Merge pull request #542 from NBISweden/feature/schema-access

Add columns for portal, file, and beacon access to data.dataset_versions

sql/data_schema.sql

@@ -115,6 +115,12 @@ CREATE TABLE IF NOT EXISTS data.sample_sets (
     phenotype       varchar(50) NOT NULL
 );
 
+CREATE TYPE access_levels AS enum('None', 'Controlled', 'Registered', 'Public');
+-- None - do not make available
+-- Controlled - access must be permitted "manually"
+-- Registered - free access after registration
+-- Public - free access
+
 CREATE TABLE IF NOT EXISTS data.dataset_versions (
     id integer PRIMARY KEY GENERATED BY DEFAULT AS IDENTITY,
     dataset             integer         NOT NULL REFERENCES data.datasets,
@@ -128,7 +134,10 @@ CREATE TABLE IF NOT EXISTS data.dataset_versions (
     data_contact_name   varchar(100)    DEFAULT NULL,
     data_contact_link   varchar(100)    DEFAULT NULL,
     num_variants        integer         DEFAULT NULL,
-    coverage_levels     integer[]       DEFAULT NULL -- Levels used for data.coverage.coverage
+    coverage_levels     integer[]       DEFAULT NULL, -- Levels used for data.coverage.coverage
+    portal_avail        boolean         NOT NULL,
+    file_access         access_levels   NOT NULL,
+    beacon_access       access_levels   NOT NULL
 );
 
 CREATE TABLE IF NOT EXISTS data.dataset_files (
@@ -209,7 +218,7 @@ CREATE OR REPLACE VIEW data.dataset_version_current AS
 -- Indexes
 --
 
-CREATE INDEX coverage_pos_chrom ON data.coverage (chrom, pos);
+CREATE INDEX coverage_chrom_pos ON data.coverage (chrom, pos);
 CREATE INDEX features_gene ON data.features (gene);
 CREATE INDEX features_transcript ON data.features (transcript);
 CREATE INDEX features_transcript_type ON data.features (transcript, feature_type);

test/data/browser_test_data.sql

@@ -24,11 +24,11 @@ COPY data.reference_sets (id, reference_build, reference_name, ensembl_version,
 1	\N	swegen	homo_sapiens_core_75_37	19	2.9.3
 \.
 
-COPY data.dataset_versions (id, dataset, reference_set, dataset_version, dataset_description, terms, var_call_ref, available_from, ref_doi, data_contact_name, data_contact_link, num_variants, coverage_levels) FROM stdin;
-2	1	1	20170823	desc	terms	hg19	2001-01-01 00:00:00	doi	place	email	\N	{1,5,10,15,20,25,30,50,100}
-3	1	1	20171025	desc	terms	hg19	2001-01-01 00:00:00	doi	place	email	\N	{1,5,10,15,20,25,30,50,100}
-1	1	1	20161223	desc	terms	hg19	2001-01-01 00:00:00	doi	place	email	\N	{1,5,10,15,20,25,30,50,100}
-4	1	1	20180409	desc	terms	hg19	2001-01-01 00:00:00	doi	place	email	\N	{1,5,10,15,20,25,30,50,100}
+COPY data.dataset_versions (id, dataset, reference_set, dataset_version, dataset_description, terms, var_call_ref, available_from, ref_doi, data_contact_name, data_contact_link, num_variants, coverage_levels, portal_avail, file_access, beacon_access) FROM stdin;
+2	1	1	20170823	desc	terms	hg19	2001-01-01 00:00:00	doi	place	email	\N	{1,5,10,15,20,25,30,50,100}	TRUE	Registered	Public
+3	1	1	20171025	desc	terms	hg19	2001-01-01 00:00:00	doi	place	email	\N	{1,5,10,15,20,25,30,50,100}	TRUE	Registered	Public
+1	1	1	20161223	desc	terms	hg19	2001-01-01 00:00:00	doi	place	email	\N	{1,5,10,15,20,25,30,50,100}	TRUE	Registered	Public
+4	1	1	20180409	desc	terms	hg19	2001-01-01 00:00:00	doi	place	email	\N	{1,5,10,15,20,25,30,50,100}	TRUE	Registered	Public
 \.
 
 COPY data.coverage (id, dataset_version, chrom, pos, mean, median, coverage) FROM stdin;

test/data/load_dummy_data.sql

@@ -24,11 +24,11 @@ INSERT INTO data.sample_sets (id, dataset, "collection", sample_size, phenotype)
            (1000002, 1000001, 1000002, 15, 'SamplePheno2 Coll1'),
            (1000003, 1000002, 1000003, 20, 'SamplePheno2 Coll2');
 
-INSERT INTO data.dataset_versions (id, dataset, reference_set, dataset_version, dataset_description, terms, var_call_ref, available_from, ref_doi, data_contact_name, data_contact_link, num_variants, coverage_levels)
-    VALUES (1000001, 1000001, 1000001, 'Version 1-1', 'Dataset 1-1, description', 'Dataset 1-1, terms', 'CallRef11', '2017-01-01', 'datset11DOI', 'Gunnar Green',     'gunnar.green@example.com', 10, ARRAY[1,5,10]),
-           (1000002, 1000002, 1000001, 'Version 2-1', 'Dataset 2-1, description', 'Dataset 2-1, terms', 'CallRef21', '2017-02-01', 'datset21DOI', NULL, NULL, 100, ARRAY[1,5,10]),
-           (1000003, 1000002, 1000002, 'Version 2-2', 'Dataset 2-2, description', 'Dataset 2-2, terms', 'CallRef22', '2017-02-02', 'datset22DOI', 'Strummer project', 'https://example.com/strummer', 1000, ARRAY[1,5,10]),
-           (1000004, 1000002, 1000002, 'InvVer  2-3', 'Dataset 2-3, description', 'Dataset 2-3, terms', 'CallRef23', '2030-02-03', 'datset23DOI', 'Drummer project',  'https://example.com/drummer', 10000, ARRAY[1,5,10]);
+INSERT INTO data.dataset_versions (id, dataset, reference_set, dataset_version, dataset_description, terms, var_call_ref, available_from, ref_doi, data_contact_name, data_contact_link, num_variants, coverage_levels, portal_avail, file_access, beacon_access)
+    VALUES (1000001, 1000001, 1000001, 'Version 1-1', 'Dataset 1-1, description', 'Dataset 1-1, terms', 'CallRef11', '2017-01-01', 'datset11DOI', 'Gunnar Green',     'gunnar.green@example.com', 10, ARRAY[1,5,10], TRUE, 'Registered', 'Public'),
+           (1000002, 1000002, 1000001, 'Version 2-1', 'Dataset 2-1, description', 'Dataset 2-1, terms', 'CallRef21', '2017-02-01', 'datset21DOI', NULL, NULL, 100, ARRAY[1,5,10], TRUE, 'Registered', 'Public'),
+           (1000003, 1000002, 1000002, 'Version 2-2', 'Dataset 2-2, description', 'Dataset 2-2, terms', 'CallRef22', '2017-02-02', 'datset22DOI', 'Strummer project', 'https://example.com/strummer', 1000, ARRAY[1,5,10], TRUE, 'Registered', 'Public'),
+           (1000004, 1000002, 1000002, 'InvVer  2-3', 'Dataset 2-3, description', 'Dataset 2-3, terms', 'CallRef23', '2030-02-03', 'datset23DOI', 'Drummer project',  'https://example.com/drummer', 10000, ARRAY[1,5,10], TRUE, 'Registered', 'Public');
 
 INSERT INTO data.dataset_files(id, dataset_version, basename, uri, file_size)
     VALUES (1000001, 1000001, 'File11-1', '/release/file111.txt', 100),