Merge pull request #141 from c3g/regenerate-migrations

Delete all migrations and regenerate new migrations

chord_metadata_service/chord/ingest.py

@@ -259,6 +259,7 @@ def ingest_phenopacket(phenopacket_data, table_id) -> pm.Phenopacket:
     biosamples = phenopacket_data.get("biosamples", [])
     genes = phenopacket_data.get("genes", [])
     diseases = phenopacket_data.get("diseases", [])
+    hts_files = phenopacket_data.get("hts_files", [])
     meta_data = phenopacket_data["meta_data"]
 
     if subject:
@@ -321,6 +322,18 @@ def ingest_phenopacket(phenopacket_data, table_id) -> pm.Phenopacket:
         )
         diseases_db.append(d_obj.id)
 
+    hts_files_db = []
+    for htsfile in hts_files:
+        htsf_obj, _ = pm.HtsFile.objects.get_or_create(
+            uri=htsfile["uri"],
+            description=htsfile.get("description", None),
+            hts_format=htsfile["hts_format"],
+            genome_assembly=htsfile["genome_assembly"],
+            individual_to_sample_identifiers=htsfile.get("individual_to_sample_identifiers", None),
+            extra_properties=htsfile.get("extra_properties", None)
+        )
+        hts_files_db.append(htsf_obj)
+
     resources_db = [ingest_resource(rs) for rs in meta_data.get("resources", [])]
 
     meta_data_obj = pm.MetaData(
@@ -346,6 +359,7 @@ def ingest_phenopacket(phenopacket_data, table_id) -> pm.Phenopacket:
     new_phenopacket.biosamples.set(biosamples_db)
     new_phenopacket.genes.set(genes_db)
     new_phenopacket.diseases.set(diseases_db)
+    new_phenopacket.hts_files.set(hts_files_db)
 
     return new_phenopacket
 

chord_metadata_service/chord/migrations/0001_v1_0_0.py

@@ -0,0 +1,90 @@
+# Generated by Django 2.2.13 on 2020-07-06 14:55
+
+import chord_metadata_service.chord.models
+import django.contrib.postgres.fields.jsonb
+from django.db import migrations, models
+import django.db.models.deletion
+import uuid
+
+
+class Migration(migrations.Migration):
+
+    initial = True
+
+    dependencies = [
+        ('resources', '0001_v1_0_0'),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name='Dataset',
+            fields=[
+                ('identifier', models.UUIDField(default=uuid.uuid4, editable=False, primary_key=True, serialize=False)),
+                ('title', models.CharField(max_length=200, unique=True)),
+                ('description', models.TextField(blank=True)),
+                ('contact_info', models.TextField(blank=True)),
+                ('data_use', django.contrib.postgres.fields.jsonb.JSONField()),
+                ('linked_field_sets', django.contrib.postgres.fields.jsonb.JSONField(blank=True, default=list, help_text='Data type fields which are linked together.')),
+                ('alternate_identifiers', django.contrib.postgres.fields.jsonb.JSONField(blank=True, default=list, help_text='Alternate identifiers for the dataset.')),
+                ('related_identifiers', django.contrib.postgres.fields.jsonb.JSONField(blank=True, default=list, help_text='Related identifiers for the dataset.')),
+                ('dates', django.contrib.postgres.fields.jsonb.JSONField(blank=True, default=list, help_text='Relevant dates for the datasets, a date must be added, e.g. creation date or last modification date should be added.')),
+                ('stored_in', django.contrib.postgres.fields.jsonb.JSONField(blank=True, help_text='The data repository hosting the dataset.', null=True)),
+                ('spatial_coverage', django.contrib.postgres.fields.jsonb.JSONField(blank=True, default=list, help_text='The geographical extension and span covered by the dataset and its measured dimensions/variables.')),
+                ('types', django.contrib.postgres.fields.jsonb.JSONField(blank=True, default=list, help_text='A term, ideally from a controlled terminology, identifying the dataset type or nature of the data, placing it in a typology.')),
+                ('availability', models.CharField(blank=True, help_text='A qualifier indicating the different types of availability for a dataset (available, unavailable, embargoed, available with restriction, information not available).', max_length=200)),
+                ('refinement', models.CharField(blank=True, help_text='A qualifier to describe the level of data processing of the dataset and its distributions.', max_length=200)),
+                ('aggregation', models.CharField(blank=True, help_text="A qualifier indicating if the entity represents an 'instance of dataset' or a 'collection of datasets'.", max_length=200)),
+                ('privacy', models.CharField(blank=True, help_text='A qualifier to describe the data protection applied to the dataset. This is relevant for clinical data.', max_length=200)),
+                ('distributions', django.contrib.postgres.fields.jsonb.JSONField(blank=True, default=list, help_text='The distribution(s) by which datasets are made available (for example: mySQL dump).')),
+                ('dimensions', django.contrib.postgres.fields.jsonb.JSONField(blank=True, default=list, help_text='The different dimensions (granular components) making up a dataset.')),
+                ('primary_publications', django.contrib.postgres.fields.jsonb.JSONField(blank=True, default=list, help_text='The primary publication(s) associated with the dataset, usually describing how the dataset was produced.')),
+                ('citations', django.contrib.postgres.fields.jsonb.JSONField(blank=True, default=list, help_text='The publication(s) that cite this dataset.')),
+                ('citation_count', models.IntegerField(blank=True, help_text='The number of publications that cite this dataset (enumerated in the citations property).', null=True)),
+                ('produced_by', django.contrib.postgres.fields.jsonb.JSONField(blank=True, help_text='A study process which generated a given dataset, if any.', null=True)),
+                ('creators', django.contrib.postgres.fields.jsonb.JSONField(blank=True, default=list, help_text='The person(s) or organization(s) which contributed to the creation of the dataset.')),
+                ('licenses', django.contrib.postgres.fields.jsonb.JSONField(blank=True, default=list, help_text='The terms of use of the dataset.')),
+                ('acknowledges', django.contrib.postgres.fields.jsonb.JSONField(blank=True, default=list, help_text='The grant(s) which funded and supported the work reported by the dataset.')),
+                ('keywords', django.contrib.postgres.fields.jsonb.JSONField(blank=True, default=list, help_text='Tags associated with the dataset, which will help in its discovery.')),
+                ('version', models.CharField(blank=True, default=chord_metadata_service.chord.models.version_default, help_text='A release point for the dataset when applicable.', max_length=200)),
+                ('extra_properties', django.contrib.postgres.fields.jsonb.JSONField(blank=True, help_text='Extra properties that do not fit in the previous specified attributes.', null=True)),
+                ('created', models.DateTimeField(auto_now_add=True)),
+                ('updated', models.DateTimeField(auto_now=True)),
+                ('additional_resources', models.ManyToManyField(blank=True, help_text="Any resource objects linked to this dataset that aren't specified by a phenopacket in the dataset.", to='resources.Resource')),
+                ('has_part', models.ManyToManyField(blank=True, help_text="A Dataset that is a subset of this Dataset; Datasets declaring the 'hasPart' relationship are considered a collection of Datasets, the aggregation criteria could be included in the 'description' field.", related_name='_dataset_has_part_+', to='chord.Dataset')),
+            ],
+        ),
+        migrations.CreateModel(
+            name='Project',
+            fields=[
+                ('identifier', models.UUIDField(default=uuid.uuid4, editable=False, primary_key=True, serialize=False)),
+                ('title', models.CharField(max_length=200, unique=True)),
+                ('description', models.TextField(blank=True)),
+                ('created', models.DateTimeField(auto_now_add=True)),
+                ('updated', models.DateTimeField(auto_now=True)),
+            ],
+        ),
+        migrations.CreateModel(
+            name='TableOwnership',
+            fields=[
+                ('table_id', models.CharField(max_length=200, primary_key=True, serialize=False)),
+                ('service_id', models.CharField(max_length=200)),
+                ('service_artifact', models.CharField(default='', max_length=200)),
+                ('dataset', models.ForeignKey(on_delete=django.db.models.deletion.CASCADE, related_name='table_ownership', to='chord.Dataset')),
+            ],
+        ),
+        migrations.CreateModel(
+            name='Table',
+            fields=[
+                ('ownership_record', models.OneToOneField(on_delete=django.db.models.deletion.CASCADE, primary_key=True, serialize=False, to='chord.TableOwnership')),
+                ('name', models.CharField(max_length=200, unique=True)),
+                ('data_type', models.CharField(choices=[('experiment', 'experiment'), ('phenopacket', 'phenopacket')], max_length=30)),
+                ('created', models.DateTimeField(auto_now_add=True)),
+                ('updated', models.DateTimeField(auto_now=True)),
+            ],
+        ),
+        migrations.AddField(
+            model_name='dataset',
+            name='project',
+            field=models.ForeignKey(on_delete=django.db.models.deletion.CASCADE, related_name='datasets', to='chord.Project'),
+        ),
+    ]