*/
#include "filterseqscommand.h"
+#include "sequence.hpp"
/**************************************************************************************/
-FilterSeqsCommand::FilterSeqsCommand(){
-
- globaldata = GlobalData::getInstance();
-
- if(globaldata->getFastaFile() == "") { cout << "You must enter a fasta formatted file" << endl; }
- trump = globaldata->getTrump()[0];
- numSeqs = 0;
-
-}
-
-/**************************************************************************************/
-
-void FilterSeqsCommand::doHard() {
-
- string hardName = globaldata->getHard();
- string hardFilter = "";
+FilterSeqsCommand::FilterSeqsCommand(string option){
+ try {
+ abort = false;
- ifstream fileHandle;
- openInputFile(hardName, fileHandle);
-
- fileHandle >> filter;
-
-}
-
-/**************************************************************************************/
-
-void FilterSeqsCommand::doTrump(Sequence seq) {
-
- string curAligned = seq.getAligned();
-
- for(int j = 0; j < alignmentLength; j++) {
- if(curAligned[j] == trump){
- filter[j] = '0';
+ //allow user to run help
+ if(option == "help") { help(); abort = true; }
+
+ else {
+ //valid paramters for this command
+ string Array[] = {"fasta", "trump", "soft", "hard", "vertical"};
+ vector<string> myArray (Array, Array+(sizeof(Array)/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; }
+ }
+
+ //check for required parameters
+ fastafile = validParameter.validFile(parameters, "fasta", true);
+ if (fastafile == "not found") { mothurOut("fasta is a required parameter for the filter.seqs command."); mothurOutEndLine(); abort = true; }
+ else if (fastafile == "not open") { abort = true; }
+
+ //check for optional parameter and set defaults
+ // ...at some point should added some additional type checking...
+
+ string temp;
+ temp = validParameter.validFile(parameters, "trump", false); if (temp == "not found") { temp = "*"; }
+ trump = temp[0];
+
+ temp = validParameter.validFile(parameters, "soft", false); if (temp == "not found") { soft = 0; }
+ else { soft = (float)atoi(temp.c_str()) / 100.0; }
+
+ hard = validParameter.validFile(parameters, "hard", true); if (hard == "not found") { hard = ""; }
+ else if (hard == "not open") { abort = true; }
+
+ vertical = validParameter.validFile(parameters, "vertical", false); if (vertical == "not found") { vertical = "T"; }
+
+ numSeqs = 0;
+
+ if (abort == false) {
+
+ if (soft != 0) { F.setSoft(soft); }
+ if (trump != '*') { F.setTrump(trump); }
+
+ }
+
}
+
}
-
-}
-
-/**************************************************************************************/
-
-void FilterSeqsCommand::doVertical() {
-
- for(int i=0;i<alignmentLength;i++){
- if(gap[i] == numSeqs) { filter[i] = '0'; }
+ catch(exception& e) {
+ errorOut(e, "FilterSeqsCommand", "FilterSeqsCommand");
+ exit(1);
}
-
}
-/**************************************************************************************/
+//**********************************************************************************************************************
-void FilterSeqsCommand::doSoft() {
-
- int threshold = int (soft * numSeqs);
- bool keep = 0;
-
- for(int i=0;i<alignmentLength;i++){
- if(a[i] >= threshold) { keep = 1; }
- else if(t[i] >= threshold) { keep = 1; }
- else if(g[i] >= threshold) { keep = 1; }
- else if(c[i] >= threshold) { keep = 1; }
+void FilterSeqsCommand::help(){
+ try {
+ mothurOut("The filter.seqs command reads a file containing sequences and creates a .filter and .filter.fasta file.\n");
+ mothurOut("The filter.seqs command parameters are fasta, trump, soft, hard and vertical. \n");
+ mothurOut("The fasta parameter is required.\n");
+ mothurOut("The trump parameter .... The default is ...\n");
+ mothurOut("The soft parameter .... The default is ....\n");
+ mothurOut("The hard parameter .... The default is ....\n");
+ mothurOut("The vertical parameter .... The default is T.\n");
+ mothurOut("The filter.seqs command should be in the following format: \n");
+ mothurOut("filter.seqs(fasta=yourFastaFile, trump=yourTrump, soft=yourSoft, hard=yourHard, vertical=yourVertical) \n");
+ mothurOut("Example filter.seqs(fasta=abrecovery.fasta, trump=..., soft=..., hard=..., vertical=T).\n");
+ mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n");
- if(keep == 0) { filter[i] = 0; }
}
-
-}
-
-/**************************************************************************************/
-
-void FilterSeqsCommand::getFreqs(Sequence seq) {
-
- string curAligned = seq.getAligned();;
-
- for(int j=0;j<alignmentLength;j++){
- if(toupper(curAligned[j]) == 'A') { a[j]++; }
- else if(toupper(curAligned[j]) == 'T' || toupper(curAligned[j]) == 'U') { t[j]++; }
- else if(toupper(curAligned[j]) == 'G') { g[j]++; }
- else if(toupper(curAligned[j]) == 'C') { c[j]++; }
- else if(curAligned[j] == '-' || curAligned[j] == '.') { gap[j]++; }
+ catch(exception& e) {
+ errorOut(e, "FilterSeqsCommand", "help");
+ exit(1);
}
-
}
/**************************************************************************************/
int FilterSeqsCommand::execute() {
try {
+
+ if (abort == true) { return 0; }
+
ifstream inFASTA;
- openInputFile(globaldata->getFastaFile(), inFASTA);
+ openInputFile(fastafile, inFASTA);
Sequence testSeq(inFASTA);
alignmentLength = testSeq.getAlignLength();
inFASTA.seekg(0);
- if(globaldata->getSoft() != "" || isTrue(globaldata->getVertical())){
- a.assign(alignmentLength, 0);
- t.assign(alignmentLength, 0);
- g.assign(alignmentLength, 0);
- c.assign(alignmentLength, 0);
- gap.assign(alignmentLength, 0);
- }
- if(globaldata->getSoft() != ""){
- soft = (float)atoi(globaldata->getSoft().c_str()) / 100.0;
+ F.setLength(alignmentLength);
+
+ if(soft != 0 || isTrue(vertical)){
+ F.initialize();
}
- if(globaldata->getHard().compare("") != 0) { doHard(); }
- else { filter = string(alignmentLength, '1'); }
+ if(hard.compare("") != 0) { F.doHard(hard); }
+ else { F.setFilter(string(alignmentLength, '1')); }
- if(globaldata->getTrump().compare("") != 0 || isTrue(globaldata->getVertical()) || globaldata->getSoft().compare("") != 0){
-
- while(!inFASTA.eof()){
+ if(trump != '*' || isTrue(vertical) || soft != 0){
+ while(!inFASTA.eof()){ //read through and create the filter...
Sequence seq(inFASTA);
- if(globaldata->getTrump().compare("") != 0) { doTrump(seq); }
- if(isTrue(globaldata->getVertical()) || globaldata->getSoft().compare("") != 0){ getFreqs(seq); }
+ if(trump != '*'){ F.doTrump(seq); }
+ if(isTrue(vertical) || soft != 0){ F.getFreqs(seq); }
numSeqs++;
cout.flush();
}
}
inFASTA.close();
+ F.setNumSeqs(numSeqs);
- if(isTrue(globaldata->getVertical()) == 1) { doVertical(); }
- if(globaldata->getSoft().compare("") != 0) { doSoft(); }
+
+ if(isTrue(vertical) == 1) { F.doVertical(); }
+ if(soft != 0) { F.doSoft(); }
+
+ filter = F.getFilter();
ofstream outFilter;
- string filterFile = getRootName(globaldata->inputFileName) + "filter";
+ string filterFile = getRootName(fastafile) + "filter";
openOutputFile(filterFile, outFilter);
outFilter << filter << endl;
outFilter.close();
-
- openInputFile(globaldata->getFastaFile(), inFASTA);
- string filteredFasta = getRootName(globaldata->inputFileName) + "filter.fasta";
+ ifstream inFasta2;
+ openInputFile(fastafile, inFasta2);
+ string filteredFasta = getRootName(fastafile) + "filter.fasta";
ofstream outFASTA;
openOutputFile(filteredFasta, outFASTA);
numSeqs = 0;
- while(!inFASTA.eof()){
- Sequence seq(inFASTA);
+ while(!inFasta2.eof()){
+ Sequence seq(inFasta2);
string align = seq.getAligned();
string filterSeq = "";
outFASTA << '>' << seq.getName() << endl << filterSeq << endl;
numSeqs++;
- gobble(inFASTA);
+ gobble(inFasta2);
}
outFASTA.close();
- inFASTA.close();
+ inFasta2.close();
int filteredLength = 0;
if(filter[i] == '1'){ filteredLength++; }
}
- cout << endl;
- cout << "Length of filtered alignment: " << filteredLength << endl;
- cout << "Number of columns removed: " << alignmentLength-filteredLength << endl;
- cout << "Length of the original alignment: " << alignmentLength << endl;
- cout << "Number of sequences used to construct filter: " << numSeqs << endl;
-
- globaldata->clear();
+ mothurOutEndLine();
+ mothurOut("Length of filtered alignment: " + toString(filteredLength)); mothurOutEndLine();
+ mothurOut("Number of columns removed: " + toString((alignmentLength-filteredLength))); mothurOutEndLine();
+ mothurOut("Length of the original alignment: " + toString(alignmentLength)); mothurOutEndLine();
+ mothurOut("Number of sequences used to construct filter: " + toString(numSeqs)); mothurOutEndLine();
return 0;
}
catch(exception& e) {
- cout << "Standard Error: " << e.what() << " has occurred in the FilterSeqsCommand class Function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
- exit(1);
- }
- catch(...) {
- cout << "An unknown error has occurred in the FilterSeqsCommand class function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
+ errorOut(e, "FilterSeqsCommand", "execute");
exit(1);
}
}