Remove BytesArray and BytesReference usage from XContentFactory (#29151)

* Remove BytesArray and BytesReference usage from XContentFactory

This removes the usage of `BytesArray` and `BytesReference` from
`XContentFactory`. Instead, a regular `byte[]` should be passed. To assist with
this a helper has been added to `XContentHelper` that will preserve the offset
and length from the underlying BytesReference.

This is part of ongoing work to separate the XContent parts from ES so they can
be factored into their own jar.

Relates to #28504

modules/percolator/src/main/java/org/elasticsearch/percolator/PercolateQueryBuilder.java

@@ -133,7 +133,7 @@ public class PercolateQueryBuilder extends AbstractQueryBuilder<PercolateQueryBu
      */
     @Deprecated
     public PercolateQueryBuilder(String field, String documentType, BytesReference document) {
-        this(field, documentType, Collections.singletonList(document), XContentFactory.xContentType(document));
+        this(field, documentType, Collections.singletonList(document), XContentHelper.xContentType(document));
     }
 
     /**
@@ -276,7 +276,7 @@ public PercolateQueryBuilder(String field, String documentType, String indexedDo
             if (in.getVersion().onOrAfter(Version.V_5_3_0)) {
                 documentXContentType = in.readEnum(XContentType.class);
             } else {
-                documentXContentType = XContentFactory.xContentType(documents.iterator().next());
+                documentXContentType = XContentHelper.xContentType(documents.iterator().next());
             }
         } else {
             documentXContentType = null;
@@ -525,7 +525,7 @@ protected QueryBuilder doRewrite(QueryRewriteContext queryShardContext) {
                 return this; // not executed yet
             } else {
                 return new PercolateQueryBuilder(field, documentType, Collections.singletonList(source),
-                    XContentFactory.xContentType(source));
+                    XContentHelper.xContentType(source));
             }
         }
         GetRequest getRequest = new GetRequest(indexedDocumentIndex, indexedDocumentType, indexedDocumentId);

server/src/main/java/org/elasticsearch/action/admin/cluster/storedscripts/PutStoredScriptRequest.java

@@ -125,7 +125,7 @@ public void readFrom(StreamInput in) throws IOException {
         if (in.getVersion().onOrAfter(Version.V_5_3_0)) {
             xContentType = in.readEnum(XContentType.class);
         } else {
-            xContentType = XContentFactory.xContentType(content);
+            xContentType = XContentHelper.xContentType(content);
         }
         if (in.getVersion().onOrAfter(Version.V_6_0_0_alpha2)) {
             context = in.readOptionalString();

server/src/main/java/org/elasticsearch/action/ingest/PutPipelineRequest.java

@@ -25,7 +25,7 @@
 import org.elasticsearch.common.bytes.BytesReference;
 import org.elasticsearch.common.io.stream.StreamInput;
 import org.elasticsearch.common.io.stream.StreamOutput;
-import org.elasticsearch.common.xcontent.XContentFactory;
+import org.elasticsearch.common.xcontent.XContentHelper;
 import org.elasticsearch.common.xcontent.XContentType;
 
 import java.io.IOException;
@@ -43,7 +43,7 @@ public class PutPipelineRequest extends AcknowledgedRequest<PutPipelineRequest>
      */
     @Deprecated
     public PutPipelineRequest(String id, BytesReference source) {
-        this(id, source, XContentFactory.xContentType(source));
+        this(id, source, XContentHelper.xContentType(source));
     }
 
     /**
@@ -83,7 +83,7 @@ public void readFrom(StreamInput in) throws IOException {
         if (in.getVersion().onOrAfter(Version.V_5_3_0)) {
             xContentType = in.readEnum(XContentType.class);
         } else {
-            xContentType = XContentFactory.xContentType(source);
+            xContentType = XContentHelper.xContentType(source);
         }
     }
 

server/src/main/java/org/elasticsearch/action/ingest/SimulatePipelineRequest.java

@@ -25,8 +25,7 @@
 import org.elasticsearch.common.bytes.BytesReference;
 import org.elasticsearch.common.io.stream.StreamInput;
 import org.elasticsearch.common.io.stream.StreamOutput;
-import org.elasticsearch.common.io.stream.Writeable;
-import org.elasticsearch.common.xcontent.XContentFactory;
+import org.elasticsearch.common.xcontent.XContentHelper;
 import org.elasticsearch.common.xcontent.XContentType;
 import org.elasticsearch.index.VersionType;
 import org.elasticsearch.ingest.ConfigurationUtils;
@@ -56,7 +55,7 @@ public class SimulatePipelineRequest extends ActionRequest {
      */
     @Deprecated
     public SimulatePipelineRequest(BytesReference source) {
-        this(source, XContentFactory.xContentType(source));
+        this(source, XContentHelper.xContentType(source));
     }
 
     /**
@@ -78,7 +77,7 @@ public SimulatePipelineRequest(BytesReference source, XContentType xContentType)
         if (in.getVersion().onOrAfter(Version.V_5_3_0)) {
             xContentType = in.readEnum(XContentType.class);
         } else {
-            xContentType = XContentFactory.xContentType(source);
+            xContentType = XContentHelper.xContentType(source);
         }
     }
 

server/src/main/java/org/elasticsearch/action/termvectors/TermVectorsRequest.java

@@ -35,7 +35,7 @@
 import org.elasticsearch.common.lucene.uid.Versions;
 import org.elasticsearch.common.util.set.Sets;
 import org.elasticsearch.common.xcontent.XContentBuilder;
-import org.elasticsearch.common.xcontent.XContentFactory;
+import org.elasticsearch.common.xcontent.XContentHelper;
 import org.elasticsearch.common.xcontent.XContentParser;
 import org.elasticsearch.common.xcontent.XContentType;
 import org.elasticsearch.index.VersionType;
@@ -265,7 +265,7 @@ public TermVectorsRequest doc(XContentBuilder documentBuilder) {
      */
     @Deprecated
     public TermVectorsRequest doc(BytesReference doc, boolean generateRandomId) {
-        return this.doc(doc, generateRandomId, XContentFactory.xContentType(doc));
+        return this.doc(doc, generateRandomId, XContentHelper.xContentType(doc));
     }
 
     /**
@@ -518,7 +518,7 @@ public void readFrom(StreamInput in) throws IOException {
             if (in.getVersion().onOrAfter(Version.V_5_3_0)) {
                 xContentType = in.readEnum(XContentType.class);
             } else {
-                xContentType = XContentFactory.xContentType(doc);
+                xContentType = XContentHelper.xContentType(doc);
             }
         }
         routing = in.readOptionalString();

server/src/main/java/org/elasticsearch/common/compress/CompressorFactory.java

@@ -24,7 +24,7 @@
 import org.elasticsearch.common.io.Streams;
 import org.elasticsearch.common.io.stream.BytesStreamOutput;
 import org.elasticsearch.common.io.stream.StreamInput;
-import org.elasticsearch.common.xcontent.XContentFactory;
+import org.elasticsearch.common.xcontent.XContentHelper;
 import org.elasticsearch.common.xcontent.XContentType;
 
 import java.io.IOException;
@@ -44,11 +44,11 @@ public static Compressor compressor(BytesReference bytes) {
                 // bytes should be either detected as compressed or as xcontent,
                 // if we have bytes that can be either detected as compressed or
                 // as a xcontent, we have a problem
-                assert XContentFactory.xContentType(bytes) == null;
+                assert XContentHelper.xContentType(bytes) == null;
                 return COMPRESSOR;
             }
 
-        XContentType contentType = XContentFactory.xContentType(bytes);
+        XContentType contentType = XContentHelper.xContentType(bytes);
         if (contentType == null) {
             if (isAncient(bytes)) {
                 throw new IllegalStateException("unsupported compression: index was created before v2.0.0.beta1 and wasn't upgraded?");

server/src/main/java/org/elasticsearch/common/xcontent/XContentFactory.java

@@ -22,9 +22,6 @@
 import com.fasterxml.jackson.dataformat.cbor.CBORConstants;
 import com.fasterxml.jackson.dataformat.smile.SmileConstants;
 import org.elasticsearch.ElasticsearchParseException;
-import org.elasticsearch.common.bytes.BytesArray;
-import org.elasticsearch.common.bytes.BytesReference;
-import org.elasticsearch.common.io.Streams;
 import org.elasticsearch.common.xcontent.cbor.CborXContent;
 import org.elasticsearch.common.xcontent.json.JsonXContent;
 import org.elasticsearch.common.xcontent.smile.SmileXContent;
@@ -221,18 +218,6 @@ public static XContent xContent(byte[] data, int offset, int length) {
         return xContent(type);
     }
 
-    /**
-     * Guesses the content type based on the provided bytes.
-     *
-     * @deprecated the content type should not be guessed except for few cases where we effectively don't know the content type.
-     * The REST layer should move to reading the Content-Type header instead. There are other places where auto-detection may be needed.
-     * This method is deprecated to prevent usages of it from spreading further without specific reasons.
-     */
-    @Deprecated
-    public static XContentType xContentType(byte[] data) {
-        return xContentType(data, 0, data.length);
-    }
-
     /**
      * Guesses the content type based on the provided input stream without consuming it.
      *
@@ -248,8 +233,15 @@ public static XContentType xContentType(InputStream si) throws IOException {
         si.mark(GUESS_HEADER_LENGTH);
         try {
             final byte[] firstBytes = new byte[GUESS_HEADER_LENGTH];
-            final int read = Streams.readFully(si, firstBytes);
-            return xContentType(new BytesArray(firstBytes, 0, read));
+            int read = 0;
+            while (read < GUESS_HEADER_LENGTH) {
+                final int r = si.read(firstBytes, read, GUESS_HEADER_LENGTH - read);
+                if (r == -1) {
+                    break;
+                }
+                read += r;
+            }
+            return xContentType(firstBytes, 0, read);
         } finally {
             si.reset();
         }
@@ -263,24 +255,8 @@ public static XContentType xContentType(InputStream si) throws IOException {
      * This method is deprecated to prevent usages of it from spreading further without specific reasons.
      */
     @Deprecated
-    public static XContentType xContentType(byte[] data, int offset, int length) {
-        return xContentType(new BytesArray(data, offset, length));
-    }
-
-    /**
-     * Guesses the content type based on the provided bytes and returns the corresponding {@link XContent}
-     *
-     * @deprecated the content type should not be guessed except for few cases where we effectively don't know the content type.
-     * The REST layer should move to reading the Content-Type header instead. There are other places where auto-detection may be needed.
-     * This method is deprecated to prevent usages of it from spreading further without specific reasons.
-     */
-    @Deprecated
-    public static XContent xContent(BytesReference bytes) {
-        XContentType type = xContentType(bytes);
-        if (type == null) {
-            throw new ElasticsearchParseException("Failed to derive xcontent");
-        }
-        return xContent(type);
+    public static XContentType xContentType(byte[] bytes) {
+        return xContentType(bytes, 0, bytes.length);
     }
 
     /**
@@ -291,19 +267,21 @@ public static XContent xContent(BytesReference bytes) {
      * This method is deprecated to prevent usages of it from spreading further without specific reasons.
      */
     @Deprecated
-    public static XContentType xContentType(BytesReference bytes) {
-        int length = bytes.length();
-        if (length == 0) {
+    public static XContentType xContentType(byte[] bytes, int offset, int length) {
+        int totalLength = bytes.length;
+        if (totalLength == 0 || length == 0) {
+            return null;
+        } else if ((offset + length) > totalLength) {
             return null;
         }
-        byte first = bytes.get(0);
+        byte first = bytes[offset];
         if (first == '{') {
             return XContentType.JSON;
         }
-        if (length > 2 && first == SmileConstants.HEADER_BYTE_1 && bytes.get(1) == SmileConstants.HEADER_BYTE_2 && bytes.get(2) == SmileConstants.HEADER_BYTE_3) {
+        if (length > 2 && first == SmileConstants.HEADER_BYTE_1 && bytes[offset + 1] == SmileConstants.HEADER_BYTE_2 && bytes[offset + 2] == SmileConstants.HEADER_BYTE_3) {
             return XContentType.SMILE;
         }
-        if (length > 2 && first == '-' && bytes.get(1) == '-' && bytes.get(2) == '-') {
+        if (length > 2 && first == '-' && bytes[offset + 1] == '-' && bytes[offset + 2] == '-') {
             return XContentType.YAML;
         }
         // CBOR logic similar to CBORFactory#hasCBORFormat
@@ -312,7 +290,7 @@ public static XContentType xContentType(BytesReference bytes) {
         }
         if (CBORConstants.hasMajorType(CBORConstants.MAJOR_TYPE_TAG, first) && length > 2) {
             // Actually, specific "self-describe tag" is a very good indicator
-            if (first == (byte) 0xD9 && bytes.get(1) == (byte) 0xD9 && bytes.get(2) == (byte) 0xF7) {
+            if (first == (byte) 0xD9 && bytes[offset + 1] == (byte) 0xD9 && bytes[offset + 2] == (byte) 0xF7) {
                 return XContentType.CBOR;
             }
         }
@@ -324,13 +302,13 @@ public static XContentType xContentType(BytesReference bytes) {
 
         int jsonStart = 0;
         // JSON may be preceded by UTF-8 BOM
-        if (length > 3 && first == (byte) 0xEF && bytes.get(1) == (byte) 0xBB && bytes.get(2) == (byte) 0xBF) {
+        if (length > 3 && first == (byte) 0xEF && bytes[offset + 1] == (byte) 0xBB && bytes[offset + 2] == (byte) 0xBF) {
             jsonStart = 3;
         }
 
         // a last chance for JSON
         for (int i = jsonStart; i < length; i++) {
-            byte b = bytes.get(i);
+            byte b = bytes[offset + i];
             if (b == '{') {
                 return XContentType.JSON;
             }

server/src/main/java/org/elasticsearch/common/xcontent/XContentHelper.java

@@ -19,6 +19,7 @@
 
 package org.elasticsearch.common.xcontent;
 
+import org.apache.lucene.util.BytesRef;
 import org.elasticsearch.ElasticsearchParseException;
 import org.elasticsearch.common.Strings;
 import org.elasticsearch.common.bytes.BytesReference;
@@ -55,7 +56,7 @@ public static XContentParser createParser(NamedXContentRegistry xContentRegistry
             final XContentType contentType = XContentFactory.xContentType(compressedInput);
             return XContentFactory.xContent(contentType).createParser(xContentRegistry, deprecationHandler, compressedInput);
         } else {
-            return XContentFactory.xContent(bytes).createParser(xContentRegistry, deprecationHandler, bytes.streamInput());
+            return XContentFactory.xContent(xContentType(bytes)).createParser(xContentRegistry, deprecationHandler, bytes.streamInput());
         }
     }
 
@@ -151,7 +152,7 @@ public static String convertToJson(BytesReference bytes, boolean reformatJson) t
 
     @Deprecated
     public static String convertToJson(BytesReference bytes, boolean reformatJson, boolean prettyPrint) throws IOException {
-        return convertToJson(bytes, reformatJson, prettyPrint, XContentFactory.xContentType(bytes));
+        return convertToJson(bytes, reformatJson, prettyPrint, XContentFactory.xContentType(bytes.toBytesRef().bytes));
     }
 
     public static String convertToJson(BytesReference bytes, boolean reformatJson, XContentType xContentType) throws IOException {
@@ -436,4 +437,17 @@ public static BytesReference toXContent(ToXContent toXContent, XContentType xCon
             return BytesReference.bytes(builder);
         }
     }
+
+    /**
+     * Guesses the content type based on the provided bytes.
+     *
+     * @deprecated the content type should not be guessed except for few cases where we effectively don't know the content type.
+     * The REST layer should move to reading the Content-Type header instead. There are other places where auto-detection may be needed.
+     * This method is deprecated to prevent usages of it from spreading further without specific reasons.
+     */
+    @Deprecated
+    public static XContentType xContentType(BytesReference bytes) {
+        BytesRef br = bytes.toBytesRef();
+        return XContentFactory.xContentType(br.bytes, br.offset, br.length);
+    }
 }

server/src/main/java/org/elasticsearch/index/query/MoreLikeThisQueryBuilder.java

@@ -48,6 +48,7 @@
 import org.elasticsearch.common.xcontent.ToXContentObject;
 import org.elasticsearch.common.xcontent.XContentBuilder;
 import org.elasticsearch.common.xcontent.XContentFactory;
+import org.elasticsearch.common.xcontent.XContentHelper;
 import org.elasticsearch.common.xcontent.XContentParser;
 import org.elasticsearch.common.xcontent.XContentType;
 import org.elasticsearch.index.VersionType;
@@ -224,7 +225,7 @@ public Item(@Nullable String index, @Nullable String type, XContentBuilder doc)
                 if (in.getVersion().onOrAfter(Version.V_5_3_0)) {
                     xContentType = in.readEnum(XContentType.class);
                 } else {
-                    xContentType = XContentFactory.xContentType(doc);
+                    xContentType = XContentHelper.xContentType(doc);
                 }
             } else {
                 id = in.readString();

server/src/main/java/org/elasticsearch/index/query/functionscore/DecayFunctionBuilder.java

@@ -38,6 +38,7 @@
 import org.elasticsearch.common.xcontent.NamedXContentRegistry;
 import org.elasticsearch.common.xcontent.XContentBuilder;
 import org.elasticsearch.common.xcontent.XContentFactory;
+import org.elasticsearch.common.xcontent.XContentHelper;
 import org.elasticsearch.common.xcontent.XContentParser;
 import org.elasticsearch.index.fielddata.IndexGeoPointFieldData;
 import org.elasticsearch.index.fielddata.IndexNumericFieldData;
@@ -186,7 +187,7 @@ protected ScoreFunction doToFunction(QueryShardContext context) throws IOExcepti
         AbstractDistanceScoreFunction scoreFunction;
         // EMPTY is safe because parseVariable doesn't use namedObject
         try (InputStream stream = functionBytes.streamInput();
-             XContentParser parser = XContentFactory.xContent(functionBytes)
+             XContentParser parser = XContentFactory.xContent(XContentHelper.xContentType(functionBytes))
                  .createParser(NamedXContentRegistry.EMPTY, LoggingDeprecationHandler.INSTANCE, stream)) {
             scoreFunction = parseVariable(fieldName, parser, context, multiValueMode);
         }

server/src/main/java/org/elasticsearch/index/reindex/ClientScrollableHitSource.java

@@ -38,7 +38,7 @@
 import org.elasticsearch.common.unit.TimeValue;
 import org.elasticsearch.common.util.concurrent.AbstractRunnable;
 import org.elasticsearch.common.util.concurrent.EsRejectedExecutionException;
-import org.elasticsearch.common.xcontent.XContentFactory;
+import org.elasticsearch.common.xcontent.XContentHelper;
 import org.elasticsearch.common.xcontent.XContentType;
 import org.elasticsearch.index.mapper.ParentFieldMapper;
 import org.elasticsearch.index.mapper.RoutingFieldMapper;
@@ -236,7 +236,7 @@ public BytesReference getSource() {
 
         @Override
         public XContentType getXContentType() {
-            return XContentFactory.xContentType(source);
+            return XContentHelper.xContentType(source);
         }
         @Override
         public long getVersion() {

server/src/main/java/org/elasticsearch/index/shard/IndexShard.java

@@ -23,7 +23,6 @@
 import org.apache.logging.log4j.Logger;
 import org.apache.logging.log4j.message.ParameterizedMessage;
 import org.apache.lucene.index.CheckIndex;
-import org.apache.lucene.index.DirectoryReader;
 import org.apache.lucene.index.IndexCommit;
 import org.apache.lucene.index.IndexOptions;
 import org.apache.lucene.index.LeafReaderContext;
@@ -37,7 +36,6 @@
 import org.apache.lucene.search.UsageTrackingQueryCachingPolicy;
 import org.apache.lucene.store.AlreadyClosedException;
 import org.apache.lucene.util.BytesRef;
-import org.elasticsearch.core.internal.io.IOUtils;
 import org.apache.lucene.util.ThreadInterruptedException;
 import org.elasticsearch.Assertions;
 import org.elasticsearch.ElasticsearchException;
@@ -66,7 +64,8 @@
 import org.elasticsearch.common.util.BigArrays;
 import org.elasticsearch.common.util.concurrent.AbstractRunnable;
 import org.elasticsearch.common.util.concurrent.AsyncIOProcessor;
-import org.elasticsearch.common.xcontent.XContentFactory;
+import org.elasticsearch.common.xcontent.XContentHelper;
+import org.elasticsearch.core.internal.io.IOUtils;
 import org.elasticsearch.index.Index;
 import org.elasticsearch.index.IndexModule;
 import org.elasticsearch.index.IndexNotFoundException;
@@ -1238,7 +1237,8 @@ public Engine.Result applyTranslogOperation(Translog.Operation operation, Engine
                 // autoGeneratedID docs that are coming from the primary are updated correctly.
                 result = applyIndexOperation(index.seqNo(), index.primaryTerm(), index.version(),
                     index.versionType().versionTypeForReplicationAndRecovery(), index.getAutoGeneratedIdTimestamp(), true, origin,
-                    source(shardId.getIndexName(), index.type(), index.id(), index.source(), XContentFactory.xContentType(index.source()))
+                    source(shardId.getIndexName(), index.type(), index.id(), index.source(),
+                        XContentHelper.xContentType(index.source()))
                         .routing(index.routing()).parent(index.parent()), onMappingUpdate);
                 break;
             case DELETE: