X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=parselistscommand.cpp;h=3ed65c67f700b98d3c99a12a9dc6018ff4cfdd76;hp=6e4082e0c139b76435aa073cd1f0c7013b85dca3;hb=1a20e24ee786195ab0e1cccd4f5aede7a88f3f4e;hpb=ca9ac1d80c62f57270b0dcd49410ebe08a8aecd6 diff --git a/parselistscommand.cpp b/parselistscommand.cpp index 6e4082e..3ed65c6 100644 --- a/parselistscommand.cpp +++ b/parselistscommand.cpp @@ -12,11 +12,12 @@ //********************************************************************************************************************** vector ParseListCommand::setParameters(){ try { - CommandParameter plist("list", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(plist); - CommandParameter pgroup("group", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pgroup); - CommandParameter plabel("label", "String", "", "", "", "", "",false,false); parameters.push_back(plabel); - CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir); - CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir); + CommandParameter plist("list", "InputTypes", "", "", "none", "none", "none","list",false,true,true); parameters.push_back(plist); + CommandParameter pcount("count", "InputTypes", "", "", "CountGroup", "CountGroup", "none","",false,false,true); parameters.push_back(pcount); + CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "CountGroup", "none","",false,false,true); parameters.push_back(pgroup); + CommandParameter plabel("label", "String", "", "", "", "", "","",false,false); parameters.push_back(plabel); + 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); } @@ -31,13 +32,15 @@ vector ParseListCommand::setParameters(){ string ParseListCommand::getHelpString(){ try { string helpString = ""; - helpString += "The parse.list command reads a list and group file and generates a list file for each group in the groupfile. \n"; - helpString += "The parse.list command parameters are list, group and label.\n"; - helpString += "The list and group parameters are required.\n"; + helpString += "The parse.list command reads a list and group or count file and generates a list file for each group in the group or count file. \n"; + helpString += "The parse.list command parameters are list, group, count and label.\n"; + helpString += "The list and group or count parameters are required.\n"; + helpString += "If a count file is provided, mothur assumes the list file contains only unique names.\n"; + helpString += "If a group file is provided, mothur assumes the list file contains all names.\n"; helpString += "The label parameter is used to read specific labels in your input you want to use.\n"; helpString += "The parse.list command should be used in the following format: parse.list(list=yourListFile, group=yourGroupFile, label=yourLabels).\n"; helpString += "Example: parse.list(list=abrecovery.fn.list, group=abrecovery.groups, label=0.03).\n"; - helpString += "Note: No spaces between parameter labels (i.e. list), '=' and parameters (i.e.yourListfile).\n\n"; + helpString += "Note: No spaces between parameter labels (i.e. list), '=' and parameters (i.e.yourListfile).\n"; return helpString; } catch(exception& e) { @@ -46,6 +49,21 @@ string ParseListCommand::getHelpString(){ } } //********************************************************************************************************************** +string ParseListCommand::getOutputPattern(string type) { + try { + string pattern = ""; + + if (type == "list") { pattern = "[filename],[group],list"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "ParseListCommand", "getOutputPattern"); + exit(1); + } +} +//********************************************************************************************************************** ParseListCommand::ParseListCommand(){ try { abort = true; calledHelp = true; @@ -66,6 +84,7 @@ ParseListCommand::ParseListCommand(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 { vector myArray = setParameters(); @@ -105,11 +124,18 @@ ParseListCommand::ParseListCommand(string option) { //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["group"] = inputDir + it->second; } } + + it = parameters.find("count"); + //user has given a template file + if(it != parameters.end()){ + path = m->hasPath(it->second); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { parameters["count"] = inputDir + it->second; } + } } - //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 = ""; } + //check for required parameters listfile = validParameter.validFile(parameters, "list", true); @@ -122,28 +148,40 @@ ParseListCommand::ParseListCommand(string option) { abort = true; } - } + }else { m->setListFile(listfile); } + + //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(listfile); } - groupfile = validParameter.validFile(parameters, "group", true); - if (groupfile == "not open") { abort = true; } - else if (groupfile == "not found") { - groupfile = m->getListFile(); - if (groupfile != "") { - m->mothurOut("Using " + groupfile + " as input file for the group parameter."); m->mothurOutEndLine(); - groupMap = new GroupMap(groupfile); - - int error = groupMap->readMap(); - if (error == 1) { abort = true; } - }else { m->mothurOut("No valid current group file. You must provide a group file."); m->mothurOutEndLine(); abort = true; } - }else { + groupfile = validParameter.validFile(parameters, "group", true); + if (groupfile == "not found") { groupfile = ""; groupMap = NULL; } + else if (groupfile == "not open") { abort = true; groupfile = ""; groupMap = NULL; } + else { + m->setGroupFile(groupfile); groupMap = new GroupMap(groupfile); int error = groupMap->readMap(); if (error == 1) { abort = true; } - } - - //do you have all files needed - if ((listfile == "") || (groupfile == "")) { m->mothurOut("You must enter both a listfile and groupfile for the parse.list command. "); m->mothurOutEndLine(); abort = true; } + } + + countfile = validParameter.validFile(parameters, "count", true); + if (countfile == "not found") { countfile = ""; } + else if (countfile == "not open") { abort = true; countfile = ""; } + else { + m->setCountTableFile(countfile); + ct.readTable(countfile); + if (!ct.hasGroupInfo()) { + abort = true; + m->mothurOut("[ERROR]: The parse.list command requires group info to be present in your countfile, quitting."); m->mothurOutEndLine(); + } + + } + + if ((groupfile != "") && (countfile != "")) { + m->mothurOut("[ERROR]: you may only use one of the following: group or count."); m->mothurOutEndLine(); abort=true; + }else if ((groupfile == "") && (countfile == "")) { + m->mothurOut("[ERROR]: you must provide one of the following: group or count."); m->mothurOutEndLine(); abort=true; + } //check for optional parameter and set defaults // ...at some point should added some additional type checking... @@ -168,16 +206,22 @@ int ParseListCommand::execute(){ if (abort == true) { if (calledHelp) { return 0; } return 2; } //set fileroot - string fileroot = outputDir + m->getRootName(m->getSimpleName(listfile)); + map variables; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(listfile)); //fill filehandles with neccessary ofstreams int i; ofstream* temp; - for (i=0; inamesOfGroups.size(); i++) { + vector gGroups; + if (groupfile != "") { gGroups = groupMap->getNamesOfGroups(); } + else { gGroups = ct.getNamesOfGroups(); } + + for (i=0; inamesOfGroups[i]] = temp; + filehandles[gGroups[i]] = temp; - string filename = fileroot + groupMap->namesOfGroups[i] + ".list"; + variables["[group]"] = gGroups[i]; + string filename = getOutputFileName("list",variables); outputNames.push_back(filename); outputTypes["list"].push_back(filename); m->openOutputFile(filename, *temp); } @@ -186,23 +230,23 @@ int ParseListCommand::execute(){ set processedLabels; set userLabels = labels; - input = new InputData(listfile, "list"); - list = input->getListVector(); + InputData input(listfile, "list"); + list = input.getListVector(); string lastLabel = list->getLabel(); if (m->control_pressed) { - delete input; delete list; delete groupMap; - for (i=0; inamesOfGroups.size(); i++) { (*(filehandles[groupMap->namesOfGroups[i]])).close(); delete filehandles[groupMap->namesOfGroups[i]]; } - for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } outputTypes.clear(); + delete list; if (groupfile != "") { delete groupMap; } + for (i=0; imothurRemove(outputNames[i]); } outputTypes.clear(); return 0; } while((list != NULL) && ((allLines == 1) || (userLabels.size() != 0))) { if (m->control_pressed) { - delete input; delete list; delete groupMap; - for (i=0; inamesOfGroups.size(); i++) { (*(filehandles[groupMap->namesOfGroups[i]])).close(); delete filehandles[groupMap->namesOfGroups[i]]; } - for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } outputTypes.clear(); + delete list; if (groupfile != "") { delete groupMap; } + for (i=0; imothurRemove(outputNames[i]); } outputTypes.clear(); return 0; } @@ -218,8 +262,7 @@ int ParseListCommand::execute(){ if ((m->anyLabelsToProcess(list->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { string saveLabel = list->getLabel(); - delete list; - list = input->getListVector(lastLabel); //get new list vector to process + list = input.getListVector(lastLabel); //get new list vector to process m->mothurOut(list->getLabel()); m->mothurOutEndLine(); parse(list); @@ -235,14 +278,14 @@ int ParseListCommand::execute(){ lastLabel = list->getLabel(); delete list; - list = input->getListVector(); //get new list vector to process + list = input.getListVector(); //get new list vector to process } if (m->control_pressed) { - delete input; delete groupMap; - for (i=0; inamesOfGroups.size(); i++) { (*(filehandles[groupMap->namesOfGroups[i]])).close(); delete filehandles[groupMap->namesOfGroups[i]]; } - for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } outputTypes.clear(); - return 0; + if (groupfile != "") { delete groupMap; } + for (i=0; imothurRemove(outputNames[i]); } outputTypes.clear(); + return 0; } //output error messages about any remaining user labels @@ -260,16 +303,16 @@ int ParseListCommand::execute(){ } if (m->control_pressed) { - delete input; delete groupMap; - for (i=0; inamesOfGroups.size(); i++) { (*(filehandles[groupMap->namesOfGroups[i]])).close(); delete filehandles[groupMap->namesOfGroups[i]]; } - for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } outputTypes.clear(); - return 0; + if (groupfile != "") { delete groupMap; } + for (i=0; imothurRemove(outputNames[i]); } outputTypes.clear(); + return 0; } //run last label if you need to if (needToRun == true) { if (list != NULL) { delete list; } - list = input->getListVector(lastLabel); //get new list vector to process + list = input.getListVector(lastLabel); //get new list vector to process m->mothurOut(list->getLabel()); m->mothurOutEndLine(); parse(list); @@ -282,12 +325,10 @@ int ParseListCommand::execute(){ delete it3->second; } - - delete groupMap; - delete input; + if (groupfile != "") { delete groupMap; } if (m->control_pressed) { - for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } outputTypes.clear(); + for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } outputTypes.clear(); return 0; } @@ -336,17 +377,33 @@ int ParseListCommand::parse(ListVector* thisList) { //parse bin into list of sequences in each group for (int j = 0; j < names.size(); j++) { - string group = groupMap->getGroup(names[j]); + if (groupfile != "") { + string group = groupMap->getGroup(names[j]); - if (group == "not found") { m->mothurOut(names[j] + " is not in your groupfile. please correct."); m->mothurOutEndLine(); exit(1); } + if (group == "not found") { m->mothurOut(names[j] + " is not in your groupfile. please correct."); m->mothurOutEndLine(); exit(1); } - itGroup = groupBins.find(group); - if(itGroup == groupBins.end()) { - groupBins[group] = names[j]; //add first name - groupNumBins[group]++; - }else{ //add another name - groupBins[group] = groupBins[group] + "," + names[j]; - } + itGroup = groupBins.find(group); + if(itGroup == groupBins.end()) { + groupBins[group] = names[j]; //add first name + groupNumBins[group]++; + }else{ //add another name + groupBins[group] = groupBins[group] + "," + names[j]; + } + }else{ + vector thisSeqsGroups = ct.getGroups(names[j]); + + for (int k = 0; k < thisSeqsGroups.size(); k++) { + string group = thisSeqsGroups[k]; + itGroup = groupBins.find(group); + if(itGroup == groupBins.end()) { + groupBins[group] = names[j]; //add first name + groupNumBins[group]++; + }else{ //add another name + groupBins[group] = groupBins[group] + "," + names[j]; + } + + } + } } //print parsed bin info to files