#include "binsequencecommand.h"
//**********************************************************************************************************************
-BinSeqCommand::BinSeqCommand(){
+BinSeqCommand::BinSeqCommand(string option){
try {
globaldata = GlobalData::getInstance();
- fastafile = globaldata->getFastaFile();
- namesfile = globaldata->getNameFile();
- groupfile = globaldata->getGroupFile();
- openInputFile(fastafile, in);
+ abort = false;
+ allLines = 1;
+ lines.clear();
+ labels.clear();
- if (groupfile != "") {
- //read in group map info.
- groupMap = new GroupMap(groupfile);
- groupMap->readMap();
- }
+ //allow user to run help
+ if(option == "help") { help(); abort = true; }
+
+ else {
+ //valid paramters for this command
+ string AlignArray[] = {"fasta","line","label","name", "group"};
+ vector<string> myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string)));
+
+ OptionParser parser(option);
+ map<string, string> parameters = parser.getParameters();
+
+ ValidParameters validParameter;
+
+ //check to make sure all parameters are valid for command
+ for (map<string, string>::iterator it = parameters.begin(); it != parameters.end(); it++) {
+ if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
+ }
+
+ //make sure the user has already run the read.otu command
+ if (globaldata->getListFile() == "") { cout << "You must read a listfile before running the bin.seqs command." << endl; abort = true; }
+
+
+ //check for required parameters
+ fastafile = validParameter.validFile(parameters, "fasta", true);
+ if (fastafile == "not found") { cout << "fasta is a required parameter for the bin.seqs command." << endl; abort = true; }
+ else if (fastafile == "not open") { abort = true; }
- fasta = new FastaMap();
+ //check for optional parameter and set defaults
+ // ...at some point should added some additional type checking...
+ line = validParameter.validFile(parameters, "line", false);
+ if (line == "not found") { line = ""; }
+ else {
+ if(line != "all") { splitAtDash(line, lines); allLines = 0; }
+ else { allLines = 1; }
+ }
+
+ label = validParameter.validFile(parameters, "label", false);
+ if (label == "not found") { label = ""; }
+ else {
+ if(label != "all") { splitAtDash(label, labels); allLines = 0; }
+ else { allLines = 1; }
+ }
+
+ //make sure user did not use both the line and label parameters
+ if ((line != "") && (label != "")) { cout << "You cannot use both the line and label parameters at the same time. " << endl; abort = true; }
+ //if the user has not specified any line or labels use the ones from read.otu
+ else if ((line == "") && (label == "")) {
+ allLines = globaldata->allLines;
+ labels = globaldata->labels;
+ lines = globaldata->lines;
+ }
+
+ namesfile = validParameter.validFile(parameters, "name", true);
+ if (namesfile == "not open") { abort = true; }
+ else if (namesfile == "not found") { namesfile = ""; }
+
+ groupfile = validParameter.validFile(parameters, "group", true);
+ if (groupfile == "not open") { abort = true; }
+ else if (groupfile == "not found") { groupfile = ""; }
+
+ if (abort == false) {
+ openInputFile(fastafile, in);
+ fasta = new FastaMap();
+ if (groupfile != "") {
+ groupMap = new GroupMap(groupfile);
+ groupMap->readMap();
+ }
+ }
+
+ }
}
catch(exception& e) {
cout << "Standard Error: " << e.what() << " has occurred in the BinSeqCommand class Function BinSeqCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
exit(1);
}
}
+//**********************************************************************************************************************
+
+void BinSeqCommand::help(){
+ try {
+ cout << "The bin.seqs command can only be executed after a successful read.otu command of a listfile." << "\n";
+ cout << "The bin.seqs command parameters are fasta, name, line, label and group. The fasta parameter is required, and you may not use line and label at the same time." << "\n";
+ cout << "The line and label allow you to select what distance levels you would like a output files created for, and are separated by dashes." << "\n";
+ cout << "The bin.seqs command should be in the following format: bin.seqs(fasta=yourFastaFile, name=yourNamesFile, group=yourGroupFile, line=yourLines, label=yourLabels)." << "\n";
+ cout << "Example bin.seqs(fasta=amazon.fasta, group=amazon.groups, line=1-3-5, name=amazon.names)." << "\n";
+ cout << "The default value for line and label are all lines in your inputfile." << "\n";
+ cout << "The bin.seqs command outputs a .fasta file for each distance you specify appending the OTU number to each name." << "\n";
+ cout << "If you provide a groupfile, then it also appends the sequences group to the name." << "\n";
+ cout << "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile)." << "\n" << "\n";
+ }
+ catch(exception& e) {
+ cout << "Standard Error: " << e.what() << " has occurred in the BinSeqCommand class Function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
+ exit(1);
+ }
+ catch(...) {
+ cout << "An unknown error has occurred in the BinSeqCommand class function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
+ exit(1);
+ }
+}
+
+
//**********************************************************************************************************************
BinSeqCommand::~BinSeqCommand(){
- delete input;
- delete read;
- delete fasta;
- delete list;
- if (groupfile != "") {
- delete groupMap;
+ //made new in execute
+ if (abort == false) {
+ delete input; globaldata->ginput = NULL;
+ delete read;
+ globaldata->gListVector = NULL;
+ delete fasta;
+ if (groupfile != "") { delete groupMap; globaldata->gGroupmap = NULL; }
}
}
int BinSeqCommand::execute(){
try {
+ if (abort == true) { return 0; }
+
int count = 1;
int error = 0;
//read fastafile
fasta->readFastaFile(in);
+ in.close();
+
//set format to list so input can get listvector
- globaldata->setFormat("list");
+// globaldata->setFormat("list");
//if user gave a namesfile then use it
if (namesfile != "") {
//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 = globaldata->labels;
+ set<string> userLabels = labels;
+ set<int> userLines = lines;
- while((list != NULL) && ((globaldata->allLines == 1) || (userLabels.size() != 0))) {
+ while((list != NULL) && ((allLines == 1) || (userLabels.size() != 0) || (userLines.size() != 0))) {
- if(globaldata->allLines == 1 || globaldata->lines.count(count) == 1 || globaldata->labels.count(list->getLabel()) == 1){
+ if(allLines == 1 || lines.count(count) == 1 || labels.count(list->getLabel()) == 1){
error = process(list, count);
if (error == 1) { return 0; }
processedLabels.insert(list->getLabel());
userLabels.erase(list->getLabel());
-
+ userLines.erase(count);
}
if ((anyLabelsToProcess(list->getLabel(), userLabels, "") == true) && (processedLabels.count(lastList->getLabel()) != 1)) {