[elasticsearch笔记] _termvectors/_mtermvectors

重点

• 统计 term 相关数据
• ttf: total term frequency
• df: document frequency
• dc: document count
• term_freq: term 出现频率

_termvectors

PUT /twitter
{ "mappings": {
    "properties": {
      "text": {
        "type": "text",
        "term_vector": "with_positions_offsets_payloads",
        "store" : true,
        "analyzer" : "fulltext_analyzer"
       },
       "fullname": {
        "type": "text",
        "term_vector": "with_positions_offsets_payloads",
        "analyzer" : "fulltext_analyzer"
      }
    }
  },
  "settings" : {
    "index" : {
      "number_of_shards" : 1,
      "number_of_replicas" : 0
    },
    "analysis": {
      "analyzer": {
        "fulltext_analyzer": {
          "type": "custom",
          "tokenizer": "whitespace",
          "filter": [
            "lowercase",
            "type_as_payload"
          ]
        }
      }
    }
  }
}

PUT /twitter/_doc/1
{
  "fullname" : "John Doe",
  "text" : "twitter test test test "
}

PUT /twitter/_doc/2
{
  "fullname" : "Jane Doe",
  "text" : "Another twitter test ..."
}

GET /twitter/_termvectors/1
{
  "fields" : ["text"],
  "offsets" : true,
  "payloads" : true,
  "positions" : true,
  "term_statistics" : true,
  "field_statistics" : true
}

GET /twitter/_termvectors/1
{
  "fields" : ["text", "some_field_without_term_vectors"],
  "offsets" : true,
  "positions" : true,
  "term_statistics" : true,
  "field_statistics" : true
}

GET /twitter/_termvectors
{
  "doc" : {
    "fullname" : "John Doe",
    "text" : "twitter test test test"
  }
}

GET /twitter/_termvectors
{
  "doc" : {
    "fullname" : "John Doe",
    "text" : "twitter test test test"
  },
  "fields": ["fullname"],
  "per_field_analyzer" : {
    "fullname": "keyword"
  }
}

GET /twitter/_termvectors
{
  "doc": {
    "fullname": "When when when wealthy industrialist Tony Stark is forced to build an armored suit after a life-threatening incident, he ultimately decides to use its technology to fight against evil.",
    "text": "twitter test test test"
  },
  "fields": [
    "fullname"
  ],
  "per_field_analyzer": {
    "fullname": "custom"
  },
  "term_statistics": true,
  "field_statistics": true,
  "positions": false,
  "offsets": false,
  "filter": {
    "max_num_terms": 3,
    "min_term_freq": 2,
    "min_doc_freq": 1
  }
}

_mtermvectors

  POST /_mtermvectors
  {
     "docs": [
        {
           "_index": "twitter",
           "_id": "2",
           "term_statistics": true
        },
        {
           "_index": "twitter",
           "_id": "1",
           "fields": [
              "text"
           ]
        }
     ]
  }
  
  POST /twitter/_mtermvectors
  {
     "docs": [
        {
           "_id": "2",
           "fields": [
              "text"
           ],
           "term_statistics": true
        },
        {
           "_id": "1"
        }
     ]
  }
  
  POST /twitter/_mtermvectors
  {
      "ids" : ["1", "2"],
      "parameters": {
      	"fields": [
           	"text"
        	],
        	"term_statistics": true
      }
  }
  
  POST /_mtermvectors
  {
     "docs": [
        {
           "_index": "twitter",
           "doc" : {
              "fullname" : "John Doe",
              "text" : "twitter test test test"
           }
        },
        {
           "_index": "twitter",
           "doc" : {
             "fullname" : "Jane Doe",
             "text" : "Another twitter test ..."
           }
        }
     ]
  }