3

This playground example shows (or correct me if I’m doing something wrong) that unigrams are not emitted by shingle filter

Index:

{
  "analyzer": "my-analyzer",
  "searchAnalyzer": "lucene.keyword",
  "mappings": {
    "dynamic": true
  },
  "analyzers": [    
    {
      "charFilters": [],
      "name": "my-analyzer",
      "tokenFilters": [ { "type": "trim" }, { "type": "lowercase"},
        {
          "minShingleSize": 2,
          "maxShingleSize": 5,
          "type": "shingle"
        }
      ],
      "tokenizer": {  "maxTokenLength": 100,   "type": "whitespace" }
    }
  ]
}

Data:

[
  {
    "value": "marry"
  },
  {
    "value": "marry had a little lamb"
  },
]

Searches:

[
  {
    $search: {
      index: "default",
      text: {
        query: "marry had",
        path: {
          wildcard: "*"
        }
      }
    }
  }
]

→ one document found

[
  {
    $search: {
      index: "default",
      text: {
        query: "had a little lamb",
        path: {
          wildcard: "*"
        }
      }
    }
  }
]

→ one document found

[
  {
    $search: {
      index: "default",
      text: {
        query: "marry",
        path: {
          wildcard: "*"
        }
      }
    }
  }
]

→ no documents found
so it seems that unigrams are not in the index