[8.15] Fix Synthetic Source Handling for bit Type in dense_vector Field (#114407) (#114759)

* Fix Synthetic Source Handling for `bit` Type in `dense_vector` Field (#114407)

**Description:**

This PR addresses the issue described in [#114402](#114402), where the `synthetic_source` feature does not correctly handle the `bit` type in `dense_vector` fields when `index` is set to `false`. The root cause of the issue was that the `bit` type was not properly accounted for, leading to an array that is 8 times the size of the actual `dims` value of docvalue. This mismatch will causes an array out-of-bounds exception when reconstructing the document.

**Changes:**

- Adjusted the `synthetic_source` logic to correctly handle the `bit` type by ensuring the array size accounts for the 8x difference in dimensions.
- Added yaml test to cover the `bit` type scenario in `dense_vector` fields with `index` set to `false`.

**Related Issues:**

- Closes [#114402](#114402)
- Introduced in [#110059](#110059)

(cherry picked from commit 465c65c)

* fixing backport of search capabilities

* fixing license header

* adding capabilities to RestSearchAction

* fixing backport

* spotless

* muting teset for ccs

* adding capabilities to the ccs test runner

---------

Co-authored-by: Rassyan <[email protected]>

Author: benwtrent

docs/changelog/114407.yaml

@@ -0,0 +1,6 @@
+pr: 114407
+summary: Fix synthetic source handling for `bit` type in `dense_vector` field
+area: Search
+type: bug
+issues:
+  - 114402

qa/ccs-common-rest/build.gradle

@@ -10,7 +10,7 @@ apply plugin: 'elasticsearch.internal-yaml-rest-test'
 
 restResources {
   restApi {
-    include '_common', 'bulk', 'count', 'cluster', 'field_caps', 'get', 'knn_search', 'index', 'indices', 'msearch',
+    include 'capabilities', '_common', 'bulk', 'count', 'cluster', 'field_caps', 'get', 'knn_search', 'index', 'indices', 'msearch',
       'search', 'async_search', 'graph', '*_point_in_time', 'info', 'scroll', 'clear_scroll', 'search_mvt', 'eql', 'sql'
   }
   restTests {

rest-api-spec/src/yamlRestTest/resources/rest-api-spec/test/search.vectors/45_knn_search_bit.yml

@@ -354,3 +354,54 @@ setup:
               dims: 40
               index: true
               similarity: max_inner_product
+
+
+---
+"Search with synthetic source":
+  - requires:
+      reason: "Support for bit dense vector synthetic source capability required"
+      test_runner_features: [capabilities]
+      capabilities:
+        - method: POST
+          path: /_search
+          capabilities: [ bit_dense_vector_synthetic_source ]
+  - do:
+      indices.create:
+        index: test_synthetic_source
+        body:
+          mappings:
+            properties:
+              name:
+                type: keyword
+              vector1:
+                type: dense_vector
+                element_type: bit
+                dims: 40
+                index: false
+              vector2:
+                type: dense_vector
+                element_type: bit
+                dims: 40
+                index: true
+                similarity: l2_norm
+
+  - do:
+      index:
+        index: test_synthetic_source
+        id: "1"
+        body:
+          name: cow.jpg
+          vector1: [2, -1, 1, 4, -3]
+          vector2: [2, -1, 1, 4, -3]
+
+  - do:
+      indices.refresh: {}
+
+  - do:
+      search:
+        force_synthetic_source: true
+        index: test_synthetic_source
+
+  - match: {hits.hits.0._id: "1"}
+  - match: {hits.hits.0._source.vector1: [2, -1, 1, 4, -3]}
+  - match: {hits.hits.0._source.vector2: [2, -1, 1, 4, -3]}

server/src/main/java/org/elasticsearch/index/mapper/vectors/DenseVectorFieldMapper.java

@@ -2218,7 +2218,7 @@ public void write(XContentBuilder b) throws IOException {
             if (indexCreatedVersion.onOrAfter(LITTLE_ENDIAN_FLOAT_STORED_INDEX_VERSION)) {
                 byteBuffer.order(ByteOrder.LITTLE_ENDIAN);
             }
-            int dims = fieldType().dims;
+            int dims = fieldType().elementType == ElementType.BIT ? fieldType().dims / Byte.SIZE : fieldType().dims;
             for (int dim = 0; dim < dims; dim++) {
                 fieldType().elementType.readAndWriteValue(byteBuffer, b);
             }

server/src/main/java/org/elasticsearch/rest/action/search/RestSearchAction.java

@@ -94,6 +94,11 @@ public List<Route> routes() {
         );
     }
 
+    @Override
+    public Set<String> supportedCapabilities() {
+        return SearchCapabilities.CAPABILITIES;
+    }
+
     @Override
     public RestChannelConsumer prepareRequest(final RestRequest request, final NodeClient client) throws IOException {
 

server/src/main/java/org/elasticsearch/rest/action/search/SearchCapabilities.java

@@ -0,0 +1,24 @@
+/*
+ * 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 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 or the Server
+ * Side Public License, v 1.
+ */
+
+package org.elasticsearch.rest.action.search;
+
+import java.util.Set;
+
+/**
+ * A {@link Set} of "capabilities" supported by the {@link RestSearchAction}.
+ */
+public final class SearchCapabilities {
+
+    private SearchCapabilities() {}
+
+    /** Support synthetic source with `bit` type in `dense_vector` field when `index` is set to `false`. */
+    private static final String BIT_DENSE_VECTOR_SYNTHETIC_SOURCE_CAPABILITY = "bit_dense_vector_synthetic_source";
+
+    public static final Set<String> CAPABILITIES = Set.of(BIT_DENSE_VECTOR_SYNTHETIC_SOURCE_CAPABILITY);
+}

server/src/test/java/org/elasticsearch/index/mapper/vectors/DenseVectorFieldMapperTests.java

@@ -1435,24 +1435,27 @@ protected boolean supportsEmptyInputArray() {
 
     private static class DenseVectorSyntheticSourceSupport implements SyntheticSourceSupport {
         private final int dims = between(5, 1000);
-        private final ElementType elementType = randomFrom(ElementType.BYTE, ElementType.FLOAT);
+        private final ElementType elementType = randomFrom(ElementType.BYTE, ElementType.FLOAT, ElementType.BIT);
         private final boolean indexed = randomBoolean();
         private final boolean indexOptionsSet = indexed && randomBoolean();
 
         @Override
         public SyntheticSourceExample example(int maxValues) throws IOException {
-            Object value = elementType == ElementType.BYTE
-                ? randomList(dims, dims, ESTestCase::randomByte)
-                : randomList(dims, dims, ESTestCase::randomFloat);
+            Object value = switch (elementType) {
+                case BYTE, BIT:
+                    yield randomList(dims, dims, ESTestCase::randomByte);
+                case FLOAT:
+                    yield randomList(dims, dims, ESTestCase::randomFloat);
+            };
             return new SyntheticSourceExample(value, value, this::mapping);
         }
 
         private void mapping(XContentBuilder b) throws IOException {
             b.field("type", "dense_vector");
-            b.field("dims", dims);
-            if (elementType == ElementType.BYTE || randomBoolean()) {
+            if (elementType == ElementType.BYTE || elementType == ElementType.BIT || randomBoolean()) {
                 b.field("element_type", elementType.toString());
             }
+            b.field("dims", elementType == ElementType.BIT ? dims * Byte.SIZE : dims);
             if (indexed) {
                 b.field("index", true);
                 b.field("similarity", "l2_norm");