blob: d1a42fb1c2b5562d04eb02c53b8586b4156ba800 [file] [log] [blame]
Akron5f9091c2017-03-24 20:37:35 +01001package Krawfish::Corpus::Distribution;
2use strict;
3use warnings;
4
5# TODO:
6# distr([1:3], 'author:Goethe', 'author:Schiller')
7#
8# Go through both queries and buffer them.
9# Once the first buffer has a position >= 1 and the
10# second query has a position >= 3, release both
11# buffers in document order (aka do an or-query)
12# in the requested ratio.
13#
14# In the worst case, this means that one of the
15# queries will be completely buffered, while the other
16# has only a few entries, making most of the buffered elements
17# rendered useless.
18# However - the strategy described above means,
19# that there may be a lot elements missing, so it may be usefull to
20# buffer the query with the lowest freq first and then go through
21# the other one with mild skips.
22#
23# However - in case skips are not available,
24# this may be slow ...
25
261;