xapian-bindings/tcl8/docs/examples/simpleindex.tcl

   1 #!/usr/bin/env tclsh
   2 # Tcl script to index each paragraph of a text file as a Xapian document.
   3 #
   4 # Copyright (C) 2004,2006,2007,2009 Olly Betts
   5 # Copyright (C) 2004 Michael Schlenker
   6 #
   7 # This program is free software; you can redistribute it and/or modify
   8 # it under the terms of the GNU General Public License as published by
   9 # the Free Software Foundation; either version 2 of the License, or
  10 # (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 USA
  20
  21 # We need at least Xapian 1.0.0 for TermGenerator.
  22 package require xapian 1.0.0
  23
  24 if {[llength $argv] != 1} {
  25     puts "Usage: $argv0 PATH_TO_DATABASE"
  26     exit 1
  27 }
  28
  29 if {[catch {
  30     set dbpath [lindex $argv 0]
  31     xapian::WritableDatabase database $dbpath $xapian::DB_CREATE_OR_OPEN
  32     xapian::TermGenerator indexer
  33     xapian::Stem stemmer "english"
  34     indexer set_stemmer stemmer
  35
  36     set para ""
  37     while {![eof stdin]} {
  38         gets stdin line
  39         set line [string trim $line]
  40         if {[string equal $line ""] && [string compare $para ""]} {
  41             # We've reached the end of a paragraph, so index it.
  42             xapian::Document doc
  43             doc set_data $para
  44
  45             indexer set_document doc
  46             indexer index_text $para
  47
  48             # Add the document to the database.
  49             database add_document doc
  50             set para ""
  51         } else {
  52             if {[string equal $para ""]} {
  53                 set para $line
  54             } else {
  55                 set para "$para $line"
  56             }
  57         }
  58     }
  59     # We *must* delete the database so that the destructor gets called so
  60     # pending changes are committed and the lock file is removed.
  61     database -delete
  62 } exception]} {
  63     puts stderr "Exception: $errorCode $exception"
  64     exit 1
  65 }