X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=readphylip.cpp;h=6de23e83279482127f5f261c53f94c345585455d;hp=174b7e3c510c1492043e21b3f94d3eb1cad76ee0;hb=1a20e24ee786195ab0e1cccd4f5aede7a88f3f4e;hpb=154e089bcd37c2c2f773e53ffb88a20170b27037 diff --git a/readphylip.cpp b/readphylip.cpp index 174b7e3..6de23e8 100644 --- a/readphylip.cpp +++ b/readphylip.cpp @@ -13,174 +13,382 @@ /***********************************************************************/ ReadPhylipMatrix::ReadPhylipMatrix(string distFile){ - - successOpen = openInputFile(distFile, fileHandle); - + + successOpen = m->openInputFile(distFile, fileHandle); + sim=false; + } - /***********************************************************************/ -void ReadPhylipMatrix::read(NameAssignment* nameMap){ - try { +ReadPhylipMatrix::ReadPhylipMatrix(string distFile, bool s){ - float distance; - int square, nseqs; - string name; - vector matrixNames; - - fileHandle >> nseqs >> name; + successOpen = m->openInputFile(distFile, fileHandle); + sim=s; +} - matrixNames.push_back(name); - if(nameMap == NULL){ - list = new ListVector(nseqs); - list->set(0, name); - } - else{ - list = new ListVector(nameMap->getListVector()); - if(nameMap->count(name)==0){ cout << "Error: Sequence '" << name << "' was not found in the names file, please correct" << endl; } - } - - char d; - while((d=fileHandle.get()) != EOF){ - - if(isalnum(d)){ - square = 1; - fileHandle.putback(d); - for(int i=0;i> distance; - } - break; - } - if(d == '\n'){ - square = 0; - break; - } - } - - Progress* reading; - - if(square == 0){ +/***********************************************************************/ - reading = new Progress("Reading matrix: ", nseqs * (nseqs - 1) / 2); - - int index = 0; - - for(int i=1;i> name; - matrixNames.push_back(name); - - //there's A LOT of repeated code throughout this method... - if(nameMap == NULL){ - list->set(i, name); - - for(int j=0;j> distance; - - if (distance == -1) { distance = 1000000; } +int ReadPhylipMatrix::read(NameAssignment* nameMap){ + try { + + float distance; + int square, nseqs; + string name; + vector matrixNames; - if(distance < cutoff){ - PCell value(i, j, distance); - D->addCell(value); - } - index++; - reading->update(index); - } - - } - else{ - if(nameMap->count(name)==0){ cout << "Error: Sequence '" << name << "' was not found in the names file, please correct" << endl; } - - for(int j=0;j> distance; - - if (distance == -1) { distance = 1000000; } - - if(distance < cutoff){ - PCell value(nameMap->get(matrixNames[i]), nameMap->get(matrixNames[j]), distance); - D->addCell(value); - } - index++; - reading->update(index); - } - } - } - } - else{ - - reading = new Progress("Reading matrix: ", nseqs * nseqs); + string numTest; + fileHandle >> numTest >> name; - int index = nseqs; - - for(int i=1;i> name; - matrixNames.push_back(name); - - if(nameMap == NULL){ - list->set(i, name); - for(int j=0;j> distance; - - if (distance == -1) { distance = 1000000; } - - if(distance < cutoff && j < i){ - PCell value(i, j, distance); - D->addCell(value); - } - index++; - reading->update(index); - } - - } - else{ - if(nameMap->count(name)==0){ cout << "Error: Sequence '" << name << "' was not found in the names file, please correct" << endl; } - - for(int j=0;j> distance; + if (!m->isContainingOnlyDigits(numTest)) { m->mothurOut("[ERROR]: expected a number and got " + numTest + ", quitting."); m->mothurOutEndLine(); exit(1); } + else { convert(numTest, nseqs); } - if (distance == -1) { distance = 1000000; } - - if(distance < cutoff && j < i){ - PCell value(nameMap->get(matrixNames[i]), nameMap->get(matrixNames[j]), distance); - D->addCell(value); - } - index++; - reading->update(index); - } - } - } - } - reading->finish(); - delete reading; + matrixNames.push_back(name); - list->setLabel("0"); - fileHandle.close(); + if(nameMap == NULL){ + list = new ListVector(nseqs); + list->set(0, name); + } + else{ + list = new ListVector(nameMap->getListVector()); + if(nameMap->count(name)==0){ m->mothurOut("Error: Sequence '" + name + "' was not found in the names file, please correct"); m->mothurOutEndLine(); } + } + + char d; + while((d=fileHandle.get()) != EOF){ + + if(isalnum(d)){ + square = 1; + fileHandle.putback(d); + for(int i=0;i> distance; + } + break; + } + if(d == '\n'){ + square = 0; + break; + } + } + + Progress* reading; + DMatrix->resize(nseqs); + + if(square == 0){ - if(nameMap != NULL){ - for(int i=0;ierase(matrixNames[i]); - } - if(nameMap->size() > 0){ - //should probably tell them what is missing if we missed something - cout << "missed something" << '\t' << nameMap->size() << endl; - } - } + reading = new Progress("Reading matrix: ", nseqs * (nseqs - 1) / 2); + + int index = 0; + + for(int i=1;icontrol_pressed) { fileHandle.close(); delete reading; return 0; } + + fileHandle >> name; + matrixNames.push_back(name); + + + //there's A LOT of repeated code throughout this method... + if(nameMap == NULL){ + list->set(i, name); + + for(int j=0;jcontrol_pressed) { delete reading; fileHandle.close(); return 0; } + + fileHandle >> distance; + + if (distance == -1) { distance = 1000000; } + else if (sim) { distance = 1.0 - distance; } //user has entered a sim matrix that we need to convert. + + if(distance < cutoff){ + PDistCell value(i, distance); + DMatrix->addCell(j, value); + } + index++; + reading->update(index); + } + + } + else{ + if(nameMap->count(name)==0){ m->mothurOut("Error: Sequence '" + name + "' was not found in the names file, please correct"); m->mothurOutEndLine(); } + + for(int j=0;j> distance; + + if (m->control_pressed) { delete reading; fileHandle.close(); return 0; } + + if (distance == -1) { distance = 1000000; } + else if (sim) { distance = 1.0 - distance; } //user has entered a sim matrix that we need to convert. + + if(distance < cutoff){ + PDistCell value(nameMap->get(matrixNames[i]), distance); + DMatrix->addCell(nameMap->get(matrixNames[j]), value); + } + index++; + reading->update(index); + } + } + } + } + else{ - } - catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the ReadPhylipMatrix class Function read. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the ReadPhylipMatrix class function read. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } -} + reading = new Progress("Reading matrix: ", nseqs * nseqs); + + int index = nseqs; + + for(int i=1;i> name; + matrixNames.push_back(name); + + + + if(nameMap == NULL){ + list->set(i, name); + for(int j=0;j> distance; + + if (m->control_pressed) { fileHandle.close(); delete reading; return 0; } + + if (distance == -1) { distance = 1000000; } + else if (sim) { distance = 1.0 - distance; } //user has entered a sim matrix that we need to convert. + + if(distance < cutoff && j < i){ + PDistCell value(i, distance); + DMatrix->addCell(j, value); + } + index++; + reading->update(index); + } + + } + else{ + if(nameMap->count(name)==0){ m->mothurOut("Error: Sequence '" + name + "' was not found in the names file, please correct"); m->mothurOutEndLine(); } + + for(int j=0;j> distance; + + if (m->control_pressed) { fileHandle.close(); delete reading; return 0; } + + if (distance == -1) { distance = 1000000; } + else if (sim) { distance = 1.0 - distance; } //user has entered a sim matrix that we need to convert. + + if(distance < cutoff && j < i){ + PDistCell value(nameMap->get(matrixNames[i]), distance); + DMatrix->addCell(nameMap->get(matrixNames[j]), value); + } + index++; + reading->update(index); + } + } + } + } + + if (m->control_pressed) { fileHandle.close(); delete reading; return 0; } + + reading->finish(); + delete reading; + + list->setLabel("0"); + fileHandle.close(); + + + return 1; + } + catch(exception& e) { + m->errorOut(e, "ReadPhylipMatrix", "read"); + exit(1); + } + } /***********************************************************************/ -ReadPhylipMatrix::~ReadPhylipMatrix(){ - delete D; - delete list; +int ReadPhylipMatrix::read(CountTable* countTable){ + try { + + float distance; + int square, nseqs; + string name; + vector matrixNames; + + string numTest; + fileHandle >> numTest >> name; + + if (!m->isContainingOnlyDigits(numTest)) { m->mothurOut("[ERROR]: expected a number and got " + numTest + ", quitting."); m->mothurOutEndLine(); exit(1); } + else { convert(numTest, nseqs); } + + matrixNames.push_back(name); + + if(countTable == NULL){ + list = new ListVector(nseqs); + list->set(0, name); + } + else{ list = new ListVector(countTable->getListVector()); } + + if (m->control_pressed) { return 0; } + + char d; + while((d=fileHandle.get()) != EOF){ + + if(isalnum(d)){ + square = 1; + fileHandle.putback(d); + for(int i=0;i> distance; + } + break; + } + if(d == '\n'){ + square = 0; + break; + } + } + + Progress* reading; + DMatrix->resize(nseqs); + + if(square == 0){ + + reading = new Progress("Reading matrix: ", nseqs * (nseqs - 1) / 2); + + int index = 0; + + for(int i=1;icontrol_pressed) { fileHandle.close(); delete reading; return 0; } + + fileHandle >> name; + matrixNames.push_back(name); + + + //there's A LOT of repeated code throughout this method... + if(countTable == NULL){ + list->set(i, name); + + for(int j=0;jcontrol_pressed) { delete reading; fileHandle.close(); return 0; } + + fileHandle >> distance; + + if (distance == -1) { distance = 1000000; } + else if (sim) { distance = 1.0 - distance; } //user has entered a sim matrix that we need to convert. + + if(distance < cutoff){ + PDistCell value(i, distance); + DMatrix->addCell(j, value); + } + index++; + reading->update(index); + } + + } + else{ + for(int j=0;j> distance; + + if (m->control_pressed) { delete reading; fileHandle.close(); return 0; } + + if (distance == -1) { distance = 1000000; } + else if (sim) { distance = 1.0 - distance; } //user has entered a sim matrix that we need to convert. + + if(distance < cutoff){ + int iIndex = countTable->get(matrixNames[i]); + int jIndex = countTable->get(matrixNames[j]); + + if (m->control_pressed) { delete reading; fileHandle.close(); return 0; } + if (iIndex < jIndex) { + PDistCell value(jIndex, distance); + DMatrix->addCell(iIndex, value); + }else { + PDistCell value(iIndex, distance); + DMatrix->addCell(jIndex, value); + + } + } + index++; + reading->update(index); + } + } + } + } + else{ + + reading = new Progress("Reading matrix: ", nseqs * nseqs); + + int index = nseqs; + + for(int i=1;i> name; + matrixNames.push_back(name); + + + + if(countTable == NULL){ + list->set(i, name); + for(int j=0;j> distance; + + if (m->control_pressed) { fileHandle.close(); delete reading; return 0; } + + if (distance == -1) { distance = 1000000; } + else if (sim) { distance = 1.0 - distance; } //user has entered a sim matrix that we need to convert. + + if(distance < cutoff && j < i){ + PDistCell value(i, distance); + DMatrix->addCell(j, value); + } + index++; + reading->update(index); + } + + } + else{ + for(int j=0;j> distance; + + if (m->control_pressed) { fileHandle.close(); delete reading; return 0; } + + if (distance == -1) { distance = 1000000; } + else if (sim) { distance = 1.0 - distance; } //user has entered a sim matrix that we need to convert. + + if(distance < cutoff && j < i){ + int iIndex = countTable->get(matrixNames[i]); + int jIndex = countTable->get(matrixNames[j]); + + if (m->control_pressed) { delete reading; fileHandle.close(); return 0; } + if (iIndex < jIndex) { + PDistCell value(jIndex, distance); + DMatrix->addCell(iIndex, value); + }else { + PDistCell value(iIndex, distance); + DMatrix->addCell(jIndex, value); + + } + } + index++; + reading->update(index); + } + } + } + } + + if (m->control_pressed) { fileHandle.close(); delete reading; return 0; } + + reading->finish(); + delete reading; + + list->setLabel("0"); + fileHandle.close(); + + + return 1; + + } + catch(exception& e) { + m->errorOut(e, "ReadPhylipMatrix", "read"); + exit(1); + } } +/***********************************************************************/ +ReadPhylipMatrix::~ReadPhylipMatrix(){} +/***********************************************************************/