Highlight synonyms with multi_match cross_field search type

Elastic Stack Elasticsearch
1

Hi. I'm facing a problem with search highlight. When using cross_field type of search, the content returned in highlight does not consider synonyms.
Example:

"settings": {
    "index": {
        "analysis": {
            "analyzer": {
                "stemmer_search": {
					"filter": [
						"lowercase",
						"asciifolding",
						"brazilian_stemmer"
					],
					"type": "custom",
					"tokenizer": "standard"
				},
				"synonyms_search": {
					"filter": [
						"lowercase",
						"asciifolding",
						"search_synoym",
						"brazilian_stop",
						"brazilian_stemmer"
					],
					"type": "custom",
					"tokenizer": "standard"
				}
            },
            "filter": {
                "brazilian_stemmer": {
					"type": "stemmer",
					"language": "brazilian"
				},
				"search_synoym": {
					"type": "synonym_graph",
					"synonyms": [
						"car, red car, big car",
						"phone, iphone, tele phone"
						]
				},
				"brazilian_stop": {
					"type": "stop",
					"stopwords": [
					"a","agora","(...)"
					]
				}	
            }
        }
    }
},
"mappings": {
    "properties": {
        "title": {
            "type": "text",
            "search_analyzer": "synonyms_search",
			"analyzer": "stemmer_search"
        },
		"body": {
            "type": "text",
            "search_analyzer": "synonyms_search",
			"analyzer": "stemmer_search"
        }			
    }

Ps: I've commented part of stopword list

PUT http://localhost:9200/teste/_doc/1
{
"title":"The search for de car",
"body": "The boy was looking for something red"
}

PUT http://localhost:9200/teste/_doc/2
{
"title":"calling from the tele phone",
"body": "the guy in the big car use your motorola for calls"
}

Search:

     {
     "highlight": {
        "encoder": "html",
        "fields": {
            "title": {
                "order": "score",
                "type": "unified"
            },
            "body": {
                "order": "score",
                "type": "unified"
            }
        },
        "post_tags": [
            "]]]"
        ],
        "pre_tags": [
            "[[["
        ]
    },
    "query": {
        "multi_match": {
            "fields": [
                "title",
                "body"
            ],
            "minimum_should_match": "100%",
            "operator": "and",
            "query": "red car",
            "type": "cross_fields"
        }
    }
}

The result:

{
    "took": 75,
    "timed_out": false,
    "_shards": {
        "total": 1,
        "successful": 1,
        "skipped": 0,
        "failed": 0
    },
    "hits": {
        "total": {
            "value": 2,
            "relation": "eq"
        },
        "max_score": 1.9061548,
        "hits": [
            {
                "_index": "teste",
                "_type": "_doc",
                "_id": "2",
                "_score": 1.9061548,
                "_source": {
                    "title": "calling from the tele phone",
                    "body": "the guy in the big car use your motorola for calls"
                },
                "highlight": {
                    "body": [
                        "the guy in the [[[big]]] [[[car]]] use your motorola for calls"
                    ]
                }
            },
            {
                "_index": "teste",
                "_type": "_doc",
                "_id": "1",
                "_score": 0.6931472,
                "_source": {
                    "title": "The search for de car",
                    "body": "The boy was looking for something red"
                }
            }
        ]
    }
}

The first result highlighted a synonym, but the second don't. The word 'car' should be highlighted.
Any clue about this situation?
Thanks.

2

This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.