Renamed the placeholder name from generated to earthface

.github/workflows/sitemap_resources.yaml

@@ -42,7 +42,27 @@ jobs:
         echo "url-count = ${{ steps.sitemap_all.outputs.url-count }}"
         echo "excluded-count = ${{ steps.sitemap_all.outputs.excluded-count }}"
 
-    - name: Generate sitemap for just AI Generated JSON-LD resources
+    - name: Check optional JSON-LD subfolders
+      id: folders
+      run: |
+        echo "earthface=$([ -d data/objects/summoned/earthface ] && echo true || echo false)" >> $GITHUB_OUTPUT
+        echo "generated=$([ -d data/objects/summoned/generated ] && echo true || echo false)" >> $GITHUB_OUTPUT
+
+    - name: Generate sitemap for earthface JSON-LD resources
+      if: steps.folders.outputs.earthface == 'true'
+      id: sitemap_earthface
+      uses: cicirello/generate-sitemap@v1
+      with:
+        base-url-path: https://raw.githubusercontent.com/earthcube/communityCollections/refs/heads/${{ github.ref_name }}/data/objects/summoned/earthface
+        path-to-root: data/objects/summoned/earthface
+        include-html: false
+        include-pdf: false
+        additional-extensions: jsonld json xml
+        exclude-paths:
+          .git .github docs scripts crawler prompts .vscode
+
+    - name: Generate sitemap for generated JSON-LD resources
+      if: steps.folders.outputs.generated == 'true'
       id: sitemap_generated
       uses: cicirello/generate-sitemap@v1
       with:
@@ -58,8 +78,9 @@ jobs:
       run: |
         git config user.name "github-actions[bot]"
         git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
-        ls -la data/objects/summoned/sitemap.xml data/objects/summoned/generated/sitemap.xml 2>/dev/null || true
-        git add data/objects/summoned/sitemap.xml data/objects/summoned/generated/sitemap.xml
+        git add data/objects/summoned/sitemap.xml
+        [ -f data/objects/summoned/earthface/sitemap.xml ] && git add data/objects/summoned/earthface/sitemap.xml
+        [ -f data/objects/summoned/generated/sitemap.xml ] && git add data/objects/summoned/generated/sitemap.xml
         git status
         if ! git diff --staged --quiet; then
           git commit -m "chore: update JSON-LD sitemaps"

.github/workflows/validate_with_dataset_schema.yaml

@@ -7,9 +7,9 @@ on:
     branches-ignore: [ 'gh-pages' ]
 
 jobs:
-  validate-jsonld-generated:
+  validate-jsonld-folders:
     runs-on: ubuntu-latest
-    name: Validate generated JSON-LD files
+    name: Validate earthface and generated JSON-LD files
     steps:
     - name: Checkout the repo
       uses: actions/checkout@v4
@@ -21,9 +21,16 @@ jobs:
       with:
         python-version: '3.11'
 
-    - name: Find and validate generated JSON-LD files
+    - name: Validate JSON-LD in earthface and generated folders
       run: |
-        python scripts/validate_jsonld_batch.py data/objects/summoned/generated
+        for dir in data/objects/summoned/earthface data/objects/summoned/generated; do
+          if [ -d "$dir" ]; then
+            echo "Validating $dir..."
+            python scripts/validate_jsonld_batch.py "$dir"
+          else
+            echo "Skipping (folder not present): $dir"
+          fi
+        done
 
   validate-jsonld-summoned:
     runs-on: ubuntu-latest
@@ -47,7 +54,7 @@ jobs:
         dir_ = Path("data/objects/summoned")
         if not dir_.exists():
             print("Directory not found, skipping."); sys.exit(0)
-        files = [f for f in dir_.rglob("*.jsonld") if "generated" not in str(f)]
+        files = [f for f in dir_.rglob("*.jsonld") if "earthface" not in str(f) and "generated" not in str(f)]
         if not files:
             print("No JSON-LD files found."); sys.exit(0)
         errs = []

.gitignore

@@ -18,4 +18,5 @@ build/
 datasets.csv
 
 # Generated JSON-LD files
+#data/objects/summoned/earthface/
 #data/objects/summoned/generated/

README.md

@@ -5,7 +5,8 @@
 
 Documentation, files and code related to the exposure of resource on the web for indexing.
 
-Sitemaps (generated by [sitemap_resources.yaml](.github/workflows/sitemap_resources.yaml) on push to `master` / `main` / feature branches):
+Sitemaps (generated by [sitemap_resources.yaml](.github/workflows/sitemap_resources.yaml) on push to `master` / `main`):
 
 - **All JSON-LD under data/objects/summoned:** [GitHub Pages](https://earthcube.github.io/communityCollections/data/objects/summoned/sitemap.xml) · [Raw (e.g. master)](https://raw.githubusercontent.com/earthcube/communityCollections/master/data/objects/summoned/sitemap.xml)
-- **AI-generated JSON-LD only:** [GitHub Pages](https://earthcube.github.io/communityCollections/data/objects/summoned/generated/sitemap.xml) · [Raw (e.g. master)](https://raw.githubusercontent.com/earthcube/communityCollections/master/data/objects/summoned/generated/sitemap.xml)
+- **Earthface JSON-LD only:** [GitHub Pages](https://earthcube.github.io/communityCollections/data/objects/summoned/earthface/sitemap.xml) · [Raw (e.g. master)](https://raw.githubusercontent.com/earthcube/communityCollections/master/data/objects/summoned/earthface/sitemap.xml)
+- **Generated JSON-LD only** (if present): [GitHub Pages](https://earthcube.github.io/communityCollections/data/objects/summoned/generated/sitemap.xml) · [Raw (e.g. master)](https://raw.githubusercontent.com/earthcube/communityCollections/master/data/objects/summoned/generated/sitemap.xml)

docs/jsonld-validation-plan.md

@@ -21,6 +21,6 @@ Validate generated JSON-LD against the authoritative dataset webpage, linked dow
 
 ## Validation
 
-- Run `python3 scripts/validate_jsonld_batch.py data/objects/summoned/generated`.
+- Run `python3 scripts/validate_jsonld_batch.py data/objects/summoned/earthface` (and/or `.../generated` when that folder exists).
 - Run `git diff --check`.
 - Review `git diff` for metadata-only changes and confirm no unrelated files are modified.

scripts/README.md

@@ -116,7 +116,7 @@ python scripts/generate_jsonld.py --ai-service gemini --csv datasets.csv
 
 ### Options
 - `--csv`: Path to CSV file (default: `datasets.csv`)
-- `--output-dir`: Output directory for JSON-LD files (default: `data/objects/summoned/generated`)
+- `--output-dir`: Output directory for JSON-LD files (default: `data/objects/summoned/earthface`)
 - `--ai-service`: Choose `gemini` (default), `nrp`, `openai`, or `anthropic` (optional - defaults to `gemini`)
 - `--api-key`: API key (or use environment variable)
 - `--model`: Model name (optional, uses defaults)

scripts/generate_jsonld.py

@@ -994,7 +994,7 @@ def save_jsonld(jsonld_str: str, output_dir: Path, dataset_name: str, url: str)
 def main():
     parser = argparse.ArgumentParser(description='Generate JSON-LD for datasets')
     parser.add_argument('--csv', default='datasets.csv', help='Path to CSV file or URL (e.g. Google Sheets export)')
-    parser.add_argument('--output-dir', default='data/objects/summoned/generated', help='Output directory for JSON-LD files')
+    parser.add_argument('--output-dir', default='data/objects/summoned/earthface', help='Output directory for JSON-LD files')
     parser.add_argument('--ai-service', choices=['openai', 'anthropic', 'nrp', 'gemini'], default='gemini', help='AI service to use (default: gemini)')
     parser.add_argument('--api-key', help='API key (or set environment variable)')
     parser.add_argument('--model', help='Model name (optional)')

scripts/validate_jsonld_batch.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 """
-Validate JSON-LD files under a directory (e.g. data/objects/summoned/generated).
+Validate JSON-LD files under a directory (e.g. data/objects/summoned/earthface).
 Checks: valid JSON, @context, @type, name; spatialCoverage box format; distribution encodingFormat as array.
 WebPage and DataCatalog are accepted with a warning (expected Dataset for dataset files).
 Exits 0 if all pass, 1 if any file fails.