Update dependencies, fix deprecations, add CI checks

.github/workflows/main.yaml

@@ -18,23 +18,23 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v7
 
       - name: Log in to the Container registry
-        uses: docker/login-action@v3
+        uses: docker/login-action@v4
         with:
           registry: ${{ env.REGISTRY }}
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Extract metadata (tags, labels) for Docker
         id: meta
-        uses: docker/metadata-action@v5
+        uses: docker/metadata-action@v6
         with:
           images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
 
       - name: Build and push Docker image
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@v7
         with:
           context: .
           push: true

.github/workflows/pr.yaml

@@ -0,0 +1,19 @@
+name: PR check
+
+on:
+  pull_request:
+    branches: ['main']
+
+jobs:
+  docker-smoke-test:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v7
+
+      - name: Build Docker image
+        run: docker build -t ci-worker-smoke .
+
+      - name: Run self-test in Docker
+        run: docker run --rm ci-worker-smoke ci-worker self-test

Dockerfile

@@ -1,5 +1,4 @@
-# GraalVM CE 22.3.3-b1 Java 17, Scala 3.3.3, SBT 1.9.9
-FROM sbtscala/scala-sbt:graalvm-ce-22.3.3-b1-java17_1.9.9_3.3.3 as builder
+FROM sbtscala/scala-sbt:eclipse-temurin-25.0.3_9_1.12.12_3.8.4 AS builder
 
 # Copy the project sources
 COPY . /app
@@ -9,11 +8,11 @@ WORKDIR /app
 RUN sbt assembly
 
 # Create the final image
-FROM eclipse-temurin:19-jre-jammy
-MAINTAINER "Piotr Sowiński <piotr.sowinski@ibspan.waw.pl>"
+FROM eclipse-temurin:25-jre-noble
+LABEL maintainer="Piotr Sowiński <piotr@neverblink.eu>"
 
-RUN apt update && \
-    apt install -y git wget && \
+RUN apt-get update && \
+    apt-get install -y git wget && \
     rm -rf /var/lib/apt/lists/*
 
 # Copy the executable jar

build.sbt

@@ -1,17 +1,17 @@
 ThisBuild / version := "0.1.0-SNAPSHOT"
-ThisBuild / scalaVersion := "3.7.1"
+ThisBuild / scalaVersion := "3.8.4"
 
 resolvers +=
   "Sonatype OSS Snapshots" at "https://s01.oss.sonatype.org/content/repositories/snapshots"
 
-lazy val circeV = "0.14.14"
-lazy val jellyV = "3.4.0"
+lazy val circeV = "0.14.15"
+lazy val jellyV = "3.7.3"
 lazy val jenaV = "5.3.0"
 lazy val pekkoV = "1.1.5"
-lazy val pekkoHttpV = "1.2.0"
-lazy val pekkoConnV = "1.1.0"
-lazy val rdf4jV = "5.1.4"
-lazy val icu4jV = "77.1"
+lazy val pekkoHttpV = "1.3.0"
+lazy val pekkoConnV = "1.3.0"
+lazy val rdf4jV = "5.3.1"
+lazy val icu4jV = "78.3"
 
 lazy val root = (project in file("."))
   .settings(
@@ -20,7 +20,7 @@ lazy val root = (project in file("."))
 
     // Scala 3 or not Scala at all
     libraryDependencies ++= Seq(
-      "com.google.guava" % "guava" % "33.4.8-jre",
+      "com.google.guava" % "guava" % "33.6.0-jre",
       "com.ibm.icu" % "icu4j" % icu4jV,
       "eu.neverblink.jelly" %% "jelly-pekko-stream" % jellyV,
       "eu.neverblink.jelly" % "jelly-jena" % jellyV,
@@ -40,8 +40,7 @@ lazy val root = (project in file("."))
       "org.eclipse.rdf4j" % "rdf4j-model" % rdf4jV,
       "org.eclipse.rdf4j" % "rdf4j-rio-turtle" % rdf4jV,
       "org.eclipse.rdf4j" % "rdf4j-rio-trig" % rdf4jV,
-      // datasketches 8 requires Java 21 it seems, so we use 7 for now
-      "org.apache.datasketches" % "datasketches-java" % "7.0.1",
+      "org.apache.datasketches" % "datasketches-java" % "9.0.0",
     ),
 
     // Discard module-info.class files

src/main/scala/commands/PackageCommand.scala

@@ -466,7 +466,7 @@ object PackageCommand extends Command:
     if !metadata.conformance.usesRdfStar then
       val rdfStar = ds.find().asScala
         .flatMap(q => q.getGraph :: q.getSubject :: q.getPredicate :: q.getObject :: Nil)
-        .exists(_.isNodeTriple)
+        .exists(_.isTripleTerm)
       if rdfStar then
         return Some(s"The dataset contains an RDF-star node, " +
           s"but the metadata does not declare the use of RDF-star.")

src/main/scala/commands/batch/DegreeDistributionsCommand.scala

@@ -104,7 +104,7 @@ object DegreeDistributionsCommand extends Command:
       counter.value += 1
 
     val statementSource: Source[Triple | Quad, NotUsed] = Source.futureSource(response.map(_.entity.dataBytes))
-      .via(Compression.gunzip())
+      .via(Compression.gzipDecompress())
       .toMat(StreamConverters.asInputStream())(Keep.right)
       .mapMaterializedValue(JellyIo.fromIoStream)
       .run()

src/main/scala/util/StatCounterSuite.scala

@@ -115,7 +115,7 @@ class StatCounterSuite(val size: Long):
     // Find triples recursively – needed for RDF-star
     def getTriples(t: Triple): List[Triple] =
       t +: (t.getSubject :: t.getPredicate :: t.getObject :: Nil)
-        .filter(_.isNodeTriple)
+        .filter(_.isTripleTerm)
         .flatMap(n => getTriples(n.getTriple))
 
     val allNodes = ds.find().asScala.flatMap(t => {
@@ -148,7 +148,7 @@ class StatCounterSuite(val size: Long):
           datatypes += n.getLiteralDatatypeURI
         else
           simpleLiterals += n.getLiteralLexicalForm
-      else if n.isNodeTriple then
+      else if n.isTripleTerm then
         // isomorphism in RDF-star is a pain...
         quotedTripleCount += 1
     })

src/main/scala/util/io/FileHelper.scala

@@ -41,7 +41,7 @@ object FileHelper:
     // Unfortunately, Pekko untar stage is glitchy with large archives, so we have to
     // use the non-reactive Apache Commons implementation instead.
     val tarIs = source
-      .via(Compression.gunzip())
+      .via(Compression.gzipDecompress())
       .toMat(StreamConverters.asInputStream())(Keep.right)
       .mapMaterializedValue(bytesIs => TarArchiveInputStream(bytesIs))
       .run()

src/main/scala/util/rdf/JsonLdEmbedding.scala

@@ -18,6 +18,7 @@ import org.apache.jena.vocabulary.*
 import java.io.FileOutputStream
 import java.nio.file.Path
 import java.util
+import scala.annotation.nowarn
 import scala.collection.mutable
 import scala.jdk.CollectionConverters.*
 
@@ -69,6 +70,7 @@ object JsonLdEmbedding:
    * @param m RDF model
    * @param mdFilePath file name of the original markdown file
    */
+  @nowarn("msg=deprecated")
   def saveEmbed(m: Model, subject: Resource, mdFilePath: Path): Unit =
     val mCopy = translateDcatToSchema(m, subject)
     // val mCopy = ModelFactory.createDefaultModel().add(m)

src/main/scala/util/rdf/SubjectNodeShape.scala

@@ -35,7 +35,7 @@ object SubjectNodeShape:
     override def findInDs(ds: DatasetGraph) = customInstance match
       case RdfUtil.`yagoTarget` => ds.find(null, null, null, null).asScala
         .map(_.getSubject)
-        .filter(_.isNodeTriple)
+        .filter(_.isTripleTerm)
         .map(_.getTriple.getSubject)
         .toSeq
       case _ => throw new Exception(s"Unknown custom target instance: $customInstance")