feat(data): validate processes files against a JSON schema. (#869)

## 🔧 Problem

We want to be sure that the processes files generated by the data
pipeline are valid.

## 🍰 Solution

Add a [JSON schema](https://json-schema.org/) and validate our files
against it.

## 🏝️ How to test

Check that the CI's green with the new CI action, or locally using:

```
$ npm run db:validate
```

.github/workflows/node.js.yml

@@ -60,6 +60,9 @@ jobs:
     - name: Install Node dependencies
       run: npm ci --prefer-offline --no-audit
 
+    - name: Check JSON db formating
+      run: npm run db:validate
+
     - name: Install Python dependencies
       run: pip install pipenv && pipenv install -d
 

package.json

@@ -20,6 +20,7 @@
     "encrypt": "./bin/encrypt",
     "db:build": "./bin/build-db && npm run db:check",
     "db:check": "elm make src/CheckDb.elm --optimize --output=check-db-app.js 1> /dev/null && node check-db.js",
+    "db:validate": "npx ajv validate --spec=draft2019 -c ajv-formats -s tests/processes-schema.json -d 'public/data/**/processes**.json'",
     "lint:openapi": "npx swagger-cli validate openapi.yaml",
     "lint:prettier": "prettier --config .prettierrc --check",
     "lint:prettier:all": "npm run lint:prettier -- .",
@@ -69,6 +70,8 @@
     "@parcel/transformer-elm": "^2.13.2",
     "@parcel/transformer-image": "^2.13.2",
     "@parcel/transformer-sass": "^2.13.2",
+    "ajv-cli": "^5.0.0",
+    "ajv-formats": "^3.0.1",
     "bootstrap": "^5.3.3",
     "concurrently": "^9.1.0",
     "elm": "^0.19.1-6",

tests/processes-schema.json

@@ -0,0 +1,120 @@
+{
+  "$schema": "https://json-schema.org/draft/2019-09/schema#",
+  "type": "array",
+  "items": {
+    "type": "object",
+    "properties": {
+      "alias": {
+        "type": ["string", "null"]
+      },
+      "categories": {
+        "type": "array",
+        "items": {
+          "type": "string"
+        }
+      },
+      "comment": {
+        "type": "string"
+      },
+      "density": {
+        "type": "number",
+        "minimum": 0
+      },
+      "displayName": {
+        "type": ["string", "null"]
+      },
+      "elec_MJ": {
+        "type": "number",
+        "minimum": 0
+      },
+      "heat_MJ": {
+        "type": "number",
+        "minimum": 0
+      },
+      "id": {
+        "type": "string",
+        "format": "uuid"
+      },
+      "sourceId": {
+        "type": ["string", "null"]
+      },
+      "impacts": {
+        "type": "object",
+        "properties": {
+          "acd": { "type": "number" },
+          "cch": { "type": "number" },
+          "etf": { "type": "number" },
+          "etf-c": { "type": "number" },
+          "fru": { "type": "number" },
+          "fwe": { "type": "number" },
+          "htc": { "type": "number" },
+          "htc-c": { "type": "number" },
+          "htn": { "type": "number" },
+          "htn-c": { "type": "number" },
+          "ior": { "type": "number" },
+          "ldu": { "type": "number" },
+          "mru": { "type": "number" },
+          "ozd": { "type": "number" },
+          "pco": { "type": "number" },
+          "pma": { "type": "number" },
+          "swe": { "type": "number" },
+          "tre": { "type": "number" },
+          "wtu": { "type": "number" },
+          "ecs": { "type": "number" },
+          "pef": { "type": "number" }
+        },
+        "required": [
+          "acd",
+          "cch",
+          "etf",
+          "etf-c",
+          "fru",
+          "fwe",
+          "htc",
+          "htc-c",
+          "htn",
+          "htn-c",
+          "ior",
+          "ldu",
+          "mru",
+          "ozd",
+          "pco",
+          "pma",
+          "swe",
+          "tre",
+          "wtu",
+          "ecs",
+          "pef"
+        ]
+      },
+      "name": {
+        "type": "string"
+      },
+      "source": {
+        "type": "string"
+      },
+      "unit": {
+        "type": "string",
+        "enum": ["kg", "t⋅km", "kWh", "MJ", "L", "Item(s)", "m2", "m3"]
+      },
+      "waste": {
+        "type": "number",
+        "minimum": 0,
+        "maximum": 1
+      }
+    },
+    "required": [
+      "categories",
+      "comment",
+      "density",
+      "elec_MJ",
+      "heat_MJ",
+      "id",
+      "impacts",
+      "name",
+      "source",
+      "unit",
+      "waste"
+    ]
+  }
+}