From 483bd4f25c4607fc3a1d08922d25c08f8b6d9f7c Mon Sep 17 00:00:00 2001
From: Hande Celikkanat <7702228+handecelikkanat@users.noreply.github.com>
Date: Thu, 18 Jun 2026 22:05:03 +0300
Subject: [PATCH 1/2] chore(pom.xml): migrate to AWS SDK v2

---
 pom.xml | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

diff --git a/pom.xml b/pom.xml
index 69b7487..e031aad 100644
--- a/pom.xml
+++ b/pom.xml
@@ -40,7 +40,7 @@ under the License.
 		<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
 		<stormcrawler.version>3.6.0</stormcrawler.version>
 		<storm.version>2.8.8</storm.version>
-		<aws.version>1.12.797</aws.version>
+		<aws.version>2.46.7</aws.version>
 		<jackson.version>2.21.3</jackson.version>
 		<crawler-commons.version>1.6</crawler-commons.version>
 		<mockito.version>5.23.0</mockito.version>
@@ -50,6 +50,18 @@ under the License.
 		<skip.format.code>true</skip.format.code>
 	</properties>
 
+	<dependencyManagement>
+		<dependencies>
+			<dependency>
+				<groupId>software.amazon.awssdk</groupId>
+				<artifactId>bom</artifactId>
+				<version>${aws.version}</version>
+				<type>pom</type>
+				<scope>import</scope>
+			</dependency>
+		</dependencies>
+	</dependencyManagement>
+
 	<dependencies>
 		<dependency>
 			<groupId>org.apache.stormcrawler</groupId>
@@ -86,9 +98,8 @@ under the License.
 		</dependency>
 
 		<dependency>
-			<groupId>com.amazonaws</groupId>
-			<artifactId>aws-java-sdk-s3</artifactId>
-			<version>${aws.version}</version>
+			<groupId>software.amazon.awssdk</groupId>
+			<artifactId>s3</artifactId>
 		</dependency>
 
 		<dependency>

From 89a826fda4e92700fdbcf56e3885b945752f6e17 Mon Sep 17 00:00:00 2001
From: Hande Celikkanat <7702228+handecelikkanat@users.noreply.github.com>
Date: Mon, 22 Jun 2026 18:00:49 +0300
Subject: [PATCH 2/2] chore(FastURLFilter.java): migrate to AWS SDK v2

---
 .../stormcrawler/filter/FastURLFilter.java    | 34 ++++++++++++-------
 1 file changed, 22 insertions(+), 12 deletions(-)

diff --git a/src/main/java/org/commoncrawl/stormcrawler/filter/FastURLFilter.java b/src/main/java/org/commoncrawl/stormcrawler/filter/FastURLFilter.java
index 9b2ee32..881f4ad 100644
--- a/src/main/java/org/commoncrawl/stormcrawler/filter/FastURLFilter.java
+++ b/src/main/java/org/commoncrawl/stormcrawler/filter/FastURLFilter.java
@@ -16,11 +16,6 @@
  */
 package org.commoncrawl.stormcrawler.filter;
 
-import com.amazonaws.services.s3.AmazonS3;
-import com.amazonaws.services.s3.AmazonS3ClientBuilder;
-import com.amazonaws.services.s3.model.GetObjectRequest;
-import com.amazonaws.services.s3.model.ObjectMetadata;
-import com.amazonaws.services.s3.model.S3Object;
 import com.fasterxml.jackson.core.JsonParseException;
 import com.fasterxml.jackson.databind.JsonMappingException;
 import com.fasterxml.jackson.databind.JsonNode;
@@ -46,6 +41,10 @@
 import org.apache.stormcrawler.util.ConfUtils;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
+import software.amazon.awssdk.services.s3.S3Client;
+import software.amazon.awssdk.services.s3.model.GetObjectRequest;
+import software.amazon.awssdk.services.s3.model.HeadObjectRequest;
+import software.amazon.awssdk.services.s3.model.HeadObjectResponse;
 
 /**
  * Version of the FastURLFilter that can load from a text representation instead of the JSON that
@@ -170,11 +169,11 @@ public void run() {
     @Override
     public void loadJSONResources() throws Exception {
         InputStream inputStream = null;
-        AmazonS3 s3client = null;
+        S3Client s3client = null;
         try {
             if (getResourceFile().startsWith("s3://")) {
                 // try loading from S3
-                s3client = AmazonS3ClientBuilder.standard().build();
+                s3client = S3Client.builder().build();
                 java.net.URI uri = new java.net.URI(getResourceFile());
 
                 String bucketName = uri.getHost();
@@ -182,8 +181,14 @@ public void loadJSONResources() throws Exception {
                 String path = uri.getPath().substring(1);
 
                 // optimisation - avoid a full reload if the resource has not changed
-                ObjectMetadata metadata = s3client.getObjectMetadata(bucketName, path);
-                final String ETAG = metadata.getETag();
+                HeadObjectResponse headResponse =
+                        s3client.headObject(
+                                HeadObjectRequest.builder()
+                                                 .bucket(bucketName)
+                                                 .key(path)
+                                                 .build()
+                        );
+                final String ETAG = headResponse.eTag();
                 if (ETAG != null && ETAG.equals(resourceETAG)) {
                     LOG.info("Unchanged ETAG for {} - skipping reload", getResourceFile());
                     return;
@@ -191,8 +196,13 @@ public void loadJSONResources() throws Exception {
                     resourceETAG = ETAG;
                 }
 
-                final S3Object object = s3client.getObject(new GetObjectRequest(bucketName, path));
-                inputStream = object.getObjectContent();
+                inputStream =
+                        s3client.getObject(
+                                GetObjectRequest.builder()
+                                                .bucket(bucketName)
+                                                .key(path)
+                                                .build()
+                        );
             } else {
                 inputStream = getClass().getClassLoader().getResourceAsStream(getResourceFile());
                 if (inputStream == null) {
@@ -210,7 +220,7 @@ public void loadJSONResources() throws Exception {
                 inputStream.close();
             }
             if (s3client != null) {
-                s3client.shutdown();
+                s3client.close();
             }
         }
     }