fix integration tests

Signed-off-by: yuye-aws <[email protected]>
yuye-aws · Mar 7, 2024 · 33e4a2b · 33e4a2b
1 parent a99beda
commit 33e4a2b
Show file tree

Hide file tree

Showing 4 changed files with 23 additions and 23 deletions.
diff --git a/src/test/java/org/opensearch/neuralsearch/processor/DocumentChunkingProcessorIT.java b/src/test/java/org/opensearch/neuralsearch/processor/DocumentChunkingProcessorIT.java
@@ -63,8 +63,8 @@ public void testDocumentChunkingProcessor_withFixedTokenLength_successful() thro
 
             List<String> expectedPassages = new ArrayList<>();
             expectedPassages.add("This is an example document to be chunked The document");
-            expectedPassages.add("The document contains a single paragraph two sentences and 24");
-            expectedPassages.add("and 24 tokens by standard tokenizer in OpenSearch");
+            expectedPassages.add("contains a single paragraph two sentences and 24 tokens by");
+            expectedPassages.add("standard tokenizer in OpenSearch");
             validateIndexIngestResults(INDEX_NAME, OUTPUT_FIELD, expectedPassages);
         } finally {
             wipeOfTestResources(INDEX_NAME, FIXED_TOKEN_LENGTH_PIPELINE_NAME, null, null);
@@ -112,7 +112,7 @@ public void testDocumentChunkingProcessor_withCascade_successful() throws Except
             // " ", "." and "," will not be included in fixed token length output
             expectedPassages.add("This is an example document to be chunked");
             expectedPassages.add("The document contains a single paragraph two sentences and 24");
-            expectedPassages.add("and 24 tokens by standard tokenizer in OpenSearch");
+            expectedPassages.add("tokens by standard tokenizer in OpenSearch");
             validateIndexIngestResults(INDEX_NAME, OUTPUT_FIELD, expectedPassages);
 
             expectedPassages.clear();

diff --git a/src/test/resources/processor/chunker/PipelineForCascadedChunker.json b/src/test/resources/processor/chunker/PipelineForCascadedChunker.json
@@ -4,23 +4,23 @@
     {
       "chunking": {
         "field_map": {
-          "body": {
-            "delimiter": {
-              "delimiter": "."
-            },
-            "output_field": "body_chunk_intermediate"
+          "body": "body_chunk_intermediate"
+        },
+        "algorithm": {
+          "delimiter": {
+            "delimiter": "."
           }
         }
       }
     },
     {
       "chunking": {
         "field_map": {
-          "body_chunk_intermediate": {
-            "fix_length": {
-              "token_limit": 10
-            },
-            "output_field": "body_chunk"
+          "body_chunk_intermediate": "body_chunk"
+        },
+        "algorithm": {
+          "fix_length": {
+            "token_limit": 10
           }
         }
       }

diff --git a/src/test/resources/processor/chunker/PipelineForDelimiterChunker.json b/src/test/resources/processor/chunker/PipelineForDelimiterChunker.json
@@ -4,11 +4,11 @@
     {
       "chunking": {
         "field_map": {
-          "body": {
-            "delimiter": {
-              "delimiter": "."
-            },
-            "output_field": "body_chunk"
+          "body": "body_chunk"
+        },
+        "algorithm": {
+          "delimiter": {
+            "delimiter": "."
           }
         }
       }

diff --git a/src/test/resources/processor/chunker/PipelineForFixedTokenLengthChunker.json b/src/test/resources/processor/chunker/PipelineForFixedTokenLengthChunker.json
@@ -4,11 +4,11 @@
     {
       "chunking": {
         "field_map": {
-          "body": {
-            "fix_length": {
-              "token_limit": 10
-            },
-            "output_field": "body_chunk"
+          "body": "body_chunk"
+        },
+        "algorithm": {
+          "fix_length": {
+            "token_limit": 10
           }
         }
       }