Merge branch 'dev' into etl-gui-changes

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 6.2.0
+current_version = 6.2.1
 commit = True
 tag = False
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>[A-z0-9-]+)
@@ -15,3 +15,7 @@ replace = version='{new_version}',
 [bumpversion:file:deploy/python/version.txt]
 search = {current_version}
 replace = {new_version}
+
+[bumpversion:file:web/package.json]
+search = "version": "{current_version}",
+replace = "version": "{new_version}",

.github/workflows/deploy.yaml

@@ -7,6 +7,10 @@ on:
       - main
       - dev
 
+permissions:
+  id-token: write
+  contents: read
+
 jobs:
   deploy:
     runs-on: ubuntu-latest
@@ -23,11 +27,16 @@ jobs:
     steps:
       - uses: actions/checkout@v3
 
-      - name: "gcloud setup"
-        uses: google-github-actions/setup-gcloud@v1
+      - id: "google-cloud-auth"
+        name: "Authenticate to Google Cloud"
+        uses: "google-github-actions/auth@v1"
         with:
-          project_id: sample-metadata
-          service_account_key: ${{ secrets.GCP_SERVER_DEPLOY_KEY }}
+          workload_identity_provider: "projects/774248915715/locations/global/workloadIdentityPools/gh-deploy-pool/providers/gh-provider"
+          service_account: "[email protected]"
+
+      - id: "google-cloud-sdk-setup"
+        name: "Set up Cloud SDK"
+        uses: google-github-actions/setup-gcloud@v1
 
       - name: "gcloud docker auth"
         run: |

README.md

@@ -1,6 +1,6 @@
 # Sample Metadata
 
-[![codecov](https://codecov.io/gh/populationgenomics/sample-metadata/branch/dev/graph/badge.svg?token=OI3XZYR9HK)](https://codecov.io/gh/populationgenomics/sample-metadata)
+[![codecov](https://codecov.io/gh/populationgenomics/metamist/branch/dev/graph/badge.svg?token=OI3XZYR9HK)](https://codecov.io/gh/populationgenomics/metamist)
 
 Metamist is database that stores **de-identified** -omics metadata.
 
@@ -390,7 +390,7 @@ will build the docker container and supply it to regenerate_api.py.
 
 ```bash
 # SM_DOCKER is a known env variable to regenerate_api.py
-export SM_DOCKER="cpg/sample-metadata-server:dev"
+export SM_DOCKER="cpg/metamist-server:dev"
 docker build --build-arg SM_ENVIRONMENT=local -t $SM_DOCKER -f deploy/api/Dockerfile .
 python regenerate_api.py
 ```

api/server.py

@@ -20,7 +20,7 @@
 from api.settings import PROFILE_REQUESTS, SKIP_DATABASE_CONNECTION
 
 # This tag is automatically updated by bump2version
-_VERSION = '6.2.0'
+_VERSION = '6.2.1'
 
 logger = get_logger()
 

db/backup/README.md

@@ -33,7 +33,7 @@ The full recovery process is detailed below. Follow the recovery stages that are
 3. Clone this repo
 
    > ```bash
-   > git clone https://github.com/populationgenomics/sample-metadata.git
+   > git clone https://github.com/populationgenomics/metamist.git
    > ```
 
 4. Navigate to the appropriate directory
@@ -85,7 +85,7 @@ The full recovery process is detailed below. Follow the recovery stages that are
 
 ### Daily Backup
 
-A cron job runs a [backup script](https://github.com/populationgenomics/sample-metadata/blob/dev/db/backup/backup.py) daily. The script outputs a folder that is uploaded to GCS in the [cpg-sm-backups](https://console.cloud.google.com/storage/browser/cpg-sm-backups;tab=objects?forceOnBucketsSortingFiltering=false&project=sample-metadata&prefix=&forceOnObjectsSortingFiltering=false) bucket.
+A cron job runs a [backup script](https://github.com/populationgenomics/metamist/blob/dev/db/backup/backup.py) daily. The script outputs a folder that is uploaded to GCS in the [cpg-sm-backups](https://console.cloud.google.com/storage/browser/cpg-sm-backups;tab=objects?forceOnBucketsSortingFiltering=false&project=sample-metadata&prefix=&forceOnObjectsSortingFiltering=false) bucket.
 
 All backups will be retained for 30 days in the event that they are deleted.
 Setting up
@@ -141,7 +141,7 @@ IMPORTANT: Do not run the validation script in a production environment. In orde
 2. Clone this repo
 
    > ```bash
-   > git clone https://github.com/populationgenomics/sample-metadata.git
+   > git clone https://github.com/populationgenomics/metamist.git
    > ```
 
 3. Navigate to the directory
@@ -196,4 +196,4 @@ To test our monitoring and alerting policy, once a year our database backups wil
 Further, alongside the procedure to validate the [database restoration](#running-the-validation-script), the SM API will be validated.
 
 1. Update the configuration to point to the new VM as the production VM.
-2. Run the test script, currently under construction [#35](https://github.com/populationgenomics/sample-metadata/pull/35)
+2. Run the test script, currently under construction [#35](https://github.com/populationgenomics/metamist/pull/35)

db/python/tables/project.py

@@ -409,7 +409,7 @@ async def create_project(
         return project_id
 
     async def update_project(self, project_name: str, update: dict, author: str):
-        """Update a sample-metadata project"""
+        """Update a metamist project"""
         await self.check_project_creator_permissions(author)
 
         meta = update.get('meta')

deploy/python/version.txt

@@ -1 +1 @@
-6.2.0
+6.2.1

metamist/parser/generic_metadata_parser.py

@@ -4,20 +4,20 @@
 import re
 import shlex
 from functools import reduce
-from typing import Dict, List, Optional, Any, Tuple, Union
+from typing import Any, Dict, List, Optional, Tuple, Union
 
 import click
 
 from metamist.parser.generic_parser import (
     GenericParser,
     GroupedRow,
-    ParsedSequencingGroup,
+    ParsedAnalysis,
     ParsedAssay,
+    ParsedSequencingGroup,
     # noqa
     SingleRow,
     run_as_sync,
-    ParsedAnalysis,
-)  # noqa
+)
 
 __DOC = """
 Parse CSV / TSV manifest of arbitrary format.
@@ -697,7 +697,7 @@ async def get_analyses_from_sequencing_group(
 @click.option(
     '--project',
     required=True,
-    help='The sample-metadata project ($DATASET) to import manifest into',
+    help='The metamist project ($DATASET) to import manifest into',
 )
 @click.option('--sample-name-column', required=True)
 @click.option(

metamist/parser/generic_parser.py

@@ -426,7 +426,7 @@ def __init__(  # pylint: disable=too-many-arguments
         self.ignore_extra_keys = ignore_extra_keys
 
         if not project:
-            raise ValueError('sample-metadata project is required')
+            raise ValueError('A metamist project is required')
 
         self.project = project
 

metamist/parser/sample_file_map_parser.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 # pylint: disable=too-many-instance-attributes,too-many-locals,unused-argument,wrong-import-order,unused-argument
-from typing import List
 import logging
+from typing import List
 
 import click
 
@@ -120,7 +120,7 @@ def get_sample_id(self, row: SingleRow) -> str:
 @click.command(help=__DOC)
 @click.option(
     '--project',
-    help='The sample-metadata project to import manifest into',
+    help='The metamist project to import manifest into',
 )
 @click.option('--default-sample-type', default='blood')
 @click.option('--default-sequence-type', default='wgs')

metamist_infrastructure/README.md

@@ -18,12 +18,12 @@ The `setup.py` in this directory does some directory magic, it adds:
 You can install from git using:
 
 ```bash
-pip install git+https://github.com/populationgenomics/sample-metadata.git@main#subdirectory=metamist_infrastructure
+pip install git+https://github.com/populationgenomics/metamist.git@main#subdirectory=metamist_infrastructure
 ```
 
 Or add the following to your `requirements.txt`:
 
 ```text
 # other requirements here
-metamist-infrastructure @ git+https://github.com/populationgenomics/sample-metadata.git@main#subdirectory=metamist_infrastructure
+metamist-infrastructure @ git+https://github.com/populationgenomics/metamist.git@main#subdirectory=metamist_infrastructure
 ```

metamist_infrastructure/setup.py

@@ -19,7 +19,7 @@
     description='Metamist infrastructure plugin for cpg-infrastructure',
     long_description=readme,
     long_description_content_type='text/markdown',
-    url=f'https://github.com/populationgenomics/sample-metadata',
+    url='https://github.com/populationgenomics/metamist',
     license='MIT',
     packages=[
         'metamist_infrastructure',

scripts/arbitrary_sm.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # pylint: disable=no-member,consider-using-with
 """
-Run the sample-metadata API through the analysis runner
+Run the metamist API through the analysis runner
 in a very generic, customisable way!
 
 For example:
@@ -11,13 +11,12 @@
         --json '{"project": "acute-care", "external_id": "<external-id>"}'
 
 """
-from typing import List
-import os.path
-import logging
-import subprocess
-
 import argparse
 import json
+import logging
+import os.path
+import subprocess
+from typing import List
 
 from metamist import apis
 from metamist.model_utils import file_type
@@ -39,7 +38,7 @@ def run_sm(
     api = getattr(apis, api_class_name)
     api_instance = api()
 
-    # the latest sample-metadata API wants an IOBase, so let's
+    # the latest metamist API wants an IOBase, so let's
     # scan through the params, open and substitute the files
     openapi_types = getattr(api_instance, f'{method_name}_endpoint').__dict__[
         'openapi_types'
@@ -90,7 +89,7 @@ def from_args(args):
 def main(args=None):
     """Main function, parses sys.argv"""
 
-    parser = argparse.ArgumentParser('Arbitrary sample-metadata script')
+    parser = argparse.ArgumentParser('Arbitrary metamist script')
     parser.add_argument('api_name')
     parser.add_argument('method_name')
     parser.add_argument(

scripts/back_populate_library_type.py

@@ -6,6 +6,7 @@
 """
 import logging
 import re
+
 import click
 
 from metamist.apis import AssayApi
@@ -45,7 +46,7 @@
 @click.option(
     '--project',
     required=True,
-    help='The sample-metadata project ($DATASET)',
+    help='The metamist project ($DATASET)',
 )
 @click.option(
     '-d',

scripts/back_populate_sequences.py

@@ -10,6 +10,7 @@
 The assay ID would be HTJMHDSX3_4_220817_FD123456
 """
 import logging
+
 import click
 
 from metamist.apis import AssayApi
@@ -24,7 +25,7 @@
 @click.option(
     '--project',
     required=True,
-    help='The sample-metadata project ($DATASET)',
+    help='The metamist project ($DATASET)',
 )
 def main(project: str):
     """Back populate external_ids for existing assays"""