GH-5648 new benchmark module (#5651)

* create module

* move common large benchmark files to the common module

* clean up shared queries

* data generator

Author: hmottestad

AGENTS.md

@@ -246,7 +246,7 @@ Evidence:
 Command: python3 .codex/skills/mvnf/scripts/mvnf.py Class#method (preferred) OR mvn -o -Dmaven.repo.local=.m2_repo -pl <module> -Dtest=Class#method verify
 Report: <module>/target/surefire-reports/<file>.txt
 Snippet:
-\<copy 10–30 lines capturing the failure or success summary>
+\<copy 1–30 lines capturing the failure or success summary>
 ```
 
 **Routine B additions**
@@ -429,6 +429,7 @@ Always keep untracked artifacts!
 3. **Migration/rename/autogen refresh** where behavior is already characterized by existing tests.
 4. **Build/CI/docs/logging/message changes** that do not alter runtime behavior or asserted outputs.
 5. **Data/resource tweaks** not asserted by tests and not affecting behavior.
+6. **Benchmark-only changes** (benchmark sources, harness scripts, or benchmark data) that do not alter production behavior.
 
 ### Routine B Gates (all must pass)
 - **Neutrality/Scope:** No externally observable behavior change. Localized edit.

compliance/model/pom.xml

@@ -21,6 +21,12 @@
 			<version>${jmhVersion}</version>
 			<scope>test</scope>
 		</dependency>
+		<dependency>
+			<groupId>${project.groupId}</groupId>
+			<artifactId>rdf4j-benchmark-common</artifactId>
+			<version>${project.version}</version>
+			<scope>test</scope>
+		</dependency>
 		<dependency>
 			<groupId>${project.groupId}</groupId>
 			<artifactId>rdf4j-model-testsuite</artifactId>

compliance/model/src/test/java/org/eclipse/rdf4j/model/util/IsomorphicBenchmark.java

@@ -8,6 +8,7 @@
  *
  * SPDX-License-Identifier: BSD-3-Clause
  *******************************************************************************/
+// Some portions generated by Codex
 
 package org.eclipse.rdf4j.model.util;
 
@@ -17,6 +18,7 @@
 import java.util.List;
 import java.util.concurrent.TimeUnit;
 
+import org.eclipse.rdf4j.benchmark.common.BenchmarkResources;
 import org.eclipse.rdf4j.model.Model;
 import org.eclipse.rdf4j.model.Statement;
 import org.eclipse.rdf4j.model.impl.TreeModel;
@@ -55,15 +57,15 @@ public class IsomorphicBenchmark {
 	private final Model longChain = getModel("longChain.ttl");
 	private final Model sparqlTestCase = getModel("sparqlTestCase.ttl");
 	private final Model spinFullForwardchained = getModel("spin-full-forwardchained.ttl");
-	private final Model bsbm = getModel("bsbm-100.ttl");
-	private final Model bsbmChanged = getModel("bsbm-100-changed.ttl");
+	private final Model bsbm = getModel("bsbm-100.ttl.gz");
+	private final Model bsbmChanged = getModel("bsbm-100-changed.ttl.gz");
 	private final List<Statement> bsbm_arraylist = new ArrayList<>(bsbm);
 	private final Model bsbmTree = new TreeModel(bsbm);
 	private final Model list = getModel("list.ttl");
 	private final Model internallyIsomorphic = getModel("internallyIsomorphic.ttl");
 	private final Model manyProperties = getModel("manyProperties.ttl");
 	private final Model manyProperties2 = getModel("manyProperties2.ttl");
-	private final Model uuid = getModel("uuid.ttl");
+	private final Model uuid = getModel("uuid.ttl.gz");
 
 	private final Model empty_2 = getModel("empty.ttl");
 	private final Model blankNodes_2 = getModel("blankNodes.ttl");
@@ -74,14 +76,14 @@ public class IsomorphicBenchmark {
 	private final Model longChain_2 = getModel("longChain.ttl");
 	private final Model sparqlTestCase_2 = getModel("sparqlTestCase.ttl");
 	private final Model spinFullForwardchained_2 = getModel("spin-full-forwardchained.ttl");
-	private final Model bsbm_2 = getModel("bsbm-100.ttl");
+	private final Model bsbm_2 = getModel("bsbm-100.ttl.gz");
 	private final List<Statement> bsbm_arraylist_2 = new ArrayList<>(bsbm);
 	private final Model bsbmTree_2 = new TreeModel(bsbm);
 	private final Model list_2 = getModel("list.ttl");
 	private final Model internallyIsomorphic_2 = getModel("internallyIsomorphic.ttl");
 	private final Model manyProperties_2 = getModel("manyProperties.ttl");
 	private final Model manyProperties2_2 = getModel("manyProperties2.ttl");
-	private final Model uuid_2 = getModel("uuid.ttl");
+	private final Model uuid_2 = getModel("uuid.ttl.gz");
 
 	public static void main(String[] args) throws RunnerException {
 		Options opt = new OptionsBuilder().include("IsomorphicBenchmark.*")
@@ -275,9 +277,15 @@ public boolean bsbmNotIsomorphic() {
 
 	private Model getModel(String name) {
 		try {
-			try (InputStream resourceAsStream = IsomorphicBenchmark.class.getClassLoader()
-					.getResourceAsStream("benchmarkFiles/" + name)) {
-				return Rio.parse(resourceAsStream, "http://example.com/", RDFFormat.TURTLE);
+			InputStream resourceAsStream;
+			if (name.endsWith(".gz")) {
+				resourceAsStream = BenchmarkResources.openDecompressedStream("benchmarkFiles/" + name);
+			} else {
+				resourceAsStream = IsomorphicBenchmark.class.getClassLoader()
+						.getResourceAsStream("benchmarkFiles/" + name);
+			}
+			try (InputStream inputStream = resourceAsStream) {
+				return Rio.parse(inputStream, "http://example.com/", RDFFormat.TURTLE);
 			}
 		} catch (IOException e) {
 			throw new RuntimeException(e);

compliance/model/src/test/java/org/eclipse/rdf4j/model/util/IsomorphicTest.java

@@ -8,6 +8,7 @@
  *
  * SPDX-License-Identifier: BSD-3-Clause
  *******************************************************************************/
+// Some portions generated by Codex
 
 package org.eclipse.rdf4j.model.util;
 
@@ -19,6 +20,7 @@
 import java.util.ArrayList;
 import java.util.List;
 
+import org.eclipse.rdf4j.benchmark.common.BenchmarkResources;
 import org.eclipse.rdf4j.model.Model;
 import org.eclipse.rdf4j.model.Statement;
 import org.eclipse.rdf4j.model.impl.TreeModel;
@@ -67,8 +69,8 @@ public static void beforeClass() {
 		longChain = getModel("longChain.ttl");
 		sparqlTestCase = getModel("sparqlTestCase.ttl");
 		spinFullForwardchained = getModel("spin-full-forwardchained.ttl");
-		bsbm = getModel("bsbm-100.ttl");
-		bsbmChanged = getModel("bsbm-100-changed.ttl");
+		bsbm = getModel("bsbm-100.ttl.gz");
+		bsbmChanged = getModel("bsbm-100-changed.ttl.gz");
 		bsbm_arraylist = new ArrayList<>(bsbm);
 		bsbmTree = new TreeModel(bsbm);
 		list = getModel("list.ttl");
@@ -82,7 +84,7 @@ public static void beforeClass() {
 		longChain_2 = getModel("longChain.ttl");
 		sparqlTestCase_2 = getModel("sparqlTestCase.ttl");
 		spinFullForwardchained_2 = getModel("spin-full-forwardchained.ttl");
-		bsbm_2 = getModel("bsbm-100.ttl");
+		bsbm_2 = getModel("bsbm-100.ttl.gz");
 		bsbm_arraylist_2 = new ArrayList<>(bsbm);
 		bsbmTree_2 = new TreeModel(bsbm);
 		list_2 = getModel("list.ttl");
@@ -255,9 +257,15 @@ public void testIsomorphicDatatype() throws Exception {
 
 	private static Model getModel(String name) {
 		try {
-			try (InputStream resourceAsStream = IsomorphicTest.class.getClassLoader()
-					.getResourceAsStream("benchmarkFiles/" + name)) {
-				return Rio.parse(resourceAsStream, "http://example.com/", RDFFormat.TURTLE);
+			InputStream resourceAsStream;
+			if (name.endsWith(".gz")) {
+				resourceAsStream = BenchmarkResources.openDecompressedStream("benchmarkFiles/" + name);
+			} else {
+				resourceAsStream = IsomorphicTest.class.getClassLoader()
+						.getResourceAsStream("benchmarkFiles/" + name);
+			}
+			try (InputStream inputStream = resourceAsStream) {
+				return Rio.parse(inputStream, "http://example.com/", RDFFormat.TURTLE);
 			}
 		} catch (IOException e) {
 			throw new RuntimeException(e);