nmdc-schema 11.14.0rc1__tar.gz → 11.15.1__tar.gz

{nmdc_schema-11.14.0rc1 → nmdc_schema-11.15.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nmdc_schema
-Version: 11.14.0rc1
+Version: 11.15.1
 Summary: Schema resources for the National Microbiome Data Collaborative (NMDC)
 License: MIT
 License-File: LICENSE
@@ -25,13 +25,16 @@ Requires-Dist: curies (>=0.9.0,<0.10.0)
 Requires-Dist: deprecated (>=1,<2)
 Requires-Dist: jsonasobj2 (>=1,<2)
 Requires-Dist: jsonschema (>=4,<5)
-Requires-Dist: linkml (>=1.9.1,<2.0.0)
-Requires-Dist: linkml-runtime (>=1.9.1,<2.0.0)
+Requires-Dist: linkml (>=1.9.6,<2.0.0)
+Requires-Dist: linkml-runtime (>=1.9.5,<2.0.0)
+Requires-Dist: pyasn1 (>=0.6.2)
+Requires-Dist: pymdown-extensions (>=10.16.1)
 Requires-Dist: pymongo (>=4.7.2,<5.0.0)
 Requires-Dist: python-dotenv
 Requires-Dist: pyyaml (>=6,<7)
 Requires-Dist: rdflib (>=6.2.0,<7.0.0)
 Requires-Dist: requests (>=2,<3)
+Requires-Dist: urllib3 (>=2.6.0)
 Project-URL: Documentation, https://microbiomedata.github.io/nmdc-schema/
 Project-URL: Homepage, https://microbiomedata.github.io/nmdc-schema/
 Project-URL: Repository, https://github.com/microbiomedata/nmdc-schema

nmdc_schema-11.15.1/nmdc_schema/migrators/migrator_from_11_13_0_to_11_14_0.py

@@ -0,0 +1,35 @@
+from nmdc_schema.migrators.migrator_base import MigratorBase
+from nmdc_schema.migrators.partials.migrator_from_11_13_0_to_11_14_0 import (
+    get_migrator_classes,
+)
+
+
+class Migrator(MigratorBase):
+    r"""
+    Migrates a database between two schemas.
+    """
+
+    _from_version = "11.13.0"
+    _to_version = "11.14.0"
+
+    def upgrade(self, commit_changes: bool = False) -> None:
+        r"""
+        Migrates the database from conforming to the original schema, to conforming to the new schema.
+
+        This migrator uses partial migrators. It runs them in the order in which they are returned by
+        the `get_migrator_classes` function.
+        
+        Args:
+            commit_changes: If True, commits the changes. If False (default), performs a dry run or rollback.
+        """
+
+        migrator_classes = get_migrator_classes()
+        num_migrators = len(migrator_classes)
+        for idx, migrator_class in enumerate(migrator_classes):
+            self.logger.info(f"Running migrator {idx + 1} of {num_migrators}")
+            self.logger.debug(
+                f"Migrating from {migrator_class.get_origin_version()} "
+                f"to {migrator_class.get_destination_version()}"
+            )
+            migrator = migrator_class(adapter=self.adapter, logger=self.logger)
+            migrator.upgrade(commit_changes=commit_changes)

nmdc_schema-11.15.1/nmdc_schema/migrators/partials/migrator_from_11_13_0_to_11_14_0/__init__.py

@@ -0,0 +1,28 @@
+from typing import List, Type
+
+from nmdc_schema.migrators.migrator_base import MigratorBase
+from nmdc_schema.migrators.partials.migrator_from_11_13_0_to_11_14_0 import (
+    migrator_from_11_13_0_to_11_14_0_part_1,
+    migrator_from_11_13_0_to_11_14_0_part_2
+)
+
+
+def get_migrator_classes() -> List[Type[MigratorBase]]:
+    r"""
+    Returns a list of migrator classes in the order in which they (i.e. their `upgrade` methods)
+    were designed to be run.
+
+    >>> migrator_classes = get_migrator_classes()
+    >>> type(migrator_classes) is list and len(migrator_classes) > 0  # the function returns a list
+    True
+    >>> from inspect import isclass
+    >>> all(isclass(c) for c in migrator_classes)  # each list item is a class
+    True
+    >>> all(callable(getattr(c, "upgrade")) for c in migrator_classes)  # each class has an `upgrade` method
+    True
+    """
+
+    return [
+        migrator_from_11_13_0_to_11_14_0_part_1.Migrator,
+        migrator_from_11_13_0_to_11_14_0_part_2.Migrator
+    ]

nmdc_schema-11.14.0rc1/nmdc_schema/migrators/migrator_from_11_13_0_to_11_14_0.py → nmdc_schema-11.15.1/nmdc_schema/migrators/partials/migrator_from_11_13_0_to_11_14_0/migrator_from_11_13_0_to_11_14_0_part_1.py

@@ -16,7 +16,7 @@ class Migrator(MigratorBase):
     is not valid against the slot's storage_unit or UnitEnum constraints."""
 
     _from_version = '11.13.0'
-    _to_version = '11.14.0'
+    _to_version = '11.14.0_part_1'
 
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
@@ -110,4 +110,4 @@ class Migrator(MigratorBase):
         target_class = document_type.replace('nmdc:', '')
         report = self.validator.validate(document, target_class)
         if report.results:
-            raise ValueError(f"In {document_id}:\n" + "\n".join("  " + result.message for result in report.results))
+            raise ValueError(f"In {document_id}:\n" + "\n".join("  " + result.message for result in report.results))

nmdc_schema-11.15.1/nmdc_schema/migrators/partials/migrator_from_11_13_0_to_11_14_0/migrator_from_11_13_0_to_11_14_0_part_2.py

@@ -0,0 +1,40 @@
+from nmdc_schema.migrators.migrator_base import MigratorBase
+
+
+class Migrator(MigratorBase):
+    r"""
+    Migrates a database between two schemas.
+    """
+
+    _from_version = "11.14.0_part_1"
+    _to_version = "11.14.0_part_2"
+
+    def upgrade(self, commit_changes: bool = False) -> None:
+        r"""
+        Migrates the database from conforming to the original schema, to conforming to the new schema.
+        """
+        self.adapter.do_for_each_document("processed_sample_set", self.confirm_empty)
+
+    def confirm_empty(self, processedsample: dict) -> None:
+        r"""
+        If a processedsample has a value for 'biomaterial_purity' raise an exception.
+
+        >>> m = Migrator()
+
+        # Test: processed sample has biomaterial_purity value
+        >>> m.confirm_empty({"id": 1, "type": "nmdc:ProcessedSample", "biomaterial_purity": ["Test_Value"]})
+        Traceback (most recent call last):
+            ...
+        ValueError: Biosample 1 'biomaterial_purity' values include: ['Test_Value']
+
+        # Test: valid processedsample
+        >>> m.confirm_empty({"id": 3, "type": "nmdc:ProcessedSample"}) is None
+        True
+        """
+        bp_values = processedsample.get("biomaterial_purity", [])
+        biosample_id = processedsample.get("id")
+
+        if len(bp_values)>0:
+            raise ValueError(
+                f"Biosample {biosample_id} 'biomaterial_purity' values include: {bp_values}"
+            )