X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=distancecommand.cpp;h=b73cd7c751176c386a95931b0887c6790f046583;hb=f06fdb807822f8e06db003ed809c87250905cfc8;hp=3d667227ae2219347f2523ee1ff8286988299423;hpb=c69e2e9749626cfbf1d6cb0125ae94f869e00b18;p=mothur.git diff --git a/distancecommand.cpp b/distancecommand.cpp index 3d66722..b73cd7c 100644 --- a/distancecommand.cpp +++ b/distancecommand.cpp @@ -14,52 +14,66 @@ #include "onegapdist.h" #include "onegapignore.h" - //********************************************************************************************************************** -vector DistanceCommand::getValidParameters(){ +vector DistanceCommand::setParameters(){ try { - string Array[] = {"fasta","oldfasta","column", "output", "calc", "countends", "cutoff", "processors", "outputdir","inputdir","compress"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + CommandParameter pcolumn("column", "InputTypes", "", "", "none", "none", "OldFastaColumn",false,false); parameters.push_back(pcolumn); + CommandParameter poldfasta("oldfasta", "InputTypes", "", "", "none", "none", "OldFastaColumn",false,false); parameters.push_back(poldfasta); + CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pfasta); + CommandParameter poutput("output", "Multiple", "column-lt-square", "column", "", "", "",false,false); parameters.push_back(poutput); + CommandParameter pcalc("calc", "Multiple", "nogaps-eachgap-onegap", "onegap", "", "", "",false,false); parameters.push_back(pcalc); + CommandParameter pcountends("countends", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pcountends); + CommandParameter pcompress("compress", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(pcompress); + CommandParameter pprocessors("processors", "Number", "", "1", "", "", "",false,false); parameters.push_back(pprocessors); + CommandParameter pcutoff("cutoff", "Number", "", "1.0", "", "", "",false,false); parameters.push_back(pcutoff); + CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir); + CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir); + + vector myArray; + for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); } return myArray; } catch(exception& e) { - m->errorOut(e, "DistanceCommand", "getValidParameters"); - exit(1); - } -} -//********************************************************************************************************************** -DistanceCommand::DistanceCommand(){ - try { - abort = true; calledHelp = true; - vector tempOutNames; - outputTypes["phylip"] = tempOutNames; - outputTypes["column"] = tempOutNames; - } - catch(exception& e) { - m->errorOut(e, "DistanceCommand", "DistanceCommand"); + m->errorOut(e, "DistanceCommand", "setParameters"); exit(1); } } //********************************************************************************************************************** -vector DistanceCommand::getRequiredParameters(){ +string DistanceCommand::getHelpString(){ try { - string Array[] = {"fasta"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); - return myArray; + string helpString = ""; + helpString += "The dist.seqs command reads a file containing sequences and creates a distance file.\n"; + helpString += "The dist.seqs command parameters are fasta, oldfasta, column, calc, countends, output, compress, cutoff and processors. \n"; + helpString += "The fasta parameter is required, unless you have a valid current fasta file.\n"; + helpString += "The oldfasta and column parameters allow you to append the distances calculated to the column file.\n"; + helpString += "The calc parameter allows you to specify the method of calculating the distances. Your options are: nogaps, onegap or eachgap. The default is onegap.\n"; + helpString += "The countends parameter allows you to specify whether to include terminal gaps in distance. Your options are: T or F. The default is T.\n"; + helpString += "The cutoff parameter allows you to specify maximum distance to keep. The default is 1.0.\n"; + helpString += "The output parameter allows you to specify format of your distance matrix. Options are column, lt, and square. The default is column.\n"; + helpString += "The processors parameter allows you to specify number of processors to use. The default is 1.\n"; + helpString += "The compress parameter allows you to indicate that you want the resulting distance file compressed. The default is false.\n"; + helpString += "The dist.seqs command should be in the following format: \n"; + helpString += "dist.seqs(fasta=yourFastaFile, calc=yourCalc, countends=yourEnds, cutoff= yourCutOff, processors=yourProcessors) \n"; + helpString += "Example dist.seqs(fasta=amazon.fasta, calc=eachgap, countends=F, cutoff= 2.0, processors=3).\n"; + helpString += "Note: No spaces between parameter labels (i.e. calc), '=' and parameters (i.e.yourCalc).\n"; + return helpString; } catch(exception& e) { - m->errorOut(e, "DistanceCommand", "getRequiredParameters"); + m->errorOut(e, "DistanceCommand", "getHelpString"); exit(1); } } //********************************************************************************************************************** -vector DistanceCommand::getRequiredFiles(){ +DistanceCommand::DistanceCommand(){ try { - vector myArray; - return myArray; + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["phylip"] = tempOutNames; + outputTypes["column"] = tempOutNames; } catch(exception& e) { - m->errorOut(e, "DistanceCommand", "getRequiredFiles"); + m->errorOut(e, "DistanceCommand", "DistanceCommand"); exit(1); } } @@ -71,12 +85,10 @@ DistanceCommand::DistanceCommand(string option) { //allow user to run help if(option == "help") { help(); abort = true; calledHelp = true; } + else if(option == "citation") { citation(); abort = true; calledHelp = true;} else { - //valid paramters for this command - string Array[] = {"fasta","oldfasta","column", "output", "calc", "countends", "cutoff", "processors", "outputdir","inputdir","compress"}; - - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -126,8 +138,15 @@ DistanceCommand::DistanceCommand(string option) { //check for required parameters fastafile = validParameter.validFile(parameters, "fasta", true); - if (fastafile == "not found") { m->mothurOut("fasta is a required parameter for the dist.seqs command."); m->mothurOutEndLine(); abort = true; } - else if (fastafile == "not open") { abort = true; } + if (fastafile == "not found") { + fastafile = m->getFastaFile(); + if (fastafile != "") { m->mothurOut("Using " + fastafile + " as input file for the fasta parameter."); m->mothurOutEndLine(); + ifstream inFASTA; + m->openInputFile(fastafile, inFASTA); + alignDB = SequenceDB(inFASTA); + inFASTA.close(); + }else { m->mothurOut("You have no current fastafile and the fasta parameter is required."); m->mothurOutEndLine(); abort = true; } + }else if (fastafile == "not open") { abort = true; } else{ ifstream inFASTA; m->openInputFile(fastafile, inFASTA); @@ -165,8 +184,9 @@ DistanceCommand::DistanceCommand(string option) { temp = validParameter.validFile(parameters, "cutoff", false); if(temp == "not found"){ temp = "1.0"; } convert(temp, cutoff); - temp = validParameter.validFile(parameters, "processors", false); if(temp == "not found"){ temp = "1"; } - convert(temp, processors); + temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = m->getProcessors(); } + m->setProcessors(temp); + convert(temp, processors); temp = validParameter.validFile(parameters, "compress", false); if(temp == "not found"){ temp = "F"; } convert(temp, compress); @@ -207,35 +227,6 @@ DistanceCommand::DistanceCommand(string option) { exit(1); } } - -//********************************************************************************************************************** - -DistanceCommand::~DistanceCommand(){} - -//********************************************************************************************************************** - -void DistanceCommand::help(){ - try { - m->mothurOut("The dist.seqs command reads a file containing sequences and creates a distance file.\n"); - m->mothurOut("The dist.seqs command parameters are fasta, oldfasta, column, calc, countends, output, compress, cutoff and processors. \n"); - m->mothurOut("The fasta parameter is required.\n"); - m->mothurOut("The oldfasta and column parameters allow you to append the distances calculated to the column file.\n"); - m->mothurOut("The calc parameter allows you to specify the method of calculating the distances. Your options are: nogaps, onegap or eachgap. The default is onegap.\n"); - m->mothurOut("The countends parameter allows you to specify whether to include terminal gaps in distance. Your options are: T or F. The default is T.\n"); - m->mothurOut("The cutoff parameter allows you to specify maximum distance to keep. The default is 1.0.\n"); - m->mothurOut("The output parameter allows you to specify format of your distance matrix. Options are column, lt, and square. The default is column.\n"); - m->mothurOut("The processors parameter allows you to specify number of processors to use. The default is 1.\n"); - m->mothurOut("The compress parameter allows you to indicate that you want the resulting distance file compressed. The default is false.\n"); - m->mothurOut("The dist.seqs command should be in the following format: \n"); - m->mothurOut("dist.seqs(fasta=yourFastaFile, calc=yourCalc, countends=yourEnds, cutoff= yourCutOff, processors=yourProcessors) \n"); - m->mothurOut("Example dist.seqs(fasta=amazon.fasta, calc=eachgap, countends=F, cutoff= 2.0, processors=3).\n"); - m->mothurOut("Note: No spaces between parameter labels (i.e. calc), '=' and parameters (i.e.yourCalc).\n\n"); - } - catch(exception& e) { - m->errorOut(e, "DistanceCommand", "help"); - exit(1); - } -} //********************************************************************************************************************** int DistanceCommand::execute(){ @@ -256,6 +247,8 @@ int DistanceCommand::execute(){ int numSeqs = alignDB.getNumSeqs(); cutoff += 0.005; + if (!alignDB.sameLength()) { m->mothurOut("[ERROR]: your sequences are not the same length, aborting."); m->mothurOutEndLine(); return 0; } + string outputFile; if (output == "lt") { //does the user want lower triangle phylip formatted file @@ -501,6 +494,19 @@ int DistanceCommand::execute(){ delete distCalculator; + //set phylip file as new current phylipfile + string current = ""; + itTypes = outputTypes.find("phylip"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setPhylipFile(current); } + } + + //set column file as new current columnfile + itTypes = outputTypes.find("column"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setColumnFile(current); } + } + m->mothurOutEndLine(); m->mothurOut("Output File Name: "); m->mothurOutEndLine(); m->mothurOut(outputFile); m->mothurOutEndLine();