Merge pull request #225 from hubmapconsortium/test-release

yuanzhou · web-flow · commit e439d8e0e665 · 2021-09-24T13:37:20.000-04:00
v2.0.17 release
diff --git a/VERSION b/VERSION
@@ -1 +1 @@
-2.0.16
+2.0.17
diff --git a/bulk-registration/donors-tsv.md b/bulk-registration/donors-tsv.md
@@ -0,0 +1,14 @@
+## Donor Bulk Registration
+
+Donors can be bulk registered by choosing the Bulk Registration -> Donors menu pick in the [Ingest UI](https://ingest.hubmapconsortium.org)
+ `insert screen shot showing menu`
+ 
+ To register multiple donors at once you'll be asked to upload a tsv file with one row of data per donor to be registered.  The tsv file has the following columns:
+ 
+ | Column<br>Name | Required | Neo4j/WS<br>attrib | Description | Validation Rules |
+ |-------------|----------|----------|-------------|------------------|
+ | lab_id | no | donor.lab_donor_id | An id used by the lab for this donor. This id can be used when searching for the donor in the Ingest UI | Can be blank or an alpha numeric string less than 1024 characters |
+ | lab_name | yes | donor.label | A de-identified name used by the lab. This name can be usd when searching for the donor in the Ingest UI | Must be a valid alpha-numeric string greater that 1 and less than 1024 characters |
+ | selection_protocol | yes |  donor.protocol_url | The doi or doi url to the Protocols IO protocol describing the criteria used when selecting this donor, e.g. 10.17504/protocols.io.bjuxknxn or https://dx.doi.org/10.17504/protocols.io.bjuxknxn | A string that matches either of the patterns<br> - `https://dx.doi.org/##.####/protocols.io.*` <br> - `##.####/protocols.io.*` <br> where # is a numeric character and * matches any characters |
+ | description | no | donor.description | A description of this donor | The field can be empty or contain an alphanumeric string less than 10,000 characters |
+ 
diff --git a/bulk-registration/example-donor-registrations.tsv b/bulk-registration/example-donor-registrations.tsv
@@ -0,0 +1,8 @@
+lab_id	lab_name	selection_protocol	description
+test_dn_01	Test Donor 1	ttps://dx.doi.org/10.17504/protocols.io.bjuxknxn	Donor 1, Male aged 87
+test_dn_2	Donor 2	ttps://dx.doi.org/10.17504/protocols.io.dkasfkkaadf	Liver donor, white female, 65 years old
+test donor 3	Donor 3	10.17504/protocols.io.adskfadfadf	surgical donor, skin biopsy
+	test donor 4	10.17504/protocols.io.ajdsjafjsdif	
+test donor 5	test donor 4	10.17504/protocols.io.kkdjdiudi	
+test donor 6 fail invalid lab_name		10.17504/protocols.io.zsdfasdfadf	
+test donor 7 fail invalid protocol		10.A7504/protocols.io.adskfadfadf	If this were a real description you'd be finding out some relevant information now
diff --git a/bulk-registration/example-sample-registrations.tsv b/bulk-registration/example-sample-registrations.tsv
@@ -0,0 +1,21 @@
+source_id	lab_id	sample_type	organ_type	sample_protocol	description	rui_location
+bfbcdea6a2b709fd0d3aa71b5a47d924	test_smpl_01	organ	br	https://dx.doi.org/10.17504/protocols.io.bjuxknxn	random sample commet	
+f083597a5ebb0fae68c17b28bd5b3bc7	test_smpl_01	organ	HT	https://dx.doi.org/10.17504/protocols.io.bjuxknxn	random sample commet	
+HBM854.MBMF.586	test_sample_2	biopsy		https://dx.doi.org/10.17504/protocols.io.dkasfkkaadf	another random comment	
+a0572d23c12e18e963f5404292b3d153	test sample 3	blood		10.17504/protocols.io.adskfadfadf		
+ff5180d5994eef2526629a710017874f	test sample 4	FRESH_TISSUE		10.17504/protocols.io.mjeisdfasdf		
+2f9522d5462d7cc22a667417c6b80623	test sample 4a	fresh_frozen_oct_block		10.17504/protocols.io.zujdiskshjy		{"@context": "https://hubmapconsortium.github.io/hubmap-ontology/ccf-context.jsonld", "@id": "http://purl.org/ccf/0.5/c62cd431-dd48-4c1b-9c7b-ca4a683fe084", "@type": "SpatialEntity", "label": "SpatialEntity for Male, Age 21, BMI 21.8", "creator": "Jeff Spraggins", "creator_first_name": "Jeff", "creator_last_name": "Spraggins", "creation_date": "2/12/2020 9:48:13 AM", "ccf_annotations": [], "x_dimension": 23, "y_dimension": 18, "z_dimension": 5, "dimension_units": "millimeter", "placement": {"@context": "https://hubmapconsortium.github.io/hubmap-ontology/ccf-context.jsonld", "@id": "http://purl.org/ccf/0.5/c62cd431-dd48-4c1b-9c7b-ca4a683fe084_placement", "@type": "SpatialPlacement", "target": "http://purl.org/ccf/latest/ccf.owl#VHRightKidney", "placement_date": "2/12/2020 9:48:13 AM", "x_scaling": 1, "y_scaling": 1, "z_scaling": 1, "scaling_units": "ratio", "x_rotation": 0, "y_rotation": 0, "z_rotation": 247.9199981689453, "rotation_order": "XYZ", "rotation_units": "degree", "x_translation": -2.729999542236328, "y_translation": 33.220001220703125, "z_translation": -8.940000534057617, "translation_units": "millimeter"}}
+a22c4514e7e40a641d1ea5cdcdb63582	test sample 5 fail invalid organ type	fresh_frozen_oct_block	LV	10.17504/protocols.io.kkdjdiudi		
+HBM265.FCRT.233	test sample 6 fail bad organ code	organ	bad_code	10.17504/protocols.io.zsdfasdfadf		
+ba906793fcba084898ac24e850d5a964	test sample 7 fail bad protocol	fresh_frozen_oct_block		10.A7504/protocols.io.adskfadfadf	If this were a real description you'd be finding out some relevant information now	
+ba5af685d3b266183ec0a903beb0d8dc	test-sample-8-missing organ code	organ		10.17504/protocols.io.adsdududys		
+HBM446.VBGG.933	test-sample-9-missing sample_type			10.17504/protocols.io.dsfsdadf		
+75870f9e402e3ac841f1ec78c290bbc9	test-sample-10-bad sample_type	zzyx		10.17504/protocols.io.ajdsjafjsdif		
+HBX222.1234.938	test-sample-11-misformatted id	gdna		10.17504/protocols.io.idsafasdfad		
+	test-sample-12 fail missing id			10.17504/protocols.io.hfiwkwsdad		
+ffd96a39274136284f5x66c7730a4d98	test-sample-13-misformatted id	gdna		10.17504/protocols.io.owjwsodffs		
+6b955ebeafe9c351831bc36aa086575f	test-sample-14 fail incorrect source type	gdna		10.17504/protocols.io.siaskasfadsf		
+75f837c40c1248e9d53cecf049dc88a6	test-sample-15 fail incorrect source type2	organ	RK	10.17504/protocols.io.fiadsfiasdfadf		
+	fail test_sample_16 missing protocol	biopsy				
+1222af1638d9bc176f393710cc8b2ebf	fail test sample-16 invalid rui json	fresh_frozen_oct_block		10.17504/protocols.io.ifjoijrlksfsdf		{ "https://hubmapconsortium.github.io/hubmap-ontology/ccf-context.jsonld", "@id": "http://purl.org/ccf/0.5/c62cd431-dd48-4c1b-9c7b-ca4a683fe084", "@type": "SpatialEntity", "label": "SpatialEntity for Male, Age 21, BMI 21.8", "creator": "Jeff Spraggins", "creator_first_name": "Jeff", "creator_last_name": "Spraggins", "creation_date": "2/12/2020 9:48:13 AM", "ccf_annotations": [], "x_dimension": 23, "y_dimension": 18, "z_dimension": 5, "dimension_units": "millimeter", "placement": {"@context": "https://hubmapconsortium.github.io/hubmap-ontology/ccf-context.jsonld", "@id": "http://purl.org/ccf/0.5/c62cd431-dd48-4c1b-9c7b-ca4a683fe084_placement", "@type": "SpatialPlacement", "target": "http://purl.org/ccf/latest/ccf.owl#VHRightKidney", "placement_date": "2/12/2020 9:48:13 AM", "x_scaling": 1, "y_scaling": 1, "z_scaling": 1, "scaling_units": "ratio", "x_rotation": 0, "y_rotation": 0, "z_rotation": 247.9199981689453, "rotation_order": "XYZ", "rotation_units": "degree", "x_translation": -2.729999542236328, "y_translation": 33.220001220703125, "z_translation": -8.940000534057617, "translation_units": "millimeter"}}"
+0cf6c31efb7463eb036d474369dfec11	fail test sample-17 organ with RUI info	organ	LK	10.17504/protocols.io.yeuiwwerwe		{"@context": "https://hubmapconsortium.github.io/hubmap-ontology/ccf-context.jsonld", "@id": "http://purl.org/ccf/0.5/c62cd431-dd48-4c1b-9c7b-ca4a683fe084", "@type": "SpatialEntity", "label": "SpatialEntity for Male, Age 21, BMI 21.8", "creator": "Jeff Spraggins", "creator_first_name": "Jeff", "creator_last_name": "Spraggins", "creation_date": "2/12/2020 9:48:13 AM", "ccf_annotations": [], "x_dimension": 23, "y_dimension": 18, "z_dimension": 5, "dimension_units": "millimeter", "placement": {"@context": "https://hubmapconsortium.github.io/hubmap-ontology/ccf-context.jsonld", "@id": "http://purl.org/ccf/0.5/c62cd431-dd48-4c1b-9c7b-ca4a683fe084_placement", "@type": "SpatialPlacement", "target": "http://purl.org/ccf/latest/ccf.owl#VHRightKidney", "placement_date": "2/12/2020 9:48:13 AM", "x_scaling": 1, "y_scaling": 1, "z_scaling": 1, "scaling_units": "ratio", "x_rotation": 0, "y_rotation": 0, "z_rotation": 247.9199981689453, "rotation_order": "XYZ", "rotation_units": "degree", "x_translation": -2.729999542236328, "y_translation": 33.220001220703125, "z_translation": -8.940000534057617, "translation_units": "millimeter"}}
diff --git a/bulk-registration/samples-tsv.md b/bulk-registration/samples-tsv.md
@@ -0,0 +1,16 @@
+## Sample Donor Registration
+
+(Tissue) Samples can be bulk registered by choosing the Bulk Registration -> Samples menu pick in the [Ingest UI](https://ingest.hubmapconsortium.org)
+ `insert screen shot showing menu`
+ 
+ To register multiple samples at once you'll be asked to upload a tsv file with one row of data per donor to be registered.  The tsv file has the following columns:
+ 
+ | Column<br>Name | Required | entity-api<br>attrib | Description | Validation Rules |
+ |-------------|----------|----------|-------------|------------------|
+ | source_id | yes | sample.direct_ancestor_uuid | The id of the source/parent of the new sample, can be a UUID, HuBMAP ID or HuBMAP Sample ID per [this](https://portal.hubmapconsortium.org/docs/apis) | - This is required and should fit the format of a hubmap uuid, hubmap id, or hubmap submission id<br> - should be checked against the uuid-api for existance<br> - if sample_type == organ it must point to a donor<br> - if sample_type != organ it must point to a sample<br> -If rui_location is not blank cannot be the id of a donor |
+ | lab_id | yes | sample.lab_tissue_sample_id  |An id used by the lab for this sample. This id can be used when searching for the donor in the Ingest UI | Must be an alpha numeric string less than 1024 characters |
+ | sample_type | yes | specimen.specimen_type | The code specifying the type of sample | -Must be a code listed in the [tissue sample types file](https://github.com/hubmapconsortium/search-api/blob/master/src/search-schema/data/definitions/enums/tissue_sample_types.yaml) via case insensitive compare<br> -If rui_location is not blank cannot be 'organ' |
+ | organ_type | maybe | specimen.organ | The code specifying the type of organ that the sample is | -if sample_type == organ must be a code from the [organ types file](https://github.com/hubmapconsortium/search-api/blob/master/src/search-schema/data/definitions/enums/organ_types.yaml) via case insensitive compare <br> -if sample_type != organ must be empty  |
+ | sample_protocol | yes |  sample.protocol_url | The doi or doi url to the Protocols IO protocol describing how the sample was procured, e.g. 10.17504/protocols.io.bjuxknxn or https://dx.doi.org/10.17504/protocols.io.bjuxknxn | A string that matches either of the patterns<br> - `https://dx.doi.org/##.####/protocols.io.*` <br> - `##.####/protocols.io.*` <br> where # is a numeric character and * matches any characters |
+ | description | no | sample.description | A description of this sample | The field can be empty or contain an alphanumeric string less than 10,000 characters |
+ | rui_location | no | sample.rui_location | The json output from the RUI location registration interface.  Must not include any line breaks. | - Can be blan  <br> - If not blank must be a valid json string |
diff --git a/src/app.py b/src/app.py
@@ -358,21 +358,32 @@ def get_entity_by_id(id):
     # On entity retrieval, the 'on_read_trigger' doesn't really need a token
     complete_dict = schema_manager.get_complete_entity_result(token, entity_dict)
 
-    # Additional handlings to make sure only public accessible info gets returned for Dataset
-    # A Dataset entity is published doesn't ensure its revisions are also published
-    if (normalized_entity_type == 'Dataset') and (entity_dict['status'].lower() == DATASET_STATUS_PUBLISHED):
-        # The `next_revision_uuid` and `previous_revision_uuid` are only availabe in complete_dict
-        # since they are generated by the 'on_read_trigger' methods
-        # Remove the properties from response if they are not published
-        properties_to_pop = ['next_revision_uuid', 'previous_revision_uuid']
-
-        for prop in properties_to_pop:
-            if prop in complete_dict:
-                revision_entity_dict = query_target_entity(complete_dict[prop], token)
-                # Remove the property from the resulting complete_dict
-                # if the revision is not also published
-                if revision_entity_dict['status'].lower() != DATASET_STATUS_PUBLISHED:
-                    complete_dict.pop(prop)
+    # Additional handlings on dataset revisions
+    # The rule is that a revision can only be made against a published dataset, 
+    # so it should never occur that a consortium level revision is between two published revisions
+    # However, the very last dataset revision can be non-published
+    if normalized_entity_type == 'Dataset':
+        # The `next_revision_uuid` is only availabe in complete_dict because it's generated by the 'on_read_trigger'
+        property_to_pop = 'next_revision_uuid'
+
+        # When the dataset is published but:
+        # - The nexus token is valid but the user doesn't belong to HuBMAP-READ group
+        # - Or the token is valid but doesn't contain group information (auth token or transfer token)
+        # We need to remove the `next_revision_uuid` from response
+        # Otherwise, we should send back the `next_revision_uuid` (if exists) when the member belongs to HuBMAP-Read group
+        if entity_dict['status'].lower() == DATASET_STATUS_PUBLISHED:
+            if not user_in_hubmap_read_group(request):
+                if property_to_pop in complete_dict:
+                    revision_entity_dict = query_target_entity(complete_dict[property_to_pop], token)
+                    # Remove the property from the resulting complete_dict
+                    # if the revision is not published
+                    if revision_entity_dict['status'].lower() != DATASET_STATUS_PUBLISHED:
+                        complete_dict.pop(property_to_pop)
+        # Non-published dataset can NOT have next revisions
+        else:
+            if property_to_pop in complete_dict:
+                # Remove the `next_revision_uuid` from response if it ever exists
+                complete_dict.pop(property_to_pop)
 
     # Also normalize the result based on schema
     final_result = schema_manager.normalize_entity_result_for_response(complete_dict)
