Merge pull request #4 from FAIRmat-NFDI/Update_reader_for_new_NXopt

dataconverter works as intented and for the new NXopt version. Some necessary changes for compatibility with other applications were as well done.
FAIRmat-NFDI · May 16, 2024 · a3f1cc5 · a3f1cc5
2 parents fd2acc9 + a100cff
commit a3f1cc5
Show file tree

Hide file tree

Showing 4 changed files with 113 additions and 91 deletions.
diff --git a/examples/eln_data.yaml b/examples/eln_data.yaml
@@ -7,44 +7,46 @@ Data:
   spectrum_type: wavelength
   spectrum_unit: angstrom
 Instrument:
-  Beam_path:
-    Detector:
-      count_time:
-        unit: s
-        value: 1.0
-      detector_type: CCD spectrometer
-    focussing_probes:
-      angular_spread:
-        unit: rad
-        value: 0.2
-      data_correction: false
-    light_source:
-      source_type: arc lamp
-    rotating_element:
-      revolutions: 50.0
+  Detector:
+    count_time:
+      unit: s
+      value: 1.0
+    detector_type: CCD spectrometer
+  focussing_probes:
+    angular_spread:
+      unit: rad
+      value: 0.2
+    data_correction: false
+  light_source:
+    source_type: arc lamp
+  rotating_element:
+    revolutions: 50.0
   Sample_stage:
     environment_conditions:
-      medium: air
     stage_type: manual stage
-  angle_of_incidence/@unit: degrees
-  calibration_status: no calibration
-  company: J. A. Woollam Co.
+#  angle_of_incidence/@unit: degrees
+  device_information:
+    vendor: J. A. Woollam Co.
+    model: RC2 (Vers. 0.0.1)
   ellipsometer_type: dual compensator
-  model: RC2
-  model/@version: 0.0.1
   rotating_element_type: compensator (source side)
-  software: CompleteEASE
-  software/@url: https://www.jawoollam.com/ellipsometry-software/completeease
-  software/version: '6.37'
+  software_RC2: CompleteEASE
+  software_RC2/@url: https://www.jawoollam.com/ellipsometry-software/completeease
+  software_RC2/@version: '6.37'
+  instrument_calibration_RC2:
+    calibration_status: no calibration
 Sample:
   atom_types: Si, O
   backside_roughness: false
   chemical_formula: SiO2
   layer_structure: 2nm SiO2 on Si
-  sample_history: Commercially purchased sample
   sample_name: 2nm SiO2 on Si
-  sample_type: multi layer
+  physical_form: multi layer
   substrate: Si
+  environment:
+    sample_medium: air
+  history:
+    notes: Commercially purchased sample
 User:
   address: Zum Großen Windkanal 2, 12489 Berlin, Germany
   affiliation: Humboldt-Universität zu Berlin
@@ -60,10 +62,14 @@ colnames:
 - err.Delta
 derived_parameter_type: depolarization
 experiment_description: RC2 scan on 2nm SiO2 on Si in air
-experiment_identifier: exp-ID
-experiment_type: NIR-Vis-UV spectroscopic ellipsometry
+experiment_identifier:
+  identifier: exp-ID
+  is_persistent: "false"
+experiment_type: ellipsometry
+ellipsometry_experiment_type: NIR-Vis-UV spectroscopic ellipsometry
 filename: test-data.dat
 plot_name: Psi and Delta
+title: RC2 Ellipsometry of 2nm SiO2 on Si
 sep: \t
 skip: 3
-start_time: '2022-01-27T03:35:00+00:00'
+start_time: '2022-01-27T03:35:00+00:00'
diff --git a/pynxtools_ellips/reader.py b/pynxtools_ellips/reader.py
@@ -37,7 +37,6 @@
 
 CONVERT_DICT = {
     "unit": "@units",
-    "Beam_path": "BEAM_PATH[beam_path]",
     "Detector": "DETECTOR[detector]",
     "Data": "data_collection",
     "Derived_parameters": "derived_parameters",
@@ -52,8 +51,18 @@
     "data_error": "data_collection/data_error",
     "depolarization": "derived_parameters/depolarization",
     "measured_data": "data_collection/measured_data",
-    "software": "software/program",
-    "data_software": "data_software/program",
+    "data_software": "software_TYPE[data_software]/program",
+    "experiment_identifier/identifier": "IDENTIFIER[experiment_identifier]/IDENTIFIER[identifier]",
+    "experiment_identifier/is_persistent": "IDENTIFIER[experiment_identifier]/IS_PERSISTENT[is_persistent]",
+    "software_RC2": "software_TYPE[software_RC2]/program",
+    "software_RC2/@url": "software_TYPE[software_RC2]/program/@url",
+    "software_RC2/@version": "software_TYPE[software_RC2]/program/@version",
+    "instrument_calibration_RC2": "instrument_calibration_DEVICE[instrument_calibration_RC2]/calibration_status",
+    "instrument_calibration_RC2/calibration_status": "instrument_calibration_DEVICE[instrument_calibration_RC2]/calibration_status",
+    "environment": "ENVIRONMENT[environment_sample]",
+    "history/notes": "HISTORY[history]/notes",
+    "light_source": "source_TYPE[source_light]",
+    "source_type": "type",
 }
 
 CONFIG_KEYS = [
@@ -70,8 +79,7 @@
 ]
 
 REPLACE_NESTED = {
-    "Instrument/Beam_path": "INSTRUMENT[instrument]/BEAM_PATH[beam_path]",
-    "Env_Conditions": "INSTRUMENT[instrument]/sample_stage/environment_conditions",
+    "Inc_Det_Angles": "INSTRUMENT[instrument]",
     "Instrument": "INSTRUMENT[instrument]",
 }
 
@@ -347,15 +355,11 @@ def populate_header_dict_with_datasets(file_paths, is_mock=False):
         )
 
         def write_scan_axis(name: str, values: list, units: str):
-            base_path = f"Env_Conditions/PARAMETER[{name}]"
-            header[f"{base_path}/values"] = values
-            header[f"{base_path}/values/@units"] = units
-            header[f"{base_path}/number_of_parameters"] = len(values)
-            header[f"{base_path}/number_of_parameters/@units"] = ""
-            header[f"{base_path}/parameter_type"] = name
-
-        header["Instrument/angle_of_incidence"] = unique_angles
-        for axis in ["detection_angle", "incident_angle"]:
+            base_path = f"Inc_Det_Angles/PARAMETER[{name}]"
+            header[f"{base_path}"] = values
+            header[f"{base_path}/@units"] = units
+
+        for axis in ["angle_of_detection", "angle_of_incidence"]:
             write_scan_axis(axis, unique_angles, "degree")
 
         # Create mocked ellipsometry data template:
@@ -409,7 +413,7 @@ def read(
         # because test-data.data has improper units like Angstroms or degrees
         # the fix above prevents that these incorrect units are get just blindly carried
         # over into the nxs file and thus causing nomas to fail
-        template[f"/ENTRY[entry]/plot/AXISNAME[{spectrum_type}]"] = {
+        template[f"/ENTRY[entry]/data_collection/AXISNAME[{spectrum_type}]"] = {
             "link": f"/entry/data_collection/{spectrum_type}_spectrum"
         }
         template[
@@ -421,18 +425,18 @@ def read(
         plot_name = header["plot_name"]
         for dindx in range(0, len(labels.keys())):
             for index, key in enumerate(data_list[dindx]):
-                template[f"/ENTRY[entry]/plot/DATA[{key}]"] = {
+                template[f"/ENTRY[entry]/data_collection/DATA[{key}]"] = {
                     "link": "/entry/data_collection/measured_data",
                     "shape": np.index_exp[index, dindx, :],
                 }
                 # MK:: Carola, Ron, Flo, Tamas, Sandor refactor the following line
                 # using a proper unit parsing logic
-                template[f"/ENTRY[entry]/plot/DATA[{key}]/@units"] = "degree"
+                template[f"/ENTRY[entry]/data_collection/DATA[{key}]/@units"] = "degree"
                 if dindx == 0 and index == 0:
-                    template[f"/ENTRY[entry]/plot/DATA[{key}]/@long_name"] = (
-                        f"{plot_name} (degree)"
-                    )
-                template[f"/ENTRY[entry]/plot/DATA[{key}_errors]"] = {
+                    template[
+                        f"/ENTRY[entry]/data_collection/DATA[{key}]/@long_name"
+                    ] = f"{plot_name} (degree)"
+                template[f"/ENTRY[entry]/data_collection/DATA[{key}_errors]"] = {
                     "link": "/entry/data_collection/data_error",
                     "shape": np.index_exp[index, dindx, :],
                 }
@@ -441,30 +445,36 @@ def read(
 
         # Define default plot showing Psi and Delta at all angles:
         template["/@default"] = "entry"
-        template["/ENTRY[entry]/@default"] = "plot"
-        template["/ENTRY[entry]/plot/@signal"] = f"{data_list[0][0]}"
-        template["/ENTRY[entry]/plot/@axes"] = spectrum_type
-        template["/ENTRY[entry]/plot/title"] = plot_name
+        template["/ENTRY[entry]/@default"] = "data_collection"
+        template["/ENTRY[entry]/data_collection/@signal"] = f"{data_list[0][0]}"
+        template["/ENTRY[entry]/data_collection/@axes"] = spectrum_type
+        template["/ENTRY[entry]/data_collection/title"] = plot_name
 
         # if len(data_list[0]) > 1:
-        template["/ENTRY[entry]/plot/@auxiliary_signals"] = data_list[0][1:]
+        template["/ENTRY[entry]/data_collection/@auxiliary_signals"] = data_list[0][1:]
         for index in range(1, len(data_list)):
-            template["/ENTRY[entry]/plot/@auxiliary_signals"] += data_list[index]
+            template["/ENTRY[entry]/data_collection/@auxiliary_signals"] += data_list[
+                index
+            ]
 
         template["/ENTRY[entry]/definition"] = "NXellipsometry"
         template["/ENTRY[entry]/definition/@url"] = (
             "https://github.com/FAIRmat-NFDI/nexus_definitions/"
             f"blob/{get_nexus_version_hash()}/contributed_definitions/NXellipsometry.nxdl.xml"
         )
         template["/ENTRY[entry]/definition/@version"] = get_nexus_version()
-        template["/ENTRY[entry]/program_name"] = "pynxtools"
+        template[
+            "/ENTRY[entry]/INSTRUMENT[instrument]/software_TYPE[software_NeXuS]/program"
+        ] = "pynxtools"
         try:
-            template["/ENTRY[entry]/program_name/@version"] = version("pynxtools")
+            template[
+                "/ENTRY[entry]/INSTRUMENT[instrument]/software_TYPE[software_NeXuS]/program/@version"
+            ] = version("pynxtools")
         except PackageNotFoundError:
             pass
-        template["/ENTRY[entry]/program_name/@url"] = (
-            "https://github.com/FAIRmat-NFDI/pynxtools"
-        )
+        template[
+            "/ENTRY[entry]/INSTRUMENT[instrument]/software_TYPE[software_NeXuS]/program/@url"
+        ] = "https://github.com/FAIRmat-NFDI/pynxtools"
 
         return template
 

diff --git a/pyproject.toml b/pyproject.toml
@@ -26,7 +26,7 @@ dependencies = [
 ]
 
 [project.entry-points."pynxtools.reader"]
-ellips = "pynxtools_ellips.reader:ELLIPSReader"
+ellips = "pynxtools_ellips.reader:EllipsometryReader"
 
 [project.urls]
 "Homepage" = "https://github.com/FAIRmat-NFDI/pynxtools-ellips"

diff --git a/tests/data/eln_data.yaml b/tests/data/eln_data.yaml
@@ -7,44 +7,46 @@ Data:
   spectrum_type: wavelength
   spectrum_unit: angstrom
 Instrument:
-  Beam_path:
-    Detector:
-      count_time:
-        unit: s
-        value: 1.0
-      detector_type: CCD spectrometer
-    focussing_probes:
-      angular_spread:
-        unit: rad
-        value: 0.2
-      data_correction: false
-    light_source:
-      source_type: arc lamp
-    rotating_element:
-      revolutions: 50.0
+  Detector:
+    count_time:
+      unit: s
+      value: 1.0
+    detector_type: CCD spectrometer
+  focussing_probes:
+    angular_spread:
+      unit: rad
+      value: 0.2
+    data_correction: false
+  light_source:
+    source_type: arc lamp
+  rotating_element:
+    revolutions: 50.0
   Sample_stage:
     environment_conditions:
-      medium: air
     stage_type: manual stage
-  angle_of_incidence/@unit: degrees
-  calibration_status: no calibration
-  company: J. A. Woollam Co.
+#  angle_of_incidence/@unit: degrees
+  device_information:
+    vendor: J. A. Woollam Co.
+    model: RC2 (Vers. 0.0.1)
   ellipsometer_type: dual compensator
-  model: RC2
-  model/@version: 0.0.1
   rotating_element_type: compensator (source side)
-  software: CompleteEASE
-  software/@url: https://www.jawoollam.com/ellipsometry-software/completeease
-  software/version: '6.37'
+  software_RC2: CompleteEASE
+  software_RC2/@url: https://www.jawoollam.com/ellipsometry-software/completeease
+  software_RC2/@version: '6.37'
+  instrument_calibration_RC2:
+    calibration_status: no calibration
 Sample:
   atom_types: Si, O
   backside_roughness: false
   chemical_formula: SiO2
   layer_structure: 2nm SiO2 on Si
-  sample_history: Commercially purchased sample
   sample_name: 2nm SiO2 on Si
-  sample_type: multi layer
+  physical_form: multi layer
   substrate: Si
+  environment:
+    sample_medium: air
+  history:
+    notes: Commercially purchased sample
 User:
   address: Zum Großen Windkanal 2, 12489 Berlin, Germany
   affiliation: Humboldt-Universität zu Berlin
@@ -60,10 +62,14 @@ colnames:
 - err.Delta
 derived_parameter_type: depolarization
 experiment_description: RC2 scan on 2nm SiO2 on Si in air
-experiment_identifier: exp-ID
-experiment_type: NIR-Vis-UV spectroscopic ellipsometry
+experiment_identifier:
+  identifier: exp-ID
+  is_persistent: "false"
+experiment_type: ellipsometry
+ellipsometry_experiment_type: NIR-Vis-UV spectroscopic ellipsometry
 filename: test-data.dat
 plot_name: Psi and Delta
+title: RC2 Ellipsometry of 2nm SiO2 on Si
 sep: \t
 skip: 3
-start_time: '2022-01-27T03:35:00+00:00'
+start_time: '2022-01-27T03:35:00+00:00'