Climate-REF · ltroussellier · Jul 23, 2026 · Jul 23, 2026
diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
@@ -0,0 +1,21 @@
+name: CI (continuous integration)
+
+on:
+  pull_request:
+  push:
+    branches: [main, esgvoc_dev]
+
+jobs:
+  check-all-filenames:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.13"
+
+      - name: Check for duplicate term IDs
+        run: |
+          python _scripts/check-cv-entry-filenames.py
diff --git a/_scripts/check-cv-entry-filenames.py b/_scripts/check-cv-entry-filenames.py
@@ -0,0 +1,53 @@
+"""
+Check for duplicate term IDs within each collection.
+
+The id field references a universe term and does not have to match the
+filename, but two files in the same collection must never share the
+same id — that causes duplicate rows during esgvoc ingestion.
+"""
+
+import json
+import os
+import sys
+from collections import defaultdict
+from pathlib import Path
+
+
+SKIP_DIRS = {".git", ".github", ".idea", ".venv", "_CVs", "_scripts"}
+
+
+def main():
+    repo_root = Path(__file__).parents[1]
+
+    failing = []
+    for entry in sorted(os.scandir(repo_root), key=lambda e: e.name):
+        if not entry.is_dir() or entry.name in SKIP_DIRS or entry.name.startswith("."):
+            continue
+
+        ids_seen: dict[str, list[str]] = defaultdict(list)
+        for cv_file in sorted(Path(entry.path).glob("*.json")):
+            with open(cv_file) as fh:
+                content = json.load(fh)
+
+            if "id" not in content:
+                continue
+
+            ids_seen[content["id"]].append(str(cv_file))
+
+        for term_id, files in ids_seen.items():
+            if len(files) > 1:
+                failing.append(
+                    f"{entry.name}: duplicate id '{term_id}' in {files}"
+                )
+
+    if failing:
+        print("Duplicate term IDs found:", file=sys.stderr)
+        for f in failing:
+            print(f"  {f}", file=sys.stderr)
+        raise SystemExit(1)
+
+    print("No duplicate term IDs found.")
+
+
+if __name__ == "__main__":
+    main()
diff --git a/citation_url/url.json b/citation_url/url.json
diff --git a/frequency/1hrCM.json b/frequency/1hrCM.json
diff --git a/frequency/1hrPt.json b/frequency/1hrPt.json
diff --git a/frequency/3hrPt.json b/frequency/3hrPt.json
diff --git a/frequency/6hrPt.json b/frequency/6hrPt.json
diff --git a/frequency/monC.json b/frequency/monC.json
diff --git a/frequency/monPt.json b/frequency/monPt.json
diff --git a/frequency/subhrPt.json b/frequency/subhrPt.json
diff --git a/frequency/yrPt.json b/frequency/yrPt.json
diff --git a/realm/atmosChem.json b/realm/atmosChem.json
diff --git a/realm/landIce.json b/realm/landIce.json
diff --git a/realm/ocnBgchem.json b/realm/ocnBgchem.json
diff --git a/realm/seaIce.json b/realm/seaIce.json
diff --git a/tracking_id/obs4ref.json b/tracking_id/obs4ref.json
diff --git a/tracking_id/prefuuid.json b/tracking_id/prefuuid.json
@@ -1,5 +1,6 @@
 {
   "@context": "000_context.jsonld",
   "id": "prefuuid",
-  "type": "tracking_id"
+  "type": "tracking_id",
+  "regex": "^hdl:21\\.14102/[a-fA-F0-9]{8}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{12}$"
 }
diff --git a/variable_id/baresoilFrac.json b/variable_id/baresoilFrac.json
diff --git a/variable_id/burntFractionAll.json b/variable_id/burntFractionAll.json
diff --git a/variable_id/c3PftFrac.json b/variable_id/c3PftFrac.json
diff --git a/variable_id/c4PftFrac.json b/variable_id/c4PftFrac.json
diff --git a/variable_id/cCwd.json b/variable_id/cCwd.json
diff --git a/variable_id/cLeaf.json b/variable_id/cLeaf.json
diff --git a/variable_id/cLitter.json b/variable_id/cLitter.json
diff --git a/variable_id/cLitterAbove.json b/variable_id/cLitterAbove.json
diff --git a/variable_id/cLitterBelow.json b/variable_id/cLitterBelow.json
diff --git a/variable_id/cProduct.json b/variable_id/cProduct.json
diff --git a/variable_id/cRoot.json b/variable_id/cRoot.json
diff --git a/variable_id/cSoilFast.json b/variable_id/cSoilFast.json
diff --git a/variable_id/cSoilMedium.json b/variable_id/cSoilMedium.json
diff --git a/variable_id/cSoilSlow.json b/variable_id/cSoilSlow.json
diff --git a/variable_id/cVeg.json b/variable_id/cVeg.json
diff --git a/variable_id/ch4Clim.json b/variable_id/ch4Clim.json
diff --git a/variable_id/ch4globalClim.json b/variable_id/ch4globalClim.json
diff --git a/variable_id/co2Clim.json b/variable_id/co2Clim.json
diff --git a/variable_id/co2massClim.json b/variable_id/co2massClim.json
diff --git a/variable_id/cropFrac.json b/variable_id/cropFrac.json
diff --git a/variable_id/fFire.json b/variable_id/fFire.json
diff --git a/variable_id/fGrazing.json b/variable_id/fGrazing.json
diff --git a/variable_id/fHarvest.json b/variable_id/fHarvest.json
diff --git a/variable_id/fLitterSoil.json b/variable_id/fLitterSoil.json
diff --git a/variable_id/fVegLitter.json b/variable_id/fVegLitter.json
diff --git a/variable_id/fVegSoil.json b/variable_id/fVegSoil.json
diff --git a/variable_id/grassFrac.json b/variable_id/grassFrac.json
diff --git a/variable_id/landCoverFrac.json b/variable_id/landCoverFrac.json
diff --git a/variable_id/n2oClim.json b/variable_id/n2oClim.json
diff --git a/variable_id/n2oglobalClim.json b/variable_id/n2oglobalClim.json
diff --git a/variable_id/nppLeaf.json b/variable_id/nppLeaf.json
diff --git a/variable_id/nppRoot.json b/variable_id/nppRoot.json
diff --git a/variable_id/nppWood.json b/variable_id/nppWood.json
diff --git a/variable_id/o3Clim.json b/variable_id/o3Clim.json
diff --git a/variable_id/pastureFrac.json b/variable_id/pastureFrac.json
diff --git a/variable_id/rGrowth.json b/variable_id/rGrowth.json
diff --git a/variable_id/rMaint.json b/variable_id/rMaint.json