X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=chopseqscommand.cpp;h=05037f6817a5a554a029a7d635460d048bf73203;hb=fdfbfe59134dd7dd3e49d90609d129128ba2d370;hp=fc2d9a7faf24c7cfa433482e6897ac7b224844a6;hpb=8bc3e5b38c2317a1715f53be22fa96455868c281;p=mothur.git diff --git a/chopseqscommand.cpp b/chopseqscommand.cpp index fc2d9a7..05037f6 100644 --- a/chopseqscommand.cpp +++ b/chopseqscommand.cpp @@ -11,65 +11,92 @@ #include "sequence.hpp" //********************************************************************************************************************** -vector ChopSeqsCommand::getValidParameters(){ +vector ChopSeqsCommand::setParameters(){ try { - string AlignArray[] = {"fasta","numbases","countgaps","keep","outputdir","inputdir"}; - vector myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string))); + CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pfasta); + CommandParameter pnumbases("numbases", "Number", "", "0", "", "", "",false,true); parameters.push_back(pnumbases); + CommandParameter pcountgaps("countgaps", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(pcountgaps); + CommandParameter pshort("short", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(pshort); + CommandParameter pkeep("keep", "Multiple", "front-back", "front", "", "", "",false,false); parameters.push_back(pkeep); + 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, "ChopSeqsCommand", "getValidParameters"); + m->errorOut(e, "ChopSeqsCommand", "setParameters"); exit(1); } } //********************************************************************************************************************** -ChopSeqsCommand::ChopSeqsCommand(){ +string ChopSeqsCommand::getHelpString(){ try { - //initialize outputTypes - vector tempOutNames; - outputTypes["fasta"] = tempOutNames; - outputTypes["accnos"] = tempOutNames; + string helpString = ""; + helpString += "The chop.seqs command reads a fasta file and outputs a .chop.fasta containing the trimmed sequences. Note: If a sequence is completely 'chopped', an accnos file will be created with the names of the sequences removed. \n"; + helpString += "The chop.seqs command parameters are fasta, numbases, countgaps and keep. fasta is required unless you have a valid current fasta file. numbases is required.\n"; + helpString += "The chop.seqs command should be in the following format: chop.seqs(fasta=yourFasta, numbases=yourNum, keep=yourKeep).\n"; + helpString += "The numbases parameter allows you to specify the number of bases you want to keep.\n"; + helpString += "The keep parameter allows you to specify whether you want to keep the front or the back of your sequence, default=front.\n"; + helpString += "The countgaps parameter allows you to specify whether you want to count gaps as bases, default=false.\n"; + helpString += "The short parameter allows you to specify you want to keep sequences that are too short to chop, default=false.\n"; + helpString += "For example, if you ran chop.seqs with numbases=200 and short=t, if a sequence had 100 bases mothur would keep the sequence rather than eliminate it.\n"; + helpString += "Example chop.seqs(fasta=amazon.fasta, numbases=200, keep=front).\n"; + helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n"; + return helpString; } catch(exception& e) { - m->errorOut(e, "ChopSeqsCommand", "ChopSeqsCommand"); + m->errorOut(e, "ChopSeqsCommand", "getHelpString"); exit(1); } } //********************************************************************************************************************** -vector ChopSeqsCommand::getRequiredParameters(){ +string ChopSeqsCommand::getOutputFileNameTag(string type, string inputName=""){ try { - string Array[] = {"fasta","numbases"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); - return myArray; + string outputFileName = ""; + map >::iterator it; + + //is this a type this command creates + it = outputTypes.find(type); + if (it == outputTypes.end()) { m->mothurOut("[ERROR]: this command doesn't create a " + type + " output file.\n"); } + else { + if (type == "fasta") { outputFileName = "chop.fasta"; } + else if (type == "accnos") { outputFileName = "chop.accnos"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output file tag.\n"); m->control_pressed = true; } + } + return outputFileName; } catch(exception& e) { - m->errorOut(e, "ChopSeqsCommand", "getRequiredParameters"); + m->errorOut(e, "ChopSeqsCommand", "getOutputFileNameTag"); exit(1); } } //********************************************************************************************************************** -vector ChopSeqsCommand::getRequiredFiles(){ +ChopSeqsCommand::ChopSeqsCommand(){ try { - vector myArray; - return myArray; + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["fasta"] = tempOutNames; + outputTypes["accnos"] = tempOutNames; } catch(exception& e) { - m->errorOut(e, "ChopSeqsCommand", "getRequiredFiles"); + m->errorOut(e, "ChopSeqsCommand", "ChopSeqsCommand"); exit(1); } } //********************************************************************************************************************** ChopSeqsCommand::ChopSeqsCommand(string option) { try { - abort = false; + abort = false; calledHelp = false; //allow user to run help - if(option == "help") { help(); abort = true; } + 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","numbases","countgaps","keep","outputdir","inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -104,16 +131,23 @@ ChopSeqsCommand::ChopSeqsCommand(string option) { //check for required parameters fastafile = validParameter.validFile(parameters, "fasta", true); if (fastafile == "not open") { abort = true; } - else if (fastafile == "not found") { m->mothurOut("You must provide a fasta file."); m->mothurOutEndLine(); abort = true; } + else if (fastafile == "not found") { //if there is a current fasta file, use it + fastafile = m->getFastaFile(); + if (fastafile != "") { m->mothurOut("Using " + fastafile + " as input file for the fasta parameter."); m->mothurOutEndLine(); } + else { m->mothurOut("You have no current fastafile and the fasta parameter is required."); m->mothurOutEndLine(); abort = true; } + }else { m->setFastaFile(fastafile); } //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 = m->hasPath(fastafile); } string temp = validParameter.validFile(parameters, "numbases", false); if (temp == "not found") { temp = "0"; } - convert(temp, numbases); + m->mothurConvert(temp, numbases); temp = validParameter.validFile(parameters, "countgaps", false); if (temp == "not found") { temp = "f"; } - countGaps = m->isTrue(temp); + countGaps = m->isTrue(temp); + + temp = validParameter.validFile(parameters, "short", false); if (temp == "not found") { temp = "f"; } + Short = m->isTrue(temp); keep = validParameter.validFile(parameters, "keep", false); if (keep == "not found") { keep = "front"; } @@ -128,32 +162,13 @@ ChopSeqsCommand::ChopSeqsCommand(string option) { } //********************************************************************************************************************** -void ChopSeqsCommand::help(){ - try { - m->mothurOut("The chop.seqs command reads a fasta file and outputs a .chop.fasta containing the trimmed sequences.\n"); - m->mothurOut("The chop.seqs command parameters are fasta, numbases, countgaps and keep. fasta and numbases are required required.\n"); - m->mothurOut("The chop.seqs command should be in the following format: chop.seqs(fasta=yourFasta, numbases=yourNum, keep=yourKeep).\n"); - m->mothurOut("The numbases parameter allows you to specify the number of bases you want to keep.\n"); - m->mothurOut("The keep parameter allows you to specify whether you want to keep the front or the back of your sequence, default=front.\n"); - m->mothurOut("The countgaps parameter allows you to specify whether you want to count gaps as bases, default=false.\n"); - m->mothurOut("Example chop.seqs(fasta=amazon.fasta, numbases=200, keep=front).\n"); - m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n"); - } - catch(exception& e) { - m->errorOut(e, "ChopSeqsCommand", "help"); - exit(1); - } -} - -//********************************************************************************************************************** - int ChopSeqsCommand::execute(){ try { - if (abort == true) { return 0; } + if (abort == true) { if (calledHelp) { return 0; } return 2; } - string outputFileName = outputDir + m->getRootName(m->getSimpleName(fastafile)) + "chop.fasta"; - string outputFileNameAccnos = outputDir + m->getRootName(m->getSimpleName(fastafile)) + "chop.accnos"; + string outputFileName = outputDir + m->getRootName(m->getSimpleName(fastafile)) + getOutputFileNameTag("fasta"); + string outputFileNameAccnos = outputDir + m->getRootName(m->getSimpleName(fastafile)) + getOutputFileNameTag("accnos"); ofstream out; m->openOutputFile(outputFileName, out); @@ -170,7 +185,7 @@ int ChopSeqsCommand::execute(){ Sequence seq(in); - if (m->control_pressed) { outputTypes.clear(); in.close(); out.close(); outAcc.close(); remove(outputFileName.c_str()); remove(outputFileNameAccnos.c_str()); return 0; } + if (m->control_pressed) { outputTypes.clear(); in.close(); out.close(); outAcc.close(); m->mothurRemove(outputFileName); m->mothurRemove(outputFileNameAccnos); return 0; } if (seq.getName() != "") { string newSeqString = getChopped(seq); @@ -193,10 +208,25 @@ int ChopSeqsCommand::execute(){ m->mothurOut(outputFileName); m->mothurOutEndLine(); outputNames.push_back(outputFileName); outputTypes["fasta"].push_back(outputFileName); if (wroteAccnos) { m->mothurOut(outputFileNameAccnos); m->mothurOutEndLine(); outputNames.push_back(outputFileNameAccnos); outputTypes["accnos"].push_back(outputFileNameAccnos); } - else { remove(outputFileNameAccnos.c_str()); } + else { m->mothurRemove(outputFileNameAccnos); } m->mothurOutEndLine(); + //set fasta file as new current fastafile + string current = ""; + itTypes = outputTypes.find("fasta"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); } + } + + if (wroteAccnos) { //set accnos file as new current accnosfile + itTypes = outputTypes.find("accnos"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setAccnosFile(current); } + } + } + + return 0; } @@ -223,7 +253,7 @@ string ChopSeqsCommand::getChopped(Sequence seq) { for (int i = 0; i < temp.length(); i++) { //eliminate N's - if (toupper(temp[i]) == 'N') { temp[i] == '.'; } + if (toupper(temp[i]) == 'N') { temp[i] = '.'; } numBasesCounted++; @@ -231,10 +261,11 @@ string ChopSeqsCommand::getChopped(Sequence seq) { } if (stopSpot == 0) { temp = ""; } - else { temp = temp.substr(0, stopSpot); } + else { temp = temp.substr(0, stopSpot+1); } - }else { temp = ""; } //sequence too short - + }else { + if (!Short) { temp = ""; } //sequence too short + } }else { //you are keeping the back int tempLength = temp.length(); if (tempLength > numbases) { //you have enough bases to remove some @@ -244,7 +275,7 @@ string ChopSeqsCommand::getChopped(Sequence seq) { for (int i = (temp.length()-1); i >= 0; i--) { //eliminate N's - if (toupper(temp[i]) == 'N') { temp[i] == '.'; } + if (toupper(temp[i]) == 'N') { temp[i] = '.'; } numBasesCounted++; @@ -253,8 +284,9 @@ string ChopSeqsCommand::getChopped(Sequence seq) { if (stopSpot == 0) { temp = ""; } else { temp = temp.substr(stopSpot+1); } + }else { + if (!Short) { temp = ""; } //sequence too short } - else { temp = ""; } //sequence too short } }else{ @@ -271,7 +303,7 @@ string ChopSeqsCommand::getChopped(Sequence seq) { for (int i = 0; i < temp.length(); i++) { //eliminate N's if (toupper(temp[i]) == 'N') { - temp[i] == '.'; + temp[i] = '.'; tempLength--; if (tempLength < numbases) { stopSpot = 0; break; } } @@ -282,10 +314,11 @@ string ChopSeqsCommand::getChopped(Sequence seq) { } if (stopSpot == 0) { temp = ""; } - else { temp = temp.substr(0, stopSpot); } + else { temp = temp.substr(0, stopSpot+1); } - }else { temp = ""; } //sequence too short - + }else { + if (!Short) { temp = ""; } //sequence too short + } }else { //you are keeping the back int tempLength = tempUnaligned.length(); if (tempLength > numbases) { //you have enough bases to remove some @@ -296,7 +329,7 @@ string ChopSeqsCommand::getChopped(Sequence seq) { for (int i = (temp.length()-1); i >= 0; i--) { //eliminate N's if (toupper(temp[i]) == 'N') { - temp[i] == '.'; + temp[i] = '.'; tempLength--; if (tempLength < numbases) { stopSpot = 0; break; } } @@ -307,9 +340,10 @@ string ChopSeqsCommand::getChopped(Sequence seq) { } if (stopSpot == 0) { temp = ""; } - else { temp = temp.substr(stopSpot+1); } + else { temp = temp.substr(stopSpot); } + }else { + if (!Short) { temp = ""; } //sequence too short } - else { temp = ""; } //sequence too short } }