5 * Created by westcott on 7/7/10.
6 * Copyright 2010 Schloss Lab. All rights reserved.
10 #include "sffinfocommand.h"
11 #include "endiannessmacros.h"
13 //**********************************************************************************************************************
14 vector<string> SffInfoCommand::setParameters(){
16 CommandParameter psff("sff", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(psff);
17 CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(paccnos);
18 CommandParameter psfftxt("sfftxt", "String", "", "", "", "", "",false,false); parameters.push_back(psfftxt);
19 CommandParameter pflow("flow", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pflow);
20 CommandParameter ptrim("trim", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(ptrim);
21 CommandParameter pfasta("fasta", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pfasta);
22 CommandParameter pqfile("name", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pqfile);
23 CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir);
24 CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir);
26 vector<string> myArray;
27 for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); }
31 m->errorOut(e, "SffInfoCommand", "setParameters");
35 //**********************************************************************************************************************
36 string SffInfoCommand::getHelpString(){
38 string helpString = "";
39 helpString += "The sffinfo command reads a sff file and extracts the sequence data, or you can use it to parse a sfftxt file.\n";
40 helpString += "The sffinfo command parameters are sff, fasta, qfile, accnos, flow, sfftxt, and trim. sff is required. \n";
41 helpString += "The sff parameter allows you to enter the sff file you would like to extract data from. You may enter multiple files by separating them by -'s.\n";
42 helpString += "The fasta parameter allows you to indicate if you would like a fasta formatted file generated. Default=True. \n";
43 helpString += "The qfile parameter allows you to indicate if you would like a quality file generated. Default=True. \n";
44 helpString += "The flow parameter allows you to indicate if you would like a flowgram file generated. Default=True. \n";
45 helpString += "The sfftxt parameter allows you to indicate if you would like a sff.txt file generated. Default=False. \n";
46 helpString += "If you want to parse an existing sfftxt file into flow, fasta and quality file, enter the file name using the sfftxt parameter. \n";
47 helpString += "The trim parameter allows you to indicate if you would like a sequences and quality scores trimmed to the clipQualLeft and clipQualRight values. Default=True. \n";
48 helpString += "The accnos parameter allows you to provide a accnos file containing the names of the sequences you would like extracted. You may enter multiple files by separating them by -'s. \n";
49 helpString += "Example sffinfo(sff=mySffFile.sff, trim=F).\n";
50 helpString += "Note: No spaces between parameter labels (i.e. sff), '=' and parameters (i.e.yourSffFileName).\n";
54 m->errorOut(e, "SffInfoCommand", "getHelpString");
60 //**********************************************************************************************************************
61 SffInfoCommand::SffInfoCommand(){
63 abort = true; calledHelp = true;
65 vector<string> tempOutNames;
66 outputTypes["fasta"] = tempOutNames;
67 outputTypes["flow"] = tempOutNames;
68 outputTypes["sfftxt"] = tempOutNames;
69 outputTypes["qfile"] = tempOutNames;
72 m->errorOut(e, "SffInfoCommand", "SffInfoCommand");
76 //**********************************************************************************************************************
78 SffInfoCommand::SffInfoCommand(string option) {
80 abort = false; calledHelp = false;
83 //allow user to run help
84 if(option == "help") { help(); abort = true; calledHelp = true; }
85 else if(option == "citation") { citation(); abort = true; calledHelp = true;}
88 //valid paramters for this command
89 vector<string> myArray = setParameters();
91 OptionParser parser(option);
92 map<string, string> parameters = parser.getParameters();
94 ValidParameters validParameter;
95 //check to make sure all parameters are valid for command
96 for (map<string,string>::iterator it = parameters.begin(); it != parameters.end(); it++) {
97 if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
100 //initialize outputTypes
101 vector<string> tempOutNames;
102 outputTypes["fasta"] = tempOutNames;
103 outputTypes["flow"] = tempOutNames;
104 outputTypes["sfftxt"] = tempOutNames;
105 outputTypes["qfile"] = tempOutNames;
107 //if the user changes the output directory command factory will send this info to us in the output parameter
108 outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; }
110 //if the user changes the input directory command factory will send this info to us in the output parameter
111 string inputDir = validParameter.validFile(parameters, "inputdir", false); if (inputDir == "not found"){ inputDir = ""; }
113 sffFilename = validParameter.validFile(parameters, "sff", false);
114 if (sffFilename == "not found") { sffFilename = ""; }
116 m->splitAtDash(sffFilename, filenames);
118 //go through files and make sure they are good, if not, then disregard them
119 for (int i = 0; i < filenames.size(); i++) {
121 if (filenames[i] == "current") {
122 filenames[i] = m->getSFFFile();
123 if (filenames[i] != "") { m->mothurOut("Using " + filenames[i] + " as input file for the sff parameter where you had given current."); m->mothurOutEndLine(); }
125 m->mothurOut("You have no current sfffile, ignoring current."); m->mothurOutEndLine(); ignore=true;
126 //erase from file list
127 filenames.erase(filenames.begin()+i);
133 if (inputDir != "") {
134 string path = m->hasPath(filenames[i]);
135 //if the user has not given a path then, add inputdir. else leave path alone.
136 if (path == "") { filenames[i] = inputDir + filenames[i]; }
140 int ableToOpen = m->openInputFile(filenames[i], in, "noerror");
142 //if you can't open it, try default location
143 if (ableToOpen == 1) {
144 if (m->getDefaultPath() != "") { //default path is set
145 string tryPath = m->getDefaultPath() + m->getSimpleName(filenames[i]);
146 m->mothurOut("Unable to open " + filenames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();
148 ableToOpen = m->openInputFile(tryPath, in2, "noerror");
150 filenames[i] = tryPath;
154 //if you can't open it, try default location
155 if (ableToOpen == 1) {
156 if (m->getOutputDir() != "") { //default path is set
157 string tryPath = m->getOutputDir() + m->getSimpleName(filenames[i]);
158 m->mothurOut("Unable to open " + filenames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();
160 ableToOpen = m->openInputFile(tryPath, in2, "noerror");
162 filenames[i] = tryPath;
168 if (ableToOpen == 1) {
169 m->mothurOut("Unable to open " + filenames[i] + ". It will be disregarded."); m->mothurOutEndLine();
170 //erase from file list
171 filenames.erase(filenames.begin()+i);
173 }else { m->setSFFFile(filenames[i]); }
177 //make sure there is at least one valid file left
178 if (filenames.size() == 0) { m->mothurOut("no valid files."); m->mothurOutEndLine(); abort = true; }
181 accnosName = validParameter.validFile(parameters, "accnos", false);
182 if (accnosName == "not found") { accnosName = ""; }
185 m->splitAtDash(accnosName, accnosFileNames);
187 //go through files and make sure they are good, if not, then disregard them
188 for (int i = 0; i < accnosFileNames.size(); i++) {
190 if (accnosFileNames[i] == "current") {
191 accnosFileNames[i] = m->getAccnosFile();
192 if (accnosFileNames[i] != "") { m->mothurOut("Using " + accnosFileNames[i] + " as input file for the accnos parameter where you had given current."); m->mothurOutEndLine(); }
194 m->mothurOut("You have no current accnosfile, ignoring current."); m->mothurOutEndLine(); ignore=true;
195 //erase from file list
196 accnosFileNames.erase(accnosFileNames.begin()+i);
203 if (inputDir != "") {
204 string path = m->hasPath(accnosFileNames[i]);
205 //if the user has not given a path then, add inputdir. else leave path alone.
206 if (path == "") { accnosFileNames[i] = inputDir + accnosFileNames[i]; }
210 int ableToOpen = m->openInputFile(accnosFileNames[i], in, "noerror");
212 //if you can't open it, try default location
213 if (ableToOpen == 1) {
214 if (m->getDefaultPath() != "") { //default path is set
215 string tryPath = m->getDefaultPath() + m->getSimpleName(accnosFileNames[i]);
216 m->mothurOut("Unable to open " + accnosFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();
218 ableToOpen = m->openInputFile(tryPath, in2, "noerror");
220 accnosFileNames[i] = tryPath;
223 //if you can't open it, try default location
224 if (ableToOpen == 1) {
225 if (m->getOutputDir() != "") { //default path is set
226 string tryPath = m->getOutputDir() + m->getSimpleName(accnosFileNames[i]);
227 m->mothurOut("Unable to open " + accnosFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();
229 ableToOpen = m->openInputFile(tryPath, in2, "noerror");
231 accnosFileNames[i] = tryPath;
236 if (ableToOpen == 1) {
237 m->mothurOut("Unable to open " + accnosFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine();
238 //erase from file list
239 accnosFileNames.erase(accnosFileNames.begin()+i);
245 //make sure there is at least one valid file left
246 if (accnosFileNames.size() == 0) { m->mothurOut("no valid files."); m->mothurOutEndLine(); abort = true; }
250 if (accnosFileNames.size() != filenames.size()) { abort = true; m->mothurOut("If you provide a accnos file, you must have one for each sff file."); m->mothurOutEndLine(); }
253 string temp = validParameter.validFile(parameters, "qfile", false); if (temp == "not found"){ temp = "T"; }
254 qual = m->isTrue(temp);
256 temp = validParameter.validFile(parameters, "fasta", false); if (temp == "not found"){ temp = "T"; }
257 fasta = m->isTrue(temp);
259 temp = validParameter.validFile(parameters, "flow", false); if (temp == "not found"){ temp = "T"; }
260 flow = m->isTrue(temp);
262 temp = validParameter.validFile(parameters, "trim", false); if (temp == "not found"){ temp = "T"; }
263 trim = m->isTrue(temp);
265 temp = validParameter.validFile(parameters, "sfftxt", false);
266 if (temp == "not found") { temp = "F"; sfftxt = false; sfftxtFilename = ""; }
267 else if (m->isTrue(temp)) { sfftxt = true; sfftxtFilename = ""; }
270 if (inputDir != "") {
271 map<string,string>::iterator it = parameters.find("sfftxt");
272 //user has given a template file
273 if(it != parameters.end()){
274 string path = m->hasPath(it->second);
275 //if the user has not given a path then, add inputdir. else leave path alone.
276 if (path == "") { parameters["sfftxt"] = inputDir + it->second; }
280 sfftxtFilename = validParameter.validFile(parameters, "sfftxt", true);
281 if (sfftxtFilename == "not found") { sfftxtFilename = ""; }
282 else if (sfftxtFilename == "not open") { sfftxtFilename = ""; }
285 if ((sfftxtFilename == "") && (filenames.size() == 0)) {
286 //if there is a current sff file, use it
287 string filename = m->getSFFFile();
288 if (filename != "") { filenames.push_back(filename); m->mothurOut("Using " + filename + " as input file for the sff parameter."); m->mothurOutEndLine(); }
289 else { m->mothurOut("[ERROR]: you must provide a valid sff or sfftxt file."); m->mothurOutEndLine(); abort=true; }
293 catch(exception& e) {
294 m->errorOut(e, "SffInfoCommand", "SffInfoCommand");
298 //**********************************************************************************************************************
299 int SffInfoCommand::execute(){
301 if (abort == true) { if (calledHelp) { return 0; } return 2; }
303 for (int s = 0; s < filenames.size(); s++) {
305 if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
307 int start = time(NULL);
309 m->mothurOut("Extracting info from " + filenames[s] + " ..." ); m->mothurOutEndLine();
312 if (hasAccnos) { accnos = accnosFileNames[s]; }
314 int numReads = extractSffInfo(filenames[s], accnos);
316 m->mothurOut("It took " + toString(time(NULL) - start) + " secs to extract " + toString(numReads) + ".");
319 if (sfftxtFilename != "") { parseSffTxt(); }
321 if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
323 //set fasta file as new current fastafile
325 itTypes = outputTypes.find("fasta");
326 if (itTypes != outputTypes.end()) {
327 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); }
330 itTypes = outputTypes.find("qfile");
331 if (itTypes != outputTypes.end()) {
332 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setQualFile(current); }
335 itTypes = outputTypes.find("flow");
336 if (itTypes != outputTypes.end()) {
337 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFlowFile(current); }
340 //report output filenames
341 m->mothurOutEndLine();
342 m->mothurOut("Output File Names: "); m->mothurOutEndLine();
343 for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
344 m->mothurOutEndLine();
348 catch(exception& e) {
349 m->errorOut(e, "SffInfoCommand", "execute");
353 //**********************************************************************************************************************
354 int SffInfoCommand::extractSffInfo(string input, string accnos){
357 if (outputDir == "") { outputDir += m->hasPath(input); }
359 if (accnos != "") { readAccnosFile(accnos); }
360 else { seqNames.clear(); }
362 ofstream outSfftxt, outFasta, outQual, outFlow;
363 string outFastaFileName, outQualFileName;
364 string rootName = outputDir + m->getRootName(m->getSimpleName(input));
365 if(rootName.find_last_of(".") == rootName.npos){ rootName += "."; }
367 string sfftxtFileName = outputDir + m->getRootName(m->getSimpleName(input)) + "sff.txt";
368 string outFlowFileName = outputDir + m->getRootName(m->getSimpleName(input)) + "flow";
370 outFastaFileName = outputDir + m->getRootName(m->getSimpleName(input)) + "fasta";
371 outQualFileName = outputDir + m->getRootName(m->getSimpleName(input)) + "qual";
373 outFastaFileName = outputDir + m->getRootName(m->getSimpleName(input)) + "raw.fasta";
374 outQualFileName = outputDir + m->getRootName(m->getSimpleName(input)) + "raw.qual";
377 if (sfftxt) { m->openOutputFile(sfftxtFileName, outSfftxt); outSfftxt.setf(ios::fixed, ios::floatfield); outSfftxt.setf(ios::showpoint); outputNames.push_back(sfftxtFileName); outputTypes["sfftxt"].push_back(sfftxtFileName); }
378 if (fasta) { m->openOutputFile(outFastaFileName, outFasta); outputNames.push_back(outFastaFileName); outputTypes["fasta"].push_back(outFastaFileName); }
379 if (qual) { m->openOutputFile(outQualFileName, outQual); outputNames.push_back(outQualFileName); outputTypes["qfile"].push_back(outQualFileName); }
380 if (flow) { m->openOutputFile(outFlowFileName, outFlow); outputNames.push_back(outFlowFileName); outFlow.setf(ios::fixed, ios::floatfield); outFlow.setf(ios::showpoint); outputTypes["flow"].push_back(outFlowFileName); }
383 in.open(input.c_str(), ios::binary);
386 readCommonHeader(in, header);
391 //check magic number and version
392 if (header.magicNumber != 779314790) { m->mothurOut("Magic Number is not correct, not a valid .sff file"); m->mothurOutEndLine(); return count; }
393 if (header.version != "0001") { m->mothurOut("Version is not supported, only support version 0001."); m->mothurOutEndLine(); return count; }
395 //print common header
396 if (sfftxt) { printCommonHeader(outSfftxt, header); }
397 if (flow) { outFlow << header.numFlowsPerRead << endl; }
399 //read through the sff file
406 readHeader(in, readheader);
410 readSeqData(in, read, header.numFlowsPerRead, readheader.numBases);
411 bool okay = sanityCheck(readheader, read);
412 if (!okay) { break; }
414 //if you have provided an accosfile and this seq is not in it, then dont print
415 if (seqNames.size() != 0) { if (seqNames.count(readheader.name) == 0) { print = false; } }
419 if (sfftxt) { printHeader(outSfftxt, readheader); printSffTxtSeqData(outSfftxt, read, readheader); }
420 if (fasta) { printFastaSeqData(outFasta, read, readheader); }
421 if (qual) { printQualSeqData(outQual, read, readheader); }
422 if (flow) { printFlowSeqData(outFlow, read, readheader); }
429 if((count+1) % 10000 == 0){ m->mothurOut(toString(count+1)); m->mothurOutEndLine(); }
431 if (m->control_pressed) { count = 0; break; }
433 if (count >= header.numReads) { break; }
437 if (!m->control_pressed) { if((count) % 10000 != 0){ m->mothurOut(toString(count)); m->mothurOutEndLine(); } }
441 if (sfftxt) { outSfftxt.close(); }
442 if (fasta) { outFasta.close(); }
443 if (qual) { outQual.close(); }
444 if (flow) { outFlow.close(); }
448 catch(exception& e) {
449 m->errorOut(e, "SffInfoCommand", "extractSffInfo");
453 //**********************************************************************************************************************
454 int SffInfoCommand::readCommonHeader(ifstream& in, CommonHeader& header){
462 header.magicNumber = be_int4(*(unsigned int *)(&buffer));
468 for (int i = 0; i < 4; i++) { header.version += toString((int)(buffer9[i])); }
473 header.indexOffset = be_int8(*(unsigned long long *)(&buffer2));
478 header.indexLength = be_int4(*(unsigned int *)(&buffer3));
483 header.numReads = be_int4(*(unsigned int *)(&buffer4));
488 header.headerLength = be_int2(*(unsigned short *)(&buffer5));
493 header.keyLength = be_int2(*(unsigned short *)(&buffer6));
495 //read number of flow reads
498 header.numFlowsPerRead = be_int2(*(unsigned short *)(&buffer7));
503 header.flogramFormatCode = (int)(buffer8[0]);
506 char* tempBuffer = new char[header.numFlowsPerRead];
507 in.read(&(*tempBuffer), header.numFlowsPerRead);
508 header.flowChars = tempBuffer;
509 if (header.flowChars.length() > header.numFlowsPerRead) { header.flowChars = header.flowChars.substr(0, header.numFlowsPerRead); }
513 char* tempBuffer2 = new char[header.keyLength];
514 in.read(&(*tempBuffer2), header.keyLength);
515 header.keySequence = tempBuffer2;
516 if (header.keySequence.length() > header.keyLength) { header.keySequence = header.keySequence.substr(0, header.keyLength); }
517 delete[] tempBuffer2;
520 unsigned long long spotInFile = in.tellg();
521 unsigned long long spot = (spotInFile + 7)& ~7; // ~ inverts
525 m->mothurOut("Error reading sff common header."); m->mothurOutEndLine();
530 catch(exception& e) {
531 m->errorOut(e, "SffInfoCommand", "readCommonHeader");
535 //**********************************************************************************************************************
536 int SffInfoCommand::readHeader(ifstream& in, Header& header){
544 header.headerLength = be_int2(*(unsigned short *)(&buffer));
549 header.nameLength = be_int2(*(unsigned short *)(&buffer2));
554 header.numBases = be_int4(*(unsigned int *)(&buffer3));
556 //read clip qual left
559 header.clipQualLeft = be_int2(*(unsigned short *)(&buffer4));
560 header.clipQualLeft = 5;
562 //read clip qual right
565 header.clipQualRight = be_int2(*(unsigned short *)(&buffer5));
567 //read clipAdapterLeft
570 header.clipAdapterLeft = be_int2(*(unsigned short *)(&buffer6));
572 //read clipAdapterRight
575 header.clipAdapterRight = be_int2(*(unsigned short *)(&buffer7));
578 char* tempBuffer = new char[header.nameLength];
579 in.read(&(*tempBuffer), header.nameLength);
580 header.name = tempBuffer;
581 if (header.name.length() > header.nameLength) { header.name = header.name.substr(0, header.nameLength); }
584 //extract info from name
585 decodeName(header.timestamp, header.region, header.xy, header.name);
588 unsigned long long spotInFile = in.tellg();
589 unsigned long long spot = (spotInFile + 7)& ~7;
593 m->mothurOut("Error reading sff header info."); m->mothurOutEndLine();
598 catch(exception& e) {
599 m->errorOut(e, "SffInfoCommand", "readHeader");
603 //**********************************************************************************************************************
604 int SffInfoCommand::readSeqData(ifstream& in, seqRead& read, int numFlowReads, int numBases){
610 read.flowgram.resize(numFlowReads);
611 for (int i = 0; i < numFlowReads; i++) {
614 read.flowgram[i] = be_int2(*(unsigned short *)(&buffer));
618 read.flowIndex.resize(numBases);
619 for (int i = 0; i < numBases; i++) {
622 read.flowIndex[i] = be_int1(*(unsigned char *)(&temp));
626 char* tempBuffer = new char[numBases];
627 in.read(&(*tempBuffer), numBases);
628 read.bases = tempBuffer;
629 if (read.bases.length() > numBases) { read.bases = read.bases.substr(0, numBases); }
633 read.qualScores.resize(numBases);
634 for (int i = 0; i < numBases; i++) {
637 read.qualScores[i] = be_int1(*(unsigned char *)(&temp));
641 unsigned long long spotInFile = in.tellg();
642 unsigned long long spot = (spotInFile + 7)& ~7;
646 m->mothurOut("Error reading."); m->mothurOutEndLine();
651 catch(exception& e) {
652 m->errorOut(e, "SffInfoCommand", "readSeqData");
656 //**********************************************************************************************************************
657 int SffInfoCommand::decodeName(string& timestamp, string& region, string& xy, string name) {
660 if (name.length() >= 6) {
661 string time = name.substr(0, 6);
662 unsigned int timeNum = m->fromBase36(time);
664 int q1 = timeNum / 60;
665 int sec = timeNum - 60 * q1;
667 int minute = q1 - 60 * q2;
669 int hr = q2 - 24 * q3;
671 int day = q3 - 32 * q4;
673 int mon = q4 - 13 * q5;
674 int year = 2000 + q5;
676 timestamp = toString(year) + "_" + toString(mon) + "_" + toString(day) + "_" + toString(hr) + "_" + toString(minute) + "_" + toString(sec);
679 if (name.length() >= 9) {
680 region = name.substr(7, 2);
682 string xyNum = name.substr(9);
683 unsigned int myXy = m->fromBase36(xyNum);
687 xy = toString(x) + "_" + toString(y);
692 catch(exception& e) {
693 m->errorOut(e, "SffInfoCommand", "decodeName");
697 //**********************************************************************************************************************
698 int SffInfoCommand::printCommonHeader(ofstream& out, CommonHeader& header) {
701 out << "Common Header:\nMagic Number: " << header.magicNumber << endl;
702 out << "Version: " << header.version << endl;
703 out << "Index Offset: " << header.indexOffset << endl;
704 out << "Index Length: " << header.indexLength << endl;
705 out << "Number of Reads: " << header.numReads << endl;
706 out << "Header Length: " << header.headerLength << endl;
707 out << "Key Length: " << header.keyLength << endl;
708 out << "Number of Flows: " << header.numFlowsPerRead << endl;
709 out << "Format Code: " << header.flogramFormatCode << endl;
710 out << "Flow Chars: " << header.flowChars << endl;
711 out << "Key Sequence: " << header.keySequence << endl << endl;
715 catch(exception& e) {
716 m->errorOut(e, "SffInfoCommand", "printCommonHeader");
720 //**********************************************************************************************************************
721 int SffInfoCommand::printHeader(ofstream& out, Header& header) {
724 out << ">" << header.name << endl;
725 out << "Run Prefix: " << header.timestamp << endl;
726 out << "Region #: " << header.region << endl;
727 out << "XY Location: " << header.xy << endl << endl;
729 out << "Run Name: " << endl;
730 out << "Analysis Name: " << endl;
731 out << "Full Path: " << endl << endl;
733 out << "Read Header Len: " << header.headerLength << endl;
734 out << "Name Length: " << header.nameLength << endl;
735 out << "# of Bases: " << header.numBases << endl;
736 out << "Clip Qual Left: " << header.clipQualLeft << endl;
737 out << "Clip Qual Right: " << header.clipQualRight << endl;
738 out << "Clip Adap Left: " << header.clipAdapterLeft << endl;
739 out << "Clip Adap Right: " << header.clipAdapterRight << endl << endl;
743 catch(exception& e) {
744 m->errorOut(e, "SffInfoCommand", "printHeader");
748 //**********************************************************************************************************************
749 bool SffInfoCommand::sanityCheck(Header& header, seqRead& read) {
752 string message = "[WARNING]: Your sff file may be corrupted! Sequence: " + header.name + "\n";
754 if (header.clipQualLeft > read.bases.length()) {
755 okay = false; message += "Clip Qual Left = " + toString(header.clipQualLeft) + ", but we only read " + toString(read.bases.length()) + " bases.\n";
757 if (header.clipQualRight > read.bases.length()) {
758 okay = false; message += "Clip Qual Right = " + toString(header.clipQualRight) + ", but we only read " + toString(read.bases.length()) + " bases.\n";
760 if (header.clipQualLeft > read.qualScores.size()) {
761 okay = false; message += "Clip Qual Left = " + toString(header.clipQualLeft) + ", but we only read " + toString(read.qualScores.size()) + " quality scores.\n";
763 if (header.clipQualRight > read.qualScores.size()) {
764 okay = false; message += "Clip Qual Right = " + toString(header.clipQualRight) + ", but we only read " + toString(read.qualScores.size()) + " quality scores.\n";
768 m->mothurOut(message); m->mothurOutEndLine();
773 catch(exception& e) {
774 m->errorOut(e, "SffInfoCommand", "sanityCheck");
778 //**********************************************************************************************************************
779 int SffInfoCommand::printSffTxtSeqData(ofstream& out, seqRead& read, Header& header) {
782 for (int i = 0; i < read.flowgram.size(); i++) { out << setprecision(2) << (read.flowgram[i]/(float)100) << '\t'; }
784 out << endl << "Flow Indexes: ";
786 for (int i = 0; i < read.flowIndex.size(); i++) { sum += read.flowIndex[i]; out << sum << '\t'; }
788 //make the bases you want to clip lowercase and the bases you want to keep upper case
789 if(header.clipQualRight == 0){ header.clipQualRight = read.bases.length(); }
790 for (int i = 0; i < (header.clipQualLeft-1); i++) { read.bases[i] = tolower(read.bases[i]); }
791 for (int i = (header.clipQualLeft-1); i < (header.clipQualRight-1); i++) { read.bases[i] = toupper(read.bases[i]); }
792 for (int i = (header.clipQualRight-1); i < read.bases.length(); i++) { read.bases[i] = tolower(read.bases[i]); }
794 out << endl << "Bases: " << read.bases << endl << "Quality Scores: ";
795 for (int i = 0; i < read.qualScores.size(); i++) { out << read.qualScores[i] << '\t'; }
802 catch(exception& e) {
803 m->errorOut(e, "SffInfoCommand", "printSffTxtSeqData");
807 //**********************************************************************************************************************
808 int SffInfoCommand::printFastaSeqData(ofstream& out, seqRead& read, Header& header) {
810 string seq = read.bases;
813 if(header.clipQualRight < header.clipQualLeft){
816 else if((header.clipQualRight != 0) && ((header.clipQualRight-header.clipQualLeft) >= 0)){
817 seq = seq.substr((header.clipQualLeft-1), (header.clipQualRight-header.clipQualLeft));
820 seq = seq.substr(header.clipQualLeft-1);
823 //if you wanted the sfftxt then you already converted the bases to the right case
825 //make the bases you want to clip lowercase and the bases you want to keep upper case
826 if(header.clipQualRight == 0){ header.clipQualRight = seq.length(); }
827 for (int i = 0; i < (header.clipQualLeft-1); i++) { seq[i] = tolower(seq[i]); }
828 for (int i = (header.clipQualLeft-1); i < (header.clipQualRight-1); i++) { seq[i] = toupper(seq[i]); }
829 for (int i = (header.clipQualRight-1); i < seq.length(); i++) { seq[i] = tolower(seq[i]); }
833 out << ">" << header.name << " xy=" << header.xy << endl;
838 catch(exception& e) {
839 m->errorOut(e, "SffInfoCommand", "printFastaSeqData");
844 //**********************************************************************************************************************
845 int SffInfoCommand::printQualSeqData(ofstream& out, seqRead& read, Header& header) {
849 if(header.clipQualRight < header.clipQualLeft){
850 out << ">" << header.name << " xy=" << header.xy << endl;
853 else if((header.clipQualRight != 0) && ((header.clipQualRight-header.clipQualLeft) >= 0)){
854 out << ">" << header.name << " xy=" << header.xy << " length=" << (header.clipQualRight-header.clipQualLeft) << endl;
855 for (int i = (header.clipQualLeft-1); i < (header.clipQualRight-1); i++) { out << read.qualScores[i] << '\t'; }
858 out << ">" << header.name << " xy=" << header.xy << " length=" << (header.clipQualRight-header.clipQualLeft) << endl;
859 for (int i = (header.clipQualLeft-1); i < read.qualScores.size(); i++) { out << read.qualScores[i] << '\t'; }
862 out << ">" << header.name << " xy=" << header.xy << " length=" << read.qualScores.size() << endl;
863 for (int i = 0; i < read.qualScores.size(); i++) { out << read.qualScores[i] << '\t'; }
870 catch(exception& e) {
871 m->errorOut(e, "SffInfoCommand", "printQualSeqData");
876 //**********************************************************************************************************************
877 int SffInfoCommand::printFlowSeqData(ofstream& out, seqRead& read, Header& header) {
879 if(header.clipQualRight > header.clipQualLeft){
882 for (int i = 0; i < header.clipQualRight; i++) { rightIndex += read.flowIndex[i]; }
884 out << header.name << ' ' << rightIndex;
885 for (int i = 0; i < read.flowgram.size(); i++) { out << setprecision(2) << ' ' << (read.flowgram[i]/(float)100); }
892 catch(exception& e) {
893 m->errorOut(e, "SffInfoCommand", "printFlowSeqData");
897 //**********************************************************************************************************************
898 int SffInfoCommand::readAccnosFile(string filename) {
904 m->openInputFile(filename, in);
908 in >> name; m->gobble(in);
910 seqNames.insert(name);
912 if (m->control_pressed) { seqNames.clear(); break; }
918 catch(exception& e) {
919 m->errorOut(e, "SffInfoCommand", "readAccnosFile");
923 //**********************************************************************************************************************
924 int SffInfoCommand::parseSffTxt() {
928 m->openInputFile(sfftxtFilename, inSFF);
930 if (outputDir == "") { outputDir += m->hasPath(sfftxtFilename); }
933 ofstream outFasta, outQual, outFlow;
934 string outFastaFileName, outQualFileName;
935 string fileRoot = m->getRootName(m->getSimpleName(sfftxtFilename));
936 if (fileRoot.length() > 0) {
938 fileRoot = fileRoot.substr(0, fileRoot.length()-1);
939 fileRoot = m->getRootName(fileRoot);
942 string outFlowFileName = outputDir + fileRoot + "flow";
944 outFastaFileName = outputDir + fileRoot + "fasta";
945 outQualFileName = outputDir + fileRoot + "qual";
947 outFastaFileName = outputDir + fileRoot + "raw.fasta";
948 outQualFileName = outputDir + fileRoot + "raw.qual";
951 if (fasta) { m->openOutputFile(outFastaFileName, outFasta); outputNames.push_back(outFastaFileName); outputTypes["fasta"].push_back(outFastaFileName); }
952 if (qual) { m->openOutputFile(outQualFileName, outQual); outputNames.push_back(outQualFileName); outputTypes["qual"].push_back(outQualFileName); }
953 if (flow) { m->openOutputFile(outFlowFileName, outFlow); outputNames.push_back(outFlowFileName); outFlow.setf(ios::fixed, ios::floatfield); outFlow.setf(ios::showpoint); outputTypes["flow"].push_back(outFlowFileName); }
956 string commonHeader = m->getline(inSFF);
957 string magicNumber = m->getline(inSFF);
958 string version = m->getline(inSFF);
959 string indexOffset = m->getline(inSFF);
960 string indexLength = m->getline(inSFF);
961 int numReads = parseHeaderLineToInt(inSFF);
962 string headerLength = m->getline(inSFF);
963 string keyLength = m->getline(inSFF);
964 int numFlows = parseHeaderLineToInt(inSFF);
965 string flowgramCode = m->getline(inSFF);
966 string flowChars = m->getline(inSFF);
967 string keySequence = m->getline(inSFF);
972 if (flow) { outFlow << numFlows << endl; }
974 for(int i=0;i<numReads;i++){
977 if (inSFF.eof()) { m->mothurOut("[ERROR]: Expected " + toString(numReads) + " but reached end of file at " + toString(i+1) + "."); m->mothurOutEndLine(); break; }
983 seqName = seqName.substr(1);
985 header.name = seqName;
987 string runPrefix = parseHeaderLineToString(inSFF); header.timestamp = runPrefix;
988 string regionNumber = parseHeaderLineToString(inSFF); header.region = regionNumber;
989 string xyLocation = parseHeaderLineToString(inSFF); header.xy = xyLocation;
992 string runName = parseHeaderLineToString(inSFF);
993 string analysisName = parseHeaderLineToString(inSFF);
994 string fullPath = parseHeaderLineToString(inSFF);
997 string readHeaderLen = parseHeaderLineToString(inSFF); convert(readHeaderLen, header.headerLength);
998 string nameLength = parseHeaderLineToString(inSFF); convert(nameLength, header.nameLength);
999 int numBases = parseHeaderLineToInt(inSFF); header.numBases = numBases;
1000 string clipQualLeft = parseHeaderLineToString(inSFF); convert(clipQualLeft, header.clipQualLeft);
1001 int clipQualRight = parseHeaderLineToInt(inSFF); header.clipQualRight = clipQualRight;
1002 string clipAdapLeft = parseHeaderLineToString(inSFF); convert(clipAdapLeft, header.clipAdapterLeft);
1003 string clipAdapRight = parseHeaderLineToString(inSFF); convert(clipAdapRight, header.clipAdapterRight);
1009 vector<unsigned short> flowVector = parseHeaderLineToFloatVector(inSFF, numFlows); read.flowgram = flowVector;
1010 vector<unsigned int> flowIndices = parseHeaderLineToIntVector(inSFF, numBases);
1013 vector<unsigned int> flowIndicesAdjusted; flowIndicesAdjusted.push_back(flowIndices[0]);
1014 for (int j = 1; j < flowIndices.size(); j++) { flowIndicesAdjusted.push_back(flowIndices[j] - flowIndices[j-1]); }
1015 read.flowIndex = flowIndicesAdjusted;
1017 string bases = parseHeaderLineToString(inSFF); read.bases = bases;
1018 vector<unsigned int> qualityScores = parseHeaderLineToIntVector(inSFF, numBases); read.qualScores = qualityScores;
1021 //if you have provided an accosfile and this seq is not in it, then dont print
1023 if (seqNames.size() != 0) { if (seqNames.count(header.name) == 0) { print = false; } }
1027 if (fasta) { printFastaSeqData(outFasta, read, header); }
1028 if (qual) { printQualSeqData(outQual, read, header); }
1029 if (flow) { printFlowSeqData(outFlow, read, header); }
1033 if((i+1) % 10000 == 0){ m->mothurOut(toString(i+1)); m->mothurOutEndLine(); }
1035 if (m->control_pressed) { break; }
1039 if (!m->control_pressed) { if((numReads) % 10000 != 0){ m->mothurOut(toString(numReads)); m->mothurOutEndLine(); } }
1043 if (fasta) { outFasta.close(); }
1044 if (qual) { outQual.close(); }
1045 if (flow) { outFlow.close(); }
1049 catch(exception& e) {
1050 m->errorOut(e, "SffInfoCommand", "parseSffTxt");
1054 //**********************************************************************************************************************
1056 int SffInfoCommand::parseHeaderLineToInt(ifstream& file){
1060 while (!file.eof()) {
1062 char c = file.get();
1072 catch(exception& e) {
1073 m->errorOut(e, "SffInfoCommand", "parseHeaderLineToInt");
1079 //**********************************************************************************************************************
1081 string SffInfoCommand::parseHeaderLineToString(ifstream& file){
1085 while (!file.eof()) {
1086 char c = file.get();
1090 //text = m->getline(file);
1099 catch(exception& e) {
1100 m->errorOut(e, "SffInfoCommand", "parseHeaderLineToString");
1105 //**********************************************************************************************************************
1107 vector<unsigned short> SffInfoCommand::parseHeaderLineToFloatVector(ifstream& file, int length){
1109 vector<unsigned short> floatVector(length);
1111 while (!file.eof()) {
1112 char c = file.get();
1115 for(int i=0;i<length;i++){
1117 floatVector[i] = temp * 100;
1125 catch(exception& e) {
1126 m->errorOut(e, "SffInfoCommand", "parseHeaderLineToFloatVector");
1131 //**********************************************************************************************************************
1133 vector<unsigned int> SffInfoCommand::parseHeaderLineToIntVector(ifstream& file, int length){
1135 vector<unsigned int> intVector(length);
1137 while (!file.eof()) {
1138 char c = file.get();
1140 for(int i=0;i<length;i++){
1141 file >> intVector[i];
1149 catch(exception& e) {
1150 m->errorOut(e, "SffInfoCommand", "parseHeaderLineToIntVector");
1155 //**********************************************************************************************************************