add pipeline checks

.github/dependabot.yml

@@ -0,0 +1,6 @@
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"

.github/workflows/ci.yml

@@ -0,0 +1,64 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  validate:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - run: pip install pyarrow pandas
+      - run: |
+          python - <<'PY'
+          import json
+          import sys
+          from pathlib import Path
+
+          import pandas as pd
+          import pyarrow.parquet as pq
+
+          failures = []
+          for path in Path(".").rglob("*.parquet"):
+              try:
+                  pq.read_table(path)
+              except Exception as exc:
+                  failures.append(f"{path}: {exc}")
+          for path in Path(".").rglob("*.csv"):
+              try:
+                  pd.read_csv(path)
+              except Exception as exc:
+                  failures.append(f"{path}: {exc}")
+          for path in Path(".").rglob("*.json"):
+              try:
+                  json.loads(path.read_text())
+              except Exception as exc:
+                  failures.append(f"{path}: {exc}")
+
+          if failures:
+              print("\n".join(failures))
+              sys.exit(1)
+          print("All Parquet/CSV/JSON files load cleanly.")
+          PY
+
+  version-bump:
+    if: github.event_name == 'pull_request'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - run: |
+          BASE_VERSION=$(git show "origin/${{ github.base_ref }}:package.json" | node -pe 'JSON.parse(require("fs").readFileSync(0,"utf8")).version')
+          HEAD_VERSION=$(node -pe 'require("./package.json").version')
+          if [ "$BASE_VERSION" = "$HEAD_VERSION" ]; then
+            echo "package.json's version must be bumped from $BASE_VERSION before merging."
+            exit 1
+          fi
+          echo "Version bumped: $BASE_VERSION -> $HEAD_VERSION"

README.md

@@ -68,8 +68,6 @@ missing from it.
   `ui_*.json` files here
 * [tehillim-embeddings](https://github.com/rdtaylorjr/tehillim-embeddings): the embedding
   vectors scored here
-* [tehillim-logos](https://github.com/rdtaylorjr/tehillim-logos): the aligned Psalms parallelism
-  dataset behind the parallelism benchmark
 
 ## License
 

package.json

@@ -0,0 +1,5 @@
+{
+  "name": "tehillim-data",
+  "private": true,
+  "version": "0.2.0"
+}