chore: improve CITATION.cff and add codemeta.json for FAIR4RS compliance

.github/ISSUE_TEMPLATE/release-checklist.md

@@ -0,0 +1,40 @@
+---
+name: Release checklist
+about: Checklist for cutting a new pycmor release
+title: "Release vX.Y.Z"
+labels: release
+assignees: ''
+---
+
+## Pre-release
+
+- [ ] All planned PRs merged
+- [ ] `CHANGELOG` / release notes up to date
+- [ ] `version` in `CITATION.cff` and `codemeta.json` matches the new version
+- [ ] `date-released` in `CITATION.cff` updated
+
+## Release
+
+- [ ] Tag pushed / GitHub Release created
+- [ ] Zenodo DOI auto-generated (check https://zenodo.org — linked via `.zenodo.json` or GitHub integration)
+- [ ] Update `doi` in `CITATION.cff` and `identifier[doi]` in `codemeta.json` with the new Zenodo DOI
+
+## Post-release: Software Heritage SWHID
+
+The GitHub Actions workflow triggers an SWH archival request automatically.
+After ~1 hour, run the helper script to fetch the new SWHID and update the files:
+
+```bash
+python scripts/update_swhid.py
+# Follow the output — it will print the SWHID and patch CITATION.cff + codemeta.json
+```
+
+Then open a PR with the updated files.
+
+- [ ] `identifiers[swh]` in `CITATION.cff` updated with new SWHID
+- [ ] `identifier[swh]` in `codemeta.json` updated with new SWHID
+- [ ] SWHID also updated in the Helmholtz RSD: https://helmholtz.software/software/pycmor/edit/software-heritage
+
+## Done
+
+- [ ] Release announcement (if applicable)

.github/workflows/software-heritage.yml

@@ -0,0 +1,34 @@
+name: Archive on Software Heritage
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  save-to-swh:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Request Software Heritage archival
+        run: |
+          ORIGIN="https://github.com/esm-tools/pycmor"
+          RESPONSE=$(curl -s -o /dev/null -w "%{http_code}" -X POST \
+            "https://archive.softwareheritage.org/api/1/origin/save/git/url/${ORIGIN}/")
+          echo "SWH save request HTTP status: $RESPONSE"
+
+      - name: Post release notes reminder
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          TAG: ${{ github.event.release.tag_name }}
+        run: |
+          ORIGIN="https://github.com/esm-tools/pycmor"
+          SWH_URL="https://archive.softwareheritage.org/browse/origin/directory/?origin_url=${ORIGIN}"
+          gh release edit "$TAG" \
+            --notes "$(gh release view "$TAG" --json body -q .body)
+
+---
+**Software Heritage archival** was requested automatically for this release.
+Once processed (usually within 1 hour), retrieve the snapshot SWHID at:
+${SWH_URL}
+
+Then update \`CITATION.cff\` (identifiers.swh) and \`codemeta.json\` (identifier[swh]) with the new SWHID.
+You can use the helper script: \`python scripts/update_swhid.py\`" || true

CITATION.cff

@@ -1,5 +1,15 @@
 cff-version: 1.2.0
-message: "If you use ESM-Tools software, please cite using the metadata below."
+message: "If you use pycmor, please cite it using the metadata below."
+type: software
+title: "pycmor"
+abstract: >-
+  pycmor (py-cmor) is a Python package that simplifies the conversion of climate
+  model output into Climate Model Output Rewriter (CMOR) compliant formats,
+  supporting both CMIP6 and CMIP7 standards. It provides a modular, plugin-based
+  pipeline architecture for processing NetCDF data from diverse Earth system
+  models, enabling compliance with WCRP Controlled Vocabularies and CF
+  conventions. Developed at the Alfred Wegener Institute Helmholtz Centre for
+  Polar and Marine Research.
 authors:
 - family-names: "Gierz"
   given-names: "Paul"
@@ -17,8 +27,30 @@ authors:
   given-names: "Jan"
   orcid: "https://orcid.org/0000-0001-9515-3322"
   affiliation: "Alfred-Wegener-Institut Helmholtz-Zentrum für Polar- und Meeresforschung"
-
-title: "pycmor"
-doi: 10.5281/zenodo.15530131
+version: "1.0.2"
 date-released: 2025-05-27
-url: "https://github.com/esm-tools/pycmor"
+license: MIT
+repository-code: "https://github.com/esm-tools/pycmor"
+url: "https://pymor.readthedocs.io"
+doi: 10.5281/zenodo.15530131
+identifiers:
+  - type: doi
+    value: "10.5281/zenodo.15530131"
+    description: "Zenodo DOI for pycmor v1.0.2"
+  - type: swh
+    value: "swh:1:snp:e4d5216be639a8e2dd2be23be1e78981de3fc67d"
+    description: "Software Heritage snapshot (HEAD, 2026-06-16)"
+keywords:
+  - CMOR
+  - CMORization
+  - CMIP6
+  - CMIP7
+  - climate
+  - climate model output
+  - NetCDF
+  - CF-conventions
+  - earth system model
+  - WCRP
+  - research software
+  - Python
+  - AWI

codemeta.json

@@ -0,0 +1,100 @@
+{
+  "@context": "https://doi.org/10.5063/schema/codemeta-2.0",
+  "@type": "SoftwareSourceCode",
+  "name": "pycmor",
+  "description": "pycmor (py-cmor) is a Python package that simplifies the conversion of climate model output into Climate Model Output Rewriter (CMOR) compliant formats, supporting both CMIP6 and CMIP7 standards. It provides a modular, plugin-based pipeline architecture for processing NetCDF data from diverse Earth system models, enabling compliance with WCRP Controlled Vocabularies and CF conventions.",
+  "identifier": [
+    {
+      "@type": "PropertyValue",
+      "propertyID": "doi",
+      "value": "https://doi.org/10.5281/zenodo.15530131"
+    },
+    {
+      "@type": "PropertyValue",
+      "propertyID": "swh",
+      "value": "swh:1:snp:e4d5216be639a8e2dd2be23be1e78981de3fc67d"
+    }
+  ],
+  "version": "1.0.2",
+  "datePublished": "2025-05-27",
+  "license": "https://spdx.org/licenses/MIT",
+  "codeRepository": "https://github.com/esm-tools/pycmor",
+  "issueTracker": "https://github.com/esm-tools/pycmor/issues",
+  "url": "https://pymor.readthedocs.io",
+  "downloadUrl": "https://pypi.org/project/py-cmor/",
+  "programmingLanguage": {
+    "@type": "ComputerLanguage",
+    "name": "Python",
+    "url": "https://www.python.org"
+  },
+  "operatingSystem": ["Linux", "macOS", "Windows"],
+  "softwareRequirements": "Python >= 3.9",
+  "developmentStatus": "active",
+  "keywords": [
+    "CMOR",
+    "CMORization",
+    "CMIP6",
+    "CMIP7",
+    "climate",
+    "climate model output",
+    "NetCDF",
+    "CF-conventions",
+    "earth system model",
+    "WCRP",
+    "research software",
+    "AWI"
+  ],
+  "author": [
+    {
+      "@type": "Person",
+      "givenName": "Paul",
+      "familyName": "Gierz",
+      "@id": "https://orcid.org/0000-0002-4512-087X",
+      "affiliation": {
+        "@type": "Organization",
+        "name": "Alfred-Wegener-Institut Helmholtz-Zentrum für Polar- und Meeresforschung",
+        "url": "https://www.awi.de"
+      }
+    },
+    {
+      "@type": "Person",
+      "givenName": "Miguel",
+      "familyName": "Andrés-Martínez",
+      "@id": "https://orcid.org/0000-0002-1525-5546",
+      "affiliation": {
+        "@type": "Organization",
+        "name": "Alfred-Wegener-Institut Helmholtz-Zentrum für Polar- und Meeresforschung",
+        "url": "https://www.awi.de"
+      }
+    },
+    {
+      "@type": "Person",
+      "givenName": "Pavan Kumar",
+      "familyName": "Siligam",
+      "@id": "https://orcid.org/0009-0003-8054-7021",
+      "affiliation": {
+        "@type": "Organization",
+        "name": "Alfred-Wegener-Institut Helmholtz-Zentrum für Polar- und Meeresforschung",
+        "url": "https://www.awi.de"
+      }
+    },
+    {
+      "@type": "Person",
+      "givenName": "Jan",
+      "familyName": "Streffing",
+      "@id": "https://orcid.org/0000-0001-9515-3322",
+      "affiliation": {
+        "@type": "Organization",
+        "name": "Alfred-Wegener-Institut Helmholtz-Zentrum für Polar- und Meeresforschung",
+        "url": "https://www.awi.de"
+      }
+    }
+  ],
+  "funder": {
+    "@type": "Organization",
+    "name": "Alfred-Wegener-Institut Helmholtz-Zentrum für Polar- und Meeresforschung",
+    "url": "https://www.awi.de"
+  },
+  "contIntegration": "https://github.com/esm-tools/pycmor/actions",
+  "readme": "https://github.com/esm-tools/pycmor/blob/main/README.rst"
+}

scripts/update_swhid.py

@@ -0,0 +1,99 @@
+#!/usr/bin/env python3
+"""
+Fetch the latest Software Heritage snapshot SWHID for pycmor and update
+CITATION.cff and codemeta.json in-place.
+
+Usage:
+    python scripts/update_swhid.py
+
+Run this after a release, once the SWH archival is complete (~1 hour after tag push).
+"""
+import json
+import re
+import sys
+import urllib.request
+from pathlib import Path
+
+ORIGIN = "https://github.com/esm-tools/pycmor"
+SWH_API = "https://archive.softwareheritage.org/api/1"
+REPO_ROOT = Path(__file__).parent.parent
+
+
+def get_latest_swhid() -> str:
+    url = f"{SWH_API}/origin/{ORIGIN}/visit/latest/?require_snapshot=true"
+    try:
+        with urllib.request.urlopen(url, timeout=15) as r:
+            data = json.load(r)
+    except Exception as e:
+        sys.exit(f"Failed to fetch latest SWH visit: {e}\n"
+                 f"Is the repository archived? Check: "
+                 f"https://archive.softwareheritage.org/browse/origin/?origin_url={ORIGIN}")
+
+    snapshot = data.get("snapshot")
+    if not snapshot:
+        sys.exit("Latest SWH visit has no snapshot yet — archival may still be in progress. "
+                 "Try again in a few minutes.")
+
+    return f"swh:1:snp:{snapshot}"
+
+
+def update_citation_cff(swhid: str) -> None:
+    path = REPO_ROOT / "CITATION.cff"
+    content = path.read_text()
+
+    # Replace existing swh identifier value
+    pattern = r'(- type: swh\s+value: ")[^"]+"'
+    replacement = rf'\g<1>{swhid}"'
+    new_content, count = re.subn(pattern, replacement, content)
+
+    if count == 0:
+        print("WARNING: could not find '- type: swh' block in CITATION.cff — "
+              "please update identifiers.swh manually.")
+        print(f"  SWHID to add: {swhid}")
+        return
+
+    path.write_text(new_content)
+    print(f"Updated CITATION.cff: identifiers.swh = {swhid}")
+
+
+def update_codemeta(swhid: str) -> None:
+    path = REPO_ROOT / "codemeta.json"
+    data = json.loads(path.read_text())
+
+    identifiers = data.get("identifier", [])
+    if isinstance(identifiers, str):
+        identifiers = [{"@type": "PropertyValue", "propertyID": "doi", "value": identifiers}]
+
+    updated = False
+    for entry in identifiers:
+        if isinstance(entry, dict) and entry.get("propertyID") == "swh":
+            entry["value"] = swhid
+            updated = True
+            break
+
+    if not updated:
+        identifiers.append({"@type": "PropertyValue", "propertyID": "swh", "value": swhid})
+
+    data["identifier"] = identifiers
+    path.write_text(json.dumps(data, indent=2, ensure_ascii=False) + "\n")
+    print(f"Updated codemeta.json: identifier[swh] = {swhid}")
+
+
+def main() -> None:
+    print(f"Fetching latest Software Heritage snapshot for {ORIGIN} ...")
+    swhid = get_latest_swhid()
+    print(f"SWHID: {swhid}\n")
+
+    update_citation_cff(swhid)
+    update_codemeta(swhid)
+
+    print("\nDone. Next steps:")
+    print("  1. git diff  # review the changes")
+    print("  2. git add CITATION.cff codemeta.json && git commit -m 'chore: update SWHID for release'")
+    print("  3. Open a PR or push directly to main")
+    print(f"  4. Update the Helmholtz RSD: "
+          f"https://helmholtz.software/software/pycmor/edit/software-heritage")
+
+
+if __name__ == "__main__":
+    main()