Merge branch 'master' into dh2-i18n-rc1

Author: ddooley

script/dh-validate.py

@@ -53,6 +53,9 @@
 from linkml_runtime.dumpers.yaml_dumper import YAMLDumper
 import subprocess
 
+BOOLEANS = {'y':1, 'yes':1, 't':1, 'true':1, 'on':1, '1':1,
+ 'n':0, 'no':0, 'f':0, 'false':0, 'off':0, '0':0}
+
 def init_parser():
 
 	parser = argparse.ArgumentParser(
@@ -74,12 +77,6 @@ def init_parser():
 		required=False, 
 	  help="A schema class to test given data file against.");
 
-	parser.add_argument("-S", "--index-slot", 
-		dest="index_slot", 
-		metavar="TEXT",
-		required=False, 
-	  help="A slot within target class which acts as an identifier or unique key. This is required for CSV dumping/loading.  It is optional when this slot can be identified automatically as the only identifier or unique_key in the slot.");
-
 	parser.add_argument('data_sources', 
 		metavar='DATA_SOURCES', 
 		#nargs='+',
@@ -142,10 +139,7 @@ def getTargetClass(SCHEMA, target_class, slot_key = None):
 
 			break;
 
-	if not found: 
-		exit("Target class [" + target_class + "] does not have an identifier or key slot!");
-
-	print ("index:", slot_key);
+	print ("Identifier slot:", slot_key);
 	return (target_class, slot_key);
 
 
@@ -392,6 +386,9 @@ def getLinkMLTransform(SCHEMA, template, row_data):
 			# datatype
 			for slot_range in ranges:
 				match slot_range:
+					case 'boolean':
+						if val.lower() in BOOLEANS:
+							output_val = bool(BOOLEANS[val.lower()]);
 					case 'integer': 
 						if isInteger(val): 
 							output_val = int(val);

web/templates/ambr/schema.json

@@ -2539,6 +2539,10 @@
       "name": "sample_received_date",
       "description": "The date on which the sample was received.",
       "title": "sample received date",
+      "todos": [
+        ">=2019-10-01",
+        "<={today}"
+      ],
       "comments": [
         "The date should be provided in ISO 8601 standard format \"YYYY-MM-DD\"."
       ],
@@ -2923,7 +2927,7 @@
     },
     "collection_method": {
       "name": "collection_method",
-      "description": "The process used to collect the sample e.g. phlebotamy, necropsy.",
+      "description": "The process used to collect the sample e.g. phlebotomy, necropsy.",
       "title": "collection method",
       "comments": [
         "Provide a descriptor if a collection method was used for sampling. Use the picklist provided in the template.  If a desired term is missing from the picklist, contact [email protected]. If not applicable, do not leave blank. Choose a null value. Information for populating this field may be available in the \"Source of Isolation\" field in the Alberta Microbiota Repository (AMBR) Master file."
@@ -3442,6 +3446,10 @@
       "name": "sequencing_date",
       "description": "The date the sample was sequenced.",
       "title": "sequencing date",
+      "todos": [
+        ">=2019-10-01",
+        "<={today}"
+      ],
       "comments": [
         "The date should be provided in ISO 8601 standard format \"YYYY-MM-DD\"."
       ],
@@ -4443,6 +4451,10 @@
           "name": "sample_received_date",
           "description": "The date on which the sample was received.",
           "title": "sample received date",
+          "todos": [
+            ">=2019-10-01",
+            "<={today}"
+          ],
           "comments": [
             "The date should be provided in ISO 8601 standard format \"YYYY-MM-DD\"."
           ],
@@ -4887,7 +4899,7 @@
         },
         "collection_method": {
           "name": "collection_method",
-          "description": "The process used to collect the sample e.g. phlebotamy, necropsy.",
+          "description": "The process used to collect the sample e.g. phlebotomy, necropsy.",
           "title": "collection method",
           "comments": [
             "Provide a descriptor if a collection method was used for sampling. Use the picklist provided in the template.  If a desired term is missing from the picklist, contact [email protected]. If not applicable, do not leave blank. Choose a null value. Information for populating this field may be available in the \"Source of Isolation\" field in the Alberta Microbiota Repository (AMBR) Master file."
@@ -5490,6 +5502,10 @@
           "name": "sequencing_date",
           "description": "The date the sample was sequenced.",
           "title": "sequencing date",
+          "todos": [
+            ">=2019-10-01",
+            "<={today}"
+          ],
           "comments": [
             "The date should be provided in ISO 8601 standard format \"YYYY-MM-DD\"."
           ],

web/templates/ambr/schema.yaml

@@ -388,6 +388,9 @@ slots:
     any_of:
     - range: date
     - range: NullValueMenu
+    todos:
+    - '>=2019-10-01'
+    - <={today}
     examples:
     - value: '2020-03-20'
   geo_loc_name_country:
@@ -608,7 +611,7 @@ slots:
   collection_method:
     name: collection_method
     title: collection method
-    description: The process used to collect the sample e.g. phlebotamy, necropsy.
+    description: The process used to collect the sample e.g. phlebotomy, necropsy.
     comments: Provide a descriptor if a collection method was used for sampling. Use
       the picklist provided in the template.  If a desired term is missing from the
       picklist, contact [email protected]. If not applicable, do not leave blank.
@@ -941,6 +944,9 @@ slots:
     any_of:
     - range: date
     - range: NullValueMenu
+    todos:
+    - '>=2019-10-01'
+    - <={today}
     examples:
     - value: '2020-06-22'
   library_id:

web/templates/ambr/schema_slots.tsv

@@ -9,7 +9,7 @@ AMBR		GENEPIO:0001122	Database Identifiers	database_identifiers
 	Sample collection and processing	GENEPIO:0001156	sample collector contact email	sample_collector_contact_email	WhitespaceMinimizedString								^\S+@\S+\.\S+$		The email address of the contact responsible for follow-up regarding the sample.	The email address can represent a specific individual or lab e.g. [email protected], or [email protected]	[email protected]					
 	Sample collection and processing	GENEPIO:0001158	sample collector contact address	sample_collector_contact_address	WhitespaceMinimizedString										The mailing address of the agency submitting the sample.	The mailing address should be in the format: Street number and name, City, Province/Territory, Postal Code, Country	655 Lab St, Vancouver, British Columbia, V5N 2A2, Canada					
 	Sample collection and processing	GENEPIO:0001174	sample collection date	sample_collection_date	date	NullValueMenu				TRUE	2019-10-01	{today}			The date on which the sample was collected.	The date should be provided in ISO 8601 standard format "YYYY-MM-DD".	2020-03-16					
-	Sample collection and processing	GENEPIO:0001179	sample received date	sample_received_date	date	NullValueMenu									The date on which the sample was received.	The date should be provided in ISO 8601 standard format "YYYY-MM-DD".	2020-03-20					
+	Sample collection and processing	GENEPIO:0001179	sample received date	sample_received_date	date	NullValueMenu					2019-10-01	{today}			The date on which the sample was received.	The date should be provided in ISO 8601 standard format "YYYY-MM-DD".	2020-03-20					
 	Sample collection and processing	GENEPIO:0001181	geo_loc_name (country)	geo_loc_name_country	GeoLocNameCountryMenu	NullValueMenu				TRUE					The country where the sample was collected.	Provide the country name from the controlled vocabulary provided.	Canada					
 	Sample collection and processing	GENEPIO:0001185	geo_loc_name (state/province/territory)	geo_loc_name_state_province_territory	WhitespaceMinimizedString	NullValueMenu				TRUE					The province/territory where the sample was collected.	Provide the province/territory name from the controlled vocabulary provided.	Saskatchewan					
 	Sample collection and processing	GENEPIO:0001189	geo_loc_name (city)	geo_loc_name_city	WhitespaceMinimizedString										The city where the sample was collected.	Provide the city name. Use this look-up service to identify the standardized term: https://www.ebi.ac.uk/ols/ontologies/gaz	Medicine Hat					
@@ -24,7 +24,7 @@ AMBR		GENEPIO:0001122	Database Identifiers	database_identifiers
 	Sample collection and processing	GENEPIO:0001223	environmental material	environmental_material	EnvironmentalMaterialMenu	NullValueMenu		TRUE	TRUE						A substance obtained from the natural or man-made environment e.g. soil, water, sewage.	Provide a descriptor if an environmental material was sampled. Use the picklist provided in the template.  If a desired term is missing from the picklist, contact [email protected]. If not applicable, do not leave blank. Choose a null value. Information for populating this field may be available in the "Source of Isolation" field in the Alberta Microbiota Repository (AMBR) Master file.	Bandage					
 	Sample collection and processing	GENEPIO:0001232	environmental site	environmental_site	EnvironmentalSiteMenu	NullValueMenu		TRUE	TRUE						An environmental location may describe a site in the natural or built environment e.g. contact surface, metal can, hospital, wet market, bat cave.	Provide a descriptor if an environmental site was sampled. Use the picklist provided in the template.  If a desired term is missing from the picklist, contact [email protected]. If not applicable, do not leave blank. Choose a null value. Information for populating this field may be available in the "Source of Isolation" field in the Alberta Microbiota Repository (AMBR) Master file.	Hospital					
 	Sample collection and processing	GENEPIO:0001234	collection device	collection_device	CollectionDeviceMenu	NullValueMenu		TRUE	TRUE						The instrument or container used to collect the sample e.g. swab.	Provide a descriptor if a device was used for sampling. Use the picklist provided in the template. If a desired term is missing from the picklist, contact [email protected]. If not applicable, do not leave blank. Choose a null value. Information for populating this field may be available in the "Source of Isolation" field in the Alberta Microbiota Repository (AMBR) Master file.	Swab					
-	Sample collection and processing	GENEPIO:0001241	collection method	collection_method	CollectionMethodMenu	NullValueMenu		TRUE	TRUE						The process used to collect the sample e.g. phlebotamy, necropsy.	Provide a descriptor if a collection method was used for sampling. Use the picklist provided in the template.  If a desired term is missing from the picklist, contact [email protected]. If not applicable, do not leave blank. Choose a null value. Information for populating this field may be available in the "Source of Isolation" field in the Alberta Microbiota Repository (AMBR) Master file.	Biopsy					
+	Sample collection and processing	GENEPIO:0001241	collection method	collection_method	CollectionMethodMenu	NullValueMenu		TRUE	TRUE						The process used to collect the sample e.g. phlebotomy, necropsy.	Provide a descriptor if a collection method was used for sampling. Use the picklist provided in the template.  If a desired term is missing from the picklist, contact [email protected]. If not applicable, do not leave blank. Choose a null value. Information for populating this field may be available in the "Source of Isolation" field in the Alberta Microbiota Repository (AMBR) Master file.	Biopsy					
 	Sample collection and processing	GENEPIO:0001243	collection protocol	collection_protocol	WhitespaceMinimizedString										The name and version of a particular protocol used for sampling.	Free text. Information for populating this field may be available in the "Source of Isolation" field in the Alberta Microbiota Repository (AMBR) Master file.	Collection_protocol_Children's Hospital biofilm study (A3-701-01)					
 	Sample collection and processing	GENEPIO:0001253	specimen processing	specimen_processing	SpecimenProcessingMenu	NullValueMenu		TRUE		TRUE					Any processing applied to the sample during or after receiving the sample.	If multiple PCR products were generated from the isolate using different primer sets, indicate that the sequence records represents the same isolate by selecting "Biological replicate" in the "specimen processing" field. Every different sequence experiment should have its own record (i.e. if different amplicons have the same sequence but were generated using different primer sets, these should be stored as separate entries/lines in the spreadsheet). Information about replicates may be available in the "Top-hit taxon (taxa)" or "Trimmed Ribosomal Sequence" fields if there are multiple values for the same "Strain ID#" in the Alberta Microbiota Repository (AMBR) Master file.	Biological replicate					
 	Sample collection and processing	GENEPIO:0100311	specimen processing details	specimen_processing_details	WhitespaceMinimizedString										Detailed information regarding the processing applied to a sample during or after receiving the sample.	Provide a free text description of any processing details applied to a sample. Information about replicates may be available in the "Top-hit taxon (taxa)" or "Trimmed Ribosomal Sequence" fields if there are multiple values for the same "Strain ID#" in the Alberta Microbiota Repository (AMBR) Master file.	Multiple amplicons generated for isolate SA32 using different primer sets 					
@@ -48,7 +48,7 @@ AMBR		GENEPIO:0001122	Database Identifiers	database_identifiers
 	Sequencing	GENEPIO:0100422	sequenced by contact email	sequenced_by_contact_email	WhitespaceMinimizedString										The email address of the contact responsible for follow-up regarding the sequence.	Provide the email associated with the listed contact. As personnel turnover may render an individual's email obsolete, it is more prefereable to provide an address for a position or lab, to ensure accuracy of information and institutional memory. If the information is unknown or cannot be provided, leave blank or provide a null value.	[email protected]					
 	Sequencing	GENEPIO:0001445	purpose of sequencing	purpose_of_sequencing	PurposeOfSequencingMenu	NullValueMenu									The reason that the sample was sequenced.	The reason why a sample was originally collected may differ from the reason why it was selected for sequencing. The reason a sample was sequenced may provide information about potential biases in sequencing strategy. Provide the purpose of sequencing from the picklist in the template. The reason for sample collection should be indicated in the "purpose of sampling" field.	Research					
 	Sequencing	GENEPIO:0001446	purpose of sequencing details	purpose_of_sequencing_details	WhitespaceMinimizedString	NullValueMenu									The description of why the sample was sequenced providing specific details.	Provide an expanded description of why the sample was sequenced using free text. This information can provide details about why the sample source might contain antibiotic potentiators.	Screening for antibiotic potentiators in Cystic fibrosis disease contexts.					
-	Sequencing	GENEPIO:0001447	sequencing date	sequencing_date	date	NullValueMenu									The date the sample was sequenced.	The date should be provided in ISO 8601 standard format "YYYY-MM-DD".	2020-06-22					
+	Sequencing	GENEPIO:0001447	sequencing date	sequencing_date	date	NullValueMenu					2019-10-01	{today}			The date the sample was sequenced.	The date should be provided in ISO 8601 standard format "YYYY-MM-DD".	2020-06-22					
 	Sequencing	GENEPIO:0001448	library ID	library_id	WhitespaceMinimizedString										The user-specified identifier for the library prepared for sequencing.	Provide the name of the run. This value maps to information in the "Sequencing Batch #" field Alberta Microbiota Repository (AMBR) Master file.	1876515_SA01_Plate 02			library ID		
 	Sequencing	GENEPIO:0001452	sequencing instrument	sequencing_instrument	SequencingInstrumentMenu	NullValueMenu		TRUE	TRUE						The model of the sequencing instrument used.	Select a sequencing instrument from the picklist provided in the template.	Oxford Nanopore MinION					
 	Sequencing	GENEPIO:0001453	sequencing protocol name	sequencing_protocol_name	WhitespaceMinimizedString					TRUE					The name and version number of the sequencing protocol used.	Provide the name and version of the sequencing protocol e.g. 1D_DNA_MinION	https://www.protocols.io/view/covid-19-artic-v3-illumina-library-construction-an-bibtkann					

web/templates/canada_covid19/locales/fr/schema.json

@@ -2998,6 +2998,10 @@
           "text": "Ontario Institute for Cancer Research (OICR)",
           "title": "Institut ontarien de recherche sur le cancer (IORC)"
         },
+        "Ontario COVID-19 Genomic Network": {
+          "text": "Ontario COVID-19 Genomic Network",
+          "title": "Réseau génomique ontarien COVID-19"
+        },
         "Prince Edward Island - Health PEI": {
           "text": "Prince Edward Island - Health PEI",
           "title": "Île-du-Prince-Édouard – Santé Î.-P.-É."
@@ -3033,6 +3037,10 @@
           "text": "Eastern Ontario Regional Laboratory Association",
           "title": "Association des laboratoires régionaux de l’Est de l’Ontario"
         },
+        "Kingston Health Sciences Centre": {
+          "text": "Kingston Health Sciences Centre",
+          "title": "Centre des sciences de la santé de Kingston"
+        },
         "Lake of the Woods District Hospital - Ontario": {
           "text": "Lake of the Woods District Hospital - Ontario",
           "title": "Lake of the Woods District Hospital – Ontario"

web/templates/canada_covid19/locales/fr/schema.yaml

@@ -3717,6 +3717,8 @@ enums:
         title: "Autorit\xE9 sanitaire de la Nouvelle-\xC9cosse"
       Ontario Institute for Cancer Research (OICR):
         title: Institut ontarien de recherche sur le cancer (IORC)
+      Ontario COVID-19 Genomic Network:
+        title: "R\xE9seau g\xE9nomique ontarien COVID-19"
       Prince Edward Island - Health PEI:
         title: "\xCEle-du-Prince-\xC9douard\_\u2013 Sant\xE9 \xCE.-P.-\xC9."
       Public Health Ontario (PHO):
@@ -3737,6 +3739,8 @@ enums:
       Eastern Ontario Regional Laboratory Association:
         title: "Association des laboratoires r\xE9gionaux de l\u2019Est de l\u2019\
           Ontario"
+      Kingston Health Sciences Centre:
+        title: "Centre des sciences de la sant\xE9 de Kingston"
       Lake of the Woods District Hospital - Ontario:
         title: "Lake of the Woods District Hospital\_\u2013 Ontario"
       Manitoba Cadham Provincial Laboratory: