nmdc-runtime 1.6.0__py3-none-any.whl → 1.8.0__py3-none-any.whl

nmdc_runtime/site/repository.py

@@ -42,6 +42,8 @@ from nmdc_runtime.site.graphs import (
     ingest_neon_soil_metadata,
     ingest_neon_benthic_metadata,
     ingest_neon_surface_water_metadata,
+    ensure_alldocs,
+    nmdc_study_to_ncbi_submission_export,
 )
 from nmdc_runtime.site.resources import (
     get_mongo,
@@ -50,7 +52,6 @@ from nmdc_runtime.site.resources import (
     nmdc_portal_api_client_resource,
     gold_api_client_resource,
     neon_api_client_resource,
-    terminus_resource,
     mongo_resource,
 )
 from nmdc_runtime.site.resources import (
@@ -68,7 +69,6 @@ resource_defs = {
     "nmdc_portal_api_client": nmdc_portal_api_client_resource,
     "gold_api_client": gold_api_client_resource,
     "neon_api_client": neon_api_client_resource,
-    "terminus": terminus_resource,
     "mongo": mongo_resource,
 }
 
@@ -451,6 +451,7 @@ def repo():
         ensure_jobs.to_job(**preset_normal),
         apply_metadata_in.to_job(**preset_normal),
         export_study_biosamples_metadata.to_job(**preset_normal),
+        ensure_alldocs.to_job(**preset_normal),
     ]
     schedules = [housekeeping_weekly]
     sensors = [
@@ -515,8 +516,8 @@ def biosample_submission_ingest():
                         "nmdc_portal_api_client": {
                             "config": {
                                 "base_url": {"env": "NMDC_PORTAL_API_BASE_URL"},
-                                "session_cookie": {
-                                    "env": "NMDC_PORTAL_API_SESSION_COOKIE"
+                                "refresh_token": {
+                                    "env": "NMDC_PORTAL_API_REFRESH_TOKEN"
                                 },
                             }
                         }
@@ -555,8 +556,8 @@ def biosample_submission_ingest():
                         "nmdc_portal_api_client": {
                             "config": {
                                 "base_url": {"env": "NMDC_PORTAL_API_BASE_URL"},
-                                "session_cookie": {
-                                    "env": "NMDC_PORTAL_API_SESSION_COOKIE"
+                                "refresh_token": {
+                                    "env": "NMDC_PORTAL_API_REFRESH_TOKEN"
                                 },
                             }
                         }
@@ -852,6 +853,57 @@ def biosample_submission_ingest():
     ]
 
 
+@repository
+def biosample_export():
+    normal_resources = run_config_frozen__normal_env["resources"]
+    return [
+        nmdc_study_to_ncbi_submission_export.to_job(
+            resource_defs=resource_defs,
+            config={
+                "resources": merge(
+                    unfreeze(normal_resources),
+                    {
+                        "mongo": {
+                            "config": {
+                                "host": {"env": "MONGO_HOST"},
+                                "username": {"env": "MONGO_USERNAME"},
+                                "password": {"env": "MONGO_PASSWORD"},
+                                "dbname": {"env": "MONGO_DBNAME"},
+                            },
+                        },
+                        "runtime_api_site_client": {
+                            "config": {
+                                "base_url": {"env": "API_HOST"},
+                                "client_id": {"env": "API_SITE_CLIENT_ID"},
+                                "client_secret": {"env": "API_SITE_CLIENT_SECRET"},
+                                "site_id": {"env": "API_SITE_ID"},
+                            },
+                        },
+                    },
+                ),
+                "ops": {
+                    "get_ncbi_export_pipeline_study": {
+                        "config": {
+                            "nmdc_study_id": "",
+                        }
+                    },
+                    "get_ncbi_export_pipeline_inputs": {
+                        "config": {
+                            "nmdc_ncbi_attribute_mapping_file_url": "",
+                            "ncbi_submission_metadata": {
+                                "organization": "",
+                            },
+                            "ncbi_biosample_metadata": {
+                                "organism_name": "",
+                            },
+                        }
+                    },
+                },
+            },
+        ),
+    ]
+
+
 # @repository
 # def validation():
 #     graph_jobs = [validate_jgi_job, validate_gold_job, validate_emsl_job]

nmdc_runtime/site/resources.py

@@ -19,7 +19,6 @@ from frozendict import frozendict
 from linkml_runtime.dumpers import json_dumper
 from pydantic import BaseModel, AnyUrl
 from pymongo import MongoClient, ReplaceOne, InsertOne
-from terminusdb_client import WOQLClient
 from toolz import get_in
 from toolz import merge
 
@@ -372,16 +371,37 @@ def gold_api_client_resource(context: InitResourceContext):
 
 @dataclass
 class NmdcPortalApiClient:
+
     base_url: str
-    # Using a cookie for authentication is not ideal and should be replaced
-    # when this API has an another authentication method
-    session_cookie: str
+    refresh_token: str
+    access_token: Optional[str] = None
+    access_token_expires_at: Optional[datetime] = None
+
+    def _request(self, method: str, endpoint: str, **kwargs):
+        r"""
+        Submits a request to the specified API endpoint;
+        after refreshing the access token, if necessary.
+        """
+        if self.access_token is None or datetime.now() > self.access_token_expires_at:
+            refresh_response = requests.post(
+                f"{self.base_url}/auth/refresh",
+                json={"refresh_token": self.refresh_token},
+            )
+            refresh_response.raise_for_status()
+            refresh_body = refresh_response.json()
+            self.access_token_expires_at = datetime.now() + timedelta(
+                seconds=refresh_body["expires_in"]
+            )
+            self.access_token = refresh_body["access_token"]
 
-    def fetch_metadata_submission(self, id: str) -> Dict[str, Any]:
-        response = requests.get(
-            f"{self.base_url}/api/metadata_submission/{id}",
-            cookies={"session": self.session_cookie},
+        headers = kwargs.get("headers", {})
+        headers["Authorization"] = f"Bearer {self.access_token}"
+        return requests.request(
+            method, f"{self.base_url}{endpoint}", **kwargs, headers=headers
         )
+
+    def fetch_metadata_submission(self, id: str) -> Dict[str, Any]:
+        response = self._request("GET", f"/api/metadata_submission/{id}")
         response.raise_for_status()
         return response.json()
 
@@ -389,13 +409,13 @@ class NmdcPortalApiClient:
 @resource(
     config_schema={
         "base_url": StringSource,
-        "session_cookie": StringSource,
+        "refresh_token": StringSource,
     }
 )
 def nmdc_portal_api_client_resource(context: InitResourceContext):
     return NmdcPortalApiClient(
         base_url=context.resource_config["base_url"],
-        session_cookie=context.resource_config["session_cookie"],
+        refresh_token=context.resource_config["refresh_token"],
     )
 
 
@@ -512,33 +532,3 @@ def get_mongo(run_config: frozendict):
         )
     )
     return mongo_resource(resource_context)
-
-
-class TerminusDB:
-    def __init__(self, server_url, user, key, account, dbid):
-        self.client = WOQLClient(server_url=server_url)
-        self.client.connect(user=user, key=key, account=account)
-        db_info = self.client.get_database(dbid=dbid, account=account)
-        if db_info is None:
-            self.client.create_database(dbid=dbid, accountid=account, label=dbid)
-            self.client.create_graph(graph_type="inference", graph_id="main")
-        self.client.connect(user=user, key=key, account=account, db=dbid)
-
-
-@resource(
-    config_schema={
-        "server_url": StringSource,
-        "user": StringSource,
-        "key": StringSource,
-        "account": StringSource,
-        "dbid": StringSource,
-    }
-)
-def terminus_resource(context):
-    return TerminusDB(
-        server_url=context.resource_config["server_url"],
-        user=context.resource_config["user"],
-        key=context.resource_config["key"],
-        account=context.resource_config["account"],
-        dbid=context.resource_config["dbid"],
-    )

nmdc_runtime/site/translation/submission_portal_translator.py

@@ -13,6 +13,9 @@ from toolz import get_in, groupby, concat, valmap, dissoc
 from nmdc_runtime.site.translation.translator import JSON_OBJECT, Translator
 
 
+BIOSAMPLE_UNIQUE_KEY_SLOT = "samp_name"
+
+
 @lru_cache
 def _get_schema_view():
     """Return a SchemaView instance representing the NMDC schema"""
@@ -98,7 +101,9 @@ class SubmissionPortalTranslator(Translator):
         self.study_pi_image_url = study_pi_image_url
         self.study_funding_sources = study_funding_sources
 
-        self.biosample_extras = group_dicts_by_key("source_mat_id", biosample_extras)
+        self.biosample_extras = group_dicts_by_key(
+            BIOSAMPLE_UNIQUE_KEY_SLOT, biosample_extras
+        )
         self.biosample_extras_slot_mapping = group_dicts_by_key(
             "subject_id", biosample_extras_slot_mapping
         )
@@ -521,7 +526,7 @@ class SubmissionPortalTranslator(Translator):
         :param default_env_package: Default value for `env_package` slot
         :return: nmdc:Biosample
         """
-        source_mat_id = sample_data[0].get("source_mat_id", "").strip()
+        biosample_key = sample_data[0].get(BIOSAMPLE_UNIQUE_KEY_SLOT, "").strip()
         slots = {
             "id": nmdc_biosample_id,
             "part_of": nmdc_study_id,
@@ -533,7 +538,7 @@ class SubmissionPortalTranslator(Translator):
             slots.update(transformed_tab)
 
         if self.biosample_extras:
-            raw_extras = self.biosample_extras.get(source_mat_id)
+            raw_extras = self.biosample_extras.get(biosample_key)
             if raw_extras:
                 transformed_extras = self._transform_dict_for_class(
                     raw_extras, "Biosample", self.biosample_extras_slot_mapping
@@ -564,7 +569,9 @@ class SubmissionPortalTranslator(Translator):
 
         sample_data = metadata_submission_data.get("sampleData", {})
         package_name = metadata_submission_data["packageName"]
-        sample_data_by_id = groupby("source_mat_id", concat(sample_data.values()))
+        sample_data_by_id = groupby(
+            BIOSAMPLE_UNIQUE_KEY_SLOT, concat(sample_data.values())
+        )
         nmdc_biosample_ids = self._id_minter("nmdc:Biosample", len(sample_data_by_id))
         sample_data_to_nmdc_biosample_ids = dict(
             zip(sample_data_by_id.keys(), nmdc_biosample_ids)
@@ -583,15 +590,15 @@ class SubmissionPortalTranslator(Translator):
 
         if self.omics_processing_mapping:
             # If there is data from an OmicsProcessing mapping file, process it now. This part
-            # assumes that there is a column in that file with the header __biosample_source_mat_id
+            # assumes that there is a column in that file with the header __biosample_samp_name
             # that can be used to join with the sample data from the submission portal. The
-            # biosample identified by that `source_mat_id` will be referenced in the `has_input`
+            # biosample identified by that `samp_name` will be referenced in the `has_input`
             # slot of the OmicsProcessing object. If a DataObject mapping file was also provided,
             # those objects will also be generated and referenced in the `has_output` slot of the
-            # OmicsProcessing object. By keying off of the `source_mat_id` slot of the submission's
+            # OmicsProcessing object. By keying off of the `samp_name` slot of the submission's
             # sample data there is an implicit 1:1 relationship between Biosample objects and
             # OmicsProcessing objects generated here.
-            join_key = "__biosample_source_mat_id"
+            join_key = f"__biosample_{BIOSAMPLE_UNIQUE_KEY_SLOT}"
             database.omics_processing_set = []
             database.data_object_set = []
             data_objects_by_sample_data_id = {}
@@ -617,7 +624,7 @@ class SubmissionPortalTranslator(Translator):
                     or sample_data_id not in sample_data_to_nmdc_biosample_ids
                 ):
                     logging.warning(
-                        f"Unrecognized biosample source_mat_id: {sample_data_id}"
+                        f"Unrecognized biosample {BIOSAMPLE_UNIQUE_KEY_SLOT}: {sample_data_id}"
                     )
                     continue
                 nmdc_biosample_id = sample_data_to_nmdc_biosample_ids[sample_data_id]

nmdc_runtime/util.py

@@ -16,7 +16,7 @@ import fastjsonschema
 import requests
 from frozendict import frozendict
 from jsonschema.validators import Draft7Validator
-from nmdc_schema.nmdc_schema_accepting_legacy_ids import Database as NMDCDatabase
+from nmdc_schema.nmdc import Database as NMDCDatabase
 from nmdc_schema.get_nmdc_view import ViewGetter
 from pydantic import Field, BaseModel
 from pymongo.database import Database as MongoDatabase
@@ -376,6 +376,24 @@ collection_name_to_class_names: Dict[str, List[str]] = {
 }
 
 
+def class_hierarchy_as_list(obj) -> list[str]:
+    """
+    get list of inherited classes for each concrete class
+    """
+    rv = []
+    current_class = obj.__class__
+
+    def recurse_through_bases(cls):
+        if cls.__name__ == "YAMLRoot":
+            return rv
+        rv.append(cls.__name__)
+        for base in cls.__bases__:
+            recurse_through_bases(base)
+        return rv
+
+    return recurse_through_bases(current_class)
+
+
 @lru_cache
 def schema_collection_names_with_id_field() -> Set[str]:
     """
@@ -393,6 +411,11 @@ def schema_collection_names_with_id_field() -> Set[str]:
     return target_collection_names
 
 
+def populated_schema_collection_names_with_id_field(mdb: MongoDatabase) -> List[str]:
+    collection_names = sorted(schema_collection_names_with_id_field())
+    return [n for n in collection_names if mdb[n].find_one({"id": {"$exists": True}})]
+
+
 def ensure_unique_id_indexes(mdb: MongoDatabase):
     """Ensure that any collections with an "id" field have an index on "id"."""
     candidate_names = (

{nmdc_runtime-1.6.0.dist-info → nmdc_runtime-1.8.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nmdc_runtime
-Version: 1.6.0
+Version: 1.8.0
 Summary: A runtime system for NMDC data management and orchestration
 Home-page: https://github.com/microbiomedata/nmdc-runtime
 Author: Donny Winston
@@ -77,18 +77,15 @@ The runtime features:
          - `schedules` trigger recurring pipeline runs based on time
          - `sensors` trigger pipeline runs based on external state
       - Each `pipeline` can declare dependencies on any runtime `resources` or additional
-         configuration. There are TerminusDB and MongoDB `resources` defined, as well as `preset`
+         configuration. There are MongoDB `resources` defined, as well as `preset`
          configuration definitions for both "dev" and "prod" `modes`. The `preset`s tell Dagster to
          look to a set of known environment variables to load resources configurations, depending on
          the `mode`.
-
-2. A [TerminusDB](https://terminusdb.com/) database supporting revision control of schema-validated
-data.
    
-3. A MongoDB database supporting write-once, high-throughput internal
+2. A MongoDB database supporting write-once, high-throughput internal
 data storage by the nmdc-runtime FastAPI instance.
    
-4. A [FastAPI](https://fastapi.tiangolo.com/) service to interface with the orchestrator and
+3. A [FastAPI](https://fastapi.tiangolo.com/) service to interface with the orchestrator and
 database, as a hub for data management and workflow automation.
 
 ## Local Development

{nmdc_runtime-1.6.0.dist-info → nmdc_runtime-1.8.0.dist-info}/RECORD

@@ -1,7 +1,7 @@
 nmdc_runtime/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/containers.py,sha256=8m_S1wiFu8VOWvY7tyqzf-02X9gXY83YGc8FgjWzLGA,418
 nmdc_runtime/main.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nmdc_runtime/util.py,sha256=o74ZKOmSD79brPFAcQFsYpA6wh9287m0hDhDlIpn9VM,19872
+nmdc_runtime/util.py,sha256=nfj1MjZzVaxs9pKrHo6A98yGAzL-jHQ0zTGs_sOkBnM,20531
 nmdc_runtime/client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/core/db/Database.py,sha256=WamgBUbq85A7-fr3p5B9Tk92U__yPdr9pBb4zyQok-4,377
@@ -35,10 +35,10 @@ nmdc_runtime/minter/domain/model.py,sha256=WMOuKub3dVzkOt_EZSRDLeTsJPqFbKx01SMQ5
 nmdc_runtime/minter/entrypoints/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/minter/entrypoints/fastapi_app.py,sha256=JC4thvzfFwRc1mhWQ-kHy3yvs0SYxF6ktE7LXNCwqlI,4031
 nmdc_runtime/site/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nmdc_runtime/site/graphs.py,sha256=mOWZvT2Rk4X96RmVAvHQwur-FhNuMWAko3jjRLGygEE,11455
-nmdc_runtime/site/ops.py,sha256=YjaH2zqzd01cRcqV0E93RoaWt8T4ExESx4SSszmczZ8,33620
-nmdc_runtime/site/repository.py,sha256=QI9Gcjr68-DT2MPwOx87Vkxcwp3ZIOVaFZ9uCO13w9U,35502
-nmdc_runtime/site/resources.py,sha256=pQSwg1dRpL_D91gYLzzaOIDZ3qa69rPqSlsq5dS9i_M,17783
+nmdc_runtime/site/graphs.py,sha256=QdmNvdtDLCgpJyKviLUj-IIF1gPS_vYzl1Kzv2mSF4g,12122
+nmdc_runtime/site/ops.py,sha256=btdgcGBwNOFnVCzAa-vO4Gs1lMxgnjcRFd8B28X0who,38222
+nmdc_runtime/site/repository.py,sha256=xTHAfokzbZVqlRFG65VuHxTfZfhyKZskOaCSGyrW_hw,37540
+nmdc_runtime/site/resources.py,sha256=ZSH1yvA-li0R7Abc22_v0XLbjBYf5igETr2G01J3hnc,17557
 nmdc_runtime/site/util.py,sha256=6hyVPpb6ZkWEG8Nm7uQxnZ-QmuPOG9hgWvl0mUBr5JU,1303
 nmdc_runtime/site/backup/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/site/backup/nmdcdb_mongodump.py,sha256=H5uosmEiXwLwklJrYJWrNhb_Nuf_ew8dBpZLl6_dYhs,2699
@@ -50,13 +50,11 @@ nmdc_runtime/site/drsobjects/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NM
 nmdc_runtime/site/drsobjects/ingest.py,sha256=pcMP69WSzFHFqHB9JIL55ePFhilnCLRc2XHCQ97w1Ik,3107
 nmdc_runtime/site/drsobjects/registration.py,sha256=D1T3QUuxEOxqKZIvB5rkb_6ZxFZiA-U9SMPajyeWC2Y,3572
 nmdc_runtime/site/export/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nmdc_runtime/site/export/study_metadata.py,sha256=d3q6RV93B0BA64ZkfCPEHdlrC1P8pm9Sj6SxRDcpB7A,4027
+nmdc_runtime/site/export/ncbi_xml.py,sha256=-GflgZO_Q4Y2rm53QIkI7vYY6pWwCf_l7tolGgTXiBg,21026
+nmdc_runtime/site/export/ncbi_xml_utils.py,sha256=CqrtjwzmUbZXEW8aD-KpnCV_PlXVH-Gqp309nw3vbeo,6464
+nmdc_runtime/site/export/study_metadata.py,sha256=WRU0F1ksWfNX3k9LD91Pn2DuLA-IOpGvYPJd6DnguEs,4819
 nmdc_runtime/site/normalization/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/site/normalization/gold.py,sha256=iISDD4qs4d6uLhv631WYNeQVOzY5DO201ZpPtxHdkVk,1311
-nmdc_runtime/site/terminusdb/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nmdc_runtime/site/terminusdb/generate.py,sha256=Z3c06LDx3TGw4pvPRO97caQvzc8SuhGmPIr_d5b_E9I,6144
-nmdc_runtime/site/terminusdb/ingest.py,sha256=WE_V4vRRnlL6hIBU1TDSUheYOBWS9d5g6FHPS64jzvM,1245
-nmdc_runtime/site/terminusdb/schema.py,sha256=3e39rHUSZsNbN_F0SHHNsvcEGRWtYa6O9KNj3cH3tUs,77129
 nmdc_runtime/site/translation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/site/translation/emsl.py,sha256=-aCTJTSCNaK-Koh8BE_4fTf5nyxP1KkquR6lloLEJl0,1245
 nmdc_runtime/site/translation/gold.py,sha256=R3W99sdQb7Pgu_esN7ruIC-tyREQD_idJ4xCzkqWuGw,1622
@@ -66,7 +64,7 @@ nmdc_runtime/site/translation/neon_benthic_translator.py,sha256=e_7tXFrP0PpdhqUC
 nmdc_runtime/site/translation/neon_soil_translator.py,sha256=cJJ_QPva5G5SIT_7DjCSsqbDvgbiKGqUYrxK3nx7_Lw,37634
 nmdc_runtime/site/translation/neon_surface_water_translator.py,sha256=6LaFwBnVx6TN9v1D-G6LFrDxY0TK05AvMklx0E1tTeQ,26590
 nmdc_runtime/site/translation/neon_utils.py,sha256=mdxJVPb3zbD4DiKW3Fwgk22kjczKMwkcozvy7fwteTE,5203
-nmdc_runtime/site/translation/submission_portal_translator.py,sha256=lHcrfPR5wk3BcZ0Uw5zUyWu5XRVikgOzdzSb5nFVS9I,27964
+nmdc_runtime/site/translation/submission_portal_translator.py,sha256=KiVO1vohhrJGfwzLJOumRfyHjcbYfswBIBvkYIdFxv8,28097
 nmdc_runtime/site/translation/translator.py,sha256=xM9dM-nTgSWwu5HFoUVNHf8kqk9iiH4PgWdSx4OKxEk,601
 nmdc_runtime/site/translation/util.py,sha256=w_l3SiExGsl6cXRqto0a_ssDmHkP64ITvrOVfPxmNpY,4366
 nmdc_runtime/site/validation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -74,9 +72,9 @@ nmdc_runtime/site/validation/emsl.py,sha256=OG20mv_3E2rkQqTQtYO0_SVRqFb-Z_zKCiAV
 nmdc_runtime/site/validation/gold.py,sha256=Z5ZzYdjERbrJ2Tu06d0TDTBSfwaFdL1Z23Rl-YkZ2Ow,803
 nmdc_runtime/site/validation/jgi.py,sha256=LdJfhqBVHWCDp0Kzyk8eJZMwEI5NQ-zuTda31BcGwOA,1299
 nmdc_runtime/site/validation/util.py,sha256=GGbMDSwR090sr_E_fHffCN418gpYESaiot6XghS7OYk,3349
-nmdc_runtime-1.6.0.dist-info/LICENSE,sha256=VWiv65r7gHGjgtr3jMJYVmQny5GRpQ6H-W9sScb1x70,2408
-nmdc_runtime-1.6.0.dist-info/METADATA,sha256=hKgDLZfx14AX3IWIi3C9vHa9YAP-agU7tsmKZ_kg8JY,7424
-nmdc_runtime-1.6.0.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-nmdc_runtime-1.6.0.dist-info/entry_points.txt,sha256=nfH6-K9tDKv7va8ENfShsBnxVQoYJdEe7HHdwtkbh1Y,289
-nmdc_runtime-1.6.0.dist-info/top_level.txt,sha256=b0K1s09L_iHH49ueBKaLrB5-lh6cyrSv9vL6x4Qvyz8,13
-nmdc_runtime-1.6.0.dist-info/RECORD,,
+nmdc_runtime-1.8.0.dist-info/LICENSE,sha256=VWiv65r7gHGjgtr3jMJYVmQny5GRpQ6H-W9sScb1x70,2408
+nmdc_runtime-1.8.0.dist-info/METADATA,sha256=lBQzzEEXtwobBObmYmDogAdFKQMLvSJn3wmjG8lHQ5I,7302
+nmdc_runtime-1.8.0.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
+nmdc_runtime-1.8.0.dist-info/entry_points.txt,sha256=JxdvOnvxHK_8046cwlvE30s_fV0-k-eTpQtkKYA69nQ,224
+nmdc_runtime-1.8.0.dist-info/top_level.txt,sha256=b0K1s09L_iHH49ueBKaLrB5-lh6cyrSv9vL6x4Qvyz8,13
+nmdc_runtime-1.8.0.dist-info/RECORD,,

{nmdc_runtime-1.6.0.dist-info → nmdc_runtime-1.8.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.43.0)
+Generator: setuptools (72.1.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

{nmdc_runtime-1.6.0.dist-info → nmdc_runtime-1.8.0.dist-info}/entry_points.txt

@@ -2,4 +2,3 @@
 nmdcdb-mongodump = nmdc_runtime.site.backup.nmdcdb_mongodump:main
 nmdcdb-mongoexport = nmdc_runtime.site.backup.nmdcdb_mongoexport:main
 nmdcdb-mongoimport = nmdc_runtime.site.backup.nmdcdb_mongoimport:main
-schemagen-terminusdb = nmdc_runtime.site.terminusdb.generate:cli

nmdc_runtime/site/terminusdb/generate.py

@@ -1,198 +0,0 @@
-"""
-Example usage:
-$ schemagen-terminusdb ../nmdc-schema/src/schema/nmdc.yaml \
-    > nmdc_runtime/site/terminusdb/nmdc.schema.terminusdb.json
-"""
-
-import json
-import os
-from typing import Union, TextIO, List
-
-import click
-from linkml.utils.generator import Generator, shared_arguments
-from linkml_runtime.linkml_model.meta import (
-    SchemaDefinition,
-    ClassDefinition,
-    SlotDefinition,
-)
-from linkml_runtime.utils.formatutils import camelcase, be, underscore
-
-# http://books.xmlschemata.org/relaxng/relax-CHP-19.html
-XSD_Ok = {
-    "xsd:anyURI",
-    "xsd:base64Binary",
-    "xsd:boolean",
-    "xsd:byte",
-    "xsd:date",
-    "xsd:dateTime",
-    "xsd:decimal",
-    "xsd:double",
-    "xsd:duration",
-    "xsd:ENTITIES",
-    "xsd:ENTITY",
-    "xsd:float",
-    "xsd:gDay",
-    "xsd:gMonth",
-    "xsd:gMonthDay",
-    "xsd:gYear",
-    "xsd:gYearMonth",
-    "xsd:hexBinary",
-    "xsd:ID",
-    "xsd:IDREF",
-    "xsd:IDREFS",
-    "xsd:int",
-    "xsd:integer",
-    "xsd:language",
-    "xsd:long",
-    "xsd:Name",
-    "xsd:NCName",
-    "xsd:negativeInteger",
-    "xsd:NMTOKEN",
-    "xsd:NMTOKENS",
-    "xsd:nonNegativeInteger",
-    "xsd:nonPositiveInteger",
-    "xsd:normalizedString",
-    "xsd:NOTATION",
-    "xsd:positiveInteger",
-    "xsd:short",
-    "xsd:string",
-    "xsd:time",
-    "xsd:token",
-    "xsd:unsignedByte",
-    "xsd:unsignedInt",
-    "xsd:unsignedLong",
-    "xsd:unsignedShort",
-}
-
-
-def as_list(thing) -> list:
-    return thing if isinstance(thing, list) else [thing]
-
-
-def has_field(graph: List[dict], cls: dict, field: str) -> bool:
-    if field in cls:
-        return True
-    for parent_id in as_list(cls.get("@inherits", [])):
-        parent_cls = next(
-            graph_cls for graph_cls in graph if graph_cls.get("@id") == parent_id
-        )
-        if parent_cls and has_field(graph, parent_cls, field):
-            return True
-    return False
-
-
-class TerminusdbGenerator(Generator):
-    """Generates JSON file to pass to WOQLClient.insert_document(..., graph_type="schema")`."""
-
-    generatorname = os.path.basename(__file__)
-    generatorversion = "0.1.0"
-    valid_formats = ["json"]
-    visit_all_class_slots = True
-
-    def __init__(self, schema: Union[str, TextIO, SchemaDefinition], **kwargs) -> None:
-        super().__init__(schema, **kwargs)
-        self.graph = []
-        self.cls_json = {}
-
-    def visit_schema(self, inline: bool = False, **kwargs) -> None:
-        self.graph.append(
-            {
-                "@type": "@context",
-                "@base": "https://api.microbiomedata.org/nmdcschema/ids/",
-                "@schema": "https://w3id.org/nmdc/",
-            }
-        )
-
-    def end_schema(self, **_) -> None:
-        for cls in self.graph:
-            if has_field(self.graph, cls, "id"):
-                cls["@key"] = {"@type": "Lexical", "@fields": ["id"]}
-        print(json.dumps(self.graph, indent=2))
-
-    def visit_class(self, cls: ClassDefinition) -> bool:
-        self.cls_json = {
-            "@type": "Class",
-            "@id": camelcase(cls.name),
-            "@documentation": {
-                "@comment": be(cls.description),
-                "@properties": {},
-            },
-        }
-        if cls.is_a:
-            self.cls_json["@inherits"] = camelcase(cls.is_a)
-        if cls.abstract:
-            self.cls_json["@abstract"] = []
-        return True
-
-    def end_class(self, cls: ClassDefinition) -> None:
-        self.cls_json["@id"] = cls.definition_uri.split(":")[-1].rpartition("/")[-1]
-        self.graph.append(self.cls_json)
-
-    # sounding board as solist
-    # safe space to ask questions. more of a whatsapp group.
-    # both re: business, how to structure proposals, etc.
-    # And also technical content suggestions. R data pipeline / copy/paste in Figma
-    #  - how far do you go in automation in delivery
-
-    def visit_class_slot(
-        self, cls: ClassDefinition, aliased_slot_name: str, slot: SlotDefinition
-    ) -> None:
-        if slot not in self.own_slots(cls):
-            return
-        if slot.is_usage_slot:
-            # TerminusDB does not support calling different things the same name.
-            # So, ignore usage overrides.
-            slot = self.schema.slots[aliased_slot_name]
-
-        if slot.range in self.schema.classes:
-            rng = camelcase(slot.range)
-        elif slot.range in self.schema.types:
-            # XXX Why does `linkml.utils.metamodelcore.Identifier` subclass `str`??
-            rng = str(self.schema.types[slot.range].uri)
-        else:
-            rng = "xsd:string"
-
-        # name = (
-        #     f"{cls.name} {aliased_slot_name}"
-        #     if slot.is_usage_slot
-        #     else aliased_slot_name
-        # )
-        name = slot.name
-        # TODO fork nmdc schema and make any slots NOT required in parent class
-        #  also NOT required in child classes. Can have opt-in entity validation logic in code.
-
-        # XXX MAG bin -> bin name goes to "mAGBin__bin_name", etc. Weird.
-
-        # # translate to terminusdb xsd builtins:
-        # if rng == "xsd:int":
-        #     rng = "xsd:integer"
-        # elif rng == "xsd:float":
-        #     rng = "xsd:double"
-        # elif rng == "xsd:language":
-        #     rng = "xsd:string"
-
-        if rng not in XSD_Ok and slot.range not in self.schema.classes:
-            raise Exception(
-                f"slot range for {name} must be schema class or supported xsd type. "
-                f"Range {rng} is of type {type(rng)}."
-            )
-
-        self.cls_json[underscore(name)] = rng
-        self.cls_json["@documentation"]["@properties"][
-            underscore(name)
-        ] = slot.description
-        if not slot.required:
-            self.cls_json[underscore(name)] = {"@type": "Optional", "@class": rng}
-        if slot.multivalued:  # XXX what about an required multivalued field?
-            self.cls_json[underscore(name)] = {"@type": "Set", "@class": rng}
-
-
-@shared_arguments(TerminusdbGenerator)
-@click.command()
-def cli(yamlfile, **args):
-    """Generate graphql representation of a biolink model"""
-    print(TerminusdbGenerator(yamlfile, **args).serialize(**args))
-
-
-if __name__ == "__main__":
-    cli()