Merge pull request #294 from dandi/devendorize

Vendor-Configurable Metadata Models

Author: yarikoptic

.github/workflows/test.yml

@@ -9,21 +9,32 @@ on:
 jobs:
   test:
     runs-on: ${{ matrix.os }}
-    env:
-      NO_ET: 1
-      DATACITE_DEV_PASSWORD: ${{ secrets.DATACITE_DEV_PASSWORD }}
+    defaults:
+      run:
+        shell: bash
     strategy:
       fail-fast: false
       matrix:
-        os:
-          - windows-latest
-          - ubuntu-latest
-          - macos-latest
-        python:
-          - 3.9
-          - '3.10'
-          - '3.11'
-          - '3.12'
+        os: [windows-latest, ubuntu-latest, macos-latest]
+        python: ['3.9', '3.10', '3.11', '3.12']
+        vendored_env: [unvendored]
+        include:
+          - os: ubuntu-latest
+            python: '3.9'
+            vendored_env: dandi
+            instance_name: DANDI
+            instance_identifier: 'RRID:SCR_017571'
+            doi_prefix: '10.80507'
+          - os: ubuntu-latest
+            python: '3.9'
+            vendored_env: ember-dandi
+            instance_name: EMBER-DANDI
+            instance_identifier: 'RRID:SCR_026700'
+            doi_prefix: '10.82754'
+          - os: ubuntu-latest
+            python: '3.9'
+            vendored_env: ember-dandi-no-doi
+            instance_name: EMBER-DANDI
     steps:
     - name: Set up environment
       uses: actions/checkout@v5
@@ -42,7 +53,36 @@ jobs:
         python -m pip install --upgrade pip wheel
         python -m pip install --upgrade tox
 
+     # Set only if matrix.instance_name is defined
+    - name: Set DANDI_INSTANCE_NAME
+      if: ${{ matrix.instance_name }}
+      run: echo "DANDI_INSTANCE_NAME=${{ matrix.instance_name }}" >> "$GITHUB_ENV"
+
+    # Set only if matrix.instance_identifier is defined
+    - name: Set DANDI_INSTANCE_IDENTIFIER
+      if: ${{ matrix.instance_identifier }}
+      run: echo "DANDI_INSTANCE_IDENTIFIER=${{ matrix.instance_identifier }}" >> "$GITHUB_ENV"
+
+    # Set only if matrix.doi_prefix is defined
+    - name: Set DANDI_DOI_PREFIX
+      if: ${{ matrix.doi_prefix }}
+      run: echo "DANDI_DOI_PREFIX=${{ matrix.doi_prefix }}" >> "$GITHUB_ENV"
+
+    - name: Set DANDI DataCite credentials
+      if: ${{ matrix.vendored_env == 'dandi' }}
+      run: |
+        echo "DATACITE_DEV_LOGIN=${{ secrets.DATACITE_DEV_DANDI_LOGIN }}" >> "$GITHUB_ENV"
+        echo "DATACITE_DEV_PASSWORD=${{ secrets.DATACITE_DEV_DANDI_PASSWORD }}" >> "$GITHUB_ENV"
+
+    - name: Set EMBER DataCite credentials
+      if: ${{ matrix.vendored_env == 'ember-dandi' }}
+      run: |
+        echo "DATACITE_DEV_LOGIN=${{ secrets.DATACITE_DEV_EMBER_LOGIN }}" >> "$GITHUB_ENV"
+        echo "DATACITE_DEV_PASSWORD=${{ secrets.DATACITE_DEV_EMBER_PASSWORD }}" >> "$GITHUB_ENV"
+
     - name: Run all tests
+      env:
+        NO_ET: 1
       run: tox -e py -- -s --cov-report=xml
 
     - name: Upload coverage to Codecov

README.md

@@ -30,6 +30,27 @@ Important files in this repository include:
 - [metadata.py](./dandischema/metadata.py) - contains functions for validating, migrating, and aggregating metadata
 - [datacite package](./dandischema/datacite) - contains functions for converting Dandiset metadata to DataCite metadata
 
+## Customization with Vendor Information
+
+The DANDI metadata models defined in this library can be customized with vendor-specific information.
+The parameters of the customization are defined by the fields of the `Config` class in
+[dandischema/conf.py](./dandischema/conf.py). The `Config` class is a subclass of
+[`pydantic_settings.BaseSettings`](https://docs.pydantic.dev/latest/concepts/pydantic_settings/),
+and the values of the fields in an instance of the `Config` class can be set through environment
+variables and `.env` files, as documented in
+[the Pydantic Settings documentation](https://docs.pydantic.dev/latest/concepts/pydantic_settings/).
+Specifically,
+
+- The value of a field is set from an environment variable with the same name, case-insensitively,
+  as one of the aliases of the field. For example, the `instance_name` field can be set from
+  the `DANDI_INSTANCE_NAME` or `DJANGO_DANDI_INSTANCE_NAME` environment variable.
+- A value of a complex type (e.g., `list`, `set`, `dict`) should be expressed as a JSON-encoded string
+  in an environment variable. For example, the value for the `licenses` field, which is of
+  type `set`, can be set from the `DANDI_LICENSES` environment variable defined as the following:
+  ```shell
+  export DANDI_LICENSES='["spdx:CC0-1.0", "spdx:CC-BY-4.0"]'
+  ```
+
 ## Resources
 
 * To learn how to interact with the DANDI archive,

dandischema/__init__.py

@@ -1,4 +1,3 @@
-__all__ = ["__version__", "migrate", "validate"]
+__all__ = ["__version__"]
 
 from ._version import __version__
-from .metadata import migrate, validate