X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=mothurout.cpp;h=81436871d6fd14b8f40c7101b397c1637887bc96;hp=96c7305b6a1fb50f42f9c2a650d0c854ccbb6f2c;hb=fefd5ee1517abd3bc38b469cb2dffc85a1571c7e;hpb=ad4f75fd7c938090d3b1ce4cfefcc21edf1869eb diff --git a/mothurout.cpp b/mothurout.cpp index 96c7305..8143687 100644 --- a/mothurout.cpp +++ b/mothurout.cpp @@ -588,6 +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 { @@ -759,6 +779,8 @@ string MothurOut::getPathName(string longName){ bool MothurOut::dirCheck(string& dirName){ try { + if (dirName == "") { return false; } + string tag = ""; #ifdef USE_MPI int pid; @@ -777,7 +799,7 @@ bool MothurOut::dirCheck(string& dirName){ //test to make sure directory exists dirName = getFullPathName(dirName); - string outTemp = dirName + tag + "temp"; + string outTemp = dirName + tag + "temp"+ toString(time(NULL)); ofstream out; out.open(outTemp.c_str(), ios::trunc); if(!out) { @@ -796,6 +818,39 @@ 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){ @@ -1087,6 +1142,105 @@ int MothurOut::openInputFile(string fileName, ifstream& fileHandle){ exit(1); } } +/***********************************************************************/ +int MothurOut::openInputFileBinary(string fileName, ifstream& fileHandle){ + try { + + //get full path name + string completeFileName = getFullPathName(fileName); +#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")) { + string tempName = string(tmpnam(0)); + mkfifo(tempName.c_str(), 0666); + int fork_result = fork(); + if (fork_result < 0) { + cerr << "Error forking.\n"; + exit(1); + } else if (fork_result == 0) { + string command = (endsWith(completeFileName, ".gz") ? "zcat " : "bzcat ") + completeFileName + string(" > ") + tempName; + cerr << "Decompressing " << completeFileName << " via temporary named pipe " << tempName << "\n"; + system(command.c_str()); + cerr << "Done decompressing " << completeFileName << "\n"; + mothurRemove(tempName); + exit(EXIT_SUCCESS); + } else { + cerr << "waiting on child process " << fork_result << "\n"; + completeFileName = tempName; + } + } +#endif +#endif + + fileHandle.open(completeFileName.c_str(), ios::binary); + if(!fileHandle) { + mothurOut("[ERROR]: Could not open " + completeFileName); mothurOutEndLine(); + return 1; + } + else { + //check for blank file + gobble(fileHandle); + if (fileHandle.eof()) { mothurOut("[ERROR]: " + completeFileName + " is blank. Please correct."); mothurOutEndLine(); } + + return 0; + } + } + catch(exception& e) { + errorOut(e, "MothurOut", "openInputFileBinary"); + exit(1); + } +} +/***********************************************************************/ +int MothurOut::openInputFileBinary(string fileName, ifstream& fileHandle, string noerror){ + try { + + //get full path name + string completeFileName = getFullPathName(fileName); +#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")) { + string tempName = string(tmpnam(0)); + mkfifo(tempName.c_str(), 0666); + int fork_result = fork(); + if (fork_result < 0) { + cerr << "Error forking.\n"; + exit(1); + } else if (fork_result == 0) { + string command = (endsWith(completeFileName, ".gz") ? "zcat " : "bzcat ") + completeFileName + string(" > ") + tempName; + cerr << "Decompressing " << completeFileName << " via temporary named pipe " << tempName << "\n"; + system(command.c_str()); + cerr << "Done decompressing " << completeFileName << "\n"; + mothurRemove(tempName); + exit(EXIT_SUCCESS); + } else { + cerr << "waiting on child process " << fork_result << "\n"; + completeFileName = tempName; + } + } +#endif +#endif + + fileHandle.open(completeFileName.c_str(), ios::binary); + if(!fileHandle) { + //mothurOut("[ERROR]: Could not open " + completeFileName); mothurOutEndLine(); + return 1; + } + else { + //check for blank file + gobble(fileHandle); + //if (fileHandle.eof()) { mothurOut("[ERROR]: " + completeFileName + " is blank. Please correct."); mothurOutEndLine(); } + + return 0; + } + } + catch(exception& e) { + errorOut(e, "MothurOut", "openInputFileBinary - no error"); + exit(1); + } +} + /***********************************************************************/ int MothurOut::renameFile(string oldName, string newName){ @@ -1161,7 +1315,48 @@ 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{ @@ -1169,8 +1364,8 @@ int MothurOut::appendFiles(string temp, string filename) { ifstream input; //open output file in append mode - openOutputFileAppend(filename, output); - int ableToOpen = openInputFile(temp, input, "no error"); + openOutputFileBinaryAppend(filename, output); + int ableToOpen = openInputFileBinary(temp, input, "no error"); //int ableToOpen = openInputFile(temp, input); int numLines = 0; @@ -1195,6 +1390,36 @@ int MothurOut::appendFiles(string temp, string filename) { exit(1); } } +/**************************************************************************************************/ +int MothurOut::appendBinaryFiles(string temp, string filename) { + try{ + ofstream output; + ifstream input; + + //open output file in append mode + openOutputFileBinaryAppend(filename, output); + int ableToOpen = openInputFileBinary(temp, input, "no error"); + + if (ableToOpen == 0) { //you opened it + + char buffer[4096]; + while (!input.eof()) { + input.read(buffer, 4096); + output.write(buffer, input.gcount()); + } + input.close(); + } + + output.close(); + + return ableToOpen; + } + catch(exception& e) { + errorOut(e, "MothurOut", "appendBinaryFiles"); + exit(1); + } +} + /**************************************************************************************************/ int MothurOut::appendFilesWithoutHeaders(string temp, string filename) { try{ @@ -1808,6 +2033,7 @@ 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; } @@ -1832,7 +2058,7 @@ 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; } @@ -1860,7 +2086,7 @@ 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; @@ -1868,6 +2094,8 @@ 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(); } @@ -2502,6 +2730,92 @@ int MothurOut::getNumChar(string line, char c){ exit(1); } } +/***********************************************************************/ +string MothurOut::getSimpleLabel(string label){ + try { + string simple = ""; + + //remove OTU or phylo tag + string newLabel1 = ""; + for (int i = 0; i < label.length(); i++) { + if(label[i]>47 && label[i]<58) { //is a digit + newLabel1 += label[i]; + } + } + + int num1; + mothurConvert(newLabel1, num1); + + simple = toString(num1); + + return simple; + } + catch(exception& e) { + errorOut(e, "MothurOut", "isLabelEquivalent"); + exit(1); + } +} +/***********************************************************************/ +string MothurOut::mothurGetpid(int threadID){ + try { + + string pid = ""; +#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) + + pid += toString(getpid()); if(debug) { mothurOut("[DEBUG]: " + pid + "\n"); } + //remove any weird chars + string pid1 = ""; + for (int i = 0; i < pid.length(); i++) { + if(pid[i]>47 && pid[i]<58) { //is a digit + pid1 += pid[i]; + } + } + pid = pid1; +#else + pid += toString(threadID); +#endif + return pid; + } + catch(exception& e) { + errorOut(e, "MothurOut", "mothurGetpid"); + exit(1); + } +} + +/***********************************************************************/ + +bool MothurOut::isLabelEquivalent(string label1, string label2){ + try { + bool same = false; + + //remove OTU or phylo tag + string newLabel1 = ""; + for (int i = 0; i < label1.length(); i++) { + if(label1[i]>47 && label1[i]<58) { //is a digit + newLabel1 += label1[i]; + } + } + + string newLabel2 = ""; + for (int i = 0; i < label2.length(); i++) { + if(label2[i]>47 && label2[i]<58) { //is a digit + newLabel2 += label2[i]; + } + } + + int num1, num2; + mothurConvert(newLabel1, num1); + mothurConvert(newLabel2, num2); + + if (num1 == num2) { same = true; } + + return same; + } + catch(exception& e) { + errorOut(e, "MothurOut", "isLabelEquivalent"); + exit(1); + } +} //********************************************************************************************************************** bool MothurOut::isSubset(vector bigset, vector subset) { try { @@ -2509,7 +2823,7 @@ bool MothurOut::isSubset(vector bigset, vector subset) { if (subset.size() > bigset.size()) { return false; } - //check if each guy in suset is also in bigset + //check if each guy in subset is also in bigset for (int i = 0; i < subset.size(); i++) { bool match = false; for (int j = 0; j < bigset.size(); j++) { @@ -2767,7 +3081,50 @@ 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; @@ -2814,6 +3171,64 @@ void MothurOut::getNumSeqs(ifstream& file, int& numSeqs){ } } /***********************************************************************/ +bool MothurOut::checkLocations(string& filename, string inputDir){ + try { + filename = getFullPathName(filename); + + int ableToOpen; + ifstream in; + ableToOpen = openInputFile(filename, in, "noerror"); + in.close(); + + //if you can't open it, try input location + if (ableToOpen == 1) { + if (inputDir != "") { //default path is set + string tryPath = inputDir + getSimpleName(filename); + mothurOut("Unable to open " + filename + ". Trying input directory " + tryPath); mothurOutEndLine(); + ifstream in2; + ableToOpen = openInputFile(tryPath, in2, "noerror"); + in2.close(); + filename = tryPath; + } + } + + //if you can't open it, try default location + if (ableToOpen == 1) { + if (getDefaultPath() != "") { //default path is set + string tryPath = getDefaultPath() + getSimpleName(filename); + mothurOut("Unable to open " + filename + ". Trying default " + tryPath); mothurOutEndLine(); + ifstream in2; + ableToOpen = openInputFile(tryPath, in2, "noerror"); + in2.close(); + filename = tryPath; + } + } + + //if you can't open it its not in current working directory or inputDir, try mothur excutable location + if (ableToOpen == 1) { + string exepath = argv; + string tempPath = exepath; + for (int i = 0; i < exepath.length(); i++) { tempPath[i] = tolower(exepath[i]); } + exepath = exepath.substr(0, (tempPath.find_last_of('m'))); + + string tryPath = getFullPathName(exepath) + getSimpleName(filename); + mothurOut("Unable to open " + filename + ". Trying mothur's executable location " + tryPath); mothurOutEndLine(); + ifstream in2; + ableToOpen = openInputFile(tryPath, in2, "noerror"); + in2.close(); + filename = tryPath; + } + + if (ableToOpen == 1) { mothurOut("Unable to open " + filename + "."); mothurOutEndLine(); return false; } + + return true; + } + catch(exception& e) { + errorOut(e, "MothurOut", "checkLocations"); + exit(1); + } +} +/***********************************************************************/ //This function parses the estimator options and puts them in a vector void MothurOut::splitAtChar(string& estim, vector& container, char symbol) { @@ -3184,6 +3599,26 @@ bool MothurOut::inUsersGroups(vector groupnames, vector Groups) exit(1); } } +/**************************************************************************************************/ +//removes entries that are only white space +int MothurOut::removeBlanks(vector& tempVector) { + try { + vector newVector; + for (int i = 0; i < tempVector.size(); i++) { + bool isBlank = true; + for (int j = 0; j < tempVector[i].length(); j++) { + if (!isspace(tempVector[i][j])) { isBlank = false; j+= tempVector[i].length(); } //contains non space chars, break out and save + } + if (!isBlank) { newVector.push_back(tempVector[i]); } + } + tempVector = newVector; + return 0; + } + catch(exception& e) { + errorOut(e, "MothurOut", "removeBlanks"); + exit(1); + } +} /***********************************************************************/ //this function determines if the user has given us labels that are smaller than the given label. //if so then it returns true so that the calling function can run the previous valid distance. @@ -3402,7 +3837,7 @@ vector MothurOut::getStandardDeviation(vector< vector >& dists, return stdDev; } catch(exception& e) { - errorOut(e, "MothurOut", "getAverages"); + errorOut(e, "MothurOut", "getStandardDeviation"); exit(1); } } @@ -3685,6 +4120,45 @@ 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); + } +} + +/**************************************************************************************************/