X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=readtree.cpp;h=1dd77f9152b241321f6658d0e0efc025c01a1a71;hb=28d6f2bddc5c0718ae7f63648be3130a35fb0f02;hp=25fee86518bc6e2177b11824aa7989168c38772f;hpb=ac1da2a793271cb67f2a2155c5558e1fabdd6aba;p=mothur.git diff --git a/readtree.cpp b/readtree.cpp index 25fee86..1dd77f9 100644 --- a/readtree.cpp +++ b/readtree.cpp @@ -13,10 +13,11 @@ ReadTree::ReadTree() { try { globaldata = GlobalData::getInstance(); + m = MothurOut::getInstance(); globaldata->gTree.clear(); } catch(exception& e) { - errorOut(e, "ReadTree", "ReadTree"); + m->errorOut(e, "ReadTree", "ReadTree"); exit(1); } } @@ -28,11 +29,11 @@ int ReadTree::readSpecialChar(istream& f, char c, string name) { char d = f.get(); if(d == EOF){ - mothurOut("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){ - mothurOut("Error: Expected " + name + " in input file. Found " + toString(d) + ".\n"); + m->mothurOut("Error: Expected " + name + " in input file. Found " + toString(d) + ".\n"); exit(1); } if(d == ')' && f.peek() == '\n'){ @@ -41,7 +42,7 @@ int ReadTree::readSpecialChar(istream& f, char c, string name) { return d; } catch(exception& e) { - errorOut(e, "ReadTree", "readSpecialChar"); + m->errorOut(e, "ReadTree", "readSpecialChar"); exit(1); } } @@ -54,13 +55,13 @@ int ReadTree::readNodeChar(istream& f) { char d = f.get(); if(d == EOF){ - mothurOut("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) { - errorOut(e, "ReadTree", "readNodeChar"); + m->errorOut(e, "ReadTree", "readNodeChar"); exit(1); } } @@ -72,14 +73,14 @@ float ReadTree::readBranchLength(istream& f) { float b; if(!(f >> b)){ - mothurOut("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) { - errorOut(e, "ReadTree", "readBranchLength"); + m->errorOut(e, "ReadTree", "readBranchLength"); exit(1); } } @@ -164,10 +165,11 @@ int ReadNewickTree::read() { if (error != 0) { readOk = error; } filehandle.close(); + return readOk; } catch(exception& e) { - errorOut(e, "ReadNewickTree", "read"); + m->errorOut(e, "ReadNewickTree", "read"); exit(1); } } @@ -208,7 +210,7 @@ void ReadNewickTree::nexusTranslation() { } } catch(exception& e) { - errorOut(e, "ReadNewickTree", "nexusTranslation"); + m->errorOut(e, "ReadNewickTree", "nexusTranslation"); exit(1); } } @@ -228,22 +230,23 @@ int ReadNewickTree::readTreeString() { 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) { mothurOut("error with lc"); mothurOutEndLine(); return -1; } //reports an error in reading - + if (lc == -1) { m->mothurOut("error with lc"); m->mothurOutEndLine(); 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); - if (rc == -1) { mothurOut("error with rc"); mothurOutEndLine(); return -1; } //reports an error in reading + 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{ @@ -255,14 +258,15 @@ int ReadNewickTree::readTreeString() { n = T->getIndex(name); if(n!=0){ - mothurOut("Internal error: The only taxon is not taxon 0.\n"); + 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())!=';') && (filehandle.eof() != true)){;} + while(((ch=filehandle.get())!=';') && (filehandle.eof() != true)){;} + if(rooted != 1){ T->tree[n].setChildren(lc,rc); T->tree[n].setBranchLength(0); @@ -270,11 +274,13 @@ int ReadNewickTree::readTreeString() { if(lc!=-1){ T->tree[lc].setParent(n); } if(rc!=-1){ T->tree[rc].setParent(n); } } + + //T->printTree(); cout << endl; return 0; } catch(exception& e) { - errorOut(e, "ReadNewickTree", "readTreeString"); + m->errorOut(e, "ReadNewickTree", "readTreeString"); exit(1); } } @@ -282,39 +288,73 @@ int ReadNewickTree::readTreeString() { int ReadNewickTree::readNewickInt(istream& f, int& n, Tree* T) { try { + + if (m->control_pressed) { return -1; } + int c = readNodeChar(f); - - if(c == '('){ - 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(c == '('){ + + //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); + 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"); //to pass over labels in trees c=filehandle.get(); - while((c!=',') && (c != -1) && (c!= ':') && (c!=';')){ 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){ mothurOut("Error: Too many nodes in input tree\n"); readOk = -1; return -1; } + 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); - + + //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 = ""; @@ -323,7 +363,7 @@ int ReadNewickTree::readNewickInt(istream& f, int& n, Tree* T) { name += d; d=f.get(); } - +//cout << name << endl; int blen = 0; if(d == ':') { blen = 1; } @@ -337,7 +377,7 @@ int ReadNewickTree::readNewickInt(istream& f, int& n, Tree* T) { //adds sequence names that are not in group file to the "xxx" group if(group == "not found") { - mothurOut("Name: " + name + " is not in your groupfile, and will be disregarded. \n"); //readOk = -1; return n1; + 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"; @@ -354,7 +394,9 @@ int ReadNewickTree::readNewickInt(istream& f, int& n, Tree* T) { group = "xxx"; } - 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){ @@ -365,13 +407,14 @@ int ReadNewickTree::readNewickInt(istream& f, int& n, Tree* T) { } while((c=f.get())!=0 && (c != ':' && c != ',' && c!=')') ) {;} + f.putback(c); return n1; } } catch(exception& e) { - errorOut(e, "ReadNewickTree", "readNewickInt"); + m->errorOut(e, "ReadNewickTree", "readNewickInt"); exit(1); } }