#include "phylosummary.h"
#include "knn.h"
-//**********************************************************************************************************************
+//**********************************************************************************************************************
+vector<string> ClassifySeqsCommand::getValidParameters(){
+ try {
+ string AlignArray[] = {"template","fasta","name","group","search","ksize","method","processors","taxonomy","match","mismatch","gapopen","gapextend","numwanted","cutoff","probs","iters", "outputdir","inputdir"};
+ vector<string> myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string)));
+ return myArray;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ClassifySeqsCommand", "getValidParameters");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+ClassifySeqsCommand::ClassifySeqsCommand(){
+ try {
+ abort = true;
+ //initialize outputTypes
+ vector<string> tempOutNames;
+ outputTypes["taxonomy"] = tempOutNames;
+ outputTypes["taxsummary"] = tempOutNames;
+ outputTypes["matchdist"] = tempOutNames;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ClassifySeqsCommand", "ClassifySeqsCommand");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+vector<string> ClassifySeqsCommand::getRequiredParameters(){
+ try {
+ string Array[] = {"fasta","template","taxonomy"};
+ vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+ return myArray;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ClassifySeqsCommand", "getRequiredParameters");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+vector<string> ClassifySeqsCommand::getRequiredFiles(){
+ try {
+ vector<string> myArray;
+ return myArray;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ClassifySeqsCommand", "getRequiredFiles");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
ClassifySeqsCommand::ClassifySeqsCommand(string option) {
try {
abort = false;
if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
}
+ //initialize outputTypes
+ vector<string> tempOutNames;
+ outputTypes["taxonomy"] = tempOutNames;
+ outputTypes["taxsummary"] = tempOutNames;
+ outputTypes["matchdist"] = tempOutNames;
+
//if the user changes the output directory command factory will send this info to us in the output parameter
outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; }
if (m->getDefaultPath() != "") { //default path is set
string tryPath = m->getDefaultPath() + m->getSimpleName(fastaFileNames[i]);
m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();
- ableToOpen = m->openInputFile(tryPath, in, "noerror");
+ ifstream in2;
+ ableToOpen = m->openInputFile(tryPath, in2, "noerror");
+ in2.close();
+ fastaFileNames[i] = tryPath;
+ }
+ }
+
+ if (ableToOpen == 1) {
+ if (m->getOutputDir() != "") { //default path is set
+ string tryPath = m->getOutputDir() + m->getSimpleName(fastaFileNames[i]);
+ m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();
+ ifstream in2;
+ ableToOpen = m->openInputFile(tryPath, in2, "noerror");
+ in2.close();
fastaFileNames[i] = tryPath;
}
}
+
in.close();
if (ableToOpen == 1) {
if (m->getDefaultPath() != "") { //default path is set
string tryPath = m->getDefaultPath() + m->getSimpleName(namefileNames[i]);
m->mothurOut("Unable to open " + namefileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();
- ableToOpen = m->openInputFile(tryPath, in, "noerror");
+ ifstream in2;
+ ableToOpen = m->openInputFile(tryPath, in2, "noerror");
+ in2.close();
+ namefileNames[i] = tryPath;
+ }
+ }
+
+ if (ableToOpen == 1) {
+ if (m->getOutputDir() != "") { //default path is set
+ string tryPath = m->getOutputDir() + m->getSimpleName(namefileNames[i]);
+ m->mothurOut("Unable to open " + namefileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();
+ ifstream in2;
+ ableToOpen = m->openInputFile(tryPath, in2, "noerror");
+ in2.close();
namefileNames[i] = tryPath;
}
}
if (m->getDefaultPath() != "") { //default path is set
string tryPath = m->getDefaultPath() + m->getSimpleName(groupfileNames[i]);
m->mothurOut("Unable to open " + groupfileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();
- ableToOpen = m->openInputFile(tryPath, in, "noerror");
+ ifstream in2;
+ ableToOpen = m->openInputFile(tryPath, in2, "noerror");
+ in2.close();
groupfileNames[i] = tryPath;
}
}
+
+ if (ableToOpen == 1) {
+ if (m->getOutputDir() != "") { //default path is set
+ string tryPath = m->getOutputDir() + m->getSimpleName(groupfileNames[i]);
+ m->mothurOut("Unable to open " + groupfileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();
+ ifstream in2;
+ ableToOpen = m->openInputFile(tryPath, in2, "noerror");
+ in2.close();
+ groupfileNames[i] = tryPath;
+ }
+ }
+
in.close();
if (ableToOpen == 1) {
if (m->control_pressed) { delete classify; return 0; }
- vector<string> outputNames;
for (int s = 0; s < fastaFileNames.size(); s++) {
if ((method == "knn") && (search == "distance")) {
string DistName = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])) + "match.dist";
- classify->setDistName(DistName); outputNames.push_back(DistName);
+ classify->setDistName(DistName); outputNames.push_back(DistName); outputTypes["matchdist"].push_back(DistName);
}
- outputNames.push_back(newTaxonomyFile);
- outputNames.push_back(taxSummary);
+ outputNames.push_back(newTaxonomyFile); outputTypes["taxonomy"].push_back(newTaxonomyFile);
+ outputNames.push_back(taxSummary); outputTypes["taxsummary"].push_back(taxSummary);
int start = time(NULL);
int numFastaSeqs = 0;
int outMode=MPI_MODE_CREATE|MPI_MODE_WRONLY;
int inMode=MPI_MODE_RDONLY;
- //char* outNewTax = new char[newTaxonomyFile.length()];
- //memcpy(outNewTax, newTaxonomyFile.c_str(), newTaxonomyFile.length());
-
char outNewTax[1024];
strcpy(outNewTax, newTaxonomyFile.c_str());
-
- //char* outTempTax = new char[tempTaxonomyFile.length()];
- //memcpy(outTempTax, tempTaxonomyFile.c_str(), tempTaxonomyFile.length());
char outTempTax[1024];
strcpy(outTempTax, tempTaxonomyFile.c_str());
-
- //char* inFileName = new char[fastaFileNames[s].length()];
- //memcpy(inFileName, fastaFileNames[s].c_str(), fastaFileNames[s].length());
char inFileName[1024];
strcpy(inFileName, fastaFileNames[s].c_str());
MPI_File_open(MPI_COMM_WORLD, outNewTax, outMode, MPI_INFO_NULL, &outMPINewTax);
MPI_File_open(MPI_COMM_WORLD, outTempTax, outMode, MPI_INFO_NULL, &outMPITempTax);
- //delete outNewTax;
- //delete outTempTax;
- //delete inFileName;
-
- if (m->control_pressed) { MPI_File_close(&inMPI); MPI_File_close(&outMPINewTax); MPI_File_close(&outMPITempTax); delete classify; return 0; }
+ if (m->control_pressed) { outputTypes.clear(); MPI_File_close(&inMPI); MPI_File_close(&outMPINewTax); MPI_File_close(&outMPITempTax); delete classify; return 0; }
if (pid == 0) { //you are the root process
//align your part
driverMPI(startIndex, numSeqsPerProcessor, inMPI, outMPINewTax, outMPITempTax, MPIPos);
- if (m->control_pressed) { MPI_File_close(&inMPI); MPI_File_close(&outMPINewTax); MPI_File_close(&outMPITempTax); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } delete classify; return 0; }
+ if (m->control_pressed) { outputTypes.clear(); MPI_File_close(&inMPI); MPI_File_close(&outMPINewTax); MPI_File_close(&outMPITempTax); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } delete classify; return 0; }
for (int i = 1; i < processors; i++) {
int done;
//align your part
driverMPI(startIndex, numSeqsPerProcessor, inMPI, outMPINewTax, outMPITempTax, MPIPos);
- if (m->control_pressed) { MPI_File_close(&inMPI); MPI_File_close(&outMPINewTax); MPI_File_close(&outMPITempTax); delete classify; return 0; }
+ if (m->control_pressed) { outputTypes.clear(); MPI_File_close(&inMPI); MPI_File_close(&outMPINewTax); MPI_File_close(&outMPITempTax); delete classify; return 0; }
int done = 0;
MPI_Send(&done, 1, MPI_INT, 0, tag, MPI_COMM_WORLD);
PhyloSummary taxaSum(taxonomyFileName, group);
- if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } delete classify; return 0; }
+ if (m->control_pressed) { outputTypes.clear(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } delete classify; return 0; }
if (namefile == "") { taxaSum.summarize(tempTaxonomyFile); }
else {
}
remove(tempTaxonomyFile.c_str());
- if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } delete classify; return 0; }
+ if (m->control_pressed) { outputTypes.clear(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } delete classify; return 0; }
//print summary file
ofstream outTaxTree;
//read taxfile - this reading and rewriting is done to preserve the confidence scores.
string name, taxon;
while (!inTax.eof()) {
- if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } remove(unclass.c_str()); delete classify; return 0; }
+ if (m->control_pressed) { outputTypes.clear(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } remove(unclass.c_str()); delete classify; return 0; }
inTax >> name >> taxon; m->gobble(inTax);
out.close();
exit(0);
- }else { m->mothurOut("unable to spawn the necessary processes."); m->mothurOutEndLine(); exit(0); }
+ }else {
+ m->mothurOut("[ERROR]: unable to spawn the necessary processes."); m->mothurOutEndLine();
+ for (int i = 0; i < processIDS.size(); i++) { kill (processIDS[i], SIGINT); }
+ exit(0);
+ }
}
//force parent to wait until all the processes are done
}
delete candidateSeq;
- unsigned long int pos = inFASTA.tellg();
- if ((pos == -1) || (pos >= filePos->end)) { break; }
+ #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
+ unsigned long int pos = inFASTA.tellg();
+ if ((pos == -1) || (pos >= filePos->end)) { break; }
+ #else
+ if (inFASTA.eof()) { break; }
+ #endif
//report progress
if((count) % 100 == 0){ m->mothurOut("Processing sequence: " + toString(count)); m->mothurOutEndLine(); }