#include "parselistscommand.h"
+//**********************************************************************************************************************
+vector<string> ParseListCommand::setParameters(){
+ try {
+ 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<string> myArray;
+ for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); }
+ return myArray;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ParseListCommand", "setParameters");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+string ParseListCommand::getHelpString(){
+ try {
+ string helpString = "";
+ 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";
+ return helpString;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ParseListCommand", "getHelpString");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+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;
+ setParameters();
+ vector<string> tempOutNames;
+ outputTypes["list"] = tempOutNames;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ParseListCommand", "ParseListCommand");
+ exit(1);
+ }
+}
//**********************************************************************************************************************
ParseListCommand::ParseListCommand(string option) {
try {
- abort = false;
+ abort = false; calledHelp = false;
allLines = 1;
//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[] = {"list","group", "label", "outputdir","inputdir"};
- vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+ vector<string> myArray = setParameters();
OptionParser parser(option);
map<string, string> parameters = parser.getParameters();
for (it = parameters.begin(); it != parameters.end(); it++) {
if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
}
-
+
+ //initialize outputTypes
+ vector<string> tempOutNames;
+ outputTypes["list"] = 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 = ""; }
it = parameters.find("list");
//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["list"] = inputDir + it->second; }
}
it = parameters.find("group");
//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["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);
if (listfile == "not open") { abort = true; }
- else if (listfile == "not found") { listfile = ""; }
+ else if (listfile == "not found") {
+ listfile = m->getListFile();
+ if (listfile != "") { m->mothurOut("Using " + listfile + " as input file for the list parameter."); m->mothurOutEndLine(); }
+ else {
+ m->mothurOut("No valid current list file. You must provide a list file."); m->mothurOutEndLine();
+ 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 = ""; }
- 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, true);
+ 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...
label = validParameter.validFile(parameters, "label", false);
if (label == "not found") { label = ""; allLines = 1; }
else {
- if(label != "all") { splitAtDash(label, labels); allLines = 0; }
+ if(label != "all") { m->splitAtDash(label, labels); allLines = 0; }
else { allLines = 1; }
}
}
}
}
//**********************************************************************************************************************
-void ParseListCommand::help(){
- try {
- m->mothurOut("The parse.list command reads a list and group file and generates a list file for each group in the groupfile. \n");
- m->mothurOut("The parse.list command parameters are list, group and label.\n");
- m->mothurOut("The list and group parameters are required.\n");
- m->mothurOut("The label parameter is used to read specific labels in your input you want to use.\n");
- m->mothurOut("The parse.list command should be used in the following format: parse.list(list=yourListFile, group=yourGroupFile, label=yourLabels).\n");
- m->mothurOut("Example: parse.list(list=abrecovery.fn.list, group=abrecovery.groups, label=0.03).\n");
- m->mothurOut("Note: No spaces between parameter labels (i.e. list), '=' and parameters (i.e.yourListfile).\n\n");
-
- }
- catch(exception& e) {
- m->errorOut(e, "ParseListCommand", "help");
- exit(1);
- }
-}
-//**********************************************************************************************************************
-ParseListCommand::~ParseListCommand(){}
-//**********************************************************************************************************************
int ParseListCommand::execute(){
try {
- if (abort == true) { return 0; }
+ if (abort == true) { if (calledHelp) { return 0; } return 2; }
//set fileroot
- string fileroot = outputDir + getRootName(getSimpleName(listfile));
- vector<string> outputNames;
+ map<string, string> variables;
+ variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(listfile));
//fill filehandles with neccessary ofstreams
int i;
ofstream* temp;
- for (i=0; i<groupMap->namesOfGroups.size(); i++) {
+ vector<string> gGroups;
+ if (groupfile != "") { gGroups = groupMap->getNamesOfGroups(); }
+ else { gGroups = ct.getNamesOfGroups(); }
+
+ for (i=0; i<gGroups.size(); i++) {
temp = new ofstream;
- filehandles[groupMap->namesOfGroups[i]] = temp;
+ filehandles[gGroups[i]] = temp;
- string filename = fileroot + groupMap->namesOfGroups[i] + ".list";
- outputNames.push_back(filename);
- openOutputFile(filename, *temp);
+ variables["[group]"] = gGroups[i];
+ string filename = getOutputFileName("list",variables);
+ outputNames.push_back(filename); outputTypes["list"].push_back(filename);
+ m->openOutputFile(filename, *temp);
}
//if the users enters label "0.06" and there is no "0.06" in their file use the next lowest label.
set<string> processedLabels;
set<string> 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; i<groupMap->namesOfGroups.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()); }
+ delete list; if (groupfile != "") { delete groupMap; }
+ for (i=0; i<gGroups.size(); i++) { (*(filehandles[gGroups[i]])).close(); delete filehandles[gGroups[i]]; }
+ for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(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; i<groupMap->namesOfGroups.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()); }
+ delete list; if (groupfile != "") { delete groupMap; }
+ for (i=0; i<gGroups.size(); i++) { (*(filehandles[gGroups[i]])).close(); delete filehandles[gGroups[i]]; }
+ for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } outputTypes.clear();
return 0;
}
userLabels.erase(list->getLabel());
}
- if ((anyLabelsToProcess(list->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) {
+ 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);
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; i<groupMap->namesOfGroups.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()); }
- return 0;
+ if (groupfile != "") { delete groupMap; }
+ for (i=0; i<gGroups.size(); i++) { (*(filehandles[gGroups[i]])).close(); delete filehandles[gGroups[i]]; }
+ for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } outputTypes.clear();
+ return 0;
}
//output error messages about any remaining user labels
}
if (m->control_pressed) {
- delete input; delete groupMap;
- for (i=0; i<groupMap->namesOfGroups.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()); }
- return 0;
+ if (groupfile != "") { delete groupMap; }
+ for (i=0; i<gGroups.size(); i++) { (*(filehandles[gGroups[i]])).close(); delete filehandles[gGroups[i]]; }
+ for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(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);
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()); }
+ for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } outputTypes.clear();
return 0;
}
+ //set fasta file as new current fastafile
+ string current = "";
+ itTypes = outputTypes.find("list");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setListFile(current); }
+ }
+
m->mothurOutEndLine();
m->mothurOut("Output File Names: "); m->mothurOutEndLine();
for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
string bin = list->get(i);
vector<string> names;
- splitAtComma(bin, names); //parses bin into individual sequence names
+ m->splitAtComma(bin, names); //parses bin into individual sequence names
//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<string> 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