Add XContentHelper.childBytes() method (#54287)

We have a number of places where we want to read a fairly complex object from
XContent, but aren't interested in its contents; for example, mappings are often
serialized and deserialized between several objects before they are actually built
into a MappingMetaData object. This means that potentially large maps of maps
are constructed several times, only to immediately be re-serialized again.

This commit adds a new helper method to XContentHelper that reads the children
of an xcontent object directly to a BytesReference, serialized via the same xcontenttype
as the parent parser, avoiding the construction of intermediary maps or lists.

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

@@ -383,4 +383,23 @@ public class XContentHelper {
         BytesRef br = bytes.toBytesRef();
         return XContentFactory.xContentType(br.bytes, br.offset, br.length);
     }
+
+    /**
+     * Returns the contents of an object as an unparsed BytesReference
+     *
+     * This is useful for things like mappings where we're copying bytes around but don't
+     * actually need to parse their contents, and so avoids building large maps of maps
+     * unnecessarily
+     */
+    public static BytesReference childBytes(XContentParser parser) throws IOException {
+        if (parser.currentToken() != XContentParser.Token.START_OBJECT) {
+            if (parser.nextToken() != XContentParser.Token.START_OBJECT) {
+                throw new XContentParseException(parser.getTokenLocation(),
+                    "Expected [START_OBJECT] but got [" + parser.currentToken() + "]");
+            }
+        }
+        XContentBuilder builder = XContentBuilder.builder(parser.contentType().xContent());
+        builder.copyCurrentStructure(parser);
+        return BytesReference.bytes(builder);
+    }
 }

server/src/test/java/org/elasticsearch/common/xcontent/support/XContentHelperTests.java

@@ -20,10 +20,12 @@
 package org.elasticsearch.common.xcontent.support;
 
 import org.elasticsearch.common.bytes.BytesReference;
+import org.elasticsearch.common.compress.CompressedXContent;
 import org.elasticsearch.common.xcontent.DeprecationHandler;
 import org.elasticsearch.common.xcontent.NamedXContentRegistry;
 import org.elasticsearch.common.xcontent.ToXContent;
 import org.elasticsearch.common.xcontent.ToXContentObject;
+import org.elasticsearch.common.xcontent.XContentBuilder;
 import org.elasticsearch.common.xcontent.XContentHelper;
 import org.elasticsearch.common.xcontent.XContentParser;
 import org.elasticsearch.common.xcontent.XContentType;
@@ -105,4 +107,127 @@ public class XContentHelperTests extends ESTestCase {
             }
         }
     }
+
+    public void testChildBytes() throws IOException {
+
+        for (XContentType xContentType : XContentType.values()) {
+
+            XContentBuilder builder = XContentBuilder.builder(xContentType.xContent());
+            builder.startObject().startObject("level1");
+            builder.startObject("level2")
+                .startObject("object").field("text", "string").field("number", 10).endObject()
+                .startObject("object2").field("boolean", true).nullField("null")
+                .startArray("array_of_strings").value("string1").value("string2").endArray().endObject().endObject();
+            builder.field("field", "value");
+            builder.endObject().endObject();
+            BytesReference input = BytesReference.bytes(builder);
+
+            BytesReference bytes;
+            try (XContentParser parser = xContentType.xContent()
+                .createParser(NamedXContentRegistry.EMPTY, DeprecationHandler.THROW_UNSUPPORTED_OPERATION, input.streamInput())) {
+
+                assertEquals(XContentParser.Token.START_OBJECT, parser.nextToken());
+                assertEquals(XContentParser.Token.FIELD_NAME, parser.nextToken());
+                assertEquals(XContentParser.Token.START_OBJECT, parser.nextToken());
+                assertEquals(XContentParser.Token.FIELD_NAME, parser.nextToken());
+                assertEquals("level2", parser.currentName());
+                // Extract everything under 'level2' as a bytestream
+                bytes = XContentHelper.childBytes(parser);
+                assertEquals(XContentParser.Token.FIELD_NAME, parser.nextToken());
+                assertEquals("field", parser.currentName());
+            }
+
+            // now parse the contents of 'level2'
+            try (XContentParser parser = xContentType.xContent()
+                .createParser(NamedXContentRegistry.EMPTY, DeprecationHandler.THROW_UNSUPPORTED_OPERATION, bytes.streamInput())) {
+                assertEquals(XContentParser.Token.START_OBJECT, parser.nextToken());
+                assertEquals(XContentParser.Token.FIELD_NAME, parser.nextToken());
+                assertEquals("object", parser.currentName());
+                assertEquals(XContentParser.Token.START_OBJECT, parser.nextToken());
+                assertEquals(XContentParser.Token.FIELD_NAME, parser.nextToken());
+                assertEquals("text", parser.currentName());
+                assertEquals(XContentParser.Token.VALUE_STRING, parser.nextToken());
+                assertEquals("string", parser.text());
+                assertEquals(XContentParser.Token.FIELD_NAME, parser.nextToken());
+                assertEquals("number", parser.currentName());
+                assertEquals(XContentParser.Token.VALUE_NUMBER, parser.nextToken());
+                assertEquals(10, parser.numberValue());
+                assertEquals(XContentParser.Token.END_OBJECT, parser.nextToken());
+                assertEquals(XContentParser.Token.FIELD_NAME, parser.nextToken());
+                assertEquals("object2", parser.currentName());
+                assertEquals(XContentParser.Token.START_OBJECT, parser.nextToken());
+                assertEquals(XContentParser.Token.FIELD_NAME, parser.nextToken());
+                assertEquals("boolean", parser.currentName());
+                assertEquals(XContentParser.Token.VALUE_BOOLEAN, parser.nextToken());
+                assertTrue(parser.booleanValue());
+                assertEquals(XContentParser.Token.FIELD_NAME, parser.nextToken());
+                assertEquals("null", parser.currentName());
+                assertEquals(XContentParser.Token.VALUE_NULL, parser.nextToken());
+                assertEquals(XContentParser.Token.FIELD_NAME, parser.nextToken());
+                assertEquals("array_of_strings", parser.currentName());
+                assertEquals(XContentParser.Token.START_ARRAY, parser.nextToken());
+                assertEquals(XContentParser.Token.VALUE_STRING, parser.nextToken());
+                assertEquals("string1", parser.text());
+                assertEquals(XContentParser.Token.VALUE_STRING, parser.nextToken());
+                assertEquals("string2", parser.text());
+                assertEquals(XContentParser.Token.END_ARRAY, parser.nextToken());
+                assertEquals(XContentParser.Token.END_OBJECT, parser.nextToken());
+                assertEquals(XContentParser.Token.END_OBJECT, parser.nextToken());
+                assertNull(parser.nextToken());
+            }
+
+        }
+    }
+
+    public void testEmbeddedObject() throws IOException {
+        // Need to test this separately as XContentType.JSON never produces VALUE_EMBEDDED_OBJECT
+        XContentBuilder builder = XContentBuilder.builder(XContentType.CBOR.xContent());
+        builder.startObject().startObject("root");
+        CompressedXContent embedded = new CompressedXContent("{\"field\":\"value\"}");
+        builder.field("bytes", embedded.compressed());
+        builder.endObject().endObject();
+        BytesReference bytes = BytesReference.bytes(builder);
+
+        BytesReference inner;
+        try (XContentParser parser = XContentType.CBOR.xContent().createParser(
+            NamedXContentRegistry.EMPTY, DeprecationHandler.THROW_UNSUPPORTED_OPERATION, bytes.streamInput())) {
+
+            assertEquals(XContentParser.Token.START_OBJECT, parser.nextToken());
+            assertEquals(XContentParser.Token.FIELD_NAME, parser.nextToken());
+            inner = XContentHelper.childBytes(parser);
+            assertEquals(XContentParser.Token.END_OBJECT, parser.nextToken());
+            assertNull(parser.nextToken());
+        }
+
+        try (XContentParser parser = XContentType.CBOR.xContent().createParser(
+            NamedXContentRegistry.EMPTY, DeprecationHandler.THROW_UNSUPPORTED_OPERATION, inner.streamInput())) {
+
+            assertEquals(XContentParser.Token.START_OBJECT, parser.nextToken());
+            assertEquals(XContentParser.Token.FIELD_NAME, parser.nextToken());
+            assertEquals("bytes", parser.currentName());
+            assertEquals(XContentParser.Token.VALUE_EMBEDDED_OBJECT, parser.nextToken());
+            assertEquals(embedded, new CompressedXContent(parser.binaryValue()));
+            assertEquals(XContentParser.Token.END_OBJECT, parser.nextToken());
+            assertNull(parser.nextToken());
+
+        }
+    }
+
+    public void testEmptyChildBytes() throws IOException {
+
+        String inputJson = "{ \"mappings\" : {} }";
+        try (XContentParser parser = XContentType.JSON.xContent()
+            .createParser(NamedXContentRegistry.EMPTY, DeprecationHandler.THROW_UNSUPPORTED_OPERATION, inputJson)) {
+
+            assertEquals(XContentParser.Token.START_OBJECT, parser.nextToken());
+            assertEquals(XContentParser.Token.FIELD_NAME, parser.nextToken());
+            BytesReference bytes = XContentHelper.childBytes(parser);
+            assertEquals(XContentParser.Token.END_OBJECT, parser.nextToken());
+            assertNull(parser.nextToken());
+
+            assertEquals("{}", bytes.utf8ToString());
+
+        }
+
+    }
 }