switch from misspell to pyspelling and introduce black formatting

.github/workflows/docs.yml

@@ -12,10 +12,9 @@ jobs:
     runs-on: ${{ matrix.os }}
 
     steps:
-    - name: Spell check install
-      run: curl -L https://git.io/misspell | bash
-    - name: Spell check docs
-      run: bin/misspell -error docs/*
+    - uses: actions/checkout@master
+    - uses: rojopolis/spellcheck-github-actions@0.20.0
+      name: Spellcheck
 
   code_docs:
     strategy:

.github/workflows/style.yml

@@ -26,9 +26,11 @@ jobs:
       run: tox -e flake8
     - name: Do bandit static check with tox
       run: tox -e bandit
+    - name: Black formatting check
+      run: tox -e black
     - name: Install libcurl-devel
       run: |
         sudo apt-get update
         sudo apt-get install libcurl4-openssl-dev
-    - name: Do typing check with tox
+    - name: Type hints check
       run: tox -e mypy

.spellcheck.yml

@@ -0,0 +1,27 @@
+matrix:
+- name: Markdown
+  aspell:
+    lang: en
+  dictionary:
+    wordlists:
+    - .wordlist.txt
+    encoding: utf-8
+  pipeline:
+  - pyspelling.filters.markdown:
+  - pyspelling.filters.context:
+      context_visible_first: true
+      escapes: '\\[\\`~]'
+      delimiters:
+      # Ignore text between inline back ticks as this is code or hightlight words
+      - open: '(?P<open>`+)'
+        close: '(?P=open)'
+      # Ignore surrounded in <> as in RST it is link
+      - open: '<([A-Za-z0-9-_:.]+)|(https?://[^\\s/$.?#].[^\\s]+|[A-Za-z0-9-_:.]+)'
+        close: '>'
+      # Ignore code in RST starting with $
+      - open: '\$.+'
+        close: ''
+  sources:
+  - 'docs/*.rst'
+  - '**/*.md'
+  default_encoding: utf-8

.wordlist.txt

@@ -0,0 +1,144 @@
+AAI
+accessType
+aiohttp
+alleleCount
+alleleRequest
+alternateBases
+alternativeUrl
+api
+APIBehavior
+APITest
+apiVersion
+assemblyId
+automodule
+autosummary
+beacondb
+beaconId
+beaconpy
+BND
+BONA
+btree
+callCount
+cd
+chr
+CHR
+claimName
+conf
+config
+contactUrl
+containerPort
+createdAt
+createDateTime
+csc
+CSC
+cscfi
+CSCfi
+datafile
+datafiles
+dataloader
+dataset
+DATASET
+datasetAlleleResponses
+datasetHandover
+datasetId
+datasetIds
+datasets
+dedent
+documentationUrl
+ebi
+ega
+EGA
+endMax
+endMin
+env
+ENV
+Espoo
+examplebrowser
+exampleid
+externalUrl
+fi
+FIDE
+finland
+ga
+genomic
+gh
+GH
+GHBeacon
+github
+GRCh
+Gunicorn
+GunicornUVLoopWebWorker
+handoverType
+hg
+hostPath
+html
+http
+HttpLocust
+https
+ICT
+ietf
+imagePullPolicy
+includeDatasetResponses
+ini
+init
+io
+javascript
+jpg
+json
+JSON
+JWK
+jwt
+JWT
+Keilaranta
+literalinclude
+localhost
+logoUrl
+matchLabels
+mateID
+mateName
+mateStart
+mountPath
+namespace
+NodePort
+OAuth
+orgInfo
+persistentVolumeClaim
+pgtune
+postgres
+POSTGRES
+py
+readthedocs
+referenceBases
+referenceID
+referenceName
+restartPolicy
+rfc
+RGB
+sampleAlleleRequests
+sampleCount
+schemas
+secretKeyRef
+SNP
+sql
+startMax
+startMin
+targetPort
+TaskSet
+TCP
+toctree
+txt
+ua
+uk
+updatedAt
+updateDateTime
+uri
+url
+utils
+valueFrom
+variantCount
+varianttype
+variantType
+vcf
+volumeMounts
+welcomeUrl
+www

beacon_api/__init__.py

@@ -24,7 +24,7 @@
 __url__ = CONFIG_INFO.url
 __alturl__ = CONFIG_INFO.alturl
 __createtime__ = CONFIG_INFO.createtime
-__updatetime__ = datetime.datetime.now().strftime('%Y-%m-%dT%H:%M:%SZ')  # Every restart of the application means an update to it
+__updatetime__ = datetime.datetime.now().strftime("%Y-%m-%dT%H:%M:%SZ")  # Every restart of the application means an update to it
 
 __org_id__ = CONFIG_INFO.org_id
 __org_name__ = CONFIG_INFO.org_name
@@ -33,12 +33,10 @@
 __org_welcomeUrl__ = CONFIG_INFO.org_welcomeUrl
 __org_contactUrl__ = CONFIG_INFO.org_contactUrl
 __org_logoUrl__ = CONFIG_INFO.org_logoUrl
-__org_info__ = {'orgInfo': CONFIG_INFO.org_info}
+__org_info__ = {"orgInfo": CONFIG_INFO.org_info}
 
 __sample_queries__ = SAMPLE_QUERIES
 
 # GA4GH Discovery
-__service_type__ = {'group': f'{CONFIG_INFO.service_group}',
-                    'artifact': f'{CONFIG_INFO.service_artifact}',
-                    'version': f'{__apiVersion__}'}
+__service_type__ = {"group": f"{CONFIG_INFO.service_group}", "artifact": f"{CONFIG_INFO.service_artifact}", "version": f"{__apiVersion__}"}
 __service_env__ = CONFIG_INFO.environment

beacon_api/conf/config.py

@@ -18,28 +18,30 @@
 import asyncpg
 from typing import Awaitable
 
-DB_SCHEMA = os.environ.get('DATABASE_SCHEMA', None)
+DB_SCHEMA = os.environ.get("DATABASE_SCHEMA", None)
 
 
 async def init_db_pool() -> Awaitable:
     """Create a connection pool.
 
     As we will have frequent requests to the database it is recommended to create a connection pool.
     """
-    return await asyncpg.create_pool(host=os.environ.get('DATABASE_URL', 'localhost'),
-                                     port=os.environ.get('DATABASE_PORT', '5432'),
-                                     user=os.environ.get('DATABASE_USER', 'beacon'),
-                                     password=os.environ.get('DATABASE_PASSWORD', 'beacon'),
-                                     database=os.environ.get('DATABASE_NAME', 'beacondb'),
-                                     # Multiple schemas can be used, and they need to be comma separated
-                                     server_settings={'search_path': DB_SCHEMA if DB_SCHEMA else 'public'},
-                                     # initializing with 0 connections allows the web server to
-                                     # start and also continue to live
-                                     min_size=0,
-                                     # for now limiting the number of connections in the pool
-                                     max_size=20,
-                                     max_queries=50000,
-                                     timeout=120,
-                                     command_timeout=180,
-                                     max_cached_statement_lifetime=0,
-                                     max_inactive_connection_lifetime=180)
+    return await asyncpg.create_pool(
+        host=os.environ.get("DATABASE_URL", "localhost"),
+        port=os.environ.get("DATABASE_PORT", "5432"),
+        user=os.environ.get("DATABASE_USER", "beacon"),
+        password=os.environ.get("DATABASE_PASSWORD", "beacon"),
+        database=os.environ.get("DATABASE_NAME", "beacondb"),
+        # Multiple schemas can be used, and they need to be comma separated
+        server_settings={"search_path": DB_SCHEMA if DB_SCHEMA else "public"},
+        # initializing with 0 connections allows the web server to
+        # start and also continue to live
+        min_size=0,
+        # for now limiting the number of connections in the pool
+        max_size=20,
+        max_queries=50000,
+        timeout=120,
+        command_timeout=180,
+        max_cached_statement_lifetime=0,
+        max_inactive_connection_lifetime=180,
+    )

data/example_metadata.json

@@ -1,5 +1,5 @@
 {
-    "name": "1000 genomoe",
+    "name": "1000 genome",
     "datasetId": "urn:hg:1000genome",
     "description": "Data from the 1000 Genomes Project. The 1000 Genomes Project ran between 2008 and 2015, creating the largest public catalogue of human variation and genotype data. As the project ended, the Data Coordination Centre at EMBL-EBI has received continued funding from the Wellcome Trust to maintain and expand the resource.",
     "assemblyId": "GRCh38",

deploy/test/example_metadata_controlled.json

@@ -1,5 +1,5 @@
 {
-    "name": "1000 genomoe",
+    "name": "1000 genome",
     "datasetId": "urn:hg:1000genome:controlled",
     "description": "Data from the 1000 Genomes Project. The 1000 Genomes Project ran between 2008 and 2015, creating the largest public catalogue of human variation and genotype data. As the project ended, the Data Coordination Centre at EMBL-EBI has received continued funding from the Wellcome Trust to maintain and expand the resource.",
     "assemblyId": "GRCh38",

deploy/test/example_metadata_controlled1.json

@@ -1,5 +1,5 @@
 {
-    "name": "1000 genomoe",
+    "name": "1000 genome",
     "datasetId": "urn:hg:1000genome:controlled1",
     "description": "Data from the 1000 Genomes Project. The 1000 Genomes Project ran between 2008 and 2015, creating the largest public catalogue of human variation and genotype data. As the project ended, the Data Coordination Centre at EMBL-EBI has received continued funding from the Wellcome Trust to maintain and expand the resource.",
     "assemblyId": "GRCh38",

deploy/test/example_metadata_registered.json

@@ -1,5 +1,5 @@
 {
-    "name": "1000 genomoe",
+    "name": "1000 genome",
     "datasetId": "urn:hg:1000genome:registered",
     "description": "Data from the 1000 Genomes Project. The 1000 Genomes Project ran between 2008 and 2015, creating the largest public catalogue of human variation and genotype data. As the project ended, the Data Coordination Centre at EMBL-EBI has received continued funding from the Wellcome Trust to maintain and expand the resource.",
     "assemblyId": "GRCh38",