feat: add storage-finder CSV importer and hourly sync

Author: kapuic

.github/workflows/storage-finder-sync.yml

@@ -0,0 +1,34 @@
+name: Sync Storage Finder Data
+
+on:
+  schedule:
+    - cron: "0 * * * *"
+  workflow_dispatch:
+
+jobs:
+  sync:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up Bun
+        uses: oven-sh/setup-bun@v2
+
+      - name: Install dependencies
+        run: bun install --frozen-lockfile
+
+      - name: Generate storage finder data from sheet
+        run: bun scripts/storage-finder-data-generator/generate.ts --output src/data/storage-finder
+
+      - name: Lint and format
+        run: |
+          bun lint --fix
+          bun format
+
+      - name: Commit changes
+        uses: stefanzweifel/git-auto-commit-action@v5
+        with:
+          commit_message: "chore: sync storage finder data from sheet"

docusaurus.config.ts

@@ -167,8 +167,7 @@ const config: Config = {
           items: [
             {
               label: "Feedback",
-              to:
-                "https://docs.google.com/forms/d/e/1FAIpQLSeHnmkPdR_IvWnT6a7U_V3RpfmQrpS8hjxI11FNnsZMlrBa4g/viewform",
+              to: "https://docs.google.com/forms/d/e/1FAIpQLSeHnmkPdR_IvWnT6a7U_V3RpfmQrpS8hjxI11FNnsZMlrBa4g/viewform",
             },
             {
               label: "Announcements",

eslint.config.mjs

@@ -66,6 +66,14 @@ const eslintConfig = tseslint.config(
   reactPlugin.configs.flat["jsx-runtime"],
   jsxA11y.flatConfigs.recommended,
 
+  {
+    settings: {
+      react: {
+        version: "detect",
+      },
+    },
+  },
+
   {
     rules: {
       "@typescript-eslint/consistent-type-imports": [

package.json

@@ -43,6 +43,7 @@
     "@docusaurus/types": "^3.9.2",
     "@eslint/compat": "^1.4.1",
     "@types/react": "^19.2.2",
+    "csv-parse": "^6.1.0",
     "eslint": "^9.39.0",
     "eslint-config-prettier": "^10.1.8",
     "eslint-import-resolver-typescript": "^4.4.4",

pnpm-lock.yaml

@@ -0,0 +1,45 @@
+# Storage Finder CSV Importer: Maintainer Guide
+
+This approach aims to balance user-friendliness (content editors update the Google Sheet) with functionality (developers tune `config.ts` so the JSON stays in sync).
+
+## What the CLI does
+
+- Reads a CSV export of the shared Google Sheet (either via `STORAGE_FINDER_SHEET_URL` or `--csv <path>`).
+- Applies the questions/choices/matchers defined in `scripts/storage-finder-data-generator/config.ts`.
+- Generates `facet-tree.json` and `service-list.json` with slug-based IDs.
+
+## How to regenerate data
+
+```sh
+bun scripts/storage-finder-data-generator/generate.ts \
+  --csv "Datafinder Data - Sheet1.csv" \
+  --output src/data/storage-finder
+```
+
+- Omit `--csv` to download from `STORAGE_FINDER_SHEET_URL`.
+- Use `--output` to write elsewhere (defaults to `src/data/storage-finder/generated` in the code).
+- If you do not have Bun, install it from <https://bun.sh/> or run with `pnpm dlx tsx scripts/storage-finder-data-generator/generate.ts ...`. Node does not run TypeScript by default; `tsx` provides the TypeScript loader.
+
+## How to add or change a question
+
+1. Add a column to the sheet that contains the signals you want to match.
+2. In `scripts/storage-finder-data-generator/config.ts`, add a new facet entry to `FACET_CONFIGS`:
+   - Set `id` (slug), `name`, `controlType` (`radio` or `checkbox`), `column` (sheet column name), and `choices` (labels the app should show).
+   - Add `matchers`: regex patterns that map cell text to choice IDs. Include `allowMultipleMatches: true` if a radio question legitimately matches more than one choice.
+   - If no regex matches, `fallback: "all"` keeps the service visible; otherwise supply an explicit array of choice IDs.
+3. Regenerate with the CLI and verify in the app.
+
+## Service fields
+
+Field definitions live in `scripts/storage-finder-data-generator/config.ts` (`FIELD_DEFINITIONS`). They map sheet columns to service detail rows (Links, Use Case, Limitations, Permission Settings, Eligibility, Synchronous Access, Alumni Access, Backup). Adjust labels or formatters there if the sheet schema changes.
+
+## Naming and IDs
+
+- Services are slugged from the `Title` column; duplicates get `-2`, `-3`, etc.
+- Facet and choice IDs are slugs defined in `config.ts`; keep them stable to avoid breaking references.
+
+## Validation rules
+
+- Radio facets throw if more than one choice matches unless `allowMultipleMatches` is set.
+- Blank cells render as “Not Available” in service fields.
+- Regexes match against raw cell text; use clear keywords in the sheet for deterministic mapping.