nmdc-runtime 2.2.1__py3-none-any.whl → 2.4.0__py3-none-any.whl

nmdc_runtime/site/translation/neon_surface_water_translator.py

@@ -71,6 +71,7 @@ class NeonSurfaceWaterDataTranslator(Translator):
         neon_amb_data_tables = (
             "mms_swMetagenomeSequencing",
             "mms_swMetagenomeDnaExtraction",
+            "mms_swRawDataFiles",
             "amc_fieldGenetic",
             "amc_fieldSuperParent",
         )
@@ -88,6 +89,9 @@ class NeonSurfaceWaterDataTranslator(Translator):
                 if_exists="replace",
                 index=False,
             )
+            surface_water_data["mms_swRawDataFiles"].to_sql(
+                "mms_swRawDataFiles", self.conn, if_exists="replace", index=False
+            )
             surface_water_data["amc_fieldGenetic"].to_sql(
                 "amc_fieldGenetic", self.conn, if_exists="replace", index=False
             )
@@ -103,10 +107,7 @@ class NeonSurfaceWaterDataTranslator(Translator):
             "neonEnvoTerms", self.conn, if_exists="replace", index=False
         )
 
-        self.neon_raw_data_file_mappings_df = neon_raw_data_file_mappings_file
-        self.neon_raw_data_file_mappings_df.to_sql(
-            "neonRawDataFile", self.conn, if_exists="replace", index=False
-        )
+        self.neon_raw_data_file_mappings_df = surface_water_data["mms_swRawDataFiles"]
 
         self.site_code_mapping = site_code_mapping
 
@@ -371,7 +372,7 @@ class NeonSurfaceWaterDataTranslator(Translator):
         )
 
     def _translate_data_object(
-        self, do_id: str, url: str, do_type: str, checksum: str
+        self, do_id: str, url: str, do_type: str, manifest_id: str
     ) -> nmdc.DataObject:
         """Create nmdc DataObject which is the output of a NucleotideSequencing process. This
         object mainly contains information about the sequencing file that was generated as
@@ -395,8 +396,15 @@ class NeonSurfaceWaterDataTranslator(Translator):
             url=url,
             description=f"sequencing results for {basename}",
             type="nmdc:DataObject",
-            md5_checksum=checksum,
             data_object_type=do_type,
+            in_manifest=manifest_id,
+        )
+
+    def _translate_manifest(self, manifest_id: str) -> nmdc.Manifest:
+        return nmdc.Manifest(
+            id=manifest_id,
+            manifest_category=nmdc.ManifestCategoryEnum.poolable_replicates,
+            type="nmdc:Manifest",
         )
 
     def get_database(self):
@@ -477,6 +485,9 @@ class NeonSurfaceWaterDataTranslator(Translator):
         """
         surface_water_samples = pd.read_sql_query(query, self.conn)
 
+        # --------------------------------------------------
+        # Create mappings for minted NMDC IDs
+        # --------------------------------------------------
         neon_biosample_ids = surface_water_samples["parentSampleID"]
         nmdc_biosample_ids = self._id_minter("nmdc:Biosample", len(neon_biosample_ids))
         neon_to_nmdc_biosample_ids = dict(zip(neon_biosample_ids, nmdc_biosample_ids))
@@ -511,30 +522,20 @@ class NeonSurfaceWaterDataTranslator(Translator):
             zip(neon_lib_prep_processed_ids, nmdc_lib_prep_processed_ids)
         )
 
-        neon_omprc_ids = surface_water_samples["parentSampleID"]
-        nmdc_omprc_ids = self._id_minter(
-            "nmdc:NucleotideSequencing", len(neon_omprc_ids)
-        )
-        neon_to_nmdc_omprc_ids = dict(zip(neon_omprc_ids, nmdc_omprc_ids))
-
-        neon_raw_data_file_mappings_df = self.neon_raw_data_file_mappings_df
-        neon_raw_file_paths = neon_raw_data_file_mappings_df["rawDataFilePath"]
-        nmdc_data_object_ids = self._id_minter(
-            "nmdc:DataObject", len(neon_raw_file_paths)
-        )
-        neon_to_nmdc_data_object_ids = dict(
-            zip(neon_raw_file_paths, nmdc_data_object_ids)
-        )
-
+        # --------------------------------------------------
+        # STEP 1: Insert Biosamples
+        # --------------------------------------------------
         for neon_id, nmdc_id in neon_to_nmdc_biosample_ids.items():
             biosample_row = surface_water_samples[
                 surface_water_samples["parentSampleID"] == neon_id
             ]
+            # database.biosample_set.append(
+            #     self._translate_biosample(neon_id, nmdc_id, biosample_row)
+            # )
 
-            database.biosample_set.append(
-                self._translate_biosample(neon_id, nmdc_id, biosample_row)
-            )
-
+        # --------------------------------------------------
+        # STEP 2: Insert Extraction Processes
+        # --------------------------------------------------
         for neon_id, nmdc_id in neon_to_nmdc_extraction_ids.items():
             extraction_row = surface_water_samples[
                 surface_water_samples["parentSampleID"] == neon_id
@@ -557,6 +558,7 @@ class NeonSurfaceWaterDataTranslator(Translator):
                     extraction_row, "genomicsSampleID"
                 )
 
+                # Each Extraction process output => ProcessedSample
                 database.processed_sample_set.append(
                     self._translate_processed_sample(
                         processed_sample_id,
@@ -564,23 +566,9 @@ class NeonSurfaceWaterDataTranslator(Translator):
                     )
                 )
 
-        query = """
-            SELECT dnaSampleID, GROUP_CONCAT(rawDataFilePath, '|') AS rawDataFilePaths
-            FROM neonRawDataFile
-            GROUP BY dnaSampleID
-        """
-        neon_raw_data_files = pd.read_sql_query(query, self.conn)
-        neon_raw_data_files_dict = (
-            neon_raw_data_files.set_index("dnaSampleID")["rawDataFilePaths"]
-            .str.split("|")
-            .to_dict()
-        )
-        filtered_neon_raw_data_files_dict = {
-            key: value
-            for key, value in neon_raw_data_files_dict.items()
-            if len(value) <= 2
-        }
-
+        # --------------------------------------------------
+        # STEP 3: Insert LibraryPreparation Processes
+        # --------------------------------------------------
         for neon_id, nmdc_id in neon_to_nmdc_lib_prep_ids.items():
             lib_prep_row = surface_water_samples[
                 surface_water_samples["parentSampleID"] == neon_id
@@ -601,6 +589,7 @@ class NeonSurfaceWaterDataTranslator(Translator):
 
                 dna_sample_id = _get_value_or_none(lib_prep_row, "dnaSampleID")
 
+                # Each LibraryPreparation process output => ProcessedSample
                 database.processed_sample_set.append(
                     self._translate_processed_sample(
                         processed_sample_id,
@@ -608,42 +597,103 @@ class NeonSurfaceWaterDataTranslator(Translator):
                     )
                 )
 
-                has_output = None
-                has_output_do_ids = []
-
-                if dna_sample_id in filtered_neon_raw_data_files_dict:
-                    has_output = filtered_neon_raw_data_files_dict[dna_sample_id]
-                    for item in has_output:
-                        if item in neon_to_nmdc_data_object_ids:
-                            has_output_do_ids.append(neon_to_nmdc_data_object_ids[item])
-
-                        checksum = None
-                        do_type = None
-
-                        checksum = neon_raw_data_file_mappings_df[
-                            neon_raw_data_file_mappings_df["rawDataFilePath"] == item
-                        ]["checkSum"].values[0]
-                        if "_R1.fastq.gz" in item:
-                            do_type = "Metagenome Raw Read 1"
-                        elif "_R2.fastq.gz" in item:
-                            do_type = "Metagenome Raw Read 2"
-
-                        database.data_object_set.append(
-                            self._translate_data_object(
-                                neon_to_nmdc_data_object_ids.get(item),
-                                item,
-                                do_type,
-                                checksum,
-                            )
-                        )
-
-                    database.data_generation_set.append(
-                        self._translate_nucleotide_sequencing(
-                            neon_to_nmdc_omprc_ids.get(neon_id),
-                            processed_sample_id,
-                            has_output_do_ids,
-                            lib_prep_row,
-                        )
+        # --------------------------------------------------
+        # STEP 4: Group raw files by (dnaSampleID, sequencerRunID)
+        #         and insert DataObjects + DataGeneration processes
+        # --------------------------------------------------
+        raw_query = """
+            SELECT dnaSampleID, sequencerRunID, rawDataFilePath
+            FROM mms_swRawDataFiles
+        """
+        neon_raw_data_files_df = pd.read_sql_query(raw_query, self.conn)
+
+        for neon_id, nmdc_libprep_id in neon_to_nmdc_lib_prep_ids.items():
+            # 1) Pull out the row that corresponds to this parentSampleID
+            lib_prep_row = surface_water_samples[
+                surface_water_samples["parentSampleID"] == neon_id
+            ]
+
+            # 2) Grab the dnaSampleID from that row
+            dna_sample_id = _get_value_or_none(lib_prep_row, "dnaSampleID")
+            if not dna_sample_id:
+                # No dnaSampleID => skip
+                continue
+
+            # 3) Find all raw files for that dnaSampleID
+            dna_files = neon_raw_data_files_df[
+                neon_raw_data_files_df["dnaSampleID"] == dna_sample_id
+            ]
+            if dna_files.empty:
+                # No raw files => skip
+                continue
+
+            # -----------------------------------------
+            # LOOKUP DICT: get "has_input" for this neon_id
+            # -----------------------------------------
+            has_input_value = self.samp_procsm_dict.get(neon_id)
+            # If some neon_id isn't in the dictionary, handle it as needed
+            if not has_input_value:
+                # Could skip, or raise an error, or set a default
+                continue
+
+            # -------------------------------------------
+            # 4) CREATE A MANIFEST IF MULTIPLE RAW FILES
+            #    for this row's dnaSampleID
+            # -------------------------------------------
+            manifest_id = None
+            if len(dna_files) > 2:
+                # For each row that references a dnaSampleID with multiple raw files,
+                # mint exactly one new manifest record
+                manifest_id = self._id_minter("nmdc:Manifest", 1)[0]
+                new_manifest = self._translate_manifest(manifest_id)
+                # Add to the database
+                database.manifest_set.append(new_manifest)
+
+            # -------------------------------------------
+            # 5) NOW GROUP FILES BY sequencerRunID
+            #    => one data_generation record per run
+            # -------------------------------------------
+            lib_prep_processed_sample_id = neon_to_nmdc_lib_prep_processed_ids.get(
+                neon_id
+            )
+            if not lib_prep_processed_sample_id:
+                # If we don't have a ProcessedSample for some reason, skip
+                continue
+
+            for run_id, group_df in dna_files.groupby("sequencerRunID"):
+                # a) Mint new data_generation (NucleotideSequencing) ID for this run
+                data_generation_id = self._id_minter("nmdc:NucleotideSequencing", 1)[0]
+
+                # b) Create DataObjects for each raw file in this run
+                data_object_ids = []
+                for raw_fp in group_df["rawDataFilePath"]:
+                    do_id = self._id_minter("nmdc:DataObject", 1)[0]
+
+                    # Distinguish read type
+                    do_type = None
+                    if "_R1.fastq.gz" in raw_fp:
+                        do_type = "Metagenome Raw Read 1"
+                    elif "_R2.fastq.gz" in raw_fp:
+                        do_type = "Metagenome Raw Read 2"
+
+                    # Create the DataObject
+                    data_obj = self._translate_data_object(
+                        do_id=do_id,
+                        url=raw_fp,
+                        do_type=do_type,
+                        manifest_id=manifest_id,  # link to the new Manifest if it exists
+                    )
+                    database.data_object_set.append(data_obj)
+                    data_object_ids.append(do_id)
+
+                # c) Finally, create the data generation record for this run
+                database.data_generation_set.append(
+                    self._translate_nucleotide_sequencing(
+                        nucleotide_sequencing_id=data_generation_id,
+                        processed_sample_id=has_input_value,
+                        raw_data_file_data=data_object_ids,
+                        nucleotide_sequencing_row=lib_prep_row,
                     )
+                )
 
         return database

nmdc_runtime/site/util.py

@@ -1,8 +1,9 @@
 import os
-from functools import lru_cache
-from subprocess import Popen, PIPE, STDOUT, CalledProcessError
 
+from dagster import op
+from functools import lru_cache
 from pymongo.database import Database as MongoDatabase
+from subprocess import Popen, PIPE, STDOUT, CalledProcessError
 
 from nmdc_runtime.api.db.mongo import get_collection_names_from_schema
 from nmdc_runtime.site.resources import mongo_resource
@@ -47,3 +48,7 @@ def schema_collection_has_index_on_id(mdb: MongoDatabase) -> dict:
 
 def get_basename(filename: str) -> str:
     return os.path.basename(filename)
+
+
+def nmdc_study_id_to_filename(nmdc_study_id: str) -> str:
+    return nmdc_study_id.replace(":", "_").replace("-", "_")

nmdc_runtime/util.py

@@ -24,6 +24,10 @@ from nmdc_schema.get_nmdc_view import ViewGetter
 from pydantic import Field, BaseModel
 from pymongo.database import Database as MongoDatabase
 from pymongo.errors import OperationFailure
+from refscan.lib.helpers import identify_references
+from refscan.lib.Finder import Finder
+from refscan.lib.ReferenceList import ReferenceList
+from refscan.scanner import scan_outgoing_references
 from toolz import merge, unique
 
 from nmdc_runtime.api.core.util import sha256hash_from_file
@@ -120,6 +124,23 @@ def get_class_names_from_collection_spec(
     return class_names
 
 
+@lru_cache
+def get_allowed_references() -> ReferenceList:
+    r"""
+    Returns a `ReferenceList` of all the inter-document references that
+    the NMDC Schema allows a schema-compliant MongoDB database to contain.
+    """
+
+    # Identify the inter-document references that the schema allows a database to contain.
+    print("Identifying schema-allowed references.")
+    references = identify_references(
+        schema_view=nmdc_schema_view(),
+        collection_name_to_class_names=collection_name_to_class_names,
+    )
+
+    return references
+
+
 @lru_cache
 def get_type_collections() -> dict:
     """Returns a dictionary mapping class names to Mongo collection names."""
@@ -353,6 +374,14 @@ def nmdc_database_collection_instance_class_names():
 
 @lru_cache
 def nmdc_database_collection_names():
+    r"""
+    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`
+          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`).
+    """
     names = []
     view = nmdc_schema_view()
     all_classes = set(view.all_classes())
@@ -513,6 +542,13 @@ class OverlayDB(AbstractContextManager):
     overlay collection, that id is marked as "seen" and will not also be returned when
     subsequently scanning the (unmodified) base-database collection.
 
+    Note: The OverlayDB object does not provide a means to perform arbitrary MongoDB queries on the virtual "merged"
+          database. Callers can access the real database via `overlay_db._bottom_db` and the overlaying database via
+          `overlay_db._top_db` and perform arbitrary MongoDB queries on the individual databases that way. Access to
+          the virtual "merged" database is limited to the methods of the `OverlayDB` class, which simulates the
+          "merging" just-in-time to process the method invocation. You can see an example of this in the implementation
+          of the `merge_find` method, which internally accesses both the real database and the overlaying database.
+
     Mongo "update" commands (as the "apply_updates" method) are simulated by first copying affected
     documents from a base collection to the overlay, and then applying the updates to the overlay,
     so that again, base collections are unmodified, and a "merge_find" call will produce a result
@@ -591,7 +627,33 @@ class OverlayDB(AbstractContextManager):
                 yield doc
 
 
-def validate_json(in_docs: dict, mdb: MongoDatabase):
+def validate_json(
+    in_docs: dict, mdb: MongoDatabase, check_inter_document_references: bool = False
+):
+    r"""
+    Checks whether the specified dictionary represents a valid instance of the `Database` class
+    defined in the NMDC Schema. Referential integrity checking is performed on an opt-in basis.
+
+    Example dictionary:
+    {
+        "biosample_set": [
+            {"id": "nmdc:bsm-00-000001", ...},
+            {"id": "nmdc:bsm-00-000002", ...}
+        ],
+        "study_set": [
+            {"id": "nmdc:sty-00-000001", ...},
+            {"id": "nmdc:sty-00-000002", ...}
+        ]
+    }
+
+    :param in_docs: The dictionary you want to validate
+    :param mdb: A reference to a MongoDB database
+    :param check_inter_document_references: Whether you want this function to check whether every document that
+                                            is referenced by any of the documents passed in would, indeed, exist
+                                            in the database, if the documents passed in were to be inserted into
+                                            the database. In other words, set this to `True` if you want this
+                                            function to perform referential integrity checks.
+    """
     validator = Draft7Validator(get_nmdc_jsonschema_dict())
     docs = deepcopy(in_docs)
     validation_errors = {}
@@ -599,6 +661,8 @@ def validate_json(in_docs: dict, mdb: MongoDatabase):
     known_coll_names = set(nmdc_database_collection_names())
     for coll_name, coll_docs in docs.items():
         if coll_name not in known_coll_names:
+            # FIXME: Document what `@type` is (conceptually; e.g., why this function accepts it as a collection name).
+            #        See: https://github.com/microbiomedata/nmdc-runtime/discussions/858
             if coll_name == "@type" and coll_docs in ("Database", "nmdc:Database"):
                 continue
             else:
@@ -631,6 +695,84 @@ def validate_json(in_docs: dict, mdb: MongoDatabase):
         except Exception as e:
             return {"result": "errors", "detail": str(e)}
 
+        # Third pass (if enabled): Check inter-document references.
+        if check_inter_document_references is True:
+            # Prepare to use `refscan`.
+            #
+            # Note: We check the inter-document references in two stages, which are:
+            #       1. For each document in the JSON payload, check whether each document it references already exists
+            #          (in the collections the schema says it can exist in) in the database. We use the
+            #          `refscan` package to do this, which returns violation details we'll use in the second stage.
+            #       2. For each violation found in the first stage (i.e. each reference to a not-found document), we
+            #          check whether that document exists (in the collections the schema says it can exist in) in the
+            #          JSON payload. If it does, then we "waive" (i.e. discard) that violation.
+            #       The violations that remain after those two stages are the ones we return to the caller.
+            #
+            # Note: The reason we do not insert documents into an `OverlayDB` and scan _that_, is that the `OverlayDB`
+            #       does not provide a means to perform arbitrary queries against its virtual "merged" database. It
+            #       is not a drop-in replacement for a pymongo's `Database` class, which is the only thing that
+            #       `refscan`'s `Finder` class accepts.
+            #
+            finder = Finder(database=mdb)
+            references = get_allowed_references()
+            reference_field_names_by_source_class_name = (
+                references.get_reference_field_names_by_source_class_name()
+            )
+
+            # Iterate over the collections in the JSON payload.
+            for source_collection_name, documents in in_docs.items():
+                for document in documents:
+                    # Add an `_id` field to the document, since `refscan` requires the document to have one.
+                    source_document = dict(document, _id=None)
+                    violations = scan_outgoing_references(
+                        document=source_document,
+                        schema_view=nmdc_schema_view(),
+                        reference_field_names_by_source_class_name=reference_field_names_by_source_class_name,
+                        references=references,
+                        finder=finder,
+                        collection_names=nmdc_database_collection_names(),
+                        source_collection_name=source_collection_name,
+                        user_wants_to_locate_misplaced_documents=False,
+                    )
+
+                    # For each violation, check whether the misplaced document is in the JSON payload, itself.
+                    for violation in violations:
+                        can_waive_violation = False
+                        # Determine which collections can contain the referenced document, based upon
+                        # the schema class of which this source document is an instance.
+                        target_collection_names = (
+                            references.get_target_collection_names(
+                                source_class_name=violation.source_class_name,
+                                source_field_name=violation.source_field_name,
+                            )
+                        )
+                        # Check whether the referenced document exists in any of those collections in the JSON payload.
+                        for json_coll_name, json_coll_docs in in_docs.items():
+                            if json_coll_name in target_collection_names:
+                                for json_coll_doc in json_coll_docs:
+                                    if json_coll_doc["id"] == violation.target_id:
+                                        can_waive_violation = True
+                                        break  # stop checking
+                            if can_waive_violation:
+                                break  # stop checking
+                        if not can_waive_violation:
+                            violation_as_str = (
+                                f"Document '{violation.source_document_id}' "
+                                f"in collection '{violation.source_collection_name}' "
+                                f"has a field '{violation.source_field_name}' that "
+                                f"references a document having id "
+                                f"'{violation.target_id}', but the latter document "
+                                f"does not exist in any of the collections the "
+                                f"NMDC Schema says it can exist in."
+                            )
+                            validation_errors[source_collection_name].append(
+                                violation_as_str
+                            )
+
+            # If any collection's error list is not empty, return an error response.
+            if any(len(v) > 0 for v in validation_errors.values()):
+                return {"result": "errors", "detail": validation_errors}
+
         return {"result": "All Okay!"}
     else:
         return {"result": "errors", "detail": validation_errors}

{nmdc_runtime-2.2.1.dist-info → nmdc_runtime-2.4.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: nmdc_runtime
-Version: 2.2.1
+Version: 2.4.0
 Summary: A runtime system for NMDC data management and orchestration
 Home-page: https://github.com/microbiomedata/nmdc-runtime
 Author: Donny Winston
@@ -11,6 +11,14 @@ Classifier: License :: OSI Approved :: Apache Software License
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: requires-python
+Dynamic: summary
 
 A runtime system for NMDC data management and orchestration.
 
@@ -29,7 +37,7 @@ houses the LinkML schema specification, as well as generated artifacts (e.g. JSO
 * [nmdc-server](https://github.com/microbiomedata/nmdc-server)
 houses code specific to the data portal -- its database, back-end API, and front-end application.
 
-* [workflow_documentation](https://nmdc-workflow-documentation.readthedocs.io/en/latest/index.html)
+* [workflow_documentation](https://docs.microbiomedata.org/workflows/)
 references workflow code spread across several repositories, that take source data and produce computed data.
 
 * This repo (nmdc-runtime)

{nmdc_runtime-2.2.1.dist-info → nmdc_runtime-2.4.0.dist-info}/RECORD

@@ -2,7 +2,7 @@ nmdc_runtime/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/config.py,sha256=qyV_To6t--DQUpYJ3SrE6sZlxuVXLPmx2dVtZV-3l-c,33
 nmdc_runtime/containers.py,sha256=8m_S1wiFu8VOWvY7tyqzf-02X9gXY83YGc8FgjWzLGA,418
 nmdc_runtime/main.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nmdc_runtime/util.py,sha256=aMzS8eATEjpXOiuyAFYthx92fb_cgIzWWd5ZQU6ZlAY,22931
+nmdc_runtime/util.py,sha256=HzQsNMYG6Pb-IuBEE9HBzX_lNkII7jiNe65UFk34ZYA,31414
 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
@@ -28,7 +28,7 @@ nmdc_runtime/lib/nmdc_etl_class.py,sha256=tVh3rKVMkBHQE65_LhKeIjCsaCZQk_HJzbc9K4
 nmdc_runtime/lib/transform_nmdc_data.py,sha256=hij4lR3IMQRJQdL-rsP_I-m_WyFPsBMchV2MNFUkh0M,39906
 nmdc_runtime/minter/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/minter/bootstrap.py,sha256=5Ej6pJVBRryRIi0ZwEloY78Zky7iE2okF6tPwRI2axM,822
-nmdc_runtime/minter/config.py,sha256=WrxX9WmyN7Ft4INRAQbd31jmlm5qwaDDaNS9AktieYA,4112
+nmdc_runtime/minter/config.py,sha256=gsXZropDeeTO5tmLAtRuoocwqL3HgfgqVAENyCbX-Gc,2739
 nmdc_runtime/minter/adapters/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/minter/adapters/repository.py,sha256=I-jmGP38-9kPhkogrwUht_Ir0CfHA9_5ZImw5I_wbcw,8323
 nmdc_runtime/minter/domain/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -36,11 +36,11 @@ 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=mu4bE8799TItWXaPBfOeFB2XMyYwPZcj-VJQmadN2MA,14171
-nmdc_runtime/site/ops.py,sha256=T9_WrwDaySGnu6olwOHQizHQfeofMOaqMcq_vYEIzO0,43140
-nmdc_runtime/site/repository.py,sha256=JtHlp6l3UVo0QhV670TGns9bMfht7NOQrNWQtvsYr2g,39183
-nmdc_runtime/site/resources.py,sha256=6bmvplgql3KdEXKI49BibSk0Sug96SFJi8eOs2zeKK0,18252
-nmdc_runtime/site/util.py,sha256=zAY0oIY7GRf63ecqWelmS27N7PVrAXVwEhtnpescBSw,1415
+nmdc_runtime/site/graphs.py,sha256=SA4Ibb1TenVgiYD4wNrMiOCwkMKrv6BTcQ8mbG4VXPs,15666
+nmdc_runtime/site/ops.py,sha256=p4F5SrDbFdKOrAHu1TUhWQA33QB7hdoQmCCuU-00Eqo,46445
+nmdc_runtime/site/repository.py,sha256=pfx7WAVgdNaPhtfF2pak-tllqPMf4-yUeOXSpr4hu30,43861
+nmdc_runtime/site/resources.py,sha256=sqtRWb4ewU61U-JZTphsC4wBvYT5B0wj33WU70vjq_k,19677
+nmdc_runtime/site/util.py,sha256=-DnNv15r6XmFZrDG3d3Z-bFn2pFo0xpyyudhKlYPJKc,1559
 nmdc_runtime/site/backup/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/site/backup/nmdcdb_mongodump.py,sha256=H5uosmEiXwLwklJrYJWrNhb_Nuf_ew8dBpZLl6_dYhs,2699
 nmdc_runtime/site/backup/nmdcdb_mongoexport.py,sha256=XIFI_AI3zl0dFr-ELOEmwvT41MyRKBGFaAT3RcamTNE,4166
@@ -51,19 +51,21 @@ 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=Vb4rNP3uhnGlHqrwUGgA2DzpOotCf3S8G4sIJml7gl4,25287
-nmdc_runtime/site/export/ncbi_xml_utils.py,sha256=Jd-d8GGkB3e71TPpl_lPukQ54TioQZynO1yPSLX_aHs,8390
+nmdc_runtime/site/export/ncbi_xml.py,sha256=Jny1SqaVlscjiMHD73aiO8dxjbdPPJF5ksvNApHh5Ck,26230
+nmdc_runtime/site/export/ncbi_xml_utils.py,sha256=Qh96kk3TxwXxzuaWi6fsqe4Smarc2NILFP8pWRD3gFA,10915
 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=EMuY8MfwQEfdejJHp0Y-Gb1eb1zOgKgfJxbtm6wM3YU,10943
 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=RfAB68dJ9hDep20wETmCNBc0gugZbEKqVimT8h2t0uM,31470
+nmdc_runtime/site/translation/gold_translator.py,sha256=Zw4IjxMWJ1wdLyxX44-faq-Nfmr42-Na1gw-Xn4tg6I,32272
 nmdc_runtime/site/translation/jgi.py,sha256=qk878KhIw674TkrVfbl2x1QJrKi3zlvE0vesIpe9slM,876
 nmdc_runtime/site/translation/neon_benthic_translator.py,sha256=QIDqYLuf-NlGY9_88gy_5qTswkei3OfgJ5AOFpEXzJo,23985
 nmdc_runtime/site/translation/neon_soil_translator.py,sha256=Rol0g67nVBGSBySUzpfdW4Fwes7bKtvnlv2g5cB0aTI,38550
-nmdc_runtime/site/translation/neon_surface_water_translator.py,sha256=MQgjIfWPgoRe-bhzyfqHSe2mZwFsjcwjdT8tNqpIhlc,27729
+nmdc_runtime/site/translation/neon_surface_water_translator.py,sha256=k06eULMTYx0sQ00UlyeNJvCJMcX-neClnES1G6zpPKg,30517
 nmdc_runtime/site/translation/neon_utils.py,sha256=d00o7duKKugpLHmsEifNbp4WjeC4GOqcgw0b5qlCg4I,5549
 nmdc_runtime/site/translation/submission_portal_translator.py,sha256=9KhFn2jlRlGEAhsZWRPkpmInpxuVmnbCyR6jhlD7ooA,30587
 nmdc_runtime/site/translation/translator.py,sha256=V6Aq0y03LoQ4LTL2iHDHxGTh_eMjOmDJJSwNHSrp2wo,837
@@ -73,9 +75,9 @@ 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-2.2.1.dist-info/LICENSE,sha256=VWiv65r7gHGjgtr3jMJYVmQny5GRpQ6H-W9sScb1x70,2408
-nmdc_runtime-2.2.1.dist-info/METADATA,sha256=yIkwZWVw8J1xDqhwVQy2Rxfz7cIc42yT4JkRBdsRBr4,7256
-nmdc_runtime-2.2.1.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-nmdc_runtime-2.2.1.dist-info/entry_points.txt,sha256=JxdvOnvxHK_8046cwlvE30s_fV0-k-eTpQtkKYA69nQ,224
-nmdc_runtime-2.2.1.dist-info/top_level.txt,sha256=b0K1s09L_iHH49ueBKaLrB5-lh6cyrSv9vL6x4Qvyz8,13
-nmdc_runtime-2.2.1.dist-info/RECORD,,
+nmdc_runtime-2.4.0.dist-info/LICENSE,sha256=VWiv65r7gHGjgtr3jMJYVmQny5GRpQ6H-W9sScb1x70,2408
+nmdc_runtime-2.4.0.dist-info/METADATA,sha256=CeZZbucd3jrD0ZqGdreH2x7ALrM9pt4ksGV2olkkpPI,7401
+nmdc_runtime-2.4.0.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+nmdc_runtime-2.4.0.dist-info/entry_points.txt,sha256=JxdvOnvxHK_8046cwlvE30s_fV0-k-eTpQtkKYA69nQ,224
+nmdc_runtime-2.4.0.dist-info/top_level.txt,sha256=b0K1s09L_iHH49ueBKaLrB5-lh6cyrSv9vL6x4Qvyz8,13
+nmdc_runtime-2.4.0.dist-info/RECORD,,

{nmdc_runtime-2.2.1.dist-info → nmdc_runtime-2.4.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.6.0)
+Generator: setuptools (75.8.0)
 Root-Is-Purelib: true
 Tag: py3-none-any