X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=chopseqscommand.cpp;h=4e06201cd352104b5ee9c9d1c41764d16473003e;hb=d6c0a11d1cecfac18b323285e7ffadb7f58e848f;hp=47f151de14c5e1494485b7eebc445125f74a4d30;hpb=86b6cc7ce1ec7fce12cdfdd6225de4dee7cfbdbf;p=mothur.git diff --git a/chopseqscommand.cpp b/chopseqscommand.cpp index 47f151d..4e06201 100644 --- a/chopseqscommand.cpp +++ b/chopseqscommand.cpp @@ -11,18 +11,72 @@ #include "sequence.hpp" //********************************************************************************************************************** +vector ChopSeqsCommand::setParameters(){ + try { + 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", "setParameters"); + exit(1); + } +} +//********************************************************************************************************************** +string ChopSeqsCommand::getHelpString(){ + try { + 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", "getHelpString"); + exit(1); + } +} +//********************************************************************************************************************** +ChopSeqsCommand::ChopSeqsCommand(){ + try { + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["fasta"] = tempOutNames; + outputTypes["accnos"] = tempOutNames; + } + catch(exception& e) { + 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","end","fromend","outputdir","inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -35,9 +89,11 @@ ChopSeqsCommand::ChopSeqsCommand(string option) { if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } } - //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 = ""; } - + //initialize outputTypes + vector tempOutNames; + outputTypes["fasta"] = tempOutNames; + outputTypes["accnos"] = tempOutNames; + //if the user changes the input directory command factory will send this info to us in the output parameter string inputDir = validParameter.validFile(parameters, "inputdir", false); if (inputDir == "not found"){ inputDir = ""; } @@ -46,7 +102,7 @@ ChopSeqsCommand::ChopSeqsCommand(string option) { it = parameters.find("fasta"); //user has given a template file if(it != parameters.end()){ - path = hasPath(it->second); + path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["fasta"] = inputDir + it->second; } } @@ -55,16 +111,27 @@ 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"; } + m->mothurConvert(temp, numbases); - string temp = validParameter.validFile(parameters, "end", false); if (temp == "not found") { temp = "0"; } - convert(temp, end); + temp = validParameter.validFile(parameters, "countgaps", false); if (temp == "not found") { temp = "f"; } + countGaps = m->isTrue(temp); + + temp = validParameter.validFile(parameters, "short", false); if (temp == "not found") { temp = "f"; } + Short = m->isTrue(temp); - temp = validParameter.validFile(parameters, "fromend", false); if (temp == "not found") { temp = "0"; } - convert(temp, fromend); + keep = validParameter.validFile(parameters, "keep", false); if (keep == "not found") { keep = "front"; } - if ((end == 0) && (fromend == 0)) { m->mothurOut("You must provide either end or fromend for the chops.seqs command."); m->mothurOutEndLine(); abort = true; } - if ((end != 0) && (fromend != 0)) { m->mothurOut("You must provide either end or fromend for the chops.seqs command, not both."); m->mothurOutEndLine(); abort = true; } + if (numbases == 0) { m->mothurOut("You must provide the number of bases you want to keep for the chops.seqs command."); m->mothurOutEndLine(); abort = true; } } } @@ -75,40 +142,22 @@ 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, end and fromend, fasta is required.\n"); - m->mothurOut("The chop.seqs command should be in the following format: chop.seqs(fasta=yourFasta, end=yourEnd).\n"); - m->mothurOut("The end parameter allows you to specify an end base position for your sequences, default = 0.\n"); - m->mothurOut("The fromend parameter allows you to remove the last X bases from the end of the sequence, default = 0.\n"); - m->mothurOut("Example chop.seqs(fasta=amazon.fasta, end=200).\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 + getRootName(getSimpleName(fastafile)) + "chop.fasta"; - string outputFileNameAccnos = outputDir + getRootName(getSimpleName(fastafile)) + "chop.accnos"; + string outputFileName = outputDir + m->getRootName(m->getSimpleName(fastafile)) + "chop.fasta"; + string outputFileNameAccnos = outputDir + m->getRootName(m->getSimpleName(fastafile)) + "chop.accnos"; ofstream out; - openOutputFile(outputFileName, out); + m->openOutputFile(outputFileName, out); ofstream outAcc; - openOutputFile(outputFileNameAccnos, outAcc); + m->openOutputFile(outputFileNameAccnos, outAcc); ifstream in; - openInputFile(fastafile, in); + m->openInputFile(fastafile, in); bool wroteAccnos = false; @@ -116,15 +165,10 @@ int ChopSeqsCommand::execute(){ Sequence seq(in); - if (m->control_pressed) { 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 = ""; - if (seq.getIsAligned()) { //sequence is aligned - newSeqString = getChoppedAligned(seq); - }else{ - newSeqString = getChoppedUnaligned(seq); - } + string newSeqString = getChopped(seq); //output trimmed sequence if (newSeqString != "") { @@ -141,13 +185,28 @@ int ChopSeqsCommand::execute(){ m->mothurOutEndLine(); m->mothurOut("Output File Name: "); m->mothurOutEndLine(); - m->mothurOut(outputFileName); m->mothurOutEndLine(); + m->mothurOut(outputFileName); m->mothurOutEndLine(); outputNames.push_back(outputFileName); outputTypes["fasta"].push_back(outputFileName); - if (wroteAccnos) { m->mothurOut(outputFileNameAccnos); m->mothurOutEndLine(); } - else { remove(outputFileNameAccnos.c_str()); } + if (wroteAccnos) { m->mothurOut(outputFileNameAccnos); m->mothurOutEndLine(); outputNames.push_back(outputFileNameAccnos); outputTypes["accnos"].push_back(outputFileNameAccnos); } + 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; } @@ -157,70 +216,121 @@ int ChopSeqsCommand::execute(){ } } //********************************************************************************************************************** -string ChopSeqsCommand::getChoppedUnaligned(Sequence seq) { - try { - string temp = seq.getUnaligned(); - - //if needed trim sequence - if (end != 0) { - if (temp.length() > end) { temp = temp.substr(0, end); } - else { temp = ""; } - }else { //you are using fromend - if (temp.length() > fromend) { temp = temp.substr(0, (temp.length()-fromend)); } - else { temp = ""; } //sequence too short - } - - return temp; - } - catch(exception& e) { - m->errorOut(e, "ChopSeqsCommand", "getChoppedUnaligned"); - exit(1); - } -} -//********************************************************************************************************************** -string ChopSeqsCommand::getChoppedAligned(Sequence seq) { +string ChopSeqsCommand::getChopped(Sequence seq) { try { string temp = seq.getAligned(); string tempUnaligned = seq.getUnaligned(); - - //if needed trim sequence - if (end != 0) { - if (tempUnaligned.length() > end) { //you have enough bases to remove some - - int stopSpot = 0; - int numBases = 0; - - for (int i = 0; i < temp.length(); i++) { - if(isalpha(temp[i])) { numBases++; } + + if (countGaps) { + //if needed trim sequence + if (keep == "front") {//you want to keep the beginning + int tempLength = temp.length(); - if (numBases >= end) { stopSpot = i; break; } - } + if (tempLength > numbases) { //you have enough bases to remove some - temp = temp.substr(0, stopSpot); - }else { temp = ""; } //sequence too short - - }else { //you are using fromend - - if (tempUnaligned.length() > fromend) { + int stopSpot = 0; + int numBasesCounted = 0; + + for (int i = 0; i < temp.length(); i++) { + //eliminate N's + if (toupper(temp[i]) == 'N') { temp[i] = '.'; } + + numBasesCounted++; + + if (numBasesCounted >= numbases) { stopSpot = i; break; } + } + + if (stopSpot == 0) { temp = ""; } + else { temp = temp.substr(0, stopSpot+1); } + + }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 + + int stopSpot = 0; + int numBasesCounted = 0; + + for (int i = (temp.length()-1); i >= 0; i--) { + //eliminate N's + if (toupper(temp[i]) == 'N') { temp[i] = '.'; } + + numBasesCounted++; + + if (numBasesCounted >= numbases) { stopSpot = i; break; } + } - int stopSpot = 0; - int numBases = 0; + if (stopSpot == 0) { temp = ""; } + else { temp = temp.substr(stopSpot+1); } + }else { + if (!Short) { temp = ""; } //sequence too short + } + } + + }else{ - for (int i = (temp.length()-1); i >= 0; i--) { - if(isalpha(temp[i])) { numBases++; } + //if needed trim sequence + if (keep == "front") {//you want to keep the beginning + int tempLength = tempUnaligned.length(); - if (numBases >= fromend) { stopSpot = i; break; } - } + if (tempLength > numbases) { //you have enough bases to remove some + + int stopSpot = 0; + int numBasesCounted = 0; + + for (int i = 0; i < temp.length(); i++) { + //eliminate N's + if (toupper(temp[i]) == 'N') { + temp[i] = '.'; + tempLength--; + if (tempLength < numbases) { stopSpot = 0; break; } + } + + if(isalpha(temp[i])) { numBasesCounted++; } + + if (numBasesCounted >= numbases) { stopSpot = i; break; } + } + + if (stopSpot == 0) { temp = ""; } + else { temp = temp.substr(0, stopSpot+1); } + + }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 + + int stopSpot = 0; + int numBasesCounted = 0; + + for (int i = (temp.length()-1); i >= 0; i--) { + //eliminate N's + if (toupper(temp[i]) == 'N') { + temp[i] = '.'; + tempLength--; + if (tempLength < numbases) { stopSpot = 0; break; } + } + + if(isalpha(temp[i])) { numBasesCounted++; } + + if (numBasesCounted >= numbases) { stopSpot = i; break; } + } - temp = temp.substr(0, stopSpot); + if (stopSpot == 0) { temp = ""; } + else { temp = temp.substr(stopSpot); } + }else { + if (!Short) { temp = ""; } //sequence too short + } } - else { temp = ""; } //sequence too short } - + return temp; } catch(exception& e) { - m->errorOut(e, "ChopSeqsCommand", "getChoppedUnaligned"); + m->errorOut(e, "ChopSeqsCommand", "getChopped"); exit(1); } }