Merge remote-tracking branch 'upstream/main' into keyword-high-cardinality-param-2

Author: jordan-powers

.buildkite/pipelines/periodic-java-ea.yml

@@ -385,8 +385,8 @@ steps:
             - signal_reason: agent_stop
               limit: 3
 
-      - label: 9.0.7 / bwc
-        command: .ci/scripts/run-gradle.sh -Druntime.java=$$JAVA_EA_VERSION -Dbwc.checkout.align=true v9.0.7#bwcTest
+      - label: 9.0.8 / bwc
+        command: .ci/scripts/run-gradle.sh -Druntime.java=$$JAVA_EA_VERSION -Dbwc.checkout.align=true v9.0.8#bwcTest
         timeout_in_minutes: 300
         agents:
           provider: gcp
@@ -395,7 +395,7 @@ steps:
           buildDirectory: /dev/shm/bk
           preemptible: true
         env:
-          BWC_VERSION: 9.0.7
+          BWC_VERSION: 9.0.8
         retry:
           automatic:
             - exit_status: "-1"

.buildkite/pipelines/periodic-packaging.yml

@@ -352,8 +352,8 @@ steps:
         env:
           BWC_VERSION: 8.19.8
 
-      - label: "{{matrix.image}} / 9.0.7 / packaging-tests-upgrade"
-        command: ./.ci/scripts/packaging-test.sh -Dbwc.checkout.align=true destructiveDistroUpgradeTest.v9.0.7
+      - label: "{{matrix.image}} / 9.0.8 / packaging-tests-upgrade"
+        command: ./.ci/scripts/packaging-test.sh -Dbwc.checkout.align=true destructiveDistroUpgradeTest.v9.0.8
         timeout_in_minutes: 300
         matrix:
           setup:
@@ -366,7 +366,7 @@ steps:
           machineType: custom-16-32768
           buildDirectory: /dev/shm/bk
         env:
-          BWC_VERSION: 9.0.7
+          BWC_VERSION: 9.0.8
 
       - label: "{{matrix.image}} / 9.1.8 / packaging-tests-upgrade"
         command: ./.ci/scripts/packaging-test.sh -Dbwc.checkout.align=true destructiveDistroUpgradeTest.v9.1.8

.buildkite/pipelines/periodic.template.yml

@@ -92,8 +92,7 @@ steps:
           setup:
             ES_RUNTIME_JAVA:
               - openjdk21
-              - openjdk23
-              - openjdk24
+              - openjdk25
             GRADLE_TASK:
               - checkPart1
               - checkPart2
@@ -118,7 +117,7 @@ steps:
           setup:
             ES_RUNTIME_JAVA:
               - openjdk21
-              - openjdk23
+              - openjdk25
             BWC_VERSION: $BWC_LIST
         agents:
           provider: gcp

.buildkite/pipelines/periodic.yml

@@ -382,8 +382,8 @@ steps:
             - signal_reason: agent_stop
               limit: 3
 
-      - label: 9.0.7 / bwc
-        command: .ci/scripts/run-gradle.sh --continue -Dbwc.checkout.align=true v9.0.7#bwcTest
+      - label: 9.0.8 / bwc
+        command: .ci/scripts/run-gradle.sh --continue -Dbwc.checkout.align=true v9.0.8#bwcTest
         timeout_in_minutes: 300
         agents:
           provider: gcp
@@ -392,7 +392,7 @@ steps:
           buildDirectory: /dev/shm/bk
           preemptible: true
         env:
-          BWC_VERSION: 9.0.7
+          BWC_VERSION: 9.0.8
         retry:
           automatic:
             - exit_status: "-1"
@@ -549,8 +549,7 @@ steps:
           setup:
             ES_RUNTIME_JAVA:
               - openjdk21
-              - openjdk23
-              - openjdk24
+              - openjdk25
             GRADLE_TASK:
               - checkPart1
               - checkPart2
@@ -575,7 +574,7 @@ steps:
           setup:
             ES_RUNTIME_JAVA:
               - openjdk21
-              - openjdk23
+              - openjdk25
             BWC_VERSION: ["8.19.8", "9.1.8", "9.2.2", "9.3.0"]
         agents:
           provider: gcp

.ci/bwcVersions

@@ -19,7 +19,7 @@ BWC_VERSION:
   - "8.17.10"
   - "8.18.8"
   - "8.19.8"
-  - "9.0.7"
+  - "9.0.8"
   - "9.1.8"
   - "9.2.2"
   - "9.3.0"

.gitattributes

@@ -4,12 +4,13 @@ CHANGELOG.asciidoc  merge=union
 # Windows
 build-tools-internal/src/test/resources/org/elasticsearch/gradle/internal/release/*.asciidoc text eol=lf
 
+# ESQL parsing and source generated related assets
 x-pack/plugin/esql/compute/src/main/generated/** linguist-generated=true
 x-pack/plugin/esql/compute/src/main/generated-src/** linguist-generated=true
 x-pack/plugin/esql/src/main/antlr/*.tokens linguist-generated=true
 x-pack/plugin/esql/src/main/java/org/elasticsearch/xpack/esql/parser/*.interp linguist-generated=true
-x-pack/plugin/esql/src/main/java/org/elasticsearch/xpack/esql/parser/EsqlBaseLexer*.java linguist-generated=true
-x-pack/plugin/esql/src/main/java/org/elasticsearch/xpack/esql/parser/EsqlBaseParser*.java linguist-generated=true
+x-pack/plugin/esql/src/main/java/org/elasticsearch/xpack/esql/parser/*BaseLexer*.java linguist-generated=true
+x-pack/plugin/esql/src/main/java/org/elasticsearch/xpack/esql/parser/*BaseParser*.java linguist-generated=true
 x-pack/plugin/esql/src/main/generated/** linguist-generated=true
 x-pack/plugin/esql/src/main/generated-src/** linguist-generated=true
 

CONTRIBUTING.md

@@ -49,6 +49,13 @@ We add the `help wanted` label to existing GitHub issues for which community
 contributions are particularly welcome, and we use the `good first issue` label
 to mark issues that we think will be suitable for new contributors.
 
+We generally do not assign issues to contributors outside of Elastic, but
+please check the discussion on the issue to see if anyone else is working on
+the same topic. If there are other active contributors in the same area then it
+is a good idea to reach out to them so you can work together on the issue. If
+there hasn't been any discussion for a while then go ahead and start working on
+the issue yourself.
+
 The process for contributing to any of the [Elastic repositories](https://github.com/elastic/) is similar. Details for individual projects can be found below.
 
 ### Fork and clone the repository

benchmarks/src/main/java/org/elasticsearch/benchmark/_nightly/esql/QueryPlanningBenchmark.java

@@ -102,7 +102,7 @@ public void setup() {
             mapping.put("field" + i, new EsField("field-" + i, TEXT, emptyMap(), true, EsField.TimeSeriesFieldType.NONE));
         }
 
-        var esIndex = new EsIndex("test", mapping, Map.of("test", IndexMode.STANDARD), Set.of());
+        var esIndex = new EsIndex("test", mapping, Map.of("test", IndexMode.STANDARD), Map.of(), Map.of(), Set.of());
 
         var functionRegistry = new EsqlFunctionRegistry();
 

benchmarks/src/main/java/org/elasticsearch/benchmark/vector/scorer/BenchmarkUtils.java

@@ -0,0 +1,94 @@
+/*
+ * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
+ * or more contributor license agreements. Licensed under the "Elastic License
+ * 2.0", the "GNU Affero General Public License v3.0 only", and the "Server Side
+ * Public License v 1"; you may not use this file except in compliance with, at
+ * your election, the "Elastic License 2.0", the "GNU Affero General Public
+ * License v3.0 only", or the "Server Side Public License, v 1".
+ */
+
+package org.elasticsearch.benchmark.vector.scorer;
+
+import org.apache.lucene.codecs.lucene99.Lucene99ScalarQuantizedVectorScorer;
+import org.apache.lucene.codecs.lucene99.OffHeapQuantizedByteVectorValues;
+import org.apache.lucene.index.VectorSimilarityFunction;
+import org.apache.lucene.store.Directory;
+import org.apache.lucene.store.IOContext;
+import org.apache.lucene.store.IndexInput;
+import org.apache.lucene.store.IndexOutput;
+import org.apache.lucene.store.MemorySegmentAccessInput;
+import org.apache.lucene.util.hnsw.RandomVectorScorer;
+import org.apache.lucene.util.hnsw.RandomVectorScorerSupplier;
+import org.apache.lucene.util.quantization.QuantizedByteVectorValues;
+import org.apache.lucene.util.quantization.ScalarQuantizer;
+import org.elasticsearch.simdvec.VectorScorerFactory;
+
+import java.io.IOException;
+import java.util.concurrent.ThreadLocalRandom;
+
+class BenchmarkUtils {
+    // Unsigned int7 byte vectors have values in the range of 0 to 127 (inclusive).
+    static final byte MIN_INT7_VALUE = 0;
+    static final byte MAX_INT7_VALUE = 127;
+
+    static void randomInt7BytesBetween(byte[] bytes) {
+        var random = ThreadLocalRandom.current();
+        for (int i = 0, len = bytes.length; i < len;) {
+            bytes[i++] = (byte) random.nextInt(MIN_INT7_VALUE, MAX_INT7_VALUE + 1);
+        }
+    }
+
+    static void createRandomInt7VectorData(ThreadLocalRandom random, Directory dir, int dims, int numVectors) throws IOException {
+        try (IndexOutput out = dir.createOutput("vector.data", IOContext.DEFAULT)) {
+            var vec = new byte[dims];
+            for (int v = 0; v < numVectors; v++) {
+                randomInt7BytesBetween(vec);
+                var vecOffset = random.nextFloat();
+                out.writeBytes(vec, 0, vec.length);
+                out.writeInt(Float.floatToIntBits(vecOffset));
+            }
+        }
+    }
+
+    static VectorScorerFactory getScorerFactoryOrDie() {
+        var optionalVectorScorerFactory = VectorScorerFactory.instance();
+        if (optionalVectorScorerFactory.isEmpty()) {
+            String msg = "JDK=["
+                + Runtime.version()
+                + "], os.name=["
+                + System.getProperty("os.name")
+                + "], os.arch=["
+                + System.getProperty("os.arch")
+                + "]";
+            throw new AssertionError("Vector scorer factory not present. Cannot run the benchmark. " + msg);
+        }
+        return optionalVectorScorerFactory.get();
+    }
+
+    static boolean supportsHeapSegments() {
+        return Runtime.version().feature() >= 22;
+    }
+
+    static QuantizedByteVectorValues vectorValues(int dims, int size, IndexInput in, VectorSimilarityFunction sim) throws IOException {
+        var sq = new ScalarQuantizer(0.1f, 0.9f, (byte) 7);
+        var slice = in.slice("values", 0, in.length());
+        return new OffHeapQuantizedByteVectorValues.DenseOffHeapVectorValues(dims, size, sq, false, sim, null, slice);
+    }
+
+    static RandomVectorScorerSupplier luceneScoreSupplier(QuantizedByteVectorValues values, VectorSimilarityFunction sim)
+        throws IOException {
+        return new Lucene99ScalarQuantizedVectorScorer(null).getRandomVectorScorerSupplier(sim, values);
+    }
+
+    static RandomVectorScorer luceneScorer(QuantizedByteVectorValues values, VectorSimilarityFunction sim, float[] queryVec)
+        throws IOException {
+        return new Lucene99ScalarQuantizedVectorScorer(null).getRandomVectorScorer(sim, values, queryVec);
+    }
+
+    static float readNodeCorrectionConstant(QuantizedByteVectorValues values, int targetOrd) throws IOException {
+        var vectorByteSize = values.getVectorByteLength();
+        var input = (MemorySegmentAccessInput) values.getSlice();
+        long byteOffset = (long) targetOrd * (vectorByteSize + Float.BYTES);
+        return Float.intBitsToFloat(input.readInt(byteOffset + vectorByteSize));
+    }
+}