else {
//valid paramters for this command
- string Array[] = {"fasta", "trump", "soft", "hard", "vertical"};
+ string Array[] = {"fasta", "trump", "soft", "hard", "vertical", "outputdir","inputdir"};
vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
OptionParser parser(option);
map<string,string> parameters = parser.getParameters();
ValidParameters validParameter;
+ map<string,string>::iterator it;
//check to make sure all parameters are valid for command
- for (map<string,string>::iterator it = parameters.begin(); it != parameters.end(); it++) {
+ for (it = parameters.begin(); it != parameters.end(); it++) {
if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
}
+ //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 = ""; }
+ else {
+ string path;
+ it = parameters.find("fasta");
+ //user has given a template file
+ if(it != parameters.end()){
+ path = hasPath(it->second);
+ //if the user has not given a path then, add inputdir. else leave path alone.
+ if (path == "") { parameters["fasta"] = inputDir + it->second; }
+ }
+
+ it = parameters.find("hard");
+ //user has given a template file
+ if(it != parameters.end()){
+ path = hasPath(it->second);
+ //if the user has not given a path then, add inputdir. else leave path alone.
+ if (path == "") { parameters["hard"] = inputDir + it->second; }
+ }
+ }
+
//check for required parameters
fastafile = validParameter.validFile(parameters, "fasta", true);
- if (fastafile == "not found") { cout << "fasta is a required parameter for the filter.seqs command." << endl; abort = 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; }
+
+ //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 = "";
+ outputDir += hasPath(fastafile); //if user entered a file with a path then preserve it
+ }
//check for optional parameter and set defaults
// ...at some point should added some additional type checking...
numSeqs = 0;
+ if (abort == false) {
+
+ if (soft != 0) { F.setSoft(soft); }
+ if (trump != '*') { F.setTrump(trump); }
+
+ }
+
}
}
catch(exception& e) {
- cout << "Standard Error: " << e.what() << " has occurred in the FilterSeqsCommand class Function FilterSeqsCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
+ errorOut(e, "FilterSeqsCommand", "FilterSeqsCommand");
exit(1);
}
- catch(...) {
- cout << "An unknown error has occurred in the FilterSeqsCommand class function FilterSeqsCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
- exit(1);
- }
}
//**********************************************************************************************************************
void FilterSeqsCommand::help(){
try {
- cout << "The filter.seqs command reads a file containing sequences and creates a .filter and .filter.fasta file." << "\n";
- cout << "The filter.seqs command parameters are fasta, trump, soft, hard and vertical. " << "\n";
- cout << "The fasta parameter is required." << "\n";
- cout << "The trump parameter .... The default is ..." << "\n";
- cout << "The soft parameter .... The default is ...." << "\n";
- cout << "The hard parameter .... The default is ...." << "\n";
- cout << "The vertical parameter .... The default is T." << "\n";
- cout << "The filter.seqs command should be in the following format: " << "\n";
- cout << "filter.seqs(fasta=yourFastaFile, trump=yourTrump, soft=yourSoft, hard=yourHard, vertical=yourVertical) " << "\n";
- cout << "Example filter.seqs(fasta=abrecovery.fasta, trump=..., soft=..., hard=..., vertical=T)." << "\n";
- cout << "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta)." << "\n" << "\n";
+ 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");
}
catch(exception& e) {
- cout << "Standard Error: " << e.what() << " has occurred in the FilterSeqsCommand class Function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
- exit(1);
- }
- catch(...) {
- cout << "An unknown error has occurred in the FilterSeqsCommand class function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
+ errorOut(e, "FilterSeqsCommand", "help");
exit(1);
- }
-}
-
-/**************************************************************************************/
-
-void FilterSeqsCommand::doHard() {
-
- ifstream fileHandle;
- openInputFile(hard, 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';
- }
- }
-
-}
-
-/**************************************************************************************/
-
-void FilterSeqsCommand::doVertical() {
-
- for(int i=0;i<alignmentLength;i++){
- if(gap[i] == numSeqs) { filter[i] = '0'; }
- }
-
-}
-
-/**************************************************************************************/
-
-void FilterSeqsCommand::doSoft() {
-
- int threshold = int (soft * numSeqs);
-
- for(int i=0;i<alignmentLength;i++){
- if(a[i] < threshold && t[i] < threshold && g[i] < threshold && c[i] < threshold){ 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]++; }
- }
-
-}
-
-/**************************************************************************************/
-
int FilterSeqsCommand::execute() {
try {
alignmentLength = testSeq.getAlignLength();
inFASTA.seekg(0);
+ F.setLength(alignmentLength);
+
if(soft != 0 || isTrue(vertical)){
- a.assign(alignmentLength, 0);
- t.assign(alignmentLength, 0);
- g.assign(alignmentLength, 0);
- c.assign(alignmentLength, 0);
- gap.assign(alignmentLength, 0);
+ F.initialize();
}
- if(hard.compare("") != 0) { doHard(); }
- else { filter = string(alignmentLength, '1'); }
+ if(hard.compare("") != 0) { F.doHard(hard); }
+ else { F.setFilter(string(alignmentLength, '1')); }
if(trump != '*' || isTrue(vertical) || soft != 0){
while(!inFASTA.eof()){ //read through and create the filter...
Sequence seq(inFASTA);
- if(trump != '*'){ doTrump(seq); }
- if(isTrue(vertical) || soft != 0){ getFreqs(seq); }
- numSeqs++;
- cout.flush();
+ if (seq.getName() != "") {
+ if(trump != '*'){ F.doTrump(seq); }
+ if(isTrue(vertical) || soft != 0){ F.getFreqs(seq); }
+ numSeqs++;
+ cout.flush();
+ }
}
}
inFASTA.close();
+ F.setNumSeqs(numSeqs);
+
- if(isTrue(vertical) == 1) { doVertical(); }
- if(soft != 0) { doSoft(); }
+ if(isTrue(vertical) == 1) { F.doVertical(); }
+ if(soft != 0) { F.doSoft(); }
+
+ filter = F.getFilter();
ofstream outFilter;
- string filterFile = getRootName(fastafile) + "filter";
+ string filterFile = outputDir + getRootName(getSimpleName(fastafile)) + "filter";
openOutputFile(filterFile, outFilter);
outFilter << filter << endl;
outFilter.close();
-
- openInputFile(fastafile, inFASTA);
- string filteredFasta = getRootName(fastafile) + "filter.fasta";
+ ifstream inFasta2;
+ openInputFile(fastafile, inFasta2);
+ string filteredFasta = outputDir + getRootName(getSimpleName(fastafile)) + "filter.fasta";
ofstream outFASTA;
openOutputFile(filteredFasta, outFASTA);
numSeqs = 0;
- while(!inFASTA.eof()){
- Sequence seq(inFASTA);
- string align = seq.getAligned();
- string filterSeq = "";
-
- for(int j=0;j<alignmentLength;j++){
- if(filter[j] == '1'){
- filterSeq += align[j];
+ while(!inFasta2.eof()){
+ Sequence seq(inFasta2);
+ if (seq.getName() != "") {
+ string align = seq.getAligned();
+ string filterSeq = "";
+
+ for(int j=0;j<alignmentLength;j++){
+ if(filter[j] == '1'){
+ filterSeq += align[j];
+ }
}
+
+ outFASTA << '>' << seq.getName() << endl << filterSeq << endl;
+ numSeqs++;
}
-
- 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;
+ 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);
}
}