Added ORCA parser.

.gitmodules

@@ -55,3 +55,6 @@
 	path = dependencies/parsers/abinit
 	url = https://gitlab.mpcdf.mpg.de/nomad-lab/parser-abinit
 
+[submodule "dependencies/parsers/orca"]
+	path = dependencies/parsers/orca
+	url = https://gitlab.mpcdf.mpg.de/nomad-lab/parser-orca

orca @ 248e14fd

+Subproject commit 248e14fd36539380eed6a4e2a41986d3317d9ac3

nomad/normalizing/system.py

@@ -46,12 +46,12 @@ class SystemNormalizer(SystemBasedNormalizer):
         """ Main normalizer that runs system, syste_type and symmetry analysis."""
 
         self.atom_labels = section_system['atom_labels']
-        # print("self.atom_labels")
-        # print(self.atom_labels)
-        # self.atom_labels =  'Fe' #['Fe2']
         self.atom_species = section_system['atom_atom_numbers']
         self.atom_positions = section_system['atom_positions']
-        self.periodic_dirs = section_system['configuration_periodic_dimensions']
+        # Assume if no config for periodic dimensions that we simply don't have any.
+        # TODO: @dts, this may be something we should change since many DFT programs
+        # have implicit periodicity. Talk with Georg/Claudia.
+        self.periodic_dirs = section_system.get('configuration_periodic_dimensions', None)
         # Try to first read the cell information from the renamed metainfo
         # lattice_vectors, if this doesn't work try the depreciated name
         # simulation_cell. Otherwise, if neither are present, assign None.
@@ -309,4 +309,4 @@ class SystemNormalizer(SystemBasedNormalizer):
         if nomad_classification == 'Atom' and (len(self.atom_labels) > 1):
             nomad_classification = 'Molecule / Cluster'
 
-        return nomad_classification
+        return nomad_classification
\ No newline at end of file

nomad/parsing/__init__.py

@@ -259,6 +259,16 @@ parsers = [
         name='parsers/abinit',
         parser_class_name='abinitparser.AbinitParser',
         mainfile_contents_re=(r'^\n\.Version\s*[0-9.]*\s*of ABINIT\s*')
+    ),
+    LegacyParser(
+        name='parsers/orca',
+        parser_class_name='orcaparser.OrcaParser',
+        mainfile_contents_re=(
+            r'\s+\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\**\s*'
+            r'\s+\* O   R   C   A \*\s*'
+            r'\s+\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\**\s*'
+            r'\s*'
+            r'\s*--- An Ab Initio, DFT and Semiempirical electronic structure package ---\s*')
     )
 ]
 

tests/test_parsing.py

@@ -42,14 +42,15 @@ parser_examples = [
     # ('parsers/band', 'tests/data/parsers/band_adf.out'),  # causes spglib to segfault
     ('parsers/gaussian', 'tests/data/parsers/gaussian/aniline.out'),
     ('parsers/abinit', 'tests/data/parsers/abinit/Fe.out'),
-    ('parsers/quantumespresso', 'tests/data/parsers/quantum-espresso/benchmark.out')
+    ('parsers/quantumespresso', 'tests/data/parsers/quantum-espresso/benchmark.out'),
+    ('parsers/orca', 'tests/data/parsers/orca/orca3dot2706823.out')
 ]
 
 faulty_unknown_one_d_matid_example = [
     ('parsers/template', 'tests/data/normalizers/no_sim_cell_boolean_positions.json')
 ]
 
-correct_num_output_files = 20
+correct_num_output_files = 21
 
 
 class TestLocalBackend(object):