inline bool comparePriority(seqPNode first, seqPNode second) { return (first.numIdentical > second.numIdentical); }
//**********************************************************************************************************************
-PreClusterCommand::PreClusterCommand(string option){
+PreClusterCommand::PreClusterCommand(string option) {
try {
abort = false;
//check for required parameters
fastafile = validParameter.validFile(parameters, "fasta", true);
- if (fastafile == "not found") { mothurOut("fasta is a required parameter for the pre.cluster command."); mothurOutEndLine(); abort = true; }
+ if (fastafile == "not found") { m->mothurOut("fasta is a required parameter for the pre.cluster command."); m->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
}
catch(exception& e) {
- errorOut(e, "PreClusterCommand", "PreClusterCommand");
+ m->errorOut(e, "PreClusterCommand", "PreClusterCommand");
exit(1);
}
}
void PreClusterCommand::help(){
try {
- mothurOut("The pre.cluster command groups sequences that are within a given number of base mismatches.\n");
- mothurOut("The pre.cluster command outputs a new fasta and name file.\n");
- mothurOut("The pre.cluster command parameters are fasta, names and diffs. The fasta parameter is required. \n");
- mothurOut("The names parameter allows you to give a list of seqs that are identical. This file is 2 columns, first column is name or representative sequence, second column is a list of its identical sequences separated by commas.\n");
- mothurOut("The diffs parameter allows you to specify maximum number of mismatched bases allowed between sequences in a grouping. The default is 1.\n");
- mothurOut("The pre.cluster command should be in the following format: \n");
- mothurOut("pre.cluster(fasta=yourFastaFile, names=yourNamesFile, diffs=yourMaxDiffs) \n");
- mothurOut("Example pre.cluster(fasta=amazon.fasta, diffs=2).\n");
- mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n");
+ m->mothurOut("The pre.cluster command groups sequences that are within a given number of base mismatches.\n");
+ m->mothurOut("The pre.cluster command outputs a new fasta and name file.\n");
+ m->mothurOut("The pre.cluster command parameters are fasta, names and diffs. The fasta parameter is required. \n");
+ m->mothurOut("The names parameter allows you to give a list of seqs that are identical. This file is 2 columns, first column is name or representative sequence, second column is a list of its identical sequences separated by commas.\n");
+ m->mothurOut("The diffs parameter allows you to specify maximum number of mismatched bases allowed between sequences in a grouping. The default is 1.\n");
+ m->mothurOut("The pre.cluster command should be in the following format: \n");
+ m->mothurOut("pre.cluster(fasta=yourFastaFile, names=yourNamesFile, diffs=yourMaxDiffs) \n");
+ m->mothurOut("Example pre.cluster(fasta=amazon.fasta, diffs=2).\n");
+ m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n");
}
catch(exception& e) {
- errorOut(e, "PreClusterCommand", "help");
+ m->errorOut(e, "PreClusterCommand", "help");
exit(1);
}
}
//reads fasta file and return number of seqs
int numSeqs = readFASTA(); //fills alignSeqs and makes all seqs active
+
+ if (m->control_pressed) { return 0; }
- if (numSeqs == 0) { mothurOut("Error reading fasta file...please correct."); mothurOutEndLine(); return 0; }
- if (diffs > length) { mothurOut("Error: diffs is greater than your sequence length."); mothurOutEndLine(); return 0; }
+ if (numSeqs == 0) { m->mothurOut("Error reading fasta file...please correct."); m->mothurOutEndLine(); return 0; }
+ if (diffs > length) { m->mothurOut("Error: diffs is greater than your sequence length."); m->mothurOutEndLine(); return 0; }
//clear sizes since you only needed this info to build the alignSeqs seqPNode structs
// sizes.clear();
//try to merge it with all smaller seqs
for (int j = i+1; j < numSeqs; j++) {
+
+ if (m->control_pressed) { return 0; }
+
if (alignSeqs[j].active) { //this sequence has not been merged yet
//are you within "diff" bases
int mismatch = calcMisMatches(alignSeqs[i].seq.getAligned(), alignSeqs[j].seq.getAligned());
string newFastaFile = fileroot + "precluster" + getExtension(fastafile);
string newNamesFile = fileroot + "precluster.names";
+ if (m->control_pressed) { return 0; }
- mothurOut("Total number of sequences before precluster was " + toString(alignSeqs.size()) + "."); mothurOutEndLine();
- mothurOut("pre.cluster removed " + toString(count) + " sequences."); mothurOutEndLine();
+ m->mothurOut("Total number of sequences before precluster was " + toString(alignSeqs.size()) + "."); m->mothurOutEndLine();
+ m->mothurOut("pre.cluster removed " + toString(count) + " sequences."); m->mothurOutEndLine();
printData(newFastaFile, newNamesFile);
+
+ if (m->control_pressed) { remove(newFastaFile.c_str()); remove(newNamesFile.c_str()); return 0; }
+
+ m->mothurOutEndLine();
+ m->mothurOut("Output File Names: "); m->mothurOutEndLine();
+ m->mothurOut(newFastaFile); m->mothurOutEndLine();
+ m->mothurOut(newNamesFile); m->mothurOutEndLine();
+ m->mothurOutEndLine();
return 0;
}
catch(exception& e) {
- errorOut(e, "PreClusterCommand", "execute");
- exit(1);
- }
-}
-/**************************************************************************************************
-int PreClusterCommand::readFASTA(){
- try {
-// ifstream inFasta;
-// openInputFile(fastafile, inFasta);
-// length = 0;
-//// map<string, string>::iterator it;
-//
-// while (!inFasta.eof()) {
-// Sequence temp(inFasta); //read seq
-//
-// if (temp.getName() != "") {
-// if (namefile != "") {
-// //make sure fasta and name files match
-// it = names.find(temp.getName());
-// if (it == names.end()) { mothurOut(temp.getName() + " is not in your names file, please correct."); mothurOutEndLine(); exit(1); }
-// }else { sizes[temp.getName()] = 1; }
-//
-// seqPNode tempNode(sizes[temp.getName()], temp);
-// alignSeqs.push_back(tempNode);
-// active[temp.getName()] = true;
-// }
-// gobble(inFasta);
-// }
-// inFasta.close();
-//
-// if (alignSeqs.size() != 0) { length = alignSeqs[0].seq.getAligned().length(); }
-//
- return alignSeqs.size();
- }
- catch(exception& e) {
- errorOut(e, "PreClusterCommand", "readFASTA");
+ m->errorOut(e, "PreClusterCommand", "execute");
exit(1);
}
}
+
/**************************************************************************************************/
-//this seems to require the names and fasta file to be in the same order???
+
+//this requires the names and fasta file to be in the same order
+
int PreClusterCommand::readFASTA(){
try {
//ifstream inNames;
length = 0;
while (!inFasta.eof()) {
-
+
+ if (m->control_pressed) { inFasta.close(); return 0; }
+
//inNames >> firstCol >> secondCol;
//nameString = secondCol;
if (namefile != "") {
itSize = sizes.find(seq.getName());
- if (itSize == sizes.end()) { mothurOut(seq.getName() + " is not in your names file, please correct."); mothurOutEndLine(); exit(1); }
+ if (itSize == sizes.end()) { m->mothurOut(seq.getName() + " is not in your names file, please correct."); m->mothurOutEndLine(); exit(1); }
else{
seqPNode tempNode(itSize->second, seq, names[seq.getName()]);
alignSeqs.push_back(tempNode);
}
catch(exception& e) {
- errorOut(e, "PreClusterCommand", "readFASTA");
+ m->errorOut(e, "PreClusterCommand", "readFASTA");
exit(1);
}
}
return numBad;
}
catch(exception& e) {
- errorOut(e, "PreClusterCommand", "calcMisMatches");
+ m->errorOut(e, "PreClusterCommand", "calcMisMatches");
exit(1);
}
}
}
catch(exception& e) {
- errorOut(e, "PreClusterCommand", "printData");
+ m->errorOut(e, "PreClusterCommand", "printData");
exit(1);
}
}
+
/**************************************************************************************************/
+
void PreClusterCommand::readNameFile(){
try {
ifstream in;
in.close();
}
catch(exception& e) {
- errorOut(e, "PreClusterCommand", "readNameFile");
+ m->errorOut(e, "PreClusterCommand", "readNameFile");
exit(1);
}
}