Parse S3 VPC endpoints for the region

Author: Shintaro Onuma

hadoop-tools/hadoop-aws/src/main/java/org/apache/hadoop/fs/s3a/DefaultS3ClientFactory.java

@@ -21,6 +21,8 @@
 import java.io.IOException;
 import java.net.URI;
 import java.net.URISyntaxException;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
 
 import org.apache.hadoop.classification.VisibleForTesting;
 import org.apache.hadoop.fs.s3a.impl.AWSClientConfig;
@@ -82,6 +84,9 @@ public class DefaultS3ClientFactory extends Configured
 
   private static final String S3_SERVICE_NAME = "s3";
 
+  private static final Pattern VPC_ENDPOINT_PATTERN =
+          Pattern.compile("^(?:.+\\.)?([a-z0-9-]+)\\.vpce\\.amazonaws\\.(?:com|com\\.cn)$");
+
   /**
    * Subclasses refer to this.
    */
@@ -379,10 +384,19 @@ private static URI getS3Endpoint(String endpoint, final Configuration conf) {
    * @param endpointEndsWithCentral true if the endpoint is configured as central.
    * @return the S3 region, null if unable to resolve from endpoint.
    */
-  private static Region getS3RegionFromEndpoint(final String endpoint,
+  @VisibleForTesting
+  static Region getS3RegionFromEndpoint(final String endpoint,
       final boolean endpointEndsWithCentral) {
 
     if (!endpointEndsWithCentral) {
+      // S3 VPC endpoint parsing
+      Matcher matcher = VPC_ENDPOINT_PATTERN.matcher(endpoint);
+      if (matcher.find()) {
+        LOG.debug("Mapping to VPCE");
+        LOG.debug("Endpoint {} is vpc endpoint; parsing region as {}", endpoint, matcher.group(1));
+        return Region.of(matcher.group(1));
+      }
+
       LOG.debug("Endpoint {} is not the default; parsing", endpoint);
       return AwsHostNameUtils.parseSigningRegion(endpoint, S3_SERVICE_NAME).orElse(null);
     }

hadoop-tools/hadoop-aws/src/test/java/org/apache/hadoop/fs/s3a/ITestS3AEndpointRegion.java

@@ -89,6 +89,8 @@ public class ITestS3AEndpointRegion extends AbstractS3ATestBase {
 
   private static final String VPC_ENDPOINT = "vpce-1a2b3c4d-5e6f.s3.us-west-2.vpce.amazonaws.com";
 
+  private static final String CN_VPC_ENDPOINT = "vpce-1a2b3c4d-5e6f.s3.cn-northwest-1.vpce.amazonaws.com.cn";
+
   public static final String EXCEPTION_THROWN_BY_INTERCEPTOR = "Exception thrown by interceptor";
 
   /**
@@ -271,7 +273,6 @@ public void testWithGovCloudEndpoint() throws Throwable {
   }
 
   @Test
-  @Ignore("Pending HADOOP-18938. S3A region logic to handle vpce and non standard endpoints")
   public void testWithVPCE() throws Throwable {
     describe("Test with vpc endpoint");
     Configuration conf = getConfiguration();
@@ -281,6 +282,16 @@ public void testWithVPCE() throws Throwable {
     expectInterceptorException(client);
   }
 
+  @Test
+  public void testWithChinaVPCE() throws Throwable {
+    describe("Test with china vpc endpoint");
+    Configuration conf = getConfiguration();
+
+    S3Client client = createS3Client(conf, CN_VPC_ENDPOINT, null, CN_NORTHWEST_1, false);
+
+    expectInterceptorException(client);
+  }
+
   @Test
   public void testCentralEndpointAndDifferentRegionThanBucket() throws Throwable {
     describe("Access public bucket using central endpoint and region "

hadoop-tools/hadoop-aws/src/test/java/org/apache/hadoop/fs/s3a/TestS3AEndpointParsing.java

@@ -0,0 +1,25 @@
+package org.apache.hadoop.fs.s3a;
+
+import org.assertj.core.api.Assertions;
+import org.junit.Test;
+import software.amazon.awssdk.regions.Region;
+
+public class TestS3AEndpointParsing extends AbstractS3AMockTest {
+
+    private static final String VPC_ENDPOINT = "vpce-1a2b3c4d-5e6f.s3.us-west-2.vpce.amazonaws.com";
+    private static final String NON_VPC_ENDPOINT = "s3.eu-west-1.amazonaws.com";
+    private static final String US_WEST_2 = "us-west-2";
+    private static final String EU_WEST_1 = "eu-west-1";
+
+    @Test
+    public void testVPCEndpoint() {
+        Region region = DefaultS3ClientFactory.getS3RegionFromEndpoint(VPC_ENDPOINT, false);
+        Assertions.assertThat(region).isEqualTo(Region.of(US_WEST_2));
+    }
+
+    @Test
+    public void testNonVPCEndpoint() {
+        Region region = DefaultS3ClientFactory.getS3RegionFromEndpoint(NON_VPC_ENDPOINT, false);
+        Assertions.assertThat(region).isEqualTo(Region.of(EU_WEST_1));
+    }
+}