[popfile-commit] engine/Classifier Bayes.pm,1.193,1.194

[<jgr...@us...>]

Update of /cvsroot/popfile/engine/Classifier
In directory sc8-pr-cvs1:/tmp/cvs-serv21095/Classifier

Modified Files:
	Bayes.pm 
Log Message:
Add new get_bucket_word_prefixesd API and use it to make the viewing of the contents of an individual bucket work; this completes the core features for v0.20.0.

Index: Bayes.pm
===================================================================
RCS file: /cvsroot/popfile/engine/Classifier/Bayes.pm,v
retrieving revision 1.193
retrieving revision 1.194
diff -C2 -d -r1.193 -r1.194
*** Bayes.pm	10 Sep 2003 18:31:39 -0000	1.193
--- Bayes.pm	10 Sep 2003 22:33:57 -0000	1.194
***************
*** 68,71 ****
--- 68,72 ----
      # Matrix of buckets, words and the word counts
      $self->{matrix__}            = {};
+     $self->{db__}                = {};
  
      # Total number of words in all buckets
***************
*** 295,298 ****
--- 296,300 ----
          untie %{$self->{matrix__}{$bucket}};
          delete $self->{matrix__}{$bucket};
+         delete $self->{db__}{$bucket};
      }
  }
***************
*** 614,620 ****
      # tied hash from it thus performing an automatic upgrade.
  
!     tie %{$self->{matrix__}{$bucket}}, "BerkeleyDB::Hash",
!             -Filename => $self->config_( 'corpus' ) . "/$bucket/table.db",
!             -Flags    => DB_CREATE;
  
      if ( !defined( $self->get_bucket_word_count( $bucket ) ) ) {
--- 616,622 ----
      # tied hash from it thus performing an automatic upgrade.
  
!     $self->{db__}{$bucket} = tie %{$self->{matrix__}{$bucket}}, "BerkeleyDB::Hash",
!                                  -Filename => $self->config_( 'corpus' ) . "/$bucket/table.db",
!                                  -Flags    => DB_CREATE;
  
      if ( !defined( $self->get_bucket_word_count( $bucket ) ) ) {
***************
*** 1435,1461 ****
  # get_bucket_word_list
  #
! # Returns a list of bucket entries, each entry corresponds to all the words with the
! # same leading character
  #
  # $bucket      The name of the bucket for which the word count is desired
  #
  # ---------------------------------------------------------------------------------------------
  sub get_bucket_word_list
  {
!     my ( $self, $bucket ) = @_;
! 
!     my @result;
  
!     if ( $self->get_bucket_word_count( $bucket ) > 0 ) {
! # TODO        my @entries = @{$self->{matrix__}{$bucket}};
  
! # TODO        for my $i (0..$#entries) {
! # TODO            if ( defined( $entries[$i] ) && ( $entries[$i] ne '' ) ) {
! # TODO                push @result, ($entries[$i]);
! # TODO            }
! # TODO        }
!     }
  
!     return @result;
  }
  
--- 1437,1468 ----
  # get_bucket_word_list
  #
! # Returns a list of words all with the same first character
  #
  # $bucket      The name of the bucket for which the word count is desired
+ # $prefix      The first character of the words
  #
  # ---------------------------------------------------------------------------------------------
  sub get_bucket_word_list
  {
!     my ( $self, $bucket, $prefix ) = @_;
  
!     return grep {/^$prefix/} keys %{$self->{matrix__}{$bucket}};
! }
  
! # ---------------------------------------------------------------------------------------------
! #
! # get_bucket_word_prefixes
! #
! # Returns a list of all the initial letters of words in a bucket
! #
! # $bucket      The name of the bucket for which the word count is desired
! #
! # ---------------------------------------------------------------------------------------------
! sub get_bucket_word_prefixes
! {
!     my ( $self, $bucket ) = @_;
  
!     my $prev = '';
!     return grep {$_ ne $prev && ($prev = $_, 1)} sort map {substr($_,0,1)} keys %{$self->{matrix__}{$bucket}};
  }