filter::filter(argStruct *arguments){
//below if shared for all analysis classes
header = arguments->hd;
revMap = arguments->revMap;
//his is used by this class
keepsChr = NULL;
curChr = -1;
fp = NULL;
minInd = -1;
fname = NULL;
doMajorMinor =0;
doFilter =0;
if(arguments->argc==2){
if(!strcmp(arguments->argv[1],"-filter")){
printArg(stdout);
exit(0);
}else
return;
}
//get options and print them
getOptions(arguments);
printArg(arguments->argumentFile);
}
abcFilter::abcFilter(argStruct *arguments){
//below if shared for all analysis classes
strict =1;
shouldRun[index] = 1;
header = arguments->hd;
revMap = arguments->revMap;
setMinIndDepth=1;
fl = NULL;
//his is used by this class
keepsChr = NULL;
curChr = -1;
fp = NULL;
minInd = 0;
fname = NULL;
doMajorMinor =0;
capDepth = -1;
if(arguments->argc==2){
if(!strcasecmp(arguments->argv[1],"-sites")){
printArg(stdout);
exit(0);
}else
return;
}
//get options and print them
getOptions(arguments);
printArg(arguments->argumentFile);
}
abcScounts::abcScounts(const char *outfiles,argStruct *arguments,int inputtype){
vcfname = NULL;
doScounts = 0;
outfile = NULL;
if(arguments->argc==2){
if(!strcasecmp(arguments->argv[1],"-doScounts")){
printArg(stdout);
exit(0);
}else
return;
}
getOptions(arguments);
if(doScounts==0)
return ;
printArg(arguments->argumentFile);
outfile = aio::openFileBG(outfiles,".scounts.gz");
if(!vcfname){
fprintf(stderr,"\t-> Must supply a file for screening\n");
exit(0);
}
int docounts =0;
docounts = angsd::getArg("-docounts",docounts,arguments);
if(docounts==0){
fprintf(stderr,"\t-> -doScounts requires -doCounts\n");
exit(0);
}
am = readvcf(vcfname);
}
//constructor
abcWriteBcf::abcWriteBcf(const char *outfiles_a,argStruct *arguments,int inputtype){
fp=NULL;
doBcf =0;
args=arguments;
outfiles=outfiles_a;
if(arguments->argc==2){
if(!strcasecmp(arguments->argv[1],"-doBcf")){
printArg(stdout);
exit(0);
}else
return;
}
getOptions(arguments);
if(doBcf==0){
shouldRun[index] =0;
return;
}else
shouldRun[index] =1;
printArg(arguments->argumentFile);
}
abcFilterSNP::abcFilterSNP(const char *outfiles,argStruct *arguments,int inputtype){
doSnpStat=0;
outfileZ = NULL;
if(arguments->argc==2){
if(!strcasecmp(arguments->argv[1],"-doSnpStat")||!strcasecmp(arguments->argv[1],"-doPost")){
printArg(stdout);
exit(0);
}else
return;
}
getOptions(arguments);
printArg(arguments->argumentFile);
if(doSnpStat==0){
shouldRun[index] =0;
return;
}
if(doSnpStat){
// fprintf(stderr,"running doSnpStat=%d\n",doSnpStat);
const char *postfix=".snpStat.gz";
outfileZ = aio::openFileBG(outfiles,postfix);
kstring_t bufstr;bufstr.s=NULL;bufstr.l=bufstr.m=0;
ksprintf(&bufstr,"Chromo\tPosition\t+Major +Minor -Major -Minor\tSB1:SB2:SB3\tHWE_LRT:HWE_pval\tbaseQ_Z:baseQ_pval\n");
aio::bgzf_write(outfileZ,bufstr.s,bufstr.l);bufstr.l=0;
free(bufstr.s);
}
}
abcHWE::abcHWE(const char *outfiles,argStruct *arguments,int inputtype){
chisq = NULL;
outfileZ = NULL;
doHWE=0;
HWE_pval = 0;
testMe=0;
tolStop = 0.00001;
bufstr.s=NULL;bufstr.l=bufstr.m=0;
if(arguments->argc==2){
if(!strcasecmp(arguments->argv[1],"-HWE_pval")){
printArg(stdout);
exit(0);
}else
return;
}
getOptions(arguments);
if(doHWE==0){
shouldRun[index] = 0;
return;
}
printArg(arguments->argumentFile);
//make output files
const char* postfix;
postfix=".hwe.gz";
if(doHWE>0){
outfileZ = aio::openFileBG(outfiles,postfix);
//print header
const char *str = "Chromo\tPosition\tMajor\tMinor\thweFreq\tFreq\tF\tLRT\tp-value\n";
aio::bgzf_write(outfileZ,str,strlen(str));
}
}
hwe::hwe(const char *outfiles,argStruct *arguments,int inputtype){
doHWE=0;
if(arguments->argc==2){
if(!strcmp(arguments->argv[1],"-doHWE")){
printArg(stdout);
exit(0);
}else
return;
}
getOptions(arguments);
printArg(arguments->argumentFile);
if(doHWE==0)
return;
//make output files
const char* postfix;
postfix=".hwe.gz";
if(doHWE>0){
outfileZ = openFileGz(outfiles,postfix,GZOPT);
//print header
gzprintf(outfileZ,"Chromo\tPosition\tMajor\tMinor\tFreq\thweFreq\tF\tLRT\n");
}
}
abcSmartCounts::abcSmartCounts(const char *outfiles,argStruct *arguments,int inputtype){
doSmartCounts =0;
fidx=NULL;
fbin=NULL;
curChr=-1;
len =-1;
if(arguments->argc==2){
if(!strcasecmp(arguments->argv[1],"-doSmartCounts")){
printArg(stdout);
exit(0);
}else
return;
}
getOptions(arguments);
printArg(arguments->argumentFile);
if(doSmartCounts==0)
return;
counts = new unsigned char*[4];
counts[0]=counts[1]=counts[2]=counts[3]=NULL;
const char * BIN= ".counts.bin";
const char * IDX= ".counts.idx";
fidx=aio::openFile(outfiles,IDX);
fbin=aio::openFileBG(outfiles,BIN,GZOPT);
}
abcSaf2::abcSaf2(const char *outfiles,argStruct *arguments,int inputtype){
const char *SAF = ".saf.gz";
const char *SFSPOS =".saf.pos.gz";
//default
underFlowProtect = 0;
fold =0;
isSim =0;
outputBanded=1;
//from command line
anc=NULL;
noTrans = 0;
mode=0; //0,1,2,3 [EJ]
doSaf2=0;
outfileSFS = Z_NULL;
outfileSFSPOS = Z_NULL;
if(arguments->argc==2){
if(!strcasecmp(arguments->argv[1],"-doSaf2")){
printArg(stdout);
exit(0);
}else
return;
}
getOptions(arguments);
printArg(arguments->argumentFile);
if(doSaf2==0){
shouldRun[index] =0;
return;
}
newDim = 2*arguments->nInd+1;
if(fold)
newDim = arguments->nInd+1;
if(doSaf2==1){
outfileSFS = aio::openFileGz(outfiles,SAF,GZOPT);
// Output tag at start to mark as saf version 2 (banded)
char buf[8]="safv2";
gzwrite(outfileSFS,buf,8);
outfileSFSPOS = aio::openFileGz(outfiles,SFSPOS,GZOPT);
}
}
majorminor::majorminor(const char *outfiles,argStruct *arguments,int inputtype){
if(arguments->argc==2){
if(!strcmp(arguments->argv[1],"-doMajorMinor")){
printArg(stdout);
exit(0);
}else
return;
}
getOptions(arguments);
printArg(arguments->argumentFile);
}
abcAncError::abcAncError(const char *outfiles,argStruct *arguments,int inputtype){
tsk_outname=NULL;
doAncError=0;
currentChr=-1;
refName=NULL;
ancName=NULL;
outfile = NULL;
outfile2= NULL;
if(arguments->argc==2){
if(!strcasecmp(arguments->argv[1],"-doAncError")){
printArg(stdout);
exit(0);
}else
return;
}
getOptions(arguments);
if(doAncError==0){
shouldRun[index] =0;
return;
}
printArg(arguments->argumentFile);
//make output files
const char* postfix;
postfix=".ancError";
outfile = aio::openFile(outfiles,postfix);
//put the name of the outputfile into tsk_outname
tsk_outname=(char*)malloc(strlen(outfiles)+strlen(postfix)+1);
sprintf(tsk_outname,"%s%s",outfiles,postfix);
const char* postfix2;
postfix2=".ancErrorChr";
outfile2 = aio::openFile(outfiles,postfix2);
//allocate allele counts
alleleCounts = new size_t *[nInd];
for(int i=0;i<nInd;i++)
alleleCounts[i] = new size_t [256];
for(int i=0;i<nInd;i++)
for(int j=0;j<256;j++)
alleleCounts[i][j]=0;
alleleCountsChr = new size_t *[nInd];
for(int i=0;i<nInd;i++)
alleleCountsChr[i] = new size_t [256];
for(int i=0;i<nInd;i++)
for(int j=0;j<256;j++)
alleleCountsChr[i][j]=0;
}
abcDstat::abcDstat(const char *outfiles,argStruct *arguments,int inputtype){
rmTrans = 0;
outfile=NULL;
ancName=NULL;
doAbbababa=0;
doCount=0;
currentChr=-1;
NbasesPerLine=50;
blockSize=5000000;
block=0;
if(arguments->argc==2){
if(!strcasecmp(arguments->argv[1],"-doAbbababa")){
printArg(stdout);
exit(0);
}else
return;
}
getOptions(arguments);
printArg(arguments->argumentFile);
if(doAbbababa==0){
shouldRun[index] = 0;
return;
}
//make output files
const char* postfix;
postfix=".abbababa";
outfile = aio::openFile(outfiles,postfix);
// const char* postfix2;
// postfix2=".fastaChr";
// outfile2 = openFile(outfiles,postfix2);
bufstr.s=NULL;
bufstr.m=0;
bufstr.l=0;
//the number of combinations
nComb=arguments->nInd*(arguments->nInd-1)*(arguments->nInd-2)/2;
ABBA = new int[nComb];
BABA = new int[nComb];
calcMatCat();
//pre calc all posible combinations
}
abcHaploCall::abcHaploCall(const char *outfiles,argStruct *arguments,int inputtype){
doHaploCall=0;
maxMis=-1;
minMinor=0;
doCount=0;
if(arguments->argc==2){
if(!strcasecmp(arguments->argv[1],"-doHaploCall")){
printArg(stdout);
exit(0);
}else
return;
}
getOptions(arguments);
printArg(arguments->argumentFile);
if(doHaploCall==0){
shouldRun[index] =0;
return;
}
//for kputs output
bufstr.s=NULL;bufstr.l=bufstr.m=0;
//make output files
const char* postfix;
postfix=".haplo.gz";
outfileZ = aio::openFileBG(outfiles,postfix);
//write header
bufstr.l=0;
ksprintf(&bufstr,"chr\tpos\tmajor");
for(int i=0;i<arguments->nInd;i++)
ksprintf(&bufstr,"\tind%d",i);
ksprintf(&bufstr,"\n");
aio::bgzf_write(outfileZ,bufstr.s,bufstr.l);
bufstr.l=0;
}
void printArgs(char* argv[]) {
for (int i = 0; argv[i] != '\0'; ++i) {
cout << '\''; printArg(argv[i]); cout << '\'';
if (argv[i+1] != '\0') cout << ' ';
}
}
void multiReader::getOptions(argStruct *arguments){
nLines=angsd::getArg("-nLines",nLines,arguments);
arguments->nLines = nLines;
fname=angsd::getArg("-beagle",fname,arguments);
fname=angsd::getArg("-pileup",fname,arguments);
minQ=angsd::getArg("-minQ",minQ,arguments);
fname=angsd::getArg("-glf",fname,arguments);
fname=angsd::getArg("-glf3",fname,arguments);
fname=angsd::getArg("-vcf-GL",fname,arguments);
fname=angsd::getArg("-vcf-GP",fname,arguments);
fname=angsd::getArg("-vcf-pl",fname,arguments);
fname=angsd::getArg("-glf10_text",fname,arguments);
intName=angsd::getArg("-intName",intName,arguments);
isSim=angsd::getArg("-isSim",intName,arguments);
nInd=angsd::getArg("-nInd",nInd,arguments);
arguments->nInd = nInd;
//read fai if suppplied (used by other than native bam readers)
char *tmptmp=NULL;
tmptmp=angsd::getArg("-fai",arguments->fai,arguments);
if(tmptmp){
free(arguments->fai);
arguments->fai=tmptmp;
}
printArg(arguments->argumentFile,arguments);
}
void abcSaf2::getOptions(argStruct *arguments){
doSaf2=angsd::getArg("-doSaf2",doSaf2,arguments);
noTrans = angsd::getArg("-noTrans",noTrans,arguments);
mode = angsd::getArg("-mode",mode,arguments); //[EJ]
int GL = 0;
GL = angsd::getArg("-GL",GL,arguments);
underFlowProtect=angsd::getArg("-underFlowProtect",underFlowProtect,arguments);
fold=angsd::getArg("-fold",fold,arguments);
char *sim1 = NULL;
isSim=angsd::getArg("-isSim",isSim,arguments);
// fprintf(stderr,"sim1=%p %s\n",sim1,sim1);
if(doSaf2==0)
return;
anc = angsd::getArg("-anc",anc,arguments);
if(doSaf2 && (anc==NULL&&isSim==0)){
if(doSaf2!=3){
fprintf(stderr,"Must supply -anc for polarizing the spectrum\n");
exit(0);
}
}
if(GL==0 &&arguments->inputtype==7){//DRAGON this is not enough, but this is most likely what everyone done...
fprintf(stderr,"Must supply genotype likelihoods (-GL [INT])\n");
printArg(arguments->argumentFile);
exit(0);
}
}
abbababa::abbababa(const char *outfiles,argStruct *arguments,int inputtype){
doAbbababa=0;
minQ=MINQ;//<-general.h
sample=1;
currentChr=-1;
if(arguments->argc==2){
if(!strcmp(arguments->argv[1],"-doAbbababa")){
printArg(stdout);
exit(0);
}else
return;
}
getOptions(arguments);
printArg(arguments->argumentFile);
if(doAbbababa==0)
return;
//make output files
const char* postfix;
postfix=".abbababa.gz";
outfileZ = openFileGz(outfiles,postfix,GZOPT);
const char* postfix2;
postfix2=".abbababa2";
outfile = openFile(outfiles,postfix2);
//allocate allele counts
alleleCounts = new size_t *[nInd];
for(int i=0;i<nInd;i++)
alleleCounts[i] = new size_t [256];
for(int i=0;i<nInd;i++)
for(int j=0;j<256;j++)
alleleCounts[i][j]=0;
alleleCountsChr = new size_t *[nInd];
for(int i=0;i<nInd;i++)
alleleCountsChr[i] = new size_t [256];
for(int i=0;i<nInd;i++)
for(int j=0;j<256;j++)
alleleCountsChr[i][j]=0;
}
//read program parameters
args *getArgsBambi(argStruct *arguments){
args *ret = allocArgs();
ret->inputfiles=angsd::getArg("-bam",ret->inputfiles,arguments);
ret->inputfile=angsd::getArg("-i",ret->inputfile,arguments);
if(ret->inputfiles==NULL && ret->inputfile==NULL)
return NULL;
if(ret->inputfiles!=NULL&&strcmp(ret->inputfiles,"-999")==0){//DRAGON fix this
ret->inputfiles=NULL;
printArg(stdout,ret);
exit(0);
}
remove_bads = angsd::getArg("-remove_bads",remove_bads,arguments);
uniqueOnly = angsd::getArg("-uniqueOnly",uniqueOnly,arguments);
only_proper_pairs =angsd::getArg("-only_proper_pairs",only_proper_pairs,arguments);
minMapQ = angsd::getArg("-minMapQ",minMapQ,arguments);
adjustMapQ = angsd::getArg("-C",adjustMapQ,arguments);
baq = angsd::getArg("-baq",baq,arguments);
ret->region =angsd::getArg("-r",ret->region,arguments);
ret->regionfile = angsd::getArg("-rf",ret->regionfile,arguments);
ret->nInd = angsd::getArg("-nInd",ret->nInd,arguments);
ret->nLines = angsd::getArg("-nLines",ret->nLines,arguments);
ret->type = angsd::getArg("-type",ret->type,arguments);
ret->show = angsd::getArg("-show",ret->show,arguments);
// minQ = angsd::getArg("-minQ",minQ,arguments);
if(ret->inputfile && ret->inputfile[0]=='-'){
fprintf(stderr,"[Error] Problem understanding inputfilename: %s\n",ret->inputfile);
return NULL;
}
char *tmp = "";
tmp = angsd::getArg("-ref",tmp,arguments);
if(strcmp(tmp,"")==0&&adjustMapQ!=0){
fprintf(stderr,"Must also supply -ref for adjusting the mapping quality\n");
exit(0);
}
if(strcmp(tmp,"")==0&&baq!=0){
fprintf(stderr,"Must also supply -ref for adjusting base qualities (baq)\n");
exit(0);
}
printArg(arguments->argumentFile,ret);
return ret;
}
abcMajorMinor::abcMajorMinor(const char *outfiles,argStruct *arguments,int inputtype){
//default
doMajorMinor = 0;
doSaf = 0;
pest = NULL;
if(arguments->argc==2){
if(!strcasecmp(arguments->argv[1],"-doMajorMinor")){
printArg(stdout);
exit(0);
}else
return;
}
getOptions(arguments);
if(doMajorMinor==0 || doMajorMinor ==3 )
shouldRun[index] =0;
printArg(arguments->argumentFile);
}
void likeClass::getOptions(argStruct *arguments){
//parse all parameters that this class could use
GL=angsd::getArg("-GL",GL,arguments);
minQ = angsd::getArg("-minQ",minQ,arguments);
trim = angsd::getArg("-trim",trim,arguments);
angsd_tmpdir = angsd::getArg("-tmpdir",angsd_tmpdir,arguments);
doGlf=angsd::getArg("-doGlf",doGlf,arguments);
errorFname = angsd::getArg("-errors",errorFname,arguments);
minInd = angsd::getArg("-minInd",minInd,arguments);
int doCounts=0;
int doMajorMinor =0;
doCounts=angsd::getArg("-doCounts",doCounts,arguments);
doMajorMinor=angsd::getArg("-doMajorMinor",doMajorMinor,arguments);
if(arguments->inputtype==4&&GL!=0){
fprintf(stderr,"Can't calculate genotype likelihoods from simulation files\n");
exit(0);
}
if(arguments->inputtype==4)
return;
if(doGlf&&GL==0){
fprintf(stderr,"You need to choose a genotype likelihood model -GL for dumping genotype likelihoods\n");
exit(0);
}
if(GL==0)
return;
if(GL<0||GL>4){
fprintf(stderr,"You've choosen a GL model=%d, only 1,2,3,4 are implemented\n",GL);
exit(0);
}
if(GL==4&&(doCounts==0)){
fprintf(stderr,"Must supply -doCounts for SYK model\n");
exit(0);
}
if((doGlf==2||doGlf==3) && doMajorMinor==0){
fprintf(stderr,"For dumping beaglestyle output you need to estimate major/minor: -doMajorMinor\n");
exit(0);
}
if(arguments->inputtype==5&&doGlf){
fprintf(stderr,"cannot output likelihoods (doGlf) when input is beagle\n");
exit(0);
}
if(arguments->inputtype!=0&&arguments->inputtype!=7){
fprintf(stderr,"Error: Likelihoods can only be estimated based on SOAP input and uppile input\n");
exit(0);
}
printArg(arguments->argumentFile);
}
void printHelp(const QString &name)
{
QString description{QCoreApplication::translate("main",
"chewing-editor is a cross platform chewing user phrase editor written "
"in Qt5. It provides a user friendly GUI to manage user phrase. With it,"
" user can customize user phrase to enhance chewing input performance.")};
printf("%s\n\n", description.toUtf8().constData());
printArg(
QCoreApplication::translate("main", "-d, --debug"),
QCoreApplication::translate("main", "Enable debug message."));
printArg(
QCoreApplication::translate("main", "-v, --version"),
QCoreApplication::translate("main", "Print program version."));
printArg(
QCoreApplication::translate("main", "-h, --help"),
QCoreApplication::translate("main", "Print help message."));
}
static void printArg(const QVariant &v)
{
if (printArgumentsLiterally) {
printf("%s\n", qPrintable(QDBusUtil::argumentToString(v)));
return;
}
if (v.userType() == QVariant::StringList) {
foreach (QString s, v.toStringList())
printf("%s\n", qPrintable(s));
} else if (v.userType() == QVariant::List) {
foreach (const QVariant &var, v.toList())
printArg(var);
} else if (v.userType() == QVariant::Map) {
//read program parameters
void setArgsBam(argStruct *arguments){
remove_bads = angsd::getArg("-remove_bads",remove_bads,arguments);
uniqueOnly = angsd::getArg("-uniqueOnly",uniqueOnly,arguments);
only_proper_pairs =angsd::getArg("-only_proper_pairs",only_proper_pairs,arguments);
minMapQ = angsd::getArg("-minMapQ",minMapQ,arguments);
minQ = angsd::getArg("-minQ",minQ,arguments);
trim = angsd::getArg("-trim",trim,arguments);
adjustMapQ = angsd::getArg("-C",adjustMapQ,arguments);
baq = angsd::getArg("-baq",baq,arguments);
regfile =angsd::getArg("-r",regfile,arguments);
regfiles = angsd::getArg("-rf",regfiles,arguments);
checkBamHeaders = angsd::getArg("-checkBamHeaders",checkBamHeaders,arguments);
arguments->show = angsd::getArg("-show",arguments->show,arguments);
char *tmp = NULL;
tmp = angsd::getArg("-ref",tmp,arguments);
if(tmp==NULL && adjustMapQ!=0){
fprintf(stderr,"Must also supply -ref for adjusting the mapping quality\n");
exit(0);
}
if(tmp==NULL&&baq!=0){
fprintf(stderr,"Must also supply -ref for adjusting base qualities (baq)\n");
exit(0);
}
free(tmp);
std::vector<char *> regionsRaw;
if(regfiles)
regionsRaw = angsd::getFilenames(regfiles,0);
if(regfile)
regionsRaw.push_back(regfile);
for(size_t i=0;i<regionsRaw.size();i++){
regs tmpRegs;
if(parse_region(regionsRaw[i],arguments->hd,tmpRegs.refID,tmpRegs.start,tmpRegs.stop,arguments->revMap)<0||tmpRegs.stop<tmpRegs.start){
fprintf(stderr,"[%s] problems with indexing: %s\n",__FUNCTION__,regionsRaw[i]);
exit(0);
}else
arguments->regions.push_back(tmpRegs);
}
printArg(arguments->argumentFile,arguments);
free(regfile);
free(regfiles);
}
//constructor
abcTemplate::abcTemplate(const char *outfiles,argStruct *arguments,int inputtype){
doTemplate = 0; //defaults= dont do analysis
outfile = NULL;
//first a hook for the interactive help:
// ./angsd -doTemplate
if(arguments->argc==2){
if(!strcasecmp(arguments->argv[1],"-doTemplate")){
printArg(stdout);
exit(0);
}else
return;
}
//now parse the arguments
getOptions(arguments);
//now print the arguments
printArg(arguments->argumentFile);
if(doTemplate==0)
return ;
//initalize outputfile
outfile = aio::openFile(outfiles,".results");
fprintf(outfile,"Chromo\tPosition\t+A\t+C\t+G\t+T\t-A\t-C\t-G\t-T\n");
}
void multiReader::getOptions(argStruct *arguments){
nLines=angsd::getArg("-nLines",nLines,arguments);
arguments->nLines = nLines;
bytesPerLine=angsd::getArg("-bytesPerLine",bytesPerLine,arguments);
fname=angsd::getArg("-beagle",fname,arguments);
fname=angsd::getArg("-pileup",fname,arguments);
minQ=angsd::getArg("-minQ",minQ,arguments);
fname=angsd::getArg("-glf",fname,arguments);
intName=angsd::getArg("-intName",intName,arguments);
isSim=angsd::getArg("-isSim",intName,arguments);
nInd=angsd::getArg("-nInd",nInd,arguments);
from=angsd::getArg("-from",from,arguments);
to=angsd::getArg("-to",to,arguments);
arguments->nInd = nInd;
//read fai if suppplied (used by other than native bam readers)
fai=angsd::getArg("-fai",fai,arguments);
printArg(arguments->argumentFile);
}
void printInfo(char* login, char host[]) {
printArg(login);
cout << '@';
printArg(host);
return;
}
void FormatPrinter::print(const char* format, va_list args)
{
const char* p = format;
const char* errorStr;
// buffer is only used for 2 purposes:
// 1. To temporarily hold a copy of normal chars (not needing formatting)
// to be passed to printArg() and printed.
//
// The incoming format string may contain a string of normal chars much
// longer than 128, but we handle this by breaking them out to 128 chars
// fragments and printing each fragment before re-using the buffer to
// load up the next fragment.
//
// 2. To hold a single "%..." format to be passed to printArg() to process
// a single va_arg.
char buffer[129]; // 128 chars + null terminator.
char* end = &buffer[sizeof(buffer) - 1];
const char* startOfFormatSpecifier = 0;
while (true) {
char c = *p++;
char* curr = buffer;
// Print leading normal chars:
while (c != '\0' && c != '%') {
*curr++ = c;
if (curr == end) {
// Out of buffer space. Flush the fragment, and start over.
*curr = '\0';
bool success = printArg("%s", buffer);
if (!success) {
errorStr = buffer;
goto handleError;
}
curr = buffer;
}
c = *p++;
}
// If we have stuff in the buffer, flush the fragment:
if (curr != buffer) {
ASSERT(curr < end + 1);
*curr = '\0';
bool success = printArg("%s", buffer);
if (!success) {
errorStr = buffer;
goto handleError;
}
}
// End if there are not more chars to print:
if (c == '\0')
break;
// If we get here, we've must have seen a '%':
startOfFormatSpecifier = p - 1;
ASSERT(*startOfFormatSpecifier == '%');
c = *p++;
// Check for "%%" case:
if (c == '%') {
bool success = printArg("%c", '%');
if (!success) {
errorStr = p - 2;
goto handleError;
}
continue;
}
// Check for JS (%J<x>) formatting extensions:
if (c == 'J') {
bool verbose = false;
c = *p++;
if (UNLIKELY(c == '\0')) {
errorStr = p - 2; // Rewind to % in "%J\0"
goto handleError;
}
if (c == '+') {
verbose = true;
c= *p++;
if (UNLIKELY(c == '\0')) {
errorStr = p - 3; // Rewind to % in "%J+\0"
goto handleError;
}
}
switch (c) {
// %Js - WTF::String*
case 's': {
printWTFString(args, verbose);
continue;
}
} // END switch.
// Check for non-JS extensions:
} else if (c == 'b') {
int value = va_arg(args, int);
printArg("%s", value ? "TRUE" : "FALSE");
continue;
}
// If we didn't handle the format in one of the above cases,
// rewind p and let the standard formatting check handle it
// if possible:
p = startOfFormatSpecifier;
ASSERT(*p == '%');
// Check for standard formatting:
// A format specifier always starts with a % and ends with some
// alphabet. We'll do the simple thing and scan until the next
// alphabet, or the end of string.
// In the following, we're going to use buffer as storage for a copy
// of a single format specifier. Hence, conceptually, we can think of
// 'buffer' as synonymous with 'argFormat' here:
#define ABORT_IF_FORMAT_TOO_LONG(curr) \
do { \
if (UNLIKELY(curr >= end)) \
goto formatTooLong; \
} while (false)
curr = buffer;
*curr++ = *p++; // Output the first % in the format specifier.
c = *p++; // Grab the next char in the format specifier.
// Checks for leading modifiers e.g. "%-d":
// 0, -, ' ', +, '\''
if (c == '0' || c == '-' || c == ' ' || c == '+' || c == '\'' || c == '#') {
ABORT_IF_FORMAT_TOO_LONG(curr);
*curr++ = c;
c = *p++;
}
// Checks for decimal digit field width modifiers e.g. "%2f":
while (c >= '0' && c <= '9') {
ABORT_IF_FORMAT_TOO_LONG(curr);
*curr++ = c;
c = *p++;
}
// Checks for '.' e.g. "%2.f":
if (c == '.') {
ABORT_IF_FORMAT_TOO_LONG(curr);
*curr++ = c;
c = *p++;
// Checks for decimal digit precision modifiers e.g. "%.2f":
while (c >= '0' && c <= '9') {
ABORT_IF_FORMAT_TOO_LONG(curr);
*curr++ = c;
c = *p++;
}
}
// Checks for the modifier <m> where <m> can be:
// l, h, j, t, z
// e.g. "%ld"
if (c == 'l' || c == 'h' || c == 'j' || c == 't' || c == 'z' || c == 'L') {
ABORT_IF_FORMAT_TOO_LONG(curr);
*curr++ = c;
char prevChar = c;
c = *p++;
// Checks for the modifier ll or hh in %<x><m>:
if ((prevChar == 'l' || prevChar == 'h') && c == prevChar) {
ABORT_IF_FORMAT_TOO_LONG(curr);
*curr++ = c;
c = *p++;
}
}
// Checks for %<x> where <x> can be:
// d, i, n, o, u, x, X
// But hey, we're just going to do the simple thing and allow any
// alphabet. The user is expected to pass correct format specifiers.
// We won't do any format checking here. We'll just pass it on, and the
// underlying ...printf() implementation may do the needed checking
// at its discretion.
while (c != '\0' && !isASCIIAlpha(c)) {
ABORT_IF_FORMAT_TOO_LONG(curr);
*curr++ = c;
c = *p++;
}
ABORT_IF_FORMAT_TOO_LONG(curr);
*curr++ = c;
if (c == '\0') {
// Uh oh. Bad format. We should have gotten an alphabet instead.
// Print the supposed format as a string instead:
errorStr = buffer;
goto handleError;
}
// Otherwise, we have the alpha that terminates the format.
// Terminate the buffer (i.e. argFormat) string:
ASSERT(isASCIIAlpha(c));
ABORT_IF_FORMAT_TOO_LONG(curr);
*curr = '\0';
bool success = printArg(buffer, args);
if (!success) {
errorStr = buffer;
goto handleError;
}
}
multiReader::multiReader(int argc,char**argv){
gz=Z_NULL;
myglf=NULL;myvcf=NULL;mpil=NULL;bglObj=NULL;
nLines=50;
fname=NULL;
intName=1;
minQ = MINQ;
nInd =0;
isSim =0;
args=NULL;
args = setArgStruct(argc,argv);
fprintf(args->argumentFile,"\t-> Command: \n");
for(int i=0;i<argc;i++)
fprintf(args->argumentFile,"%s ",argv[i]);
// fprintf(args->argumentFile,"\n\n");
if(args->argumentFile!=stderr)
fprintf(args->argumentFile,"\n\t-> angsd version: %s (htslib: %s) build(%s %s)\n",ANGSD_VERSION,hts_version(),__DATE__,__TIME__);
void printTime(FILE *fp);
printTime(args->argumentFile);
//type = args->inputtype;
if(args->argc==2) {
if((!strcasecmp(args->argv[1],"-beagle")) ||
(!strcasecmp(args->argv[1],"-glf")) ||
(!strcasecmp(args->argv[1],"-glf3")) ||
(!strcasecmp(args->argv[1],"-pileup")) ||
(!strcasecmp(args->argv[1],"-vcf-GL")) ||
(!strcasecmp(args->argv[1],"-vcf-pl")) ||
(!strcasecmp(args->argv[1],"-glf10_text")) ||
(!strcasecmp(args->argv[1],"-vcf-GP"))) {
printArg(stdout,args);
exit(0);
}else if ((!strcasecmp(args->argv[1],"-bam")) ||
(!strcasecmp(args->argv[1],"-b"))){
setArgsBam(args);
exit(0);
}else
return;
}
getOptions(args);
if(args->fai==NULL){
int printAndExit =0;
switch(args->inputtype)
{
case INPUT_GLF:
printAndExit=1;
break;
case INPUT_GLF10_TEXT:
printAndExit=1;
break;
case INPUT_GLF3:
printAndExit=1;
break;
case INPUT_BEAGLE:
printAndExit=1;
break;
case INPUT_PILEUP:
printAndExit=1;
break;
}
if(printAndExit){
fprintf(stderr,"\t-> Must supply -fai file\n");
exit(0);
}
}
if(args->fai){
if(!(args->hd=getHeadFromFai(args->fai)))
exit(0);
}else{
if(args->nams.size()==0){
fprintf(stderr,"\t-> Must choose inputfile -bam/-glf/-glf3/-pileup/-i/-vcf-gl/-vcf-gp/-vcf-pl/-glf10_text filename\n");
exit(0);
}
if(args->inputtype==INPUT_BAM){
htsFile *in=sam_open(args->nams[0],"r");
assert(in);
args->hd= sam_hdr_read(in);
hts_close(in);
}
}
if(!(INPUT_VCF_GL||INPUT_VCF_GP)){
if(args->hd==NULL){
fprintf(stderr,"For non-bams you should include -fai arguments\n");
exit(0);
}
}
if((args->inputtype==INPUT_PILEUP||args->inputtype==INPUT_GLF||args->inputtype==INPUT_GLF3||args->inputtype==INPUT_GLF10_TEXT)){
if(nInd==0){
fprintf(stderr,"\t-> Must supply -nInd when using -glf/-glf3/-pileup/-glf10_text files\n");
exit(0);
}
}else
args->nInd = args->nams.size();
if(args->inputtype==INPUT_VCF_GP||args->inputtype==INPUT_VCF_GL){
if(args->regions.size()>1){
fprintf(stderr,"\t-> Only one region can be specified with using bcf (i doubt more is needed) will exit\n");
exit(0);
}else if(args->regions.size()<=1){
myvcf = new vcfReader(args->infile,NULL);
args->hd=bcf_hdr_2_bam_hdr_t(myvcf->hs);
args->nInd = myvcf->hs->nsamples;
}
}
//make args->hd
revMap = buildRevTable(args->hd);
args->revMap = revMap;
setArgsBam(args);
if(args->inputtype==INPUT_VCF_GL){
if(args->regions.size()==1){
char tmp[1024];
int start=args->regions[0].start;
int stop=args->regions[0].stop;
int ref=args->regions[0].refID;
snprintf(tmp,1024,"%s:%d-%d",args->hd->target_name[ref],start+1,stop);
// fprintf(stderr,"tmp:%s\n",tmp);
// exit(0);
myvcf->seek(tmp);
}
}
if(fname==NULL)
return;
gz=Z_NULL;
gz=gzopen(fname,"r");
if(gz==Z_NULL){
fprintf(stderr,"\t-> Problem opening file: \'%s\'\n",fname);
exit(0);
}
switch(args->inputtype){
case INPUT_PILEUP:{
mpil = new mpileup(args->nInd,gz,args->revMap,minQ);
break;
}
case INPUT_GLF:{
myglf = new glfReader(args->nInd,gz,10,isSim);
break;
}
case INPUT_GLF3:{
isSim = 1; //Added by FGV on 22/02/2015: GLF3 is always simulated data until a better alternative can be found
myglf = new glfReader(args->nInd,gz,3,isSim);
break;
}
case INPUT_GLF10_TEXT:{
myglf_text = new glfReader_text(args->nInd,gz,args->revMap);
break;
}
case INPUT_BEAGLE:{
bglObj = new beagle_reader(gz,args->revMap,intName,args->nInd);
break;
}
default:{
break;
}
}
if(args->inputtype==INPUT_VCF_GL||args->inputtype==INPUT_VCF_GL){
fprintf(stderr,"\t-> VCF still beta. Remember that\n");
fprintf(stderr,"\t 1. indels are are discarded\n");
fprintf(stderr,"\t 2. will use chrom, pos PL columns\n");
fprintf(stderr,"\t 3. GL tags are interpreted as log10 and are scaled to ln (NOT USED)\n");
fprintf(stderr,"\t 4. GP tags are interpreted directly as unscaled post probs (spec says phredscaled...) (NOT USED)\n");
fprintf(stderr,"\t 5. FILTER column is currently NOT used (not sure what concensus is)\n");
fprintf(stderr,"\t 6. -sites does NOT work with vcf input but -r does\n");
fprintf(stderr,"\t 7. vcffilereading is still BETA, please report strange behaviour\n");
}
}
// Construction
abcDstat2::abcDstat2(const char *outfiles, argStruct *arguments,int inputtype){
//default values
rmTrans = 0;
sample = 0;
outfile=NULL;
ancName=NULL;
doAbbababa2=0;
doCount=0;
blockSize=5000000;
block=0;
NSITEprint=0;
sizeH1 = 1;
sizeH2 = 1;
sizeH3 = 1;
sizeH4 = 1;
enhance = 1;
DENprint=0;
NUMprint=0;
maxDepth=100;
// you are starting before chromosome 0
currentChr=-1;
NbasesPerLine=50;
//if you dont use the -doAbbababa2 argument then return
if(arguments->argc==2){
if(!strcasecmp(arguments->argv[1],"-doAbbababa2")){
printArg(stdout);
exit(0);
}else
return;
}
//get all options
getOptions(arguments);
printArg(arguments->argumentFile);
//ignore
if(doAbbababa2==0){
shouldRun[index] = 0;
return;
}
//make output files
const char* postfix;
postfix=".abbababa2";
outfile = aio::openFile(outfiles,postfix);
//const char* postfix2;
//postfix2=".abbababaComp";
//outfile2 = aio::openFile(outfiles,postfix2);
// store large amounts of data for printing fast
bufstr.s=NULL;
bufstr.m=0;
bufstr.l=0;
//the number of combinations
nComb=arguments->nInd*(arguments->nInd-1)*(arguments->nInd-2)/2;
COMBprint = new double[256];
fprintf(outfile,"CHR\tBLOCKstart\tBLOCKend\tNumer\tDenom\tnumSites");
for(int a=0;a<4;a++)
for(int b=0;b<4;b++)
for(int c=0;c<4;c++)
for(int d=0;d<4;d++)
fprintf(outfile,"\t%d%d%d%d",a,b,c,d);
fprintf(outfile,"\n");
}//---end of abcDstat2::abcDstat2(const char *outfiles, argStruct *arguments,int inputtype)
//read program parameters
void setArgsBam(argStruct *arguments){
int seed=0;
remove_bads = angsd::getArg("-remove_bads",remove_bads,arguments);
uniqueOnly = angsd::getArg("-uniqueOnly",uniqueOnly,arguments);
only_proper_pairs =angsd::getArg("-only_proper_pairs",only_proper_pairs,arguments);
fai_fname =angsd::getArg("-f",fai_fname,arguments);
minMapQ = angsd::getArg("-minMapQ",minMapQ,arguments);
cigstat = angsd::getArg("-cigstat",cigstat,arguments);
minQ = angsd::getArg("-minQ",minQ,arguments);
downSample = angsd::getArg("-downSample",downSample,arguments);
seed = angsd::getArg("-seed",seed,arguments);
trim = angsd::getArg("-trim",trim,arguments);
trim5 = angsd::getArg("-trim5",trim5,arguments);
trim3 = angsd::getArg("-trim3",trim3,arguments);
arguments->ref=angsd::getArg("-ref",arguments->ref,arguments);
arguments->anc=angsd::getArg("-anc",arguments->anc,arguments);
rghash_name= angsd::getArg("+RG",rghash_name,arguments);
if(rghash_name&&!angsd::fexists(rghash_name))
rghash = add_read_group_single(rghash_name);
if(rghash_name&&angsd::fexists(rghash_name))
rghash = add_read_groups_file(rghash_name);
if(rghash)
fprintf(stderr,"\t-> [READGROUP info] Number of readgroups to include: %d\n",khash_str2int_size(rghash));
adjustMapQ = angsd::getArg("-C",adjustMapQ,arguments);
baq = angsd::getArg("-baq",baq,arguments);
redo_baq = angsd::getArg("-redo-baq",redo_baq,arguments);
if(baq){
if(baq==1)
baq=1; //wauv
else if(baq==2)
baq=3;
else{
fprintf(stderr,"\t-> only supported options for -baq is: 1 (normal baq) and 2 (extended baq (SAMtools default)). Value supplied:%d\n",baq);
exit(0);//ly su
}
if(redo_baq==1)
baq |=4;
}
// fprintf(stderr,"baq:%d redobaq:%d\n",baq,redo_baq);exit(0);
regfile =angsd::getArg("-r",regfile,arguments);
regfiles = angsd::getArg("-rf",regfiles,arguments);
MAX_SEQ_LEN = angsd::getArg("-setMinChunkSize",MAX_SEQ_LEN,arguments);
checkBamHeaders = angsd::getArg("-checkBamHeaders",checkBamHeaders,arguments);
doCheck = angsd::getArg("-doCheck",doCheck,arguments);
MPLP_IGNORE_RG = angsd::getArg("--ignore-RG",MPLP_IGNORE_RG,arguments);
arguments->nReads = angsd::getArg("-nReads",arguments->nReads,arguments);
arguments->show = angsd::getArg("-show",arguments->show,arguments);
if(regfile && regfiles)
fprintf(stderr,"\t-> WARNING both -r and -rf has been set \n");
if(seed)
srand48(seed);
char *tmp = NULL;
tmp = angsd::getArg("-ref",tmp,arguments);
if(tmp==NULL && adjustMapQ!=0){
fprintf(stderr,"\t-> Must also supply -ref for adjusting the mapping quality\n");
exit(0);
}
if(tmp==NULL&&baq!=0){
fprintf(stderr,"\t-> Must also supply -ref for adjusting base qualities (baq)\n");
exit(0);
}
free(tmp);
std::vector<char *> regionsRaw;
if(regfiles)
regionsRaw = angsd::getFilenames(regfiles,0);
if(regfile)
regionsRaw.push_back(strdup(regfile));
// fprintf(stderr,"\t-> RegionsRaw.size():%lu hd:%p\n",regionsRaw.size(),arguments->hd);
for(size_t i=0;i<regionsRaw.size();i++){
regs tmpRegs;
if(parse_region(regionsRaw[i],arguments->hd,tmpRegs.refID,tmpRegs.start,tmpRegs.stop,arguments->revMap)<0||tmpRegs.stop<tmpRegs.start){
fprintf(stderr,"[%s] Problems with indexing: %s\n",__FUNCTION__,regionsRaw[i]);
exit(0);
}else
arguments->regions.push_back(tmpRegs);
free(regionsRaw[i]);
}
printArg(arguments->argumentFile,arguments);
if(regfile)
free(regfile);
if(regfiles)
free(regfiles);
}
