X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=readtree.cpp;h=b9c38e973f2cea531c03c17071ed65a155bf65a3;hp=9b96861a661a6a794120f2d47899222f3664e33b;hb=b206f634aae1b4ce13978d203247fb64757d5482;hpb=60fdefb3a300b59c3bbeffdca8a5f1f30c6a43af diff --git a/readtree.cpp b/readtree.cpp index 9b96861..b9c38e9 100644 --- a/readtree.cpp +++ b/readtree.cpp @@ -10,75 +10,73 @@ #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(); + m = MothurOut::getInstance(); } 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"; +} +/***********************************************************************/ +int ReadTree::AssembleTrees() { + try { + //assemble users trees + for (int i = 0; i < Trees.size(); i++) { + if (m->control_pressed) { return 0; } + Trees[i]->assembleTree(); + } + return 0; + } + catch(exception& e) { + m->errorOut(e, "ReadTree", "AssembleTrees"); exit(1); - } + } } /***********************************************************************/ int ReadTree::readSpecialChar(istream& f, char c, string name) { try { - char d; - while(isspace(d=f.get())) {;} + m->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); + m->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())) {;} + m->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 +86,155 @@ 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); } - + m->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(CountTable* ct) { + try { + holder = ""; + int c, error; + int comment = 0; + + //if you are not a nexus file + if ((c = filehandle.peek()) != '#') { + while((c = filehandle.peek()) != EOF) { + if (m->control_pressed) { filehandle.close(); return 0; } + while ((c = filehandle.peek()) != EOF) { + if (m->control_pressed) { filehandle.close(); return 0; } + // get past comments + if(c == '[') { + comment = 1; + } + if(c == ']'){ + comment = 0; + } + if((c == '(') && (comment != 1)){ break; } + filehandle.get(); + } + + //make new tree + T = new Tree(ct); + + numNodes = T->getNumNodes(); + numLeaves = T->getNumLeaves(); + + error = readTreeString(ct); + + //save trees for later commands + Trees.push_back(T); + m->gobble(filehandle); + } + //if you are a nexus file + }else if ((c = filehandle.peek()) == '#') { + //get right number of seqs from nexus file. + Tree* temp = new Tree(ct); delete temp; + + nexusTranslation(ct); //reads file through the translation and updates treemap + while((c = filehandle.peek()) != EOF) { + if (m->control_pressed) { filehandle.close(); return 0; } + // get past comments + while ((c = filehandle.peek()) != EOF) { + if (m->control_pressed) { filehandle.close(); return 0; } + 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(ct); + numNodes = T->getNumNodes(); + numLeaves = T->getNumLeaves(); + + //read tree info + error = readTreeString(ct); + + //save trees for later commands + Trees.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. +string ReadNewickTree::nexusTranslation(CountTable* ct) { + try { + + holder = ""; + int numSeqs = m->Treenames.size(); //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 holder;} + } + + string number, name; + for(int i=0;i> number; + filehandle >> name; + name.erase(name.end()-1); //erase the comma + ct->renameSeq(name, toString(number)); + } + + return name; + } + catch(exception& e) { + m->errorOut(e, "ReadNewickTree", "nexusTranslation"); + exit(1); + } +} + +/**************************************************************************************************/ +int ReadNewickTree::readTreeString(CountTable* ct) { try { + int n = 0; int lc, rc; @@ -126,40 +244,46 @@ 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); - + + lc = readNewickInt(filehandle, n, T, ct); + if (lc == -1) { m->mothurOut("error with lc"); m->mothurOutEndLine(); m->control_pressed = true; return -1; } //reports an error in reading + if(filehandle.peek()==','){ readSpecialChar(filehandle,',',"comma"); } // ';' means end of tree. else if((ch=filehandle.peek())==';' || ch=='['){ rooted = 1; - } + } + if(rooted != 1){ - rc = readNewickInt(filehandle, n, T); + rc = readNewickInt(filehandle, n, T, ct); + if (rc == -1) { m->mothurOut("error with rc"); m->mothurOutEndLine(); m->control_pressed = true; 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); @@ -167,44 +291,81 @@ void ReadNewickTree::read() { if(rc!=-1){ T->tree[rc].setParent(n); } } - //save tree for later commands - globaldata->gTree = T; + //T->printTree(); cout << endl; + 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) { +int ReadNewickTree::readNewickInt(istream& f, int& n, Tree* T, CountTable* ct) { try { + + if (m->control_pressed) { return -1; } + int c = readNodeChar(f); - + if(c == '('){ - int lc = readNewickInt(f, n, T); - readSpecialChar(f,',',"comma"); - int rc = readNewickInt(f, n, T); + //to account for multifurcating trees generated by fasttree, we are forcing them to be bifurcating + //read all children + vector childrenNodes; + while(f.peek() != ')'){ + int child = readNewickInt(f, n, T, ct); + if (child == -1) { return -1; } //reports an error in reading + //cout << "child = " << child << endl; + 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 {;} + } + //cout << childrenNodes.size() << endl; + if (childrenNodes.size() < 2) { m->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-1; 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--; + 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!=')')){ 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); } - - T->tree[n].setChildren(lc,rc); - T->tree[lc].setParent(n); - T->tree[rc].setParent(n); - + }else{ + T->tree[n].setBranchLength(0.0); + } + return n++; + }else{ f.putback(c); string name = ""; @@ -213,46 +374,55 @@ 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); //set group info - string group = globaldata->gTreemap->getGroup(name); - + vector group = ct->getGroups(name); + //cout << name << endl; //find index in tree of name int n1 = T->getIndex(name); - if(n1 == -1){cerr << "Name: " << name << " not found\n"; exit(1);} - - else T->tree[n1].setGroup(group); - + //adds sequence names that are not in group file to the "xxx" group + if(group.size() == 0) { + m->mothurOut("Name: " + name + " is not in your groupfile, and will be disregarded. \n"); //readOk = -1; return n1; + + vector currentGroups = ct->getNamesOfGroups(); + if (!m->inUsersGroups("xxx", currentGroups)) { ct->addGroup("xxx"); } + currentGroups = ct->getNamesOfGroups(); + vector thisCounts; thisCounts.resize(currentGroups.size(), 0); + for (int h = 0; h < currentGroups.size(); h++) { + if (currentGroups[h] == "xxx") { thisCounts[h] = 1; break; } + } + ct->push_back(name, thisCounts); + + group.push_back("xxx"); + } + T->tree[n1].setGroup(group); 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); } while((c=f.get())!=0 && (c != ':' && c != ',' && c!=')') ) {;} + f.putback(c); return n1; } } 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); - } } /**************************************************************************************************/ /**************************************************************************************************/ - \ No newline at end of file +