Rcpp::StringMatrix DataFrame_to_StringMatrix( Rcpp::DataFrame df ){
Rcpp::StringVector sv = df(0);
Rcpp::StringMatrix sm(sv.size(), df.size());
sm.attr("col.names") = df.attr("col.names");
sm.attr("row.names") = df.attr("row.names");
for(int i=0; i < df.size(); i++){
sv = df(i);
for(int j=0; j < sv.size(); j++){
sm(j, i) = sv(j);
}
}
return sm;
}
// [[Rcpp::export]]
void write_vcf_body_gz( Rcpp::DataFrame fix, Rcpp::DataFrame gt, std::string filename , int mask=0 ) {
// http://stackoverflow.com/a/5649224
// fix DataFrame
Rcpp::StringVector chrom = fix["CHROM"];
Rcpp::StringVector pos = fix["POS"];
Rcpp::StringVector id = fix["ID"];
Rcpp::StringVector ref = fix["REF"];
Rcpp::StringVector alt = fix["ALT"];
Rcpp::StringVector qual = fix["QUAL"];
Rcpp::StringVector filter = fix["FILTER"];
Rcpp::StringVector info = fix["INFO"];
// gt DataFrame
Rcpp::StringMatrix gt_cm = DataFrame_to_StringMatrix(gt);
Rcpp::StringVector column_names(gt.size());
column_names = gt.attr("names");
int i = 0;
int j = 0;
gzFile *fi = (gzFile *)gzopen(filename.c_str(),"ab");
// gzFile *fi = (gzFile *)gzopen(filename.c_str(),"abw");
for(i=0; i<chrom.size(); i++){
Rcpp::checkUserInterrupt();
if(mask == 1 && filter(i) != "PASS" ){
// Don't print variant.
} else {
std::string tmpstring;
tmpstring = chrom(i);
tmpstring = tmpstring + "\t" + pos(i) + "\t";
if(id(i) == NA_STRING){
tmpstring = tmpstring + ".";
} else {
tmpstring = tmpstring + id(i);
}
tmpstring = tmpstring + "\t" + ref(i) + "\t" + alt(i) + "\t";
if(qual(i) == NA_STRING){
tmpstring = tmpstring + "." + "\t";
} else {
tmpstring = tmpstring + qual(i) + "\t";
}
if(filter(i) == NA_STRING){
tmpstring = tmpstring + "." + "\t";
} else {
tmpstring = tmpstring + filter(i) + "\t";
}
tmpstring = tmpstring + info(i);
// gt portion
for(j=0; j<column_names.size(); j++){
if(gt_cm(i, j) == NA_STRING){
tmpstring = tmpstring + "\t" + "./.";
} else {
tmpstring = tmpstring + "\t" + gt_cm(i, j);
}
}
// gzwrite(fi,"my decompressed data",strlen("my decompressed data"));
// gzwrite(fi,"\n",strlen("\n"));
// std::string tmpstring = "test string\n";
gzwrite(fi, (char *)tmpstring.c_str(), tmpstring.size());
gzwrite(fi,"\n",strlen("\n"));
}
}
gzclose(fi);
return;
}
RcppExport SEXP RXMLADiscover(SEXP handle, SEXP request, SEXP rRestrictionsString, SEXP rPropertiesString)
{
XmlaWebServiceSoapProxy service = XmlaWebServiceSoapProxy(SOAP_XML_DEFAULTNS, SOAP_XML_DEFAULTNS);
Rcpp::XPtr<XMLAHandle> ptr(handle);
const char *connectionString = ptr->connectionString;
std::string propertiesString = CHAR(STRING_ELT(rPropertiesString,0));
std::string restrictionsString = CHAR(STRING_ELT(rRestrictionsString, 0));
ns1__Session session;
std::string sessionId = ptr->sessionID;
session.SessionId = &sessionId;
service.soap_header(NULL, NULL, &session, NULL);
_ns1__Discover discover;
ns1__Restrictions restrictions;
ns1__RestrictionList restrictionList;
ns1__Properties properties;
ns1__PropertyList propertyList;
_ns1__DiscoverResponse discoverResponse;
std::string requestType = CHAR(STRING_ELT(request,0));
std::transform(requestType.begin(), requestType.end(), requestType.begin(), ::toupper);
discover.RequestType = &requestType;
discover.Restrictions = &restrictions;
restrictions.RestrictionList = &restrictionList;
discover.Properties = &properties;
properties.PropertyList = &propertyList;
if (!propertiesString.empty()) {
parseKeyValuePairs(&propertiesString, propertyList.__any);
}
if (!restrictionsString.empty()) {
parseKeyValuePairs(&restrictionsString, restrictionList.__any);
}
service.userid = ptr->userName;
service.passwd = ptr->password;
if (service.Discover(connectionString, NULL, &discover, &discoverResponse) == SOAP_OK) {
std::string rawXML = "<root xmlns=\"urn:schemas-microsoft-com:xml-analysis:rowset\" xmlns:xsi=\"http://www.w3.org/2001/XMLSchema-instance\" xmlns:xsd=\"http://www.w3.org/2001/XMLSchema\"><xsd:schema targetNamespace=\"urn:schemas-microsoft-com:xml-analysis:rowset\" xmlns:sql=\"urn:schemas-microsoft-com:xml-sql\" elementFormDefault=\"qualified\">";
rawXML = rawXML + discoverResponse.return_->ns2__root->xsd__schema + "</xsd:schema></root>";
char *schema = strdup(rawXML.c_str());
rapidxml::xml_document<> doc;
doc.parse<0>(schema);
// Find XML section containing column names
rapidxml::xml_node<char> *rowNode = doc.first_node()->first_node()->first_node("xsd:complexType");
while(rowNode != NULL && strcmp(rowNode->first_attribute("name")->value(), "row") != 0) {
rowNode = rowNode->next_sibling("xsd:complexType");
}
rapidxml::xml_node<char> *schemaElementNode = rowNode->first_node()->first_node();
std::vector<char *> rows = discoverResponse.return_->ns2__root->__union_ResultXmlRoot->row;
Rcpp::DataFrame resultDataFrame;
Rcpp::CharacterVector colNames;
char *colName;
while(schemaElementNode != NULL) {
colName = schemaElementNode->first_attribute("name")->value();
colNames.push_back(colName);
if (schemaElementNode->first_attribute("type") != 0) {
rowSetParseData(rows, &resultDataFrame, colName, true);
}
else {
rowSetParseData(rows, &resultDataFrame, colName, false);
}
schemaElementNode = schemaElementNode->next_sibling();
}
resultDataFrame.attr("names") = colNames;
service.destroy();
return resultDataFrame;
}
else {
std::cerr << service.fault->faultstring << std::endl;
}
service.destroy();
return Rcpp::wrap(false);
}
// [[Rcpp::export]]
void write_vcf_body( Rcpp::DataFrame fix, Rcpp::DataFrame gt, std::string filename , int mask=0 ) {
//int write_vcf_body( Rcpp::DataFrame fix, Rcpp::DataFrame gt, std::string filename , int mask=0 ) {
// fix DataFrame
Rcpp::StringVector chrom = fix["CHROM"];
Rcpp::StringVector pos = fix["POS"];
Rcpp::StringVector id = fix["ID"];
Rcpp::StringVector ref = fix["REF"];
Rcpp::StringVector alt = fix["ALT"];
Rcpp::StringVector qual = fix["QUAL"];
Rcpp::StringVector filter = fix["FILTER"];
Rcpp::StringVector info = fix["INFO"];
// gt DataFrame
Rcpp::StringMatrix gt_cm = DataFrame_to_StringMatrix(gt);
Rcpp::StringVector column_names(gt.size());
column_names = gt.attr("names");
// column_names = gt_cm.attr("col.names");
// delete gt;
int i = 0;
int j = 0;
// Uncompressed.
std::ofstream myfile;
myfile.open (filename.c_str(), std::ios::out | std::ios::app | std::ios::binary);
// gzFile *fi = (gzFile *)gzopen("file.gz","wb");
for(i=0; i<chrom.size(); i++){
Rcpp::checkUserInterrupt();
if(mask == 1 && filter(i) == "PASS" ){
// Don't print variant.
} else {
myfile << chrom(i);
myfile << "\t";
myfile << pos(i);
myfile << "\t";
if(id(i) == NA_STRING){
myfile << ".";
myfile << "\t";
} else {
myfile << id(i);
myfile << "\t";
}
myfile << ref(i);
myfile << "\t";
myfile << alt(i);
myfile << "\t";
if(qual(i) == NA_STRING){
myfile << ".";
myfile << "\t";
} else {
myfile << qual(i);
myfile << "\t";
}
if(filter(i) == NA_STRING){
myfile << ".";
myfile << "\t";
} else {
myfile << filter(i);
myfile << "\t";
}
if(info(i) == NA_STRING){
myfile << ".";
myfile << "\t";
} else {
myfile << info(i);
}
// gt region.
myfile << "\t";
myfile << gt_cm(i, 0);
for(j=1; j<column_names.size(); j++){
myfile << "\t";
myfile << gt_cm(i, j);
}
myfile << "\n";
}
}
myfile.close();
return;
}
RcppExport SEXP RXMLAExecute(SEXP handle, SEXP query, SEXP rPropertiesString)
{
XmlaWebServiceSoapProxy service = XmlaWebServiceSoapProxy(SOAP_XML_DEFAULTNS, SOAP_XML_DEFAULTNS);
Rcpp::XPtr<XMLAHandle> ptr(handle);
const char *connectionString = ptr->connectionString;
std::string propertiesString = CHAR(STRING_ELT(rPropertiesString,0));
ns1__Session session;
std::string sessionId = ptr->sessionID;
session.SessionId = &sessionId;
service.soap_header(NULL, NULL, &session, NULL);
_ns1__Execute execute;
ns1__CommandStatement command;
ns1__Properties properties;
ns1__PropertyList propertyList;
_ns1__ExecuteResponse response;
std::string statement = CHAR(STRING_ELT(query,0));
command.Statement = &statement;
execute.Command = &command;
execute.Properties = &properties;
properties.PropertyList = &propertyList;
if (!propertiesString.empty()) {
parseKeyValuePairs(&propertiesString, propertyList.__any);
}
service.userid = ptr->userName;
service.passwd = ptr->password;
if (service.Execute(connectionString, NULL, &execute, &response) == SOAP_OK) {
// Parse MDDataSet
if (response.return_->ns4__root != NULL && response.return_->ns4__root->__union_ResultXmlRoot != NULL && response.return_->ns4__root->__union_ResultXmlRoot->Axes != NULL) {
if (response.return_->ns4__root->__union_ResultXmlRoot->Axes->Axis.size() < 3) {
std::cerr << "Error: No data on Axis1" << std::endl;
return Rcpp::wrap(false);
}
if (response.return_->ns4__root->__union_ResultXmlRoot->Axes->Axis.size() > 3) {
std::cerr << "Error: More than 2 axes not supported" << std::endl;
return Rcpp::wrap(false);
}
ns4__Axes *axes = response.return_->ns4__root->__union_ResultXmlRoot->Axes;
std::vector<ns4__Cell *> cellDataVector = response.return_->ns4__root->__union_ResultXmlRoot->CellData->Cell;
int numCols = response.return_->ns4__root->__union_ResultXmlRoot->Axes->Axis[0]->__union_Axis->Tuples->Tuple.size();
int numRows = response.return_->ns4__root->__union_ResultXmlRoot->Axes->Axis[1]->__union_Axis->Tuples->Tuple.size();
int cellDataVectorMember = 0;
Rcpp::CharacterVector colNames;
Rcpp::CharacterVector rowNames;
Rcpp::NumericMatrix resultMatrix(numRows, numCols);
for (int row = 0; row < numRows; row++) {
for (int col = 0; col < numCols; col++) {
if (cellDataVector[cellDataVectorMember]->CellOrdinal == ((row * numCols) + col)) {
resultMatrix(row, col) = *cellDataVector[cellDataVectorMember]->Value;
if (cellDataVectorMember < cellDataVector.size() - 1) {
cellDataVectorMember += 1;
}
}
else {
resultMatrix(row, col) = NA_REAL;
}
}
mdDataSetGetNames(rowNames, axes, row, true);
}
for (int col = 0; col < numCols; col++) {
mdDataSetGetNames(colNames, axes, col, false);
}
colNames.push_front("Row Names");
Rcpp::DataFrame resultDataFrame(resultMatrix);
resultDataFrame.push_front(rowNames);
resultDataFrame.attr("names") = colNames;
service.destroy();
return resultDataFrame;
}
// Parse RowSet
else if (response.return_->ns2__root != NULL
&& response.return_->ns2__root->xsd__schema != NULL
&& response.return_->ns2__root->__union_ResultXmlRoot != NULL
&& !response.return_->ns2__root->__union_ResultXmlRoot->row.empty()) {
std::string rawXML = "<root xmlns=\"urn:schemas-microsoft-com:xml-analysis:rowset\" xmlns:xsi=\"http://www.w3.org/2001/XMLSchema-instance\" xmlns:xsd=\"http://www.w3.org/2001/XMLSchema\"><xsd:schema targetNamespace=\"urn:schemas-microsoft-com:xml-analysis:rowset\" xmlns:sql=\"urn:schemas-microsoft-com:xml-sql\" elementFormDefault=\"qualified\">";
rawXML = rawXML + response.return_->ns2__root->xsd__schema + "</xsd:schema></root>";
char *schema = strdup(rawXML.c_str());
rapidxml::xml_document<> doc;
doc.parse<0>(schema);
// Find XML section containing column names
rapidxml::xml_node<char> *rowNode = doc.first_node()->first_node()->first_node("xsd:complexType");
while(rowNode != NULL && strcmp(rowNode->first_attribute("name")->value(), "row") != 0) {
rowNode = rowNode->next_sibling("xsd:complexType");
}
rapidxml::xml_node<char> *schemaElementNode = rowNode->first_node()->first_node();
std::vector<char *> rows = response.return_->ns2__root->__union_ResultXmlRoot->row;
Rcpp::DataFrame resultDataFrame;
Rcpp::CharacterVector colNames;
char *colName;
while(schemaElementNode != NULL) {
colName = schemaElementNode->first_attribute("name")->value();
colNames.push_back(colName);
if (schemaElementNode->first_attribute("type") != 0) {
rowSetParseData(rows, &resultDataFrame, colName, true);
}
else {
rowSetParseData(rows, &resultDataFrame, colName, false);
}
schemaElementNode = schemaElementNode->next_sibling();
}
resultDataFrame.attr("names") = colNames;
service.destroy();
return resultDataFrame;
}
service.destroy();
return Rcpp::wrap(true);
}
else {
char * errorMessage = service.fault->detail->__any;
std::cerr << errorMessage << std::endl;
}
service.destroy();
return Rcpp::wrap(false);
}