HDF5: inserting a set of strings in a dataset
I'm currently learning the HDF5 API and I'm trying to insert a set of C++ std::string into a HDF5 dataset (1 column).
In the following snippet, how should I loop over a vector<string>
and insert each string at the right index ?
How should I tell HDF5 whether I want to use a fixed-length string or a can-have-any-length std::string ?
vector<string> samples;
(...)
/* create HDF5 file */
hid_t hdf5file= H5Fcreate(hdf5_filename, H5F_ACC_TRUNC, H5P_DEFAULT, H5P_DEFAULT);
if(hdf5file==-1)
{
cerr << "Cannot create HDF5 file "<< hdf5_filename << endl;
return(EXIT_FAILURE);
}
/* create a group in this file */
hid_t group = H5Gcreate2(hdf5file, "/MyGroup", H5P_DEFAULT, H5P_DEFAULT, H5P_DEFAULT);
if(group==-1)
{
cerr << "Cannot create HDF5 group "<< endl;
return(EXIT_FAILURE);
}
/* create a dataspace for the samples array of one dimension */
hsize_t dim1=samples.size();
hid_t dataspace = H5Screate_simple(1, &dim1, NULL);
if(dataspace==-1)
{
cerr << "Cannot create HDF5 dataspace "<< endl;
return(EXIT_FAILURE);
}
/* create datatype for a string . How shoud I tell if i want a fixed-length string or a can-have-any-length string ?*/
hid_t datatype = H5Tcopy(H5T_C_S1);
if(datatype==-1)
{
cerr << "Cannot create H5Tset_size "<< endl;
return(EXIT_FAILURE);
}
int ret = H5Tset_size (datatype, H5T_VARIABLE);
if(ret!=0)
{
cerr << "Cannot create H5Tset_size "<< endl;
return(EXIT_FAILURE);
}
hid_t dataset = H5Dcreate2(group, "Samples", datatype, dataspace,
H5P_DEFAULT, H5P_DEFAULT, H5P_D开发者_如何学GoEFAULT);
for(vector<string>::size_type i=0;i< samples.size();++i)
{
/** here I'm puzzled, how should I insert the value of samples[i].c_str() at
the i-th index of the dataset ? */
const char* sampleName= samples[i].c_str() ;
????
????
????
}
/* close data set */
H5Dclose(dataset);
/* close datatype */
H5Tclose(datatype);
/* close the dataspace */
H5Sclose(dataspace);
/* close the group */
H5Gclose(group);
/* close hdf5 file */
H5Fclose(hdf5file);
First, make a C-style array of char*
with pointers to your strings:
const size_t n = samples.size();
char* data[n];
for (size_t i = 0; i < n; i++)
{
data[i] = samples[i].c_str();
}
Then write everything in one go:
H5Dwrite(dataset, datatype, dataspace, H5S_ALL, H5P_DEFAULT, data);
精彩评论