Sorting + pagination for some endpoints

emmet-api/emmet/api/query_operator/pagination.py

@@ -3,11 +3,14 @@
 from emmet.api.query_operator import QueryOperator
 from emmet.api.utils import STORE_PARAMS
 
+DEFAULT_LIMIT: int = 100
+MAX_LIMIT: int = 1000
+
 
 class AtlasPaginationQuery(QueryOperator):
     """Query operators to provides pagination for Atlas Search queries."""
 
-    def __init__(self, default_limit: int = 100, max_limit: int = 1000):
+    def __init__(self, default_limit: int = DEFAULT_LIMIT, max_limit: int = MAX_LIMIT):
         """
         Args:
             default_limit: the default number of documents to return
@@ -71,7 +74,7 @@ def meta(self) -> dict:
 class PaginationQuery(QueryOperator):
     """Query operators to provides Pagination."""
 
-    def __init__(self, default_limit: int = 100, max_limit: int = 1000):
+    def __init__(self, default_limit: int = DEFAULT_LIMIT, max_limit: int = MAX_LIMIT):
         """
         Args:
             default_limit: the default number of documents to return

emmet-api/emmet/api/routes/legacy/jcesr/resources.py

@@ -1,7 +1,7 @@
 from emmet.api.resource import ReadOnlyResource
 from emmet.core.molecules_jcesr import MoleculesDoc
 
-from emmet.api.query_operator import PaginationQuery, SparseFieldsQuery
+from emmet.api.query_operator import PaginationQuery, SortQuery, SparseFieldsQuery
 from emmet.api.routes.legacy.jcesr.query_operators import (
     MoleculeBaseQuery,
     MoleculeElementsQuery,
@@ -11,6 +11,13 @@
 from emmet.api.core.global_header import GlobalHeaderProcessor
 from emmet.api.core.settings import MAPISettings
 
+JCESR_SORT_FIELDS = [
+    "task_id",
+    "EA",
+    "IE",
+    "charge",
+]
+
 
 def jcesr_resource(molecules_store):
     resource = ReadOnlyResource(
@@ -22,6 +29,7 @@ def jcesr_resource(molecules_store):
             MoleculeFormulaQuery(),
             MultipleTaskIDsQuery(),
             PaginationQuery(),
+            SortQuery(fields=JCESR_SORT_FIELDS, max_num=1),
             SparseFieldsQuery(MoleculesDoc, default_fields=["task_id"]),
         ],
         header_processor=GlobalHeaderProcessor(),

emmet-api/emmet/api/routes/materials/insertion_electrodes/resources.py

@@ -1,9 +1,13 @@
-from emmet.api.query_operator.dynamic import NumericQuery
+from emmet.api.query_operator import (
+    NumericQuery,
+    PaginationQuery,
+    SortQuery,
+    SparseFieldsQuery,
+)
 from emmet.api.resource import ReadOnlyResource
 from emmet.core.electrode import InsertionElectrodeDoc
 from emmet.api.core.global_header import GlobalHeaderProcessor
 
-from emmet.api.query_operator import PaginationQuery, SparseFieldsQuery
 from emmet.api.routes.materials.insertion_electrodes.query_operators import (
     ElectrodeFormulaQuery,
     ElectrodeElementsQuery,
@@ -14,6 +18,18 @@
 
 from emmet.api.core.settings import MAPISettings
 
+sort_fields = [
+    "battery_id",
+    "max_delta_volume",
+    "average_voltage",
+    "capacity_grav",
+    "capacity_vol",
+    "energy_grav",
+    "energy_vol",
+    "stability_charge",
+    "stability_discharge",
+]
+
 
 def insertion_electrodes_resource(insertion_electrodes_store):
     resource = ReadOnlyResource(
@@ -31,6 +47,7 @@ def insertion_electrodes_resource(insertion_electrodes_store):
                 InsertionElectrodeDoc,
                 default_fields=["battery_id", "last_updated"],
             ),
+            SortQuery(fields=sort_fields, max_num=1),
         ],
         header_processor=GlobalHeaderProcessor(),
         tags=["Materials Electrodes"],

emmet-api/emmet/api/routes/materials/insertion_electrodes/utils.py

@@ -5,7 +5,7 @@
 
 def electrodes_formula_to_criteria(formulas: str) -> dict:
     """
-    Santizes formula into a dictionary to search with wild cards
+    Sanitizes formula into a dictionary to search with wild cards
     over electrodes data
 
     Arguments:
@@ -116,7 +116,7 @@ def electrodes_formula_to_criteria(formulas: str) -> dict:
 
 def electrodes_chemsys_to_criteria(chemsys: str) -> dict:
     """
-    Santizes chemsys into a dictionary to search with wild cards
+    Sanitizes chemsys into a dictionary to search with wild cards
     over electrodes data
 
     Arguments:

emmet-api/emmet/api/routes/materials/materials/query_operators.py

@@ -151,6 +151,9 @@ class SymmetryQuery(QueryOperator):
     Method to generate a query on symmetry information.
     """
 
+    MAX_SPACE_GROUPS: int = 115
+    MAX_CRYSTAL_SYSTEMS: int = 3
+
     def query(
         self,
         crystal_system: str | None = Query(
@@ -188,6 +191,13 @@ def query(
                 else {"$in": crystal_systems}
             )
 
+        crystal_systems = sorted(set(crystal_systems))
+        if len(crystal_systems) > self.MAX_CRYSTAL_SYSTEMS:
+            raise ValueError(
+                f"You have queried for {len(crystal_systems)} crystal systems, "
+                f"however {self.MAX_CRYSTAL_SYSTEMS} can be queried at most."
+            )
+
         spacegroup_numbers: list[int] = []
         if isinstance(spacegroup_number, str | int):
             spacegroup_numbers += (
@@ -227,8 +237,14 @@ def query(
                 )
             spacegroup_numbers += new_sgn
 
+        spacegroup_numbers = sorted(set(spacegroup_numbers))
+        if len(spacegroup_numbers) > self.MAX_SPACE_GROUPS:
+            raise ValueError(
+                f"You have queried for {len(spacegroup_numbers)} space groups, "
+                f"however {self.MAX_SPACE_GROUPS} can be queried at most."
+            )
+
         if len(spacegroup_numbers) > 0:
-            spacegroup_numbers = sorted(set(spacegroup_numbers))
             crit["symmetry.number"] = (
                 spacegroup_numbers[0]
                 if len(spacegroup_numbers) == 1

emmet-api/emmet/api/routes/materials/robocrys/query_operators.py

@@ -5,7 +5,7 @@
 
 class RoboTextSearchQuery(QueryOperator):
     """
-    Method to generate a robocrystallographer text search query
+    Method to generate a robocrystallographer text search query.
     """
 
     def query(
@@ -32,7 +32,7 @@ def query(
                         "path": "description",
                         "allowAnalyzedField": True,
                     },
-                    "sort": {"score": {"$meta": "searchScore"}, "description": 1},
+                    "sort": {"score": {"$meta": "searchScore"}, "material_id": 1},
                     "count": {"type": "total"},
                 }
             },

emmet-api/emmet/api/routes/materials/xas/resources.py

@@ -1,7 +1,7 @@
 from emmet.api.resource import ReadOnlyResource
 from emmet.core.xas import XASDoc
 
-from emmet.api.query_operator import PaginationQuery, SparseFieldsQuery
+from emmet.api.query_operator import PaginationQuery, SortQuery, SparseFieldsQuery
 from emmet.api.routes.materials.materials.query_operators import MultiMaterialIDQuery
 from emmet.api.routes.materials.materials.query_operators import (
     ElementsQuery,
@@ -12,6 +12,14 @@
 from emmet.api.routes.materials.xas.query_operators import XASQuery, XASIDQuery
 from emmet.api.core.settings import MAPISettings
 
+XAS_SORT_FIELDS = [
+    "material_id",
+    "absorbing_element",
+    "edge",
+    "spectrum_type",
+    "spectrum_id",
+]
+
 
 def xas_resource(xas_store):
     resource = ReadOnlyResource(
@@ -37,6 +45,7 @@ def xas_resource(xas_store):
                     "last_updated",
                 ],
             ),
+            SortQuery(fields=XAS_SORT_FIELDS, max_num=1),
         ],
         header_processor=GlobalHeaderProcessor(),
         tags=["Materials XAS"],

emmet-api/emmet/api/routes/molecules/summary/resources.py

@@ -2,8 +2,9 @@
 
 from emmet.api.query_operator import (
     PaginationQuery,
-    SparseFieldsQuery,
     NumericQuery,
+    SortQuery,
+    SparseFieldsQuery,
 )
 from emmet.api.resource import ReadOnlyResource
 from emmet.api.routes.molecules.molecules.query_operators import (
@@ -22,6 +23,14 @@
 
 timeout = MAPISettings().TIMEOUT
 
+MOLECULES_SUMMARY_SORT_FIELDS = [
+    "molecule_id",
+    "redox.NONE.electron_affinity",
+    "redox.NONE.ionization_energy",
+    "charge",
+    "spin_multiplicity",
+]
+
 
 def summary_resource(summary_store):
     resource = ReadOnlyResource(
@@ -43,6 +52,7 @@ def summary_resource(summary_store):
                     "nelements",
                 ],
             ),
+            SortQuery(fields=MOLECULES_SUMMARY_SORT_FIELDS, max_num=1),
             SparseFieldsQuery(MoleculeSummaryDoc, default_fields=["molecule_id"]),
         ],
         hint_scheme=SummaryHintScheme(),