search-xapian/Xapian/TermGenerator.pm

   1 package Search::Xapian::TermGenerator;
   2
   3 use 5.006;
   4 use strict;
   5 use warnings;
   6
   7 require DynaLoader;
   8
   9 our @ISA = qw(DynaLoader);
  10
  11 # Preloaded methods go here.
  12
  13 # In a new thread, copy objects of this class to unblessed, undef values.
  14 sub CLONE_SKIP { 1 }
  15
  16 use overload '='  => sub { $_[0]->clone() },
  17              'fallback' => 1;
  18
  19 sub clone() {
  20   my $self = shift;
  21   my $class = ref( $self );
  22   my $copy = new2( $self );
  23   bless $copy, $class;
  24   return $copy;
  25 }
  26
  27 sub new() {
  28   my $class = shift;
  29   my $tg = new0();
  30
  31   bless $tg, $class;
  32
  33   return $tg;
  34 }
  35
  36 1;
  37
  38 __END__
  39
  40 =head1 NAME
  41
  42 Search::Xapian::TermGenerator - Parses a piece of text and generates terms.
  43
  44 =head1 DESCRIPTION
  45
  46 This module takes a piece of text and parses it to produce words which are
  47 then used to generate suitable terms for indexing.  The terms generated
  48 are suitable for use with L<Search::Xapian::Query> objects produced by the
  49 L<Search::Xapian::QueryParser> class.
  50
  51 =head1 SYNOPSIS
  52
  53   use Search::Xapian;
  54
  55   my $doc = new Search::Xapian::Document();
  56   my $tg = new Search::Xapian::TermGenerator();
  57   $tg->set_stemmer(new Search::Xapian::Stem("english"));
  58   $tg->set_document($doc);
  59   $tg->index_text("The cat sat on the mat");
  60
  61 =head1 METHODS
  62
  63 =over 4
  64
  65 =item new
  66
  67 TermGenerator constructor.
  68
  69 =item set_stemmer <stemmer>
  70
  71 Set the L<Search::Xapian::Stem> object to be used for generating stemmed terms.
  72
  73 =item set_stopper <stopper>
  74
  75 Set the L<Search::Xapian::Stopper> object to be used for identifying stopwords.
  76
  77 =item set_document <document>
  78
  79 Set the L<Search::Xapian::Document> object to index terms into.
  80
  81 =item get_document <document>
  82
  83 Get the currently set L<Search::Xapian::Document> object.
  84
  85 =item index_text <text> [<wdf_inc> [<prefix>]]
  86
  87 Indexes the text in string <text>.  The optional parameter <wdf_inc> sets the
  88 wdf increment (default 1).  The optional parameter <prefix> sets the term
  89 prefix to use (default is no prefix).
  90
  91 =item index_text_without_positions <text> [<wdf_inc> [<prefix>]]
  92
  93 Just like index_text, but no positional information is generated.  This means
  94 that the database will be significantly smaller, but that phrase searching
  95 and NEAR won't be supported.
  96
  97 =item increase_termpos [<delta>]
  98
  99 Increase the termpos used by index_text by <delta> (default 100).
 100
 101 This can be used to prevent phrase searches from spanning two
 102 unconnected blocks of text (e.g. the title and body text).
 103
 104 =item get_termpos
 105
 106 Get the current term position.
 107
 108 =item set_termpos <termpos>
 109
 110 Set the current term position.
 111
 112 =item get_description
 113
 114 Return a description of this object.
 115
 116 =back
 117
 118 =head1 REFERENCE
 119
 120   https://xapian.org/docs/sourcedoc/html/classXapian_1_1TermGenerator.html
 121
 122 =cut