Various fixes

Author: ladinesa

src/nomad_simulation_parsers/parsers/__init__.py

@@ -63,7 +63,7 @@ class Wannier90ParserEntryPoint(EntryPoint):
     description='NOMAD parser for CRYSTAL.',
     python_package='nomad_simulation_parsers',
     mainfile_contents_re=r'(\r?\n \*\s+CRYSTAL[\d]+\s+\*\r?\n \*\s*[a-zA-Z]+ :'
-        ' \d+[\.\d+]*)',
+    r' \d+[\.\d+]*)',
     parser_class_name='nomad_simulation_parsers.parsers.crystal.parser.CrystalParser',
     code_name='CRYSTAL',
     code_homepage='https://www.crystal.unito.it/',

src/nomad_simulation_parsers/parsers/crystal/parser.py

@@ -6,6 +6,7 @@
 
 import numpy as np
 import pint
+from ase.data import chemical_symbols
 from nomad import atomutils
 from nomad.datamodel import EntryArchive
 from nomad.parsing import MatchingParser
@@ -104,10 +105,13 @@ def get_atoms(self, source: dict[str, Any]) -> list[str]:
 
         def normalize_label(label: str) -> str:
             norm = re.match(r'([a-z][a-z]?).*', label.lower())
-            if norm:
-                return norm.group(1).capitalize()
             # unknown specie
-            return 'X'
+            # TODO not possible to define ghost atom
+            unknown = None
+            if norm:
+                label = norm.group(1).capitalize()
+                return label if label in chemical_symbols[1:] else unknown
+            return unknown
 
         return [
             dict(label=normalize_label(label), number=numbers[n])

src/nomad_simulation_parsers/parsers/fhiaims/common.py

@@ -39,7 +39,7 @@ def init_quantities(self) -> None:
         ]
 
     def get_atoms(self) -> Atoms:
-        return Atoms(
+        atoms = Atoms(
             cell=self.lattice_vector,
             pbc=self.lattice_vector is not None,
             positions=[
@@ -51,7 +51,15 @@ def get_atoms(self) -> Atoms:
             symbols=[atom.label for atom in self.atom],
             magmoms=self.magmom,
         )
-
+        # TODO compatibility with PhonopyAtoms
+        add_attribs = dict(
+            masses=atoms.get_masses(),
+            magnetic_moments=None,
+            scaled_positions=atoms.get_scaled_positions(),
+        )
+        for key, val in add_attribs.items():
+            setattr(atoms, key, val)
+        return atoms
 
 class ControlParser(TextParser):
     def __init__(self):

src/nomad_simulation_parsers/parsers/fhiaims/parser.py

@@ -602,7 +602,8 @@ def is_mainfile(
                     children = ['phonon', 'phonon_workflow']
 
         if children:
-            self.level = 1
+            # TODO not possible at the moment to redefine level
+            # self.level = 1
             self.creates_children = True
 
         return children or is_mainfile

src/nomad_simulation_parsers/parsers/quantumespresso/parser.py

@@ -216,6 +216,16 @@ class QuantumEspressoParser(MatchingParser):
     """
 
     archive_writer = QuantumEspressoArchiveWriter()
+    _levels = {}
+    _mainfile = None
+
+    @property
+    def level(self):
+        return self._levels.pop(self._mainfile, self._level)
+
+    @level.setter
+    def level(self, value: int):
+        self._level = value
 
     def is_mainfile(
         self,
@@ -239,7 +249,10 @@ def is_mainfile(
                         continue
                     programs.append(f'{len(programs)} {match.group(1)}')
             if 'pwscf' in programs[0].lower():
-                self.level = 2
+                # TODO not possible at the moment to redefine level
+                self._levels[filename] = 2
+                self._mainfile = filename
+                # self.level = 2
                 # search all qe mainfiles in the directory and sub directories
                 qe_files = search_files(
                     '*.out', os.path.dirname(filename), include_all=True
@@ -266,5 +279,4 @@ def parse(
         logger: BoundLogger,
         child_archives: dict[str, EntryArchive] = {},
     ) -> None:
-        print('PPPP')
         self.archive_writer.write(mainfile, archive, logger, child_archives)

src/nomad_simulation_parsers/parsers/vasp/parser.py

@@ -25,7 +25,7 @@ def parse(
         mainfile: str,
         archive: 'EntryArchive',
         logger: 'BoundLogger',
-        child_archives: dict[str, 'EntryArchive'] = None,
+        child_archives: dict[str, 'EntryArchive'] = {},
     ) -> None:
         # reload schema to load vasp annotations
         reload(vasp)

src/nomad_simulation_parsers/parsers/vasp/xml_parser.py

@@ -36,7 +36,7 @@ def get_eigenvalues(self, array: list) -> dict[str, Any]:
         return dict(eigenvalues=transposed[0], occupations=transposed[1])
 
     def get_energy_contributions(
-        self, source: dict[str, Any], **kwargs
+        self, source: list[dict[str, Any]], **kwargs
     ) -> list[dict[str, Any]]:
         return [
             c
@@ -60,6 +60,13 @@ def get_forces(self, source: dict[str, Any]) -> dict[str, Any]:
             return {}
         return dict(forces=value, npoints=len(value), rank=[3])
 
+    def reshape_array(self, source: np.ndarray, shape_rest: tuple = (3,)) -> np.ndarray:
+        if source is None:
+            return
+        return np.reshape(
+            source, (np.size(source) // int(np.prod(shape_rest)), *shape_rest)
+        )
+
 
 class XMLArchiveWriter(ArchiveWriter):
     def write_to_archive(self) -> None:

src/nomad_simulation_parsers/schema_packages/vasp.py

@@ -166,13 +166,29 @@ class KMesh(numerical_settings.KMesh):
     numerical_settings.KMesh.points.m_annotations.setdefault(
         MAPPING_ANNOTATION_KEY, {}
     ).update(
-        dict(xml=MapperAnnotation(mapper='.varray[?"@name"==\'kpointlist\'].v | [0]'))
+        dict(
+            xml=MapperAnnotation(
+                mapper=(
+                    'reshape_array',
+                    ['.varray[?"@name"==\'kpointlist\'].v | [0]'],
+                    dict(shape_rest=(3)),
+                )
+            )
+        )
     )
 
     numerical_settings.KMesh.weights.m_annotations.setdefault(
         MAPPING_ANNOTATION_KEY, {}
     ).update(
-        dict(xml=MapperAnnotation(mapper='.varray[?"@name"==\'weights\'].v | [0]'))
+        dict(
+            xml=MapperAnnotation(
+                mapper=(
+                    'reshape_array',
+                    ['.varray[?"@name"==\'weights\'].v | [0]'],
+                    dict(shape_rest=()),
+                )
+            )
+        )
     )
 
 
@@ -193,7 +209,10 @@ class AtomicCell(model_system.AtomicCell):
         MAPPING_ANNOTATION_KEY, {}
     ).update(
         dict(
-            xml=MapperAnnotation(mapper='.varray.v', unit='angstrom'),
+            xml=MapperAnnotation(
+                mapper=('reshape_array', ['.varray.v'], dict(shape_rest=(3))),
+                unit='angstrom',
+            ),
             outcar=MapperAnnotation(
                 mapper='.positions_forces', unit='angstrom', search='@ | [0]'
             ),