add validation for code metadata (#78)

And prepare way for transition to YAML format for code metadata.

.github/codes.py

@@ -0,0 +1,64 @@
+# -*- coding: utf-8 -*-
+"""Schema and validation of simulation code metadata."""
+from dataclasses import dataclass
+from enum import Enum
+from typing import Dict, Optional, List
+from pathlib import Path
+from serde import serialize, deserialize, json, yaml
+
+DATA_DIR = Path(__file__).parent.parent / 'src' / 'data'
+
+class QueryMethods(str, Enum):
+    """Methods for querying Google Scholar."""
+    SEARCH = 'search term'
+    PUBLICATION = 'publication'
+
+
+@deserialize
+@serialize
+@dataclass
+class Code:  # pylint: disable=too-many-instance-attributes
+    """Class representing a code.
+    
+    Optional fields are no longer used by the web application.
+    Fields with default values are used by the web application.
+    """
+    name: str
+    benchmarks: List[str]
+    homepage: str
+    author_name: Optional[str]
+    query_method: str
+    query_string: str
+    types: List[str]
+    license: str
+    tags: List
+    nomad_tags: list = None
+    query_publication_id: int = None
+    notes: str = None
+    license_annotation: str = None
+
+def read_codes_json(path: Path = DATA_DIR / 'codes.json') -> Dict[str, Code]:
+    """Read codes.json file and return dictionary."""
+
+    with open(path) as handle:
+        return json.from_json(Dict[str, Code], handle.read())
+
+def write_codes_yaml(path: Path = DATA_DIR / 'codes.yaml', codes: Dict[str, Code] = read_codes_json()) -> None:
+    """Write codes.yaml file.
+    
+    May use if switch to yaml format is made.
+    """
+
+    with open(path, 'w') as handle:
+        handle.write(yaml.to_yaml(codes))
+
+def read_codes_yaml(path: Path = DATA_DIR / 'codes.yaml') -> Dict[str, Code]:
+    """Read codes.yaml file and return dictionary.
+
+    May use if switch to yaml format is made.
+    """
+
+    with open(path) as handle:
+        return yaml.from_yaml(Dict[str, Code], handle.read())
+
+print(read_codes_json())

.github/requirements.txt

@@ -0,0 +1 @@
+pyserde[yaml]~=0.4.0

.github/workflows/ci.yml

@@ -39,3 +39,16 @@ jobs:
         run: npm install --include=dev
       - name: Run ESLint
         run: npx eslint 'src/**/*js'
+
+  validate-codes:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python 3.9
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.9
+      - name: Install dependencies
+        run: pip install -r .github/requirements.txt
+      - name: Validate code metadata
+        run: python .github/codes.py

src/text/about.md

@@ -4,9 +4,9 @@
 
 Practitioners and software developers in the field of atomistic simulations may find it useful for:
 
- * getting an overview of major simulation engines with specific features, licensing conditions, ...
+ * getting an [overview of major simulation engines](#/table) with specific features, licensing conditions, ...
  * monitoring how the use of individual simulation engines has evolved over time
- * analyzing trends at the ecosystem level (licensing, ...)
+ * analyzing [trends at the ecosystem level](#/statistics) (licensing, ...)
 
 Citation data are updated annually, while [corrections and additions](${this.packageJson.repository.url}#adding-a-simulation-engine) are welcome throughout the year.