X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=splitgroupscommand.cpp;h=26716554decad148623563d4b120148325b7477a;hb=2009a1a1f47e7467094d844e7c07ab8ddf7bb447;hp=d389d8907bfaffde16b8ca9eac4dad0061341831;hpb=c69e2e9749626cfbf1d6cb0125ae94f869e00b18;p=mothur.git diff --git a/splitgroupscommand.cpp b/splitgroupscommand.cpp index d389d89..2671655 100644 --- a/splitgroupscommand.cpp +++ b/splitgroupscommand.cpp @@ -9,39 +9,44 @@ #include "splitgroupscommand.h" #include "sharedutilities.h" +#include "sequenceparser.h" //********************************************************************************************************************** -vector SplitGroupCommand::getValidParameters(){ - try { - string Array[] = {"name","group","groups","fasta","outputdir","inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); +vector SplitGroupCommand::setParameters(){ + try { + CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pfasta); + CommandParameter pname("name", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pname); + CommandParameter pgroup("group", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pgroup); + CommandParameter pgroups("groups", "String", "", "", "", "", "",false,false); parameters.push_back(pgroups); + 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, "SplitGroupCommand", "getValidParameters"); + m->errorOut(e, "SplitGroupCommand", "setParameters"); exit(1); } } //********************************************************************************************************************** -vector SplitGroupCommand::getRequiredParameters(){ +string SplitGroupCommand::getHelpString(){ try { - string Array[] = {"fasta","group"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); - return myArray; + string helpString = ""; + helpString += "The split.group command reads a group file, and parses your fasta and names files by groups. \n"; + helpString += "The split.group command parameters are fasta, name, group and groups.\n"; + helpString += "The fasta and group parameters are required.\n"; + helpString += "The groups parameter allows you to select groups to create files for. \n"; + helpString += "For example if you set groups=A-B-C, you will get a .A.fasta, .A.names, .B.fasta, .B.names, .C.fasta, .C.names files. \n"; + helpString += "If you want .fasta and .names files for all groups, set groups=all. \n"; + helpString += "The split.group command should be used in the following format: split.group(fasta=yourFasta, group=yourGroupFile).\n"; + helpString += "Example: split.group(fasta=abrecovery.fasta, group=abrecovery.groups).\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, "SplitGroupCommand", "getRequiredParameters"); - exit(1); - } -} -//********************************************************************************************************************** -vector SplitGroupCommand::getRequiredFiles(){ - try { - vector myArray; - return myArray; - } - catch(exception& e) { - m->errorOut(e, "SplitGroupCommand", "getRequiredFiles"); + m->errorOut(e, "SplitGroupCommand", "getHelpString"); exit(1); } } @@ -49,6 +54,7 @@ vector SplitGroupCommand::getRequiredFiles(){ SplitGroupCommand::SplitGroupCommand(){ try { abort = true; calledHelp = true; + setParameters(); vector tempOutNames; outputTypes["fasta"] = tempOutNames; outputTypes["name"] = tempOutNames; @@ -65,11 +71,10 @@ SplitGroupCommand::SplitGroupCommand(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[] = {"name","group","groups","fasta","outputdir","inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -120,16 +125,25 @@ SplitGroupCommand::SplitGroupCommand(string option) { namefile = validParameter.validFile(parameters, "name", true); - if (namefile == "not open") { abort = true; } + if (namefile == "not open") { namefile = ""; abort = true; } else if (namefile == "not found") { namefile = ""; } + else { m->setNameFile(namefile); } fastafile = validParameter.validFile(parameters, "fasta", true); if (fastafile == "not open") { abort = true; } - else if (fastafile == "not found") { fastafile = ""; m->mothurOut("fasta is a required parameter for the split.group command. "); m->mothurOutEndLine(); abort = true; } + else if (fastafile == "not found") { + 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); } groupfile = validParameter.validFile(parameters, "group", true); if (groupfile == "not open") { groupfile = ""; abort = true; } - else if (groupfile == "not found") { groupfile = ""; m->mothurOut("group is a required parameter for the split.group command. "); m->mothurOutEndLine(); abort = true; } + else if (groupfile == "not found") { + groupfile = m->getGroupFile(); + if (groupfile != "") { m->mothurOut("Using " + groupfile + " as input file for the group parameter."); m->mothurOutEndLine(); } + else { m->mothurOut("You have no current groupfile and the group parameter is required."); m->mothurOutEndLine(); abort = true; } + }else { m->setGroupFile(groupfile); } groups = validParameter.validFile(parameters, "groups", false); if (groups == "not found") { groups = ""; } @@ -137,6 +151,11 @@ SplitGroupCommand::SplitGroupCommand(string option) { //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(groupfile); } + + if (namefile == "") { + vector files; files.push_back(fastafile); + parser.getNameFile(files); + } } } @@ -146,197 +165,71 @@ SplitGroupCommand::SplitGroupCommand(string option) { } } //********************************************************************************************************************** -void SplitGroupCommand::help(){ - try { - m->mothurOut("The split.group command reads a group file, and parses your fasta and names files by groups. \n"); - m->mothurOut("The split.group command parameters are fasta, name, group and groups.\n"); - m->mothurOut("The fasta and group parameters are required.\n"); - m->mothurOut("The groups parameter allows you to select groups to create files for. \n"); - m->mothurOut("For example if you set groups=A-B-C, you will get a .A.fasta, .A.names, .B.fasta, .B.names, .C.fasta, .C.names files. \n"); - m->mothurOut("If you want .fasta and .names files for all groups, set groups=all. \n"); - m->mothurOut("The split.group command should be used in the following format: split.group(fasta=yourFasta, group=yourGroupFile).\n"); - m->mothurOut("Example: split.group(fasta=abrecovery.fasta, group=abrecovery.groups).\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, "SplitGroupCommand", "help"); - exit(1); - } -} -//********************************************************************************************************************** -SplitGroupCommand::~SplitGroupCommand(){ } -//********************************************************************************************************************** int SplitGroupCommand::execute(){ try { if (abort == true) { if (calledHelp) { return 0; } return 2; } - groupMap = new GroupMap(groupfile); - groupMap->readMap(); + SequenceParser* parser; - SharedUtil util; util.setGroups(Groups, groupMap->namesOfGroups); + if (namefile == "") { parser = new SequenceParser(groupfile, fastafile); } + else { parser = new SequenceParser(groupfile, fastafile, namefile); } - if (namefile != "") { readNames(); } - splitFasta(); - - delete groupMap; + if (m->control_pressed) { delete parser; return 0; } + + vector namesGroups = parser->getNamesOfGroups(); + SharedUtil util; util.setGroups(Groups, namesGroups); - if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + string fastafileRoot = outputDir + m->getRootName(m->getSimpleName(fastafile)); + string namefileRoot = outputDir + m->getRootName(m->getSimpleName(namefile)); m->mothurOutEndLine(); - m->mothurOut("Output File Names: "); m->mothurOutEndLine(); - for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); } - m->mothurOutEndLine(); - - return 0; - } - catch(exception& e) { - m->errorOut(e, "SplitGroupCommand", "execute"); - exit(1); - } -} -/**********************************************************************************************************************/ -int SplitGroupCommand::readNames() { - try { - //open input file - ifstream in; - m->openInputFile(namefile, in); - - while (!in.eof()) { - if (m->control_pressed) { break; } + for (int i = 0; i < Groups.size(); i++) { - string firstCol, secondCol; - in >> firstCol >> secondCol; m->gobble(in); + m->mothurOut("Processing group: " + Groups[i]); m->mothurOutEndLine(); - vector names; - m->splitAtComma(secondCol, names); + string newFasta = fastafileRoot + Groups[i] + ".fasta"; + string newName = namefileRoot + Groups[i] + ".names"; - nameMap[firstCol] = names; - } - in.close(); - - return 0; - - } - catch(exception& e) { - m->errorOut(e, "SplitGroupCommand", "readNames"); - exit(1); - } -} - -/**********************************************************************************************************************/ -int SplitGroupCommand::splitFasta() { - try { - - string filerootFasta = outputDir + m->getRootName(m->getSimpleName(fastafile)); - string filerootName = outputDir + m->getRootName(m->getSimpleName(namefile)); - ofstream* temp; - ofstream* temp2; - map filehandles; - map::iterator it3; + parser->getSeqs(Groups[i], newFasta, false); + outputNames.push_back(newFasta); outputTypes["fasta"].push_back(newFasta); + if (m->control_pressed) { delete parser; for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } - for (int i=0; iopenOutputFile(filerootFasta + Groups[i] + ".fasta", *(filehandles[Groups[i]+"fasta"])); - outputNames.push_back(filerootFasta + Groups[i] + ".fasta"); outputTypes["fasta"].push_back(filerootFasta + Groups[i] + ".fasta"); - - if (namefile != "") { - temp2 = new ofstream; - filehandles[Groups[i]+"name"] = temp2; - m->openOutputFile(filerootName + Groups[i] + ".names", *(filehandles[Groups[i]+"name"])); - outputNames.push_back(filerootName + Groups[i] + ".names"); outputTypes["name"].push_back(filerootFasta + Groups[i] + ".names"); + if (namefile != "") { + parser->getNameMap(Groups[i], newName); + outputNames.push_back(newName); outputTypes["name"].push_back(newName); } - } - //open input file - ifstream in; - m->openInputFile(fastafile, in); - - while (!in.eof()) { - if (m->control_pressed) { break; } - - Sequence seq(in); m->gobble(in); - - if (seq.getName() != "") { - - itNames = nameMap.find(seq.getName()); - - if (itNames == nameMap.end()) { - if (namefile != "") { m->mothurOut(seq.getName() + " is not in your namesfile, ignoring."); m->mothurOutEndLine(); } - else { //no names file given - string group = groupMap->getGroup(seq.getName()); - - if (m->inUsersGroups(group, Groups)) { //only add if this is in a group we want - seq.printSequence(*(filehandles[group+"fasta"])); - }else if(group == "not found") { - m->mothurOut(seq.getName() + " is not in your groupfile. Ignoring."); m->mothurOutEndLine(); - } - } - }else{ - vector names = itNames->second; - map group2Names; - map::iterator it; - - for (int i = 0; i < names.size(); i++) { //build strings for new group names file, will select rep below - string group = groupMap->getGroup(names[i]); - - if (m->inUsersGroups(group, Groups)) { //only add if this is in a group we want - it = group2Names.find(group); - if (it == group2Names.end()) { - group2Names[group] = names[i] + ","; - }else{ - group2Names[group] += names[i] + ","; - } - }else if(group == "not found") { - m->mothurOut(names[i] + " is not in your groupfile. Ignoring."); m->mothurOutEndLine(); - } - } - - for (map::iterator itGroups = group2Names.begin(); itGroups != group2Names.end(); itGroups++) { - //edit names string, by grabbing the first guy as the rep and removing the last comma - string newNames = itGroups->second; - newNames = newNames.substr(0, newNames.length()-1); - string repName = ""; - - int pos = newNames.find_first_of(','); - if (pos == newNames.npos) { //only one sequence so it represents itself - repName = newNames; - }else{ - repName = newNames.substr(0, pos); - } - - *(filehandles[itGroups->first+"name"]) << repName << '\t' << newNames << endl; - *(filehandles[itGroups->first+"fasta"]) << ">" << repName << endl << seq.getAligned() << endl; - } - } - } + if (m->control_pressed) { delete parser; for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } } - - in.close(); - - for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { - (*(filehandles[it3->first])).close(); - delete it3->second; + + delete parser; + + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } + + string current = ""; + itTypes = outputTypes.find("fasta"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); } } - vector newOutputNames; - //remove blank files - for (int i = 0; i < outputNames.size(); i++) { - if (m->isBlank(outputNames[i])) { - remove(outputNames[i].c_str()); - }else { newOutputNames.push_back(outputNames[i]); } + itTypes = outputTypes.find("name"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setNameFile(current); } } - outputNames = newOutputNames; - + + m->mothurOutEndLine(); + m->mothurOut("Output File Names: "); m->mothurOutEndLine(); + for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); } + m->mothurOutEndLine(); + return 0; - } catch(exception& e) { - m->errorOut(e, "SplitGroupCommand", "splitFasta"); + m->errorOut(e, "SplitGroupCommand", "execute"); exit(1); } } -/**********************************************************************************************************************/ +//********************************************************************************************************************** +