Fix Search Indexes: Normalize display name to be lowercase, such that upper or lowercase searches can work (#10611)

* Fix Search Indexes: Normalize display name to be lowercase, such that upper or lowercase searches can work

* Fix Search Indexes: Normalize display name to be lowercase, such that upper or lowercase searches can work

openmetadata-service/src/main/java/org/openmetadata/service/resources/search/SearchResource.java

@@ -102,6 +102,7 @@ public class SearchResource {
   private static final Integer MAX_RESULT_HITS = 10000;
   private static final String NAME_KEYWORD = "name.keyword";
   private static final String DISPLAY_NAME = "displayName";
+  private static final String FIELD_NAME_NGRAM = "name.ngram";
   private static final String DISPLAY_NAME_KEYWORD = "displayName.keyword";
   private static final String FIELD_DISPLAY_NAME_NGRAM = "displayName.ngram";
   private static final String QUERY = "query";
@@ -551,6 +552,7 @@ public class SearchResource {
             .field(FIELD_DISPLAY_NAME, 15.0f)
             .field(FIELD_DISPLAY_NAME_NGRAM)
             .field(FIELD_NAME, 15.0f)
+            .field(FIELD_NAME_NGRAM)
             .field(DISPLAY_NAME_KEYWORD, 25.0f)
             .field(NAME_KEYWORD, 25.0f)
             .field(FIELD_DESCRIPTION, 1.0f)
@@ -605,6 +607,7 @@ public class SearchResource {
             .field(FIELD_DISPLAY_NAME, 15.0f)
             .field(FIELD_DISPLAY_NAME_NGRAM)
             .field(FIELD_NAME, 15.0f)
+            .field(FIELD_NAME_NGRAM)
             .field(DISPLAY_NAME_KEYWORD, 25.0f)
             .field(NAME_KEYWORD, 25.0f)
             .field(FIELD_DESCRIPTION, 1.0f)
@@ -634,6 +637,7 @@ public class SearchResource {
             .field(FIELD_DISPLAY_NAME, 15.0f)
             .field(FIELD_DISPLAY_NAME_NGRAM)
             .field(FIELD_NAME, 15.0f)
+            .field(FIELD_NAME_NGRAM)
             .field(DISPLAY_NAME_KEYWORD, 25.0f)
             .field(NAME_KEYWORD, 25.0f)
             .field(FIELD_DESCRIPTION, 1.0f)
@@ -839,6 +843,8 @@ public class SearchResource {
   private SearchSourceBuilder buildGlossaryTermSearchBuilder(String query, int from, int size) {
     QueryStringQueryBuilder queryBuilder =
         QueryBuilders.queryStringQuery(query)
+            .field(FIELD_DISPLAY_NAME, 10.0f)
+            .field(FIELD_DISPLAY_NAME_NGRAM, 1.0f)
             .field(FIELD_NAME, 10.0f)
             .field(NAME_KEYWORD, 10.0f)
             .field(DISPLAY_NAME_KEYWORD, 10.0f)
@@ -855,6 +861,8 @@ public class SearchResource {
 
     HighlightBuilder.Field highlightGlossaryName = new HighlightBuilder.Field(FIELD_NAME);
     highlightGlossaryName.highlighterType(UNIFIED);
+    HighlightBuilder.Field highlightGlossaryDisplayName = new HighlightBuilder.Field(FIELD_DISPLAY_NAME);
+    highlightGlossaryDisplayName.highlighterType(UNIFIED);
     HighlightBuilder.Field highlightDescription = new HighlightBuilder.Field(FIELD_DESCRIPTION);
     highlightDescription.highlighterType(UNIFIED);
     HighlightBuilder.Field highlightSynonym = new HighlightBuilder.Field("synonyms");
@@ -862,7 +870,9 @@ public class SearchResource {
     HighlightBuilder hb = new HighlightBuilder();
     hb.field(highlightDescription);
     hb.field(highlightGlossaryName);
+    hb.field(highlightGlossaryDisplayName);
     hb.field(highlightSynonym);
+
     hb.preTags("<span class=\"text-highlighter\">");
     hb.postTags("</span>");
     SearchSourceBuilder searchSourceBuilder =
@@ -877,15 +887,20 @@ public class SearchResource {
     QueryStringQueryBuilder queryBuilder =
         QueryBuilders.queryStringQuery(query)
             .field(FIELD_NAME, 10.0f)
+            .field(FIELD_DISPLAY_NAME, 10.0f)
+            .field(FIELD_DISPLAY_NAME_NGRAM, 1.0f)
             .field(DESCRIPTION, 3.0f)
             .defaultOperator(Operator.AND)
             .fuzziness(Fuzziness.AUTO);
 
     HighlightBuilder.Field highlightTagName = new HighlightBuilder.Field(FIELD_NAME);
     highlightTagName.highlighterType(UNIFIED);
+    HighlightBuilder.Field highlightTagDisplayName = new HighlightBuilder.Field(FIELD_DISPLAY_NAME);
+    highlightTagDisplayName.highlighterType(UNIFIED);
     HighlightBuilder.Field highlightDescription = new HighlightBuilder.Field(FIELD_DESCRIPTION);
     highlightDescription.highlighterType(UNIFIED);
     HighlightBuilder hb = new HighlightBuilder();
+    hb.field(highlightTagDisplayName);
     hb.field(highlightDescription);
     hb.field(highlightTagName);
     hb.preTags("<span class=\"text-highlighter\">");

openmetadata-service/src/main/resources/elasticsearch/en/dashboard_index_mapping.json

@@ -21,7 +21,10 @@
         "om_ngram": {
           "tokenizer": "ngram",
           "min_gram": 1,
-          "max_gram": 2
+          "max_gram": 2,
+          "filter": [
+            "lowercase"
+          ]
         }
       },
       "filter": {
@@ -39,10 +42,15 @@
       },
       "name": {
         "type": "text",
+        "analyzer": "om_analyzer",
         "fields": {
           "keyword": {
             "type": "keyword",
             "ignore_above": 256
+          },
+          "ngram": {
+            "type": "text",
+            "analyzer": "om_ngram"
           }
         }
       },
@@ -57,6 +65,10 @@
           "ngram": {
             "type": "text",
             "analyzer": "om_ngram"
+          },
+          "keyword": {
+            "type": "keyword",
+            "ignore_above": 256
           }
         }
       },

openmetadata-service/src/main/resources/elasticsearch/en/glossary_index_mapping.json

@@ -21,7 +21,10 @@
         "om_ngram": {
           "tokenizer": "ngram",
           "min_gram": 1,
-          "max_gram": 2
+          "max_gram": 2,
+          "filter": [
+            "lowercase"
+          ]
         }
       },
       "filter": {
@@ -38,11 +41,16 @@
         "type": "text"
       },
       "name": {
-        "type": "keyword",
+        "type": "text",
+        "analyzer": "om_analyzer",
         "fields": {
           "keyword": {
             "type": "keyword",
             "ignore_above": 256
+          },
+          "ngram": {
+            "type": "text",
+            "analyzer": "om_ngram"
           }
         }
       },

openmetadata-service/src/main/resources/elasticsearch/en/mlmodel_index_mapping.json

@@ -21,7 +21,10 @@
         "om_ngram": {
           "tokenizer": "ngram",
           "min_gram": 1,
-          "max_gram": 2
+          "max_gram": 2,
+          "filter": [
+            "lowercase"
+          ]
         }
       },
       "filter": {
@@ -39,10 +42,15 @@
       },
       "name": {
         "type": "text",
+        "analyzer": "om_analyzer",
         "fields": {
           "keyword": {
             "type": "keyword",
             "ignore_above": 256
+          },
+          "ngram": {
+            "type": "text",
+            "analyzer": "om_ngram"
           }
         }
       },
@@ -54,6 +62,10 @@
         "type": "text",
         "analyzer": "om_analyzer",
         "fields": {
+          "keyword": {
+            "type": "keyword",
+            "ignore_above": 256
+          },
           "ngram": {
             "type": "text",
             "analyzer": "om_ngram"

openmetadata-service/src/main/resources/elasticsearch/en/pipeline_index_mapping.json

@@ -17,6 +17,14 @@
             "lowercase",
             "om_stemmer"
           ]
+        },
+        "om_ngram": {
+          "tokenizer": "ngram",
+          "min_gram": 1,
+          "max_gram": 2,
+          "filter": [
+            "lowercase"
+          ]
         }
       },
       "filter": {
@@ -47,7 +55,17 @@
       },
       "displayName": {
         "type": "text",
-        "analyzer": "om_analyzer"
+        "analyzer": "om_analyzer",
+        "fields": {
+          "ngram": {
+            "type": "text",
+            "analyzer": "om_ngram"
+          },
+          "keyword": {
+            "type": "keyword",
+            "ignore_above": 256
+          }
+        }
       },
       "description": {
         "type": "text",

openmetadata-service/src/main/resources/elasticsearch/en/table_index_mapping.json

@@ -21,7 +21,10 @@
         "om_ngram": {
           "tokenizer": "ngram",
           "min_gram": 1,
-          "max_gram": 2
+          "max_gram": 2,
+          "filter": [
+            "lowercase"
+          ]
         }
       },
       "filter": {
@@ -39,10 +42,15 @@
       },
       "name": {
         "type": "text",
+        "analyzer": "om_analyzer",
         "fields": {
           "keyword": {
             "type": "keyword",
             "ignore_above": 256
+          },
+          "ngram": {
+            "type": "text",
+            "analyzer": "om_ngram"
           }
         }
       },
@@ -54,6 +62,10 @@
         "type": "text",
         "analyzer": "om_analyzer",
         "fields": {
+          "keyword": {
+            "type": "keyword",
+            "ignore_above": 256
+          },
           "ngram": {
             "type": "text",
             "analyzer": "om_ngram"

openmetadata-service/src/main/resources/elasticsearch/en/tag_index_mapping.json

@@ -21,7 +21,10 @@
         "om_ngram": {
           "tokenizer": "ngram",
           "min_gram": 1,
-          "max_gram": 2
+          "max_gram": 2,
+          "filter": [
+            "lowercase"
+          ]
         }
       },
       "filter": {
@@ -38,11 +41,16 @@
         "type": "text"
       },
       "name": {
-        "type": "keyword",
+        "type": "text",
+        "analyzer": "om_analyzer",
         "fields": {
           "keyword": {
             "type": "keyword",
             "ignore_above": 256
+          },
+          "ngram": {
+            "type": "text",
+            "analyzer": "om_ngram"
           }
         }
       },
@@ -52,10 +60,15 @@
       },
       "displayName": {
         "type": "text",
+        "analyzer": "om_analyzer",
         "fields": {
           "keyword": {
             "type": "keyword",
             "ignore_above": 256
+          },
+          "ngram": {
+            "type": "text",
+            "analyzer": "om_ngram"
           }
         }
       },

openmetadata-service/src/main/resources/elasticsearch/en/team_index_mapping.json

@@ -1,6 +1,6 @@
 {
   "settings": {
-  "analysis": {
+   "analysis": {
     "normalizer": {
       "lowercase_normalizer": {
         "type": "custom",
@@ -39,10 +39,15 @@
       },
       "name": {
         "type": "text",
+        "analyzer": "om_analyzer",
         "fields": {
           "keyword": {
             "type": "keyword",
             "ignore_above": 256
+          },
+          "ngram": {
+            "type": "text",
+            "analyzer": "om_ngram"
           }
         }
       },

openmetadata-service/src/main/resources/elasticsearch/en/topic_index_mapping.json

@@ -21,7 +21,10 @@
         "om_ngram": {
           "tokenizer": "ngram",
           "min_gram": 1,
-          "max_gram": 2
+          "max_gram": 2,
+          "filter": [
+            "lowercase"
+          ]
         }
       },
       "filter": {
@@ -39,10 +42,15 @@
       },
       "name": {
         "type": "text",
+        "analyzer": "om_analyzer",
         "fields": {
           "keyword": {
             "type": "keyword",
             "ignore_above": 256
+          },
+          "ngram": {
+            "type": "text",
+            "analyzer": "om_ngram"
           }
         }
       },

openmetadata-service/src/main/resources/elasticsearch/en/user_index_mapping.json

@@ -21,7 +21,10 @@
         "om_ngram": {
           "tokenizer": "ngram",
           "min_gram": 1,
-          "max_gram": 2
+          "max_gram": 2,
+          "filter": [
+            "lowercase"
+          ]
         }
       },
       "filter": {