Add Description Ngram for search (#11395)

* Add Description Ngram for search

* Fix glosssary aggregation
This commit is contained in:
Sriharsha Chintalapani 2023-05-04 00:16:06 -07:00 committed by GitHub
parent 544d8c722f
commit 3e9288be9a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
10 changed files with 93 additions and 16 deletions

View File

@ -105,6 +105,7 @@ public class SearchResource {
private static final String FIELD_NAME_NGRAM = "name.ngram"; private static final String FIELD_NAME_NGRAM = "name.ngram";
private static final String DISPLAY_NAME_KEYWORD = "displayName.keyword"; private static final String DISPLAY_NAME_KEYWORD = "displayName.keyword";
private static final String FIELD_DISPLAY_NAME_NGRAM = "displayName.ngram"; private static final String FIELD_DISPLAY_NAME_NGRAM = "displayName.ngram";
private static final String FIELD_DESCRIPTION_NGRAM = "description.ngram";
private static final String QUERY = "query"; private static final String QUERY = "query";
private static final String QUERY_NGRAM = "query.ngram"; private static final String QUERY_NGRAM = "query.ngram";
private static final String DESCRIPTION = "description"; private static final String DESCRIPTION = "description";
@ -556,6 +557,7 @@ public class SearchResource {
.field(DISPLAY_NAME_KEYWORD, 25.0f) .field(DISPLAY_NAME_KEYWORD, 25.0f)
.field(NAME_KEYWORD, 25.0f) .field(NAME_KEYWORD, 25.0f)
.field(FIELD_DESCRIPTION, 1.0f) .field(FIELD_DESCRIPTION, 1.0f)
.field(FIELD_DESCRIPTION_NGRAM, 1.0f)
.field("columns.name.keyword", 10.0f) .field("columns.name.keyword", 10.0f)
.field("columns.name", 2.0f) .field("columns.name", 2.0f)
.field("columns.name.ngram") .field("columns.name.ngram")
@ -608,6 +610,7 @@ public class SearchResource {
.field(FIELD_DISPLAY_NAME_NGRAM) .field(FIELD_DISPLAY_NAME_NGRAM)
.field(FIELD_NAME, 15.0f) .field(FIELD_NAME, 15.0f)
.field(FIELD_NAME_NGRAM) .field(FIELD_NAME_NGRAM)
.field(FIELD_DESCRIPTION_NGRAM, 1.0f)
.field(DISPLAY_NAME_KEYWORD, 25.0f) .field(DISPLAY_NAME_KEYWORD, 25.0f)
.field(NAME_KEYWORD, 25.0f) .field(NAME_KEYWORD, 25.0f)
.field(FIELD_DESCRIPTION, 1.0f) .field(FIELD_DESCRIPTION, 1.0f)
@ -638,6 +641,7 @@ public class SearchResource {
.field(FIELD_DISPLAY_NAME_NGRAM) .field(FIELD_DISPLAY_NAME_NGRAM)
.field(FIELD_NAME, 15.0f) .field(FIELD_NAME, 15.0f)
.field(FIELD_NAME_NGRAM) .field(FIELD_NAME_NGRAM)
.field(FIELD_DESCRIPTION_NGRAM, 1.0f)
.field(DISPLAY_NAME_KEYWORD, 25.0f) .field(DISPLAY_NAME_KEYWORD, 25.0f)
.field(NAME_KEYWORD, 25.0f) .field(NAME_KEYWORD, 25.0f)
.field(FIELD_DESCRIPTION, 1.0f) .field(FIELD_DESCRIPTION, 1.0f)
@ -670,6 +674,7 @@ public class SearchResource {
.field(FIELD_DISPLAY_NAME, 15.0f) .field(FIELD_DISPLAY_NAME, 15.0f)
.field(FIELD_DISPLAY_NAME_NGRAM) .field(FIELD_DISPLAY_NAME_NGRAM)
.field(FIELD_NAME, 15.0f) .field(FIELD_NAME, 15.0f)
.field(FIELD_DESCRIPTION_NGRAM, 1.0f)
.field(DISPLAY_NAME_KEYWORD, 25.0f) .field(DISPLAY_NAME_KEYWORD, 25.0f)
.field(NAME_KEYWORD, 25.0f) .field(NAME_KEYWORD, 25.0f)
.field(DESCRIPTION, 1.0f) .field(DESCRIPTION, 1.0f)
@ -700,6 +705,7 @@ public class SearchResource {
.field(FIELD_DISPLAY_NAME, 15.0f) .field(FIELD_DISPLAY_NAME, 15.0f)
.field(FIELD_DISPLAY_NAME_NGRAM) .field(FIELD_DISPLAY_NAME_NGRAM)
.field(FIELD_NAME, 15.0f) .field(FIELD_NAME, 15.0f)
.field(FIELD_DESCRIPTION_NGRAM, 1.0f)
.field(DISPLAY_NAME_KEYWORD, 25.0f) .field(DISPLAY_NAME_KEYWORD, 25.0f)
.field(NAME_KEYWORD, 25.0f) .field(NAME_KEYWORD, 25.0f)
.field(DESCRIPTION, 1.0f) .field(DESCRIPTION, 1.0f)
@ -731,6 +737,7 @@ public class SearchResource {
.field(FIELD_DISPLAY_NAME_NGRAM) .field(FIELD_DISPLAY_NAME_NGRAM)
.field(FIELD_NAME, 15.0f) .field(FIELD_NAME, 15.0f)
.field(FIELD_DESCRIPTION, 1.0f) .field(FIELD_DESCRIPTION, 1.0f)
.field(FIELD_DESCRIPTION_NGRAM, 1.0f)
.field(DISPLAY_NAME_KEYWORD, 25.0f) .field(DISPLAY_NAME_KEYWORD, 25.0f)
.field(NAME_KEYWORD, 25.0f) .field(NAME_KEYWORD, 25.0f)
.field("dataModel.columns.name", 2.0f) .field("dataModel.columns.name", 2.0f)
@ -772,7 +779,8 @@ public class SearchResource {
.field(FIELD_DISPLAY_NAME_NGRAM) .field(FIELD_DISPLAY_NAME_NGRAM)
.field(QUERY, 10.0f) .field(QUERY, 10.0f)
.field(QUERY_NGRAM) .field(QUERY_NGRAM)
.field(DESCRIPTION, 3.0f) .field(DESCRIPTION, 1.0f)
.field(FIELD_DESCRIPTION_NGRAM, 1.0f)
.defaultOperator(Operator.AND) .defaultOperator(Operator.AND)
.fuzziness(Fuzziness.AUTO); .fuzziness(Fuzziness.AUTO);
@ -879,7 +887,7 @@ public class SearchResource {
new SearchSourceBuilder().query(queryBuilder).highlighter(hb).from(from).size(size); new SearchSourceBuilder().query(queryBuilder).highlighter(hb).from(from).size(size);
searchSourceBuilder searchSourceBuilder
.aggregation(AggregationBuilders.terms("tags.tagFQN").field("tags.tagFQN").size(MAX_AGGREGATE_SIZE)) .aggregation(AggregationBuilders.terms("tags.tagFQN").field("tags.tagFQN").size(MAX_AGGREGATE_SIZE))
.aggregation(AggregationBuilders.terms("glossary.name").field("glossary.name.keyword")); .aggregation(AggregationBuilders.terms("glossary.name.keyword").field("glossary.name.keyword"));
return searchSourceBuilder; return searchSourceBuilder;
} }

View File

@ -67,7 +67,12 @@
"type": "text", "type": "text",
"index_options": "docs", "index_options": "docs",
"analyzer": "om_analyzer", "analyzer": "om_analyzer",
"norms": false "fields": {
"ngram": {
"type": "text",
"analyzer": "om_ngram"
}
}
}, },
"version": { "version": {
"type": "float" "type": "float"
@ -147,7 +152,12 @@
"type": "text", "type": "text",
"index_options": "docs", "index_options": "docs",
"analyzer": "om_analyzer", "analyzer": "om_analyzer",
"norms": false "fields": {
"ngram": {
"type": "text",
"analyzer": "om_ngram"
}
}
}, },
"fullyQualifiedName": { "fullyQualifiedName": {
"type": "text" "type": "text"
@ -205,7 +215,15 @@
"type": "text" "type": "text"
}, },
"description": { "description": {
"type": "text" "type": "text",
"index_options": "docs",
"analyzer": "om_analyzer",
"fields": {
"ngram": {
"type": "text",
"analyzer": "om_ngram"
}
}
}, },
"deleted": { "deleted": {
"type": "text" "type": "text"

View File

@ -74,7 +74,13 @@
}, },
"description": { "description": {
"type": "text", "type": "text",
"analyzer": "om_analyzer" "analyzer": "om_analyzer",
"fields": {
"ngram": {
"type": "text",
"analyzer": "om_ngram"
}
}
}, },
"version": { "version": {
"type": "float" "type": "float"
@ -129,7 +135,13 @@
}, },
"description": { "description": {
"type": "text", "type": "text",
"analyzer": "om_analyzer" "analyzer": "om_analyzer",
"fields": {
"ngram": {
"type": "text",
"analyzer": "om_ngram"
}
}
}, },
"deleted": { "deleted": {
"type": "text" "type": "text"

View File

@ -73,7 +73,14 @@
} }
}, },
"description": { "description": {
"type": "text" "type": "text",
"analyzer": "om_analyzer",
"fields": {
"ngram": {
"type": "text",
"analyzer": "om_ngram"
}
}
}, },
"version": { "version": {
"type": "float" "type": "float"

View File

@ -74,7 +74,13 @@
}, },
"description": { "description": {
"type": "text", "type": "text",
"analyzer": "om_analyzer" "analyzer": "om_analyzer",
"fields": {
"ngram": {
"type": "text",
"analyzer": "om_ngram"
}
}
}, },
"version": { "version": {
"type": "float" "type": "float"

View File

@ -69,7 +69,13 @@
}, },
"description": { "description": {
"type": "text", "type": "text",
"analyzer": "om_analyzer" "analyzer": "om_analyzer",
"fields": {
"ngram": {
"type": "text",
"analyzer": "om_ngram"
}
}
}, },
"version": { "version": {
"type": "float" "type": "float"

View File

@ -65,9 +65,13 @@
}, },
"description": { "description": {
"type": "text", "type": "text",
"index_options": "docs",
"analyzer": "om_analyzer", "analyzer": "om_analyzer",
"norms": false "fields": {
"ngram": {
"type": "text",
"analyzer": "om_ngram"
}
}
}, },
"version": { "version": {
"type": "float" "type": "float"

View File

@ -74,9 +74,13 @@
}, },
"description": { "description": {
"type": "text", "type": "text",
"index_options": "docs",
"analyzer": "om_analyzer", "analyzer": "om_analyzer",
"norms": false "fields": {
"ngram": {
"type": "text",
"analyzer": "om_ngram"
}
}
}, },
"version": { "version": {
"type": "float" "type": "float"

View File

@ -73,7 +73,13 @@
} }
}, },
"description": { "description": {
"type": "text" "analyzer": "om_analyzer",
"fields": {
"ngram": {
"type": "text",
"analyzer": "om_ngram"
}
}
}, },
"version": { "version": {
"type": "float" "type": "float"

View File

@ -70,7 +70,13 @@
}, },
"description": { "description": {
"type": "text", "type": "text",
"analyzer": "om_analyzer" "analyzer": "om_analyzer",
"fields": {
"ngram": {
"type": "text",
"analyzer": "om_ngram"
}
}
}, },
"version": { "version": {
"type": "float" "type": "float"