Fix ruff check issues (E501 line too long)

Changes:
- Extract POTCAR regex pattern to module-level constant
- Break long log messages and comments to fit 88 char limit
- Auto-format multiline function calls and annotations
- Remove unused import in test file

All ruff checks now pass.

Author: ndaelman-hu

src/nomad_simulation_parsers/parsers/vasp/outcar_parser.py

@@ -60,13 +60,23 @@ def convert(v):
     Quantity('RCORE', r'RCORE\s*=\s*([\d\.]+)', dtype=float),
     Quantity('ENMAX', r'ENMAX\s*=\s*([\d\.]+)', dtype=float),
     Quantity('ENMIN', r'ENMIN\s*=\s*([\d\.]+)', dtype=float),
-    Quantity('LPAW', r'LPAW\s*=\s*([TF])', dtype=bool), ## doublecheck mapping
-    Quantity('LULTRA', r'LULTRA\s*=\s*([TF])', dtype=bool), ## doublecheck mapping
-    Quantity('LMAX', r'number of l-projection\s+operators is LMAX\s*=\s*(\d+)', dtype=int),
-    Quantity('LMMAX', r'number of lm-projection\s+operators is LMMAX\s*=\s*(\d+)', dtype=int),
+    Quantity('LPAW', r'LPAW\s*=\s*([TF])', dtype=bool),  ## doublecheck mapping
+    Quantity('LULTRA', r'LULTRA\s*=\s*([TF])', dtype=bool),  ## doublecheck mapping
+    Quantity(
+        'LMAX', r'number of l-projection\s+operators is LMAX\s*=\s*(\d+)', dtype=int
+    ),
+    Quantity(
+        'LMMAX', r'number of lm-projection\s+operators is LMMAX\s*=\s*(\d+)', dtype=int
+    ),
     Quantity('SHA256', r'SHA256\s*=\s*(\w+)', dtype=str),
 ]
 
+# Regex pattern for POTCAR sections in OUTCAR
+POTCAR_PATTERN = (
+    r'POTCAR:([\s\S]+?VRHFIN[\s\S]+?)'
+    r'(?=\s*POTCAR:|\s*local pseudopotential:|\Z)'
+)
+
 
 # TODO temporary fix for structlog unable to propagate logger
 class VASPMetainfoParser(MetainfoParser):
@@ -336,7 +346,7 @@ def str_to_eigenvalues(val_in):
             ),
             Quantity(
                 'pseudopotentials',
-                r'POTCAR:([\s\S]+?VRHFIN[\s\S]+?)(?=\s*POTCAR:|\s*local pseudopotential:|\Z)',
+                POTCAR_PATTERN,
                 repeats=True,
                 sub_parser=TextParser(quantities=potcar_quantities),
             ),
@@ -536,7 +546,6 @@ def derive_is_gw_optimized(self, titel: str) -> bool:
         return titel is not None and '_GW' in titel
 
 
-
 class OutcarArchiveWriter(ArchiveWriter):
     def write_to_archive(self) -> None:
         # set up archive parser

src/nomad_simulation_parsers/parsers/vasp/xml_parser.py

@@ -76,7 +76,6 @@ def reshape_array(self, source: np.ndarray, shape_rest: tuple = (3,)) -> np.ndar
         )
 
 
-
 class XMLArchiveWriter(ArchiveWriter):
     def write_to_archive(self) -> None:
         data_parser = VASPMetainfoParser()
@@ -106,22 +105,27 @@ def write_to_archive(self) -> None:
         outcar_path = self._find_outcar()
         if outcar_path and os.path.exists(outcar_path):
             LOGGER.info(
-                f'Found OUTCAR at {outcar_path}, extending vasprun.xml pseudopotentials '
-                'with detailed metadata'
+                f'Found OUTCAR at {outcar_path}, extending vasprun.xml '
+                'pseudopotentials with detailed metadata'
             )
             from nomad.parsing.file_parser import Quantity, TextParser
             from nomad.parsing.file_parser.mapping_parser import (
                 TextParser as MappingTextParser,
             )
+
             from nomad_simulation_parsers.parsers.vasp.outcar_parser import (
                 potcar_quantities,
             )
 
+            potcar_pattern = (
+                r'POTCAR:([\s\S]+?VRHFIN[\s\S]+?)'
+                r'(?=\s*POTCAR:|\s*local pseudopotential:|\Z)'
+            )
             outcar_supplement_parser = TextParser(
                 quantities=[
                     Quantity(
                         'pseudopotentials',
-                        r'POTCAR:([\s\S]+?VRHFIN[\s\S]+?)(?=\s*POTCAR:|\s*local pseudopotential:|\Z)',
+                        potcar_pattern,
                         repeats=True,
                         sub_parser=TextParser(quantities=potcar_quantities),
                     )
@@ -136,8 +140,8 @@ def write_to_archive(self) -> None:
             # This preserves XML structure while adding OUTCAR's detailed metadata
             outcar_parser.convert(data_parser, update_mode='merge')
 
-            # Clean up duplicate pseudopotentials created by type mismatch during merge
-            # When PP_OUT tries to merge at index 0 but finds KSpace, it creates a new PP
+            # Clean up duplicate pseudopotentials created by type mismatch
+            # When PP_OUT merges at index 0 but finds KSpace, creates new PP
             model_method = data_parser.data_object.model_method[0]
             seen_pp_names = set()
             deduplicated_ns = []
@@ -170,6 +174,10 @@ def _find_outcar(self) -> str | None:
         """
         mainfile_dir = PathLib(self.mainfile).parent
         return next(
-            (str(f) for f in mainfile_dir.iterdir() if f.name.lower().startswith('outcar')),
-            None
+            (
+                str(f)
+                for f in mainfile_dir.iterdir()
+                if f.name.lower().startswith('outcar')
+            ),
+            None,
         )

src/nomad_simulation_parsers/schema_packages/vasp.py

@@ -54,9 +54,7 @@ class Simulation(general.Simulation):
     add_mapping_annotation(general.ModelMethod.m_def, KPOINTS_XML, '.@')
     add_mapping_annotation(general.ModelMethod.m_def, PP_XML, '.@')
     add_mapping_annotation(general.ModelMethod.m_def, PP_OUT, '.@')
-    add_mapping_annotation(
-        general.Simulation.model_system, XML_KEY, '.calculation'
-    )
+    add_mapping_annotation(general.Simulation.model_system, XML_KEY, '.calculation')
     add_mapping_annotation(general.Simulation.model_system, OUTCAR_KEY, '.calculation')
     add_mapping_annotation(general.Simulation.outputs, XML_KEY, '.calculation')
     add_mapping_annotation(general.Simulation.outputs, XML2_KEY, '.calculation')
@@ -80,7 +78,9 @@ class Program(general.Program):
 
 class ModelMethod(general.ModelMethod):
     add_mapping_annotation(
-        numerical_settings.Pseudopotential.m_def, PP_XML, '.atominfo.array[?"@name"==\'atomtypes\'] | [0].set.rc'
+        numerical_settings.Pseudopotential.m_def,
+        PP_XML,
+        '.atominfo.array[?"@name"==\'atomtypes\'] | [0].set.rc',
     )
 
 
@@ -114,6 +114,7 @@ class XCComponent(model_method.XCComponent):
         model_method.XCComponent.canonical_label, OUTCAR_KEY, '.name'
     )
 
+
 class KSpace(numerical_settings.KSpace):
     add_mapping_annotation(numerical_settings.KSpace.k_mesh, KPOINTS_XML, '.@')
 
@@ -347,12 +348,8 @@ class Pseudopotential(numerical_settings.Pseudopotential):
         '.RCORE',
         unit='angstrom',
     )
-    add_mapping_annotation(
-        numerical_settings.Pseudopotential.l_max, PP_OUT, '.LMAX'
-    )
-    add_mapping_annotation(
-        numerical_settings.Pseudopotential.lm_max, PP_OUT, '.LMMAX'
-    )
+    add_mapping_annotation(numerical_settings.Pseudopotential.l_max, PP_OUT, '.LMAX')
+    add_mapping_annotation(numerical_settings.Pseudopotential.lm_max, PP_OUT, '.LMMAX')
     add_mapping_annotation(
         numerical_settings.Pseudopotential.type,
         PP_OUT,
@@ -375,4 +372,5 @@ class Pseudopotential(numerical_settings.Pseudopotential):
 except Exception as e:
     print(f'[ERROR] Failed to initialize VASP schema package: {e}', flush=True)
     import traceback
+
     traceback.print_exc()

tests/parsers/test_vasp_parser.py

@@ -2,7 +2,6 @@
 from nomad.utils import get_logger
 
 from nomad_simulation_parsers.parsers.vasp.parser import VASPParser
-from tests.parsers.utils import approx
 
 LOGGER = get_logger(__name__)