Parsers: remove explicit check for the retrieved folder's existence

aiida_quantumespresso/calculations/cp.py

@@ -132,8 +132,6 @@ def define(cls, spec):
  spec.output('output_parameters', valid_type=orm.Dict)
  spec.default_output_node = 'output_parameters'
 
- spec.exit_code(300, 'ERROR_NO_RETRIEVED_FOLDER',
- message='The retrieved folder data node could not be accessed.')
  spec.exit_code(301, 'ERROR_NO_RETRIEVED_TEMPORARY_FOLDER',
  message='The retrieved temporary folder could not be accessed.')
  spec.exit_code(303, 'ERROR_MISSING_XML_FILE',

aiida_quantumespresso/calculations/dos.py

@@ -26,8 +26,6 @@ def define(cls, spec):
  spec.output('output_parameters', valid_type=orm.Dict)
  spec.output('output_dos', valid_type=orm.XyData)
  spec.default_output_node = 'output_parameters'
- spec.exit_code(300, 'ERROR_NO_RETRIEVED_FOLDER',
- message='The retrieved folder data node could not be accessed.')
  spec.exit_code(310, 'ERROR_OUTPUT_STDOUT_READ',
  message='The stdout output file could not be read.')
  spec.exit_code(312, 'ERROR_OUTPUT_STDOUT_INCOMPLETE',

aiida_quantumespresso/calculations/matdyn.py

@@ -34,8 +34,6 @@ def define(cls, spec):
  spec.output('output_parameters', valid_type=orm.Dict)
  spec.output('output_phonon_bands', valid_type=orm.BandsData)
  spec.default_output_node = 'output_parameters'
- spec.exit_code(300, 'ERROR_NO_RETRIEVED_FOLDER',
- message='The retrieved folder data node could not be accessed.')
  spec.exit_code(310, 'ERROR_OUTPUT_STDOUT_READ',
  message='The stdout output file could not be read.')
  spec.exit_code(312, 'ERROR_OUTPUT_STDOUT_INCOMPLETE',

aiida_quantumespresso/calculations/neb.py

@@ -76,8 +76,6 @@ def define(cls, spec):
  spec.output('output_mep', valid_type=orm.ArrayData,
  help='The original and interpolated energy profiles along the minimum-energy path (mep)')
  spec.default_output_node = 'output_parameters'
- spec.exit_code(300, 'ERROR_NO_RETRIEVED_FOLDER',
- message='The retrieved folder data node could not be accessed.')
  spec.exit_code(303, 'ERROR_MISSING_XML_FILE',
  message='The required XML file is not present in the retrieved folder.')
  spec.exit_code(310, 'ERROR_OUTPUT_STDOUT_READ',

aiida_quantumespresso/calculations/ph.py

@@ -59,8 +59,6 @@ def define(cls, spec):
  spec.default_output_node = 'output_parameters'
 
  # Unrecoverable errors: required retrieved files could not be read, parsed or are otherwise incomplete
- spec.exit_code(300, 'ERROR_NO_RETRIEVED_FOLDER',
- message='The retrieved folder data node could not be accessed.')
  spec.exit_code(302, 'ERROR_OUTPUT_STDOUT_MISSING',
  message='The retrieved folder did not contain the required stdout output file.')
  spec.exit_code(305, 'ERROR_OUTPUT_FILES',

aiida_quantumespresso/calculations/pp.py

@@ -89,8 +89,6 @@ def define(cls, spec):
  spec.default_output_node = 'output_parameters'
 
  # Standard exceptions
- spec.exit_code(300, 'ERROR_NO_RETRIEVED_FOLDER',
- message='The retrieved folder data node could not be accessed.')
  spec.exit_code(301, 'ERROR_NO_RETRIEVED_TEMPORARY_FOLDER',
  message='The retrieved temporary folder could not be accessed.')
  spec.exit_code(302, 'ERROR_OUTPUT_STDOUT_MISSING',

aiida_quantumespresso/calculations/projwfc.py

@@ -45,8 +45,6 @@ def define(cls, spec):
  spec.output('projections', valid_type=ProjectionData, required=False)
  spec.output('bands', valid_type=BandsData, required=False)
  spec.default_output_node = 'output_parameters'
- spec.exit_code(300, 'ERROR_NO_RETRIEVED_FOLDER',
- message='The retrieved folder data node could not be accessed.')
  spec.exit_code(310, 'ERROR_OUTPUT_STDOUT_READ',
  message='The stdout output file could not be read.')
  spec.exit_code(312, 'ERROR_OUTPUT_STDOUT_INCOMPLETE',

aiida_quantumespresso/calculations/pw.py

@@ -79,8 +79,6 @@ def define(cls, spec):
  spec.default_output_node = 'output_parameters'
 
  # Unrecoverable errors: required retrieved files could not be read, parsed or are otherwise incomplete
- spec.exit_code(300, 'ERROR_NO_RETRIEVED_FOLDER',
- message='The retrieved folder data node could not be accessed.')
  spec.exit_code(301, 'ERROR_NO_RETRIEVED_TEMPORARY_FOLDER',
  message='The retrieved temporary folder could not be accessed.')
  spec.exit_code(302, 'ERROR_OUTPUT_STDOUT_MISSING',

aiida_quantumespresso/calculations/pw2gw.py

@@ -37,8 +37,6 @@ def define(cls, spec):
  spec.output('eps', valid_type=orm.ArrayData,
  help='The `eps` output node containing 5 arrays `energy`, `epsX`, `epsY`, `epsZ`, `epsTOT`')
 
- spec.exit_code(300, 'ERROR_NO_RETRIEVED_FOLDER',
- message='The retrieved folder data node could not be accessed.')
  spec.exit_code(302, 'ERROR_OUTPUT_STDOUT_MISSING',
  message='The retrieved folder did not contain the required stdout output file.')
  spec.exit_code(305, 'ERROR_OUTPUT_FILES',

aiida_quantumespresso/calculations/pw2wannier90.py

@@ -31,8 +31,6 @@ def define(cls, spec):
  help='The output folder of a pw.x calculation')
  spec.output('output_parameters', valid_type=Dict)
  spec.default_output_node = 'output_parameters'
- spec.exit_code(300, 'ERROR_NO_RETRIEVED_FOLDER',
- message='The retrieved folder data node could not be accessed.')
  spec.exit_code(310, 'ERROR_OUTPUT_STDOUT_READ',
  message='The stdout output file could not be read.')
  spec.exit_code(312, 'ERROR_OUTPUT_STDOUT_INCOMPLETE',

aiida_quantumespresso/calculations/q2r.py

@@ -31,8 +31,6 @@ def define(cls, spec):
  super().define(spec)
  spec.input('parent_folder', valid_type=(orm.RemoteData, orm.FolderData), required=True)
  spec.output('force_constants', valid_type=ForceConstantsData)
- spec.exit_code(300, 'ERROR_NO_RETRIEVED_FOLDER',
- message='The retrieved folder data node could not be accessed.')
  spec.exit_code(310, 'ERROR_OUTPUT_STDOUT_READ',
  message='The stdout output file could not be read.')
  spec.exit_code(312, 'ERROR_OUTPUT_STDOUT_INCOMPLETE',

aiida_quantumespresso/parsers/cp.py

@@ -1,11 +1,10 @@
 # -*- coding: utf-8 -*-
 from distutils.version import LooseVersion
-
 import numpy
-from aiida.common import NotExistent
-from aiida.orm import Dict, TrajectoryData
 
+from aiida.orm import Dict, TrajectoryData
 from qe_tools import CONSTANTS
+
 from aiida_quantumespresso.parsers.parse_raw.cp import parse_cp_raw_output, parse_cp_traj_stanzas
 from .base import Parser
 
@@ -18,13 +17,10 @@ def parse(self, **kwargs):
 
  Does all the logic here.
  """
- try:
- out_folder = self.retrieved
- except NotExistent:
- return self.exit(self.exit_codes.ERROR_NO_RETRIEVED_FOLDER)
+ retrieved = self.retrieved
 
  # check what is inside the folder
- list_of_files = out_folder._repository.list_object_names()
+ list_of_files = retrieved._repository.list_object_names()
 
  # options.metadata become attributes like this:
  stdout_filename = self.node.get_attribute('output_filename')
@@ -44,9 +40,9 @@ def parse(self, **kwargs):
  # TODO: Add an error for this counter
  return self.exit(self.exit_codes.ERROR_MISSING_XML_FILE)
 
- output_stdout = out_folder.get_object_content(stdout_filename)
- output_xml = out_folder.get_object_content(xml_files[0])
- output_xml_counter = out_folder.get_object_content(self.node.process_class._FILE_XML_PRINT_COUNTER_BASENAME)
+ output_stdout = retrieved.get_object_content(stdout_filename)
+ output_xml = retrieved.get_object_content(xml_files[0])
+ output_xml_counter = retrieved.get_object_content(self.node.process_class._FILE_XML_PRINT_COUNTER_BASENAME)
  out_dict, _raw_successful = parse_cp_raw_output(output_stdout, output_xml, output_xml_counter)
 
  # parse the trajectory. Units in Angstrom, picoseconds and eV.
@@ -75,7 +71,7 @@ def parse(self, **kwargs):
 
  for name, extension, scale, elements in trajectories:
  try:
- with out_folder.open(f'{self.node.process_class._PREFIX}.{extension}') as datafile:
+ with retrieved.open(f'{self.node.process_class._PREFIX}.{extension}') as datafile:
  data = [l.split() for l in datafile]
  # POSITIONS stored in angstrom
  traj_data = parse_cp_traj_stanzas(
@@ -96,7 +92,7 @@ def parse(self, **kwargs):
 
  # =============== EVP trajectory ============================
  try:
- with out_folder.open(f'{self._node.process_class._PREFIX}.evp') as handle:
+ with retrieved.open(f'{self._node.process_class._PREFIX}.evp') as handle:
  matrix = numpy.genfromtxt(handle)
  # there might be a different format if the matrix has one row only
  try:

aiida_quantumespresso/parsers/dos.py

@@ -2,7 +2,6 @@
 import numpy as np
 
 from aiida.orm import Dict, XyData
-from aiida.common import NotExistent
 
 from aiida_quantumespresso.parsers import QEOutputParsingError
 from aiida_quantumespresso.parsers.parse_raw.base import parse_output_base
@@ -17,15 +16,12 @@ def parse(self, **kwargs):
 
  Retrieves dos output, and some basic information from the out_file, such as warnings and wall_time
  """
- try:
- out_folder = self.retrieved
- except NotExistent:
- return self.exit(self.exit_codes.ERROR_NO_RETRIEVED_FOLDER)
+ retrieved = self.retrieved
 
  # Read standard out
  try:
  filename_stdout = self.node.get_option('output_filename') # or get_attribute(), but this is clearer
- with out_folder.open(filename_stdout, 'r') as fil:
+ with retrieved.open(filename_stdout, 'r') as fil:
  out_file = fil.readlines()
  except OSError:
  return self.exit(self.exit_codes.ERROR_OUTPUT_STDOUT_READ)
@@ -41,7 +37,7 @@ def parse(self, **kwargs):
 
  # check that the dos file is present, if it is, read it
  try:
- with out_folder.open(self.node.process_class._DOS_FILENAME, 'r') as fil:
+ with retrieved.open(self.node.process_class._DOS_FILENAME, 'r') as fil:
  dos_file = fil.readlines()
  except OSError:
  return self.exit(self.exit_codes.ERROR_READING_DOS_FILE)

aiida_quantumespresso/parsers/matdyn.py

@@ -1,6 +1,5 @@
 # -*- coding: utf-8 -*-
 from aiida import orm
-from aiida.common import exceptions
 from qe_tools import CONSTANTS
 
 from aiida_quantumespresso.calculations.matdyn import MatdynCalculation
@@ -12,21 +11,17 @@ class MatdynParser(Parser):
 
  def parse(self, **kwargs):
  """Parse the retrieved files from a `MatdynCalculation`."""
- try:
- output_folder = self.retrieved
- except exceptions.NotExistent:
- return self.exit(self.exit_codes.ERROR_NO_RETRIEVED_FOLDER)
-
+ retrieved = self.retrieved
  filename_stdout = self.node.get_option('output_filename')
  filename_frequencies = MatdynCalculation._PHONON_FREQUENCIES_NAME
 
- if filename_stdout not in output_folder.list_object_names():
+ if filename_stdout not in retrieved.list_object_names():
  return self.exit(self.exit_codes.ERROR_OUTPUT_STDOUT_READ)
 
- if 'JOB DONE' not in output_folder.get_object_content(filename_stdout):
+ if 'JOB DONE' not in retrieved.get_object_content(filename_stdout):
  return self.exit(self.exit_codes.ERROR_OUTPUT_STDOUT_INCOMPLETE)
 
- if filename_frequencies not in output_folder.list_object_names():
+ if filename_frequencies not in retrieved.list_object_names():
  return self.exit(self.exit_codes.ERROR_OUTPUT_STDOUT_READ)
 
  # Extract the kpoints from the input data and create the `KpointsData` for the `BandsData`
@@ -38,7 +33,7 @@ def parse(self, **kwargs):
  kpoints_for_bands = orm.KpointsData()
  kpoints_for_bands.set_kpoints(kpoints)
 
- parsed_data = parse_raw_matdyn_phonon_file(output_folder.get_object_content(filename_frequencies))
+ parsed_data = parse_raw_matdyn_phonon_file(retrieved.get_object_content(filename_frequencies))
 
  try:
  num_kpoints = parsed_data.pop('num_kpoints')

aiida_quantumespresso/parsers/neb.py

@@ -30,13 +30,8 @@ def parse(self, **kwargs):
 
  PREFIX = self.node.process_class._PREFIX
 
- # Check that the retrieved folder is there
- try:
- out_folder = self.retrieved
- except NotExistent:
- return self.exit(self.exit_codes.ERROR_NO_RETRIEVED_FOLDER)
-
- list_of_files = out_folder.list_object_names() # Note: this includes folders, but not the files they contain.
+ retrieved = self.retrieved
+ list_of_files = retrieved.list_object_names() # Note: this includes folders, but not the files they contain.
 
  # The stdout is required for parsing
  filename_stdout = self.node.get_attribute('output_filename')
@@ -62,7 +57,7 @@ def parse(self, **kwargs):
 
  # First parse the Neb output
  try:
- stdout = out_folder.get_object_content(filename_stdout)
+ stdout = retrieved.get_object_content(filename_stdout)
  neb_out_dict, iteration_data, raw_successful = parse_raw_output_neb(stdout, neb_input_dict)
  # TODO: why do we ignore raw_successful ?
  except (OSError, QEOutputParsingError):
@@ -99,7 +94,7 @@ def parse(self, **kwargs):
  if xml_filename in retrieved_files:
  xml_file_path = os.path.join(relative_output_folder, xml_filename)
  try:
- with out_folder.open(xml_file_path) as xml_file:
+ with retrieved.open(xml_file_path) as xml_file:
  parsed_data_xml, logs_xml = parse_pw_xml(xml_file, None)
  except IOError:
  return self.exit(self.exit_codes.ERROR_OUTPUT_XML_READ)
@@ -120,7 +115,7 @@ def parse(self, **kwargs):
  # look for pw output and parse it
  pw_out_file = os.path.join(f'{PREFIX}_{i + 1}', 'PW.out')
  try:
- with out_folder.open(pw_out_file, 'r') as f:
+ with retrieved.open(pw_out_file, 'r') as f:
  pw_out_text = f.read() # Note: read() and not readlines()
  except IOError:
  return self.exit(self.exit_codes.ERROR_OUTPUT_STDOUT_READ)
@@ -192,15 +187,15 @@ def parse(self, **kwargs):
  # Load the original and interpolated energy profile along the minimum-energy path (mep)
  try:
  filename = PREFIX + '.dat'
- with out_folder.open(filename, 'r') as handle:
+ with retrieved.open(filename, 'r') as handle:
  mep = numpy.loadtxt(handle)
  except Exception:
  self.logger.warning(f'could not open expected output file `{filename}`.')
  mep = numpy.array([[]])
 
  try:
  filename = PREFIX + '.int'
- with out_folder.open(filename, 'r') as handle:
+ with retrieved.open(filename, 'r') as handle:
  interp_mep = numpy.loadtxt(handle)
  except Exception:
  self.logger.warning(f'could not open expected output file `{filename}`.')

aiida_quantumespresso/parsers/ph.py

@@ -5,7 +5,6 @@
 import traceback
 
 from aiida import orm
-from aiida.common import exceptions
 
 from aiida_quantumespresso.calculations.ph import PhCalculation
 from aiida_quantumespresso.parsers.parse_raw.ph import parse_raw_ph_output as parse_stdout
@@ -17,25 +16,22 @@ class PhParser(Parser):
 
  def parse(self, **kwargs):
  """Parse the retrieved files from a `PhCalculation`."""
- try:
- self.retrieved
- except exceptions.NotExistent:
- return self.exit(self.exit_codes.ERROR_NO_RETRIEVED_FOLDER)
+ retrieved = self.retrieved
 
  # The stdout is required for parsing
  filename_stdout = self.node.get_attribute('output_filename')
  filename_tensor = PhCalculation._OUTPUT_XML_TENSOR_FILE_NAME
 
- if filename_stdout not in self.retrieved.list_object_names():
+ if filename_stdout not in retrieved.list_object_names():
  return self.exit(self.exit_codes.ERROR_OUTPUT_STDOUT_MISSING)
 
  try:
- stdout = self.retrieved.get_object_content(filename_stdout)
+ stdout = retrieved.get_object_content(filename_stdout)
  except (IOError, OSError):
  return self.exit(self.exit_codes.ERROR_OUTPUT_STDOUT_READ)
 
  try:
- tensor_file = self.retrieved.get_object_content(filename_tensor)
+ tensor_file = retrieved.get_object_content(filename_tensor)
  except (IOError, OSError):
  tensor_file = None
 
@@ -45,11 +41,11 @@ def parse(self, **kwargs):
  dynmat_prefix = os.path.split(PhCalculation._OUTPUT_DYNAMICAL_MATRIX_PREFIX)[1]
 
  natural_sort = lambda string: [int(c) if c.isdigit() else c.lower() for c in re.split(r'(\d+)', string)]
- for filename in sorted(self.retrieved.list_object_names(dynmat_folder), key=natural_sort):
+ for filename in sorted(retrieved.list_object_names(dynmat_folder), key=natural_sort):
  if not filename.startswith(dynmat_prefix) or filename.endswith('.freq'):
  continue
 
- dynmat_files.append(self.retrieved.get_object_content(os.path.join(dynmat_folder, filename)))
+ dynmat_files.append(retrieved.get_object_content(os.path.join(dynmat_folder, filename)))
 
  try:
  parsed_data, logs = parse_stdout(stdout, tensor_file, dynmat_files)

aiida_quantumespresso/parsers/pp.py

@@ -46,11 +46,7 @@ def parse(self, **kwargs):
  """
  Parse raw files retrieved from remote dir
  """
- try:
- self.retrieved
- except exceptions.NotExistent:
- return self.exit_codes.ERROR_NO_RETRIEVED_FOLDER
-
+ retrieved = self.retrieved
  retrieve_temporary_list = self.node.get_attribute('retrieve_temporary_list', None)
  filename_stdout = self.node.get_option('output_filename')
 
@@ -62,11 +58,11 @@ def parse(self, **kwargs):
  return self.exit(self.exit_codes.ERROR_NO_RETRIEVED_TEMPORARY_FOLDER)
 
  # The stdout is required for parsing
- if filename_stdout not in self.retrieved.list_object_names():
+ if filename_stdout not in retrieved.list_object_names():
  return self.exit_codes.ERROR_OUTPUT_STDOUT_MISSING
 
  try:
- stdout_raw = self.retrieved.get_object_content(filename_stdout)
+ stdout_raw = retrieved.get_object_content(filename_stdout)
  except (IOError, OSError):
  return self.exit_codes.ERROR_OUTPUT_STDOUT_READ
 
@@ -89,8 +85,8 @@ def parse(self, **kwargs):
  filenames = os.listdir(retrieved_temporary_folder)
  file_opener = lambda filename: open(os.path.join(retrieved_temporary_folder, filename))
  else:
- filenames = self.retrieved.list_object_names()
- file_opener = self.retrieved.open
+ filenames = retrieved.list_object_names()
+ file_opener = retrieved.open
 
  for filename in filenames:
  if filename.endswith(filename_suffix):