Merge branch 'main' into mw-synthetic

Author: marciw

distribution/docker/src/docker/dockerfiles/default/Dockerfile

@@ -29,23 +29,20 @@ RUN microdnf install -y findutils tar gzip
 # The tini GitHub page gives instructions for verifying the binary using
 # gpg, but the keyservers are slow to return the key and this can fail the
 # build. Instead, we check the binary against the published checksum.
-RUN set -eux ; \\
-    tini_bin="" ; \\
-    arch="\$(rpm --query --queryformat='%{ARCH}' rpm)"; \
-    case "\$(arch)" in \\
-        aarch64) tini_bin='tini-arm64' ;; \\
-        x86_64)  tini_bin='tini-amd64' ;; \\
-        *) echo >&2 ; echo >&2 "Unsupported architecture \$arch" ; echo >&2 ; exit 1 ;; \\
+RUN set -eux; \\
+    arch="\$(rpm --query --queryformat='%{ARCH}' rpm)"; \\
+    case "\$arch" in \\
+        aarch64) tini_bin='tini-arm64'; tini_sum='07952557df20bfd2a95f9bef198b445e006171969499a1d361bd9e6f8e5e0e81' ;; \\
+        x86_64)  tini_bin='tini-amd64'; tini_sum='93dcc18adc78c65a028a84799ecf8ad40c936fdfc5f2a57b1acda5a8117fa82c' ;; \\
+        *) echo >&2 "Unsupported architecture \$arch"; exit 1 ;; \\
     esac ; \\
-    curl -f --retry 10 -S -L -O https://github.com/krallin/tini/releases/download/v0.19.0/\${tini_bin} ; \\
-    curl -f --retry 10 -S -L -O https://github.com/krallin/tini/releases/download/v0.19.0/\${tini_bin}.sha256sum ; \\
-    sha256sum -c \${tini_bin}.sha256sum ; \\
-    rm \${tini_bin}.sha256sum ; \\
-    mv \${tini_bin} /bin/tini ; \\
+    curl -f --retry 10 -S -L -o /tmp/tini https://github.com/krallin/tini/releases/download/v0.19.0/\${tini_bin}; \\
+    echo "\${tini_sum}  /tmp/tini" | sha256sum -c -; \\
+    mv /tmp/tini /bin/tini; \\
     chmod 0555 /bin/tini
 
 WORKDIR /usr/share/elasticsearch
-RUN arch="\$(rpm --query --queryformat='%{ARCH}' rpm)" && curl -f --retry 10 -S -L --output /tmp/elasticsearch.tar.gz https://artifacts-no-kpi.elastic.co/downloads/elasticsearch/elasticsearch-${version}-linux-\$(arch).tar.gz
+RUN arch="\$(rpm --query --queryformat='%{ARCH}' rpm)" && curl -f --retry 10 -S -L --output /tmp/elasticsearch.tar.gz https://artifacts-no-kpi.elastic.co/downloads/elasticsearch/elasticsearch-${version}-linux-\$arch.tar.gz
 RUN tar -zxf /tmp/elasticsearch.tar.gz --strip-components=1 && \\
 # Configure the distribution for Docker
     sed -i -e 's/ES_DISTRIBUTION_TYPE=tar/ES_DISTRIBUTION_TYPE=docker/' bin/elasticsearch-env && \\
@@ -111,12 +108,10 @@ ENV SHELL=/bin/bash
 COPY --chmod=0555 bin/docker-entrypoint.sh /usr/local/bin/docker-entrypoint.sh
 
 RUN chmod g=u /etc/passwd && \\
-    chmod 0555 /usr/local/bin/docker-entrypoint.sh && \\
     find / -xdev -perm -4000 -exec chmod ug-s {} + && \\
     chmod 0775 /usr/share/elasticsearch && \\
     chown elasticsearch bin config config/jvm.options.d data logs plugins
 
-
 EXPOSE 9200 9300
 
 LABEL org.label-schema.build-date="${build_date}" \\

docs/changelog/127962.yaml

@@ -0,0 +1,6 @@
+pr: 127962
+summary: Support DATE_NANOS in LOOKUP JOIN
+area: ES|QL
+type: bug
+issues:
+ - 127249

docs/changelog/128538.yaml

@@ -0,0 +1,5 @@
+pr: 128538
+summary: "Added Mistral Chat Completion support to the Inference Plugin"
+area: Machine Learning
+type: enhancement
+issues: []

docs/changelog/128788.yaml

@@ -0,0 +1,6 @@
+pr: 105773
+summary: Inject an unfollow action before executing a downsample action in ILM
+area: ILM+SLM
+type: bug
+issues:
+ - 105773

docs/changelog/128858.yaml

@@ -0,0 +1,6 @@
+pr: 128858
+summary: Fix unsupported privileges error message during role and API key crea…
+area: Authorization
+type: enhancement
+issues:
+ - 128132

server/src/main/java/org/elasticsearch/common/text/Text.java renamed to libs/x-content/src/main/java/org/elasticsearch/xcontent/Text.java

@@ -6,22 +6,17 @@
  * 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.common.text;
-
-import org.apache.lucene.util.BytesRef;
-import org.elasticsearch.common.bytes.BytesArray;
-import org.elasticsearch.common.bytes.BytesReference;
-import org.elasticsearch.xcontent.ToXContentFragment;
-import org.elasticsearch.xcontent.XContentBuilder;
+package org.elasticsearch.xcontent;
 
 import java.io.IOException;
+import java.nio.ByteBuffer;
 import java.nio.charset.StandardCharsets;
 
 /**
- * Both {@link String} and {@link BytesReference} representation of the text. Starts with one of those, and if
- * the other is requests, caches the other one in a local reference so no additional conversion will be needed.
+ * Both {@link String} and {@link UTF8Bytes} representation of the text. Starts with one of those, and if
+ * the other is requested, caches the other one in a local reference so no additional conversion will be needed.
  */
-public final class Text implements Comparable<Text>, ToXContentFragment {
+public final class Text implements XContentString, Comparable<Text>, ToXContentFragment {
 
     public static final Text[] EMPTY_ARRAY = new Text[0];
 
@@ -36,31 +31,46 @@ public static Text[] convertFromStringArray(String[] strings) {
         return texts;
     }
 
-    private BytesReference bytes;
-    private String text;
+    private UTF8Bytes bytes;
+    private String string;
     private int hash;
+    private int stringLength = -1;
+
+    /**
+     * Construct a Text from encoded UTF8Bytes. Since no string length is specified, {@link #stringLength()}
+     * will perform a string conversion to measure the string length.
+     */
+    public Text(UTF8Bytes bytes) {
+        this.bytes = bytes;
+    }
 
-    public Text(BytesReference bytes) {
+    /**
+     * Construct a Text from encoded UTF8Bytes and an explicit string length. Used to avoid string conversion
+     * in {@link #stringLength()}. The provided stringLength should match the value that would
+     * be calculated by {@link Text#Text(UTF8Bytes)}.
+     */
+    public Text(UTF8Bytes bytes, int stringLength) {
         this.bytes = bytes;
+        this.stringLength = stringLength;
     }
 
-    public Text(String text) {
-        this.text = text;
+    public Text(String string) {
+        this.string = string;
     }
 
     /**
-     * Whether a {@link BytesReference} view of the data is already materialized.
+     * Whether an {@link UTF8Bytes} view of the data is already materialized.
      */
     public boolean hasBytes() {
         return bytes != null;
     }
 
-    /**
-     * Returns a {@link BytesReference} view of the data.
-     */
-    public BytesReference bytes() {
+    @Override
+    public UTF8Bytes bytes() {
         if (bytes == null) {
-            bytes = new BytesArray(text.getBytes(StandardCharsets.UTF_8));
+            var byteBuff = StandardCharsets.UTF_8.encode(string);
+            assert byteBuff.hasArray();
+            bytes = new UTF8Bytes(byteBuff.array(), byteBuff.arrayOffset() + byteBuff.position(), byteBuff.remaining());
         }
         return bytes;
     }
@@ -69,14 +79,25 @@ public BytesReference bytes() {
      * Whether a {@link String} view of the data is already materialized.
      */
     public boolean hasString() {
-        return text != null;
+        return string != null;
     }
 
-    /**
-     * Returns a {@link String} view of the data.
-     */
+    @Override
     public String string() {
-        return text == null ? bytes.utf8ToString() : text;
+        if (string == null) {
+            var byteBuff = ByteBuffer.wrap(bytes.bytes(), bytes.offset(), bytes.length());
+            string = StandardCharsets.UTF_8.decode(byteBuff).toString();
+            assert (stringLength < 0) || (string.length() == stringLength);
+        }
+        return string;
+    }
+
+    @Override
+    public int stringLength() {
+        if (stringLength < 0) {
+            stringLength = string().length();
+        }
+        return stringLength;
     }
 
     @Override
@@ -115,8 +136,7 @@ public XContentBuilder toXContent(XContentBuilder builder, Params params) throws
         } else {
             // TODO: TextBytesOptimization we can use a buffer here to convert it? maybe add a
             // request to jackson to support InputStream as well?
-            BytesRef br = this.bytes().toBytesRef();
-            return builder.utf8Value(br.bytes, br.offset, br.length);
+            return builder.utf8Value(bytes.bytes(), bytes.offset(), bytes.length());
         }
     }
 }

libs/x-content/src/main/java/org/elasticsearch/xcontent/XContentString.java

@@ -0,0 +1,61 @@
+/*
+ * 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.xcontent;
+
+import java.nio.ByteBuffer;
+
+public interface XContentString {
+    record UTF8Bytes(byte[] bytes, int offset, int length) implements Comparable<UTF8Bytes> {
+        public UTF8Bytes(byte[] bytes) {
+            this(bytes, 0, bytes.length);
+        }
+
+        @Override
+        public int compareTo(UTF8Bytes o) {
+            if (this.bytes == o.bytes && this.offset == o.offset && this.length == o.length) {
+                return 0;
+            }
+
+            return ByteBuffer.wrap(bytes, offset, length).compareTo(ByteBuffer.wrap(o.bytes, o.offset, o.length));
+        }
+
+        @Override
+        public boolean equals(Object o) {
+            if (this == o) {
+                return true;
+            }
+            if (o == null || getClass() != o.getClass()) {
+                return false;
+            }
+
+            return this.compareTo((UTF8Bytes) o) == 0;
+        }
+
+        @Override
+        public int hashCode() {
+            return ByteBuffer.wrap(bytes, offset, length).hashCode();
+        }
+    }
+
+    /**
+     * Returns a {@link String} view of the data.
+     */
+    String string();
+
+    /**
+     * Returns an encoded {@link UTF8Bytes} view of the data.
+     */
+    UTF8Bytes bytes();
+
+    /**
+     * Returns the number of characters in the represented string.
+     */
+    int stringLength();
+}