X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=mothurout.cpp;h=713bafd0c2a79ec637abdf9d481a0c96c183ee77;hp=8892febb384cbb07233858f2c6b608f8153ca09f;hb=d1c97b8c04bb75faca1e76ffad60b37a4d789d3d;hpb=a54ba6143022dc7294f4fdc468fc10b627c64b0e diff --git a/mothurout.cpp b/mothurout.cpp index 8892feb..713bafd 100644 --- a/mothurout.cpp +++ b/mothurout.cpp @@ -348,6 +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 @@ -567,6 +588,26 @@ int MothurOut::openOutputFileAppend(string fileName, ofstream& fileHandle){ exit(1); } } +/***********************************************************************/ +int MothurOut::openOutputFileBinaryAppend(string fileName, ofstream& fileHandle){ + try { + fileName = getFullPathName(fileName); + + fileHandle.open(fileName.c_str(), ios::app | ios::binary); + if(!fileHandle) { + mothurOut("[ERROR]: Could not open " + fileName); mothurOutEndLine(); + return 1; + } + else { + return 0; + } + } + catch(exception& e) { + errorOut(e, "MothurOut", "openOutputFileAppend"); + exit(1); + } +} + /***********************************************************************/ void MothurOut::gobble(istream& f){ try { @@ -775,6 +816,39 @@ bool MothurOut::dirCheck(string& dirName){ } } +//********************************************************************************************************************** + +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){ @@ -1140,7 +1214,48 @@ int MothurOut::openOutputFile(string fileName, ofstream& fileHandle){ } } +/***********************************************************************/ +int MothurOut::openOutputFileBinary(string fileName, ofstream& fileHandle){ + try { + + string completeFileName = getFullPathName(fileName); +#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) +#ifdef USE_COMPRESSION + // check for gzipped file + if (endsWith(completeFileName, ".gz") || endsWith(completeFileName, ".bz2")) { + string tempName = string(tmpnam(0)); + mkfifo(tempName.c_str(), 0666); + cerr << "Compressing " << completeFileName << " via temporary named pipe " << tempName << "\n"; + int fork_result = fork(); + if (fork_result < 0) { + cerr << "Error forking.\n"; + exit(1); + } else if (fork_result == 0) { + string command = string(endsWith(completeFileName, ".gz") ? "gzip" : "bzip2") + " -v > " + completeFileName + string(" < ") + tempName; + system(command.c_str()); + exit(0); + } else { + completeFileName = tempName; + } + } +#endif +#endif + fileHandle.open(completeFileName.c_str(), ios::trunc | ios::binary); + if(!fileHandle) { + mothurOut("[ERROR]: Could not open " + completeFileName); mothurOutEndLine(); + return 1; + } + else { + return 0; + } + } + catch(exception& e) { + errorOut(e, "MothurOut", "openOutputFileBinary"); + exit(1); + } + +} /**************************************************************************************************/ int MothurOut::appendFiles(string temp, string filename) { try{ @@ -1296,15 +1411,15 @@ 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"); @@ -1313,9 +1428,9 @@ 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); @@ -1325,8 +1440,10 @@ 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; @@ -1337,6 +1454,67 @@ 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 { @@ -1724,6 +1902,7 @@ int MothurOut::readTax(string namefile, map& taxMap) { bool pairDone = false; bool columnOne = true; string firstCol, secondCol; + bool error = false; while (!in.eof()) { if (control_pressed) { break; } @@ -1748,7 +1927,7 @@ int MothurOut::readTax(string namefile, map& taxMap) { 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; + mothurOut("[ERROR]: " + firstCol + " is already in your taxonomy file, names must be unique.\n"); error = true; } pairDone = false; } @@ -1776,7 +1955,7 @@ int MothurOut::readTax(string namefile, map& taxMap) { 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; + mothurOut("[ERROR]: " + firstCol + " is already in your taxonomy file, names must be unique./n"); error = true; } pairDone = false; @@ -1784,6 +1963,8 @@ int MothurOut::readTax(string namefile, map& taxMap) { } } + if (error) { control_pressed = true; } + if (debug) { mothurOut("[DEBUG]: numSeqs saved = '" + toString(taxMap.size()) + "'\n"); } return taxMap.size(); } @@ -2219,9 +2400,11 @@ map MothurOut::readNames(string namefile, unsigned long int& numSeq /************************************************************/ int MothurOut::checkName(string& name) { try { - for (int i = 0; i < name.length(); i++) { - if (name[i] == ':') { name[i] = '_'; changedSeqNames = true; } - } + if (modifyNames) { + for (int i = 0; i < name.length(); i++) { + if (name[i] == ':') { name[i] = '_'; changedSeqNames = true; } + } + } return 0; } catch(exception& e) { @@ -2323,7 +2506,9 @@ set MothurOut::readAccnos(string accnosfile){ 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]); } + for (int i = 0; i < pieces.size(); i++) { checkName(pieces[i]); + names.insert(pieces[i]); + } } in.close(); @@ -2679,7 +2864,50 @@ unsigned int MothurOut::fromBase36(string base36){ } } /***********************************************************************/ - +string MothurOut::findEdianness() { + try { + // find real endian type + unsigned char EndianTest[2] = {1,0}; + short x = *(short *)EndianTest; + + string endianType = "unknown"; + if(x == 1) { endianType = "BIG_ENDIAN"; } + else { endianType = "LITTLE_ENDIAN"; } + + return endianType; + } + catch(exception& e) { + errorOut(e, "MothurOut", "findEdianness"); + exit(1); + } +} +/***********************************************************************/ +double MothurOut::median(vector x) { + try { + double value = 0.0; + + if (x.size() == 0) { } //error + else { + //For example, if a < b < c, then the median of the list {a, b, c} is b, and, if a < b < c < d, then the median of the list {a, b, c, d} is the mean of b and c; i.e., it is (b + c)/2. + sort(x.begin(), x.end()); + //is x.size even? + if ((x.size()%2) == 0) { //size() is even. median = average of 2 midpoints + int midIndex1 = (x.size()/2)-1; + int midIndex2 = (x.size()/2); + value = (x[midIndex1]+ x[midIndex2]) / 2.0; + }else { + int midIndex = (x.size()/2); + value = x[midIndex]; + } + } + return value; + } + catch(exception& e) { + errorOut(e, "MothurOut", "median"); + exit(1); + } +} +/***********************************************************************/ int MothurOut::factorial(int num){ try { int total = 1; @@ -3247,6 +3475,26 @@ vector MothurOut::getAverages(vector< vector >& dists) { 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{ @@ -3294,7 +3542,7 @@ vector MothurOut::getStandardDeviation(vector< vector >& dists, return stdDev; } catch(exception& e) { - errorOut(e, "MothurOut", "getAverages"); + errorOut(e, "MothurOut", "getStandardDeviation"); exit(1); } } @@ -3577,6 +3825,44 @@ double MothurOut::getStandardDeviation(vector& featureVector){ } } /**************************************************************************************************/ +// returns largest value in vector +double MothurOut::max(vector& featureVector){ + try { + if (featureVector.size() == 0) { mothurOut("[ERROR]: vector size = 0!\n"); control_pressed=true; return 0.0; } + + //finds largest + double largest = featureVector[0]; + for (int i = 1; i < featureVector.size(); i++) { + if (featureVector[i] > largest) { largest = featureVector[i]; } + } + + return largest; + } + catch(exception& e) { + errorOut(e, "MothurOut", "max"); + exit(1); + } +} +/**************************************************************************************************/ +// returns smallest value in vector +double MothurOut::min(vector& featureVector){ + try { + if (featureVector.size() == 0) { mothurOut("[ERROR]: vector size = 0!\n"); control_pressed=true; return 0.0; } + + //finds smallest + double smallest = featureVector[0]; + for (int i = 1; i < featureVector.size(); i++) { + if (featureVector[i] < smallest) { smallest = featureVector[i]; } + } + + return smallest; + } + catch(exception& e) { + errorOut(e, "MothurOut", "min"); + exit(1); + } +} +/**************************************************************************************************/