Merge afb7ae8 into 4674dcb

pyUSID/__version__.py

@@ -1,2 +1,2 @@
-version = '0.0.8'
+version = '0.0.8.1'
 time = '2020-01-14 11:20:25'

pyUSID/io/hdf_utils/simple.py

@@ -370,7 +370,6 @@ def validate_anc_h5_dsets(h5_inds, h5_vals, main_shape, is_spectroscopic=True):
     if h5_inds.shape != h5_vals.shape:
         raise ValueError('h5_inds: {} and h5_vals: {} should be of the same '
                          'shape'.format(h5_inds.shape, h5_vals.shape))
-    print(main_shape)
     if isinstance(main_shape, (list, tuple)):
         if not contains_integers(main_shape, min_val=1) or \
                 len(main_shape) != 2:
@@ -802,8 +801,9 @@ def create_results_group(h5_main, tool_name, h5_parent_group=None):
     # this are NOT being used right now but will be in the subsequent versions of pyUSID
     write_simple_attrs(h5_group, {'tool': tool_name, 'num_source_dsets': 1})
     # in this case, there is only one source
-    for dset_ind, dset in enumerate([h5_main]):
-        h5_group.attrs['source_' + '{:03d}'.format(dset_ind)] = dset.ref
+    if h5_parent_group.file == h5_main.file:
+        for dset_ind, dset in enumerate([h5_main]):
+            h5_group.attrs['source_' + '{:03d}'.format(dset_ind)] = dset.ref
 
     return h5_group
 

pyUSID/processing/process.py

@@ -18,7 +18,7 @@
 
 from .comp_utils import parallel_compute, get_MPI, group_ranks_by_socket, \
     get_available_memory
-from ..io.hdf_utils import check_if_main, check_for_old, get_attributes
+from ..io.hdf_utils import check_if_main, check_for_old, write_simple_attrs
 from ..io.usi_data import USIDataset
 from ..io.dtype_utils import integers_to_slices, lazy_load_array, \
     validate_single_string_arg
@@ -276,7 +276,7 @@ def __init__(self, h5_main, process_name, parms_dict=None, cores=None,
 
         if self.mpi_rank == 0:
             print('Consider calling test() to check results before calling compute() which computes on the entire'
-                  ' dataset and writes back to the HDF5 file')
+                  ' dataset and writes results to the HDF5 file')
 
         self.duplicate_h5_groups, self.partial_h5_groups = self._check_for_duplicates()
 
@@ -771,6 +771,17 @@ def __create_compute_status_dataset(self):
                 if completed_pixels > 0:
                     self._h5_status_dset[:completed_pixels] = 1
 
+    def _write_source_dset_provenance(self):
+        """
+        Writes path of HDF5 file and path of h5_main to the results group
+        if results are being written to a new HDF5 file
+        """
+        if self.h5_main.file == self.h5_results_grp.file:
+            return
+        write_simple_attrs(self.h5_results_grp,
+                           {'source_file_path': self.h5_main.file.filename,
+                            'source_dataset_path': self.h5_main.name})
+
     def _get_existing_datasets(self):
         """
         The purpose of this function is to allow processes to resume from partly computed results
@@ -892,6 +903,7 @@ def get_cycles(self):
             if self.verbose and self.mpi_rank == 0:
                 print('Creating HDF5 group and datasets to hold results')
             self._create_results_datasets()
+            self._write_source_dset_provenance()
         else:
             # resuming from previous checkpoint
             resuming = True