apache · jnioche · Jul 23, 2026 · Jul 23, 2026
diff --git a/docs/src/main/asciidoc/configuration.adoc b/docs/src/main/asciidoc/configuration.adoc
@@ -517,6 +517,8 @@ NOTE: When using the Tika `ParserBolt` alongside `JSoupParserBolt`, set `jsoup.t
 Integration with AWS services: CloudSearch for indexing and S3 for content caching.
 See the link:https://github.com/apache/stormcrawler/tree/main/external/aws[aws module] for full details.
 
+NOTE: AWS CloudSearch support (the `cloudsearch.*` settings below) is deprecated and will be removed in the next major release of StormCrawler.
+
 [cols="1,1,3", options="header"]
 |===
 | key | default value | description

diff --git a/docs/src/main/asciidoc/internals.adoc b/docs/src/main/asciidoc/internals.adoc
@@ -103,7 +103,7 @@ The purpose of crawlers is often to index web pages to make them searchable. The
 
 * link:https://github.com/apache/stormcrawler/blob/main/external/solr/src/main/java/org/apache/stormcrawler/solr/bolt/IndexerBolt.java[Apache SOLR]
 * link:https://github.com/apache/stormcrawler/blob/main/external/opensearch/src/main/java/org/apache/stormcrawler/opensearch/bolt/IndexerBolt.java[OpenSearch]
-* link:https://github.com/apache/stormcrawler/blob/main/external/aws/src/main/java/org/apache/stormcrawler/aws/bolt/CloudSearchIndexerBolt.java[AWS CloudSearch]
+* link:https://github.com/apache/stormcrawler/blob/main/external/aws/src/main/java/org/apache/stormcrawler/aws/bolt/CloudSearchIndexerBolt.java[AWS CloudSearch] (deprecated, will be removed in the next major release)
 
 All of these extend the class link:https://github.com/apache/stormcrawler/blob/main/core/src/main/java/org/apache/stormcrawler/indexing/AbstractIndexerBolt.java[AbstractIndexerBolt].
 

diff --git a/external/aws/README.md b/external/aws/README.md
@@ -1,7 +1,7 @@
 # stormcrawler-aws
 ================================
 
-AWS resources for StormCrawler, currently contains an indexer bolt for [CloudSearch](https://aws.amazon.com/cloudsearch/) and another bolt for storing and retrieving web pages to/from [S3](https://aws.amazon.com/s3/).
+AWS resources for StormCrawler, currently contains an indexer bolt for [CloudSearch](https://aws.amazon.com/cloudsearch/) (**deprecated**, see below) and another bolt for storing and retrieving web pages to/from [S3](https://aws.amazon.com/s3/).
 
 This module is built on the [AWS SDK for Java 2.x](https://docs.aws.amazon.com/sdk-for-java/latest/developer-guide/home.html). Credentials are resolved through the SDK's [default credentials provider chain](https://docs.aws.amazon.com/sdk-for-java/latest/developer-guide/credentials-chain.html) (environment variables, Java system properties, `~/.aws/credentials`, container/instance profiles, etc.).
 
@@ -21,6 +21,8 @@ Edit `~/.aws/credentials`, see [http://docs.aws.amazon.com/cli/latest/userguide/
 
 ## CloudSearch
 
+> **Deprecated:** AWS CloudSearch support is deprecated and will be removed in the next major release of StormCrawler.
+
 * How to use?
 
 Add stormcrawler-aws as a Maven dependency, use the class CloudSearchIndexWriter in your Storm topology alongside the core StormCrawler components and create a yaml configuration file (see below).

diff --git a/external/aws/aws-conf.yaml b/external/aws/aws-conf.yaml
@@ -17,6 +17,9 @@
 #  CloudSearch Configuration  #
 ###############################
 
+# NOTE: AWS CloudSearch support is deprecated and will be removed
+# in the next major release of StormCrawler.
+
 # max number of docs to keep in buffer
 # before sending to CS irrespective of size limits
 cloudsearch.batch.maxSize: 100

diff --git a/external/aws/src/main/java/org/apache/stormcrawler/aws/bolt/CloudSearchConstants.java b/external/aws/src/main/java/org/apache/stormcrawler/aws/bolt/CloudSearchConstants.java
@@ -17,6 +17,11 @@
 
 package org.apache.stormcrawler.aws.bolt;
 
+/**
+ * @deprecated AWS CloudSearch support is deprecated and will be removed in the next major release
+ *     of StormCrawler.
+ */
+@Deprecated
 public interface CloudSearchConstants {
     public static final String CLOUDSEARCH_PREFIX = "cloudsearch.";
     public static final String ENDPOINT = CLOUDSEARCH_PREFIX + "endpoint";

diff --git a/external/aws/src/main/java/org/apache/stormcrawler/aws/bolt/CloudSearchIndexerBolt.java b/external/aws/src/main/java/org/apache/stormcrawler/aws/bolt/CloudSearchIndexerBolt.java
@@ -66,7 +66,13 @@
 import software.amazon.awssdk.services.cloudsearchdomain.model.UploadDocumentsRequest;
 import software.amazon.awssdk.services.cloudsearchdomain.model.UploadDocumentsResponse;
 
-/** Writes documents to CloudSearch. */
+/**
+ * Writes documents to CloudSearch.
+ *
+ * @deprecated AWS CloudSearch support is deprecated and will be removed in the next major release
+ *     of StormCrawler.
+ */
+@Deprecated
 public class CloudSearchIndexerBolt extends AbstractIndexerBolt {
 
     public static final Logger LOG = LoggerFactory.getLogger(CloudSearchIndexerBolt.class);

diff --git a/external/aws/src/main/java/org/apache/stormcrawler/aws/bolt/CloudSearchUtils.java b/external/aws/src/main/java/org/apache/stormcrawler/aws/bolt/CloudSearchUtils.java
@@ -22,6 +22,11 @@
 import java.util.regex.Pattern;
 import org.apache.commons.codec.digest.DigestUtils;
 
+/**
+ * @deprecated AWS CloudSearch support is deprecated and will be removed in the next major release
+ *     of StormCrawler.
+ */
+@Deprecated
 public class CloudSearchUtils {
 
     private static final Pattern INVALID_XML_CHARS =