Update with mpes-parser content

mpesparser/__init__.py

+# Copyright 2016-2018 Markus Scheidgen
+#   Licensed under the Apache License, Version 2.0 (the "License");
+#   you may not use this file except in compliance with the License.
+#   You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#   Unless required by applicable law or agreed to in writing, software
+#   distributed under the License is distributed on an "AS IS" BASIS,
+#   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#   See the License for the specific language governing permissions and
+#   limitations under the License.
+
+import sys
+import os.path
+import json
+import ase
+import re
+import numpy as np
+from datetime import datetime
+
+from nomadcore.simple_parser import SimpleMatcher
+from nomadcore.baseclasses import ParserInterface, AbstractBaseParser
+
+from nomad.parsing import LocalBackend
+
+
+class MPESParserInterface(ParserInterface):
+    def get_metainfo_filename(self):
+        """
+        The parser specific metainfo. To include other metadata definitions, use
+        the 'dependencies' key to refer to other local nomadmetainfo.json files or
+        to nomadmetainfo.json files that are part of the general nomad-meta-info
+        submodule (i.e. ``dependencies/nomad-meta-info``).
+         """
+        return os.path.join(os.path.dirname(__file__), 'mpes.nomadmetainfo.json')
+
+    def get_parser_info(self):
+        """ Basic info about parser used in archive data and logs. """
+        return {
+            'name': 'mpes-parser',
+            'version': '1.0.0'
+        }
+
+    def setup_version(self):
+        """ Can be used to call :func:`setup_main_parser` differently for different code versions. """
+        self.setup_main_parser(None)
+
+    def setup_main_parser(self, _):
+        """ Setup the actual parser (behind this interface) """
+        self.main_parser = MPESParser(self.parser_context)
+
+
+class MPESParser(AbstractBaseParser):
+
+    def parse(self, filepath):
+        backend = self.parser_context.super_backend
+
+        with open(filepath, 'rt') as f:
+            data = json.load(f)
+            # print(data)
+
+        # # You need to open sections before you can add values or sub sections to it.
+        # # The returned 'gid' can be used to reference a specific section if multiple
+        # # sections of the same type are opened.
+        root_gid = backend.openSection('section_experiment')
+        # # Values do not necessarely have to be read from the parsed file.
+        # # The backend will check the type of the given value agains the metadata definition.
+        # backend.addValue('experiment_time', int(datetime.strptime(data.get('date'), '%d.%M.%Y').timestamp()))
+        #
+        # # Read data .
+        # data_gid = backend.openSection('section_data')
+        # backend.addValue('data_repository_name', 'zenodo.org')
+        # backend.addValue('data_repository_url', 'https://zenodo.org/path/to/mydata')
+        # backend.addValue('data_preview_url', 'https://www.physicsforums.com/insights/wp-content/uploads/2015/09/fem.jpg')
+        # backend.closeSection('section_data', data_gid)
+
+        # Read general experimental parameters
+        # general_gid = backend.openSection('section_experiment_general_parameters')
+        backend.addValue('general_experiment_method', data.get('experiment_method'))
+        backend.addValue('general_experiment_method_abbreviation', data.get('experiment_method_abbrv'))
+        backend.addArrayValues('general_experiment_location', np.array(re.findall(r"[\w']+", data.get('experiment_location'))))
+        backend.addValue('general_experiment_date', data.get('experiment_date'))
+        backend.addValue('general_experiment_summary', data.get('experiment_summary'))
+        backend.addValue('general_experiment_facility_institution', data.get('facility_institution'))
+        backend.addValue('general_experiment_facility_name', data.get('facility_name'))
+        backend.addValue('general_beamline', data.get('beamline'))
+        backend.addValue('general_source_pump', data.get('source_pump'))
+        backend.addValue('general_source_probe', data.get('source_probe'))
+        backend.addValue('general_equipment_description', data.get('equipment_description'))
+        backend.addValue('general_sample_description', data.get('sample_description'))
+        backend.addArrayValues('general_measurement_axis', np.array(re.findall(r"[\w']+", data.get('measurement_axis'))))
+        backend.addArrayValues('general_physical_axis', np.array(re.findall(r"[\w']+", data.get('physical_axis'))))
+
+        # Read parameters related to experimental source
+        # source_gid = backend.openSection('section_experiment_source_parameters')
+        backend.addValue('source_pump_repetition_rate', data.get('pump_rep_rate'))
+        backend.addValue('source_pump_pulse_duration', data.get('pump_pulse_duration'))
+        backend.addValue('source_pump_wavelength', data.get('pump_wavelength'))
+        backend.addArrayValues('source_pump_spectrum', np.array(data.get('pump_spectrum')))
+        backend.addValue('source_pump_photon_energy', data.get('pump_photon_energy'))
+        backend.addArrayValues('source_pump_size', np.array(data.get('pump_size')))
+        backend.addArrayValues('source_pump_fluence', np.array(data.get('pump_fluence')))
+        backend.addValue('source_pump_polarization', data.get('pump_polarization'))
+        backend.addValue('source_pump_bunch', data.get('pump_bunch'))
+        backend.addValue('source_probe_repetition_rate', data.get('probe_rep_rate'))
+        backend.addValue('source_probe_pulse_duration', data.get('probe_pulse_duration'))
+        backend.addValue('source_probe_wavelength', data.get('probe_wavelength'))
+        backend.addArrayValues('source_probe_spectrum', np.array(data.get('probe_spectrum')))
+        backend.addValue('source_probe_photon_energy', data.get('probe_photon_energy'))
+        backend.addArrayValues('source_probe_size', np.array(data.get('probe_size')))
+        backend.addArrayValues('source_probe_fluence', np.array(data.get('probe_fluence')))
+        backend.addValue('source_probe_polarization', data.get('probe_polarization'))
+        backend.addValue('source_probe_bunch', data.get('probe_bunch'))
+        backend.addValue('source_temporal_resolution', data.get('temporal_resolution'))
+
+        # Read parameters related to detector
+        # detector_gid = backend.openSection('section_experiment_detector_parameters')
+        backend.addValue('detector_extractor_voltage', data.get('extractor_voltage'))
+        backend.addValue('detector_work_distance', data.get('work_distance'))
+        backend.addArrayValues('detector_lens_names', np.array(re.findall(r"[\w']+", data.get('lens_names'))))
+        backend.addArrayValues('detector_lens_voltages', np.array(data.get('lens_voltages')))
+        backend.addValue('detector_tof_distance', data.get('tof_distance'))
+        backend.addArrayValues('detector_tof_voltages', np.array(data.get('tof_voltages')))
+        backend.addValue('detector_sample_bias', data.get('sample_bias'))
+        backend.addValue('detector_magnification', data.get('magnification'))
+        backend.addArrayValues('detector_voltages', np.array(data.get('detector_voltages')))
+        backend.addValue('detector_type', data.get('detector_type'))
+        backend.addArrayValues('detector_sensor_size', np.array(data.get('sensor_size')))
+        backend.addValue('detector_sensor_count', data.get('sensor_count'))
+        backend.addArrayValues('detector_sensor_pixel_size', np.array(data.get('sensor_pixel_size')))
+        backend.addArrayValues('detector_calibration_x_to_momentum', np.array(data.get('calibration_x_to_momentum')))
+        backend.addArrayValues('detector_calibration_y_to_momentum', np.array(data.get('calibration_y_to_momentum')))
+        backend.addArrayValues('detector_calibration_tof_to_energy', np.array(data.get('calibration_tof_to_energy')))
+        backend.addArrayValues('detector_calibration_stage_to_delay', np.array(data.get('calibration_stage_to_delay')))
+        backend.addArrayValues('detector_calibration_other_converts', np.array(data.get('calibration_other_converts')))
+        backend.addArrayValues('detector_momentum_resolution', np.array(data.get('momentum_resolution')))
+        backend.addArrayValues('detector_spatial_resolution', np.array(data.get('spatial_resolution')))
+        backend.addArrayValues('detector_energy_resolution', np.array(data.get('energy_resolution')))
+
+        # Read parameters related to sample
+        # sample_gid = backend.openSection('section_experiment_sample_parameters')
+        backend.addValue('sample_id', data.get('sample_id'))
+        backend.addValue('sample_state_of_matter', data.get('sample_state'))
+        backend.addValue('sample_purity', data.get('sample_purity'))
+        backend.addValue('sample_surface_termination', data.get('sample_surface_termination'))
+        backend.addValue('sample_layers', data.get('sample_layers'))
+        backend.addValue('sample_stacking_order', data.get('sample_stacking_order'))
+        backend.addValue('sample_space_group', data.get('sample_space_group'))
+        backend.addValue('sample_chemical_name', data.get('chemical_name'))
+        backend.addValue('sample_chemical_formula', data.get('chemical_formula'))
+        # backend.addArrayValues('sample_chemical_elements', np.array(re.findall(r"[\w']+", data.get('chemical_elements'))))
+        atoms = set(ase.Atoms(data.get('chemical_formula')).get_chemical_symbols())
+        backend.addArrayValues('sample_atom_labels', np.array(list(atoms)))
+        backend.addValue('sample_chemical_id_cas', data.get('chemical_id_cas'))
+        backend.addValue('sample_temperature', data.get('sample_temperature'))
+        backend.addValue('sample_pressure', data.get('sample_pressure'))
+        backend.addValue('sample_growth_method', data.get('growth_method'))
+        backend.addValue('sample_preparation_method', data.get('preparation_method'))
+        backend.addValue('sample_vendor', data.get('sample_vendor'))
+        backend.addValue('sample_substrate_material', data.get('substrate_material'))
+        backend.addValue('sample_substrate_state_of_matter', data.get('substrate_state'))
+        backend.addValue('sample_substrate_vendor', data.get('substrate_vendor'))
+
+        # To add arrays (vectors, matrices, etc.) use addArrayValues and provide a
+        # numpy array. The shape of the numpy array must match the shape defined in
+        # the respective metadata definition.
+
+
+        # Close sections in the reverse order
+        # backend.closeSection('section_data', data_gid)
+        backend.closeSection('section_experiment', root_gid)
+        # backend.closeSection('section_experiment_general_parameters', general_gid)
+        # backend.closeSection('section_experiment_source_parameters', source_gid)
+        # backend.closeSection('section_experiment_detector_parameters', detector_gid)
+        # backend.closeSection('section_experiment_sample_parameters', sample_gid)

skeletonparser/__main__.py → mpesparser/__main__.py

@@ -14,11 +14,11 @@
 import sys
 
 from nomad.parsing import LocalBackend
-from skeletonparser import SkeletonParserInterface
+from mpesparser import MPESParserInterface
 
 if __name__ == "__main__":
     # instantiate the parser via its interface with a LocalBackend
-    parser = SkeletonParserInterface(backend=LocalBackend)
+    parser = MPESParserInterface(backend=LocalBackend)
     # call the actual parsing with the given mainfile
     parser.parse(sys.argv[1])
     # print the results stored in the LocalBackend

setup.py

@@ -16,14 +16,14 @@ from setuptools import setup, find_packages
 
 def main():
     setup(
-        name='skeletonparser',  # replace with new name for parser's python package
+        name='mpesparser',
         version='0.1',
-        description='A skeleton NOMAD parser implementation.',  # change accordingly
-        author='',  # add your names
+        description='NOMAD parser implementation for multidimensional photoemission spectroscopy data.',
+        author='R. Patrick Xian',
         license='APACHE 2.0',
         packages=find_packages(),
         package_data={
-            'skeletonparser': ['*.json']
+            'mpesparser': ['*.json']
         },
         install_requires=[
             'nomadcore'

skeletonparser/__init__.py

-# Copyright 2016-2018 Markus Scheidgen
-#   Licensed under the Apache License, Version 2.0 (the "License");
-#   you may not use this file except in compliance with the License.
-#   You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-#   Unless required by applicable law or agreed to in writing, software
-#   distributed under the License is distributed on an "AS IS" BASIS,
-#   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-#   See the License for the specific language governing permissions and
-#   limitations under the License.
-
-import sys
-import os.path
-import json
-import ase
-import numpy as np
-from datetime import datetime
-
-from nomadcore.simple_parser import SimpleMatcher
-from nomadcore.baseclasses import ParserInterface, AbstractBaseParser
-
-from nomad.parsing import LocalBackend
-
-
-class SkeletonParserInterface(ParserInterface):
-
-    def get_metainfo_filename(self):
-        """
-        The parser specific metainfo. To include other metadata definitions, use
-        the 'dependencies' key to refer to other local nomadmetainfo.json files or
-        to nomadmetainfo.json files that are part of the general nomad-meta-info
-        submodule (i.e. ``dependencies/nomad-meta-info``).
-         """
-        return os.path.join(os.path.dirname(__file__), 'skeleton.nomadmetainfo.json')
-
-    def get_parser_info(self):
-        """ Basic info about parser used in archive data and logs. """
-        return {
-            'name': 'you parser name',
-            'version': '1.0.0'
-        }
-
-    def setup_version(self):
-        """ Can be used to call :func:`setup_main_parser` differently for different code versions. """
-        self.setup_main_parser(None)
-
-    def setup_main_parser(self, _):
-        """ Setup the actual parser (behind this interface) """
-        self.main_parser = SkeletonParser(self.parser_context)
-
-
-class SkeletonParser(AbstractBaseParser):
-    def parse(self, filepath):
-        backend = self.parser_context.super_backend
-
-        with open(filepath, 'rt') as f:
-            data = json.load(f)
-
-        # You need to open sections before you can add values or sub sections to it.
-        # The returned 'gid' can be used to reference a specific section if multiple
-        # sections of the same type are opened.
-        root_gid = backend.openSection('section_experiment')
-        # Values are added to the open section of the given metadata definitions. In
-        # the following case 'experiment_location' is a quantity of 'section_experiment'.
-        # When multiple sections of the same type (e.g. 'section_experiment') are open,
-        # you can use the 'gid' as an additional argument.
-        backend.addValue('experiment_location', data.get('location'))
-        # Values do not necessarely have to be read from the parsed file.
-        backend.addValue('experiment_method_name', data.get('method', 'Bare eyes'))
-        # The backend will check the type of the given value agains the metadata definition.
-        backend.addValue('experiment_time', int(datetime.strptime(data.get('date'), '%d.%M.%Y').timestamp()))
-
-        # Subsections work like before. The parent section must still be open.
-        data_gid = backend.openSection('section_data')
-        backend.addValue('data_repository_name', 'zenedo.org')
-        backend.addValue('data_repository_url', 'https://zenedo.org/path/to/mydata')
-        backend.addValue('data_preview_url', 'https://www.physicsforums.com/insights/wp-content/uploads/2015/09/fem.jpg')
-        backend.closeSection('section_data', data_gid)
-
-        # Subsections work like before. The parent section must still be open.
-        sample_gid = backend.openSection('section_sample')
-        backend.addValue('sample_chemical_name', data.get('sample_chemical'))
-        backend.addValue('sample_chemical_formula', data.get('sample_formula'))
-        backend.addValue('sample_temperature', data.get('sample_temp'))
-
-        atoms = set(ase.Atoms(data.get('sample_formula')).get_chemical_symbols())
-        # To add arrays (vectors, matrices, etc.) use addArrayValues and provide a
-        # numpy array. The shape of the numpy array must match the shape defined in
-        # the respective metadata definition.
-        backend.addArrayValues('sample_atom_labels', np.array(list(atoms)))
-
-        # Close sections in the reverse order.
-        backend.closeSection('section_sample', sample_gid)
-        backend.closeSection('section_experiment', root_gid)

skeletonparser/skeleton.nomadmetainfo.json

-{
-  "type": "nomad_meta_info_1_0",
-  "description": "Parser specific metadata definitions.",
-  "dependencies":[
-    {
-      "metainfoPath":"general.nomadmetainfo.json"
-    },
-    {
-      "metainfoPath":"general.experimental.nomadmetainfo.json"
-    }
-  ],
-  "metaInfos": [
-    {
-      "description": "Contains information relating to an archive.",
-      "name": "experiment_location",
-      "dtypeStr": "C",
-      "superNames": ["section_experiment"]
-    }
-  ]
-}

tests/example.metadata.json

-{
-    "type":"skeleton experimental metadata format 1.0",
-    "date":"24.12.2018",
-    "location":"Northpole",
-    "sample_formula":"H2O",
-    "sample_chemical":"Ice",
-    "sample_state":"Frozen",
-    "result":"https://bitcoinist.com/wp-content/uploads/2018/08/shutterstock_764225425.jpg",
-    "sample_temp":384
-}
\ No newline at end of file

tests/mpes_data.json

+{"GeneralParameters":
+  {"experiment_location": "Hamburg, Germany",
+    "experiment_date": "04.2018 - 05.2018",
+    "experiment_summary": "Characterization of excited-state circular dichroism of WSe2",
+    "institution": "DESY",
+    "facility": "FLASH",
+    "beamline": "PG-2",
+    "source_pump": "Free electron laser",
+    "source_probe": "Femtosecond laser",
+    "equipment": "HEXTOF detector",
+    "sample": "Bulk tungsten diselenide",
+    "measurement_axis": ["X", "Y", "t", "ADC"],
+    "physical_axis": ["kx", "ky", "E", "tpp"]},
+"SourceParameters":
+  {"pump_rep_rate": 1000,
+    "pump_pulse_duration": 100,
+    "pump_wavelength": 800,
+    "pump_spectrum": [],
+    "pump_photon_energy": 1.55,
+    "pump_size": "",
+    "pump_fluence": 1.5,
+    "pump_polarization": "linear",
+    "pump_bunch": 400,
+    "probe_rep_rate": 1000,
+    "probe_pulse_duration": 100,
+    "probe_wavelength": 800,
+    "probe_spectrum": [],
+    "probe_photon_energy": 109,
+    "probe_size": "",
+    "probe_fluence": "",
+    "probe_polarization": "circular",
+    "probe_bunch": 400,
+    "temporal_resolution": 100},
+"DetectorParameters":
+  {"extractor_voltage": 6000,
+    "work_distance": 4,
+    "lens_names": ["A", "B", "C", "D", "E", "F", "G", "H"],
+    "lens_voltages": [],
+    "tof_distance": 0.9,
+    "tof_voltages": 30,
+    "sample_bias": 15,
+    "magnification": [],
+    "detector_voltage": [],
+    "detector_type": "MCP",
+    "sensor_size": [],
+    "sensor_count": 4,
+    "sensor_pixel_size": [],
+    "x_to_momentum": [],
+    "y_to_momentum": [],
+    "tof_to_energy": [],
+    "stage_to_delay": [],
+    "other_converts": [],
+    "momentum_resolution": 0.01,
+    "spatial_resolution": "",
+    "energy_resolution": ""},
+"SampleParameters":
+  {"sample_id": "000",
+    "sample_state": "solid",
+    "sample_purity": 0.99,
+    "sample_surface_term": "",
+    "sample_layer": "bulk",
+    "sample_stacking": "2H",
+    "sample_space_group": 194,
+    "chem_formula": "WSe2",
+    "chem_elements": ["W", "Se"],
+    "chem_name": "tungsten diselenide",
+    "chem_id_cas": "12067-46-8",
+    "sample_temp": 300,
+    "sample_pressure": 1e-11,
+    "growth_method": "chemical vaport transport",
+    "preparation_method": "in-vacuum cleaving",
+    "sample_vendor": "HQ Graphene",
+    "substrate_material": "copper",
+    "substrate_state": "solid",
+    "substrate_vendor": "custom"
+  }
+}

tests/mpes_data_redacted.json

+{
+  "experiment_method": "multidimensional photoemission spectroscopy",
+  "experiment_method_abbrv": "MPES",
+  "experiment_location": "Hamburg, Germany",
+  "experiment_date": "04.2018 05.2018",
+  "experiment_summary": "Characterization of excited-state circular dichroism of WSe2",
+  "facility_institution": "DESY",
+  "facility_name": "FLASH",
+  "beamline": "PG-2",
+  "source_pump": "Free electron laser",
+  "source_probe": "Femtosecond laser",
+  "equipment_description": "HEXTOF detector",
+  "sample_description": "Bulk tungsten diselenide",
+  "measurement_axis": "X, Y, TOF, ADC",
+  "physical_axis": "kx, ky, E, tpp",
+  "pump_rep_rate": 1000,
+  "pump_pulse_duration": 100,
+  "pump_wavelength": 800,
+  "pump_spectrum": [],
+  "pump_photon_energy": 1.55,
+  "pump_size": [],
+  "pump_fluence": [],
+  "pump_polarization": "linear",
+  "pump_bunch": 400,
+  "probe_rep_rate": 1000,
+  "probe_pulse_duration": 100,
+  "probe_wavelength": 800,
+  "probe_spectrum": [],
+  "probe_photon_energy": 36.4970,
+  "probe_size": [],
+  "probe_fluence": [],
+  "probe_polarization": "circular",
+  "probe_bunch": 400,
+  "temporal_resolution": 100,
+  "extractor_voltage": 6030,
+  "work_distance": 4,
+  "lens_names": "A, B, C, D, E, F, G, H, I",
+  "lens_voltages": [],
+  "tof_distance": 0.9,
+  "tof_voltages": [20],
+  "sample_bias": 29,
+  "magnification": [-1.5],
+  "detector_voltages": [],
+  "detector_type": "MCP",
+  "sensor_size": [],
+  "sensor_count": 4,
+  "sensor_pixel_size": [],
+  "calibration_x_to_momentum": [],
+  "calibration_y_to_momentum": [],
+  "calibration_tof_to_energy": [],
+  "calibration_stage_to_delay": [],
+  "calibration_other_converts": [],
+  "momentum_resolution": [0.01],
+  "spatial_resolution": [],
+  "energy_resolution": [],
+  "sample_id": "000",
+  "sample_state": "solid",
+  "sample_purity": 0.99,
+  "sample_surface_termination": "0001",
+  "sample_layers": "bulk",
+  "sample_stacking_order": "2H",
+  "sample_space_group": 194,
+  "chemical_name": "tungsten diselenide",
+  "chemical_formula": "WSe2",
+  "chemical_id_cas": "12067-46-8",
+  "sample_temperature": 300,
+  "sample_pressure": 3.85e-10,
+  "growth_method": "chemical vaport transport",
+  "preparation_method": "in-vacuum cleaving",
+  "sample_vendor": "HQ Graphene",
+  "substrate_material": "copper",
+  "substrate_state": "solid",
+  "substrate_vendor": "custom"
+}