Add remaining symmetry group fields (Hall, HM symbols, IT number)

openapi/openapi.json

@@ -4371,6 +4371,68 @@
             "x-optimade-queryable": "optional",
             "x-optimade-support": "optional"
           },
+          "space_group_symbol_hall": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "title": "Space Group Symbol Hall",
+            "description": "A Hall space group symbol representing the symmetry of the structure as defined in (Hall, 1981, 1981a).\n\n- **Type**: string\n\n- **Requirements/Conventions**:\n    - **Support**: OPTIONAL support in implementations, i.e., MAY be `null`.\n    - **Query**: Support for queries on this property is OPTIONAL.\n    - The change-of-basis operations are used as defined in the International Tables of Crystallography (ITC) Vol. B, Sect. 1.4, Appendix A1.4.2 (IUCr, 2001).\n    - Each component of the Hall symbol MUST be separated by a single space symbol.\n    - If there exists a standard Hall symbol which represents the symmetry it SHOULD be used.\n    - MUST be `null` if `nperiodic_dimensions` is not equal to 3.\n\n- **Examples**:\n    - Space group symbols with explicit origin (the Hall symbols):\n        - `P 2c -2ac`\n        - `I 4bd 2ab 3`\n    - Space group symbols with change-of-basis operations:\n        - `P 2yb (-1/2*x+z,1/2*x,y)`\n        - `-I 4 2 (1/2*x+1/2*y,-1/2*x+1/2*y,z)`\n\n- **Bibliographic References**:\n    - Hall, S. R. (1981) Space-group notation with an explicit origin. Acta Crystallographica Section A, 37, 517-525, International Union of Crystallography (IUCr), DOI: https://doi.org/10.1107/s0567739481001228\n    - Hall, S. R. (1981a) Space-group notation with an explicit origin; erratum. Acta Crystallographica Section A, 37, 921-921, International Union of Crystallography (IUCr), DOI: https://doi.org/10.1107/s0567739481001976\n    - IUCr (2001). International Tables for Crystallography vol. B. Reciprocal Space. Ed. U. Shmueli. 2-nd edition. Dordrecht/Boston/London, Kluwer Academic Publishers.",
+            "x-optimade-queryable": "optional",
+            "x-optimade-support": "optional"
+          },
+          "space_group_symbol_hermann_mauguin": {
+            "anyOf": [
+              {
+                "type": "string",
+                "pattern": "^(P|I|F|A|B|C|R)(\\s+\\d+|\\s+[a-z]+|\\s+\\d+/[a-z]+|\\s+\\d+/\\d+|\\s+-\\d*|\\s+\\d+/m|\\s+[a-z]+/m)*$"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "pattern": "^(P|I|F|A|B|C|R)(\\s+\\d+|\\s+[a-z]+|\\s+\\d+/[a-z]+|\\s+\\d+/\\d+|\\s+-\\d*|\\s+\\d+/m|\\s+[a-z]+/m)*$",
+            "title": "Space Group Symbol Hermann Mauguin",
+            "description": "A human- and machine-readable string containing the short Hermann-Mauguin (H-M) symbol which specifies the space group of the structure in the response.\n\n- **Type**: string\n\n- **Requirements/Conventions**:\n    - **Support**: OPTIONAL support in implementations, i.e., MAY be `null`.\n    - **Query**: Support for queries on this property is OPTIONAL.\n    - The H-M symbol SHOULD aim to convey the closest representation of the symmetry information that can be specified using the short format used in the International Tables for Crystallography vol. A (IUCr, 2005), Table 4.3.2.1 as described in the accompanying text.\n    - The symbol MAY be a non-standard short H-M symbol.\n    - The H-M symbol does not unambiguously communicate the axis, cell, and origin choice, and the given symbol SHOULD NOT be amended to convey this information.\n    - To encode as character strings, the following adaptations MUST be made when representing H-M symbols given in their typesetted form:\n        - the overbar above the numbers MUST be changed to the minus sign in front of the digit (e.g. '-2');\n        - subscripts that denote screw axes are written as digits immediately after the axis designator without a space (e.g. 'P 32')\n        - the space group generators MUST be separated by a single space (e.g. 'P 21 21 2');\n        - there MUST be no spaces in the space group generator designation (i.e. use 'P 21/m', not the 'P 21 / m');\n\n- **Examples**:\n    - `C 2`\n    - `P 21 21 21`\n\n- **Bibliographic References**:\n    - IUCr (2005). International Tables for Crystallography vol. A. Space-Group Symmetry. Ed. Theo Hahn. 5-th edition. Dordrecht, Springer.\n",
+            "x-optimade-queryable": "optional",
+            "x-optimade-support": "optional"
+          },
+          "space_group_symbol_hermann_mauguin_extended": {
+            "anyOf": [
+              {
+                "type": "string",
+                "pattern": "^(P|I|F|A|B|C|R)(\\s+\\d+|\\s+[a-z]+|\\s+\\d+/[a-z]+|\\s+\\d+/\\d+|\\s+-\\d*|\\s+\\d+/m|\\s+[a-z]+/m)*$"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "pattern": "^(P|I|F|A|B|C|R)(\\s+\\d+|\\s+[a-z]+|\\s+\\d+/[a-z]+|\\s+\\d+/\\d+|\\s+-\\d*|\\s+\\d+/m|\\s+[a-z]+/m)*$",
+            "title": "Space Group Symbol Hermann Mauguin Extended",
+            "description": "A human- and machine-readable string containing the extended Hermann-Mauguin (H-M) symbol which specifies the space group of the structure in the response.\n\n- **Type**: string\n\n- **Requirements/Conventions**:\n    - **Support**: OPTIONAL support in implementations, i.e., MAY be `null`.\n    - **Query**: Support for queries on this property is OPTIONAL.\n    - The H-M symbols SHOULD be given as specified in the International Tables for Crystallography vol. A (IUCr, 2005), Table 4.3.2.1.\n    - The change-of-basis operation SHOULD be provided for the non-standard axis and cell choices.\n    - The extended H-M symbol does not unambiguously communicate the origin choice, and the given symbol SHOULD NOT be amended to convey this information.\n    - The description of the change-of-basis SHOULD follow conventions of the ITC Vol. B, Sect. 1.4, Appendix A1.4.2 (IUCr, 2001).\n    - The same character string encoding conventions MUST be used as for the specification of the `space_group_symbol_hermann_mauguin` property.\n\n- **Examples**:\n    - `C 1 2 1`\n\n- **Bibliographic References**:\n    - IUCr (2001). International Tables for Crystallography vol. B. Reciprocal Space. Ed. U. Shmueli. 2-nd edition. Dordrecht/Boston/London, Kluwer Academic Publishers.\n    - IUCr (2005). International Tables for Crystallography vol. A. Space-Group Symmetry. Ed. Theo Hahn. 5-th edition. Dordrecht, Springer.\n\n",
+            "x-optimade-queryable": "optional",
+            "x-optimade-support": "optional"
+          },
+          "space_group_it_number": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "maximum": 230.0,
+                "minimum": 1.0
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "title": "Space Group It Number",
+            "description": "Space group number which specifies the space group of the structure as defined in the International Tables for Crystallography Vol. A. (IUCr, 2005).\n\n- **Type**: integer\n\n- **Requirements/Conventions**:\n    - **Support**: OPTIONAL support in implementations, i.e., MAY be `null`.\n    - **Query**: Support for queries on this property is OPTIONAL.\n    - The integer value MUST be between 1 and 230.\n    - MUST be null if `nperiodic_dimensions` is not equal to 3.",
+            "x-optimade-queryable": "optional",
+            "x-optimade-support": "optional"
+          },
           "cartesian_site_positions": {
             "anyOf": [
               {

optimade/models/structures.py

@@ -11,6 +11,7 @@
     ANONYMOUS_ELEMENTS,
     CHEMICAL_FORMULA_REGEXP,
     CHEMICAL_SYMBOLS,
+    HM_SYMBOL_REGEXP,
     OptimadeField,
     StrictField,
     SupportLevel,
@@ -601,6 +602,119 @@ class StructureResourceAttributes(EntryResourceAttributes):
         ),
     ] = None
 
+    space_group_symbol_hall: Annotated[
+        str | None,
+        OptimadeField(
+            description="""A Hall space group symbol representing the symmetry of the structure as defined in (Hall, 1981, 1981a).
+
+- **Type**: string
+
+- **Requirements/Conventions**:
+    - **Support**: OPTIONAL support in implementations, i.e., MAY be `null`.
+    - **Query**: Support for queries on this property is OPTIONAL.
+    - The change-of-basis operations are used as defined in the International Tables of Crystallography (ITC) Vol. B, Sect. 1.4, Appendix A1.4.2 (IUCr, 2001).
+    - Each component of the Hall symbol MUST be separated by a single space symbol.
+    - If there exists a standard Hall symbol which represents the symmetry it SHOULD be used.
+    - MUST be `null` if `nperiodic_dimensions` is not equal to 3.
+
+- **Examples**:
+    - Space group symbols with explicit origin (the Hall symbols):
+        - `P 2c -2ac`
+        - `I 4bd 2ab 3`
+    - Space group symbols with change-of-basis operations:
+        - `P 2yb (-1/2*x+z,1/2*x,y)`
+        - `-I 4 2 (1/2*x+1/2*y,-1/2*x+1/2*y,z)`
+
+- **Bibliographic References**:
+    - Hall, S. R. (1981) Space-group notation with an explicit origin. Acta Crystallographica Section A, 37, 517-525, International Union of Crystallography (IUCr), DOI: https://doi.org/10.1107/s0567739481001228
+    - Hall, S. R. (1981a) Space-group notation with an explicit origin; erratum. Acta Crystallographica Section A, 37, 921-921, International Union of Crystallography (IUCr), DOI: https://doi.org/10.1107/s0567739481001976
+    - IUCr (2001). International Tables for Crystallography vol. B. Reciprocal Space. Ed. U. Shmueli. 2-nd edition. Dordrecht/Boston/London, Kluwer Academic Publishers.""",
+            support=SupportLevel.OPTIONAL,
+            queryable=SupportLevel.OPTIONAL,
+        ),
+    ] = None
+
+    space_group_symbol_hermann_mauguin: Annotated[
+        str | None,
+        OptimadeField(
+            description="""A human- and machine-readable string containing the short Hermann-Mauguin (H-M) symbol which specifies the space group of the structure in the response.
+
+- **Type**: string
+
+- **Requirements/Conventions**:
+    - **Support**: OPTIONAL support in implementations, i.e., MAY be `null`.
+    - **Query**: Support for queries on this property is OPTIONAL.
+    - The H-M symbol SHOULD aim to convey the closest representation of the symmetry information that can be specified using the short format used in the International Tables for Crystallography vol. A (IUCr, 2005), Table 4.3.2.1 as described in the accompanying text.
+    - The symbol MAY be a non-standard short H-M symbol.
+    - The H-M symbol does not unambiguously communicate the axis, cell, and origin choice, and the given symbol SHOULD NOT be amended to convey this information.
+    - To encode as character strings, the following adaptations MUST be made when representing H-M symbols given in their typesetted form:
+        - the overbar above the numbers MUST be changed to the minus sign in front of the digit (e.g. '-2');
+        - subscripts that denote screw axes are written as digits immediately after the axis designator without a space (e.g. 'P 32')
+        - the space group generators MUST be separated by a single space (e.g. 'P 21 21 2');
+        - there MUST be no spaces in the space group generator designation (i.e. use 'P 21/m', not the 'P 21 / m');
+
+- **Examples**:
+    - `C 2`
+    - `P 21 21 21`
+
+- **Bibliographic References**:
+    - IUCr (2005). International Tables for Crystallography vol. A. Space-Group Symmetry. Ed. Theo Hahn. 5-th edition. Dordrecht, Springer.
+""",
+            support=SupportLevel.OPTIONAL,
+            queryable=SupportLevel.OPTIONAL,
+            pattern=HM_SYMBOL_REGEXP,
+        ),
+    ] = None
+
+    space_group_symbol_hermann_mauguin_extended: Annotated[
+        str | None,
+        OptimadeField(
+            description="""A human- and machine-readable string containing the extended Hermann-Mauguin (H-M) symbol which specifies the space group of the structure in the response.
+
+- **Type**: string
+
+- **Requirements/Conventions**:
+    - **Support**: OPTIONAL support in implementations, i.e., MAY be `null`.
+    - **Query**: Support for queries on this property is OPTIONAL.
+    - The H-M symbols SHOULD be given as specified in the International Tables for Crystallography vol. A (IUCr, 2005), Table 4.3.2.1.
+    - The change-of-basis operation SHOULD be provided for the non-standard axis and cell choices.
+    - The extended H-M symbol does not unambiguously communicate the origin choice, and the given symbol SHOULD NOT be amended to convey this information.
+    - The description of the change-of-basis SHOULD follow conventions of the ITC Vol. B, Sect. 1.4, Appendix A1.4.2 (IUCr, 2001).
+    - The same character string encoding conventions MUST be used as for the specification of the `space_group_symbol_hermann_mauguin` property.
+
+- **Examples**:
+    - `C 1 2 1`
+
+- **Bibliographic References**:
+    - IUCr (2001). International Tables for Crystallography vol. B. Reciprocal Space. Ed. U. Shmueli. 2-nd edition. Dordrecht/Boston/London, Kluwer Academic Publishers.
+    - IUCr (2005). International Tables for Crystallography vol. A. Space-Group Symmetry. Ed. Theo Hahn. 5-th edition. Dordrecht, Springer.
+
+""",
+            support=SupportLevel.OPTIONAL,
+            queryable=SupportLevel.OPTIONAL,
+            pattern=HM_SYMBOL_REGEXP,
+        ),
+    ] = None
+
+    space_group_it_number: Annotated[
+        int | None,
+        OptimadeField(
+            description="""Space group number which specifies the space group of the structure as defined in the International Tables for Crystallography Vol. A. (IUCr, 2005).
+
+- **Type**: integer
+
+- **Requirements/Conventions**:
+    - **Support**: OPTIONAL support in implementations, i.e., MAY be `null`.
+    - **Query**: Support for queries on this property is OPTIONAL.
+    - The integer value MUST be between 1 and 230.
+    - MUST be null if `nperiodic_dimensions` is not equal to 3.""",
+            support=SupportLevel.OPTIONAL,
+            queryable=SupportLevel.OPTIONAL,
+            ge=1,
+            le=230,
+        ),
+    ] = None
+
     cartesian_site_positions: Annotated[
         list[Vector3D] | None,
         OptimadeField(

optimade/models/utils.py

@@ -234,6 +234,18 @@ def reduce_formula(formula: str) -> str:
 
 CHEMICAL_FORMULA_REGEXP = r"(^$)|^([A-Z][a-z]?([2-9]|[1-9]\d+)?)+$"
 SYMMETRY_OPERATION_REGEXP = r"^([-+]?[xyz]([-+][xyz])?([-+](1/2|[12]/3|[1-3]/4|[1-5]/6))?|[-+]?(1/2|[12]/3|[1-3]/4|[1-5]/6)([-+][xyz]([-+][xyz])?)?),([-+]?[xyz]([-+][xyz])?([-+](1/2|[12]/3|[1-3]/4|[1-5]/6))?|[-+]?(1/2|[12]/3|[1-3]/4|[1-5]/6)([-+][xyz]([-+][xyz])?)?),([-+]?[xyz]([-+][xyz])?([-+](1/2|[12]/3|[1-3]/4|[1-5]/6))?|[-+]?(1/2|[12]/3|[1-3]/4|[1-5]/6)([-+][xyz]([-+][xyz])?)?)$"
+HM_SYMBOL_REGEXP = r"^(P|I|F|A|B|C|R)(\s+\d+|\s+[a-z]+|\s+\d+/[a-z]+|\s+\d+/\d+|\s+-\d*|\s+\d+/m|\s+[a-z]+/m)*$"
+
+
+def _generate_symmetry_operation_regex():
+    translation = "1/2|[12]/3|[1-3]/4|[1-5]/6"
+    translation_appended = f"[-+]? [xyz] ([-+][xyz])? ([-+] ({translation}) )?"
+    translation_prepended = f"[-+]? ({translation}) ([-+] [xyz] ([-+][xyz])? )?"
+    symop = f"({translation_appended}|{translation_prepended})".replace(" ", "")
+    return f"^{symop},{symop},{symop}$"
+
+
+SPACE_GROUP_SYMMETRY_OPERATION_REGEX = _generate_symmetry_operation_regex()
 
 EXTRA_SYMBOLS = ["X", "vacancy"]
 

tests/adapters/structures/test_structures.py

@@ -192,6 +192,10 @@ def compare_lossy_conversion(
         "species",
         "fractional_site_positions",
         "space_group_symmetry_operations_xyz",
+        "space_group_symbol_hall",
+        "space_group_symbol_hermann_mauguin",
+        "space_group_symbol_hermann_mauguin_extended",
+        "space_group_it_number",
     )
     array_keys = ("cartesian_site_positions", "lattice_vectors")
 

tests/models/test_data/test_good_structures.json

@@ -191,7 +191,10 @@
       {"name": "P", "chemical_symbols": ["P"], "concentration": [1.0] }
     ],
     "structure_features": ["site_attachments"],
-    "space_group_symmetry_operations_xyz": ["x,y,z", "-x,y,-z", "x+1/2,y+1/2,z", "-x+1/2,y+1/2,-z"]
+    "space_group_symmetry_operations_xyz": ["x,y,z", "-x,y,-z", "x+1/2,y+1/2,z", "-x+1/2,y+1/2,-z"],
+    "space_group_symbol_hermann_mauguin": "R -3 m",
+    "space_group_symbol_hermann_mauguin_extended": "R -3 m",
+    "space_group_symbol_hall": "I 4bd 2ab 3"
   },
   {
     "task_id": "db/1234567",
@@ -224,6 +227,10 @@
       {"name": "P", "chemical_symbols": ["P"], "concentration": [1.0] }
     ],
     "structure_features": ["disorder", "site_attachments"],
-    "space_group_symmetry_operations_xyz": ["x,y,z"]
+    "space_group_symmetry_operations_xyz": ["x,y,z"],
+    "space_group_symbol_hall": "P 2yb (-1/2*x+z,1/2*x,y)",
+    "space_group_symbol_hermann_mauguin": "P 1",
+    "space_group_symbol_hermann_mauguin_extended": "P 1",
+    "space_group_it_number": 122
   }
 ]

tests/models/test_structures.py

@@ -211,6 +211,10 @@ def test_bad_structures(
         {"space_group_symmetry_operations_xyz": ["xy,z"]},
         "String should match pattern",
     ),
+    (
+        {"space_group_symbol_hermann_mauguin": "P1"},
+        "String should match pattern",
+    ),
 )
 
 

tests/models/test_utils.py

@@ -1,9 +1,15 @@
+import re
 from collections.abc import Callable
 
 import pytest
 from pydantic import BaseModel, Field, ValidationError
 
-from optimade.models.utils import OptimadeField, StrictField, SupportLevel
+from optimade.models.utils import (
+    HM_SYMBOL_REGEXP,
+    OptimadeField,
+    StrictField,
+    SupportLevel,
+)
 
 
 def make_bad_models(field: Callable):
@@ -159,3 +165,58 @@ def test_anonymize_formula():
     assert anonymize_formula("Si1 O2") == "A2B"
     assert anonymize_formula("Si11 O2") == "A11B2"
     assert anonymize_formula("Si10 O2C4") == "A5B2C"
+
+
+VALID_HM_SYMBOLS = [
+    "P 1",  # Triclinic
+    "P -1",
+    "P 2",  # Monoclinic
+    "P 21",
+    "P m",
+    "P c",
+    "P 2/m",
+    "P 21/c",
+    "P 21/n",
+    "C 2/c",
+    "P 2 2 2",  # Orthorhombic
+    "P 21 21 21",
+    "P n n n",
+    "P m m a",
+    "F d d d",
+    "I m m a",
+    "P 4",  # Tetragonal
+    "P 41",
+    "P 42",
+    "P 43",
+    "I 4/m m m",
+    "P 3",  # Trigonal
+    "R 3",
+    "P 31",
+    "R -3 m",
+    "P 6",  # Hexagonal
+    "P 63/m m c",
+    "P m -3",  # Cubic
+    "F m -3 m",
+    "I a -3 d",
+]
+
+INVALID_HM_SYMBOLS = [
+    "",  # Empty string
+    "p 1",  # Lowercase lattice
+    "Q 1",  # Invalid lattice
+    "P1",  # No space
+    "1 P",  # Wrong order
+    "P 2/c/m",  # Invalid combination
+    "PP 2",  # Double letter
+    "X -3 m",  # Invalid lattice
+]
+
+
+@pytest.mark.parametrize("hm_symbol", VALID_HM_SYMBOLS)
+def test_hm_symbol_regexp(hm_symbol):
+    assert re.match(HM_SYMBOL_REGEXP, hm_symbol)
+
+
+@pytest.mark.parametrize("hm_symbol", INVALID_HM_SYMBOLS)
+def test_invalid_space_groups(hm_symbol):
+    assert re.match(HM_SYMBOL_REGEXP, hm_symbol) is None

tests/server/test_client.py

@@ -509,7 +509,7 @@ def test_list_properties(
 
     results = cli.list_properties("structures")
     for database in results:
-        assert len(results[database]) == 23, str(results[database])
+        assert len(results[database]) == 27, str(results[database])
 
     results = cli.search_property("structures", "site")
     for database in results: