nmdc-runtime 2.6.0__py3-none-any.whl → 2.8.0__py3-none-any.whl

nmdc_runtime/site/repair/database_updater.py

@@ -1,5 +1,5 @@
 from functools import lru_cache
-from typing import Any, Dict, List
+from typing import Any, Dict, List, Union
 import pandas as pd
 from nmdc_runtime.site.resources import (
     RuntimeApiUserClient,
@@ -240,3 +240,204 @@ class DatabaseUpdater:
         ]
 
         return database
+
+    def queries_run_script_to_update_insdc_identifiers(
+        self,
+    ) -> Union[Dict[str, Any], List[Dict[str, Any]]]:
+        """This method creates a `/queries:run` API endpoint compatible update script that can be run
+        using that API endpoint to update/add information on the `insdc_biosample_identifiers` field
+        of biosample_set records and the `insdc_bioproject_identifiers` field on data_generation_set records.
+
+        The information to be asserted is retrieved from the `ncbiBioSampleAccession` and
+        `ncbiBioProjectAccession` fields on the GOLD `/projects` API endpoint.
+
+        :return: A `/queries:run` update query compatible script serialized as a dictionary/JSON.
+        """
+        # Fetch all biosamples associated with the study
+        biosample_set = self.runtime_api_user_client.get_biosamples_for_study(
+            self.study_id
+        )
+
+        # Fetch all data_generation records associated with the study
+        data_generation_set = (
+            self.runtime_api_user_client.get_data_generation_records_for_study(
+                self.study_id
+            )
+        )
+
+        biosample_updates = []
+        data_generation_updates = []
+
+        # Dictionary to store gold_project_id -> ncbi_bioproject_accession mapping
+        gold_project_to_bioproject = {}
+
+        # Dictionary to store all project data we gather during biosample processing
+        all_processed_projects = {}
+
+        # Process biosamples for insdc_biosample_identifiers
+        for biosample in biosample_set:
+            # get the list (usually one) of GOLD biosample identifiers on the gold_biosample_identifiers slot
+            gold_biosample_identifiers = biosample.get("gold_biosample_identifiers", [])
+            if not gold_biosample_identifiers:
+                continue
+
+            biosample_id = biosample.get("id")
+            if not biosample_id:
+                continue
+
+            insdc_biosample_identifiers = []
+
+            for gold_biosample_id in gold_biosample_identifiers:
+                normalized_id = gold_biosample_id.replace("gold:", "")
+
+                # fetch projects associated with a GOLD biosample from the GOLD `/projects` API endpoint
+                gold_projects = self.gold_api_client.fetch_projects_by_biosample(
+                    normalized_id
+                )
+
+                for project in gold_projects:
+                    # Store each project for later use
+                    project_gold_id = project.get("projectGoldId")
+                    if project_gold_id:
+                        all_processed_projects[project_gold_id] = project
+
+                    # Collect ncbi_biosample_accession for biosample updates
+                    ncbi_biosample_accession = project.get("ncbiBioSampleAccession")
+                    if ncbi_biosample_accession and ncbi_biosample_accession.strip():
+                        insdc_biosample_identifiers.append(ncbi_biosample_accession)
+
+                    # Collect ncbi_bioproject_accession for data_generation records
+                    ncbi_bioproject_accession = project.get("ncbiBioProjectAccession")
+                    if (
+                        project_gold_id
+                        and ncbi_bioproject_accession
+                        and ncbi_bioproject_accession.strip()
+                    ):
+                        gold_project_to_bioproject[project_gold_id] = (
+                            ncbi_bioproject_accession
+                        )
+
+            if insdc_biosample_identifiers:
+                existing_insdc_biosample_identifiers = biosample.get(
+                    "insdc_biosample_identifiers", []
+                )
+                new_insdc_biosample_identifiers = list(
+                    set(insdc_biosample_identifiers)
+                    - set(existing_insdc_biosample_identifiers)
+                )
+
+                if new_insdc_biosample_identifiers:
+                    prefixed_new_biosample_identifiers = [
+                        f"biosample:{id}" for id in new_insdc_biosample_identifiers
+                    ]
+
+                    if existing_insdc_biosample_identifiers:
+                        all_biosample_identifiers = list(
+                            set(
+                                existing_insdc_biosample_identifiers
+                                + prefixed_new_biosample_identifiers
+                            )
+                        )
+                        biosample_updates.append(
+                            {
+                                "q": {"id": biosample_id},
+                                "u": {
+                                    "$set": {
+                                        "insdc_biosample_identifiers": all_biosample_identifiers
+                                    }
+                                },
+                            }
+                        )
+                    else:
+                        biosample_updates.append(
+                            {
+                                "q": {"id": biosample_id},
+                                "u": {
+                                    "$set": {
+                                        "insdc_biosample_identifiers": prefixed_new_biosample_identifiers
+                                    }
+                                },
+                            }
+                        )
+
+        # Process data_generation records for insdc_bioproject_identifiers
+        for data_generation in data_generation_set:
+            data_generation_id = data_generation.get("id")
+            if not data_generation_id:
+                continue
+
+            # Extract existing insdc_bioproject_identifiers
+            existing_insdc_bioproject_identifiers = data_generation.get(
+                "insdc_bioproject_identifiers", []
+            )
+
+            collected_insdc_bioproject_identifiers = set()
+
+            # Add any project identifiers already on the record
+            if "insdc_bioproject_identifiers" in data_generation:
+                for identifier in data_generation["insdc_bioproject_identifiers"]:
+                    collected_insdc_bioproject_identifiers.add(identifier)
+
+            # If there are gold_sequencing_project_identifiers, use our pre-collected mapping
+            gold_project_identifiers = data_generation.get(
+                "gold_sequencing_project_identifiers", []
+            )
+            for gold_project_id in gold_project_identifiers:
+                normalized_id = gold_project_id.replace("gold:", "")
+
+                # Check if we have a bioproject ID for this GOLD project ID
+                if normalized_id in gold_project_to_bioproject:
+                    ncbi_bioproject_accession = gold_project_to_bioproject[
+                        normalized_id
+                    ]
+                    collected_insdc_bioproject_identifiers.add(
+                        f"bioproject:{ncbi_bioproject_accession}"
+                    )
+                else:
+                    # Only if we don't have it in our mapping, try to fetch it
+                    # Instead of making a direct API request, check if we've already seen this project
+                    if normalized_id in all_processed_projects:
+                        project_data = all_processed_projects[normalized_id]
+                        ncbi_bioproject_accession = project_data.get(
+                            "ncbiBioProjectAccession"
+                        )
+                        if (
+                            ncbi_bioproject_accession
+                            and ncbi_bioproject_accession.strip()
+                        ):
+                            collected_insdc_bioproject_identifiers.add(
+                                f"bioproject:{ncbi_bioproject_accession}"
+                            )
+                            # Add to our mapping for future reference
+                            gold_project_to_bioproject[normalized_id] = (
+                                ncbi_bioproject_accession
+                            )
+
+            # Create a list from the set of collected identifiers
+            collected_insdc_bioproject_identifiers = list(
+                collected_insdc_bioproject_identifiers
+            )
+
+            # Only update if there are identifiers to add
+            if collected_insdc_bioproject_identifiers and set(
+                collected_insdc_bioproject_identifiers
+            ) != set(existing_insdc_bioproject_identifiers):
+                data_generation_updates.append(
+                    {
+                        "q": {"id": data_generation_id},
+                        "u": {
+                            "$set": {
+                                "insdc_bioproject_identifiers": collected_insdc_bioproject_identifiers
+                            }
+                        },
+                    }
+                )
+
+        # Return updates for both collections
+        if data_generation_updates:
+            return [
+                {"update": "biosample_set", "updates": biosample_updates},
+                {"update": "data_generation_set", "updates": data_generation_updates},
+            ]
+        else:
+            return {"update": "biosample_set", "updates": biosample_updates}

nmdc_runtime/site/repository.py

@@ -14,6 +14,7 @@ from dagster import (
     DagsterRunStatus,
     RunStatusSensorContext,
     DefaultSensorStatus,
+    in_process_executor,
 )
 from starlette import status
 from toolz import merge, get_in
@@ -44,8 +45,10 @@ from nmdc_runtime.site.graphs import (
     ingest_neon_benthic_metadata,
     ingest_neon_surface_water_metadata,
     ensure_alldocs,
+    run_ontology_load,
     nmdc_study_to_ncbi_submission_export,
     generate_data_generation_set_for_biosamples_in_nmdc_study,
+    generate_update_script_for_insdc_biosample_identifiers,
 )
 from nmdc_runtime.site.resources import (
     get_mongo,
@@ -123,6 +126,55 @@ ensure_alldocs_daily = ScheduleDefinition(
 )
 
 
+load_envo_ontology_weekly = ScheduleDefinition(
+    name="weekly_load_envo_ontology",
+    cron_schedule="0 7 * * 1",
+    execution_timezone="America/New_York",
+    job=run_ontology_load.to_job(
+        name="scheduled_envo_ontology_load",
+        config=unfreeze(
+            merge(
+                run_config_frozen__normal_env,
+                {"ops": {"load_ontology": {"config": {"source_ontology": "envo"}}}},
+            )
+        ),
+        resource_defs=resource_defs,
+    ),
+)
+
+load_uberon_ontology_weekly = ScheduleDefinition(
+    name="weekly_load_uberon_ontology",
+    cron_schedule="0 8 * * 1",
+    execution_timezone="America/New_York",
+    job=run_ontology_load.to_job(
+        name="scheduled_uberon_ontology_load",
+        config=unfreeze(
+            merge(
+                run_config_frozen__normal_env,
+                {"ops": {"load_ontology": {"config": {"source_ontology": "uberon"}}}},
+            )
+        ),
+        resource_defs=resource_defs,
+    ),
+)
+
+load_po_ontology_weekly = ScheduleDefinition(
+    name="weekly_load_po_ontology",
+    cron_schedule="0 9 * * 1",
+    execution_timezone="America/New_York",
+    job=run_ontology_load.to_job(
+        name="scheduled_po_ontology_load",
+        config=unfreeze(
+            merge(
+                run_config_frozen__normal_env,
+                {"ops": {"load_ontology": {"config": {"source_ontology": "po"}}}},
+            )
+        ),
+        resource_defs=resource_defs,
+    ),
+)
+
+
 def asset_materialization_metadata(asset_event, key):
     """Get metadata from an asset materialization event.
 
@@ -462,7 +514,13 @@ def repo():
         export_study_biosamples_metadata.to_job(**preset_normal),
         ensure_alldocs.to_job(**preset_normal),
     ]
-    schedules = [housekeeping_weekly, ensure_alldocs_daily]
+    schedules = [
+        housekeeping_weekly,
+        ensure_alldocs_daily,
+        load_envo_ontology_weekly,
+        load_uberon_ontology_weekly,
+        load_po_ontology_weekly,
+    ]
     sensors = [
         done_object_put_ops,
         ensure_gold_translation_job,
@@ -1008,6 +1066,47 @@ def database_records_stitching():
                 },
             },
         ),
+        generate_update_script_for_insdc_biosample_identifiers.to_job(
+            description="This job generates a MongoDB update script to add INSDC biosample identifiers to biosamples based on GOLD data.",
+            resource_defs=resource_defs,
+            config={
+                "resources": merge(
+                    unfreeze(normal_resources),
+                    {
+                        "runtime_api_user_client": {
+                            "config": {
+                                "base_url": {"env": "API_HOST"},
+                                "username": {"env": "API_ADMIN_USER"},
+                                "password": {"env": "API_ADMIN_PASS"},
+                            },
+                        },
+                        "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"},
+                            },
+                        },
+                        "gold_api_client": {
+                            "config": {
+                                "base_url": {"env": "GOLD_API_BASE_URL"},
+                                "username": {"env": "GOLD_API_USERNAME"},
+                                "password": {"env": "GOLD_API_PASSWORD"},
+                            },
+                        },
+                    },
+                ),
+                "ops": {
+                    "get_database_updater_inputs": {
+                        "config": {
+                            "nmdc_study_id": "",
+                            "gold_nmdc_instrument_mapping_file_url": "https://raw.githubusercontent.com/microbiomedata/nmdc-schema/refs/heads/main/assets/misc/gold_seqMethod_to_nmdc_instrument_set.tsv",
+                        }
+                    },
+                },
+            },
+        ),
     ]
 
 

nmdc_runtime/site/resources.py

@@ -147,6 +147,19 @@ class RuntimeApiUserClient(RuntimeApiClient):
         response.raise_for_status()
         return response.json()["resources"]
 
+    def get_data_generation_records_for_study(self, study_id: str):
+        # TODO: same as above, we are using a large max_page_size to avoid pagination.
+        response = self.request(
+            "GET",
+            f"/nmdcschema/data_generation_set",
+            {
+                "filter": json.dumps({"associated_studies": study_id}),
+                "max_page_size": 10000,
+            },
+        )
+        response.raise_for_status()
+        return response.json()["resources"]
+
     def get_omics_processing_by_name(self, name: str):
         response = self.request(
             "POST",

nmdc_runtime/site/translation/neon_benthic_translator.py

@@ -349,6 +349,7 @@ class NeonBenthicDataTranslator(Translator):
             description=f"sequencing results for {basename}",
             type="nmdc:DataObject",
             data_object_type=do_type,
+            data_category=nmdc.DataCategoryEnum.instrument_data.text,
             in_manifest=manifest_id,
         )
 

nmdc_runtime/site/translation/neon_soil_translator.py

@@ -264,6 +264,7 @@ class NeonSoilDataTranslator(Translator):
             description=f"sequencing results for {basename}",
             type="nmdc:DataObject",
             md5_checksum=checksum,
+            data_category=nmdc.DataCategoryEnum.instrument_data.text,
             data_object_type=do_type,
         )
 

nmdc_runtime/site/translation/neon_surface_water_translator.py

@@ -397,6 +397,7 @@ class NeonSurfaceWaterDataTranslator(Translator):
             description=f"sequencing results for {basename}",
             type="nmdc:DataObject",
             data_object_type=do_type,
+            data_category=nmdc.DataCategoryEnum.instrument_data.text,
             in_manifest=manifest_id,
         )
 

nmdc_runtime/util.py

@@ -11,7 +11,7 @@ from io import BytesIO
 from itertools import chain
 from pathlib import Path
 from uuid import uuid4
-from typing import List, Optional, Set, Dict
+from typing import Callable, List, Optional, Set, Dict
 
 import fastjsonschema
 import requests
@@ -510,7 +510,27 @@ def ensure_unique_id_indexes(mdb: MongoDatabase):
             collection_name in schema_collection_names_with_id_field()
             or all_docs_have_unique_id(mdb[collection_name])
         ):
-            mdb[collection_name].create_index("id", unique=True)
+            # Check if index already exists, and if so, drop it if not unique
+            try:
+                existing_indexes = list(mdb[collection_name].list_indexes())
+                id_index = next(
+                    (idx for idx in existing_indexes if idx["name"] == "id_1"), None
+                )
+
+                if id_index:
+                    # If index exists but isn't unique, drop it so we can recreate
+                    if not id_index.get("unique", False):
+                        mdb[collection_name].drop_index("id_1")
+
+                # Create index with unique constraint
+                mdb[collection_name].create_index("id", unique=True)
+            except OperationFailure as e:
+                # If error is about index with same name, just continue
+                if "An existing index has the same name" in str(e):
+                    continue
+                else:
+                    # Re-raise other errors
+                    raise
 
 
 class UpdateStatement(BaseModel):
@@ -776,3 +796,37 @@ def validate_json(
         return {"result": "All Okay!"}
     else:
         return {"result": "errors", "detail": validation_errors}
+
+
+def decorate_if(condition: bool = False) -> Callable:
+    r"""
+    Decorator that applies another decorator only when `condition` is `True`.
+
+    Note: We implemented this so we could conditionally register
+          endpoints with FastAPI's `@router`.
+
+    Example usages:
+    A. Apply the `@router.get` decorator:
+       ```python
+       @decorate_if(True)(router.get("/me"))
+       def get_me(...):
+           ...
+       ```
+    B. Bypass the `@router.get` decorator:
+       ```python
+       @decorate_if(False)(router.get("/me"))
+       def get_me(...):
+           ...
+       ```
+    """
+
+    def apply_original_decorator(original_decorator: Callable) -> Callable:
+        def check_condition(original_function: Callable) -> Callable:
+            if condition:
+                return original_decorator(original_function)
+            else:
+                return original_function
+
+        return check_condition
+
+    return apply_original_decorator

{nmdc_runtime-2.6.0.dist-info → nmdc_runtime-2.8.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nmdc_runtime
-Version: 2.6.0
+Version: 2.8.0
 Summary: A runtime system for NMDC data management and orchestration
 Home-page: https://github.com/microbiomedata/nmdc-runtime
 Author: Donny Winston
@@ -127,7 +127,8 @@ source .env
 set +a
 ```
 
-If you are connecting to resources that require an SSH tunnel—for example, a MongoDB server that is only accessible on the NERSC network—set up the SSH tunnel.
+If you are connecting to resources that require an SSH tunnel—for example, a MongoDB server that is only accessible on 
+the NERSC network—set up the SSH tunnel.
 
 The following command could be useful to you, either directly or as a template (see `Makefile`).
 
@@ -149,6 +150,19 @@ The Dagit web server is viewable at http://127.0.0.1:3000/.
 The FastAPI service is viewable at http://127.0.0.1:8000/ -- e.g., rendered documentation at
 http://127.0.0.1:8000/redoc/.
 
+
+*  NOTE: Any time you add or change requirements in requirements/main.in or requirements/dev.in, you must run:
+```
+pip-compile --build-isolation --allow-unsafe --resolver=backtracking --strip-extras --output-file requirements/[main|dev].txt requirements/[main|dev].in
+```
+to generate main.txt and dev.txt files respectively. main.in is kind of like a poetry dependency stanza, dev.in is kind 
+of like poetry dev.dependencies stanza. main.txt and dev.txt are kind of like poetry.lock files to specify the exact 
+versions of dependencies to use. main.txt and dev.txt are combined in the docker compose build process to create the 
+final requirements.txt file and import the dependencies into the Docker image.
+
+
+```bash
+
 ## Local Testing
 
 Tests can be found in `tests` and are run with the following commands:
@@ -160,12 +174,13 @@ make test
 # Run a Specific test file eg. tests/test_api/test_endpoints.py
 make test ARGS="tests/test_api/test_endpoints.py"
 ```
+docker compose --file docker-compose.test.yml run test
 
 As you create Dagster solids and pipelines, add tests in `tests/` to check that your code behaves as
 desired and does not break over time.
 
 [For hints on how to write tests for solids and pipelines in Dagster, see their documentation
-tutorial on Testing](https://docs.dagster.io/tutorial/testable).
+tutorial on Testing](https://docs.dagster.io/guides/test/unit-testing-assets-and-ops).
 
 ### RAM usage
 

{nmdc_runtime-2.6.0.dist-info → nmdc_runtime-2.8.0.dist-info}/RECORD

@@ -1,8 +1,9 @@
 nmdc_runtime/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nmdc_runtime/config.py,sha256=qyV_To6t--DQUpYJ3SrE6sZlxuVXLPmx2dVtZV-3l-c,33
+nmdc_runtime/config.py,sha256=GKmovwYD3tIiUQX-mAOcHI8NMEMLhogjHDB9I8azA4c,195
 nmdc_runtime/containers.py,sha256=8m_S1wiFu8VOWvY7tyqzf-02X9gXY83YGc8FgjWzLGA,418
 nmdc_runtime/main.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nmdc_runtime/util.py,sha256=HzQsNMYG6Pb-IuBEE9HBzX_lNkII7jiNe65UFk34ZYA,31414
+nmdc_runtime/mongo_util.py,sha256=7NRvqFE8W2CUcpcXAA4KElUACIdAkBehZ9TBG4k7zNE,3000
+nmdc_runtime/util.py,sha256=FfGNfcnHKS6Yzuwbdj0FtCcL-ks9HUjwWUfsPs1H2ao,33285
 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
@@ -36,10 +37,10 @@ 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=DoKK6B6xkSwRcY5PVVo6jV_IA4HI5qL8xW9_n94jVfQ,15990
-nmdc_runtime/site/ops.py,sha256=atZNkU5mzRRqTnaW39fvq7gVO2sKSH8ztVOp8_dOLbU,48048
-nmdc_runtime/site/repository.py,sha256=nHu1skayyTjJWwGEf5eToX02cgBNTG_kdSluzJZ6rJc,43695
-nmdc_runtime/site/resources.py,sha256=sqtRWb4ewU61U-JZTphsC4wBvYT5B0wj33WU70vjq_k,19677
+nmdc_runtime/site/graphs.py,sha256=cJfLCRYH6l3SW-0MYIOihORit6Fe_gziwQ6BJaph55c,17713
+nmdc_runtime/site/ops.py,sha256=m9p8dlfNVpdEyu0o06cT9jMLkjZh0GGFxEQxDuDPUaA,65917
+nmdc_runtime/site/repository.py,sha256=ZkIykDDaFTxB4QW1Eo_w-9IywQrXXTV7Ugogf8vQ604,47439
+nmdc_runtime/site/resources.py,sha256=2R9X-06f9ZpDWYKltOkl_IIAScQGEEbsZF-URm4O6dM,20164
 nmdc_runtime/site/util.py,sha256=h70UJCT9g-I63EJn0drZjv1iaQ8LHJTbG29R9kqJ04c,1821
 nmdc_runtime/site/backup/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/site/backup/nmdcdb_mongodump.py,sha256=H5uosmEiXwLwklJrYJWrNhb_Nuf_ew8dBpZLl6_dYhs,2699
@@ -51,21 +52,21 @@ 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/ncbi_xml.py,sha256=4RqaT6qs1LDSiDDfF-JNZL5gOel8m65oCOelfr0blXs,26209
-nmdc_runtime/site/export/ncbi_xml_utils.py,sha256=X35zbkxBxEyCnA9peY9YBAa_0oeoWy3DQEXoAXmc6vg,10100
+nmdc_runtime/site/export/ncbi_xml.py,sha256=iZQHBr3LL5Q32I2L_Xpfp9n4ZtgAz_MwrlxIF5do7Pw,29715
+nmdc_runtime/site/export/ncbi_xml_utils.py,sha256=RnoAW0HQwBG6JR63d9muI18RIC114wnX3iYPqOllw44,10700
 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=eTNAPtgAc_xQodADBfgomwow9-14j5rBqQWF8R7BheY,11525
+nmdc_runtime/site/repair/database_updater.py,sha256=gRZ-NxZzXNd-vTIuygabEUqUSiF9eL4hL2rI9Qdf2WI,20764
 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
 nmdc_runtime/site/translation/gold_translator.py,sha256=HGbWeuxppqlVfU8F5oKTYIDoC6qaftugJeWFIALB9XE,32720
 nmdc_runtime/site/translation/jgi.py,sha256=qk878KhIw674TkrVfbl2x1QJrKi3zlvE0vesIpe9slM,876
-nmdc_runtime/site/translation/neon_benthic_translator.py,sha256=VxN7yCziQE-ZP9mtrzqI-yaS9taEgTy0EnIEattYeKo,23727
-nmdc_runtime/site/translation/neon_soil_translator.py,sha256=Rol0g67nVBGSBySUzpfdW4Fwes7bKtvnlv2g5cB0aTI,38550
-nmdc_runtime/site/translation/neon_surface_water_translator.py,sha256=k06eULMTYx0sQ00UlyeNJvCJMcX-neClnES1G6zpPKg,30517
+nmdc_runtime/site/translation/neon_benthic_translator.py,sha256=8_QF75Gf-dc2xVeO6jzTmdDrlGdh1-QrLJKG2SwUhCA,23797
+nmdc_runtime/site/translation/neon_soil_translator.py,sha256=IMeq4ABgWaSUbB_gmG8vBCMeynQSlbCUw9p2be6o8kE,38620
+nmdc_runtime/site/translation/neon_surface_water_translator.py,sha256=Js8_r6vHBW8b-_BpFySTUuYOFe7r51k8HwaNCQ7nAAg,30587
 nmdc_runtime/site/translation/neon_utils.py,sha256=d00o7duKKugpLHmsEifNbp4WjeC4GOqcgw0b5qlCg4I,5549
 nmdc_runtime/site/translation/submission_portal_translator.py,sha256=UEeqlkz_YGqcnx8vomFysetOlXxDu23q0Ryr93SZy78,41684
 nmdc_runtime/site/translation/translator.py,sha256=V6Aq0y03LoQ4LTL2iHDHxGTh_eMjOmDJJSwNHSrp2wo,837
@@ -75,9 +76,9 @@ 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-2.6.0.dist-info/licenses/LICENSE,sha256=VWiv65r7gHGjgtr3jMJYVmQny5GRpQ6H-W9sScb1x70,2408
-nmdc_runtime-2.6.0.dist-info/METADATA,sha256=RK075FB7BHmZL0fm3elHYjBV7YB4hsG-pQRHfgCUm0g,8155
-nmdc_runtime-2.6.0.dist-info/WHEEL,sha256=ck4Vq1_RXyvS4Jt6SI0Vz6fyVs4GWg7AINwpsaGEgPE,91
-nmdc_runtime-2.6.0.dist-info/entry_points.txt,sha256=JxdvOnvxHK_8046cwlvE30s_fV0-k-eTpQtkKYA69nQ,224
-nmdc_runtime-2.6.0.dist-info/top_level.txt,sha256=b0K1s09L_iHH49ueBKaLrB5-lh6cyrSv9vL6x4Qvyz8,13
-nmdc_runtime-2.6.0.dist-info/RECORD,,
+nmdc_runtime-2.8.0.dist-info/licenses/LICENSE,sha256=VWiv65r7gHGjgtr3jMJYVmQny5GRpQ6H-W9sScb1x70,2408
+nmdc_runtime-2.8.0.dist-info/METADATA,sha256=B8Vhde36JVAAwdCqKkcFaTyF13D0uWL8KEQnsyJUajc,8953
+nmdc_runtime-2.8.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+nmdc_runtime-2.8.0.dist-info/entry_points.txt,sha256=JxdvOnvxHK_8046cwlvE30s_fV0-k-eTpQtkKYA69nQ,224
+nmdc_runtime-2.8.0.dist-info/top_level.txt,sha256=b0K1s09L_iHH49ueBKaLrB5-lh6cyrSv9vL6x4Qvyz8,13
+nmdc_runtime-2.8.0.dist-info/RECORD,,

{nmdc_runtime-2.6.0.dist-info → nmdc_runtime-2.8.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.0.0)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any