Used UTF-8 bytes for length

Signed-off-by: Owais <[email protected]>

Author: owaiskazi19

CHANGELOG.md

@@ -24,7 +24,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 ### Changed
 - Migrate BC libs to their FIPS counterparts ([#14912](https://github.com/opensearch-project/OpenSearch/pull/14912))
 - Increase the floor segment size to 16MB ([#17699](https://github.com/opensearch-project/OpenSearch/pull/17699))
-- Add validation for Ingest and Search pipeline length ([#17786](https://github.com/opensearch-project/OpenSearch/pull/17786))
+- Introduce 512 byte limit to search and ingest pipeline IDs ([#17786](https://github.com/opensearch-project/OpenSearch/pull/17786))
 
 ### Dependencies
 - Bump `com.nimbusds:nimbus-jose-jwt` from 9.41.1 to 10.0.2 ([#17607](https://github.com/opensearch-project/OpenSearch/pull/17607), [#17669](https://github.com/opensearch-project/OpenSearch/pull/17669))

server/src/main/java/org/opensearch/ingest/IngestService.java

@@ -35,6 +35,7 @@
 import org.apache.logging.log4j.LogManager;
 import org.apache.logging.log4j.Logger;
 import org.apache.logging.log4j.message.ParameterizedMessage;
+import org.apache.lucene.util.UnicodeUtil;
 import org.opensearch.ExceptionsHelper;
 import org.opensearch.OpenSearchParseException;
 import org.opensearch.ResourceNotFoundException;
@@ -108,7 +109,7 @@ public class IngestService implements ClusterStateApplier, ReportingService<Inge
     public static final String NOOP_PIPELINE_NAME = "_none";
 
     public static final String INGEST_ORIGIN = "ingest";
-    private static final int MAX_PIPELINE_ID_LENGTH = 20;
+    private static final int MAX_PIPELINE_ID_BYTES = 512;
 
     /**
      * Defines the limit for the number of processors which can run on a given document during ingestion.
@@ -514,13 +515,16 @@ void validatePipeline(Map<DiscoveryNode, IngestInfo> ingestInfos, PutPipelineReq
             throw new IllegalStateException("Ingest info is empty");
         }
 
-        if (request.getId().length() > MAX_PIPELINE_ID_LENGTH) {
+        int pipelineIdLength = UnicodeUtil.calcUTF16toUTF8Length(request.getId(), 0, request.getId().length());
+
+        if (pipelineIdLength > MAX_PIPELINE_ID_BYTES) {
             throw new IllegalArgumentException(
                 String.format(
                     Locale.ROOT,
-                    "Pipeline id [%s] exceeds maximum length of %d characters",
+                    "Pipeline id [%s] exceeds maximum length of %d UTF-8 bytes (actual: %d bytes)",
                     request.getId(),
-                    MAX_PIPELINE_ID_LENGTH
+                    MAX_PIPELINE_ID_BYTES,
+                    pipelineIdLength
                 )
             );
         }

server/src/main/java/org/opensearch/search/pipeline/SearchPipelineService.java

@@ -10,6 +10,7 @@
 
 import org.apache.logging.log4j.LogManager;
 import org.apache.logging.log4j.Logger;
+import org.apache.lucene.util.UnicodeUtil;
 import org.opensearch.ExceptionsHelper;
 import org.opensearch.OpenSearchParseException;
 import org.opensearch.ResourceNotFoundException;
@@ -74,7 +75,7 @@ public class SearchPipelineService implements ClusterStateApplier, ReportingServ
     public static final String SEARCH_PIPELINE_ORIGIN = "search_pipeline";
     public static final String AD_HOC_PIPELINE_ID = "_ad_hoc_pipeline";
     public static final String NOOP_PIPELINE_ID = "_none";
-    private static final int MAX_PIPELINE_ID_LENGTH = 20;
+    private static final int MAX_PIPELINE_ID_BYTES = 512;
     private static final Logger logger = LogManager.getLogger(SearchPipelineService.class);
     private final ClusterService clusterService;
     private final ScriptService scriptService;
@@ -281,13 +282,16 @@ void validatePipeline(Map<DiscoveryNode, SearchPipelineInfo> searchPipelineInfos
             throw new IllegalStateException("Search pipeline info is empty");
         }
 
-        if (request.getId().length() > MAX_PIPELINE_ID_LENGTH) {
+        int pipelineIdLength = UnicodeUtil.calcUTF16toUTF8Length(request.getId(), 0, request.getId().length());
+
+        if (pipelineIdLength > MAX_PIPELINE_ID_BYTES) {
             throw new IllegalArgumentException(
                 String.format(
                     Locale.ROOT,
-                    "Search pipeline id [%s] exceeds maximum length of %d characters",
+                    "Search Pipeline id [%s] exceeds maximum length of %d UTF-8 bytes (actual: %d bytes)",
                     request.getId(),
-                    MAX_PIPELINE_ID_LENGTH
+                    MAX_PIPELINE_ID_BYTES,
+                    pipelineIdLength
                 )
             );
         }

server/src/test/java/org/opensearch/ingest/IngestServiceTests.java

@@ -89,6 +89,7 @@
 import java.util.Comparator;
 import java.util.HashMap;
 import java.util.List;
+import java.util.Locale;
 import java.util.Map;
 import java.util.Objects;
 import java.util.Set;
@@ -397,8 +398,10 @@ public void testValidateNoIngestInfo() throws Exception {
 
     public void testValidatePipelineId_WithNotValidLength_ShouldThrowException() throws Exception {
         IngestService ingestService = createWithProcessors();
+
+        String longId = "a".repeat(512) + "a";
         PutPipelineRequest putRequest = new PutPipelineRequest(
-            "_idwyebdjgeiwnddhekebddmd",
+            longId,
             new BytesArray(
                 "{\"processors\": [{\"set\" : {\"field\": \"_field\", \"value\": \"_value\", \"tag\": \"tag1\"}},"
                     + "{\"remove\" : {\"field\": \"_field\", \"tag\": \"tag2\"}}]}"
@@ -418,7 +421,12 @@ public void testValidatePipelineId_WithNotValidLength_ShouldThrowException() thr
             IllegalArgumentException.class,
             () -> ingestService.validatePipeline(Collections.singletonMap(discoveryNode, ingestInfo), putRequest)
         );
-        assertEquals("Pipeline id [_idwyebdjgeiwnddhekebddmd] exceeds maximum length of 20 characters", e.getMessage());
+        String errorMessage = String.format(
+            Locale.ROOT,
+            "Pipeline id [%s] exceeds maximum length of 512 UTF-8 bytes (actual: 513 bytes)",
+            longId
+        );
+        assertEquals(errorMessage, e.getMessage());
     }
 
     public void testGetProcessorsInPipeline() throws Exception {

server/src/test/java/org/opensearch/search/pipeline/SearchPipelineServiceTests.java

@@ -70,6 +70,7 @@
 import java.util.Comparator;
 import java.util.HashMap;
 import java.util.List;
+import java.util.Locale;
 import java.util.Map;
 import java.util.concurrent.ExecutorService;
 import java.util.concurrent.atomic.AtomicReference;
@@ -892,8 +893,9 @@ public void testValidatePipeline() throws Exception {
             MediaTypeRegistry.JSON
         );
 
+        String longId = "a".repeat(512) + "a";
         PutSearchPipelineRequest maxLengthIdPutRequest = new PutSearchPipelineRequest(
-            "_idwyebdjgeiwnddhekebddmd",
+            longId,
             new BytesArray("{\"request_processors\" : [ { \"scale_request_size\": { \"scale\" : \"foo\" } } ] }"),
             MediaTypeRegistry.JSON
         );
@@ -916,7 +918,12 @@ public void testValidatePipeline() throws Exception {
             IllegalArgumentException.class,
             () -> searchPipelineService.validatePipeline(Map.of(n1, completePipelineInfo), maxLengthIdPutRequest)
         );
-        assertEquals("Search pipeline id [_idwyebdjgeiwnddhekebddmd] exceeds maximum length of 20 characters", e.getMessage());
+        String errorMessage = String.format(
+            Locale.ROOT,
+            "Search Pipeline id [%s] exceeds maximum length of 512 UTF-8 bytes (actual: 513 bytes)",
+            longId
+        );
+        assertEquals(errorMessage, e.getMessage());
 
         // Invalid configuration in request
         PutSearchPipelineRequest badPutRequest = new PutSearchPipelineRequest(