mp-api 0.46.2rc10__tar.gz → 0.46.2rc12__tar.gz

{mp_api-0.46.2rc10 → mp_api-0.46.2rc12}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mp-api
-Version: 0.46.2rc10
+Version: 0.46.2rc12
 Summary: API Client for the Materials Project
 Author-email: The Materials Project <feedback@materialsproject.org>
 License-Expression: BSD-3-Clause-LBNL

{mp_api-0.46.2rc10 → mp_api-0.46.2rc12}/mp_api/client/core/client.py

@@ -33,7 +33,7 @@ import requests
 from botocore import UNSIGNED
 from botocore.config import Config
 from botocore.exceptions import ClientError
-from deltalake import DeltaTable, QueryBuilder, convert_to_deltalake
+from deltalake import DeltaTable, QueryBuilder, Schema, convert_to_deltalake
 from emmet.core.arrow import arrowize
 from emmet.core.utils import jsanitize
 from pydantic import BaseModel
@@ -79,6 +79,13 @@ STATIC_COLLECTIONS = [
     "synth-descriptions",
     "xas",
 ]
+CONTROLLED_COLLECTIONS = [
+    "chemenv",
+    "materials",
+    "oxidation-states",
+    "summary",
+    "thermo",
+]
 
 hdlr = logging.StreamHandler()
 fmt = logging.Formatter("%(name)s - %(levelname)s - %(message)s")
@@ -683,6 +690,7 @@ class BaseRester(_Rester):
         bucket: str,
         prefix: str,
         access_controlled: bool = True,
+        versioned: bool = False,
         timeout: int | None = None,
         label: str | None = None,
     ) -> dict[str, Any]:
@@ -692,12 +700,16 @@ class BaseRester(_Rester):
             bucket (str) : S3 OpenData bucket
             prefix (str) : S3 object prefix
             access_controlled (bool): whether or not table has access controlled data
+            versioned (bool): whether or not table is partitioned on db version
             timeout (int or None) : timeout on getting access-controlled groups
             label (str or None) : label of the table in QueryBuilder
 
         Returns:
             dict of str to Any
         """
+        # just in case
+        prefix = prefix.rstrip("/")
+
         # Check if user has access to GNoMe
         # temp suppress tqdm
         re_enable = not self.mute_progress_bars
@@ -755,11 +767,15 @@ class BaseRester(_Rester):
         controlled_batch_str = ",".join(
             [f"'{tag}'" for tag in self.access_controlled_batch_ids]
         )
+        _coll = prefix.split("/")[-1]
+
+        if _coll == "tasks":
+            condition = f"batch_id NOT IN ({controlled_batch_str})"
+        else:
+            condition = "builder_meta.license != 'BY-NC'"
 
         predicate = (
-            f"WHERE batch_id NOT IN ({controlled_batch_str})"
-            if not has_gnome_access and controlled_batch_str and access_controlled
-            else ""
+            f"WHERE {condition}" if not has_gnome_access and access_controlled else ""
         )
         # TODO: do we need something like this?
         # predicate += f"{' AND ' if predicate else 'WHERE '}version='{self.db_version}'"
@@ -768,10 +784,13 @@ class BaseRester(_Rester):
         num_docs_needed: int = tbl.count()
 
         if not has_gnome_access:
+            mongo_predicate = (
+                {"batch_id_neq_any": self.access_controlled_batch_ids}
+                if _coll == "tasks"
+                else {"license": "BY-NC"}
+            )
             try:
-                num_docs_needed = self.count(
-                    {"batch_id_neq_any": self.access_controlled_batch_ids}
-                )
+                num_docs_needed = self.count(mongo_predicate)
             except MPRestError:
                 # batch_id isn't a valid field
                 num_docs_needed = self.count()
@@ -793,7 +812,12 @@ class BaseRester(_Rester):
 
         file_options = ds.ParquetFileFormat().make_write_options(compression="zstd")
 
-        def _flush(accumulator: list[pa.RecordBatch], group: int, schema: pa.Schema):
+        def _flush(
+            accumulator: list[pa.RecordBatch],
+            group: int,
+            schema: pa.Schema,
+            partitioning: pa.dataset.partitioning,
+        ):
             # somewhere post datafusion 51.0.0 and arrow-rs 57.0.0
             # casts to *View types began, need to cast back to base schema
             # -> pyarrow is behind on implementation support for *View types
@@ -807,6 +831,7 @@ class BaseRester(_Rester):
                 tbl,
                 base_dir=target_path,
                 format="parquet",
+                partitioning=partitioning,
                 basename_template=f"group-{group}-" + "part-{i}.zstd.parquet",
                 existing_data_behavior="overwrite_or_ignore",
                 max_rows_per_group=1024,
@@ -816,7 +841,18 @@ class BaseRester(_Rester):
         group = 1
         size = 0
         accumulator = []
-        schema = pa.schema(arrowize(self.document_model))
+        _schema = pa.schema(arrowize(self.document_model))
+        schema = (
+            _schema.insert(0, pa.field("version", pa.string()))
+            if versioned
+            else _schema
+        )
+        partitioning_schema = pa.schema([pa.field("version", pa.string())])
+        partitioning = (
+            pa.dataset.partitioning(partitioning_schema, flavor="hive")
+            if versioned
+            else None
+        )
         for page in iterator:
             # arro3 rb to pyarrow rb for compat w/ pyarrow ds writer
             rg = pa.record_batch(page)
@@ -828,13 +864,13 @@ class BaseRester(_Rester):
                 pbar.update(page_size)
 
             if size >= MAPI_CLIENT_SETTINGS.DATASET_FLUSH_THRESHOLD:
-                _flush(accumulator, group, schema)
+                _flush(accumulator, group, schema, partitioning)
                 group += 1
                 size = 0
                 accumulator.clear()
 
         if accumulator:
-            _flush(accumulator, group + 1, schema)
+            _flush(accumulator, group + 1, schema, partitioning)
 
         if pbar is not None:
             pbar.close()
@@ -842,7 +878,13 @@ class BaseRester(_Rester):
         logger.info(f"Dataset for {suffix} written to {target_path}")
         logger.info("Converting to DeltaTable...")
 
-        convert_to_deltalake(target_path)
+        delta_paritioning = Schema.from_arrow(partitioning_schema)
+
+        convert_to_deltalake(
+            target_path,
+            partition_by=delta_paritioning if versioned else None,
+            partition_strategy="hive" if versioned else None,
+        )
 
         logger.info(
             "Consult the delta-rs and pyarrow documentation for advanced usage: "
@@ -928,13 +970,15 @@ class BaseRester(_Rester):
                     suffix = self.suffix
                 elif self.suffix == "molecules/summary":
                     suffix = "molecules"
+                elif self.suffix == "molecules/jcesr":
+                    suffix = "jcesr"
                 else:
                     infix, suffix = self.suffix.split("/", 1)
                     suffix = infix if suffix == "core" else suffix
                     suffix = suffix.replace("_", "-")
 
                 if "tasks" in suffix:
-                    bucket_suffix, prefix = ("parsed", "core/tasks/")
+                    bucket_suffix, prefix = ("parsed", "core/tasks")
                 elif suffix in STATIC_COLLECTIONS:
                     bucket_suffix = "build"
                     prefix = f"static-collections/{suffix}"
@@ -946,9 +990,14 @@ class BaseRester(_Rester):
                 bucket = f"materialsproject-{bucket_suffix}"
 
                 if self.delta_backed:
-                    access_controlled = suffix not in STATIC_COLLECTIONS
+                    access_controlled = suffix in CONTROLLED_COLLECTIONS
+                    versioned = suffix != "tasks" and suffix not in STATIC_COLLECTIONS
                     return self._query_delta_backed(
-                        bucket, prefix, access_controlled, timeout=timeout
+                        bucket=bucket,
+                        prefix=prefix,
+                        access_controlled=access_controlled,
+                        versioned=versioned,
+                        timeout=timeout,
                     )
 
                 # Paginate over all entries in the bucket.

{mp_api-0.46.2rc10 → mp_api-0.46.2rc12}/mp_api/client/core/settings.py

@@ -21,7 +21,7 @@ _MUTE_PROGRESS_BAR = PMG_SETTINGS.get("MPRESTER_MUTE_PROGRESS_BARS", False)
 _MAX_LIST_LENGTH = min(PMG_SETTINGS.get("MPRESTER_MAX_LIST_LENGTH", 10000), 10000)
 
 _EMMET_SETTINGS = EmmetSettings()  # type: ignore[call-arg]
-_DEFAULT_ENDPOINT = "https://api-preview.materialsproject.org/"
+_DEFAULT_ENDPOINT = "https://api.materialsproject.org/"
 
 
 class MAPIClientSettings(BaseSettings):

{mp_api-0.46.2rc10 → mp_api-0.46.2rc12}/mp_api/client/routes/materials/materials.py

@@ -102,7 +102,7 @@ class MaterialsRester(CoreRester):
         Returns:
             ([MaterialsDoc], [dict]) List of material documents or dictionaries.
         """
-        query_params: dict = {"deprecated": deprecated}
+        query_params: dict = dict()
 
         if material_ids:
             if isinstance(material_ids, str):
@@ -163,6 +163,9 @@ class MaterialsRester(CoreRester):
             if query_params[entry] is not None
         }
 
+        if query_params:
+            query_params.update({"deprecated": deprecated})
+
         return super()._search(  # type: ignore[return-value]
             num_chunks=num_chunks,
             chunk_size=chunk_size,

{mp_api-0.46.2rc10 → mp_api-0.46.2rc12}/mp_api/client/routes/materials/phonon.py

@@ -89,8 +89,8 @@ class PhononRester(BaseRester):
             missing: list[str] = []
             found_material_ids: set[str] = set()
             for doc in summary_docs:
-                mid = str(doc["material_id"])
-                phonon_ids_by_method = doc.get("phonon_IDs") or {}
+                mid = str(doc["material_id"])  # type: ignore[arg-type, index]
+                phonon_ids_by_method = doc.get("phonon_IDs") or {}  # type: ignore[union-attr]
 
                 if phonon_method:
                     method_ids = phonon_ids_by_method.get(phonon_method) or []
@@ -215,13 +215,13 @@ class PhononRester(BaseRester):
                 f"No phonon bandstructure data found for material ID {material_id}."
             )
 
-        if phonon_method not in summary_doc[0]["phonon_IDs"]:
+        if phonon_method not in summary_doc[0]["phonon_IDs"]:  # type: ignore[arg-type, index]
             raise MPRestError(
                 f"No phonon bandstructure data found for material ID: {material_id} and phonon method: {phonon_method}."
             )
 
         return self.get_bandstructure_from_phonon_id(
-            summary_doc[0]["phonon_IDs"][phonon_method][0], phonon_method, pt
+            summary_doc[0]["phonon_IDs"][phonon_method][0], phonon_method, pt  # type: ignore[arg-type, index]
         )
 
     def get_dos_from_phonon_id(
@@ -280,13 +280,13 @@ class PhononRester(BaseRester):
                 f"No phonon dos data found for material ID {material_id}."
             )
 
-        if phonon_method not in summary_doc[0]["phonon_IDs"]:
+        if phonon_method not in summary_doc[0]["phonon_IDs"]:  # type: ignore[arg-type, index]
             raise MPRestError(
                 f"No phonon dos data found for material ID: {material_id} and phonon method: {phonon_method}."
             )
 
         return self.get_dos_from_phonon_id(
-            summary_doc[0]["phonon_IDs"][phonon_method][0], phonon_method
+            summary_doc[0]["phonon_IDs"][phonon_method][0], phonon_method  # type: ignore[arg-type, index]
         )
 
     def get_forceconstants_from_phonon_id(
@@ -344,20 +344,20 @@ class PhononRester(BaseRester):
                 f"No phonon force constants data found for material ID {material_id}."
             )
 
-        if phonon_method not in summary_doc[0]["phonon_IDs"]:
+        if phonon_method not in summary_doc[0]["phonon_IDs"]:  # type: ignore[arg-type, index]
             raise MPRestError(
                 f"No phonon force constants data found for material ID: {material_id} and phonon method: {phonon_method}."
             )
 
         return self.get_forceconstants_from_phonon_id(
-            summary_doc[0]["phonon_IDs"][phonon_method][0], phonon_method
+            summary_doc[0]["phonon_IDs"][phonon_method][0], phonon_method  # type: ignore[arg-type, index]
         )
 
     def compute_thermo_quantities(
         self,
-        identifier: str | None = None,
         material_id: str | None = None,
         phonon_method: str | None = None,
+        identifier: str | None = None,
     ):
         """Compute thermodynamical quantities for a given phonon ID or material ID and phonon_method.
 
@@ -392,12 +392,21 @@ class PhononRester(BaseRester):
                     raise MPRestError(
                         f"No phonon data found for material ID {material_id}."
                     )
-                if phonon_method not in summary_doc[0]["phonon_IDs"]:
+                if phonon_method not in summary_doc[0]["phonon_IDs"]:  # type: ignore[arg-type, index]
                     raise MPRestError(
                         f"No phonon data found for material ID: {material_id} and "
                         f"phonon method: {phonon_method}."
                     )
-                identifier = summary_doc[0]["phonon_IDs"][phonon_method][0]
+                identifier = summary_doc[0]["phonon_IDs"][phonon_method][0]  # type: ignore[arg-type, index]
+
+            if identifier is None or phonon_method is None:
+                suffix = (
+                    f" for {material_id=}" if material_id else f" for {identifier=}"
+                )
+                raise MPRestError(
+                    f"Could not resolve a phonon identifier or method{suffix} "
+                    f"({phonon_method=})."
+                )
 
             ph_dos = self.get_dos_from_phonon_id(identifier, phonon_method)
             docs = self.search(identifiers=identifier, phonon_method=phonon_method)
@@ -406,7 +415,7 @@ class PhononRester(BaseRester):
 
             self.use_document_model = True
             docs[0]["phonon_dos"] = ph_dos  # type: ignore[index]
-            doc = PhononBSDOSDoc(**docs[0])  # type: ignore[arg-type]
+            doc = PhononBSDOSDoc(**docs[0])  # type: ignore[arg-type, index]
         finally:
             self.use_document_model = use_document_model
         # below: same as numpy.linspace(0,800,100) but written out for mypy

{mp_api-0.46.2rc10 → mp_api-0.46.2rc12}/mp_api.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mp-api
-Version: 0.46.2rc10
+Version: 0.46.2rc12
 Summary: API Client for the Materials Project
 Author-email: The Materials Project <feedback@materialsproject.org>
 License-Expression: BSD-3-Clause-LBNL

{mp_api-0.46.2rc10 → mp_api-0.46.2rc12}/requirements/requirements-ubuntu-latest_py3.11.txt

@@ -12,9 +12,9 @@ bibtexparser==1.4.4
     # via pymatgen-core
 blake3==1.0.8
     # via emmet-core
-boto3==1.43.19
+boto3==1.43.24
     # via mp-api (pyproject.toml)
-botocore==1.43.19
+botocore==1.43.24
     # via
     #   boto3
     #   s3transfer
@@ -30,11 +30,11 @@ deltalake==1.5.1
     # via mp-api (pyproject.toml)
 deprecated==1.3.1
     # via deltalake
-emmet-core==0.87.0rc10
+emmet-core==0.87.0rc13
     # via mp-api (pyproject.toml)
 fonttools==4.63.0
     # via matplotlib
-idna==3.17
+idna==3.18
     # via requests
 inflect==7.5.0
     # via emmet-core
@@ -61,7 +61,7 @@ more-itertools==11.1.0
     # via inflect
 mpmath==1.3.0
     # via sympy
-narwhals==2.22.0
+narwhals==2.22.1
     # via plotly
 networkx==3.6.1
     # via pymatgen-core
@@ -89,7 +89,7 @@ pandas==3.0.3
     # via pymatgen-core
 pillow==12.2.0
     # via matplotlib
-plotly==6.7.0
+plotly==6.8.0
     # via pymatgen-core
 pubchempy==1.0.5
     # via emmet-core
@@ -149,7 +149,7 @@ sympy==1.14.0
     # via pymatgen-core
 tabulate==0.10.0
     # via pymatgen-core
-tqdm==4.67.3
+tqdm==4.68.1
     # via pymatgen-core
 typeguard==4.5.2
     # via inflect

{mp_api-0.46.2rc10 → mp_api-0.46.2rc12}/requirements/requirements-ubuntu-latest_py3.11_extras.txt

@@ -50,9 +50,9 @@ blinker==1.9.0
     # via flask
 boltons==25.0.0
     # via mp-api (pyproject.toml)
-boto3==1.43.19
+boto3==1.43.24
     # via mp-api (pyproject.toml)
-botocore==1.43.19
+botocore==1.43.24
     # via
     #   boto3
     #   s3transfer
@@ -103,7 +103,7 @@ deltalake==1.5.1
     # via mp-api (pyproject.toml)
 deprecated==1.3.1
     # via deltalake
-distlib==0.4.0
+distlib==0.4.1
     # via virtualenv
 dnspython==2.8.0
     # via
@@ -116,7 +116,7 @@ docutils==0.22.4
     # via sphinx
 email-validator==2.3.0
     # via pydantic
-emmet-core[all]==0.87.0rc10
+emmet-core[all]==0.87.0rc13
     # via mp-api (pyproject.toml)
 exceptiongroup==1.3.1
     # via fastmcp-slim
@@ -124,11 +124,11 @@ execnet==2.1.2
     # via pytest-xdist
 executing==2.2.1
     # via stack-data
-fastmcp==3.3.1
+fastmcp==3.4.1
     # via mp-api (pyproject.toml)
-fastmcp-slim[client,server]==3.3.1
+fastmcp-slim[client,server]==3.4.1
     # via fastmcp
-filelock==3.29.0
+filelock==3.29.1
     # via
     #   python-discovery
     #   virtualenv
@@ -164,7 +164,7 @@ httpx-sse==0.4.3
     # via mcp
 identify==2.6.19
     # via pre-commit
-idna==3.17
+idna==3.18
     # via
     #   anyio
     #   email-validator
@@ -183,7 +183,7 @@ inflect==7.5.0
     # via emmet-core
 iniconfig==2.3.0
     # via pytest
-ipython==9.14.0
+ipython==9.14.1
     # via mp-api (pyproject.toml)
 ipython-pygments-lexers==1.1.1
     # via ipython
@@ -215,8 +215,10 @@ joblib==1.5.3
     # via
     #   pymatgen-analysis-diffusion
     #   pymatgen-core
-joserfc==1.6.8
-    # via authlib
+joserfc==1.7.0
+    # via
+    #   authlib
+    #   fastmcp-slim
 json2html==1.3.0
     # via mp-api (pyproject.toml)
 jsonpointer==3.1.1
@@ -298,7 +300,7 @@ mypy-extensions==1.1.0
     # via
     #   mp-api (pyproject.toml)
     #   mypy
-narwhals==2.22.0
+narwhals==2.22.1
     # via plotly
 networkx==3.6.1
     # via
@@ -377,7 +379,7 @@ platformdirs==4.10.0
     #   pint
     #   python-discovery
     #   virtualenv
-plotly==6.7.0
+plotly==6.8.0
     # via pymatgen-core
 pluggy==1.6.0
     # via
@@ -502,7 +504,7 @@ python-dotenv==1.2.2
     # via
     #   fastmcp-slim
     #   pydantic-settings
-python-multipart==0.0.30
+python-multipart==0.0.32
     # via
     #   fastmcp-slim
     #   mcp
@@ -585,7 +587,7 @@ six==1.17.0
     #   bravado-core
     #   python-dateutil
     #   rfc3339-validator
-snowballstemmer==3.1.0
+snowballstemmer==3.1.1
     # via sphinx
 spglib==2.7.0
     # via
@@ -613,6 +615,7 @@ stack-data==0.6.3
     # via ipython
 starlette==1.2.1
     # via
+    #   fastmcp-slim
     #   mcp
     #   sse-starlette
 swagger-spec-validator==3.0.4
@@ -627,9 +630,9 @@ tabulate==0.10.0
     # via pymatgen-core
 tifffile==2026.3.3
     # via scikit-image
-tqdm==4.67.3
+tqdm==4.68.1
     # via pymatgen-core
-traitlets==5.15.0
+traitlets==5.15.1
     # via
     #   ipython
     #   matplotlib-inline
@@ -688,7 +691,7 @@ urllib3==2.7.0
     #   botocore
     #   requests
     #   types-requests
-uvicorn==0.48.0
+uvicorn==0.49.0
     # via
     #   fastmcp-slim
     #   mcp

{mp_api-0.46.2rc10 → mp_api-0.46.2rc12}/requirements/requirements-ubuntu-latest_py3.12.txt

@@ -12,9 +12,9 @@ bibtexparser==1.4.4
     # via pymatgen-core
 blake3==1.0.8
     # via emmet-core
-boto3==1.43.19
+boto3==1.43.24
     # via mp-api (pyproject.toml)
-botocore==1.43.19
+botocore==1.43.24
     # via
     #   boto3
     #   s3transfer
@@ -30,11 +30,11 @@ deltalake==1.5.1
     # via mp-api (pyproject.toml)
 deprecated==1.3.1
     # via deltalake
-emmet-core==0.87.0rc10
+emmet-core==0.87.0rc13
     # via mp-api (pyproject.toml)
 fonttools==4.63.0
     # via matplotlib
-idna==3.17
+idna==3.18
     # via requests
 inflect==7.5.0
     # via emmet-core
@@ -61,7 +61,7 @@ more-itertools==11.1.0
     # via inflect
 mpmath==1.3.0
     # via sympy
-narwhals==2.22.0
+narwhals==2.22.1
     # via plotly
 networkx==3.6.1
     # via pymatgen-core
@@ -89,7 +89,7 @@ pandas==3.0.3
     # via pymatgen-core
 pillow==12.2.0
     # via matplotlib
-plotly==6.7.0
+plotly==6.8.0
     # via pymatgen-core
 pubchempy==1.0.5
     # via emmet-core
@@ -149,7 +149,7 @@ sympy==1.14.0
     # via pymatgen-core
 tabulate==0.10.0
     # via pymatgen-core
-tqdm==4.67.3
+tqdm==4.68.1
     # via pymatgen-core
 typeguard==4.5.2
     # via inflect