X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=readtree.cpp;h=c805edc9896bf15b4e7397305c13d8bfbce175d8;hb=cad05a21b084833b07808c1586e755be48fe7e1a;hp=47da6d6c81886e84961c5170267d5908199dd135;hpb=58cf1d08fee8c64334979075fa57bcafb035a2ed;p=mothur.git diff --git a/readtree.cpp b/readtree.cpp index 47da6d6..c805edc 100644 --- a/readtree.cpp +++ b/readtree.cpp @@ -10,75 +10,60 @@ #include "readtree.h" /***********************************************************************/ -//Parent Class -// The following functions are used by all reading formats. -/***********************************************************************/ -ReadTree::ReadTree() { +ReadTree::ReadTree() { try { - globaldata = GlobalData::getInstance(); - T = new Tree(); - numNodes = T->getNumNodes(); - numLeaves = T->getNumLeaves(); + globaldata = GlobalData::getInstance(); + m = MothurOut::getInstance(); + globaldata->gTree.clear(); } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the ReadTree class Function ReadTree. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "ReadTree", "ReadTree"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the ReadTree class function ReadTree. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } /***********************************************************************/ int ReadTree::readSpecialChar(istream& f, char c, string name) { try { - char d; - while(isspace(d=f.get())) {;} + gobble(f); + char d = f.get(); + if(d == EOF){ - cerr << "Error: Input file ends prematurely, expecting a " << name << "\n"; + m->mothurOut("Error: Input file ends prematurely, expecting a " + name + "\n"); exit(1); } if(d != c){ - cerr << "Error: Expected " << name << " in input file. Found " << d << ".\n"; + m->mothurOut("Error: Expected " + name + " in input file. Found " + toString(d) + ".\n"); exit(1); } if(d == ')' && f.peek() == '\n'){ - while(isspace(d=f.get())) {;} - f.putback(d); + gobble(f); } - return d; } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the ReadTree class Function readSpecialChar. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "ReadTree", "readSpecialChar"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the ReadTree class function readSpecialChar. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } /**************************************************************************************************/ int ReadTree::readNodeChar(istream& f) { try { - char d; - while(isspace(d=f.get())) {;} +// while(isspace(d=f.get())) {;} + gobble(f); + char d = f.get(); + if(d == EOF){ - cerr << "Error: Input file ends prematurely, expecting a left parenthesis\n"; + m->mothurOut("Error: Input file ends prematurely, expecting a left parenthesis\n"); exit(1); } return d; } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the ReadTree class Function readNodeChar. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "ReadTree", "readNodeChar"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the ReadTree class function readNodeChar. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } /**************************************************************************************************/ @@ -88,35 +73,151 @@ float ReadTree::readBranchLength(istream& f) { float b; if(!(f >> b)){ - cerr << "Error: Missing branch length in input tree.\n"; + m->mothurOut("Error: Missing branch length in input tree.\n"); exit(1); } - + gobble(f); return b; } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the ReadTree class Function readBranchLength. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "ReadTree", "readBranchLength"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the ReadTree class function readBranchLength. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } - /***********************************************************************/ /***********************************************************************/ - //Child Classes Below /***********************************************************************/ /***********************************************************************/ //This class reads a file in Newick form and stores it in a tree. -void ReadNewickTree::read() { +int ReadNewickTree::read() { try { + holder = ""; + int c, error; + int comment = 0; + + //if you are not a nexus file + if ((c = filehandle.peek()) != '#') { + while((c = filehandle.peek()) != EOF) { + while ((c = filehandle.peek()) != EOF) { + // get past comments + if(c == '[') { + comment = 1; + } + if(c == ']'){ + comment = 0; + } + if((c == '(') && (comment != 1)){ break; } + filehandle.get(); + } + + //make new tree + T = new Tree(); + + numNodes = T->getNumNodes(); + numLeaves = T->getNumLeaves(); + + error = readTreeString(); + + //save trees for later commands + globaldata->gTree.push_back(T); + gobble(filehandle); + } + //if you are a nexus file + }else if ((c = filehandle.peek()) == '#') { + nexusTranslation(); //reads file through the translation and updates treemap + while((c = filehandle.peek()) != EOF) { + // get past comments + while ((c = filehandle.peek()) != EOF) { + if(holder == "[" || holder == "[!"){ + comment = 1; + } + if(holder == "]"){ + comment = 0; + } + if((holder == "tree" || holder == "end;") && comment != 1){ holder = ""; comment = 0; break;} + filehandle >> holder; + } + + //pass over the "tree rep.6878900 = " + while (((c = filehandle.get()) != '(') && ((c = filehandle.peek()) != EOF) ) {;} + + if (c == EOF ) { break; } + filehandle.putback(c); //put back first ( of tree. + + //make new tree + T = new Tree(); + numNodes = T->getNumNodes(); + numLeaves = T->getNumLeaves(); + + //read tree info + error = readTreeString(); + + //save trees for later commands + globaldata->gTree.push_back(T); + } + } + + if (error != 0) { readOk = error; } + + filehandle.close(); + return readOk; + } + catch(exception& e) { + m->errorOut(e, "ReadNewickTree", "read"); + exit(1); + } +} +/**************************************************************************************************/ +//This function read the file through the translation of the sequences names and updates treemap. +void ReadNewickTree::nexusTranslation() { + try { + + holder = ""; + int numSeqs = globaldata->gTreemap->getNumSeqs(); //must save this some when we clear old names we can still know how many sequences there were + int comment = 0; + + // get past comments + while(holder != "translate" && holder != "Translate"){ + if(holder == "[" || holder == "[!"){ + comment = 1; + } + if(holder == "]"){ + comment = 0; + } + filehandle >> holder; + if(holder == "tree" && comment != 1){return;} + } + + //update treemap + globaldata->gTreemap->namesOfSeqs.clear(); + for(int i=0;i> number; + filehandle >> name; + name.erase(name.end()-1); //erase the comma + //insert new one with new name + globaldata->gTreemap->treemap[toString(number)].groupname = globaldata->gTreemap->treemap[name].groupname; + globaldata->gTreemap->treemap[toString(number)].vectorIndex = globaldata->gTreemap->treemap[name].vectorIndex; + //erase old one. so treemap[sarah].groupnumber is now treemap[1].groupnumber. if number is 1 and name is sarah. + globaldata->gTreemap->treemap.erase(name); + globaldata->gTreemap->namesOfSeqs.push_back(number); + } + } + catch(exception& e) { + m->errorOut(e, "ReadNewickTree", "nexusTranslation"); + exit(1); + } +} + +/**************************************************************************************************/ +int ReadNewickTree::readTreeString() { + try { + int n = 0; int lc, rc; @@ -126,8 +227,10 @@ void ReadNewickTree::read() { if(ch == '('){ n = numLeaves; //number of leaves / sequences, we want node 1 to start where the leaves left off + lc = readNewickInt(filehandle, n, T); - + if (lc == -1) { m->mothurOut("error with lc"); m->mothurOutEndLine(); return -1; } //reports an error in reading + if(filehandle.peek()==','){ readSpecialChar(filehandle,',',"comma"); } @@ -137,74 +240,169 @@ void ReadNewickTree::read() { } if(rooted != 1){ rc = readNewickInt(filehandle, n, T); + if (rc == -1) { m->mothurOut("error with rc"); m->mothurOutEndLine(); return -1; } //reports an error in reading if(filehandle.peek() == ')'){ readSpecialChar(filehandle,')',"right parenthesis"); } } } //note: treeclimber had the code below added - not sure why? - else{ + else{ filehandle.putback(ch); char name[MAX_LINE]; filehandle.get(name, MAX_LINE,'\n'); SKIPLINE(filehandle, ch); - n = T->getIndex(name); + if(n!=0){ - cerr << "Internal error: The only taxon is not taxon 0.\n"; - exit(1); + m->mothurOut("Internal error: The only taxon is not taxon 0.\n"); + //exit(1); + readOk = -1; return -1; } lc = rc = -1; } - while((ch=filehandle.get())!=';'){;} - if(rooted != 1){ + while(((ch=filehandle.get())!=';') && (filehandle.eof() != true)){;} + if(rooted != 1){ T->tree[n].setChildren(lc,rc); T->tree[n].setBranchLength(0); T->tree[n].setParent(-1); if(lc!=-1){ T->tree[lc].setParent(n); } if(rc!=-1){ T->tree[rc].setParent(n); } } - - //save tree for later commands - globaldata->gTree = T; + return 0; + } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the ReadNewickTree class Function read. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "ReadNewickTree", "readTreeString"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the ReadNewickTree class function read. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } /**************************************************************************************************/ int ReadNewickTree::readNewickInt(istream& f, int& n, Tree* T) { try { + + if (m->control_pressed) { return -1; } + int c = readNodeChar(f); - + string k; +k = c; + cout << "at beginning = " << k < childrenNodes; + while(f.peek() != ')'){ + int child = readNewickInt(f, n, T); + if (child == -1) { return -1; } //reports an error in reading + + childrenNodes.push_back(child); + + //after a child you either have , or ), check for both + if(f.peek()==')'){ break; } + else if (f.peek()==',') { readSpecialChar(f,',',"comma"); } + else { string k; + k = f.peek(); + cout << "in here k = " << k << '\t' << f.tellg() <mothurOut("Error in tree, please correct."); m->mothurOutEndLine(); return -1; } + + //then force into 2 node structure + for (int i = 1; i < childrenNodes.size(); i++) { + + int lc, rc; + if (i == 1) { lc = childrenNodes[i-1]; rc = childrenNodes[i]; } + else { lc = n; rc = childrenNodes[i]; } + cout << i << '\t' << lc << '\t' << rc << endl; + T->tree[n].setChildren(lc,rc); + T->tree[lc].setParent(n); + T->tree[rc].setParent(n); + + T->printTree(); cout << endl; + n++; + } + + //to account for extra ++ in looping + n--; + //int lc = readNewickInt(f, n, T); + //if (lc == -1) { return -1; } //reports an error in reading + + //readSpecialChar(f,',',"comma"); + + //int rc = readNewickInt(f, n, T); + //if (rc == -1) { return -1; } //reports an error in reading + if(f.peek()==')'){ - readSpecialChar(f,')',"right parenthesis"); + readSpecialChar(f,')',"right parenthesis"); + //to pass over labels in trees + c=filehandle.get(); + while((c!=',') && (c != -1) && (c!= ':') && (c!=';')){ c=filehandle.get(); } + filehandle.putback(c); } if(f.peek() == ':'){ - readSpecialChar(f,':',"colon"); - if(n >= numNodes){ cerr << "Error: Too many nodes in input tree\n"; exit(1); } + readSpecialChar(f,':',"colon"); + + if(n >= numNodes){ m->mothurOut("Error: Too many nodes in input tree\n"); readOk = -1; return -1; } + T->tree[n].setBranchLength(readBranchLength(f)); - }else{T->tree[n].setBranchLength(0.0); } + }else{ + T->tree[n].setBranchLength(0.0); + } + + //to account for multifurcating trees generated by fasttree, we are forcing them to be bifurcating + /*while(f.peek() == ','){ + string k; + k = f.peek(); + cout << "in here k = " << k << '\t' << f.tellg() <tree[n].setChildren(lc,rc); + T->tree[lc].setParent(n); + T->tree[rc].setParent(n); + + T->printTree(); cout << endl; + lc = n; + n++; + + readSpecialChar(f,',',"comma"); + + rc = readNewickInt(f, n, T); - T->tree[n].setChildren(lc,rc); - T->tree[lc].setParent(n); - T->tree[rc].setParent(n); + if (rc == -1) { return -1; } //reports an error in reading + + if(f.peek()==')'){ + readSpecialChar(f,')',"right parenthesis"); + //to pass over labels in trees + c=filehandle.get(); + while((c!=',') && (c != -1) && (c!= ':') && (c!=';')){ c=filehandle.get(); } + filehandle.putback(c); + + if(f.peek() == ':'){ + readSpecialChar(f,':',"colon"); + + if(n >= numNodes){ m->mothurOut("Error: Too many nodes in input tree\n"); readOk = -1; return -1; } + + T->tree[n].setBranchLength(readBranchLength(f)); + }else{ + T->tree[n].setBranchLength(0.0); + } + + break; + } + }*/ + //T->tree[n].setChildren(lc,rc); + //T->tree[lc].setParent(n); + //T->tree[rc].setParent(n); + //T->printTree(); cout << endl; + return n++; + }else{ f.putback(c); string name = ""; @@ -213,9 +411,9 @@ int ReadNewickTree::readNewickInt(istream& f, int& n, Tree* T) { name += d; d=f.get(); } - + cout << name << endl; int blen = 0; - if(d == ':') { blen = 1; } + if(d == ':') { blen = 1; } f.putback(d); @@ -225,14 +423,32 @@ int ReadNewickTree::readNewickInt(istream& f, int& n, Tree* T) { //find index in tree of name int n1 = T->getIndex(name); - if(n1 == -1){cerr << "Name: " << name << " not found\n"; exit(1);} + //adds sequence names that are not in group file to the "xxx" group + if(group == "not found") { + m->mothurOut("Name: " + name + " is not in your groupfile, and will be disregarded. \n"); //readOk = -1; return n1; + + globaldata->gTreemap->namesOfSeqs.push_back(name); + globaldata->gTreemap->treemap[name].groupname = "xxx"; + + map::iterator it; + it = globaldata->gTreemap->seqsPerGroup.find("xxx"); + if (it == globaldata->gTreemap->seqsPerGroup.end()) { //its a new group + globaldata->gTreemap->namesOfGroups.push_back("xxx"); + globaldata->gTreemap->seqsPerGroup["xxx"] = 1; + }else { + globaldata->gTreemap->seqsPerGroup["xxx"]++; + } + + group = "xxx"; + } - else T->tree[n1].setGroup(group); - + vector tempGroup; tempGroup.push_back(group); + + T->tree[n1].setGroup(tempGroup); T->tree[n1].setChildren(-1,-1); if(blen == 1){ - f.get(); + f.get(); T->tree[n1].setBranchLength(readBranchLength(f)); }else{ T->tree[n1].setBranchLength(0.0); @@ -245,13 +461,9 @@ int ReadNewickTree::readNewickInt(istream& f, int& n, Tree* T) { } } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the ReadNewickTree class Function readNewickInt. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "ReadNewickTree", "readNewickInt"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the ReadNewickTree class function readNewickInt. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } /**************************************************************************************************/ /**************************************************************************************************/