xapian-bindings/lua/docs/examples/simpleexpand.lua

   1 #!/usr/bin/env lua
   2 --
   3 -- Simple example script demonstrating query expansion.
   4 --
   5 -- Copyright (C) 2011 Xiaona Han
   6 --
   7 -- This program is free software; you can redistribute it and/or
   8 -- modify it under the terms of the GNU General Public License as
   9 -- published by the Free Software Foundation; either version 2 of the
  10 -- License, or (at your option) any later version.
  11 --
  12 -- This program is distributed in the hope that it will be useful,
  13 -- but WITHOUT ANY WARRANTY; without even the implied warranty of
  14 -- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  15 -- GNU General Public License for more details.
  16 --
  17 -- You should have received a copy of the GNU General Public License
  18 -- along with this program; if not, write to the Free Software
  19 -- Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301
  20 -- USA
  21
  22 require("xapian")
  23
  24 -- Require at least two command line arguments.
  25 if #arg < 2 then
  26         io.stderr:write("Usage:" .. arg[0] .. " PATH_TO_DATABASE QUERY [-- [DOCID...]]\n")
  27         os.exit()
  28 end
  29
  30 -- Open the database for searching.
  31 database = xapian.Database(arg[1])
  32
  33 -- Start an enquire session.
  34 enquire = xapian.Enquire(database)
  35
  36 -- Combine command line arguments up to "--" with spaces between
  37 -- them, so that simple queries don't have to be quoted at the shell level.
  38 query_string = arg[2]
  39 local index = 3
  40 while index <= #arg do
  41         local para = arg[index]
  42         index = index + 1;
  43         if para == '--' then
  44                 break
  45         end
  46         query_string = query_string .. ' ' .. para
  47 end
  48
  49 -- Create an RSet with the listed docids in.
  50 reldocs = xapian.RSet()
  51
  52 --for index in range(index, #arg) do
  53 for i = index, #arg do
  54         reldocs:add_document(tonumber(arg[index]))
  55         index = index + 1
  56 end
  57
  58 -- Parse the query string to produce a Xapian::Query object.
  59 qp = xapian.QueryParser()
  60 stemmer = xapian.Stem("english")
  61 qp:set_stemmer(stemmer)
  62 qp:set_database(database)
  63 qp:set_stemming_strategy(xapian.QueryParser_STEM_SOME)
  64 query = qp:parse_query(query_string)
  65
  66 if not query:empty() then
  67         print("Parsed query is: " .. tostring(query))
  68
  69         -- Find the top 10 results for the query.
  70         enquire:set_query(query)
  71         matches = enquire:get_mset(0, 10)
  72
  73         -- Display the size of the results.
  74         print(string.format("%i results found.", matches:get_matches_estimated()))
  75         print(string.format("Results 1-%i:", matches:size()))
  76
  77         -- Display the results
  78         for m in matches:items() do
  79                 print(m:get_rank() + 1, m:get_percent() .. "%", m:get_docid(), m:get_document():get_data())
  80         end
  81
  82         -- Put the top 5 (at most) docs into the rset if rset is empty
  83         if reldocs:empty() then
  84                 local c = 5
  85                 for m in matches:items() do
  86                         reldocs:add_document(m:get_docid())
  87                         print (c)
  88                         c = c - 1
  89                         if c == 0 then
  90                                 break
  91                         end
  92                 end
  93         end
  94
  95         -- Get the suggested expand terms
  96         eterms = enquire:get_eset(10, reldocs)
  97         print (string.format("%i suggested additional terms", eterms:size()))
  98         for m in eterms:terms() do
  99                 print(string.format("%s: %f", m:get_term(), m:get_weight()))
 100         end
 101
 102 end