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

   1 #!/usr/bin/env lua
   2 --
   3 -- Index each paragraph of a text file as a Xapian document.
   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 -- Remove leading and trailing whitespace from a string
  25 function trim(s)
  26   return (s:gsub("^%s*(.-)%s*$", "%1"))
  27 end
  28
  29 -- Require one command line argument to mean the database directory
  30 if #arg ~= 1 then
  31         io.stderr:write("Usage: " .. arg[0] .. " PATH_TO_DATABASE\n")
  32         os.exit()
  33 end
  34
  35 -- Open the database for update, creating a new database if necessary.
  36 database = xapian.WritableDatabase(arg[1], xapian.DB_CREATE_OR_OPEN)
  37
  38
  39 indexer = xapian.TermGenerator()
  40 stemmer = xapian.Stem("english")
  41 indexer:set_stemmer(stemmer)
  42
  43 -- Read document data from standard input line.
  44 -- An empty line means the end of a doc and the start of another doc
  45 local para = ''
  46 for line in io.lines() do
  47         if line == nil then
  48                 break
  49         end
  50
  51         line = trim(line)
  52         if line == '' then
  53                 if para ~= '' then
  54
  55                         -- We've reached the end of a paragraph, so index it.
  56                         doc = xapian.Document()
  57                         doc:set_data(para)
  58
  59                         indexer:set_document(doc)
  60                         indexer:index_text(para)
  61
  62                         -- Add the document to the database.
  63                         database:add_document(doc)
  64                         para = ''
  65                 end
  66         else
  67                 if para ~= '' then
  68                         para = para .. ' '
  69                 end
  70                 para = para .. line
  71         end
  72 end