Merge branch 'main' into ivf_zero_docs

Author: benwtrent

benchmarks/build.gradle

@@ -41,6 +41,7 @@ dependencies {
   }
   api(project(':libs:h3'))
   api(project(':modules:aggregations'))
+  implementation project(':modules:mapper-extras');
   api(project(':x-pack:plugin:esql-core'))
   api(project(':x-pack:plugin:core'))
   api(project(':x-pack:plugin:esql'))

benchmarks/src/main/java/org/elasticsearch/benchmark/index/mapper/MapperServiceFactory.java

@@ -29,6 +29,7 @@
 import org.elasticsearch.index.mapper.ProvidedIdFieldMapper;
 import org.elasticsearch.index.similarity.SimilarityService;
 import org.elasticsearch.indices.IndicesModule;
+import org.elasticsearch.plugins.MapperPlugin;
 import org.elasticsearch.script.Script;
 import org.elasticsearch.script.ScriptCompiler;
 import org.elasticsearch.script.ScriptContext;
@@ -38,11 +39,16 @@
 import java.io.IOException;
 import java.io.UncheckedIOException;
 import java.util.Collections;
+import java.util.List;
 import java.util.Map;
 
 public class MapperServiceFactory {
 
     public static MapperService create(String mappings) {
+        return create(mappings, Collections.emptyList());
+    }
+
+    public static MapperService create(String mappings, List<MapperPlugin> mapperPlugins) {
         Settings settings = Settings.builder()
             .put("index.number_of_replicas", 0)
             .put("index.number_of_shards", 1)
@@ -51,7 +57,7 @@ public static MapperService create(String mappings) {
             .build();
         IndexMetadata meta = IndexMetadata.builder("index").settings(settings).build();
         IndexSettings indexSettings = new IndexSettings(meta, settings);
-        MapperRegistry mapperRegistry = new IndicesModule(Collections.emptyList()).getMapperRegistry();
+        MapperRegistry mapperRegistry = new IndicesModule(mapperPlugins).getMapperRegistry();
 
         SimilarityService similarityService = new SimilarityService(indexSettings, null, Map.of());
         BitsetFilterCache bitsetFilterCache = new BitsetFilterCache(indexSettings, BitsetFilterCache.Listener.NOOP);

benchmarks/src/main/java/org/elasticsearch/benchmark/xcontent/OptimizedTextBenchmark.java

@@ -15,6 +15,7 @@
 import org.elasticsearch.common.logging.LogConfigurator;
 import org.elasticsearch.index.mapper.MapperService;
 import org.elasticsearch.index.mapper.SourceToParse;
+import org.elasticsearch.index.mapper.extras.MapperExtrasPlugin;
 import org.elasticsearch.xcontent.XContentBuilder;
 import org.elasticsearch.xcontent.XContentFactory;
 import org.elasticsearch.xcontent.XContentType;
@@ -34,6 +35,7 @@
 import org.openjdk.jmh.infra.Blackhole;
 
 import java.io.IOException;
+import java.util.List;
 import java.util.Random;
 import java.util.concurrent.TimeUnit;
 
@@ -66,7 +68,7 @@ public class OptimizedTextBenchmark {
     private SourceToParse[] sources;
 
     private String randomValue(int length) {
-        final String CHARS = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789";
+        final String CHARS = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789 ";
         Random random = new Random();
         StringBuilder builder = new StringBuilder(length);
         for (int i = 0; i < length; i++) {
@@ -83,17 +85,17 @@ public void setup() throws IOException {
                     "dynamic": false,
                     "properties": {
                         "field": {
-                            "type": "keyword"
+                            "type": "match_only_text"
                         }
                     }
                 }
             }
-            """);
+            """, List.of(new MapperExtrasPlugin()));
 
         sources = new SourceToParse[nDocs];
         for (int i = 0; i < nDocs; i++) {
             XContentBuilder b = XContentFactory.jsonBuilder();
-            b.startObject().field("field", randomValue(8)).endObject();
+            b.startObject().field("field", randomValue(512)).endObject();
             sources[i] = new SourceToParse(UUIDs.randomBase64UUID(), BytesReference.bytes(b), XContentType.JSON);
         }
     }

docs/changelog/127636.yaml

@@ -0,0 +1,17 @@
+pr: 127636
+summary: Disallow mixed quoted/unquoted patterns in FROM
+area: ES|QL
+type: breaking
+issues:
+ - 122651
+breaking:
+  title: Disallow mixed quoted/unquoted patterns in FROM
+  area: ES|QL
+  details: "Previously, the ES|QL grammar allowed users to individually quote constituent strings in index patterns\
+    \ such as \"remote_cluster\":\"index_name\". This would allow users to write complex malformed index patterns\
+    \ that often slip through grammar and the subsequent validation. This could result in runtime errors\
+    \ that can be misleading. This change simplifies the grammar to early reject such malformed index patterns\
+    \ at the parsing stage, allowing users to write simpler queries and see more relevant and meaningful\
+    \ errors."
+  impact: "Users can write queries with simpler index patterns and see more meaningful and relevant errors."
+  notable: false

modules/mapper-extras/src/main/java/org/elasticsearch/index/mapper/extras/MatchOnlyTextFieldMapper.java

@@ -31,6 +31,7 @@
 import org.apache.lucene.util.IOFunction;
 import org.elasticsearch.common.CheckedIntFunction;
 import org.elasticsearch.common.lucene.Lucene;
+import org.elasticsearch.common.text.UTF8DecodingReader;
 import org.elasticsearch.common.unit.Fuzziness;
 import org.elasticsearch.index.IndexVersion;
 import org.elasticsearch.index.analysis.IndexAnalyzers;
@@ -364,7 +365,7 @@ public Query phrasePrefixQuery(TokenStream stream, int slop, int maxExpansions,
         @Override
         public BlockLoader blockLoader(BlockLoaderContext blContext) {
             if (textFieldType.isSyntheticSource()) {
-                return new BlockStoredFieldsReader.BytesFromStringsBlockLoader(storedFieldNameForSyntheticSource());
+                return new BlockStoredFieldsReader.BytesFromBytesRefsBlockLoader(storedFieldNameForSyntheticSource());
             }
             SourceValueFetcher fetcher = SourceValueFetcher.toString(blContext.sourcePaths(name()));
             // MatchOnlyText never has norms, so we have to use the field names field
@@ -385,7 +386,7 @@ public IndexFieldData.Builder fielddataBuilder(FieldDataContext fieldDataContext
                 ) {
                     @Override
                     protected BytesRef storedToBytesRef(Object stored) {
-                        return new BytesRef((String) stored);
+                        return (BytesRef) stored;
                     }
                 };
             }
@@ -443,18 +444,20 @@ public FieldMapper.Builder getMergeBuilder() {
 
     @Override
     protected void parseCreateField(DocumentParserContext context) throws IOException {
-        final String value = context.parser().textOrNull();
+        final var value = context.parser().optimizedTextOrNull();
 
         if (value == null) {
             return;
         }
 
-        Field field = new Field(fieldType().name(), value, fieldType);
+        final var utfBytes = value.bytes();
+        Field field = new Field(fieldType().name(), new UTF8DecodingReader(utfBytes), fieldType);
         context.doc().add(field);
         context.addToFieldNames(fieldType().name());
 
         if (storeSource) {
-            context.doc().add(new StoredField(fieldType().storedFieldNameForSyntheticSource(), value));
+            final var bytesRef = new BytesRef(utfBytes.bytes(), utfBytes.offset(), utfBytes.length());
+            context.doc().add(new StoredField(fieldType().storedFieldNameForSyntheticSource(), bytesRef));
         }
     }
 
@@ -474,7 +477,7 @@ protected SyntheticSourceSupport syntheticSourceSupport() {
             () -> new StringStoredFieldFieldLoader(fieldType().storedFieldNameForSyntheticSource(), fieldType().name(), leafName()) {
                 @Override
                 protected void write(XContentBuilder b, Object value) throws IOException {
-                    b.value((String) value);
+                    b.value(((BytesRef) value).utf8ToString());
                 }
             }
         );

modules/mapper-extras/src/main/java/org/elasticsearch/index/mapper/extras/SourceConfirmedTextQuery.java

@@ -41,6 +41,7 @@
 import org.apache.lucene.search.Weight;
 import org.apache.lucene.search.similarities.Similarity;
 import org.apache.lucene.search.similarities.Similarity.SimScorer;
+import org.apache.lucene.util.BytesRef;
 import org.apache.lucene.util.IOFunction;
 import org.elasticsearch.common.CheckedIntFunction;
 import org.elasticsearch.common.lucene.search.MultiPhrasePrefixQuery;
@@ -438,7 +439,13 @@ private MemoryIndex getOrCreateMemoryIndex() throws IOException {
                     if (value == null) {
                         continue;
                     }
-                    cacheEntry.memoryIndex.addField(field, value.toString(), indexAnalyzer);
+                    String valueStr;
+                    if (value instanceof BytesRef valueRef) {
+                        valueStr = valueRef.utf8ToString();
+                    } else {
+                        valueStr = value.toString();
+                    }
+                    cacheEntry.memoryIndex.addField(field, valueStr, indexAnalyzer);
                 }
             }
             return cacheEntry.memoryIndex;

modules/mapper-extras/src/test/java/org/elasticsearch/index/mapper/extras/MatchOnlyTextFieldMapperTests.java

@@ -123,7 +123,12 @@ public void testDefaults() throws IOException {
         ParsedDocument doc = mapper.parse(source(b -> b.field("field", "1234")));
         List<IndexableField> fields = doc.rootDoc().getFields("field");
         assertEquals(1, fields.size());
-        assertEquals("1234", fields.get(0).stringValue());
+
+        var reader = fields.get(0).readerValue();
+        char[] buff = new char[20];
+        assertEquals(4, reader.read(buff));
+        assertEquals("1234", new String(buff, 0, 4));
+
         IndexableFieldType fieldType = fields.get(0).fieldType();
         assertThat(fieldType.omitNorms(), equalTo(true));
         assertTrue(fieldType.tokenized());

server/src/main/java/org/elasticsearch/TransportVersions.java

@@ -196,6 +196,7 @@ static TransportVersion def(int id) {
     public static final TransportVersion ML_INFERENCE_ELASTIC_RERANK_ADDED_8_19 = def(8_841_0_48);
     public static final TransportVersion NONE_CHUNKING_STRATEGY_8_19 = def(8_841_0_49);
     public static final TransportVersion IDP_CUSTOM_SAML_ATTRIBUTES_ALLOW_LIST_8_19 = def(8_841_0_50);
+    public static final TransportVersion SETTINGS_IN_DATA_STREAMS_8_19 = def(8_841_0_51);
     public static final TransportVersion V_9_0_0 = def(9_000_0_09);
     public static final TransportVersion INITIAL_ELASTICSEARCH_9_0_1 = def(9_000_0_10);
     public static final TransportVersion INITIAL_ELASTICSEARCH_9_0_2 = def(9_000_0_11);

server/src/main/java/org/elasticsearch/action/datastreams/UpdateDataStreamSettingsAction.java

@@ -83,7 +83,8 @@ public Request(StreamInput in) throws IOException {
             super(in);
             this.dataStreamNames = in.readStringArray();
             this.settings = Settings.readSettingsFromStream(in);
-            if (in.getTransportVersion().onOrAfter(TransportVersions.SETTINGS_IN_DATA_STREAMS)) {
+            if (in.getTransportVersion().onOrAfter(TransportVersions.SETTINGS_IN_DATA_STREAMS_DRY_RUN)
+                || in.getTransportVersion().isPatchFrom(TransportVersions.SETTINGS_IN_DATA_STREAMS_8_19)) {
                 this.dryRun = in.readBoolean();
             } else {
                 this.dryRun = false;
@@ -95,7 +96,8 @@ public void writeTo(StreamOutput out) throws IOException {
             super.writeTo(out);
             out.writeStringArray(dataStreamNames);
             settings.writeTo(out);
-            if (out.getTransportVersion().onOrAfter(TransportVersions.SETTINGS_IN_DATA_STREAMS_DRY_RUN)) {
+            if (out.getTransportVersion().onOrAfter(TransportVersions.SETTINGS_IN_DATA_STREAMS_DRY_RUN)
+                || out.getTransportVersion().isPatchFrom(TransportVersions.SETTINGS_IN_DATA_STREAMS_8_19)) {
                 out.writeBoolean(dryRun);
             }
         }

server/src/main/java/org/elasticsearch/cluster/metadata/DataStream.java

@@ -280,7 +280,8 @@ public static DataStream read(StreamInput in) throws IOException {
             dataStreamOptions = failureStoreEnabled ? DataStreamOptions.FAILURE_STORE_ENABLED : null;
         }
         final Settings settings;
-        if (in.getTransportVersion().onOrAfter(TransportVersions.SETTINGS_IN_DATA_STREAMS)) {
+        if (in.getTransportVersion().onOrAfter(TransportVersions.SETTINGS_IN_DATA_STREAMS)
+            || in.getTransportVersion().isPatchFrom(TransportVersions.SETTINGS_IN_DATA_STREAMS_8_19)) {
             settings = Settings.readSettingsFromStream(in);
         } else {
             settings = Settings.EMPTY;
@@ -1349,7 +1350,8 @@ public void writeTo(StreamOutput out) throws IOException {
         if (out.getTransportVersion().onOrAfter(DataStream.ADD_DATA_STREAM_OPTIONS_VERSION)) {
             out.writeOptionalWriteable(dataStreamOptions.isEmpty() ? null : dataStreamOptions);
         }
-        if (out.getTransportVersion().onOrAfter(TransportVersions.SETTINGS_IN_DATA_STREAMS)) {
+        if (out.getTransportVersion().onOrAfter(TransportVersions.SETTINGS_IN_DATA_STREAMS)
+            || out.getTransportVersion().isPatchFrom(TransportVersions.SETTINGS_IN_DATA_STREAMS_8_19)) {
             settings.writeTo(out);
         }
     }