More terms and validation

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.1.2
+current_version = 0.2.0
 commit = True
 tag = True
 

conceptual_dictionary/__init__.py

@@ -5,6 +5,20 @@
     property_template,
     workflow_template,
     operation_template,
+    math_operation_template,
+)
+from conceptual_dictionary.vocabs import (
+    CONTROLLED_VALUES,
+    METHOD,
+    ALGORITHM,
+    DEGREES_OF_FREEDOM,
+    THERMODYNAMIC_ENSEMBLE,
+    POTENTIAL_TYPE,
+    XC_FUNCTIONAL,
+    OPERATION_METHOD,
+    GRAIN_BOUNDARY_TYPE,
+    MATH_OPERATION_TYPE,
+    YAML_TOP_LEVEL_KEYS,
 )
 
 __all__ = [
@@ -13,4 +27,16 @@
     "property_template",
     "workflow_template",
     "operation_template",
+    "math_operation_template",
+    "CONTROLLED_VALUES",
+    "METHOD",
+    "ALGORITHM",
+    "DEGREES_OF_FREEDOM",
+    "THERMODYNAMIC_ENSEMBLE",
+    "POTENTIAL_TYPE",
+    "XC_FUNCTIONAL",
+    "OPERATION_METHOD",
+    "GRAIN_BOUNDARY_TYPE",
+    "MATH_OPERATION_TYPE",
+    "YAML_TOP_LEVEL_KEYS",
 ]

conceptual_dictionary/conceptualdict.py

@@ -1,14 +1,22 @@
+import warnings
 import yaml
 import json
-from typing import Any, Dict
+from typing import Any, Dict, List
 import numpy as np
 import string
 import random
 
+from conceptual_dictionary.vocabs import CONTROLLED_VALUES
+
 
 class ConceptualDict(dict):
     def __init__(self, *args, **kwargs):
-        data = {"computational_sample": [], "workflow": [], "operation": []}
+        data = {
+            "computational_sample": [],
+            "workflow": [],
+            "operation": [],
+            "math_operation": [],
+        }
         super().__init__(data, *args, **kwargs)
 
     def generate_id(self, length=7):
@@ -68,3 +76,113 @@ def from_json(cls, filepath: str) -> "ConceptualDict":
         kg = cls()
         kg.update(data)
         return kg
+
+    # --------------------
+    # Validation
+    # --------------------
+    def validate(self, strict: bool = False) -> List[dict]:
+        """Check all entries against controlled vocabularies sourced from atomRDF.
+
+        Parameters
+        ----------
+        strict : bool
+            If False (default), emit ``warnings.warn`` for each violation and
+            return the full list.  If True, raise ``ValueError`` on the first
+            violation — useful in CI / test contexts.
+
+        Returns
+        -------
+        list[dict]
+            Each item has keys ``section``, ``index``, ``field``, ``value``,
+            ``allowed`` so callers can inspect violations programmatically.
+        """
+        violations: List[dict] = []
+
+        def _check(section: str, idx: int, field: str, value, allowed: frozenset):
+            if value is None:
+                return
+            values = value if isinstance(value, list) else [value]
+            for v in values:
+                if v not in allowed:
+                    msg = (
+                        f"[{section}][{idx}] '{field}' has invalid value '{v}'. "
+                        f"Allowed: {sorted(allowed)}"
+                    )
+                    violations.append(
+                        dict(
+                            section=section,
+                            index=idx,
+                            field=field,
+                            value=v,
+                            allowed=allowed,
+                        )
+                    )
+                    if strict:
+                        raise ValueError(msg)
+                    warnings.warn(msg, UserWarning, stacklevel=2)
+
+        for i, wf in enumerate(self.get("workflow", [])):
+            _check(
+                "workflow",
+                i,
+                "method",
+                wf.get("method"),
+                CONTROLLED_VALUES["workflow.method"][0],
+            )
+            _check(
+                "workflow",
+                i,
+                "algorithm",
+                wf.get("algorithm"),
+                CONTROLLED_VALUES["workflow.algorithm"][0],
+            )
+            _check(
+                "workflow",
+                i,
+                "degrees_of_freedom",
+                wf.get("degrees_of_freedom"),
+                CONTROLLED_VALUES["workflow.degrees_of_freedom"][0],
+            )
+            _check(
+                "workflow",
+                i,
+                "thermodynamic_ensemble",
+                wf.get("thermodynamic_ensemble"),
+                CONTROLLED_VALUES["workflow.thermodynamic_ensemble"][0],
+            )
+            _check(
+                "workflow",
+                i,
+                "xc_functional",
+                wf.get("xc_functional"),
+                CONTROLLED_VALUES["workflow.xc_functional"][0],
+            )
+            pot = wf.get("interatomic_potential")
+            if isinstance(pot, dict):
+                _check(
+                    "workflow",
+                    i,
+                    "potential_type",
+                    pot.get("potential_type"),
+                    CONTROLLED_VALUES["workflow.potential_type"][0],
+                )
+
+        for i, op in enumerate(self.get("operation", [])):
+            _check(
+                "operation",
+                i,
+                "method",
+                op.get("method"),
+                CONTROLLED_VALUES["operation.method"][0],
+            )
+
+        for i, mo in enumerate(self.get("math_operation", [])):
+            _check(
+                "math_operation",
+                i,
+                "type",
+                mo.get("type"),
+                CONTROLLED_VALUES["math_operation.type"][0],
+            )
+
+        return violations

conceptual_dictionary/templates.py

@@ -28,15 +28,17 @@
         "species": None,
         # Option B — file reference (preferred for large MD snapshots)
         # WorkflowParser resolves this relative to the YAML file's directory.
-        "file_path": None,    # path to structure file, e.g. '../DC3_benchmark_data_set/Al_fcc/T_0.10Tm_snapshot_1.gz'
+        "file_path": None,  # path to structure file, e.g. '../DC3_benchmark_data_set/Al_fcc/T_0.10Tm_snapshot_1.gz'
         "file_format": None,  # ASE format string, e.g. 'lammps-dump-text' (auto-detected if None)
-        "file_species": None, # species order for LAMMPS numeric types, e.g. ['Al']
+        "file_species": None,  # species order for LAMMPS numeric types, e.g. ['Al']
     },
     "calculated_property": [],
 }
 
 property_template = {
-    "basename": None,
+    "id": None,  # optional local ID; used to reference this property in math_operation operands
+    "label": None,  # primary name read by atomRDF WorkflowParser
+    "basename": None,  # kept for backwards compat
     "value": None,
     "unit": None,
     "associate_to_sample": [],
@@ -46,20 +48,29 @@
     "algorithm": None,
     "method": None,
     "xc_functional": None,
-    "input_parameter": [],
+    # Each entry in these lists may include an optional 'id' field so later
+    # math_operation entries can reference the property by its local ID.
+    "input_parameter": [
+        # {"id": None, "label": None, "basename": None, "value": None, "unit": None}
+    ],
     "input_sample": [],
     "output_sample": [],
-    "calculated_property": [],
+    "output_parameter": [
+        # {"id": None, "label": None, "basename": None, "value": None, "unit": None}
+    ],
+    "calculated_property": [
+        # {"id": None, "label": None, "basename": None, "value": None, "unit": None,
+        #  "associate_to_sample": []}
+    ],
     "degrees_of_freedom": [],
     "interatomic_potential": {
         "potential_type": None,
         "uri": None,
     },
-    "software": {
-        "uri": None,
-        "version": None,
-        "label": None,
-    },
+    # software is a list of {uri, version, label} dicts
+    "software": [],
+    # single-software template kept for reference:
+    # {"uri": None, "version": None, "label": None}
     "workflow_manager": {
         "uri": None,
         "version": None,
@@ -68,6 +79,58 @@
     "thermodynamic_ensemble": None,
 }
 
+dataset_template = {
+    # dcat:Dataset — the dataset node
+    "identifier": None,  # URI/IRI for the dataset, e.g. "https://doi.org/10.5281/zenodo.1234567"
+    "title": None,  # dcterms:title, e.g. "Grain boundary energies for Al"
+    # dcterms:creator — list of foaf:Person entries
+    "creators": [
+        {
+            "id": None,  # URI for the person, e.g. "https://orcid.org/0000-0000-0000-0000"
+            "name": None,  # foaf:name, e.g. "Abril Guzman"
+        }
+    ],
+    # dcterms:isReferencedBy — the associated publication
+    "publication": {
+        "id": None,  # URI for the paper
+        "identifier": None,  # dcterms:identifier — DOI string, e.g. "10.1016/j.actamat.2024.12345"
+        "title": None,  # dcterms:title (optional)
+    },
+    # dcterms:isPartOf — list of sample IDs that belong to this dataset
+    # (these are added as triples on each sample: sample dcterms:isPartOf dataset)
+    "samples": [],
+}
+
+# Math-operation template for ASMO arithmetic activities.
+# Operands may be a local property ID string (referencing an earlier
+# calculated / input / output property by its 'id' field) or a numeric
+# scalar.  The result is a CalculatedProperty and may carry its own 'id'
+# so subsequent math_operation entries can use it as an operand.
+math_operation_template = {
+    "type": None,  # Required: Subtraction | Addition | Multiplication | Division | Exponentiation
+    "result": {
+        "id": None,  # optional local ID for use as operand in later math operations
+        "label": None,
+        "basename": None,
+        "value": None,  # set if result value is known; otherwise leave None
+        "unit": None,
+        "associate_to_sample": [],
+    },
+    # ── Subtraction ──────────────────────────────────────────────────────────
+    "minuend": None,  # property ID or scalar
+    "subtrahend": None,  # property ID or scalar
+    # ── Addition ─────────────────────────────────────────────────────────────
+    "addend": [],  # list of property IDs and/or scalars
+    # ── Multiplication ───────────────────────────────────────────────────────
+    "factor": [],  # list of property IDs and/or scalars
+    # ── Division ─────────────────────────────────────────────────────────────
+    "dividend": None,  # property ID or scalar
+    "divisor": None,  # property ID or scalar
+    # ── Exponentiation ───────────────────────────────────────────────────────
+    "base": None,  # property ID or scalar
+    "exponent": None,  # property ID or scalar
+}
+
 # Operation template for atomic-scale transformations
 # Contains all possible fields for all operation types
 operation_template = {