Análise de consultas, parte 2: ajustando o sistema

1
"compound": {
2
  "should": [
3
    {
4
      "text": {
5
        "query": "purple rain",
6
        "path": "title",
7
        "score": {
8
          "boost": {
9
            "value": 3.0
10
          }
11
        }
12
      }
13
    },
14
    {
15
      "text": {
16
        "query": "purple rain",
17
        "path": "cast",
18
        "score": {
19
          "boost": {
20
            "value": 2.0
21
           }
22
        }
23
      }
24
    },
25
    {
26
      "text": {
27
        "query": "purple rain",
28
        "path": "plot",
29
        "score": {
30
          "boost": {
31
            "value": 1.0
32
          }
33
        }
34
      }
35
    },
36
    {
37
      "phrase": {
38
        "query": "purple rain",
39
        "path": [
40
          "title",
41
          "phrase",
42
          "cast"
43
        ],
44
        "score": {
45
          "boost": {
46
            "value": 11.0
47
          }
48
        }
49
      }
50
    }
51
  ]
52
}

1
"title": [
2
  {
3
    "foldDiacritics": false,
4
    "maxGrams": 7,
5
    "minGrams": 3,
6
    "tokenization": "nGram",
7
    "type": "autocomplete"
8
  },
9
  {
10
    "multi": {
11
      "english": {
12
        "analyzer": "lucene.english",
13
        "type": "string"
14
      },
15
      "phonetic": {
16
        "analyzer": "custom.phonetic",
17
        "type": "string"
18
      },
19
      "shingles": {
20
        "analyzer": "custom.shingles",
21
        "type": "string"
22
      }
23
    },
24
  "type": "string"
25
}

1
"analyzers": [
2
  {
3
    "charFilters": [],
4
    "name": "standard.shingles",
5
    "tokenFilters": [
6
      {
7
        "type": "lowercase"
8
      },
9
      {
10
        "maxShingleSize": 3,
11
        "minShingleSize": 2,
12
        "type": "shingle"
13
      }
14
    ],
15
    "tokenizer": {
16
      "type": "standard"
17
    }
18
  },
19
  {
20
    "name": "phonetic",
21
    "tokenFilters": [
22
      {
23
        "originalTokens": "include",
24
        "type": "daitchMokotoffSoundex"
25
      }
26
    ],
27
    "tokenizer": {
28
      "type": "standard"
29
    }
30
  }
31
]

1
$search: {	
2
  "text": {
3
    "query": "kat in the hat",
4
    "path": { "value": "title", "multi": "custom.phonetic" }
5
  }
6
}

1
{
2
  $search: {
3
    "tracking": {
4
      "searchTerms": "<query to track>"
5
    }
6
  }
7
}

1
SearchOptions opts = SearchOptions.searchOptions()
2
   .option("scoreDetails", BsonBoolean.TRUE)
3
   .option("tracking", new Document("searchTerms", query_string));