Changeset 1917

Show
Ignore:
Timestamp:
07.02.2001 13:09:29 (19 years ago)
Author:
kjm18
Message:

minor changes

Location:
trunk/gsdl/perllib
Files:
2 modified

Legend:

Unmodified
Added
Removed
  • trunk/gsdl/perllib/mgppbuilder.pm

    r1852 r1917  
    135135    } 
    136136 
     137    # make sure that the same index isn't specified more than once 
     138    my %tmphash = (); 
     139    my @tmparray = @{$self->{'collect_cfg'}->{'indexes'}}; 
     140    $self->{'collect_cfg'}->{'indexes'} = []; 
     141    foreach my $i (@tmparray) { 
     142    if (!defined ($tmphash{$i})) { 
     143        push (@{$self->{'collect_cfg'}->{'indexes'}}, $i); 
     144        $tmphash{$i} = 1; 
     145    } 
     146    } 
     147 
     148 
    137149    # get the levels (Section, Paragraph) for indexing and compression 
    138150    $self->{'levels'} = {}; 
     
    150162     
    151163    # load all the plugins 
    152     $self->{'pluginfo'} = &plugin::load_plugins ($plugins); 
     164    $self->{'pluginfo'} = &plugin::load_plugins ($plugins, $verbosity, $outhandle); 
    153165    if (scalar(@{$self->{'pluginfo'}}) == 0) { 
    154166    print $outhandle "No plugins were loaded.\n"; 
     
    163175     
    164176    # load all the classifiers 
    165     $self->{'classifiers'} = &classify::load_classifiers ($classifiers, $outhandle); 
     177    $self->{'classifiers'} = &classify::load_classifiers ($classifiers, $build_dir, $outhandle); 
    166178 
    167179    # load up any dontgdbm fields 
  • trunk/gsdl/perllib/mgppbuildproc.pm

    r1852 r1917  
    324324    # output all the section metadata 
    325325    my $metadata = $doc_obj->get_all_metadata ($section); 
    326     foreach $pair (@$metadata) { 
     326    foreach my $pair (@$metadata) { 
    327327        my ($field, $value) = (@$pair); 
    328328 
     
    482482 
    483483    # see if this document belongs to this subcollection 
    484     foreach $indexexp (@{$self->{'indexexparr'}}) { 
     484    foreach my $indexexp (@{$self->{'indexexparr'}}) { 
    485485    $indexed_doc = 0; 
    486486    my ($field, $exp, $options) = split /\//, $indexexp; 
     
    525525    } 
    526526    my $doc_section = 0; # just for this document 
    527     my $text = ""; 
    528     if ($self->{'num_docs'} == 1) { 
    529     $text = "<Document>\n"; 
    530     } 
    531     else { 
    532     $text = "</Document><Document>\n"; 
    533     } 
    534     my $text_extra = ""; 
    535  
     527    my $text = "<Document>\n"; 
     528    
    536529    # get the text for this document 
    537530    my $section = $doc_obj->get_top_section(); 
     
    544537    if ($indexed_doc) { 
    545538        $self->{'num_bytes'} += $doc_obj->get_text_length ($section); 
    546         foreach $field (split (/,/, $fields)) { 
     539        foreach my $field (split (/,/, $fields)) { 
    547540        # only deal with this field if it doesn't start with top or 
    548541        # this is the first section 
     
    618611            $self->filter_text ($field, $new_text); 
    619612 
    620             #???????????????????? 
    621             if ($self->{'indexing_text'} &&  
    622             $new_text =~ /[\(\)\{\}]/) { 
    623             } 
    624613            $self->{'num_processed_bytes'} += length ($new_text); 
    625614            $text .= "$new_text"; 
     
    630619    $section = $doc_obj->get_next_section($section); 
    631620    } #while defined section 
    632     print $handle "$text";  
     621    print $handle "$text\n</Document>\n";  
    633622} 
    634623