diff --git a/.github/workflows/sitemap_resources.yaml b/.github/workflows/sitemap_resources.yaml index 8c13d79..486643b 100644 --- a/.github/workflows/sitemap_resources.yaml +++ b/.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" diff --git a/.github/workflows/validate_with_dataset_schema.yaml b/.github/workflows/validate_with_dataset_schema.yaml index 309a9df..16801ff 100644 --- a/.github/workflows/validate_with_dataset_schema.yaml +++ b/.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 = [] diff --git a/.gitignore b/.gitignore index c569d3d..8264449 100644 --- a/.gitignore +++ b/.gitignore @@ -18,4 +18,5 @@ build/ datasets.csv # Generated JSON-LD files +#data/objects/summoned/earthface/ #data/objects/summoned/generated/ diff --git a/README.md b/README.md index 28729ce..79e3c5a 100644 --- a/README.md +++ b/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) \ No newline at end of file +- **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) \ No newline at end of file diff --git a/data/objects/summoned/generated/CHELSA/chelsa_bioclim.jsonld b/data/objects/summoned/earthface/CHELSA/chelsa_bioclim.jsonld similarity index 100% rename from data/objects/summoned/generated/CHELSA/chelsa_bioclim.jsonld rename to data/objects/summoned/earthface/CHELSA/chelsa_bioclim.jsonld diff --git a/data/objects/summoned/generated/CHELSA/chelsa_canaryclim_climatologies.jsonld b/data/objects/summoned/earthface/CHELSA/chelsa_canaryclim_climatologies.jsonld similarity index 100% rename from data/objects/summoned/generated/CHELSA/chelsa_canaryclim_climatologies.jsonld rename to data/objects/summoned/earthface/CHELSA/chelsa_canaryclim_climatologies.jsonld diff --git a/data/objects/summoned/generated/CHELSA/chelsa_cerra_daily.jsonld b/data/objects/summoned/earthface/CHELSA/chelsa_cerra_daily.jsonld similarity index 100% rename from data/objects/summoned/generated/CHELSA/chelsa_cerra_daily.jsonld rename to data/objects/summoned/earthface/CHELSA/chelsa_cerra_daily.jsonld diff --git a/data/objects/summoned/generated/CHELSA/chelsa_ch_highres_climatologies.jsonld b/data/objects/summoned/earthface/CHELSA/chelsa_ch_highres_climatologies.jsonld similarity index 100% rename from data/objects/summoned/generated/CHELSA/chelsa_ch_highres_climatologies.jsonld rename to data/objects/summoned/earthface/CHELSA/chelsa_ch_highres_climatologies.jsonld diff --git a/data/objects/summoned/generated/CHELSA/chelsa_ch_highres_daily.jsonld b/data/objects/summoned/earthface/CHELSA/chelsa_ch_highres_daily.jsonld similarity index 100% rename from data/objects/summoned/generated/CHELSA/chelsa_ch_highres_daily.jsonld rename to data/objects/summoned/earthface/CHELSA/chelsa_ch_highres_daily.jsonld diff --git a/data/objects/summoned/generated/CHELSA/chelsa_climatologies.jsonld b/data/objects/summoned/earthface/CHELSA/chelsa_climatologies.jsonld similarity index 100% rename from data/objects/summoned/generated/CHELSA/chelsa_climatologies.jsonld rename to data/objects/summoned/earthface/CHELSA/chelsa_climatologies.jsonld diff --git a/data/objects/summoned/generated/CHELSA/chelsa_daily.jsonld b/data/objects/summoned/earthface/CHELSA/chelsa_daily.jsonld similarity index 100% rename from data/objects/summoned/generated/CHELSA/chelsa_daily.jsonld rename to data/objects/summoned/earthface/CHELSA/chelsa_daily.jsonld diff --git a/data/objects/summoned/generated/CHELSA/chelsa_drought_indices.jsonld b/data/objects/summoned/earthface/CHELSA/chelsa_drought_indices.jsonld similarity index 100% rename from data/objects/summoned/generated/CHELSA/chelsa_drought_indices.jsonld rename to data/objects/summoned/earthface/CHELSA/chelsa_drought_indices.jsonld diff --git a/data/objects/summoned/generated/CHELSA/chelsa_monthly.jsonld b/data/objects/summoned/earthface/CHELSA/chelsa_monthly.jsonld similarity index 100% rename from data/objects/summoned/generated/CHELSA/chelsa_monthly.jsonld rename to data/objects/summoned/earthface/CHELSA/chelsa_monthly.jsonld diff --git a/data/objects/summoned/generated/CHELSA/chelsa_trace21k_centennial.jsonld b/data/objects/summoned/earthface/CHELSA/chelsa_trace21k_centennial.jsonld similarity index 100% rename from data/objects/summoned/generated/CHELSA/chelsa_trace21k_centennial.jsonld rename to data/objects/summoned/earthface/CHELSA/chelsa_trace21k_centennial.jsonld diff --git a/data/objects/summoned/generated/CHELSA/chelsa_trace21k_centennial_bioclim.jsonld b/data/objects/summoned/earthface/CHELSA/chelsa_trace21k_centennial_bioclim.jsonld similarity index 100% rename from data/objects/summoned/generated/CHELSA/chelsa_trace21k_centennial_bioclim.jsonld rename to data/objects/summoned/earthface/CHELSA/chelsa_trace21k_centennial_bioclim.jsonld diff --git a/data/objects/summoned/generated/CHELSA/chelsa_w5e5_daily.jsonld b/data/objects/summoned/earthface/CHELSA/chelsa_w5e5_daily.jsonld similarity index 100% rename from data/objects/summoned/generated/CHELSA/chelsa_w5e5_daily.jsonld rename to data/objects/summoned/earthface/CHELSA/chelsa_w5e5_daily.jsonld diff --git a/data/objects/summoned/generated/CHELSA/datacatalog.jsonld b/data/objects/summoned/earthface/CHELSA/datacatalog.jsonld similarity index 100% rename from data/objects/summoned/generated/CHELSA/datacatalog.jsonld rename to data/objects/summoned/earthface/CHELSA/datacatalog.jsonld diff --git a/data/objects/summoned/generated/CHELSA/webpage.jsonld b/data/objects/summoned/earthface/CHELSA/webpage.jsonld similarity index 100% rename from data/objects/summoned/generated/CHELSA/webpage.jsonld rename to data/objects/summoned/earthface/CHELSA/webpage.jsonld diff --git a/data/objects/summoned/generated/Consensus_Land_Cover/consensus-land-cover.jsonld b/data/objects/summoned/earthface/Consensus_Land_Cover/consensus-land-cover.jsonld similarity index 100% rename from data/objects/summoned/generated/Consensus_Land_Cover/consensus-land-cover.jsonld rename to data/objects/summoned/earthface/Consensus_Land_Cover/consensus-land-cover.jsonld diff --git a/data/objects/summoned/generated/Consensus_Land_Cover/webpage.jsonld b/data/objects/summoned/earthface/Consensus_Land_Cover/webpage.jsonld similarity index 100% rename from data/objects/summoned/generated/Consensus_Land_Cover/webpage.jsonld rename to data/objects/summoned/earthface/Consensus_Land_Cover/webpage.jsonld diff --git a/data/objects/summoned/generated/FLO1K/flo1k.jsonld b/data/objects/summoned/earthface/FLO1K/flo1k.jsonld similarity index 100% rename from data/objects/summoned/generated/FLO1K/flo1k.jsonld rename to data/objects/summoned/earthface/FLO1K/flo1k.jsonld diff --git a/data/objects/summoned/generated/FLO1K/webpage.jsonld b/data/objects/summoned/earthface/FLO1K/webpage.jsonld similarity index 100% rename from data/objects/summoned/generated/FLO1K/webpage.jsonld rename to data/objects/summoned/earthface/FLO1K/webpage.jsonld diff --git a/data/objects/summoned/generated/G-RUN/g-run.jsonld b/data/objects/summoned/earthface/G-RUN/g-run.jsonld similarity index 100% rename from data/objects/summoned/generated/G-RUN/g-run.jsonld rename to data/objects/summoned/earthface/G-RUN/g-run.jsonld diff --git a/data/objects/summoned/generated/G-RUN/webpage.jsonld b/data/objects/summoned/earthface/G-RUN/webpage.jsonld similarity index 100% rename from data/objects/summoned/generated/G-RUN/webpage.jsonld rename to data/objects/summoned/earthface/G-RUN/webpage.jsonld diff --git a/data/objects/summoned/generated/GFC/gfc.jsonld b/data/objects/summoned/earthface/GFC/gfc.jsonld similarity index 100% rename from data/objects/summoned/generated/GFC/gfc.jsonld rename to data/objects/summoned/earthface/GFC/gfc.jsonld diff --git a/data/objects/summoned/generated/GFC/webpage.jsonld b/data/objects/summoned/earthface/GFC/webpage.jsonld similarity index 100% rename from data/objects/summoned/generated/GFC/webpage.jsonld rename to data/objects/summoned/earthface/GFC/webpage.jsonld diff --git a/data/objects/summoned/generated/GHSL/ghsl.jsonld b/data/objects/summoned/earthface/GHSL/ghsl.jsonld similarity index 100% rename from data/objects/summoned/generated/GHSL/ghsl.jsonld rename to data/objects/summoned/earthface/GHSL/ghsl.jsonld diff --git a/data/objects/summoned/generated/GHSL/webpage.jsonld b/data/objects/summoned/earthface/GHSL/webpage.jsonld similarity index 100% rename from data/objects/summoned/generated/GHSL/webpage.jsonld rename to data/objects/summoned/earthface/GHSL/webpage.jsonld diff --git a/data/objects/summoned/generated/GPP_MOD17/gpp_mod17.jsonld b/data/objects/summoned/earthface/GPP_MOD17/gpp_mod17.jsonld similarity index 100% rename from data/objects/summoned/generated/GPP_MOD17/gpp_mod17.jsonld rename to data/objects/summoned/earthface/GPP_MOD17/gpp_mod17.jsonld diff --git a/data/objects/summoned/generated/GPP_MOD17/webpage.jsonld b/data/objects/summoned/earthface/GPP_MOD17/webpage.jsonld similarity index 100% rename from data/objects/summoned/generated/GPP_MOD17/webpage.jsonld rename to data/objects/summoned/earthface/GPP_MOD17/webpage.jsonld diff --git a/data/objects/summoned/generated/GRACE-REC/grace-rec.jsonld b/data/objects/summoned/earthface/GRACE-REC/grace-rec.jsonld similarity index 100% rename from data/objects/summoned/generated/GRACE-REC/grace-rec.jsonld rename to data/objects/summoned/earthface/GRACE-REC/grace-rec.jsonld diff --git a/data/objects/summoned/generated/GRACE-REC/webpage.jsonld b/data/objects/summoned/earthface/GRACE-REC/webpage.jsonld similarity index 100% rename from data/objects/summoned/generated/GRACE-REC/webpage.jsonld rename to data/objects/summoned/earthface/GRACE-REC/webpage.jsonld diff --git a/data/objects/summoned/generated/Global_Multi-layer_Soil_Moisture/global-multi-layer-soil-moisture.jsonld b/data/objects/summoned/earthface/Global_Multi-layer_Soil_Moisture/global-multi-layer-soil-moisture.jsonld similarity index 100% rename from data/objects/summoned/generated/Global_Multi-layer_Soil_Moisture/global-multi-layer-soil-moisture.jsonld rename to data/objects/summoned/earthface/Global_Multi-layer_Soil_Moisture/global-multi-layer-soil-moisture.jsonld diff --git a/data/objects/summoned/generated/Global_Multi-layer_Soil_Moisture/webpage.jsonld b/data/objects/summoned/earthface/Global_Multi-layer_Soil_Moisture/webpage.jsonld similarity index 100% rename from data/objects/summoned/generated/Global_Multi-layer_Soil_Moisture/webpage.jsonld rename to data/objects/summoned/earthface/Global_Multi-layer_Soil_Moisture/webpage.jsonld diff --git a/data/objects/summoned/generated/Global_Tree_Density/global-tree-density.jsonld b/data/objects/summoned/earthface/Global_Tree_Density/global-tree-density.jsonld similarity index 100% rename from data/objects/summoned/generated/Global_Tree_Density/global-tree-density.jsonld rename to data/objects/summoned/earthface/Global_Tree_Density/global-tree-density.jsonld diff --git a/data/objects/summoned/generated/Global_Tree_Density/webpage.jsonld b/data/objects/summoned/earthface/Global_Tree_Density/webpage.jsonld similarity index 100% rename from data/objects/summoned/generated/Global_Tree_Density/webpage.jsonld rename to data/objects/summoned/earthface/Global_Tree_Density/webpage.jsonld diff --git a/data/objects/summoned/generated/HydroSHEDS/hydrosheds.jsonld b/data/objects/summoned/earthface/HydroSHEDS/hydrosheds.jsonld similarity index 100% rename from data/objects/summoned/generated/HydroSHEDS/hydrosheds.jsonld rename to data/objects/summoned/earthface/HydroSHEDS/hydrosheds.jsonld diff --git a/data/objects/summoned/generated/HydroSHEDS/webpage.jsonld b/data/objects/summoned/earthface/HydroSHEDS/webpage.jsonld similarity index 100% rename from data/objects/summoned/generated/HydroSHEDS/webpage.jsonld rename to data/objects/summoned/earthface/HydroSHEDS/webpage.jsonld diff --git a/data/objects/summoned/generated/Hydrography90m/hydrography90m.jsonld b/data/objects/summoned/earthface/Hydrography90m/hydrography90m.jsonld similarity index 100% rename from data/objects/summoned/generated/Hydrography90m/hydrography90m.jsonld rename to data/objects/summoned/earthface/Hydrography90m/hydrography90m.jsonld diff --git a/data/objects/summoned/generated/Hydrography90m/webpage.jsonld b/data/objects/summoned/earthface/Hydrography90m/webpage.jsonld similarity index 100% rename from data/objects/summoned/generated/Hydrography90m/webpage.jsonld rename to data/objects/summoned/earthface/Hydrography90m/webpage.jsonld diff --git a/data/objects/summoned/generated/MERIT_DEM/merit-dem.jsonld b/data/objects/summoned/earthface/MERIT_DEM/merit-dem.jsonld similarity index 100% rename from data/objects/summoned/generated/MERIT_DEM/merit-dem.jsonld rename to data/objects/summoned/earthface/MERIT_DEM/merit-dem.jsonld diff --git a/data/objects/summoned/generated/MERIT_DEM/webpage.jsonld b/data/objects/summoned/earthface/MERIT_DEM/webpage.jsonld similarity index 100% rename from data/objects/summoned/generated/MERIT_DEM/webpage.jsonld rename to data/objects/summoned/earthface/MERIT_DEM/webpage.jsonld diff --git a/data/objects/summoned/generated/MRLC_NLCD/annual-nlcd.jsonld b/data/objects/summoned/earthface/MRLC_NLCD/annual-nlcd.jsonld similarity index 100% rename from data/objects/summoned/generated/MRLC_NLCD/annual-nlcd.jsonld rename to data/objects/summoned/earthface/MRLC_NLCD/annual-nlcd.jsonld diff --git a/data/objects/summoned/generated/MRLC_NLCD/datacatalog.jsonld b/data/objects/summoned/earthface/MRLC_NLCD/datacatalog.jsonld similarity index 100% rename from data/objects/summoned/generated/MRLC_NLCD/datacatalog.jsonld rename to data/objects/summoned/earthface/MRLC_NLCD/datacatalog.jsonld diff --git a/data/objects/summoned/generated/MRLC_NLCD/exotic-annual-grass.jsonld b/data/objects/summoned/earthface/MRLC_NLCD/exotic-annual-grass.jsonld similarity index 100% rename from data/objects/summoned/generated/MRLC_NLCD/exotic-annual-grass.jsonld rename to data/objects/summoned/earthface/MRLC_NLCD/exotic-annual-grass.jsonld diff --git a/data/objects/summoned/generated/MRLC_NLCD/legacy-nlcd.jsonld b/data/objects/summoned/earthface/MRLC_NLCD/legacy-nlcd.jsonld similarity index 100% rename from data/objects/summoned/generated/MRLC_NLCD/legacy-nlcd.jsonld rename to data/objects/summoned/earthface/MRLC_NLCD/legacy-nlcd.jsonld diff --git a/data/objects/summoned/generated/MRLC_NLCD/nalcms.jsonld b/data/objects/summoned/earthface/MRLC_NLCD/nalcms.jsonld similarity index 100% rename from data/objects/summoned/generated/MRLC_NLCD/nalcms.jsonld rename to data/objects/summoned/earthface/MRLC_NLCD/nalcms.jsonld diff --git a/data/objects/summoned/generated/MRLC_NLCD/rcmap.jsonld b/data/objects/summoned/earthface/MRLC_NLCD/rcmap.jsonld similarity index 100% rename from data/objects/summoned/generated/MRLC_NLCD/rcmap.jsonld rename to data/objects/summoned/earthface/MRLC_NLCD/rcmap.jsonld diff --git a/data/objects/summoned/generated/MRLC_NLCD/webpage.jsonld b/data/objects/summoned/earthface/MRLC_NLCD/webpage.jsonld similarity index 100% rename from data/objects/summoned/generated/MRLC_NLCD/webpage.jsonld rename to data/objects/summoned/earthface/MRLC_NLCD/webpage.jsonld diff --git a/data/objects/summoned/generated/Shale_Network/shale-network.jsonld b/data/objects/summoned/earthface/Shale_Network/shale-network.jsonld similarity index 100% rename from data/objects/summoned/generated/Shale_Network/shale-network.jsonld rename to data/objects/summoned/earthface/Shale_Network/shale-network.jsonld diff --git a/data/objects/summoned/generated/Shale_Network/webpage.jsonld b/data/objects/summoned/earthface/Shale_Network/webpage.jsonld similarity index 100% rename from data/objects/summoned/generated/Shale_Network/webpage.jsonld rename to data/objects/summoned/earthface/Shale_Network/webpage.jsonld diff --git a/data/objects/summoned/generated/SoilGrids2/soilgrids2.jsonld b/data/objects/summoned/earthface/SoilGrids2/soilgrids2.jsonld similarity index 100% rename from data/objects/summoned/generated/SoilGrids2/soilgrids2.jsonld rename to data/objects/summoned/earthface/SoilGrids2/soilgrids2.jsonld diff --git a/data/objects/summoned/generated/SoilGrids2/webpage.jsonld b/data/objects/summoned/earthface/SoilGrids2/webpage.jsonld similarity index 100% rename from data/objects/summoned/generated/SoilGrids2/webpage.jsonld rename to data/objects/summoned/earthface/SoilGrids2/webpage.jsonld diff --git a/data/objects/summoned/generated/TerraClimate/terraclimate.jsonld b/data/objects/summoned/earthface/TerraClimate/terraclimate.jsonld similarity index 100% rename from data/objects/summoned/generated/TerraClimate/terraclimate.jsonld rename to data/objects/summoned/earthface/TerraClimate/terraclimate.jsonld diff --git a/data/objects/summoned/generated/TerraClimate/webpage.jsonld b/data/objects/summoned/earthface/TerraClimate/webpage.jsonld similarity index 100% rename from data/objects/summoned/generated/TerraClimate/webpage.jsonld rename to data/objects/summoned/earthface/TerraClimate/webpage.jsonld diff --git a/data/objects/summoned/generated/WATERBASE/waterbase.jsonld b/data/objects/summoned/earthface/WATERBASE/waterbase.jsonld similarity index 100% rename from data/objects/summoned/generated/WATERBASE/waterbase.jsonld rename to data/objects/summoned/earthface/WATERBASE/waterbase.jsonld diff --git a/data/objects/summoned/generated/WATERBASE/webpage.jsonld b/data/objects/summoned/earthface/WATERBASE/webpage.jsonld similarity index 100% rename from data/objects/summoned/generated/WATERBASE/webpage.jsonld rename to data/objects/summoned/earthface/WATERBASE/webpage.jsonld diff --git a/data/objects/summoned/generated/Water_Quality_Portal/water-quality-portal.jsonld b/data/objects/summoned/earthface/Water_Quality_Portal/water-quality-portal.jsonld similarity index 100% rename from data/objects/summoned/generated/Water_Quality_Portal/water-quality-portal.jsonld rename to data/objects/summoned/earthface/Water_Quality_Portal/water-quality-portal.jsonld diff --git a/data/objects/summoned/generated/Water_Quality_Portal/webpage.jsonld b/data/objects/summoned/earthface/Water_Quality_Portal/webpage.jsonld similarity index 100% rename from data/objects/summoned/generated/Water_Quality_Portal/webpage.jsonld rename to data/objects/summoned/earthface/Water_Quality_Portal/webpage.jsonld diff --git a/data/objects/summoned/generated/sitemap.xml b/data/objects/summoned/earthface/sitemap.xml similarity index 100% rename from data/objects/summoned/generated/sitemap.xml rename to data/objects/summoned/earthface/sitemap.xml diff --git a/docs/jsonld-validation-plan.md b/docs/jsonld-validation-plan.md index 2cb3be2..22b98c7 100644 --- a/docs/jsonld-validation-plan.md +++ b/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. diff --git a/scripts/README.md b/scripts/README.md index fdb4b2c..15976f4 100644 --- a/scripts/README.md +++ b/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) diff --git a/scripts/generate_jsonld.py b/scripts/generate_jsonld.py index d053fb4..cb7ba00 100644 --- a/scripts/generate_jsonld.py +++ b/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)') diff --git a/scripts/validate_jsonld_batch.py b/scripts/validate_jsonld_batch.py index 2768c0e..e89eee0 100644 --- a/scripts/validate_jsonld_batch.py +++ b/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.