1 #include "globaldata.hpp"
3 #include "sparsematrix.hpp"
5 /*******************************************************/
7 /******************************************************/
8 GlobalData* GlobalData::getInstance() {
9 if( _uniqueInstance == 0) {
10 _uniqueInstance = new GlobalData();
12 return _uniqueInstance;
14 /*******************************************************/
16 /******************************************************/
17 //This function parses through the option string of the command to remove its parameters
18 void GlobalData::parseGlobalData(string commandString, string optionText){
20 commandName = commandString; //save command name to be used by other classes
22 //set all non filename paramters to default
25 //clears out data from previous read
26 if((commandName == "read.dist") || (commandName == "read.otu") || (commandName == "read.tree")) {
33 labels.clear(); lines.clear(); Groups.clear();
38 if(commandName =="help") {
39 helpRequest = optionText;
42 if(commandName == "libshuff") {
47 //set default value for cutoff and phylip
48 if (commandName == "dist.seqs") { cutoff = "1.0"; phylipfile = "F"; }
51 //reads in parameters and values
52 if((optionText != "") && (commandName != "help")){
53 while((optionText.find_first_of(',') != -1)) { //while there are parameters
54 splitAtComma(value, optionText);
55 splitAtEquals(key, value);
57 if(key == "phylip") { phylipfile = value; inputFileName = value; fileroot = value; format = "phylip"; }
58 if(key == "column") { columnfile = value; inputFileName = value; fileroot = value; format = "column"; }
59 if(key == "list") { listfile = value; inputFileName = value; fileroot = value; format = "list"; }
60 if(key == "rabund") { rabundfile = value; inputFileName = value; fileroot = value; format = "rabund"; }
61 if(key == "sabund") { sabundfile = value; inputFileName = value; fileroot = value; format = "sabund"; }
62 if(key == "fasta") { fastafile = value; inputFileName = value; fileroot = value; format = "fasta"; }
63 if(key == "tree") { treefile = value; inputFileName = value; fileroot = value; format = "tree"; }
64 if(key == "shared") { sharedfile = value; inputFileName = value; fileroot = value; format = "sharedfile"; }
65 if(key == "name") { namefile = value; }
66 if(key == "order") { orderfile = value; }
67 if(key == "group") { groupfile = value; }
68 if(key == "cutoff") { cutoff = value; }
69 if(key == "precision") { precision = value; }
70 if(key == "iters") { iters = value; }
71 if(key == "jumble") { jumble = value; }
72 if(key == "freq") { freq = value; }
73 if(key == "method") { method = value; }
74 if(key == "fileroot") { fileroot = value; }
75 if(key == "abund") { abund = value; }
76 if(key == "random") { randomtree = value; }
77 if(key == "calc") { calc = value; }
78 if(key == "step") { step = value; }
79 if(key == "form") { form = value; }
80 if(key == "sorted") { sorted = value; }
81 if(key == "vertical") { vertical = value; }
82 if(key == "trump") { trump = value; }
83 if(key == "hard") { hard = value; }
84 if(key == "soft") { soft = value; }
85 if(key == "scale") { scale = value; }
86 if(key == "countends") { countends = value; }
87 if(key == "processors") { processors = value; }
88 if(key == "size") { size = value; }
89 if(key == "candidate") { candidatefile = value; }
90 if(key == "search") { search = value; }
91 if(key == "ksize") { ksize = value; }
92 if(key == "align") { align = value; }
93 if(key == "match") { match = value; }
94 if(key == "mismatch") { mismatch = value; }
95 if(key == "gapopen") { gapopen = value; }
96 if(key == "gapextend") { gapextend = value; }
97 if(key == "start") { startPos = value; }
98 if(key == "end") { endPos = value; }
99 if(key == "maxambig") { maxAmbig = value; }
100 if(key == "maxhomop") { maxHomoPolymer = value; }
101 if(key == "minlength") { minLength = value; }
102 if(key == "maxlength") { maxLength = value; }
103 if(key == "flip" ) { flip = value; }
104 if(key == "oligos" ) { oligoFile = value; }
106 if(key == "line") {//stores lines to be used in a vector
111 if(line != "all") { splitAtDash(value, lines); allLines = 0; }
112 else { allLines = 1; }
115 if(key == "label") {//stores lines to be used in a vector
120 if(label != "all") { splitAtDash(value, labels); allLines = 0; }
121 else { allLines = 1; }
124 if(key == "groups") {//stores groups to be used in a vector
127 splitAtDash(value, Groups);
132 //saves the last parameter ==> this seems silly...
134 splitAtEquals(key, value);
135 if(key == "phylip") { phylipfile = value; inputFileName = value; fileroot = value; format = "phylip"; }
136 if(key == "column") { columnfile = value; inputFileName = value; fileroot = value; format = "column"; }
137 if(key == "list") { listfile = value; inputFileName = value; fileroot = value; format = "list"; }
138 if(key == "rabund") { rabundfile = value; inputFileName = value; fileroot = value; format = "rabund"; }
139 if(key == "sabund") { sabundfile = value; inputFileName = value; fileroot = value; format = "sabund"; }
140 if(key == "fasta") { fastafile = value; inputFileName = value; fileroot = value; format = "fasta"; }
141 if(key == "tree") { treefile = value; inputFileName = value; fileroot = value; format = "tree"; }
142 if(key == "shared") { sharedfile = value; inputFileName = value; fileroot = value; format = "sharedfile"; }
143 if(key == "name") { namefile = value; }
144 if(key == "order") { orderfile = value; }
145 if(key == "group") { groupfile = value; }
146 if(key == "cutoff") { cutoff = value; }
147 if(key == "precision") { precision = value; }
148 if(key == "iters") { iters = value; }
149 if(key == "jumble") { jumble = value; }
150 if(key == "freq") { freq = value; }
151 if(key == "method") { method = value; }
152 if(key == "fileroot") { fileroot = value; }
153 if(key == "abund") { abund = value; }
154 if(key == "random") { randomtree = value; }
155 if(key == "calc") { calc = value; }
156 if(key == "step") { step = value; }
157 if(key == "form") { form = value; }
158 if(key == "sorted") { sorted = value; }
159 if(key == "vertical") { vertical = value; }
160 if(key == "trump") { trump = value; }
161 if(key == "hard") { hard = value; }
162 if(key == "soft") { soft = value; }
163 if(key == "scale") { scale = value; }
164 if(key == "countends") { countends = value; }
165 if(key == "processors") { processors = value; }
166 if(key == "size") { size = value; }
167 if(key == "candidate") { candidatefile = value; }
168 if(key == "search") { search = value; }
169 if(key == "ksize") { ksize = value; }
170 if(key == "align") { align = value; }
171 if(key == "match") { match = value; }
172 if(key == "mismatch") { mismatch = value; }
173 if(key == "gapopen") { gapopen = value; }
174 if(key == "gapextend") { gapextend = value; }
175 if(key == "start") { startPos = value; }
176 if(key == "end") { endPos = value; }
177 if(key == "maxambig") { maxAmbig = value; }
178 if(key == "maxhomop") { maxHomoPolymer = value; }
179 if(key == "minlength") { minLength = value; }
180 if(key == "maxlength") { maxLength = value; }
181 if(key == "flip" ) { flip = value; }
182 if(key == "oligos" ) { oligoFile = value; }
185 if(key == "line") {//stores lines to be used in a vector
190 if(line != "all") { splitAtDash(value, lines); allLines = 0; }
191 else { allLines = 1; }
194 if(key == "label") {//stores lines to be used in a vector
199 if(label != "all") { splitAtDash(value, labels); allLines = 0; }
200 else { allLines = 1; }
203 if(key == "groups") {//stores groups to be used in a vector
206 splitAtDash(value, Groups);
210 //set format for shared
211 if ((listfile != "") && (groupfile != "")) { format = "shared"; }
212 if ((phylipfile != "") && (groupfile != "")) { format = "matrix"; }
214 //set default value for cutoff
215 if (commandName == "dist.seqs") { format = "fasta"; inputFileName = fastafile; fileroot = fastafile; }
217 //input defaults for calculators
218 if(commandName == "collect.single") {
220 if((calc == "default") || (calc == "")) { calc = "sobs-chao-ace-jack-shannon-npshannon-simpson"; }
222 splitAtDash(calc, Estimators);
224 if(commandName == "rarefaction.single") {
225 if((calc == "default") || (calc == "")) { calc = "sobs"; }
227 splitAtDash(calc, Estimators);
229 if(commandName == "collect.shared") {
230 if((calc == "default") || (calc == "")) { calc = "sharedsobs-sharedchao-sharedace-jabund-sorabund-jclass-sorclass-jest-sorest-thetayc-thetan"; }
232 splitAtDash(calc, Estimators);
234 if(commandName == "summary.single") {
235 if((calc == "default") || (calc == "")) { calc = "sobs-chao-ace-jack-shannon-npshannon-simpson"; }
237 splitAtDash(calc, Estimators);
239 if(commandName == "summary.shared") {
240 if((calc == "default") || (calc == "")) { calc = "sharedsobs-sharedchao-sharedace-jabund-sorabund-jclass-sorclass-jest-sorest-thetayc-thetan"; }
242 splitAtDash(calc, Estimators);
244 if(commandName == "rarefaction.shared") {
245 if((calc == "default") || (calc == "")) { calc = "sharedobserved"; }
247 splitAtDash(calc, Estimators);
249 if(commandName == "dist.seqs") {
250 if((calc == "default") || (calc == "")) { calc = "onegap"; }
251 if(countends == "") { countends = "T"; }
253 splitAtDash(calc, Estimators);
255 if(commandName == "venn") {
256 if((calc == "default") || (calc == "")) {
257 if(format == "list") { calc = "sobs"; }
258 else { calc = "sharedsobs"; }
261 splitAtDash(calc, Estimators);
263 if((commandName == "tree.shared") || (commandName == "bootstrap.shared") || (commandName == "dist.shared")) {
264 if((calc == "default") || (calc == "")) {
265 calc = "jclass-thetayc";
268 splitAtDash(calc, Estimators);
271 if(commandName == "filter.seqs"){
272 if(trump == "" && vertical == "" && hard == "" && soft == ""){
278 //ifyou have done a read.otu with a groupfile but don't want to use it anymore because you want to do single commands
279 if((commandName == "collect.single") || (commandName == "rarefaction.single") || (commandName == "summary.single")) {
280 if(listfile != "") { format = "list"; }
281 else if(sabundfile != "") { format = "sabund"; }
282 else if(rabundfile != "") { format = "rabund"; }
285 catch(exception& e) {
286 cout << "Standard Error: " << e.what() << " has occurred in the GlobalData class Function parseGlobalData. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
290 cout << "An unknown error has occurred in the GlobalData class function parseGlobalData. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
294 /*******************************************************/
296 /******************************************************/
297 // These functions give you the option parameters of the commands
298 string GlobalData::getPhylipFile() { return phylipfile; }
299 string GlobalData::getColumnFile() { return columnfile; }
300 string GlobalData::getListFile() { return listfile; }
301 string GlobalData::getRabundFile() { return rabundfile; }
302 string GlobalData::getSabundFile() { return sabundfile; }
303 string GlobalData::getNameFile() { return namefile; }
304 string GlobalData::getGroupFile() { return groupfile; }
305 string GlobalData::getOrderFile() { return orderfile; }
306 string GlobalData::getTreeFile() { return treefile; }
307 string GlobalData::getSharedFile() { return sharedfile; }
308 string GlobalData::getFastaFile() { return fastafile; }
309 string GlobalData::getCutOff() { return cutoff; }
310 string GlobalData::getFormat() { return format; }
311 string GlobalData::getPrecision() { return precision; }
312 string GlobalData::getMethod() { return method; }
313 string GlobalData::getFileRoot() { return fileroot; }
314 string GlobalData::getIters() { return iters; }
315 string GlobalData::getJumble() { return jumble; }
316 string GlobalData::getFreq() { return freq; }
317 string GlobalData::getAbund() { return abund; }
318 string GlobalData::getRandomTree() { return randomtree; }
319 string GlobalData::getGroups() { return groups; }
320 string GlobalData::getStep() { return step; }
321 string GlobalData::getForm() { return form; }
322 string GlobalData::getSorted() { return sorted; }
323 string GlobalData::getVertical() { return vertical; }
324 string GlobalData::getTrump() { return trump; }
325 string GlobalData::getSoft() { return soft; }
326 string GlobalData::getHard() { return hard; }
327 string GlobalData::getScale() { return scale; }
328 string GlobalData::getCountEnds() { return countends; }
329 string GlobalData::getProcessors() { return processors; }
330 string GlobalData::getSize() { return size; }
331 string GlobalData::getCandidateFile() { return candidatefile; }
332 string GlobalData::getSearch() { return search; }
333 string GlobalData::getKSize() { return ksize; }
334 string GlobalData::getAlign() { return align; }
335 string GlobalData::getMatch() { return match; }
336 string GlobalData::getMismatch() { return mismatch; }
337 string GlobalData::getGapopen() { return gapopen; }
338 string GlobalData::getGapextend() { return gapextend; }
339 string GlobalData::getStartPos() { return startPos; }
340 string GlobalData::getEndPos() { return endPos; }
341 string GlobalData::getMaxAmbig() { return maxAmbig; }
342 string GlobalData::getMaxHomoPolymer() { return maxHomoPolymer; }
343 string GlobalData::getMinLength() { return minLength; }
344 string GlobalData::getMaxLength() { return maxLength; }
345 string GlobalData::getFlip() { return flip; }
346 string GlobalData::getOligosFile() { return oligoFile; }
349 void GlobalData::setListFile(string file) { listfile = file; inputFileName = file; }
350 void GlobalData::setRabundFile(string file) { rabundfile = file; inputFileName = file; }
351 void GlobalData::setSabundFile(string file) { sabundfile = file; inputFileName = file; }
352 void GlobalData::setPhylipFile(string file) { phylipfile = file; inputFileName = file; }
353 void GlobalData::setColumnFile(string file) { columnfile = file; inputFileName = file; }
354 void GlobalData::setGroupFile(string file) { groupfile = file; }
355 void GlobalData::setSharedFile(string file) { sharedfile = file; inputFileName = file; fileroot = file; }
356 void GlobalData::setNameFile(string file) { namefile = file; }
357 void GlobalData::setFormat(string Format) { format = Format; }
358 void GlobalData::setRandomTree(string Random) { randomtree = Random; }
359 void GlobalData::setGroups(string g) { groups = g; }
360 void GlobalData::setCalc(string Calc) { calc = Calc; }
361 void GlobalData::setCountEnds(string e) { countends = e; }
362 void GlobalData::setProcessors(string p) { processors = p; }
365 /*******************************************************/
367 /******************************************************/
368 GlobalData::GlobalData() {
369 //option definitions should go here...
373 gSparseMatrix = NULL;
375 /*******************************************************/
377 /******************************************************/
378 void GlobalData::clear() {
379 //option definitions should go here...
399 jumble = "1"; //0 means don't jumble, 1 means jumble.
400 randomtree = ""; //"" means user will enter some user trees, "outputfile" means they just want the random tree distribution to be outputted to outputfile.
407 sorted = "T"; //F means don't sort, T means sort.
413 countends = "T"; //yes
426 maxHomoPolymer = "-1";
433 //*******************************************************/
435 /******************************************************/
436 void GlobalData::reset() {
443 jumble = "1"; //0 means don't jumble, 1 means jumble.
444 sorted = "T"; //F means don't sort, T means sort.
445 randomtree = ""; //"" means user will enter some user trees, "outputfile" means they just want the random tree distribution to be outputted to outputfile.
469 maxHomoPolymer = "-1";
476 /*******************************************************/
478 /******************************************************/
479 GlobalData::~GlobalData() {
481 if(gListVector != NULL) { delete gListVector; }
482 if(gSparseMatrix != NULL) { delete gSparseMatrix; }
483 if(gorder != NULL) { delete gorder; }
485 /*******************************************************/
487 /*******************************************************/
488 void GlobalData::parseTreeFile() {
489 //Why is THIS in GlobalData??? - PDS
491 //only takes names from the first tree and assumes that all trees use the same names.
493 string filename = treefile;
495 openInputFile(filename, filehandle);
499 //ifyou are not a nexus file
500 if((c = filehandle.peek()) != '#') {
501 while((c = filehandle.peek()) != ';') {
502 while ((c = filehandle.peek()) != ';') {
510 if((c == '(') && (comment != 1)){ break; }
514 readTreeString(filehandle);
516 //ifyou are a nexus file
517 }else if((c = filehandle.peek()) == '#') {
521 while(holder != "translate" && holder != "Translate"){
522 if(holder == "[" || holder == "[!"){
528 filehandle >> holder;
530 //ifthere is no translate then you must read tree string otherwise use translate to get names
531 if(holder == "tree" && comment != 1){
532 //pass over the "tree rep.6878900 = "
533 while (((c = filehandle.get()) != '(') && ((c = filehandle.peek()) != EOF)) {;}
535 if(c == EOF) { break; }
536 filehandle.putback(c); //put back first ( of tree.
537 readTreeString(filehandle);
542 //use nexus translation rather than parsing tree to save time
543 if((holder == "translate") || (holder == "Translate")) {
545 string number, name, h;
546 h = ""; // so it enters the loop the first time
547 while((h != ";") && (number != ";")) {
548 filehandle >> number;
551 //c = , until done with translation then c = ;
552 h = name.substr(name.length()-1, name.length());
553 name.erase(name.end()-1); //erase the comma
554 Treenames.push_back(number);
556 if(number == ";") { Treenames.pop_back(); } //in case ';' from translation is on next line instead of next to last name
561 catch(exception& e) {
562 cout << "Standard Error: " << e.what() << " has occurred in the GlobalData class Function parseTreeFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
566 cout << "An unknown error has occurred in the GlobalData class function parseTreeFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
570 /*******************************************************/
572 /*******************************************************/
573 void GlobalData::readTreeString(ifstream& filehandle) {
578 while((c = filehandle.peek()) != ';') {
580 if((c != '(') && (c != ')') && (c != ',') && (c != ':') && (c != '\n') && (c != '\t') && (c != 32)) { //32 is space
582 c = filehandle.get();
585 while ((c != '(') && (c != ')') && (c != ',') && (c != ':') && (c != '\n') && (c != 32) && (c != '\t')) {
587 c = filehandle.get();
589 //cout << " in name while " << k << endl;
592 //cout << "name = " << name << endl;
593 Treenames.push_back(name);
594 filehandle.putback(c);
596 //cout << " after putback" << k << endl;
599 if(c == ':') { //read until you reach the end of the branch length
600 while ((c != '(') && (c != ')') && (c != ',') && (c != ';') && (c != '\n') && (c != '\t') && (c != 32)) {
601 c = filehandle.get();
603 //cout << " in branch while " << k << endl;
605 filehandle.putback(c);
607 c = filehandle.get();
608 if(c == ';') { break; }
614 catch(exception& e) {
615 cout << "Standard Error: " << e.what() << " has occurred in the GlobalData class Function parseTreeFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
619 cout << "An unknown error has occurred in the GlobalData class function parseTreeFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
624 /*******************************************************/
626 /*******************************************************/