jaro-similarity ( a b -- n )

Vocabulary

math.similarity

Inputs

a	an object
b	an object

Outputs

n

an object

Definition

USING: bit-arrays combinators.short-circuit kernel math
math.order sequences sequences.extras sequences.private ;

IN: math.similarity

:: jaro-similarity ( a b -- n )
    a b 2dup [ length ] bi@ 2dup < [ [ swap ] 2bi@ ] when
    :> ( str1 str2 len1 len2 ) len1 len2 max 2/ 1 [-]
    :> delta len2 <bit-array> :> flags str1 [| ch i |
        i delta [-] :> from i delta + 1 + len2 min :> to from to
        [ integer>fixnum-strict ] bi@ [| j |
            {
                [ j flags nth-unsafe not ]
                [ ch j str2 nth-unsafe = ]
            } 0&& dup [ t j flags set-nth-unsafe ] when
        ] find-integer-from
    ] filter-index :> matches matches
    [ 0 ] [
        length :> #matches 0 :> i! str2 flags [
            [ i matches nth-unsafe = not i 1 + i! ] [ drop f ]
            if
        ] 2count :> #transpositions #matches len1 /f
        #matches len2 /f + #matches #transpositions 2/ -
        #matches /f + 3 /
    ] if-empty ;