m = MothurOut::getInstance();
initialize();
name = newName;
+
+ for (int i = 0; i < name.length(); i++) {
+ if (name[i] == ':') { name[i] = '_'; m->changedSeqNames = true; }
+ }
//setUnaligned removes any gap characters for us
setUnaligned(sequence);
m = MothurOut::getInstance();
initialize();
name = newName;
+
+ for (int i = 0; i < name.length(); i++) {
+ if (name[i] == ':') { name[i] = '_'; m->changedSeqNames = true; }
+ }
//setUnaligned removes any gap characters for us
setUnaligned(sequence);
m = MothurOut::getInstance();
initialize();
- fastaString >> name;
-
- if (name.length() != 0) {
+ name = getSequenceName(fastaString);
- name = name.substr(1);
+ if (!m->control_pressed) {
string sequence;
//read comments
setUnaligned(sequence);
if ((numAmbig / (float) numBases) > 0.25) { m->mothurOut("[WARNING]: We found more than 25% of the bases in sequence " + name + " to be ambiguous. Mothur is not setup to process protein sequences."); m->mothurOutEndLine(); }
-
- }else{ m->mothurOut("Error in reading your fastafile, at position " + toString(fastaString.tellg()) + ". Blank name."); m->mothurOutEndLine(); }
+ }
}
catch(exception& e) {
m = MothurOut::getInstance();
initialize();
- fastaString >> name;
-
- if (name.length() != 0) {
+ name = getSequenceName(fastaString);
- name = name.substr(1);
+ if (!m->control_pressed) {
string sequence;
//read comments
if ((numAmbig / (float) numBases) > 0.25) { m->mothurOut("[WARNING]: We found more than 25% of the bases in sequence " + name + " to be ambiguous. Mothur is not setup to process protein sequences."); m->mothurOutEndLine(); }
- }else{ m->mothurOut("Error in reading your fastafile, at position " + toString(fastaString.tellg()) + ". Blank name."); m->mothurOutEndLine(); }
+ }
}
catch(exception& e) {
try {
m = MothurOut::getInstance();
initialize();
- fastaFile >> name;
-
- if (name.length() != 0) {
+ name = getSequenceName(fastaFile);
- name = name.substr(1);
+ if (!m->control_pressed) {
string sequence;
if ((numAmbig / (float) numBases) > 0.25) { m->mothurOut("[WARNING]: We found more than 25% of the bases in sequence " + name + " to be ambiguous. Mothur is not setup to process protein sequences."); m->mothurOutEndLine(); }
- }else{ m->mothurOut("Error in reading your fastafile, at position " + toString(fastaFile.tellg()) + ". Blank name."); m->mothurOutEndLine(); }
+ }
}
catch(exception& e) {
try {
m = MothurOut::getInstance();
initialize();
- fastaFile >> name;
extraInfo = "";
- if (name.length() != 0) {
-
- name = name.substr(1);
-
+ name = getSequenceName(fastaFile);
+
+ if (!m->control_pressed) {
string sequence;
//read comments
setUnaligned(sequence);
if ((numAmbig / (float) numBases) > 0.25) { m->mothurOut("[WARNING]: We found more than 25% of the bases in sequence " + name + " to be ambiguous. Mothur is not setup to process protein sequences."); m->mothurOutEndLine(); }
-
- }else{ m->mothurOut("Error in reading your fastafile, at position " + toString(fastaFile.tellg()) + ". Blank name."); m->mothurOutEndLine(); }
+ }
}
catch(exception& e) {
try {
m = MothurOut::getInstance();
initialize();
- fastaFile >> name;
+ name = getSequenceName(fastaFile);
- if (name.length() != 0) {
- name = name.substr(1);
+ if (!m->control_pressed) {
string sequence;
//read comments
if ((numAmbig / (float) numBases) > 0.25) { m->mothurOut("[WARNING]: We found more than 25% of the bases in sequence " + name + " to be ambiguous. Mothur is not setup to process protein sequences."); m->mothurOutEndLine(); }
- }else{ m->mothurOut("Error in reading your fastafile, at position " + toString(fastaFile.tellg()) + ". Blank name."); m->mothurOutEndLine(); }
+ }
}
catch(exception& e) {
exit(1);
}
}
-
+//********************************************************************************************************************
+string Sequence::getSequenceName(ifstream& fastaFile) {
+ try {
+ string name = "";
+
+ fastaFile >> name;
+
+ if (name.length() != 0) {
+
+ name = name.substr(1);
+
+ for (int i = 0; i < name.length(); i++) {
+ if (name[i] == ':') { name[i] = '_'; m->changedSeqNames = true; }
+ }
+
+ }else{ m->mothurOut("Error in reading your fastafile, at position " + toString(fastaFile.tellg()) + ". Blank name."); m->mothurOutEndLine(); m->control_pressed = true; }
+
+ return name;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "Sequence", "getSequenceName");
+ exit(1);
+ }
+}
+//********************************************************************************************************************
+string Sequence::getSequenceName(istringstream& fastaFile) {
+ try {
+ string name = "";
+
+ fastaFile >> name;
+
+ if (name.length() != 0) {
+
+ name = name.substr(1);
+
+ for (int i = 0; i < name.length(); i++) {
+ if (name[i] == ':') { name[i] = '_'; m->changedSeqNames = true; }
+ }
+
+ }else{ m->mothurOut("Error in reading your fastafile, at position " + toString(fastaFile.tellg()) + ". Blank name."); m->mothurOutEndLine(); m->control_pressed = true; }
+
+ return name;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "Sequence", "getSequenceName");
+ exit(1);
+ }
+}
//********************************************************************************************************************
string Sequence::getSequenceString(ifstream& fastaFile, int& numAmbig) {
try {
if(letter == '>'){
fastaFile.putback(letter);
break;
- }
+ }else if (letter == ' ') {;}
else if(isprint(letter)){
letter = toupper(letter);
if(letter == 'U'){letter = 'T';}
if(letter == '>'){
fastaFile.putback(letter);
break;
- }
+ }else if (letter == ' ') {;}
else if(isprint(letter)){
letter = toupper(letter);
if(letter == 'U'){letter = 'T';}
int Sequence::getNumBases(){
return numBases;
}
+//********************************************************************************************************************
+
+int Sequence::getNumNs(){
+ int numNs = 0;
+ for (int i = 0; i < unaligned.length(); i++) {
+ if(toupper(unaligned[i]) == 'N') { numNs++; }
+ }
+ return numNs;
+}
//********************************************************************************************************************
//********************************************************************************************************************
void Sequence::padFromPos(int end){
- cout << end << '\t' << endPos << endl;
+ //cout << end << '\t' << endPos << endl;
for(int j = end; j < endPos; j++) {
aligned[j] = '.';
}