Keep only the published site in this repository

.github/workflows/public-files.yml

@@ -0,0 +1,37 @@
+name: Public files
+
+# This repository publishes the site only. Fail when a commit adds a file
+# outside PUBLIC_FILES, or any Python other than the page build, so pipeline
+# code or source data cannot slip in by accident.
+on:
+  push:
+    branches: [main]
+  pull_request:
+
+jobs:
+  allowlist:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Check tracked files against PUBLIC_FILES
+        run: |
+          python3 - <<'PY'
+          import re, subprocess, sys
+          rules = [l.strip() for l in open('PUBLIC_FILES') if l.strip() and not l.lstrip().startswith('#')]
+          def allowed(path):
+              for rule in rules:
+                  if rule.endswith('/'):
+                      if path.startswith(rule):
+                          return True
+                  elif re.fullmatch(re.escape(rule).replace(r'\*', '[^/]*'), path):
+                      return True
+              return False
+          files = [f for f in subprocess.run(['git', 'ls-files'], capture_output=True, text=True, check=True).stdout.splitlines() if f]
+          bad = [f for f in files if not allowed(f)]
+          bad += [f for f in files if f.endswith('.py') and f != 'build_static_pages.py' and f not in bad]
+          if bad:
+              print('Not allowed in the public site repository (see PUBLIC_FILES):')
+              print('\n'.join('  ' + f for f in bad))
+              sys.exit(1)
+          print(f'{len(files)} tracked files, all allowed.')
+          PY

.zenodo.json

@@ -3,7 +3,7 @@
   "upload_type": "software",
   "access_right": "open",
   "license": "PolyForm-Noncommercial-1.0.0",
-  "description": "Open-source paragraph-level research environment for UN human rights law. UNHRDB combines Treaty Body General Comments and Recommendations, individual-communication jurisprudence, and thematic Special Procedures reports in a source-first interface with faceted search, citation export, document workspaces, and extractive retrieval. The software and curated datasets have separate licences; see LICENSE, LICENSE-DATA, and NOTICE in the repository. The v2.1.0 release (3 September 2026) covers 6,111 documents and 323,065 paragraphs: 187 General Comments and Recommendations, 4,333 individual-communication decisions from 8 treaty bodies, and 1,591 thematic Special Procedures reports from all 46 mandates.",
+  "description": "Paragraph-level research environment for UN human rights law. UNHRDB combines Treaty Body General Comments and Recommendations, individual-communication jurisprudence, and thematic Special Procedures reports in a source-first interface with faceted search, citation export, document workspaces, and extractive retrieval. The software and curated datasets have separate licences; see LICENSE, LICENSE-DATA, and NOTICE in the repository. The v2.1.0 release (3 September 2026) covers 6,111 documents and 323,065 paragraphs: 187 General Comments and Recommendations, 4,333 individual-communication decisions from 8 treaty bodies, and 1,591 thematic Special Procedures reports from all 46 mandates. The repository holds the published site and its front-end code; the data-processing pipeline is kept in a separate, private repository.",
   "creators": [
     {
       "name": "Szoszkiewicz, Łukasz",

CITATION.cff

@@ -15,11 +15,13 @@ authors:
     given-names: "Zuzanna"
     affiliation: "Adam Mickiewicz University, Poznań"
 abstract: >-
-  UNHRDB is an open-source, paragraph-level research environment for UN human
-  rights law. It combines Treaty Body General Comments and Recommendations,
+  UNHRDB is a paragraph-level research environment for UN human rights law.
+  It combines Treaty Body General Comments and Recommendations,
   individual-communication jurisprudence, and thematic Special Procedures
   reports in a source-first interface with faceted search, document reading,
   citation export, workspaces, and an experimental extractive Ask workflow.
+  The repository holds the published site and its front-end code; the
+  data-processing pipeline is kept in a separate, private repository.
 keywords:
   - "UN human rights"
   - "UN Treaty Bodies"