Order AnVIL fields consistently with schema document

DataBiosphere · Dec 6, 2022 · dad7322 · dad7322
1 parent 1ed0473
commit dad7322
Show file tree

Hide file tree

Showing 4 changed files with 37 additions and 29 deletions.
diff --git a/src/azul/plugins/metadata/anvil/__init__.py b/src/azul/plugins/metadata/anvil/__init__.py
@@ -85,6 +85,10 @@ def mapping(self) -> MutableJSON:
 
     @property
     def _field_mapping(self) -> MetadataPlugin._FieldMapping:
+        common_fields = [
+            'document_id',
+            'source_datarepo_row_ids'
+        ]
         return {
             'entity_id': 'entryId',
             'bundles': {
@@ -98,58 +102,57 @@ def _field_mapping(self) -> MetadataPlugin._FieldMapping:
             'contents': {
                 'activities': {
                     f: f'activities.{f}' for f in [
+                        *common_fields,
                         'activity_id',
                         'activity_table',
                         'activity_type',
                         'assay_category',
                         'data_modality',
-                        'date_created',
                         'document_id',
                         'source_datarepo_row_ids',
+                        # Not in schema
+                        'date_created',
                     ]
                 },
                 'biosamples': {
                     f: f'biosamples.{f}' for f in [
-                        'anatomical_site',
+                        *common_fields,
                         'biosample_id',
+                        'anatomical_site',
                         'biosample_type',
-                        'document_id',
-                        'donor_age_at_collection_age_range',
-                        'donor_age_at_collection_unit',
                         'disease',
-                        'source_datarepo_row_ids',
+                        'donor_age_at_collection_unit',
+                        'donor_age_at_collection_age_range',
                     ]
                 },
                 'datasets': {
                     f: f'datasets.{f}' for f in [
+                        *common_fields,
                         'dataset_id',
                         'consent_group',
                         'data_use_permission',
-                        'document_id',
                         'registered_identifier',
-                        'source_datarepo_row_ids',
                         'title',
                     ]
                 },
                 'donors': {
                     f: f'donors.{f}' for f in [
-                        'document_id',
+                        *common_fields,
                         'donor_id',
                         'organism_type',
                         'phenotypic_sex',
                         'reported_ethnicity',
-                        'source_datarepo_row_ids',
                     ]
                 },
                 'files': {
                     **{
                         f: f'files.{f}' for f in [
+                            *common_fields,
+                            'file_id',
                             'data_modality',
-                            'document_id',
                             'file_format',
-                            'file_id',
                             'reference_assembly',
-                            'source_datarepo_row_ids',
+                            # Not in schema
                             'crc32',
                             'sha256',
                             'drs_path',
@@ -159,9 +162,10 @@ def _field_mapping(self) -> MetadataPlugin._FieldMapping:
                     # These field names are hard-coded in the implementation of
                     # the repository service/controller.
                     **{
+                        'byte_size': 'size',
+                        # Not in schema
                         'version': 'fileVersion',
                         'uuid': 'fileId',
-                        'byte_size': 'size'
                     }
                 }
             }

diff --git a/src/azul/plugins/metadata/anvil/indexer/transform.py b/src/azul/plugins/metadata/anvil/indexer/transform.py
@@ -197,19 +197,20 @@ def _activity_types(cls) -> FieldTypes:
             'activity_type': null_str,
             'assay_category': null_str,
             'data_modality': null_str,
+            # Not in schema
             'date_created': null_datetime,
         }
 
     @classmethod
     def _biosample_types(cls) -> FieldTypes:
         return {
             **cls._entity_types(),
-            'anatomical_site': null_str,
             'biosample_id': null_str,
+            'anatomical_site': null_str,
             'biosample_type': null_str,
-            'donor_age_at_collection_age_range': pass_thru_json,
-            'donor_age_at_collection_unit': null_str,
             'disease': null_str,
+            'donor_age_at_collection_unit': null_str,
+            'donor_age_at_collection_age_range': pass_thru_json,
         }
 
     @classmethod
@@ -237,15 +238,16 @@ def _donor_types(cls) -> FieldTypes:
     def _file_types(cls) -> FieldTypes:
         return {
             **cls._entity_types(),
-            'version': null_str,
-            'uuid': null_str,
+            'file_id': null_str,
             'data_modality': [null_str],
             'file_format': null_str,
-            'file_id': null_str,
             'byte_size': null_int,
+            'reference_assembly': [null_str],
+            # Not in schema
+            'version': null_str,
+            'uuid': null_str,
             'size': null_int,
             'name': null_str,
-            'reference_assembly': [null_str],
             'crc32': null_str,
             'sha256': null_str,
             'drs_path': null_str

diff --git a/src/azul/plugins/metadata/anvil/service/response.py b/src/azul/plugins/metadata/anvil/service/response.py
@@ -187,9 +187,9 @@ def _non_pivotal_entity(self,
         'biosamples': {
             'anatomical_site',
             'biosample_type',
-            'donor_age_at_collection_age_range',
-            'donor_age_at_collection_unit',
             'disease',
+            'donor_age_at_collection_unit',
+            'donor_age_at_collection_age_range',
         },
         'datasets': {
             'dataset_id',

diff --git a/src/azul/plugins/repository/tdr_anvil/__init__.py b/src/azul/plugins/repository/tdr_anvil/__init__.py
@@ -490,12 +490,12 @@ def convert_column(value):
     indexed_columns_by_entity_type = {
         'biosample': {
             'biosample_id',
-            'biosample_type',
             'anatomical_site',
+            'biosample_type',
+            'disease',
+            'donor_age_at_collection_unit',
             'donor_age_at_collection_lower_bound',
             'donor_age_at_collection_upper_bound',
-            'donor_age_at_collection_unit',
-            'disease',
         },
         'dataset': {
             'dataset_id',
@@ -512,11 +512,11 @@ def convert_column(value):
         },
         'file': {
             'file_id',
-            'file_ref',
-            'byte_size',
             'data_modality',
             'file_format',
+            'byte_size',
             'reference_assembly',
+            'file_ref',
         },
         'activity': {
             'activity_id',
@@ -526,13 +526,15 @@ def convert_column(value):
             'alignmentactivity_id',
             'activity_type',
             'data_modality',
+            # Not in schema
             'date_created',
         },
         'assayactivity': {
             'assayactivity_id',
             'activity_type',
-            'assay_category',
             'data_modality',
+            # Not in schema
+            'assay_category',
             'date_created',
         },
         'sequencingactivity': {