Added citations for 176case study and fixed NX_CLASS decoration bug f…

…or charge_state_model

apm.dev.ipynb

@@ -0,0 +1,59 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6da1aea0-545b-446b-a3d1-1574af72f6c6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import numpy as np\n",
+    "from jupyterlab_h5web import H5Web"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3889c47f-11c4-4bf3-97de-04fc52f0798d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "src = f\"{os.getcwd()}\"\n",
+    "print(src)\n",
+    "fnm = [\"debug.nor_trondheim_hatzeglou_0.nxs\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "aec5b20a-20ed-4fe3-8097-a53bcc9dded0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "H5Web(f\"{src}/debug/{fnm[0]}\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

debug/apm.oasis.specific.yaml

@@ -1 +1,5 @@
-operation_mode: apt
+citation:
+- doi: https://doi.org/repo
+  description: DOI to the respective entry in a data repository.
+- doi: https://doi.org/paper
+  description: DOI to the respective publication.

pynxtools/dataconverter/readers/apm/map_concepts/apm_oasis_cfg_to_nx_map.py

@@ -17,7 +17,7 @@
 #
 """Dict mapping values for a specifically configured NOMAD OASIS."""
 
-# pylint: disable=no-member,line-too-long
+# pylint: disable=line-too-long
 
 # currently by virtue of design NOMAD OASIS specific examples show how different tools and
 # services can be specifically coupled and implemented so that they work together
@@ -43,15 +43,16 @@
 import datetime as dt
 
 from pynxtools.dataconverter.readers.apm.utils.apm_versioning \
-    import NX_APM_ADEF_NAME, NX_APM_ADEF_VERSION, NX_APM_EXEC_NAME, NX_APM_EXEC_VERSION
+    import NX_APM_ADEF_NAME, NX_APM_ADEF_VERSION
 
 
 APM_OASIS_TO_NEXUS_CFG \
     = [("/ENTRY[entry*]/@version", f"{NX_APM_ADEF_VERSION}"),
        ("/ENTRY[entry*]/definition", f"{NX_APM_ADEF_NAME}"),
-       ("/ENTRY[entry*]/operation_mode", "load_from", "operation_mode"),
+       ("/ENTRY[entry*]/operation_mode", "ignore", "operation_mode"),
        ("/ENTRY[entry*]/start_time", f"{dt.datetime.now(dt.timezone.utc).isoformat().replace('+00:00', 'Z')}")]
 
-#      ("/ENTRY[entry*]/PROGRAM[program1]/program", f"{NX_APM_EXEC_NAME}"),
-#      ("/ENTRY[entry*]/PROGRAM[program1]/program/@version", f"{NX_APM_EXEC_VERSION}"),
-#      ("/ENTRY[entry*]/atom_probe/location", "load_from", "location")]
+
+APM_PARAPROBE_EXAMPLE_TO_NEXUS_CFG \
+    = [("/ENTRY[entry*]/CITE[cite*]/doi", "load_from", "doi"),
+       ("/ENTRY[entry*]/CITE[cite*]/description", "load_from", "description")]

pynxtools/dataconverter/readers/apm/utils/apm_load_deployment_specifics.py

@@ -23,9 +23,9 @@
 import yaml
 
 from pynxtools.dataconverter.readers.apm.map_concepts.apm_oasis_cfg_to_nx_map \
-    import APM_OASIS_TO_NEXUS_CFG
+    import APM_OASIS_TO_NEXUS_CFG, APM_PARAPROBE_EXAMPLE_TO_NEXUS_CFG
 from pynxtools.dataconverter.readers.shared.map_concepts.mapping_functors \
-    import apply_modifier, variadic_path_to_specific_path
+    import variadic_path_to_specific_path
 
 
 class NxApmNomadOasisConfigurationParser:  # pylint: disable=too-few-public-methods
@@ -49,22 +49,38 @@ def __init__(self, file_path: str, entry_id: int, verbose: bool = False):
 
     def report(self, template: dict) -> dict:
         """Copy data from configuration applying mapping functors."""
+        identifier = [self.entry_id]
         for tpl in APM_OASIS_TO_NEXUS_CFG:
-            identifier = [self.entry_id]
             if isinstance(tpl, tuple) and len(tpl) >= 2:
-                if tpl[0] not in ("IGNORE", "UNCLEAR"):
+                if tpl[1] != "ignore":
                     trg = variadic_path_to_specific_path(tpl[0], identifier)
-                    # print(f"processing tpl {tpl} ... trg {trg}")
                     if len(tpl) == 2:
                         # nxpath, value to use directly
                         template[trg] = tpl[1]
                     if len(tpl) == 3:
                         # nxpath, modifier, value, modifier (function) evaluates value to use
-                        if tpl[1] == "load_from":
-                            if tpl[2] in self.yml.keys():
-                                template[trg] = self.yml[tpl[2]]
-                            else:
-                                raise ValueError(f"tpl2 {tpl[2]} not in self.yml.keys()!")
-                        else:
-                            raise ValueError(f"tpl1 {tpl[1]} is not load_from!")
+                        if (tpl[1] == "load_from") and (tpl[2] in self.yml):
+                            template[trg] = self.yml[tpl[2]]
+
+        # related to joint paper https://arxiv.org/abs/2205.13510 and NOMAD OASIS
+        src = "citation"
+        if src in self.yml:
+            if isinstance(self.yml[src], list):
+                if all(isinstance(entry, dict) for entry in self.yml[src]) is True:
+                    ref_id = 1
+                    # custom schema delivers a list of dictionaries...
+                    for cite_dict in self.yml[src]:
+                        if cite_dict == {}:
+                            continue
+                        identifier = [self.entry_id, ref_id]
+                        for key in cite_dict:
+                            for tpl in APM_PARAPROBE_EXAMPLE_TO_NEXUS_CFG:
+                                if isinstance(tpl, tuple) and (len(tpl) == 3):
+                                    if (tpl[1] == "load_from") and (key == tpl[2]):
+                                        trg = variadic_path_to_specific_path(
+                                            tpl[0], identifier)
+                                        # res = apply_modifier(modifier, user_dict)
+                                        # res is not None
+                                        template[trg] = cite_dict[tpl[2]]
+                        ref_id += 1
         return template

pynxtools/dataconverter/readers/apm/utils/apm_load_generic_eln.py

@@ -115,14 +115,8 @@ def parse_user(self, template: dict) -> dict:
                         identifier = [self.entry_id, user_id]
                         for key in user_dict:
                             for tpl in APM_EXAMPLE_USER_TO_NEXUS:
-                                # this currently N_user * M_nxpaths complexity implementation should
-                                # be replaced with a faster ideally N_user * log(M_nxpaths)
-                                # implementation also because the mapping table is defined
-                                # trg <- modifier, src, instead of src, modifier -> trg
-                                # but the first formulation is easier to read as typically
-                                # the nxpath is longer than the src path
                                 if isinstance(tpl, tuple) and (len(tpl) == 3):
-                                    if (tpl[1] == "load_from") and (tpl[2] == key):
+                                    if (tpl[1] == "load_from") and (key == tpl[2]):
                                         trg = variadic_path_to_specific_path(
                                             tpl[0], identifier)
                                         # res = apply_modifier(modifier, user_dict)
@@ -146,7 +140,7 @@ def parse_pulser_source(self, template: dict) -> dict:
                     # custom schema delivers a list of dictionaries...
                     for ldct in self.yml[src]:
                         trg_sta = f"/ENTRY[entry{self.entry_id}]/measurement/" \
-                                  f"pulser/SOURCE[source{laser_id}]"
+                                  f"instrument/pulser/SOURCE[source{laser_id}]"
                         if "name" in ldct:
                             template[f"{trg_sta}/name"] = ldct["name"]
                         quantities = ["wavelength"]

pynxtools/dataconverter/readers/apm/utils/apm_load_ranging.py

@@ -80,7 +80,7 @@ def add_standardize_molecular_ions(ion_lst: list, template: dict, entry_id: int)
         template[f"{path}name"] = ion.name.values
 
         if ion.charge_state_model["n_cand"] > 0:
-            path = f"{trg}ION[ion{ion_id}]/charge_state_model/"
+            path = f"{trg}ION[ion{ion_id}]/charge_state_analysis/"
             template[f"{path}min_abundance"] \
                 = np.float64(ion.charge_state_model["min_abundance"])
             template[f"{path}min_abundance_product"] \