nmdc-runtime 2.9.0__py3-none-any.whl → 2.11.0__py3-none-any.whl

nmdc_runtime/static/ORCID-iD_icon_vector.svg

@@ -0,0 +1,4 @@
+<svg width="32" height="32" fill="none" xmlns="http://www.w3.org/2000/svg">
+  <path fill-rule="evenodd" clip-rule="evenodd" d="M32 16c0 8.837-7.163 16-16 16-8.838 0-16-7.163-16-16C0 7.162 7.162 0 16 0c8.837 0 16 7.162 16 16Z" fill="#A6CE39"/>
+  <path fill-rule="evenodd" clip-rule="evenodd" d="M18.813 9.637h-5.45v13.9h5.474c4.555 0 7.35-3.378 7.35-6.95 0-1.635-.562-3.372-1.77-4.704-1.215-1.336-3.065-2.246-5.605-2.246ZM18.6 21.3h-2.813v-9.425H18.5c1.823 0 3.12.552 3.96 1.4.842.849 1.252 2.021 1.252 3.312 0 .784-.239 1.967-.993 2.948-.745.969-2.01 1.765-4.119 1.765Zm5.311-4.026c-.251 1.74-1.494 4.276-5.311 4.276h-3.063H18.6c3.817 0 5.06-2.536 5.311-4.276Zm1.812-2.405c-.657-2.601-2.85-4.982-6.91-4.982h-5.2 5.2c4.06 0 6.253 2.38 6.91 4.982Zm.215 1.718ZM8.363 9.675v13.887h2.425V9.675H8.363Zm2.175 13.637H8.612h1.925ZM9.575 8.65c.84 0 1.513-.689 1.513-1.513 0-.823-.673-1.512-1.513-1.512-.838 0-1.512.674-1.512 1.513 0 .823.672 1.512 1.512 1.512Z" fill="#fff"/>
+</svg>

nmdc_runtime/static/README.md

@@ -0,0 +1,5 @@
+# Static
+
+This document contains information about the origins of the other files in this directory.
+
+- `ORCID-iD_icon_vector.svg`: On September 27, 2025, we downloaded this SVG file from ORCID's [Brand Library](https://orcid.filecamp.com/s/o/3CCuLloCl73Knntn/VU19wHSMUnX9TD4R), which we found a link to on the [Brand Guidelines](https://info.orcid.org/brand-guidelines/) page of ORCID's website.

nmdc_runtime/util.py

@@ -2,6 +2,7 @@ import json
 import mimetypes
 import os
 import pkgutil
+from collections import defaultdict
 from collections.abc import Iterable
 from copy import deepcopy
 from datetime import datetime, timezone
@@ -13,13 +14,16 @@ from typing import Callable, List, Optional, Set, Dict
 
 import fastjsonschema
 import requests
+from bson.son import SON
 from frozendict import frozendict
-from linkml_runtime import linkml_model
-from linkml_runtime.utils.schemaview import SchemaView
+from linkml_runtime import SchemaView
 from nmdc_schema.get_nmdc_view import ViewGetter
 from pymongo.database import Database as MongoDatabase
 from pymongo.errors import OperationFailure
-from refscan.lib.helpers import identify_references
+from refscan.lib.helpers import (
+    identify_references,
+    get_collection_name_to_class_names_map,
+)
 from refscan.lib.ReferenceList import ReferenceList
 from toolz import merge
 
@@ -27,48 +31,6 @@ from nmdc_runtime.api.core.util import sha256hash_from_file
 from nmdc_runtime.api.models.object import DrsObjectIn
 
 
-def get_names_of_classes_in_effective_range_of_slot(
-    schema_view: SchemaView, slot_definition: linkml_model.SlotDefinition
-) -> List[str]:
-    r"""
-    Determine the slot's "effective" range, by taking into account its `any_of` constraints (if defined).
-
-    Note: The `any_of` constraints constrain the slot's "effective" range beyond that described by the
-          induced slot definition's `range` attribute. `SchemaView` does not seem to provide the result
-          of applying those additional constraints, so we do it manually here (if any are defined).
-          Reference: https://github.com/orgs/linkml/discussions/2101#discussion-6625646
-
-    Reference: https://linkml.io/linkml-model/latest/docs/any_of/
-    """
-
-    # Initialize the list to be empty.
-    names_of_eligible_target_classes = []
-
-    # If the `any_of` constraint is defined on this slot, use that instead of the `range`.
-    if "any_of" in slot_definition and len(slot_definition.any_of) > 0:
-        for slot_expression in slot_definition.any_of:
-            # Use the slot expression's `range` to get the specified eligible class name
-            # and the names of all classes that inherit from that eligible class.
-            if slot_expression.range in schema_view.all_classes():
-                own_and_descendant_class_names = schema_view.class_descendants(
-                    slot_expression.range
-                )
-                names_of_eligible_target_classes.extend(own_and_descendant_class_names)
-    else:
-        # Use the slot's `range` to get the specified eligible class name
-        # and the names of all classes that inherit from that eligible class.
-        if slot_definition.range in schema_view.all_classes():
-            own_and_descendant_class_names = schema_view.class_descendants(
-                slot_definition.range
-            )
-            names_of_eligible_target_classes.extend(own_and_descendant_class_names)
-
-    # Remove duplicate class names.
-    names_of_eligible_target_classes = list(set(names_of_eligible_target_classes))
-
-    return names_of_eligible_target_classes
-
-
 def get_class_names_from_collection_spec(
     spec: dict, prefix: Optional[str] = None
 ) -> List[str]:
@@ -324,9 +286,9 @@ def find_one(k_v: dict, entities: Iterable[dict]):
     """Find the first entity with key-value pair k_v, if any?
 
     >>> find_one({"id": "foo"}, [{"id": "foo"}])
+    {'id': 'foo'}
+    >>> find_one({"id": "foo"}, [{"id": "bar"}]) is None
     True
-    >>> find_one({"id": "foo"}, [{"id": "bar"}])
-    False
     """
     if len(k_v) > 1:
         raise Exception("Supports only one key-value pair")
@@ -352,6 +314,32 @@ def nmdc_schema_view():
     return ViewGetter().get_view()
 
 
+@lru_cache
+def get_class_name_to_collection_names_map(
+    schema_view: SchemaView,
+) -> Dict[str, List[str]]:
+    """
+    Returns a mapping of class names to the names of the collections that can store instances of those classes/types,
+    according to the specified `SchemaView`.
+
+    Example output:
+    ```
+    {
+        "Study": ["study_set"],
+        "Biosample": ["biosample_set"],
+        ...
+    }
+    ```
+    """
+    class_name_to_collection_names = defaultdict(list)
+    for collection_name, class_names in get_collection_name_to_class_names_map(
+        schema_view
+    ).items():
+        for class_name in class_names:
+            class_name_to_collection_names[class_name].append(collection_name)
+    return class_name_to_collection_names
+
+
 @lru_cache
 def nmdc_database_collection_instance_class_names():
     names = []
@@ -370,7 +358,7 @@ def nmdc_database_collection_names():
     TODO: Document this function.
 
     TODO: Assuming this function was designed to return a list of names of all Database slots that represents database
-          collections, use the function named `get_collection_names_from_schema` in `nmdc_runtime/api/db/mongo.py`
+          collections, import/use the function named `get_collection_names_from_schema` from `refscan.lib.helpers`
           instead, since (a) it includes documentation and (b) it performs the additional checks the lead schema
           maintainer expects (e.g. checking whether a slot is `multivalued` and `inlined_as_list`).
     """
@@ -406,6 +394,12 @@ def all_docs_have_unique_id(coll) -> bool:
 
 
 def specialize_activity_set_docs(docs):
+    """
+    TODO: Document this function.
+
+    TODO: Check whether this function is still necessary, given that the `Database` class
+          in `nmdc-schema` does not have a slot named `activity_set`.
+    """
     validation_errors = {}
     type_collections = get_type_collections()
     if "activity_set" in docs:
@@ -489,6 +483,49 @@ def populated_schema_collection_names_with_id_field(mdb: MongoDatabase) -> List[
     return [n for n in collection_names if mdb[n].find_one({"id": {"$exists": True}})]
 
 
+def does_collection_have_unique_index_on_id_field(
+    collection_name: str, db: MongoDatabase
+) -> bool:
+    """Check whether the specified MongoDB collection has a unique index on its `id` field (not `_id`).
+
+    Note: If the specified MongoDB collection either does not exist or is a _view_ instead of a collection,
+          this function will return `False`.
+
+    References:
+    - https://pymongo.readthedocs.io/en/stable/api/pymongo/collection.html#pymongo.collection.Collection.list_indexes
+    - https://pymongo.readthedocs.io/en/stable/api/pymongo/collection.html#pymongo.collection.Collection.index_information
+    """
+    # Check whether the specified collection actually exists in the database; and, if it does,
+    # whether it is really a _collection_ (as opposed to being a _view_). If it doesn't exist,
+    # or it is a view, return `False` right away.
+    collection_infos_cursor = db.list_collections(filter={"name": collection_name})
+    collection_infos = list(collection_infos_cursor)
+    if len(collection_infos) == 0:
+        return False
+    collection_info = collection_infos[0]
+    if collection_info["type"] != "collection":
+        return False
+
+    # Now that we know we're dealing with a collection, get information about each of its indexes.
+    collection = db.get_collection(collection_name)
+    for index_information in collection.list_indexes():
+        # Get the "field_name-direction" pairs that make up this index.
+        field_name_and_direction_pairs: SON = index_information["key"]
+
+        # If this index involves a number of fields other than one, skip it.
+        # We're only interested in indexes that involve the `id` field by itself.
+        if len(field_name_and_direction_pairs.keys()) != 1:
+            continue
+
+        # Check whether the field this index involves is the `id` field,
+        # and whether this index is `unique`.
+        field_name = list(field_name_and_direction_pairs.keys())[0]
+        if field_name == "id" and index_information.get("unique", False):
+            return True
+
+    return False
+
+
 def ensure_unique_id_indexes(mdb: MongoDatabase):
     """Ensure that any collections with an "id" field have an index on "id"."""
 
@@ -503,6 +540,11 @@ def ensure_unique_id_indexes(mdb: MongoDatabase):
         if collection_name.startswith("system."):  # reserved by mongodb
             continue
 
+        # If the collection already has a unique index on `id`, there's no need
+        # to check anything else about the collection.
+        if does_collection_have_unique_index_on_id_field(collection_name, mdb):
+            continue
+
         if (
             collection_name in schema_collection_names_with_id_field()
             or all_docs_have_unique_id(mdb[collection_name])

nmdc_runtime-2.11.0.dist-info/METADATA

@@ -0,0 +1,46 @@
+Metadata-Version: 2.4
+Name: nmdc-runtime
+Version: 2.11.0
+Summary: A runtime system for NMDC data management and orchestration
+Project-URL: Changelog, https://github.com/microbiomedata/nmdc-runtime/releases
+Project-URL: Documentation, https://docs.microbiomedata.org/runtime
+Project-URL: Issues, https://github.com/microbiomedata/nmdc-runtime/issues
+Project-URL: Repository, https://github.com/microbiomedata/nmdc-runtime
+License-File: LICENSE
+Requires-Python: >=3.10
+Requires-Dist: base32-lib
+Requires-Dist: boto3
+Requires-Dist: click
+Requires-Dist: dagit
+Requires-Dist: dagster
+Requires-Dist: dagster-graphql
+Requires-Dist: dagster-postgres
+Requires-Dist: fastapi>=0.115.0
+Requires-Dist: fastjsonschema
+Requires-Dist: frozendict
+Requires-Dist: git-root
+Requires-Dist: jq
+Requires-Dist: jsonasobj2
+Requires-Dist: linkml
+Requires-Dist: linkml-runtime
+Requires-Dist: lxml
+Requires-Dist: nmdc-schema==11.11.1
+Requires-Dist: ontology-loader==0.2.2
+Requires-Dist: pandas
+Requires-Dist: passlib[bcrypt]
+Requires-Dist: pydantic[email]>=1.10.0
+Requires-Dist: pyinstrument
+Requires-Dist: pymongo
+Requires-Dist: python-dotenv
+Requires-Dist: python-jose[cryptography]
+Requires-Dist: python-multipart>=0.0.18
+Requires-Dist: pyyaml
+Requires-Dist: refscan==0.3.2
+Requires-Dist: requests
+Requires-Dist: requests-cache
+Requires-Dist: scalar-fastapi<2.0.0,>=1.4.1
+Requires-Dist: tenacity
+Requires-Dist: toolz
+Requires-Dist: tqdm
+Requires-Dist: unidecode
+Requires-Dist: uvicorn[standard]

nmdc_runtime-2.11.0.dist-info/RECORD

@@ -0,0 +1,128 @@
+nmdc_runtime/Dockerfile,sha256=3CyLW_4PRP-8cpwJHAiP4u_n736de-TJmi0dcVXbP1s,9257
+nmdc_runtime/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nmdc_runtime/config.py,sha256=fVxcqdXv13Fa9CSRPnFIsfmvmlos8o4SFUZcmsXfX_8,2020
+nmdc_runtime/main.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nmdc_runtime/mongo_util.py,sha256=L6UxK_6f0wQw2NTKCUVKCp-QLhBudQczDLUdF5odbP8,2943
+nmdc_runtime/util.py,sha256=jHrpk79XHWgarOEzSP9nAsenu5zTV2PrkdIslDeQf8I,21071
+nmdc_runtime/api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nmdc_runtime/api/analytics.py,sha256=Vp-BYQZ_sqR282FLLkGUoxlieSqyXxU0DmMvjDzMVsI,3723
+nmdc_runtime/api/entrypoint.sh,sha256=y3lZU2xPnZ3cAVK7tn0Nw-qVGElryt9fzj1IaZ5kkGw,209
+nmdc_runtime/api/main.py,sha256=WnpM-abWDLbxj5mT116UO_45xiO7ec0LQ2ZhGdZhE78,16649
+nmdc_runtime/api/middleware.py,sha256=GUVN26Ym9H87gaxrBs0NAMpOoA7qQfv-7UnIJOkcQkI,1703
+nmdc_runtime/api/openapi.py,sha256=8E522L6zvhtfM_-eyTNE_Z7EwVvLQh54QUhvvSO5bj0,10159
+nmdc_runtime/api/boot/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nmdc_runtime/api/boot/capabilities.py,sha256=9Cp_yULUeEXN7Nz-WC5XJXTaB7fhOWOCGp8mx050qgg,291
+nmdc_runtime/api/boot/object_types.py,sha256=JL6OZw34lKkbKJJXDIiswfLmn1tkOng4ZKF6ypqWKhs,4382
+nmdc_runtime/api/boot/triggers.py,sha256=fLM588CBYft_no1ENN13XSO6Cj4DB90ZKJl-1UgfsYw,2723
+nmdc_runtime/api/boot/workflows.py,sha256=UpOAMjVKagat-PCKPx7HuriLTnCbhj0EVgpk7UuLpQQ,3826
+nmdc_runtime/api/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nmdc_runtime/api/core/auth.py,sha256=c38EjN3Ckd3uuR70qqTiAKF3EedZCihoVvTKBmBSRMQ,7453
+nmdc_runtime/api/core/idgen.py,sha256=ru9nAczRAEp1Koq8yXLCMdkN39dNvfTrIwWwVI2SeWo,8101
+nmdc_runtime/api/core/metadata.py,sha256=AMX-EWfyOU_xobIlDf98PTQLuNCbZuyCPCIELKAoMIk,27943
+nmdc_runtime/api/core/util.py,sha256=OGE9kCui-wEfkfdUeUOBNeqmHJ5fNpJepBo0ivYkMnE,3232
+nmdc_runtime/api/db/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nmdc_runtime/api/db/mongo.py,sha256=9TfgCTvAmaKp6C7a9AkUTqkYTMYYzyM4na2Ying2ip0,19988
+nmdc_runtime/api/db/s3.py,sha256=tRFEjjVXHMiUdZtRiq1ImvLza2s86TkgubDw3kchDOA,1046
+nmdc_runtime/api/endpoints/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nmdc_runtime/api/endpoints/capabilities.py,sha256=AkSh8wcsVSOkkjH0kzcM2TcO2o8AuKyXGt1km_VgwVs,717
+nmdc_runtime/api/endpoints/find.py,sha256=AimO1vgq2DlO17yrPa1QCkEzZDbxyIBFxd09cTGbcOE,27063
+nmdc_runtime/api/endpoints/jobs.py,sha256=waQk3A7gGIqcr2GNNX988Bxbvx5bxq-kGKmWXeNBrpY,5010
+nmdc_runtime/api/endpoints/metadata.py,sha256=Msj7k5DxXUzXCZWcvy91T7AIFj1chhn_53Dsc44_qmc,9886
+nmdc_runtime/api/endpoints/nmdcschema.py,sha256=-bP9vL_CglQXwSC_5mO8zf4AOlehM_8mmn0ksEFZkOk,20515
+nmdc_runtime/api/endpoints/object_types.py,sha256=dTbl3A9j9lyk186arA7cszTEKOY7vXWJO_aKYfFAV8s,1179
+nmdc_runtime/api/endpoints/objects.py,sha256=J9cJENV8hfHjGAszft2j15OqAxDmrKhtsfJmEYHdpdE,10380
+nmdc_runtime/api/endpoints/operations.py,sha256=iWDGoxa2w5k9tHaW0V_o6IjZZipUJqyY3OiCiYCBluA,2542
+nmdc_runtime/api/endpoints/queries.py,sha256=2e3XiIH1dNULF42g3JHw-s0heRIjpe2rsBuIb4XhIb0,29716
+nmdc_runtime/api/endpoints/runs.py,sha256=PWoEKCFQhWgpWklmRUjTc0UZCvDAa1i59gnPhAcZirA,3326
+nmdc_runtime/api/endpoints/search.py,sha256=_h30mu8_Xndjggg3IllMDn5h8k92BX0ubxqRO85R0Ss,1187
+nmdc_runtime/api/endpoints/sites.py,sha256=Cju6x1Trb25cZMc7BjumupVbpJleDf8Y3bVeuuxR4NE,6565
+nmdc_runtime/api/endpoints/triggers.py,sha256=1DG2oEOV7zu5bT2qoeHrLNajY6K6sEGi7O7po3Bcmbk,673
+nmdc_runtime/api/endpoints/users.py,sha256=syu_Tz05k-OAsDMhe125ofqeiCkmDMjdbRlfvRZ5_rI,7816
+nmdc_runtime/api/endpoints/util.py,sha256=gNRIFNxBBDxY-qMBnr8F8qjhkNYxJTy_IN0JQkU5wp4,28393
+nmdc_runtime/api/endpoints/workflows.py,sha256=HWTnt-yrHp2DcrQT8BS_-SRQWNibkKNPVOpwqjS9QCA,14383
+nmdc_runtime/api/endpoints/lib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nmdc_runtime/api/endpoints/lib/helpers.py,sha256=E6pH0NtzKiSGBgIfoeukH5qeHKtxjLtCvw4F8LOacTQ,13874
+nmdc_runtime/api/endpoints/lib/linked_instances.py,sha256=eGBStkzI4bNHqFi1wILQ0JtfolC3h1dFWd8zGDeXdXY,7226
+nmdc_runtime/api/endpoints/lib/path_segments.py,sha256=4nIy_KrYvTc80Np3ELnT94VCk2QfR-2055fMlcbBSPw,5724
+nmdc_runtime/api/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nmdc_runtime/api/models/capability.py,sha256=4__rqgLS4MCMjbaCM3e_ncR9KW001Klm34p2t_bp65k,262
+nmdc_runtime/api/models/id.py,sha256=D8kDS-f3-OIxaNKrkhrdvyxu90ac4SDeFpVHboycDac,2724
+nmdc_runtime/api/models/job.py,sha256=GrmGDlw7qJS8FCz4Z5PvC2U5LcwC_DZXvTYAmEOSI4g,755
+nmdc_runtime/api/models/metadata.py,sha256=mVCC0KODtKzNEYABk70jaKVoOTyZP87eCtzf96lgysw,196
+nmdc_runtime/api/models/minter.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nmdc_runtime/api/models/nmdc_schema.py,sha256=C-Jb_eHr4dSVoYP-r7ldBUW-JHhCqSMtxSMT9HWKZ70,5768
+nmdc_runtime/api/models/object.py,sha256=A-U5RkWfmEsb50x9ai5xdpHo9xy-O9mZj2gKCoBR87E,5004
+nmdc_runtime/api/models/object_type.py,sha256=2Ejn5iCbqwqVEaOcYo4mvUJgBTDMhlmw8cLD92bWwSE,399
+nmdc_runtime/api/models/operation.py,sha256=Nb_Ys8P_vdxL-5fcKTeNTmB9CongxK3-JWs0vhgkNq8,1606
+nmdc_runtime/api/models/query.py,sha256=899fPzA55xyskflLXQKlIADQATsnpl8-Pu5rhrE7MvA,6739
+nmdc_runtime/api/models/query_continuation.py,sha256=bWVX7ijk34kOCedxAWFGgSTNgpy98yp0IZni31oD3-Y,4150
+nmdc_runtime/api/models/run.py,sha256=OhWBc6lQeEM-GSgUpvJCE2xbZQzv8kdPsEkWlL0xolM,4406
+nmdc_runtime/api/models/site.py,sha256=KLLgln2KJrinUDp6ixxci1JFmcLAL4O4vEtFTZKc82U,2310
+nmdc_runtime/api/models/trigger.py,sha256=TviQMk9-2HMZgCiaXYAF0WFnjD295jxnJLJCWsmtem4,201
+nmdc_runtime/api/models/user.py,sha256=R_K7f2Zaajo8-gCwKwu4Ytfg063v31Yb5xQSIH_iYxw,4083
+nmdc_runtime/api/models/util.py,sha256=koEyCBqizwHr-fzjoD_OJCN0c1n5apd3bVYdU-YWRvM,11659
+nmdc_runtime/api/models/workflow.py,sha256=etPFP_L9DcRoIAFwvMYzLLT2WlwRG6T68-7tzNzXnQ0,326
+nmdc_runtime/api/models/lib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nmdc_runtime/api/models/lib/helpers.py,sha256=k6AihKIiQ0kg2kk_qY_VNWTb96LGkazuztARhgjHr8M,2410
+nmdc_runtime/api/swagger_ui/swagger_ui.py,sha256=lGl4sF7MXsWbX7fiauDPKUOVSVag_WeH7ja5J_KBHg0,1887
+nmdc_runtime/api/swagger_ui/assets/custom-elements.js,sha256=0bxUleZpdRbjFB0t0Tmg3-ReGKfnK6r3bUGjr7zW5UQ,23972
+nmdc_runtime/api/swagger_ui/assets/script.js,sha256=tB7q6OxCLQOOd_-PMt1DjFnQgn3ticM8yemrpetZkQA,13536
+nmdc_runtime/api/swagger_ui/assets/style.css,sha256=BucritiMpu_UJdgSdDBImFpQHMQ2SaZzUd179gZ2Zx0,4565
+nmdc_runtime/minter/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nmdc_runtime/minter/bootstrap.py,sha256=5Ej6pJVBRryRIi0ZwEloY78Zky7iE2okF6tPwRI2axM,822
+nmdc_runtime/minter/config.py,sha256=-E1kQXTDraabrN4CENuVCHcNJafjVdiHWeUrucxBzMQ,2741
+nmdc_runtime/minter/adapters/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nmdc_runtime/minter/adapters/repository.py,sha256=CVVRdGclIDBgbqaOSmSl7OkOSE43kt6zJpE-etXIkOs,9267
+nmdc_runtime/minter/domain/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nmdc_runtime/minter/domain/model.py,sha256=k1n3O3GYfhmFdjU_oHadVTeUIxORQf-VPW4Xy6S5SCQ,3599
+nmdc_runtime/minter/entrypoints/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nmdc_runtime/minter/entrypoints/fastapi_app.py,sha256=I_lgExs6g1MRpMQdpedrnYdA1L7r_TBi4RiiD8ogrkM,4015
+nmdc_runtime/site/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nmdc_runtime/site/dagster.yaml,sha256=VCFx2naLjaNzP8AYr5uvzxRIf4fC0mHm7cctcYsVrNA,1204
+nmdc_runtime/site/entrypoint-daemon.sh,sha256=kTc9dQqzR0eQ9TBZcOeeYRXBOKRe05A1INRFes-z3hw,513
+nmdc_runtime/site/entrypoint-dagit-readonly.sh,sha256=ZY-K3l6apK8jA4mjcxePsjWb4_rh-WKz3CHmvvK_zj0,549
+nmdc_runtime/site/entrypoint-dagit.sh,sha256=TWEIAyKyCEMHX5XnbGLO0xdhYNgeXsxgs1GFnr2Avms,537
+nmdc_runtime/site/graphs.py,sha256=KeC6SKFNUW6SGubruFRrZsfBRN6tUfc3tp6tEst8bMU,17910
+nmdc_runtime/site/ops.py,sha256=RainLCYEvgglHqgwJWdHu4C15W3DxKOx428vxZSIK_Q,62974
+nmdc_runtime/site/repository.py,sha256=Kcdt293K1irWcmw7R9L-5sTEBhdoaIdgdM0mgFNrMMc,44117
+nmdc_runtime/site/resources.py,sha256=474u5BvwKubW-oMlQNTXQ9nJTh8dU-Sr_L9k7VhYt_s,20756
+nmdc_runtime/site/util.py,sha256=4h0X_fhjf3HdX6XDR8GvHgkrpxQY4OnZVtaOeXJVxJQ,1935
+nmdc_runtime/site/workspace.yaml,sha256=RCw5i-v0T9MWuEZE-y1vEIJz6x2bpm1fyxheLxLEVLk,431
+nmdc_runtime/site/backup/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nmdc_runtime/site/backup/nmdcdb_mongodump.py,sha256=My2ORKVIk_Z9wzfnIuamDe3_hv4viid9ToSJDC5J4mY,2689
+nmdc_runtime/site/backup/nmdcdb_mongoexport.py,sha256=y1x3B4-qxF5_itXOKYaix99OvDhW_PYxhLoLc4Y5E1M,4028
+nmdc_runtime/site/backup/nmdcdb_mongoimport.py,sha256=k6w5yscMNYoMBVkaAA9soWS0Dj2CB0FRBSFlifRO3Ro,1739
+nmdc_runtime/site/changesheets/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nmdc_runtime/site/changesheets/base.py,sha256=lZT6WCsEBl-FsTr7Ki8_ploT93uMiVyIWWKM36aOrRk,3171
+nmdc_runtime/site/changesheets/data/OmicsProcessing-to-catted-Biosamples.tsv,sha256=lfAaAhnEOBbXoGmGhVoxbbJRnUOLDtWrF6ycAOtsJFg,128790
+nmdc_runtime/site/changesheets/scripts/missing_neon_soils_ecosystem_data.py,sha256=w7025ohUmoWxYHAl4zTFaV_Ig-CWkeeiZGlEs2J57mc,11628
+nmdc_runtime/site/changesheets/scripts/neon_soils_add_ncbi_ids.py,sha256=OfaVAlhtd7DbH3Y5jHMGnDgOobWel4FnL3tP5BGJqaA,7969
+nmdc_runtime/site/export/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nmdc_runtime/site/export/ncbi_xml.py,sha256=kDRIv_0eeXfXlpTmK6PbvQYHd1bS69fa3RfE5XpLeIM,54933
+nmdc_runtime/site/export/ncbi_xml_utils.py,sha256=HkE3Iufoqe-9rc6gOVVaqxpz7j98O5idL027w624UwA,15423
+nmdc_runtime/site/export/study_metadata.py,sha256=yR5pXL6JG8d7cAtqcF-60Hp7bLD3dJ0Rut4AtYc0tXA,4844
+nmdc_runtime/site/normalization/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nmdc_runtime/site/normalization/gold.py,sha256=iISDD4qs4d6uLhv631WYNeQVOzY5DO201ZpPtxHdkVk,1311
+nmdc_runtime/site/repair/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nmdc_runtime/site/repair/database_updater.py,sha256=a6POYZcLEl0JvnuWxPjaOJtwZjkJhhvvUg1ABhnBiP8,21268
+nmdc_runtime/site/translation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nmdc_runtime/site/translation/gold_translator.py,sha256=4AFgbJtHaVwme3a57Y6Foi-uzI8oBHUlOt3Ns7_a5_o,32879
+nmdc_runtime/site/translation/neon_benthic_translator.py,sha256=CMoC56ymA0DKPkzqdMR4m5yYV6EcyH3tOvOiA3P6goE,23762
+nmdc_runtime/site/translation/neon_soil_translator.py,sha256=MMntFXwK62PdPNGpurTq5L3-pct7xAmUymRE2QqMPso,38572
+nmdc_runtime/site/translation/neon_surface_water_translator.py,sha256=_-KDZzC30dQ1y57lXEKWXE6ZfGozNHxGFvbGaj4f0Lg,30536
+nmdc_runtime/site/translation/neon_utils.py,sha256=d00o7duKKugpLHmsEifNbp4WjeC4GOqcgw0b5qlCg4I,5549
+nmdc_runtime/site/translation/submission_portal_translator.py,sha256=351ZfV-SleRAlKEufntP68xYl_oE4b-SeFnHgMpoB1g,45284
+nmdc_runtime/site/translation/translator.py,sha256=kVmDIVfxQ0ry6obAc_SyvlEcPwPCupYeKenRylZWWbI,3643
+nmdc_runtime/site/validation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nmdc_runtime/site/validation/emsl.py,sha256=OG20mv_3E2rkQqTQtYO0_SVRqFb-Z_zKCiAVbty6Wl0,671
+nmdc_runtime/site/validation/gold.py,sha256=Z5ZzYdjERbrJ2Tu06d0TDTBSfwaFdL1Z23Rl-YkZ2Ow,803
+nmdc_runtime/site/validation/util.py,sha256=Fz3c7dOEKOiYXssitYb50uUI1yRx3wJzFBl0s95Za7s,3632
+nmdc_runtime/static/NMDC_logo.svg,sha256=-13FrhQMWOg7FMprd3p6dwSOEf8xWkrHJB_P-nxGvLw,40570
+nmdc_runtime/static/ORCID-iD_icon_vector.svg,sha256=JOKAW7lAn7Giws6aS_jBQGYG4DoPUBQ5S5mgmCSwmcA,973
+nmdc_runtime/static/README.md,sha256=g0fitEFvZfBcSWzgjOxzDdfouBlq95xFKpAag0VPzL4,397
+nmdc_runtime/static/favicon.ico,sha256=FsOefOmgCU9fp2f1FxKimZ8zHg7mBYj_Cv70S5VIcuI,15086
+nmdc_runtime-2.11.0.dist-info/METADATA,sha256=_lp2sVUd9rtPOgYgMSkF6TOgmIDSV9pT-mhr8hGtjTg,1470
+nmdc_runtime-2.11.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+nmdc_runtime-2.11.0.dist-info/entry_points.txt,sha256=JxdvOnvxHK_8046cwlvE30s_fV0-k-eTpQtkKYA69nQ,224
+nmdc_runtime-2.11.0.dist-info/licenses/LICENSE,sha256=VWiv65r7gHGjgtr3jMJYVmQny5GRpQ6H-W9sScb1x70,2408
+nmdc_runtime-2.11.0.dist-info/RECORD,,

{nmdc_runtime-2.9.0.dist-info → nmdc_runtime-2.11.0.dist-info}/WHEEL

@@ -1,5 +1,4 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.9.0)
+Generator: hatchling 1.27.0
 Root-Is-Purelib: true
 Tag: py3-none-any
-

nmdc_runtime/containers.py

@@ -1,14 +0,0 @@
-"""Containers module."""
-
-from dependency_injector import containers, providers
-
-from nmdc_runtime.domain.users.userService import UserService
-from nmdc_runtime.infrastructure.database.impl.mongo.models.user import (
-    UserQueries,
-)
-
-
-class Container(containers.DeclarativeContainer):
-    user_queries = providers.Singleton(UserQueries)
-
-    user_service = providers.Factory(UserService, user_queries=user_queries)

nmdc_runtime/core/db/Database.py

@@ -1,15 +0,0 @@
-from contextlib import contextmanager, AbstractContextManager
-from typing import Callable
-import logging
-
-from motor import motor_asyncio
-
-
-class Database:
-    def __init__(self, db_url: str) -> None:
-        self._client = motor_asyncio.AsyncIOMotorClient(db_url)
-        self._db = self._client["database"]
-
-    @contextmanager
-    def session(self):
-        return self._db

nmdc_runtime/core/exceptions/__init__.py

@@ -1,23 +0,0 @@
-from .base import (
-    CustomException,
-    BadRequestException,
-    NotFoundException,
-    ForbiddenException,
-    UnprocessableEntity,
-    DuplicateValueException,
-    UnauthorizedException,
-)
-from .token import DecodeTokenException, ExpiredTokenException
-
-
-__all__ = [
-    "CustomException",
-    "BadRequestException",
-    "NotFoundException",
-    "ForbiddenException",
-    "UnprocessableEntity",
-    "DuplicateValueException",
-    "UnauthorizedException",
-    "DecodeTokenException",
-    "ExpiredTokenException",
-]

nmdc_runtime/core/exceptions/base.py

@@ -1,47 +0,0 @@
-from http import HTTPStatus
-
-
-class CustomException(Exception):
-    code = HTTPStatus.BAD_GATEWAY
-    error_code = HTTPStatus.BAD_GATEWAY
-    message = HTTPStatus.BAD_GATEWAY.description
-
-    def __init__(self, message=None):
-        if message:
-            self.message = message
-
-
-class BadRequestException(CustomException):
-    code = HTTPStatus.BAD_REQUEST
-    error_code = HTTPStatus.BAD_REQUEST
-    message = HTTPStatus.BAD_REQUEST.description
-
-
-class NotFoundException(CustomException):
-    code = HTTPStatus.NOT_FOUND
-    error_code = HTTPStatus.NOT_FOUND
-    message = HTTPStatus.NOT_FOUND.description
-
-
-class ForbiddenException(CustomException):
-    code = HTTPStatus.FORBIDDEN
-    error_code = HTTPStatus.FORBIDDEN
-    message = HTTPStatus.FORBIDDEN.description
-
-
-class UnauthorizedException(CustomException):
-    code = HTTPStatus.UNAUTHORIZED
-    error_code = HTTPStatus.UNAUTHORIZED
-    message = HTTPStatus.UNAUTHORIZED.description
-
-
-class UnprocessableEntity(CustomException):
-    code = HTTPStatus.UNPROCESSABLE_ENTITY
-    error_code = HTTPStatus.UNPROCESSABLE_ENTITY
-    message = HTTPStatus.UNPROCESSABLE_ENTITY.description
-
-
-class DuplicateValueException(CustomException):
-    code = HTTPStatus.UNPROCESSABLE_ENTITY
-    error_code = HTTPStatus.UNPROCESSABLE_ENTITY
-    message = HTTPStatus.UNPROCESSABLE_ENTITY.description

nmdc_runtime/core/exceptions/token.py

@@ -1,13 +0,0 @@
-from nmdc_runtime.core.exceptions import CustomException
-
-
-class DecodeTokenException(CustomException):
-    code = 400
-    error_code = 10000
-    message = "token decode error"
-
-
-class ExpiredTokenException(CustomException):
-    code = 400
-    error_code = 10001
-    message = "expired token"

nmdc_runtime/domain/users/queriesInterface.py

@@ -1,18 +0,0 @@
-from __future__ import annotations
-from abc import ABC
-
-from abc import abstractmethod
-
-from nmdc_runtime.domain.users.userSchema import UserAuth, UserUpdate, UserOut
-
-
-class IUserQueries(ABC):
-    @abstractmethod
-    async def create(self, user: UserAuth) -> UserOut:
-        """Create new user"""
-        raise NotImplementedError
-
-    @abstractmethod
-    async def update(self, user: UserUpdate) -> UserOut:
-        """Update user data"""
-        raise NotImplementedError

nmdc_runtime/domain/users/userSchema.py

@@ -1,37 +0,0 @@
-from typing import Optional, List
-
-
-from pydantic import BaseModel, EmailStr
-
-
-class UserBase(BaseModel):
-    username: Optional[str] = None
-    email: Optional[str] = None
-    full_name: Optional[str] = None
-    site_admin: Optional[List[str]] = []
-    disabled: Optional[bool] = False
-
-
-class UserAuth(UserBase):
-    """User register and login auth"""
-
-    username: str
-    password: str
-
-
-# Properties to receive via API on update
-class UserUpdate(UserBase):
-    """Updatable user fields"""
-
-    email: Optional[EmailStr] = None
-
-    # User information
-    full_name: Optional[str] = None
-    password: Optional[str] = None
-
-
-class UserOut(UserUpdate):
-    """User fields pushed to the client"""
-
-    email: EmailStr
-    disabled: Optional[bool] = False

nmdc_runtime/domain/users/userService.py

@@ -1,14 +0,0 @@
-from typing import Any
-
-from nmdc_runtime.domain.users.userSchema import UserAuth, UserUpdate, UserOut
-
-
-class UserService:
-    def __init__(self, user_queries: Any) -> None:
-        self.__user_queries = user_queries
-
-    async def create_user(self, user: UserAuth) -> UserOut:
-        return await self.__user_queries.create(user)
-
-    async def update_user(self, username: str, new_user: UserUpdate) -> UserOut:
-        pass

nmdc_runtime/infrastructure/database/db.py

@@ -1,3 +0,0 @@
-"""
-Database initialization
-"""

nmdc_runtime/infrastructure/database/models/user.py

@@ -1,10 +0,0 @@
-from __future__ import annotations
-
-from abc import abstractmethod
-from typing import List
-
-from nmdc_runtime.domain.users.userSchema import (
-    UserAuth,
-    UserUpdate,
-    UserOut,
-)

nmdc_runtime/lib/__init__.py

@@ -1 +0,0 @@
-

nmdc_runtime/lib/extract_nmdc_data.py

@@ -1,41 +0,0 @@
-## author: Bill Duncan
-## summary: Contains methods for extracting data for the NMDC ETL pipeline.
-
-## system level modules
-import pandas as pds
-import jq
-import jsonasobj
-import json
-import zipfile
-import yaml
-from yaml import CLoader as Loader, CDumper as Dumper
-from dotted_dict import DottedDict
-from collections import namedtuple
-
-
-def extract_table(merged_df, table_name):
-    df = unpivot_dataframe(merged_df[merged_df.nmdc_data_source == table_name])
-    return df
-
-
-def unpivot_dataframe(
-    df,
-    index="nmdc_record_id",
-    columns="attribute",
-    value="value",
-    splice=["nmdc_record_id", "attribute", "value"],
-):
-    ## reshape eav structure to row-column structure
-    ## see: https://www.journaldev.com/33398/pandas-melt-unmelt-pivot-function
-    if len(splice) > 0:
-        df = df[splice].pivot(index=index, columns=columns)
-    else:
-        df = df.pivot(index=index, columns=columns)
-
-    if len(df) > 0:
-        df = df[value].reset_index()  # drop value hierarchical index
-    if len(df) > 0:
-        df = df.where(pds.notnull(df), None)  # replace an NaN values with None
-    df.columns.name = None  # remove column name attribute
-
-    return df