Query processor and index

Query processor - supported operations

Query is a JSON structure (object or array) made of query operations, set operations and sub-queries.

Here is the comprehensive list of all supported query operations:

Document ID number as string	No operation, the ID number goes to result
"all"	Return all document IDs (slow!)
{"eq": #, "in": [#], "limit": #}	Index value lookup
{"int-from": #, "int-to": #, "in": [#], "limit": #}	Hash lookup over a range of integers
{"has": [#], "limit": #}	Return all documents that has the attribute set (not null)
[sub-query1, sub-query2..]	Evaluate union of sub-query results.
{"n": [sub-query1, sub-query2..]}	Evaluate intersection of sub-query results.
{"c": [sub-query1, sub-query2..]}	Evaluate complement of sub-query results.

limit is optional.

Lookup queries

Indexes works on a "path" - a series of attribute names locating the indexed value, for example, path a,b,c will locate value 1 in document {"a": {"b": {"c": 1}}}.

If the index path visits or ultimately leads to an array of values, every value element will be indexed and a lookup query will match any value in the array. For example, an index on "Name,Pen Name" will index all of "John", "David", "Joshua" in the following document:

{ "Name: [
    {"Pen Name": [ "John", "David" ]},
    {"Pen Name": "Joshua"}
] }

Index must be available before carrying out lookup queries.

Index assisted range queries

tiedot supports a special case of range query - integer range lookup, which is essentially a batch of hash table lookups.

Better range query support will be introduced in later releases with help from another type of index.