Span field masking query

Wrapper to allow span queries to participate in composite single-field span queries by lying about their search field.

This can be used to support queries like span-near or span-or across different fields, which is not ordinarily permitted.

Span field masking query is invaluable in conjunction with multi-fields when same content is indexed with multiple analyzers. For instance, we could index a field with the standard analyzer which breaks text up into words, and again with the english analyzer which stems words into their root form.

Example:

resp = client.search(
    query={
        "span_near": {
            "clauses": [
                {
                    "span_term": {
                        "text": "quick brown"
                    }
                },
                {
                    "span_field_masking": {
                        "query": {
                            "span_term": {
                                "text.stems": "fox"
                            }
                        },
                        "field": "text"
                    }
                }
            ],
            "slop": 5,
            "in_order": False
        }
    },
    highlight={
        "require_field_match": False,
        "fields": {
            "*": {}
        }
    },
)
print(resp)

response = client.search(
  body: {
    query: {
      span_near: {
        clauses: [
          {
            span_term: {
              text: 'quick brown'
            }
          },
          {
            span_field_masking: {
              query: {
                span_term: {
                  'text.stems' => 'fox'
                }
              },
              field: 'text'
            }
          }
        ],
        slop: 5,
        in_order: false
      }
    },
    highlight: {
      require_field_match: false,
      fields: {
        "*": {}
      }
    }
  }
)
puts response

const response = await client.search({
  query: {
    span_near: {
      clauses: [
        {
          span_term: {
            text: "quick brown",
          },
        },
        {
          span_field_masking: {
            query: {
              span_term: {
                "text.stems": "fox",
              },
            },
            field: "text",
          },
        },
      ],
      slop: 5,
      in_order: false,
    },
  },
  highlight: {
    require_field_match: false,
    fields: {
      "*": {},
    },
  },
});
console.log(response);

GET /_search
{
  "query": {
    "span_near": {
      "clauses": [
        {
          "span_term": {
            "text": "quick brown"
          }
        },
        {
          "span_field_masking": {
            "query": {
              "span_term": {
                "text.stems": "fox" 
              }
            },
            "field": "text" 
          }
        }
      ],
      "slop": 5,
      "in_order": false
    }
  },
  "highlight": {
    "require_field_match" : false, 
    "fields": {
      "*": {}
    }
  }
}

Note: span_field_masking query may have unexpected scoring and highlighting behaviour. This is because the query returns and highlights the masked field, but scoring and highlighting are done using the terms statistics and offsets of the original field.

Note: For highlighting to work the parameter: require_field_match should be set to false on the highlighter.