Adding yaml tests for match_all

Author: Samiul-TheSoccerFan

x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/InferenceFeatures.java

@@ -34,6 +34,7 @@ public class InferenceFeatures implements FeatureSpecification {
     private static final NodeFeature TEST_RULE_RETRIEVER_WITH_INDICES_THAT_DONT_RETURN_RANK_DOCS = new NodeFeature(
         "test_rule_retriever.with_indices_that_dont_return_rank_docs"
     );
+    private static final NodeFeature SEMANTIC_TEXT_MATCH_ALL_HIGHLIGHTER = new NodeFeature("semantic_text.match_all_highlighter");
 
     @Override
     public Set<NodeFeature> getTestFeatures() {
@@ -57,7 +58,8 @@ public Set<NodeFeature> getTestFeatures() {
             SemanticTextFieldMapper.SEMANTIC_TEXT_BIT_VECTOR_SUPPORT,
             SemanticTextFieldMapper.SEMANTIC_TEXT_HANDLE_EMPTY_INPUT,
             TEST_RULE_RETRIEVER_WITH_INDICES_THAT_DONT_RETURN_RANK_DOCS,
-            SEMANTIC_TEXT_SUPPORT_CHUNKING_CONFIG
+            SEMANTIC_TEXT_SUPPORT_CHUNKING_CONFIG,
+            SEMANTIC_TEXT_MATCH_ALL_HIGHLIGHTER
         );
     }
 }

x-pack/plugin/inference/src/yamlRestTest/resources/rest-api-spec/test/inference/90_semantic_text_highlighter.yml

@@ -336,3 +336,133 @@ setup:
   - length: { hits.hits.0.highlight.semantic_text_field: 2 }
   - match: { hits.hits.0.highlight.semantic_text_field.0: "some test data" }
   - match: { hits.hits.0.highlight.semantic_text_field.1: "now with chunks" }
+
+---
+"Highlighting with match_all query":
+  - requires:
+      cluster_features: "semantic_text.match_all_highlighter"
+      reason: semantic text field supports match_all query with semantic highlighter, effective from 8.19 and 9.1.0.
+
+  - do:
+      search:
+        index: test-sparse-index
+        body:
+          query:
+            match_all: {}
+          highlight:
+            fields:
+              body:
+                type: "semantic"
+                number_of_fragments: 2
+
+  - match:  { hits.total.value: 1 }
+  - match:  { hits.hits.0._id: "doc_1" }
+  - length: { hits.hits.0.highlight.body: 2 }
+  - match:  { hits.hits.0.highlight.body.0: "ElasticSearch is an open source, distributed, RESTful, search engine which is built on top of Lucene internally and enjoys all the features it provides." }
+  - match:  { hits.hits.0.highlight.body.1: "You Know, for Search!" }
+
+  - do:
+      search:
+        index: test-dense-index
+        body:
+          query:
+            match_all: {}
+          highlight:
+            fields:
+              body:
+                type: "semantic"
+                number_of_fragments: 2
+
+  - match: { hits.total.value: 1 }
+  - match: { hits.hits.0._id: "doc_1" }
+  - length: { hits.hits.0.highlight.body: 2 }
+  - match: { hits.hits.0.highlight.body.0: "ElasticSearch is an open source, distributed, RESTful, search engine which is built on top of Lucene internally and enjoys all the features it provides." }
+  - match: { hits.hits.0.highlight.body.1: "You Know, for Search!" }
+
+---
+"Highlighting with match_all query and multiple field types":
+  - requires:
+      cluster_features: "semantic_text.match_all_highlighter"
+      reason: semantic text field supports match_all query with semantic highlighter, effective from 8.19 and 9.1.0.
+
+  - do:
+      indices.create:
+        index: test-index-sparse
+        body:
+          settings:
+            index.mapping.semantic_text.use_legacy_format: false
+          mappings:
+            properties:
+              semantic_text_field:
+                type: semantic_text
+                inference_id: sparse-inference-id
+              text_field:
+                type: text
+
+  - do:
+      index:
+        index: test-index-sparse
+        id: doc_1
+        body:
+          semantic_text_field: [ "some test data", "    ", "now with chunks" ]
+          text_field: "some test data"
+        refresh: true
+
+  - do:
+      search:
+        index: test-index-sparse
+        body:
+          query:
+            match_all: {}
+          highlight:
+            fields:
+              body:
+                type: "semantic"
+                number_of_fragments: 2
+
+  - match:  { hits.total.value: 1 }
+  - match:  { hits.hits.0._id: "doc_1" }
+  - length: { hits.hits.0.highlight.body: 2 }
+  - match:  { hits.hits.0.highlight.body.0: "some test data" }
+  - match:  { hits.hits.0.highlight.body.1: "now with chunks" }
+
+  - do:
+      indices.create:
+        index: test-index-dense
+        body:
+          settings:
+            index.mapping.semantic_text.use_legacy_format: false
+          mappings:
+            properties:
+              semantic_text_field:
+                type: semantic_text
+                inference_id: sparse-inference-id
+              text_field:
+                type: text
+
+  - do:
+      index:
+        index: test-index-dense
+        id: doc_1
+        body:
+          semantic_text_field: [ "some test data", "    ", "now with chunks" ]
+          text_field: "some test data"
+        refresh: true
+
+  - do:
+      search:
+        index: test-index-dense
+        body:
+          query:
+            match_all: {}
+          highlight:
+            fields:
+              body:
+                type: "semantic"
+                number_of_fragments: 2
+
+  - match: { hits.total.value: 1 }
+  - match: { hits.hits.0._id: "doc_1" }
+  - length: { hits.hits.0.highlight.body: 2 }
+  - match: { hits.hits.0.highlight.body.0: "some test data" }
+  - match: { hits.hits.0.highlight.body.1: "now with chunks" }

x-pack/plugin/inference/src/yamlRestTest/resources/rest-api-spec/test/inference/90_semantic_text_highlighter_bwc.yml

@@ -288,3 +288,134 @@ setup:
   - length: { hits.hits.0.highlight.semantic_text_field: 2 }
   - match: { hits.hits.0.highlight.semantic_text_field.0: "some test data" }
   - match: { hits.hits.0.highlight.semantic_text_field.1: "now with chunks" }
+
+---
+"Highlighting with match_all query":
+  - requires:
+      cluster_features: "semantic_text.match_all_highlighter"
+      reason: semantic text field supports match_all query with semantic highlighter, effective from 8.19 and 9.1.0.
+
+  - do:
+      search:
+        index: test-sparse-index
+        body:
+          query:
+            match_all: {}
+          highlight:
+            fields:
+              body:
+                type: "semantic"
+                number_of_fragments: 2
+
+  - match:  { hits.total.value: 1 }
+  - match:  { hits.hits.0._id: "doc_1" }
+  - length: { hits.hits.0.highlight.body: 2 }
+  - match:  { hits.hits.0.highlight.body.0: "ElasticSearch is an open source, distributed, RESTful, search engine which is built on top of Lucene internally and enjoys all the features it provides." }
+  - match:  { hits.hits.0.highlight.body.1: "You Know, for Search!" }
+
+  - do:
+      search:
+        index: test-dense-index
+        body:
+          query:
+            match_all: {}
+          highlight:
+            fields:
+              body:
+                type: "semantic"
+                number_of_fragments: 2
+
+  - match: { hits.total.value: 1 }
+  - match: { hits.hits.0._id: "doc_1" }
+  - length: { hits.hits.0.highlight.body: 2 }
+  - match: { hits.hits.0.highlight.body.0: "ElasticSearch is an open source, distributed, RESTful, search engine which is built on top of Lucene internally and enjoys all the features it provides." }
+  - match: { hits.hits.0.highlight.body.1: "You Know, for Search!" }
+
+---
+"Highlighting with match_all query and multiple field types":
+  - requires:
+      cluster_features: "semantic_text.match_all_highlighter"
+      reason: semantic text field supports match_all query with semantic highlighter, effective from 8.19 and 9.1.0.
+
+  - do:
+      indices.create:
+        index: test-index-sparse
+        body:
+          settings:
+            index.mapping.semantic_text.use_legacy_format: true
+          mappings:
+            properties:
+              semantic_text_field:
+                type: semantic_text
+                inference_id: sparse-inference-id
+              text_field:
+                type: text
+
+  - do:
+      index:
+        index: test-index-sparse
+        id: doc_1
+        body:
+          semantic_text_field: [ "some test data", "    ", "now with chunks" ]
+          text_field: "some test data"
+        refresh: true
+
+  - do:
+      search:
+        index: test-index-sparse
+        body:
+          query:
+            match_all: {}
+          highlight:
+            fields:
+              body:
+                type: "semantic"
+                number_of_fragments: 2
+
+  - match:  { hits.total.value: 1 }
+  - match:  { hits.hits.0._id: "doc_1" }
+  - length: { hits.hits.0.highlight.body: 2 }
+  - match:  { hits.hits.0.highlight.body.0: "some test data" }
+  - match:  { hits.hits.0.highlight.body.1: "now with chunks" }
+
+  - do:
+      indices.create:
+        index: test-index-dense
+        body:
+          settings:
+            index.mapping.semantic_text.use_legacy_format: true
+          mappings:
+            properties:
+              semantic_text_field:
+                type: semantic_text
+                inference_id: sparse-inference-id
+              text_field:
+                type: text
+
+  - do:
+      index:
+        index: test-index-dense
+        id: doc_1
+        body:
+          semantic_text_field: [ "some test data", "    ", "now with chunks" ]
+          text_field: "some test data"
+        refresh: true
+
+  - do:
+      search:
+        index: test-index-dense
+        body:
+          query:
+            match_all: {}
+          highlight:
+            fields:
+              body:
+                type: "semantic"
+                number_of_fragments: 2
+
+  - match: { hits.total.value: 1 }
+  - match: { hits.hits.0._id: "doc_1" }
+  - length: { hits.hits.0.highlight.body: 2 }
+  - match: { hits.hits.0.highlight.body.0: "some test data" }
+  - match: { hits.hits.0.highlight.body.1: "now with chunks" }
+