Fixes 9192 - Add entity link in response (#9239)

* staging commit

* updated terms to french

* fix(dataInsight): updated ES response to get entityType and total non tiered entities

* fix(dataInsight): removed fields=*

* fix(dataInsight): Added entity migration

* cleaned up branch

* feat: Added entity URL for most viewed entity

* feat(dataInsight): Added href to entity

* feat(DataInsight): Added backend logic for entity href

* Fix conflict resolving typos

* Update openmetadata-service/src/main/resources/json/data/dataInsight/mostViewedEntities.json

Co-authored-by: Nahuel <nahuel@getcollate.io>

* fix: addressed comments from PR review

Co-authored-by: Nahuel <nahuel@getcollate.io>

bootstrap/sql/com.mysql.cj.jdbc.Driver/v007__create_db_connection_info.sql

@@ -9,7 +9,8 @@ SET json = JSON_INSERT(
 	JSON_ARRAY(
 		JSON_OBJECT('name', 'entityFqn', 'chartDataType', 'STRING'),
 		JSON_OBJECT('name', 'owner', 'chartDataType', 'STRING'),
-		JSON_OBJECT('name', 'entityType', 'chartDataType', 'STRING')
+		JSON_OBJECT('name', 'entityType', 'chartDataType', 'STRING'),
+		JSON_OBJECT('name', 'entityHref', 'chartDataType', 'STRING')
 		)
 )
 WHERE name = 'mostViewedEntities';

bootstrap/sql/org.postgresql.Driver/v007__create_db_connection_info.sql

@@ -6,6 +6,6 @@ UPDATE data_insight_chart
 SET json = jsonb_set(
         json,
         '{dimensions}',
-        '[{"name":"entityFqn","chartDataType":"STRING"},{"name":"owner","chartDataType":"STRING"},{"name":"owner","entityType":"STRING"}]'
+        '[{"name":"entityFqn","chartDataType":"STRING"},{"name":"entityType","chartDataType":"STRING"},{"name":"owner","chartDataType":"STRING"},{"name":"entityHref","chartDataType":"STRING"}]'
 )
 WHERE name = 'mostViewedEntities';

ingestion/src/metadata/data_insight/processor/web_analytic_report_data_processor.py

@@ -15,6 +15,7 @@ Processor class used to compute refined report data
 
 from __future__ import annotations
 
+import re
 from collections import namedtuple
 from typing import Generator, Iterable, Optional
 
@@ -107,12 +108,28 @@ class WebAnalyticEntityViewReportDataProcessor(DataProcessor):
                 continue
 
             entity_obj = EntityObj(split_url[0], split_url[1])
+            entity_type = entity_obj.entity_type
+            re_pattern = re.compile(f"(.*{entity_type}/{entity_obj.fqn})")
+
+            if (
+                entity_obj.fqn in refined_data
+                and not refined_data[entity_obj.fqn]["entityHref"]
+            ):
+                # if we've seen the entity previously but were not able to get
+                # the URL we'll try again from the new event.
+                try:
+                    entity_href = re.search(re_pattern, event.eventData.fullUrl).group(
+                        1
+                    )
+                    refined_data[entity_obj.fqn]["entityHref"] = entity_href
+                except IndexError:
+                    logger.debug(f"Could not find entity Href for {entity_obj.fqn}")
 
             if entity_obj.fqn not in refined_data:
                 entity = self.metadata.get_by_name(
                     ENTITIES[entity_obj.entity_type],
                     fqn=entity_obj.fqn,
-                    fields="*",
+                    fields=["tags"],
                 )
 
                 try:
@@ -143,10 +160,18 @@ class WebAnalyticEntityViewReportDataProcessor(DataProcessor):
                         "`tags` attribute not supported for entity type",
                     )
 
+                try:
+                    entity_href = re.search(re_pattern, event.eventData.fullUrl).group(
+                        1
+                    )
+                except IndexError:
+                    entity_href = None
+
                 refined_data[split_url[1]] = {
-                    "entityType": entity_obj.entity_type.title(),
+                    "entityType": ENTITIES[entity_type].__name__,
                     "entityTier": entity_tier,
                     "entityFqn": entity_obj.fqn,
+                    "entityHref": entity_href,
                     "tagsFQN": tags,
                     "owner": owner,
                     "ownerId": owner_id,

ingestion/src/metadata/ingestion/sink/elasticsearch_mapping/web_analytic_entity_view_report_data_index_mapping.py

@@ -29,6 +29,9 @@ WEB_ANALYTIC_ENTITY_VIEW_REPORT_DATA_INDEX_MAPPING = textwrap.dedent(
                         "entityType": {
                             "type": "keyword"
                         },
+                        "entityHref": {
+                            "type": "keyword"
+                        },
                         "entityTier": {
                             "type": "keyword"
                         },

openmetadata-service/src/main/java/org/openmetadata/service/dataInsight/MostViewedEntitiesAggregator.java

@@ -32,14 +32,20 @@ public class MostViewedEntitiesAggregator extends DataInsightAggregatorInterface
       Sum sumPageViews = entityFqnBucket.getAggregations().get("pageViews");
       MultiBucketsAggregation ownerBucket = entityFqnBucket.getAggregations().get("owner");
       MultiBucketsAggregation entityTypeBucket = entityFqnBucket.getAggregations().get("entityType");
+      MultiBucketsAggregation entityHrefBucket = entityFqnBucket.getAggregations().get("entityHref");
       String owner = null;
       String entityType = null;
+      String entityHref = null;
       if (!ownerBucket.getBuckets().isEmpty()) {
         owner = ownerBucket.getBuckets().get(0).getKeyAsString();
       }
 
       if (!entityTypeBucket.getBuckets().isEmpty()) {
-        entityType = entityTypeBucket.getBuckets().get(0).getKeyAsString().toLowerCase();
+        entityType = entityTypeBucket.getBuckets().get(0).getKeyAsString();
+      }
+
+      if (!entityHrefBucket.getBuckets().isEmpty()) {
+        entityHref = entityHrefBucket.getBuckets().get(0).getKeyAsString();
       }
 
       data.add(
@@ -47,6 +53,7 @@ public class MostViewedEntitiesAggregator extends DataInsightAggregatorInterface
               .withEntityFqn(tableFqn)
               .withOwner(owner)
               .withEntityType(entityType)
+              .withEntityHref(entityHref)
               .withPageViews(sumPageViews.getValue()));
     }
     return data;

openmetadata-service/src/main/java/org/openmetadata/service/jdbi3/DataInsightChartRepository.java

@@ -56,6 +56,8 @@ public class DataInsightChartRepository extends EntityRepository<DataInsightChar
   private static final String DATA_OWNER = "data.owner";
   private static final String USER_NAME = "userName";
   private static final String TEAM = "team";
+  private static final String ENTITY_HREF = "entityHref";
+  private static final String DATA_ENTITY_HREF = "data.entityHref";
   private static final List<String> SUPPORTS_TEAM_FILTER =
       Arrays.asList(
           "TotalEntitiesByType",
@@ -191,13 +193,16 @@ public class DataInsightChartRepository extends EntityRepository<DataInsightChar
         TermsAggregationBuilder ownerTermsAggregationBuilder = AggregationBuilders.terms(OWNER).field(DATA_OWNER);
         TermsAggregationBuilder entityTypeTermsAggregationBuilder =
             AggregationBuilders.terms(ENTITY_TYPE).field(DATA_ENTITY_TYPE);
+        TermsAggregationBuilder entityHrefAggregationBuilder =
+            AggregationBuilders.terms(ENTITY_HREF).field(DATA_ENTITY_HREF);
         SumAggregationBuilder sumEntityPageViewsAggregationBuilder =
             AggregationBuilders.sum(PAGE_VIEWS).field(DATA_VIEWS);
 
         return termsAggregationBuilder
             .subAggregation(sumEntityPageViewsAggregationBuilder)
             .subAggregation(ownerTermsAggregationBuilder)
-            .subAggregation(entityTypeTermsAggregationBuilder);
+            .subAggregation(entityTypeTermsAggregationBuilder)
+            .subAggregation(entityHrefAggregationBuilder);
       case MOST_ACTIVE_USERS:
         termsAggregationBuilder =
             AggregationBuilders.terms(USER_NAME)

openmetadata-service/src/main/resources/elasticsearch/web_analytic_entity_view_report_data_index.json

@@ -18,6 +18,9 @@
           "entityFqn": {
             "type": "keyword"
           },
+          "entityHref": {
+            "type": "keyword"
+        },
           "owner": {
             "type": "keyword"
           },

openmetadata-service/src/main/resources/json/data/dataInsight/mostViewedEntities.json

@@ -6,7 +6,8 @@
   "dataIndexType": "web_analytic_entity_view_report_data_index",
   "dimensions": [
     {"name": "entityFqn","chartDataType":"STRING"},
-    {"name":  "entityType", "chartDataType":  "STRING"},
+    {"name": "entityType", "chartDataType":  "STRING"},
+    {"name": "entityHref", "chartDataType":  "STRING"},
     {"name": "owner","chartDataType":"STRING"}
   ],
   "metrics": [

openmetadata-spec/src/main/resources/json/schema/analytics/reportDataType/webAnalyticEntityViewReportData.json

@@ -18,6 +18,10 @@
         "$ref": "../../type/basic.json#/definitions/fullyQualifiedEntityName",
         "description": "entity fully qualified name"
       },
+      "entityHref": {
+        "description": "entity href",
+        "type": "string"
+      },
       "tagsFQN": {
         "description": "Tags FQN",
         "type": "array",

openmetadata-spec/src/main/resources/json/schema/dataInsight/type/mostViewedEntities.json

@@ -10,6 +10,10 @@
       "description": "Number of page views",
       "type": "string"
     },
+    "entityHref": {
+      "description": "Entity href link",
+      "type": "string"
+    },
     "owner": {
       "description": "Owner of the entity",
       "type": "string"