirs[i]; break; } + } + + if (debug) { mothurOut("[DEBUG]: programPath = " + pPath + "\n"); } + + if (pPath != "") { + //add programName so it looks like what argv would look like +#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) + pPath += "/" + programName; +#else + pPath += "\\" + programName; +#endif + }else { + //okay programName is not in the path, so the folder programName is in must be in the path + //lets find out which one + + //get path related to the program + for (int i = 0; i < dirs.size(); i++) { + + if (debug) { mothurOut("[DEBUG]: looking in " + dirs[i] + " for " + programName + " \n"); } + + //is this the programs path? + ifstream in; + string tempIn = dirs[i]; +#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) + tempIn += "/" + programName; +#else + tempIn += "\\" + programName; +#endif + openInputFile(tempIn, in, ""); + + //if this file exists + if (in) { in.close(); pPath = tempIn; if (debug) { mothurOut("[DEBUG]: found it, programPath = " + pPath + "\n"); } break; } + } + } + + return pPath; + + } + catch(exception& e) { + errorOut(e, "MothurOut", "findProgramPath"); + exit(1); + } +} /*********************************************************************************************/ void MothurOut::setFileName(string filename) { try { @@ -143,7 +266,7 @@ void MothurOut::setDefaultPath(string pathname) { //add / to name if needed string lastChar = pathname.substr(pathname.length()-1); - #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) + #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) if (lastChar != "/") { pathname += "/"; } #else if (lastChar != "\\") { pathname += "\\"; } @@ -212,8 +335,8 @@ void MothurOut::mothurOut(string output) { if (pid == 0) { //only one process should output to screen #endif - cout << output; out << output; + logger() << output; #ifdef USE_MPI } @@ -225,6 +348,27 @@ void MothurOut::mothurOut(string output) { } } /*********************************************************************************************/ +void MothurOut::mothurOutJustToScreen(string output) { + try { + +#ifdef USE_MPI + int pid; + MPI_Comm_rank(MPI_COMM_WORLD, &pid); + + if (pid == 0) { //only one process should output to screen +#endif + logger() << output; + +#ifdef USE_MPI + } +#endif + } + catch(exception& e) { + errorOut(e, "MothurOut", "MothurOut"); + exit(1); + } +} +/*********************************************************************************************/ void MothurOut::mothurOutEndLine() { try { #ifdef USE_MPI @@ -234,8 +378,8 @@ void MothurOut::mothurOutEndLine() { if (pid == 0) { //only one process should output to screen #endif - cout << endl; out << endl; + logger() << endl; #ifdef USE_MPI } @@ -257,13 +401,15 @@ void MothurOut::mothurOut(string output, ofstream& outputFile) { if (pid == 0) { //only one process should output to screen #endif - cout << output; + out << output; outputFile << output; + logger() << output; #ifdef USE_MPI } #endif + } catch(exception& e) { errorOut(e, "MothurOut", "MothurOut"); @@ -280,9 +426,9 @@ void MothurOut::mothurOutEndLine(ofstream& outputFile) { if (pid == 0) { //only one process should output to screen #endif - cout << endl; out << endl; outputFile << endl; + logger() << endl; #ifdef USE_MPI } @@ -319,10 +465,24 @@ void MothurOut::errorOut(exception& e, string object, string function) { //double vm, rss; //mem_usage(vm, rss); - mothurOut("[ERROR]: "); - mothurOut(toString(e.what())); - mothurOut(" has occurred in the " + object + " class function " + function + ". Please contact Pat Schloss at mothur.bugs@gmail.com, and be sure to include the mothur.logFile with your inquiry."); - mothurOutEndLine(); + string errorType = toString(e.what()); + + int pos = errorType.find("bad_alloc"); + mothurOut("[ERROR]: "); + mothurOut(errorType); + + if (pos == string::npos) { //not bad_alloc + mothurOut(" has occurred in the " + object + " class function " + function + ". Please contact Pat Schloss at mothur.bugs@gmail.com, and be sure to include the mothur.logFile with your inquiry."); + mothurOutEndLine(); + }else { //bad alloc + if (object == "cluster"){ + mothurOut(" has occurred in the " + object + " class function " + function + ". This error indicates your computer is running out of memory. There are two common causes for this, file size and format.\n\nFile Size:\nThe cluster command loads your distance matrix into RAM, and your distance file is most likely too large to fit in RAM. There are two options to help with this. The first is to use a cutoff. By using a cutoff mothur will only load distances that are below the cutoff. If that is still not enough, there is a command called cluster.split, http://www.mothur.org/wiki/cluster.split which divides the distance matrix, and clusters the smaller pieces separately. You may also be able to reduce the size of the original distance matrix by using the commands outlined in the Schloss SOP, http://www.mothur.org/wiki/Schloss_SOP. \n\nWrong Format:\nThis error can be caused by trying to read a column formatted distance matrix using the phylip parameter. By default, the dist.seqs command generates a column formatted distance matrix. To make a phylip formatted matrix set the dist.seqs command parameter output to lt. \n\nIf you are uable to resolve the issue, please contact Pat Schloss at mothur.bugs@gmail.com, and be sure to include the mothur.logFile with your inquiry."); + }else if (object == "shhh.flows"){ + mothurOut(" has occurred in the " + object + " class function " + function + ". This error indicates your computer is running out of memory. The shhh.flows command is very memory intensive. This error is most commonly caused by trying to process a dataset too large, using multiple processors, or failing to run trim.flows before shhh.flows. If you are running our 32bit version, your memory usage is limited to 4G. If you have more than 4G of RAM and are running a 64bit OS, using our 64bit version may resolve your issue. If you are using multiple processors, try running the command with processors=1, the more processors you use the more memory is required. Running trim.flows with an oligos file, and then shhh.flows with the file option may also resolve the issue. If for some reason you are unable to run shhh.flows with your data, a good alternative is to use the trim.seqs command using a 50-bp sliding window and to trim the sequence when the average quality score over that window drops below 35. Our results suggest that the sequencing error rates by this method are very good, but not quite as good as by shhh.flows and that the resulting sequences tend to be a bit shorter. If you are uable to resolve the issue, please contact Pat Schloss at mothur.bugs@gmail.com, and be sure to include the mothur.logFile with your inquiry. "); + }else { + mothurOut(" has occurred in the " + object + " class function " + function + ". This error indicates your computer is running out of memory. This is most commonly caused by trying to process a dataset too large, using multiple processors, or a file format issue. If you are running our 32bit version, your memory usage is limited to 4G. If you have more than 4G of RAM and are running a 64bit OS, using our 64bit version may resolve your issue. If you are using multiple processors, try running the command with processors=1, the more processors you use the more memory is required. Also, you may be able to reduce the size of your dataset by using the commands outlined in the Schloss SOP, http://www.mothur.org/wiki/Schloss_SOP. If you are uable to resolve the issue, please contact Pat Schloss at mothur.bugs@gmail.com, and be sure to include the mothur.logFile with your inquiry."); + } + } } /*********************************************************************************************/ //The following was originally from http://stackoverflow.com/questions/669438/how-to-get-memory-usage-at-run-time-in-c @@ -332,7 +492,7 @@ void MothurOut::errorOut(exception& e, string object, string function) { // // On failure, returns 0.0, 0.0 int MothurOut::mem_usage(double& vm_usage, double& resident_set) { - #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) + #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) vm_usage = 0.0; resident_set = 0.0; @@ -434,7 +594,7 @@ void MothurOut::gobble(istream& f){ char d; while(isspace(d=f.get())) { ;} - f.putback(d); + if(!f.eof()) { f.putback(d); } } catch(exception& e) { errorOut(e, "MothurOut", "gobble"); @@ -446,7 +606,7 @@ void MothurOut::gobble(istringstream& f){ try { char d; while(isspace(d=f.get())) {;} - f.putback(d); + if(!f.eof()) { f.putback(d); } } catch(exception& e) { errorOut(e, "MothurOut", "gobble"); @@ -504,7 +664,7 @@ string MothurOut::getline(ifstream& fileHandle) { } /***********************************************************************/ -#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) +#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) #ifdef USE_COMPRESSION inline bool endsWith(string s, const char * suffix){ size_t suffixLength = strlen(suffix); @@ -518,7 +678,7 @@ string MothurOut::getRootName(string longName){ string rootName = longName; -#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) +#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) #ifdef USE_COMPRESSION if (endsWith(rootName, ".gz") || endsWith(rootName, ".bz2")) { int pos = rootName.find_last_of('.'); @@ -596,6 +756,81 @@ string MothurOut::getPathName(string longName){ } /***********************************************************************/ +bool MothurOut::dirCheck(string& dirName){ + try { + + string tag = ""; + #ifdef USE_MPI + int pid; + MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are + + tag = toString(pid); + #endif + + //add / to name if needed + string lastChar = dirName.substr(dirName.length()-1); + #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) + if (lastChar != "/") { dirName += "/"; } + #else + if (lastChar != "\\") { dirName += "\\"; } + #endif + + //test to make sure directory exists + dirName = getFullPathName(dirName); + string outTemp = dirName + tag + "temp"; + ofstream out; + out.open(outTemp.c_str(), ios::trunc); + if(!out) { + mothurOut(dirName + " directory does not exist or is not writable."); mothurOutEndLine(); + }else{ + out.close(); + mothurRemove(outTemp); + return true; + } + + return false; + } + catch(exception& e) { + errorOut(e, "MothurOut", "dirCheck"); + exit(1); + } + +} +//********************************************************************************************************************** + +map > MothurOut::parseClasses(string classes){ + try { + map > parts; + + //treatment-age + vector pieces; splitAtDash(classes, pieces); // -> treatment, age + + for (int i = 0; i < pieces.size(); i++) { + string category = ""; string value = ""; + bool foundOpen = false; + for (int j = 0; j < pieces[i].length(); j++) { + if (control_pressed) { return parts; } + + if (pieces[i][j] == '<') { foundOpen = true; } + else if (pieces[i][j] == '>') { j += pieces[i].length(); } + else { + if (!foundOpen) { category += pieces[i][j]; } + else { value += pieces[i][j]; } + } + } + vector values; splitAtChar(value, values, '|'); + parts[category] = values; + } + + return parts; + } + catch(exception& e) { + errorOut(e, "MothurOut", "parseClasses"); + exit(1); + } +} +/***********************************************************************/ + string MothurOut::hasPath(string longName){ try { string path = ""; @@ -619,7 +854,7 @@ string MothurOut::hasPath(string longName){ string MothurOut::getExtension(string longName){ try { - string extension = longName; + string extension = ""; if(longName.find_last_of('.') != longName.npos){ int pos = longName.find_last_of('.'); @@ -673,7 +908,7 @@ string MothurOut::getFullPathName(string fileName){ string cwd; //get current working directory - #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) + #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) if (path.find("~") != -1) { //go to home directory string homeDir; @@ -726,7 +961,7 @@ string MothurOut::getFullPathName(string fileName){ }else if (path[(pos-1)] == '/') { //you want the current working dir ./ path = path.substr(0, pos); }else if (pos == 1) { break; //you are at the end - }else { cout << "cannot resolve path for " << fileName << endl; return fileName; } + }else { mothurOut("cannot resolve path for " + fileName + "\n"); return fileName; } } for (int i = index; i >= 0; i--) { @@ -772,7 +1007,7 @@ string MothurOut::getFullPathName(string fileName){ }else if (path[(pos-1)] == '\\') { //you want the current working dir ./ path = path.substr(0, pos); }else if (pos == 1) { break; //you are at the end - }else { cout << "cannot resolve path for " << fileName << endl; return fileName; } + }else { mothurOut("cannot resolve path for " + fileName + "\n"); return fileName; } } for (int i = index; i >= 0; i--) { @@ -796,7 +1031,7 @@ int MothurOut::openInputFile(string fileName, ifstream& fileHandle, string m){ try { //get full path name string completeFileName = getFullPathName(fileName); -#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) +#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) #ifdef USE_COMPRESSION // check for gzipped or bzipped file if (endsWith(completeFileName, ".gz") || endsWith(completeFileName, ".bz2")) { @@ -842,7 +1077,7 @@ int MothurOut::openInputFile(string fileName, ifstream& fileHandle){ //get full path name string completeFileName = getFullPathName(fileName); -#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) +#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) #ifdef USE_COMPRESSION // check for gzipped or bzipped file if (endsWith(completeFileName, ".gz") || endsWith(completeFileName, ".bz2")) { @@ -889,12 +1124,15 @@ 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(); - #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) + #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) if (exist == 0) { //you could open it so you want to delete it - inTest.close(); string command = "rm " + newName; system(command.c_str()); } @@ -920,7 +1158,7 @@ int MothurOut::openOutputFile(string fileName, ofstream& fileHandle){ try { string completeFileName = getFullPathName(fileName); -#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) +#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) #ifdef USE_COMPRESSION // check for gzipped file if (endsWith(completeFileName, ".gz") || endsWith(completeFileName, ".bz2")) { @@ -970,10 +1208,50 @@ int MothurOut::appendFiles(string temp, string filename) { int numLines = 0; if (ableToOpen == 0) { //you opened it - while(char c = input.get()){ - if(input.eof()) { break; } - else { output << c; if (c == '\n') {numLines++;} } - } + + char buffer[4096]; + while (!input.eof()) { + input.read(buffer, 4096); + output.write(buffer, input.gcount()); + //count number of lines + for (int i = 0; i < input.gcount(); i++) { if (buffer[i] == '\n') {numLines++;} } + } + input.close(); + } + + output.close(); + + return numLines; + } + catch(exception& e) { + errorOut(e, "MothurOut", "appendFiles"); + exit(1); + } +} +/**************************************************************************************************/ +int MothurOut::appendFilesWithoutHeaders(string temp, string filename) { + try{ + ofstream output; + ifstream input; + + //open output file in append mode + openOutputFileAppend(filename, output); + int ableToOpen = openInputFile(temp, input, "no error"); + //int ableToOpen = openInputFile(temp, input); + + int numLines = 0; + if (ableToOpen == 0) { //you opened it + + string headers = getline(input); gobble(input); + if (debug) { mothurOut("[DEBUG]: skipping headers " + headers +'\n'); } + + char buffer[4096]; + while (!input.eof()) { + input.read(buffer, 4096); + output.write(buffer, input.gcount()); + //count number of lines + for (int i = 0; i < input.gcount(); i++) { if (buffer[i] == '\n') {numLines++;} } + } input.close(); } @@ -986,7 +1264,6 @@ int MothurOut::appendFiles(string temp, string filename) { exit(1); } } - /**************************************************************************************************/ string MothurOut::sortFile(string distFile, string outputDir){ try { @@ -996,7 +1273,7 @@ string MothurOut::sortFile(string distFile, string outputDir){ //if you can, use the unix sort since its been optimized for years - #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) + #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) string command = "sort -n -k +3 " + distFile + " -o " + outfile; system(command.c_str()); #else //you are stuck with my best attempt... @@ -1013,7 +1290,7 @@ 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); @@ -1029,16 +1306,17 @@ 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); @@ -1072,15 +1350,15 @@ vector MothurOut::setFilePosFasta(string filename, int& num) char c = inFASTA.get(); count++; if (c == '>') { positions.push_back(count-1); - //cout << count << endl; + if (debug) { mothurOut("[DEBUG]: numSeqs = " + toString(positions.size()) + " count = " + toString(count) + ".\n"); } } } inFASTA.close(); num = positions.size(); - - /*FILE * pFile; - long size; + if (debug) { mothurOut("[DEBUG]: num = " + toString(num) + ".\n"); } + FILE * pFile; + unsigned long long size; //get num bytes in file pFile = fopen (filename.c_str(),"rb"); @@ -1089,9 +1367,9 @@ vector MothurOut::setFilePosFasta(string filename, int& num) fseek (pFile, 0, SEEK_END); size=ftell (pFile); fclose (pFile); - }*/ + } - unsigned long long size = positions[(positions.size()-1)]; + /*unsigned long long size = positions[(positions.size()-1)]; ifstream in; openInputFile(filename, in); @@ -1101,8 +1379,10 @@ vector MothurOut::setFilePosFasta(string filename, int& num) if(in.eof()) { break; } else { size++; } } - in.close(); - + in.close();*/ + + if (debug) { mothurOut("[DEBUG]: size = " + toString(size) + ".\n"); } + positions.push_back(size); positions[0] = 0; @@ -1113,6 +1393,67 @@ vector MothurOut::setFilePosFasta(string filename, int& num) exit(1); } } +//********************************************************************************************************************** +vector MothurOut::readConsTax(string inputfile){ + try { + + vector taxes; + + ifstream in; + openInputFile(inputfile, in); + + //read headers + getline(in); + + while (!in.eof()) { + + if (control_pressed) { break; } + + string otu = ""; string tax = "unknown"; + int size = 0; + + in >> otu >> size >> tax; gobble(in); + consTax temp(otu, tax, size); + taxes.push_back(temp); + } + in.close(); + + return taxes; + } + catch(exception& e) { + errorOut(e, "MothurOut", "readConsTax"); + exit(1); + } +} +//********************************************************************************************************************** +int MothurOut::readConsTax(string inputfile, map& taxes){ + try { + ifstream in; + openInputFile(inputfile, in); + + //read headers + getline(in); + + while (!in.eof()) { + + if (control_pressed) { break; } + + string otu = ""; string tax = "unknown"; + int size = 0; + + in >> otu >> size >> tax; gobble(in); + consTax2 temp(tax, size); + taxes[otu] = temp; + } + in.close(); + + return 0; + } + catch(exception& e) { + errorOut(e, "MothurOut", "readConsTax"); + exit(1); + } +} /**************************************************************************************************/ vector MothurOut::setFilePosEachLine(string filename, int& num) { try { @@ -1128,16 +1469,6 @@ vector 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())) { @@ -1151,7 +1482,7 @@ vector MothurOut::setFilePosEachLine(string filename, int& n while(isspace(d) && (d != in.eof())) { d=in.get(); count++;} } positions.push_back(count-1); - cout << count-1 << endl; + //cout << count-1 << endl; } in.close(); @@ -1182,7 +1513,6 @@ vector MothurOut::setFilePosEachLine(string filename, int& n vector MothurOut::divideFile(string filename, int& proc) { try{ - vector filePos; filePos.push_back(0); @@ -1190,7 +1520,7 @@ vector MothurOut::divideFile(string filename, int& proc) { unsigned long long size; filename = getFullPathName(filename); - + //get num bytes in file pFile = fopen (filename.c_str(),"rb"); if (pFile==NULL) perror ("Error opening file"); @@ -1199,7 +1529,9 @@ vector MothurOut::divideFile(string filename, int& proc) { size=ftell (pFile); fclose (pFile); } - + + #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) + //estimate file breaks unsigned long long chunkSize = 0; chunkSize = size / proc; @@ -1219,7 +1551,10 @@ vector MothurOut::divideFile(string filename, int& proc) { unsigned long long newSpot = spot; while (!in.eof()) { char c = in.get(); + if (c == '>') { in.putback(c); newSpot = in.tellg(); break; } + else if (int(c) == -1) { break; } + } //there was not another sequence before the end of the file @@ -1233,14 +1568,95 @@ vector MothurOut::divideFile(string filename, int& proc) { //save end pos filePos.push_back(size); - + //sanity check filePos for (int i = 0; i < (filePos.size()-1); i++) { if (filePos[(i+1)] <= filePos[i]) { filePos.erase(filePos.begin()+(i+1)); i--; } } proc = (filePos.size() - 1); +#else + mothurOut("[ERROR]: Windows version should not be calling the divideFile function."); mothurOutEndLine(); + proc=1; + filePos.push_back(size); +#endif + return filePos; + } + catch(exception& e) { + errorOut(e, "MothurOut", "divideFile"); + exit(1); + } +} +/**************************************************************************************************/ + +vector MothurOut::divideFilePerLine(string filename, int& proc) { + try{ + vector filePos; + filePos.push_back(0); + + FILE * pFile; + unsigned long long size; + + filename = getFullPathName(filename); + + //get num bytes in file + pFile = fopen (filename.c_str(),"rb"); + if (pFile==NULL) perror ("Error opening file"); + else{ + fseek (pFile, 0, SEEK_END); + size=ftell (pFile); + fclose (pFile); + } + +#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) + + //estimate file breaks + unsigned long long chunkSize = 0; + chunkSize = size / proc; + + //file to small to divide by processors + if (chunkSize == 0) { proc = 1; filePos.push_back(size); return filePos; } + + //for each process seekg to closest file break and search for next '>' char. make that the filebreak + for (int i = 0; i < proc; i++) { + unsigned long long spot = (i+1) * chunkSize; + + ifstream in; + openInputFile(filename, in); + in.seekg(spot); + + //look for next line break + unsigned long long newSpot = spot; + while (!in.eof()) { + char c = in.get(); + + if ((c == '\n') || (c == '\r') || (c == '\f')) { gobble(in); newSpot = in.tellg(); break; } + else if (int(c) == -1) { break; } + } + + //there was not another line before the end of the file + unsigned long long sanityPos = in.tellg(); + + if (sanityPos == -1) { break; } + else { filePos.push_back(newSpot); } + + in.close(); + } + + //save end pos + filePos.push_back(size); + //sanity check filePos + for (int i = 0; i < (filePos.size()-1); i++) { + if (filePos[(i+1)] <= filePos[i]) { filePos.erase(filePos.begin()+(i+1)); i--; } + } + + proc = (filePos.size() - 1); +#else + mothurOut("[ERROR]: Windows version should not be calling the divideFile function."); mothurOutEndLine(); + proc=1; + filePos.push_back(size); +#endif return filePos; } catch(exception& e) { @@ -1323,54 +1739,234 @@ float MothurOut::ceilDist(float dist, int precision){ exit(1); } } -/**********************************************************************************************************************/ -int MothurOut::readNames(string namefile, map& nameMap) { +/***********************************************************************/ + +vector MothurOut::splitWhiteSpace(string& rest, char buffer[], int size){ try { - - //open input file + vector pieces; + + for (int i = 0; i < size; i++) { + if (!isspace(buffer[i])) { rest += buffer[i]; } + else { + 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; + } + } + } + + return pieces; + } + catch(exception& e) { + errorOut(e, "MothurOut", "splitWhiteSpace"); + exit(1); + } +} +/***********************************************************************/ +vector MothurOut::splitWhiteSpace(string input){ + try { + vector pieces; + string rest = ""; + + for (int i = 0; i < input.length(); i++) { + 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); + } +} +/***********************************************************************/ +vector MothurOut::splitWhiteSpaceWithQuotes(string input){ + try { + vector 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& taxMap) { + 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; } - string firstCol, secondCol; - in >> firstCol >> secondCol; gobble(in); - - nameMap[firstCol] = secondCol; + in.read(buffer, 4096); + vector 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) { + checkName(firstCol); + //are there confidence scores, if so remove them + if (secondCol.find_first_of('(') != -1) { removeConfidences(secondCol); } + map::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; + } + } } in.close(); + + if (rest != "") { + vector 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) { + checkName(firstCol); + //are there confidence scores, if so remove them + if (secondCol.find_first_of('(') != -1) { removeConfidences(secondCol); } + map::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; + } + } + } - return 0; - + return taxMap.size(); + } catch(exception& e) { - errorOut(e, "MothurOut", "readNames"); + errorOut(e, "MothurOut", "readTax"); exit(1); } } /**********************************************************************************************************************/ -int MothurOut::readNames(string namefile, map >& nameMap) { +int MothurOut::readNames(string namefile, map& nameMap, bool redund) { 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; } - string firstCol, secondCol; - in >> firstCol >> secondCol; gobble(in); - - vector temp; - splitAtComma(secondCol, temp); - - nameMap[firstCol] = temp; + in.read(buffer, 4096); + vector 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) { + checkName(firstCol); + checkName(secondCol); + + //parse names into vector + vector theseNames; + splitAtComma(secondCol, theseNames); + for (int i = 0; i < theseNames.size(); i++) { nameMap[theseNames[i]] = firstCol; } + pairDone = false; + } + } } in.close(); + + if (rest != "") { + vector 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) { + checkName(firstCol); + checkName(secondCol); + + //parse names into vector + vector theseNames; + splitAtComma(secondCol, theseNames); + for (int i = 0; i < theseNames.size(); i++) { nameMap[theseNames[i]] = firstCol; } + pairDone = false; + } + } + } - return 0; + return nameMap.size(); } catch(exception& e) { @@ -1379,28 +1975,55 @@ int MothurOut::readNames(string namefile, map >& nameMap) } } /**********************************************************************************************************************/ -map MothurOut::readNames(string namefile) { +int MothurOut::readNames(string namefile, map& nameMap, int flip) { try { - - map nameMap; - //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; } - string firstCol, secondCol; - in >> firstCol >> secondCol; gobble(in); - - int num = getNumNames(secondCol); - - nameMap[firstCol] = num; + in.read(buffer, 4096); + vector 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) { + checkName(firstCol); + checkName(secondCol); + nameMap[secondCol] = firstCol; + pairDone = false; + } + } } in.close(); + + if (rest != "") { + vector 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) { + checkName(firstCol); + checkName(secondCol); + nameMap[secondCol] = firstCol; + pairDone = false; + } + } + } - return nameMap; + return nameMap.size(); } catch(exception& e) { @@ -1409,34 +2032,64 @@ map MothurOut::readNames(string namefile) { } } /**********************************************************************************************************************/ -int MothurOut::readNames(string namefile, vector& nameVector, map& fastamap) { +int MothurOut::readNames(string namefile, map& nameMap, map& nameCount) { try { - int error = 0; - + nameMap.clear(); nameCount.clear(); //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; } - string firstCol, secondCol; - in >> firstCol >> secondCol; gobble(in); - - int num = getNumNames(secondCol); - - map::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); - } + in.read(buffer, 4096); + vector 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) { + checkName(firstCol); + checkName(secondCol); + //parse names into vector + vector theseNames; + splitAtComma(secondCol, theseNames); + for (int i = 0; i < theseNames.size(); i++) { nameMap[theseNames[i]] = firstCol; } + nameCount[firstCol] = theseNames.size(); + pairDone = false; + } + } } in.close(); - return error; + if (rest != "") { + vector 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) { + checkName(firstCol); + checkName(secondCol); + //parse names into vector + vector 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(); } catch(exception& e) { @@ -1444,14 +2097,408 @@ int MothurOut::readNames(string namefile, vector& nameVector, m exit(1); } } - -/***********************************************************************/ - -int MothurOut::getNumNames(string names){ +/**********************************************************************************************************************/ +int MothurOut::readNames(string namefile, map& nameMap) { try { - int count = 0; - - if(names != ""){ + //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 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) { + checkName(firstCol); + checkName(secondCol); + nameMap[firstCol] = secondCol; pairDone = false; } + } + } + in.close(); + + if (rest != "") { + vector 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) { + checkName(firstCol); + checkName(secondCol); + nameMap[firstCol] = secondCol; pairDone = false; } + } + } + + return nameMap.size(); + + } + catch(exception& e) { + errorOut(e, "MothurOut", "readNames"); + exit(1); + } +} +/**********************************************************************************************************************/ +int MothurOut::readNames(string namefile, map >& nameMap) { + 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 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) { + checkName(firstCol); + checkName(secondCol); + vector temp; + splitAtComma(secondCol, temp); + nameMap[firstCol] = temp; + pairDone = false; + } + } + } + in.close(); + + if (rest != "") { + vector 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) { + checkName(firstCol); + checkName(secondCol); + vector temp; + splitAtComma(secondCol, temp); + nameMap[firstCol] = temp; + pairDone = false; + } + } + } + + return nameMap.size(); + } + catch(exception& e) { + errorOut(e, "MothurOut", "readNames"); + exit(1); + } +} +/**********************************************************************************************************************/ +map MothurOut::readNames(string namefile) { + try { + map nameMap; + + //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 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) { + checkName(firstCol); + checkName(secondCol); + int num = getNumNames(secondCol); + nameMap[firstCol] = num; + pairDone = false; + } + } + } + in.close(); + + if (rest != "") { + vector 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) { + checkName(firstCol); + checkName(secondCol); + int num = getNumNames(secondCol); + nameMap[firstCol] = num; + pairDone = false; + } + } + } + + return nameMap; + + } + catch(exception& e) { + errorOut(e, "MothurOut", "readNames"); + exit(1); + } +} +/**********************************************************************************************************************/ +map MothurOut::readNames(string namefile, unsigned long int& numSeqs) { + try { + map nameMap; + numSeqs = 0; + + //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 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) { + checkName(firstCol); + checkName(secondCol); + int num = getNumNames(secondCol); + nameMap[firstCol] = num; + pairDone = false; + numSeqs += num; + } + } + } + in.close(); + + if (rest != "") { + vector 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) { + checkName(firstCol); + checkName(secondCol); + int num = getNumNames(secondCol); + nameMap[firstCol] = num; + pairDone = false; + numSeqs += num; + } + } + } + + return nameMap; + + } + catch(exception& e) { + errorOut(e, "MothurOut", "readNames"); + exit(1); + } +} +/************************************************************/ +int MothurOut::checkName(string& name) { + try { + if (modifyNames) { + for (int i = 0; i < name.length(); i++) { + if (name[i] == ':') { name[i] = '_'; changedSeqNames = true; } + } + } + return 0; + } + catch(exception& e) { + errorOut(e, "MothurOut", "checkName"); + exit(1); + } +} +/**********************************************************************************************************************/ +int MothurOut::readNames(string namefile, vector& nameVector, map& fastamap) { + try { + int error = 0; + + //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 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) { + checkName(firstCol); + checkName(secondCol); + int num = getNumNames(secondCol); + + map::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; + } + } + } + in.close(); + + if (rest != "") { + vector 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) { + checkName(firstCol); + checkName(secondCol); + int num = getNumNames(secondCol); + + map::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) { + errorOut(e, "MothurOut", "readNames"); + exit(1); + } +} +//********************************************************************************************************************** +set MothurOut::readAccnos(string accnosfile){ + try { + set names; + ifstream in; + openInputFile(accnosfile, in); + string name; + + string rest = ""; + char buffer[4096]; + + while (!in.eof()) { + if (control_pressed) { break; } + + in.read(buffer, 4096); + vector pieces = splitWhiteSpace(rest, buffer, in.gcount()); + + for (int i = 0; i < pieces.size(); i++) { checkName(pieces[i]); + names.insert(pieces[i]); + } + } + in.close(); + + if (rest != "") { + vector pieces = splitWhiteSpace(rest); + for (int i = 0; i < pieces.size(); i++) { checkName(pieces[i]); names.insert(pieces[i]); } + } + return names; + } + catch(exception& e) { + errorOut(e, "MothurOut", "readAccnos"); + exit(1); + } +} +//********************************************************************************************************************** +int MothurOut::readAccnos(string accnosfile, vector& names){ + try { + names.clear(); + ifstream in; + openInputFile(accnosfile, in); + string name; + + string rest = ""; + char buffer[4096]; + + while (!in.eof()) { + if (control_pressed) { break; } + + in.read(buffer, 4096); + vector pieces = splitWhiteSpace(rest, buffer, in.gcount()); + + for (int i = 0; i < pieces.size(); i++) { checkName(pieces[i]); names.push_back(pieces[i]); } + } + in.close(); + + if (rest != "") { + vector pieces = splitWhiteSpace(rest); + for (int i = 0; i < pieces.size(); i++) { checkName(pieces[i]); names.push_back(pieces[i]); } + } + + return 0; + } + catch(exception& e) { + errorOut(e, "MothurOut", "readAccnos"); + exit(1); + } +} +/***********************************************************************/ + +int MothurOut::getNumNames(string names){ + try { + int count = 0; + + if(names != ""){ count = 1; for(int i=0;i bigset, vector 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 { filename = getFullPathName(filename); - remove(filename.c_str()); + int error = remove(filename.c_str()); + //if (error != 0) { + // if (errno != ENOENT) { //ENOENT == file does not exist + // string message = "Error deleting file " + filename; + // perror(message.c_str()); + // } + //} + return error; } catch(exception& e) { errorOut(e, "MothurOut", "mothurRemove"); exit(1); } } +/***********************************************************************/ +bool MothurOut::mothurConvert(string item, int& 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::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 { + bool numeric = false; + + if(stringToCheck.find_first_not_of("0123456789.-") == string::npos) { numeric = true; } + + return numeric; + } + catch(exception& e) { + errorOut(e, "MothurOut", "isNumeric1"); + exit(1); + } + +} +/***********************************************************************/ +bool MothurOut::mothurConvert(string item, float& num){ + try { + bool error = false; + + if (isNumeric1(item)) { + convert(item, num); + }else { + num = 0; + error = true; + mothurOut("[ERROR]: cannot convert " + item + " to a float."); mothurOutEndLine(); + commandInputsConvertError = true; + } + + return error; + } + catch(exception& e) { + errorOut(e, "MothurOut", "mothurConvert"); + exit(1); + } +} +/***********************************************************************/ +bool MothurOut::mothurConvert(string item, double& num){ + try { + bool error = false; + + if (isNumeric1(item)) { + convert(item, num); + }else { + num = 0; + error = true; + mothurOut("[ERROR]: cannot convert " + item + " to a double."); mothurOutEndLine(); + commandInputsConvertError = true; + } + + return error; + } + catch(exception& e) { + errorOut(e, "MothurOut", "mothurConvert"); + exit(1); + } +} /**************************************************************************************************/ vector > MothurOut::binomial(int maxOrder){ @@ -1651,6 +2851,9 @@ 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& container, char symbol) { try { + + if (symbol == '-') { splitAtDash(estim, container); return; } + string individual = ""; int estimLength = estim.size(); for(int i=0;i& container) { try { string individual = ""; int estimLength = estim.size(); - for(int i=0;i& container) { try { string individual = ""; int estimLength = estim.size(); + bool prevEscape = false; + /* for(int i=0;i& container) { //This function parses the line options and puts them in a set void MothurOut::splitAtDash(string& estim, set& 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& container) { exit(1); } } + +/***********************************************************************/ +string MothurOut::makeList(vector& names) { + try { + string list = ""; + + if (names.size() == 0) { return list; } + + for (int i = 0; i < names.size()-1; i++) { list += names[i] + ","; } + + //get last name + list += names[names.size()-1]; + + return list; + } + catch(exception& e) { + errorOut(e, "MothurOut", "makeList"); + exit(1); + } +} + /***********************************************************************/ //This function parses the a string and puts peices in a vector void MothurOut::splitAtComma(string& estim, vector& container) { @@ -1804,6 +3100,25 @@ void MothurOut::splitAtComma(string& estim, vector& container) { exit(1); } } +/***********************************************************************/ +//This function splits up the various option parameters +void MothurOut::splitAtChar(string& prefix, string& suffix, char c){ + try { + prefix = suffix.substr(0,suffix.find_first_of(c)); + if ((suffix.find_first_of(c)+2) <= suffix.length()) { //checks to make sure you don't have comma at end of string + suffix = suffix.substr(suffix.find_first_of(c)+1, suffix.length()); + string space = " "; + while(suffix.at(0) == ' ') + suffix = suffix.substr(1, suffix.length()); + }else { suffix = ""; } + + } + catch(exception& e) { + errorOut(e, "MothurOut", "splitAtChar"); + exit(1); + } +} + /***********************************************************************/ //This function splits up the various option parameters @@ -1815,7 +3130,7 @@ void MothurOut::splitAtComma(string& prefix, string& suffix){ string space = " "; while(suffix.at(0) == ' ') suffix = suffix.substr(1, suffix.length()); - } + }else { suffix = ""; } } catch(exception& e) { @@ -1858,6 +3173,35 @@ bool MothurOut::inUsersGroups(string groupname, vector Groups) { exit(1); } } +/**************************************************************************************************/ + +bool MothurOut::inUsersGroups(vector set, vector< vector > 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 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 groupnames, vector Groups) { @@ -2002,6 +3346,273 @@ bool MothurOut::checkReleaseVersion(ifstream& file, string version) { exit(1); } } +/**************************************************************************************************/ +vector MothurOut::getAverages(vector< vector >& dists) { + try{ + vector averages; //averages.resize(numComp, 0.0); + for (int i = 0; i < dists[0].size(); i++) { averages.push_back(0.0); } + + for (int thisIter = 0; thisIter < dists.size(); thisIter++) { + for (int i = 0; i < dists[thisIter].size(); i++) { + averages[i] += dists[thisIter][i]; + } + } + + //finds average. + for (int i = 0; i < averages.size(); i++) { averages[i] /= (double) dists.size(); } + + return averages; + } + catch(exception& e) { + errorOut(e, "MothurOut", "getAverages"); + exit(1); + } +} +/**************************************************************************************************/ +double MothurOut::getAverage(vector dists) { + try{ + double average = 0; + + for (int i = 0; i < dists.size(); i++) { + average += dists[i]; + } + + //finds average. + average /= (double) dists.size(); + + return average; + } + catch(exception& e) { + errorOut(e, "MothurOut", "getAverage"); + exit(1); + } +} + +/**************************************************************************************************/ +vector MothurOut::getStandardDeviation(vector< vector >& dists) { + try{ + + vector averages = getAverages(dists); + + //find standard deviation + vector stdDev; //stdDev.resize(numComp, 0.0); + for (int i = 0; i < dists[0].size(); i++) { stdDev.push_back(0.0); } + + for (int thisIter = 0; thisIter < dists.size(); thisIter++) { //compute the difference of each dist from the mean, and square the result of each + for (int j = 0; j < dists[thisIter].size(); j++) { + stdDev[j] += ((dists[thisIter][j] - averages[j]) * (dists[thisIter][j] - averages[j])); + } + } + for (int i = 0; i < stdDev.size(); i++) { + stdDev[i] /= (double) dists.size(); + stdDev[i] = sqrt(stdDev[i]); + } + + return stdDev; + } + catch(exception& e) { + errorOut(e, "MothurOut", "getAverages"); + exit(1); + } +} +/**************************************************************************************************/ +vector MothurOut::getStandardDeviation(vector< vector >& dists, vector& averages) { + try{ + //find standard deviation + vector stdDev; //stdDev.resize(numComp, 0.0); + for (int i = 0; i < dists[0].size(); i++) { stdDev.push_back(0.0); } + + for (int thisIter = 0; thisIter < dists.size(); thisIter++) { //compute the difference of each dist from the mean, and square the result of each + for (int j = 0; j < dists[thisIter].size(); j++) { + stdDev[j] += ((dists[thisIter][j] - averages[j]) * (dists[thisIter][j] - averages[j])); + } + } + for (int i = 0; i < stdDev.size(); i++) { + stdDev[i] /= (double) dists.size(); + stdDev[i] = sqrt(stdDev[i]); + } + + return stdDev; + } + catch(exception& e) { + errorOut(e, "MothurOut", "getAverages"); + exit(1); + } +} +/**************************************************************************************************/ +vector< vector > MothurOut::getAverages(vector< vector< vector > >& calcDistsTotals, string mode) { + try{ + + vector< vector > calcAverages; //calcAverages.resize(calcDistsTotals[0].size()); + for (int i = 0; i < calcDistsTotals[0].size(); i++) { //initialize sums to zero. + //calcAverages[i].resize(calcDistsTotals[0][i].size()); + vector temp; + for (int j = 0; j < calcDistsTotals[0][i].size(); j++) { + seqDist tempDist; + tempDist.seq1 = calcDistsTotals[0][i][j].seq1; + tempDist.seq2 = calcDistsTotals[0][i][j].seq2; + tempDist.dist = 0.0; + temp.push_back(tempDist); + } + calcAverages.push_back(temp); + } + + if (mode == "average") { + for (int thisIter = 0; thisIter < calcDistsTotals.size(); thisIter++) { //sum all groups dists for each calculator + for (int i = 0; i < calcAverages.size(); i++) { //initialize sums to zero. + for (int j = 0; j < calcAverages[i].size(); j++) { + calcAverages[i][j].dist += calcDistsTotals[thisIter][i][j].dist; + } + } + } + + for (int i = 0; i < calcAverages.size(); i++) { //finds average. + for (int j = 0; j < calcAverages[i].size(); j++) { + calcAverages[i][j].dist /= (float) calcDistsTotals.size(); + } + } + }else { //find median + for (int i = 0; i < calcAverages.size(); i++) { //for each calc + for (int j = 0; j < calcAverages[i].size(); j++) { //for each comparison + vector dists; + for (int thisIter = 0; thisIter < calcDistsTotals.size(); thisIter++) { //for each subsample + dists.push_back(calcDistsTotals[thisIter][i][j].dist); + } + sort(dists.begin(), dists.end()); + calcAverages[i][j].dist = dists[(calcDistsTotals.size()/2)]; + } + } + } + + return calcAverages; + } + catch(exception& e) { + errorOut(e, "MothurOut", "getAverages"); + exit(1); + } +} +/**************************************************************************************************/ +vector< vector > MothurOut::getAverages(vector< vector< vector > >& calcDistsTotals) { + try{ + + vector< vector > calcAverages; //calcAverages.resize(calcDistsTotals[0].size()); + for (int i = 0; i < calcDistsTotals[0].size(); i++) { //initialize sums to zero. + //calcAverages[i].resize(calcDistsTotals[0][i].size()); + vector temp; + for (int j = 0; j < calcDistsTotals[0][i].size(); j++) { + seqDist tempDist; + tempDist.seq1 = calcDistsTotals[0][i][j].seq1; + tempDist.seq2 = calcDistsTotals[0][i][j].seq2; + tempDist.dist = 0.0; + temp.push_back(tempDist); + } + calcAverages.push_back(temp); + } + + + for (int thisIter = 0; thisIter < calcDistsTotals.size(); thisIter++) { //sum all groups dists for each calculator + for (int i = 0; i < calcAverages.size(); i++) { //initialize sums to zero. + for (int j = 0; j < calcAverages[i].size(); j++) { + calcAverages[i][j].dist += calcDistsTotals[thisIter][i][j].dist; + } + } + } + + for (int i = 0; i < calcAverages.size(); i++) { //finds average. + for (int j = 0; j < calcAverages[i].size(); j++) { + calcAverages[i][j].dist /= (float) calcDistsTotals.size(); + } + } + + return calcAverages; + } + catch(exception& e) { + errorOut(e, "MothurOut", "getAverages"); + exit(1); + } +} +/**************************************************************************************************/ +vector< vector > MothurOut::getStandardDeviation(vector< vector< vector > >& calcDistsTotals) { + try{ + + vector< vector > calcAverages = getAverages(calcDistsTotals); + + //find standard deviation + vector< vector > stdDev; + for (int i = 0; i < calcDistsTotals[0].size(); i++) { //initialize sums to zero. + vector temp; + for (int j = 0; j < calcDistsTotals[0][i].size(); j++) { + seqDist tempDist; + tempDist.seq1 = calcDistsTotals[0][i][j].seq1; + tempDist.seq2 = calcDistsTotals[0][i][j].seq2; + tempDist.dist = 0.0; + temp.push_back(tempDist); + } + stdDev.push_back(temp); + } + + for (int thisIter = 0; thisIter < calcDistsTotals.size(); thisIter++) { //compute the difference of each dist from the mean, and square the result of each + for (int i = 0; i < stdDev.size(); i++) { + for (int j = 0; j < stdDev[i].size(); j++) { + stdDev[i][j].dist += ((calcDistsTotals[thisIter][i][j].dist - calcAverages[i][j].dist) * (calcDistsTotals[thisIter][i][j].dist - calcAverages[i][j].dist)); + } + } + } + + for (int i = 0; i < stdDev.size(); i++) { //finds average. + for (int j = 0; j < stdDev[i].size(); j++) { + stdDev[i][j].dist /= (float) calcDistsTotals.size(); + stdDev[i][j].dist = sqrt(stdDev[i][j].dist); + } + } + + return stdDev; + } + catch(exception& e) { + errorOut(e, "MothurOut", "getAverages"); + exit(1); + } +} +/**************************************************************************************************/ +vector< vector > MothurOut::getStandardDeviation(vector< vector< vector > >& calcDistsTotals, vector< vector >& calcAverages) { + try{ + //find standard deviation + vector< vector > stdDev; + for (int i = 0; i < calcDistsTotals[0].size(); i++) { //initialize sums to zero. + vector temp; + for (int j = 0; j < calcDistsTotals[0][i].size(); j++) { + seqDist tempDist; + tempDist.seq1 = calcDistsTotals[0][i][j].seq1; + tempDist.seq2 = calcDistsTotals[0][i][j].seq2; + tempDist.dist = 0.0; + temp.push_back(tempDist); + } + stdDev.push_back(temp); + } + + for (int thisIter = 0; thisIter < calcDistsTotals.size(); thisIter++) { //compute the difference of each dist from the mean, and square the result of each + for (int i = 0; i < stdDev.size(); i++) { + for (int j = 0; j < stdDev[i].size(); j++) { + stdDev[i][j].dist += ((calcDistsTotals[thisIter][i][j].dist - calcAverages[i][j].dist) * (calcDistsTotals[thisIter][i][j].dist - calcAverages[i][j].dist)); + } + } + } + + for (int i = 0; i < stdDev.size(); i++) { //finds average. + for (int j = 0; j < stdDev[i].size(); j++) { + stdDev[i][j].dist /= (float) calcDistsTotals.size(); + stdDev[i][j].dist = sqrt(stdDev[i][j].dist); + } + } + + return stdDev; + } + catch(exception& e) { + errorOut(e, "MothurOut", "getAverages"); + exit(1); + } +} + /**************************************************************************************************/ bool MothurOut::isContainingOnlyDigits(string input) { try{ @@ -2020,8 +3631,93 @@ bool MothurOut::isContainingOnlyDigits(string input) { } } /**************************************************************************************************/ - - +int MothurOut::removeConfidences(string& tax) { + try { + + string taxon; + string newTax = ""; + + while (tax.find_first_of(';') != -1) { + + if (control_pressed) { return 0; } + + //get taxon + taxon = tax.substr(0,tax.find_first_of(';')); + + int pos = taxon.find_last_of('('); + if (pos != -1) { + //is it a number? + int pos2 = taxon.find_last_of(')'); + if (pos2 != -1) { + string confidenceScore = taxon.substr(pos+1, (pos2-(pos+1))); + if (isNumeric1(confidenceScore)) { + taxon = taxon.substr(0, pos); //rip off confidence + } + } + } + taxon += ";"; + + tax = tax.substr(tax.find_first_of(';')+1, tax.length()); + newTax += taxon; + } + + tax = newTax; + + return 0; + } + catch(exception& e) { + errorOut(e, "MothurOut", "removeConfidences"); + exit(1); + } +} +/**************************************************************************************************/ +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& 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); + } +} +/**************************************************************************************************/