X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=chopseqscommand.cpp;h=4e06201cd352104b5ee9c9d1c41764d16473003e;hb=d205e70ae86dbee2efc2df02f2717975854de6ba;hp=a09ff65856ae39c1e8fbb1a662ed8bacd8860694;hpb=348de0f8b17d84ede77081dcf67bd6ef43496677;p=mothur.git diff --git a/chopseqscommand.cpp b/chopseqscommand.cpp index a09ff65..4e06201 100644 --- a/chopseqscommand.cpp +++ b/chopseqscommand.cpp @@ -11,50 +11,58 @@ #include "sequence.hpp" //********************************************************************************************************************** -vector ChopSeqsCommand::getValidParameters(){ +vector ChopSeqsCommand::setParameters(){ try { - string AlignArray[] = {"fasta","short","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"); - exit(1); - } -} -//********************************************************************************************************************** -ChopSeqsCommand::ChopSeqsCommand(){ - try { - abort = true; calledHelp = true; - vector tempOutNames; - outputTypes["fasta"] = tempOutNames; - outputTypes["accnos"] = tempOutNames; - } - catch(exception& e) { - m->errorOut(e, "ChopSeqsCommand", "ChopSeqsCommand"); + m->errorOut(e, "ChopSeqsCommand", "setParameters"); exit(1); } } //********************************************************************************************************************** -vector ChopSeqsCommand::getRequiredParameters(){ +string ChopSeqsCommand::getHelpString(){ try { - string Array[] = {"fasta","numbases"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); - return myArray; + 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", "getRequiredParameters"); + m->errorOut(e, "ChopSeqsCommand", "getHelpString"); 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); } } @@ -65,11 +73,10 @@ ChopSeqsCommand::ChopSeqsCommand(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","numbases","countgaps","keep","short","outputdir","inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -104,13 +111,17 @@ 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); @@ -131,27 +142,6 @@ 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. Note: If a sequence is completely 'chopped', an accnos file will be created with the names of the sequences removed. \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("The short parameter allows you to specify you want to keep sequences that are too short to chop, default=false.\n"); - m->mothurOut("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"); - 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 { @@ -175,7 +165,7 @@ 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); @@ -198,7 +188,7 @@ 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(); @@ -243,7 +233,7 @@ 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++; @@ -251,7 +241,7 @@ string ChopSeqsCommand::getChopped(Sequence seq) { } if (stopSpot == 0) { temp = ""; } - else { temp = temp.substr(0, stopSpot); } + else { temp = temp.substr(0, stopSpot+1); } }else { if (!Short) { temp = ""; } //sequence too short @@ -265,7 +255,7 @@ 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++; @@ -293,7 +283,7 @@ 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; } } @@ -304,7 +294,7 @@ string ChopSeqsCommand::getChopped(Sequence seq) { } if (stopSpot == 0) { temp = ""; } - else { temp = temp.substr(0, stopSpot); } + else { temp = temp.substr(0, stopSpot+1); } }else { if (!Short) { temp = ""; } //sequence too short @@ -319,7 +309,7 @@ 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; } } @@ -330,7 +320,7 @@ 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 }