Elasticsearch术语聚合和匹配项

Question

有没有一种方法可以获得索引中最常用的单词列表以及这些单词出现的记录？

顺便说一句。如果我没有在查询中请求hits，有没有办法从聚合结果中去掉它？

我使用的是Elasticsearch 7.4.0。

示例查询：

POST text-analysis/_search
{
    "aggs" : {
        "most_common_words" : {
            "terms": {
                "field" : "sentence"
            }
        }
    }
}

响应：

{
    "took": 5,
    "timed_out": false,
    "_shards": {
        "total": 1,
        "successful": 1,
        "skipped": 0,
        "failed": 0
    },
    "hits": {
        "total": {
            "value": 63,
            "relation": "eq"
        },
        "max_score": 1.0,
        "hits": [
            {
                "_index": "text-analysis",
                "_type": "_doc",
                "_id": "T64Nvm4BAE1yJwCxLvwo",
                "_score": 1.0,
                "_source": {
                    "data_set": "lorem_ipsum",
                    "sentence": "Lorem ipsum dolor sit amet, consectetur adipiscing elit."
                }
            },
            {
                "_index": "text-analysis",
                "_type": "_doc",
                "_id": "UK4Nvm4BAE1yJwCxLvwx",
                "_score": 1.0,
                "_source": {
                    "data_set": "lorem_ipsum",
                    "sentence": "Nam sodales justo eget varius blandit."
                }
            },
            {
                "_index": "text-analysis",
                "_type": "_doc",
                "_id": "Ua4Nvm4BAE1yJwCxLvw1",
                "_score": 1.0,
                "_source": {
                    "data_set": "lorem_ipsum",
                    "sentence": "Fusce velit erat, molestie nec varius et, semper quis arcu."
                }
            },
            {
                "_index": "text-analysis",
                "_type": "_doc",
                "_id": "Uq4Nvm4BAE1yJwCxLvw5",
                "_score": 1.0,
                "_source": {
                    "data_set": "lorem_ipsum",
                    "sentence": "Quisque maximus porta purus at dignissim."
                }
            },
            {
                "_index": "text-analysis",
                "_type": "_doc",
                "_id": "U64Nvm4BAE1yJwCxLvw8",
                "_score": 1.0,
                "_source": {
                    "data_set": "lorem_ipsum",
                    "sentence": "Donec blandit ipsum mauris, ornare aliquam mauris malesuada et."
                }
            },
            {
                "_index": "text-analysis",
                "_type": "_doc",
                "_id": "VK4Nvm4BAE1yJwCxLvw_",
                "_score": 1.0,
                "_source": {
                    "data_set": "lorem_ipsum",
                    "sentence": "Sed et venenatis nibh."
                }
            },
            {
                "_index": "text-analysis",
                "_type": "_doc",
                "_id": "Va4Nvm4BAE1yJwCxLvxD",
                "_score": 1.0,
                "_source": {
                    "data_set": "lorem_ipsum",
                    "sentence": "Aliquam semper, lorem et commodo cursus, quam turpis commodo sem, eget aliquet est mi in nibh."
                }
            },
            {
                "_index": "text-analysis",
                "_type": "_doc",
                "_id": "Vq4Nvm4BAE1yJwCxLvxG",
                "_score": 1.0,
                "_source": {
                    "data_set": "lorem_ipsum",
                    "sentence": "Maecenas metus diam, volutpat pharetra elit consequat, posuere pretium nisi."
                }
            },
            {
                "_index": "text-analysis",
                "_type": "_doc",
                "_id": "V64Nvm4BAE1yJwCxLvxJ",
                "_score": 1.0,
                "_source": {
                    "data_set": "lorem_ipsum",
                    "sentence": "Nam sem ligula, laoreet varius viverra quis, tincidunt id dui."
                }
            },
            {
                "_index": "text-analysis",
                "_type": "_doc",
                "_id": "WK4Nvm4BAE1yJwCxLvxL",
                "_score": 1.0,
                "_source": {
                    "data_set": "lorem_ipsum",
                    "sentence": "Integer tempor pulvinar mi, ut dignissim erat blandit et."
                }
            }
        ]
    },
    "aggregations": {
        "most_common_words": {
            "doc_count_error_upper_bound": 0,
            "sum_other_doc_count": 425,
            "buckets": [
                {
                    "key": "et",
                    "doc_count": 11
                },
                {
                    "key": "nec",
                    "doc_count": 11
                },
                {
                    "key": "ut",
                    "doc_count": 11
                },
                {
                    "key": "eget",
                    "doc_count": 9
                },
                {
                    "key": "sed",
                    "doc_count": 9
                },
                {
                    "key": "aliquam",
                    "doc_count": 8
                },
                {
                    "key": "est",
                    "doc_count": 8
                },
                {
                    "key": "in",
                    "doc_count": 8
                },
                {
                    "key": "molestie",
                    "doc_count": 8
                },
                {
                    "key": "quis",
                    "doc_count": 8
                }
            ]
        }
    }
}

预期响应：

{
    "aggregations": {
        "most_common_words": {
            "doc_count_error_upper_bound": 0,
            "sum_other_doc_count": 425,
            "buckets": [
                {
                    "key": "et",
                    "doc_count": 11,
                    "occurrences": [
                        "A sentence with word et in it.",
                        "A sentence with word et in it.",
                        "A sentence with word et in it.",
                        "A sentence with word et in it.",
                        "A sentence with word et in it.",
                        "A sentence with word et in it.",
                        "A sentence with word et in it.",
                        "A sentence with word et in it.",
                        "A sentence with word et in it.",
                        "A sentence with word et in it.",
                        "A sentence with word et in it."
                    ]
                },
                {
                    "key": "nec",
                    "doc_count": 11,
                    "occurrences": [
                        "A sentence with word nec in it.",
                        "A sentence with word nec in it.",
                        "A sentence with word nec in it.",
                        "A sentence with word nec in it.",
                        "A sentence with word nec in it.",
                        "A sentence with word nec in it.",
                        "A sentence with word nec in it.",
                        "A sentence with word nec in it.",
                        "A sentence with word nec in it.",
                        "A sentence with word nec in it.",
                        "A sentence with word nec in it."
                    ]
                }
                ...
            ]
        }
    }

Answer 1

使用size:0，你不会在你的结果中得到命中。

POST text-analysis/_search
{
    "size":0,
    "aggs" : {
        "most_common_words" : {
            "terms": {
                "field" : "sentence"
            }
        }
    }
}