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

nmdc_runtime/site/repository.py

@@ -1,6 +1,5 @@
 import json
 
-from typing import Any
 
 from dagster import (
     repository,
@@ -14,7 +13,6 @@ from dagster import (
     DagsterRunStatus,
     RunStatusSensorContext,
     DefaultSensorStatus,
-    in_process_executor,
 )
 from starlette import status
 from toolz import merge, get_in
@@ -30,8 +28,6 @@ from nmdc_runtime.site.graphs import (
     translate_metadata_submission_to_nmdc_schema_database,
     ingest_metadata_submission,
     gold_study_to_database,
-    gold_translation,
-    gold_translation_curation,
     create_objects_from_site_object_puts,
     housekeeping,
     ensure_jobs,
@@ -62,9 +58,6 @@ from nmdc_runtime.site.resources import (
 from nmdc_runtime.site.resources import (
     get_runtime_api_site_client,
 )
-from nmdc_runtime.site.translation.emsl import emsl_job, test_emsl_job
-from nmdc_runtime.site.translation.gold import gold_job, test_gold_job
-from nmdc_runtime.site.translation.jgi import jgi_job, test_jgi_job
 from nmdc_runtime.util import freeze
 from nmdc_runtime.util import unfreeze
 
@@ -249,82 +242,6 @@ def process_workflow_job_triggers(_context):
         yield SkipReason("No new jobs required")
 
 
-@asset_sensor(
-    asset_key=AssetKey(["object", "nmdc_database.json.zip"]),
-    job=ensure_jobs.to_job(name="ensure_gold_translation", **preset_normal),
-)
-def ensure_gold_translation_job(_context, asset_event):
-    mdb = get_mongo(run_config_frozen__normal_env).db
-    gold_etl_latest = mdb.objects.find_one(
-        {"name": "nmdc_database.json.zip"}, sort=[("created_time", -1)]
-    )
-    sensed_object_id = asset_materialization_metadata(asset_event, "object_id").text
-    if gold_etl_latest is None:
-        yield SkipReason("can't find sensed asset object_id in database")
-        return
-    elif gold_etl_latest["id"] != sensed_object_id:
-        yield SkipReason("later object than sensed materialization")
-        return
-
-    run_config = merge(
-        run_config_frozen__normal_env,
-        {
-            "solids": {
-                "construct_jobs": {
-                    "config": {
-                        "base_jobs": [
-                            {
-                                "workflow": {"id": "gold-translation-1.0.0"},
-                                "config": {"object_id": gold_etl_latest["id"]},
-                            }
-                        ]
-                    }
-                }
-            }
-        },
-    )
-    yield RunRequest(run_key=sensed_object_id, run_config=unfreeze(run_config))
-
-
-@asset_sensor(
-    asset_key=AssetKey(["job", "gold-translation-1.0.0"]),
-    job=gold_translation_curation.to_job(**preset_normal),
-)
-def claim_and_run_gold_translation_curation(_context, asset_event):
-    client = get_runtime_api_site_client(run_config_frozen__normal_env)
-    mdb = get_mongo(run_config_frozen__normal_env).db
-    object_id_latest = asset_materialization_metadata(
-        asset_event, "object_id_latest"
-    ).text
-    job = mdb.jobs.find_one(
-        {
-            "workflow.id": "gold-translation-1.0.0",
-            "config.object_id_latest": object_id_latest,
-        }
-    )
-    if job is not None:
-        rv = client.claim_job(job["id"])
-        if rv.status_code == status.HTTP_200_OK:
-            operation = rv.json()
-            run_config = merge(
-                run_config_frozen__normal_env,
-                {
-                    "ops": {
-                        "get_operation": {
-                            "config": {
-                                "operation_id": operation["id"],
-                            }
-                        }
-                    }
-                },
-            )
-            yield RunRequest(run_key=operation["id"], run_config=unfreeze(run_config))
-        else:
-            yield SkipReason("Job found, but already claimed by this site")
-    else:
-        yield SkipReason("No job found")
-
-
 @sensor(
     job=apply_metadata_in.to_job(name="apply_metadata_in_sensed", **preset_normal),
     default_status=DefaultSensorStatus.RUNNING,
@@ -502,7 +419,6 @@ def on_run_fail(context: RunStatusSensorContext):
 @repository
 def repo():
     graph_jobs = [
-        gold_translation.to_job(**preset_normal),
         hello_graph.to_job(name="hello_job"),
         ensure_jobs.to_job(**preset_normal),
         apply_metadata_in.to_job(**preset_normal),
@@ -518,8 +434,6 @@ def repo():
     ]
     sensors = [
         done_object_put_ops,
-        ensure_gold_translation_job,
-        claim_and_run_gold_translation_curation,
         process_workflow_job_triggers,
         claim_and_run_apply_changesheet_jobs,
         claim_and_run_metadata_in_jobs,
@@ -529,20 +443,6 @@ def repo():
     return graph_jobs + schedules + sensors
 
 
-@repository
-def translation():
-    graph_jobs = [jgi_job, gold_job, emsl_job]
-
-    return graph_jobs
-
-
-@repository
-def test_translation():
-    graph_jobs = [test_jgi_job, test_gold_job, test_emsl_job]
-
-    return graph_jobs
-
-
 @repository
 def biosample_submission_ingest():
     normal_resources = run_config_frozen__normal_env["resources"]
@@ -602,6 +502,7 @@ def biosample_submission_ingest():
                             "data_object_mapping_file_url": None,
                             "biosample_extras_file_url": None,
                             "biosample_extras_slot_mapping_file_url": None,
+                            "study_id": None,
                         }
                     },
                     "translate_portal_submission_to_nmdc_schema_database": {
@@ -638,6 +539,7 @@ def biosample_submission_ingest():
                             "data_object_mapping_file_url": None,
                             "biosample_extras_file_url": None,
                             "biosample_extras_slot_mapping_file_url": None,
+                            "study_id": None,
                         }
                     },
                     "translate_portal_submission_to_nmdc_schema_database": {
@@ -1110,15 +1012,3 @@ def database_records_stitching():
             },
         ),
     ]
-
-
-# @repository
-# def validation():
-#     graph_jobs = [validate_jgi_job, validate_gold_job, validate_emsl_job]
-#     return graph_jobs
-#
-#
-# @repository
-# def test_validation():
-#     graph_jobs = [test_validate_jgi_job, test_validate_gold_job, test_validate_emsl_job]
-#     return graph_jobs

nmdc_runtime/site/resources.py

@@ -520,11 +520,24 @@ class MongoDB:
         self.db = self.client[dbname]
 
     def add_docs(self, docs, validate=True, replace=True):
+        """
+        TODO: Document this function.
+        """
         try:
             if validate:
                 nmdc_jsonschema_validator_noidpatterns(docs)
             rv = {}
-            for collection_name, docs in docs.items():
+            for collection_name, collection_docs in docs.items():
+                # If `collection_docs` is empty, abort this iteration.
+                #
+                # Note: We do this because the `bulk_write` method called below will raise
+                #       an `InvalidOperation` exception if it is passed 0 operations.
+                #
+                # Reference: https://pymongo.readthedocs.io/en/stable/api/pymongo/collection.html#pymongo.collection.Collection.bulk_write
+                #
+                if len(collection_docs) == 0:
+                    continue
+
                 rv[collection_name] = self.db[collection_name].bulk_write(
                     [
                         (
@@ -532,7 +545,7 @@ class MongoDB:
                             if replace
                             else InsertOne(d)
                         )
-                        for d in docs
+                        for d in collection_docs
                     ]
                 )
                 now = datetime.now(timezone.utc)
@@ -544,7 +557,7 @@ class MongoDB:
                             "ts": now,
                             # "dtl": {},
                         }
-                        for d in docs
+                        for d in collection_docs
                     ]
                 )
             return rv

nmdc_runtime/site/translation/gold_translator.py

@@ -1,5 +1,4 @@
 import collections
-import csv
 import re
 from typing import List, Tuple, Union
 from nmdc_schema import nmdc
@@ -342,12 +341,7 @@ class GoldStudyTranslator(Translator):
         if field_value is None:
             return None
 
-        return nmdc.QuantityValue(
-            has_raw_value=field_value,
-            has_numeric_value=nmdc.Double(field_value),
-            has_unit=unit,
-            type="nmdc:QuantityValue",
-        )
+        return self._parse_quantity_value(str(field_value), unit)
 
     def _get_text_value(
         self, gold_entity: JSON_OBJECT, gold_field: str
@@ -573,13 +567,11 @@ class GoldStudyTranslator(Translator):
         gold_biosample_id = gold_biosample["biosampleGoldId"]
         return nmdc.Biosample(
             add_date=gold_biosample.get("addDate"),
-            alt=self._get_quantity_value(
-                gold_biosample, "altitudeInMeters", unit="meters"
-            ),
+            alt=self._get_quantity_value(gold_biosample, "altitudeInMeters", unit="m"),
             collected_from=nmdc_field_site_id,
             collection_date=self._get_collection_date(gold_biosample),
             depth=self._get_quantity_value(
-                gold_biosample, ("depthInMeters", "depthInMeters2"), unit="meters"
+                gold_biosample, ("depthInMeters", "depthInMeters2"), unit="m"
             ),
             description=gold_biosample.get("description"),
             diss_oxygen=self._get_quantity_value(gold_biosample, "oxygenConcentration"),
@@ -618,7 +610,7 @@ class GoldStudyTranslator(Translator):
             ),
             specific_ecosystem=gold_biosample.get("specificEcosystem"),
             subsurface_depth=self._get_quantity_value(
-                gold_biosample, "subsurfaceDepthInMeters", unit="meters"
+                gold_biosample, "subsurfaceDepthInMeters", unit="m"
             ),
             temp=self._get_quantity_value(
                 gold_biosample, "sampleCollectionTemperature"

nmdc_runtime/site/translation/neon_benthic_translator.py

@@ -11,7 +11,6 @@ from nmdc_runtime.site.util import get_basename
 from nmdc_runtime.site.translation.neon_utils import (
     _get_value_or_none,
     _create_controlled_identified_term_value,
-    _create_controlled_term_value,
     _create_geolocation_value,
     _create_quantity_value,
     _create_timestamp_value,

nmdc_runtime/site/translation/neon_soil_translator.py

@@ -10,7 +10,6 @@ from nmdc_runtime.site.util import get_basename
 from nmdc_runtime.site.translation.neon_utils import (
     _get_value_or_none,
     _create_controlled_identified_term_value,
-    _create_controlled_term_value,
     _create_geolocation_value,
     _create_quantity_value,
     _create_timestamp_value,
@@ -153,7 +152,7 @@ class NeonSoilDataTranslator(Translator):
             collection_date=_create_timestamp_value(
                 biosample_row["collectDate"].values[0]
             ),
-            temp=_create_quantity_value(biosample_row["soilTemp"].values[0], "Celsius"),
+            temp=_create_quantity_value(biosample_row["soilTemp"].values[0], "Cel"),
             depth=nmdc.QuantityValue(
                 has_minimum_numeric_value=_get_value_or_none(
                     biosample_row, "sampleTopDepth"
@@ -169,13 +168,13 @@ class NeonSoilDataTranslator(Translator):
             analysis_type=_get_value_or_none(biosample_row, "sequenceAnalysisType"),
             env_package=_create_text_value(biosample_row["sampleType"].values[0]),
             nitro=_create_quantity_value(
-                biosample_row["nitrogenPercent"].values[0], "percent"
+                biosample_row["nitrogenPercent"].values[0], "%"
             ),
             org_carb=_create_quantity_value(
-                biosample_row["organicCPercent"].values[0], "percent"
+                biosample_row["organicCPercent"].values[0], "%"
             ),
             carb_nitro_ratio=_create_quantity_value(
-                biosample_row["CNratio"].values[0], None
+                biosample_row["CNratio"].values[0], "ratio"
             ),
             ph=_create_double_value(biosample_row["soilInWaterpH"].values[0]),
             water_content=(

nmdc_runtime/site/translation/neon_surface_water_translator.py

@@ -3,7 +3,6 @@ import sqlite3
 from typing import Dict, Optional, Union
 
 import pandas as pd
-import requests
 import requests_cache
 
 from nmdc_schema import nmdc
@@ -12,7 +11,6 @@ from nmdc_runtime.site.util import get_basename
 from nmdc_runtime.site.translation.neon_utils import (
     _get_value_or_none,
     _create_controlled_identified_term_value,
-    _create_controlled_term_value,
     _create_geolocation_value,
     _create_quantity_value,
     _create_timestamp_value,

nmdc_runtime/site/translation/submission_portal_translator.py

@@ -145,6 +145,7 @@ class SubmissionPortalTranslator(Translator):
         # See: https://github.com/microbiomedata/submission-schema/issues/162
         study_category: Optional[str] = None,
         study_pi_image_url: Optional[str] = None,
+        study_id: Optional[str] = None,
         # Additional biosample-level metadata with optional column mapping information not captured
         # by the submission portal currently.
         # See: https://github.com/microbiomedata/submission-schema/issues/162
@@ -165,6 +166,7 @@ class SubmissionPortalTranslator(Translator):
             nmdc.StudyCategoryEnum(study_category) if study_category else None
         )
         self.study_pi_image_url = study_pi_image_url
+        self.study_id = study_id
 
         self.biosample_extras = group_dicts_by_key(
             BIOSAMPLE_UNIQUE_KEY_SLOT, biosample_extras
@@ -174,6 +176,13 @@ class SubmissionPortalTranslator(Translator):
         )
 
         self.schema_view: SchemaView = _get_schema_view()
+        self._material_processing_subclass_names = []
+        for class_name in self.schema_view.class_descendants(
+            "MaterialProcessing", reflexive=False
+        ):
+            class_def = self.schema_view.get_class(class_name)
+            if not class_def.abstract:
+                self._material_processing_subclass_names.append(class_name)
 
     def _get_pi(
         self, metadata_submission: JSON_OBJECT
@@ -278,61 +287,9 @@ class SubmissionPortalTranslator(Translator):
     def _get_quantity_value(
         self, raw_value: Optional[str], unit: Optional[str] = None
     ) -> Union[nmdc.QuantityValue, None]:
-        """Construct a nmdc:QuantityValue from a raw value string
+        """Construct a nmdc:QuantityValue from a raw value string"""
 
-        The regex pattern minimally matches on a single numeric value (possibly
-        floating point). The pattern can also identify a range represented by
-        two numeric values separated by a hyphen. It can also identify non-numeric
-        characters at the end of the string which are interpreted as a unit. A unit
-        may also be explicitly provided as an argument to this function. If parsing
-        identifies a unit and a unit argument is provided, the unit argument is used.
-        If the pattern is not matched at all None is returned.
-
-        TODO: currently the parsed unit string is used as-is. In the future we may want
-        to be stricter about what we accept or coerce into a controlled value set
-
-        :param raw_value: string to parse
-        :param unit: optional unit, defaults to None
-        :return: nmdc:QuantityValue
-        """
-        if raw_value is None:
-            return None
-
-        match = re.fullmatch(
-            "([+-]?(?=\.\d|\d)(?:\d+)?(?:\.?\d*)(?:[eE][+-]?\d+)?)(?: *- *([+-]?(?=\.\d|\d)(?:\d+)?(?:\.?\d*)(?:[eE][+-]?\d+)?))?(?: *(\S+))?",
-            raw_value,
-        )
-        if not match:
-            return None
-
-        qv = nmdc.QuantityValue(
-            has_raw_value=raw_value,
-            type="nmdc:QuantityValue",
-        )
-        if match.group(2):
-            # having group 2 means the value is a range like "0 - 1". Either
-            # group 1 or group 2 might be the minimum especially when handling
-            # negative ranges like "0 - -1"
-            num_1 = float(match.group(1))
-            num_2 = float(match.group(2))
-            qv.has_minimum_numeric_value = min(num_1, num_2)
-            qv.has_maximum_numeric_value = max(num_1, num_2)
-        else:
-            # otherwise we just have a single numeric value
-            qv.has_numeric_value = float(match.group(1))
-
-        if unit:
-            # a unit was manually specified
-            if match.group(3) and unit != match.group(3):
-                # a unit was also found in the raw string; issue a warning
-                # if they don't agree, but keep the manually specified one
-                logging.warning(f'Unit mismatch: "{unit}" and "{match.group(3)}"')
-            qv.has_unit = unit
-        elif match.group(3):
-            # a unit was found in the raw string
-            qv.has_unit = match.group(3)
-
-        return qv
+        return self._parse_quantity_value(raw_value, unit)
 
     def _get_ontology_class(
         self, raw_value: Optional[str]
@@ -594,6 +551,14 @@ class SubmissionPortalTranslator(Translator):
 
         return data_objects, manifest
 
+    def _parse_sample_link(self, sample_link: str) -> tuple[str, list[str]] | None:
+        """Parse a sample link in the form of `ProcessingName:SampleName,..."""
+        pattern = r"(" + "|".join(self._material_processing_subclass_names) + r"):(.+)"
+        match = re.match(pattern, sample_link)
+        if not match:
+            return None
+        return match.group(1), split_strip(match.group(2), ",")
+
     def _translate_study(
         self, metadata_submission: JSON_OBJECT, nmdc_study_id: str
     ) -> nmdc.Study:
@@ -804,11 +769,14 @@ class SubmissionPortalTranslator(Translator):
             "metadata_submission", {}
         )
 
-        # Generate one Study instance based on the metadata submission
-        nmdc_study_id = self._id_minter("nmdc:Study")[0]
-        database.study_set = [
-            self._translate_study(metadata_submission_data, nmdc_study_id)
-        ]
+        # Generate one Study instance based on the metadata submission, if a study_id wasn't provided
+        if self.study_id:
+            nmdc_study_id = self.study_id
+        else:
+            nmdc_study_id = self._id_minter("nmdc:Study")[0]
+            database.study_set = [
+                self._translate_study(metadata_submission_data, nmdc_study_id)
+            ]
 
         # Automatically populate the `env_package` field in the sample data based on which
         # environmental data tab the sample data came from.
@@ -840,15 +808,63 @@ class SubmissionPortalTranslator(Translator):
         )
 
         # Translate the sample data into nmdc:Biosample objects
-        database.biosample_set = [
-            self._translate_biosample(
-                sample_data,
-                nmdc_biosample_id=sample_data_to_nmdc_biosample_ids[sample_data_id],
-                nmdc_study_id=nmdc_study_id,
-            )
-            for sample_data_id, sample_data in sample_data_by_id.items()
-            if sample_data
-        ]
+        database.biosample_set = []
+        for sample_data_id, sample_data in sample_data_by_id.items():
+            # This shouldn't happen, but just in case skip empty sample data
+            if not sample_data:
+                continue
+
+            # Find the first tab that has a sample_link value and attempt to parse it
+            sample_link = ""
+            for tab in sample_data:
+                if tab.get("sample_link"):
+                    sample_link = tab.get("sample_link")
+                    break
+            parsed_sample_link = self._parse_sample_link(sample_link)
+
+            # If the sample_link could be parsed according to the [ProcessName]:[InputSample,...]
+            # format, then create a ProcessedSample and MaterialProcessing instance instead of a
+            # Biosample instance. The input samples must be present in the submission for this to
+            # work. An exception is raised if any of the referenced input samples are missing.
+            if parsed_sample_link is not None:
+                processing_type, processing_inputs = parsed_sample_link
+                if not all(
+                    input_id in sample_data_to_nmdc_biosample_ids
+                    for input_id in processing_inputs
+                ):
+                    raise ValueError(
+                        f"Could not find all input samples in sample_link '{sample_link}'"
+                    )
+                processed_sample_id = self._id_minter("nmdc:ProcessedSample")[0]
+                database.processed_sample_set.append(
+                    nmdc.ProcessedSample(
+                        id=processed_sample_id,
+                        type="nmdc:ProcessedSample",
+                        name=sample_data[0].get(BIOSAMPLE_UNIQUE_KEY_SLOT, "").strip(),
+                    )
+                )
+
+                processing_class = getattr(nmdc, processing_type)
+                material_processing = processing_class(
+                    id=self._id_minter(f"nmdc:{processing_type}")[0],
+                    type=f"nmdc:{processing_type}",
+                    has_input=[
+                        sample_data_to_nmdc_biosample_ids[input_id]
+                        for input_id in processing_inputs
+                    ],
+                    has_output=[processed_sample_id],
+                )
+                database.material_processing_set.append(material_processing)
+
+            # If there was no sample_link or it doesn't follow the expected format, create a
+            # Biosample instance as normal.
+            else:
+                biosample = self._translate_biosample(
+                    sample_data,
+                    nmdc_biosample_id=sample_data_to_nmdc_biosample_ids[sample_data_id],
+                    nmdc_study_id=nmdc_study_id,
+                )
+                database.biosample_set.append(biosample)
 
         # This section handles the translation of information in the external sequencing tabs into
         # various NMDC objects.

nmdc_runtime/site/translation/translator.py

@@ -1,9 +1,13 @@
+import logging
+import re
 from abc import ABC, abstractmethod
-from typing import Any, Callable, Dict, List, Optional
+from typing import Any, Callable, Dict, List, Optional, Union
 from nmdc_schema import nmdc
 
 JSON_OBJECT = Dict[str, Any]
 
+logger = logging.getLogger(__name__)
+
 
 class Translator(ABC):
     def __init__(
@@ -27,3 +31,61 @@ class Translator(ABC):
     @abstractmethod
     def get_database(self) -> nmdc.Database:
         pass
+
+    def _parse_quantity_value(
+        self, raw_value: Optional[str], unit: Optional[str] = None
+    ) -> Union[nmdc.QuantityValue, None]:
+        """Construct a nmdc:QuantityValue from a raw value string
+
+        The regex pattern minimally matches on a single numeric value (possibly
+        floating point). The pattern can also identify a range represented by
+        two numeric values separated by a hyphen. It can also identify non-numeric
+        characters at the end of the string which are interpreted as a unit. A unit
+        may also be explicitly provided as an argument to this function. If parsing
+        identifies a unit and a unit argument is provided, the unit argument is used.
+        If the pattern is not matched at all None is returned.
+
+        :param raw_value: string to parse
+        :param unit: optional unit, defaults to None. If None, the unit is extracted from the
+            raw_value. If a unit is provided, it will override the unit extracted from the
+            raw_value.
+        :return: nmdc:QuantityValue
+        """
+        if raw_value is None:
+            return None
+
+        match = re.fullmatch(
+            "([+-]?(?=\.\d|\d)(?:\d+)?(?:\.?\d*)(?:[eE][+-]?\d+)?)(?: *- *([+-]?(?=\.\d|\d)(?:\d+)?(?:\.?\d*)(?:[eE][+-]?\d+)?))?(?: *(\S+))?",
+            raw_value,
+        )
+        if not match:
+            return None
+
+        quantity_value_kwargs = {
+            "has_raw_value": raw_value,
+            "type": "nmdc:QuantityValue",
+        }
+        if match.group(2):
+            # having group 2 means the value is a range like "0 - 1". Either
+            # group 1 or group 2 might be the minimum especially when handling
+            # negative ranges like "0 - -1"
+            num_1 = float(match.group(1))
+            num_2 = float(match.group(2))
+            quantity_value_kwargs["has_minimum_numeric_value"] = min(num_1, num_2)
+            quantity_value_kwargs["has_maximum_numeric_value"] = max(num_1, num_2)
+        else:
+            # otherwise we just have a single numeric value
+            quantity_value_kwargs["has_numeric_value"] = float(match.group(1))
+
+        if unit:
+            # a unit was manually specified
+            if match.group(3) and unit != match.group(3):
+                # a unit was also found in the raw string; issue a warning
+                # if they don't agree, but keep the manually specified one
+                logger.warning(f'Unit mismatch: "{unit}" and "{match.group(3)}"')
+            quantity_value_kwargs["has_unit"] = unit
+        elif match.group(3):
+            # a unit was found in the raw string
+            quantity_value_kwargs["has_unit"] = match.group(3)
+
+        return nmdc.QuantityValue(**quantity_value_kwargs)

nmdc_runtime/site/util.py

@@ -3,10 +3,11 @@ import os
 from functools import lru_cache
 from pymongo.database import Database as MongoDatabase
 from subprocess import Popen, PIPE, STDOUT, CalledProcessError
-from toolz import groupby
+from refscan.lib.helpers import get_collection_names_from_schema
 
-from nmdc_runtime.api.db.mongo import get_collection_names_from_schema
 from nmdc_runtime.site.resources import mongo_resource
+from nmdc_runtime.util import nmdc_schema_view
+
 
 mode_test = {
     "resource_defs": {"mongo": mongo_resource}
@@ -37,12 +38,16 @@ def run_and_log(shell_cmd, context):
 
 @lru_cache
 def schema_collection_has_index_on_id(mdb: MongoDatabase) -> dict:
+    """
+    TODO: Document this function.
+    """
+    schema_view = nmdc_schema_view()
     present_collection_names = set(mdb.list_collection_names())
     return {
         name: (
             name in present_collection_names and "id_1" in mdb[name].index_information()
         )
-        for name in get_collection_names_from_schema()
+        for name in get_collection_names_from_schema(schema_view)
     }
 
 

nmdc_runtime/site/validation/util.py

@@ -1,4 +1,4 @@
-from dagster import op, AssetMaterialization, AssetKey, EventMetadata
+from dagster import op, AssetMaterialization, AssetKey, MetadataValue
 from jsonschema import Draft7Validator
 from nmdc_runtime.util import get_nmdc_jsonschema_dict
 from toolz import dissoc
@@ -92,10 +92,15 @@ def announce_validation_report(context, report, api_object):
         asset_key=AssetKey(["validation", f"{collection_name}_validation"]),
         description=f"{collection_name} translation validation",
         metadata={
-            # https://docs.dagster.io/_apidocs/solids#event-metadata
-            # also .json, .md, .path, .url, .python_artifact, ...
-            "n_errors": EventMetadata.int(len(report["errors"])),
-            "object_id": EventMetadata.text(api_object["id"]),
+            # Note: When this code was originally written, it used Dagster's `EventMetadata` class,
+            #       which has since been replaced by Dagster's `MetadataValue` class.
+            #
+            #       Reference:
+            #       - https://docs.dagster.io/api/dagster/ops#dagster.MetadataValue
+            #       - https://docs.dagster.io/api/dagster/metadata#dagster.MetadataValue
+            #
+            "n_errors": MetadataValue.int(len(report["errors"])),
+            "object_id": MetadataValue.text(api_object["id"]),
         },
     )