Changeset 1772


Ignore:
Timestamp:
2000-12-08T12:18:37+13:00 (23 years ago)
Author:
kjm18
Message:

removed Paragraph stuff - now only has Document and Section; added </Document>

tags at end of docs; the metadata fields that are indexed are written to

indexfields line in build.cfg

Location:
trunk/gsdl/perllib
Files:
2 edited

Legend:

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

    r1694 r1772  
    238238    } else {
    239239    if (!-e "$mg_passes_exe" ||
    240         !open (PIPEOUT, "| $mg_passes_exe -K Section -K Paragraph -T1 -I1 -d $fulltextprefix -f $basefilename")) {
     240        !open (PIPEOUT, "| $mg_passes_exe -K Section -T1 -I1 -d $fulltextprefix -f $basefilename")) {
    241241        die "mgppbuilder::compress_text - couldn't run $mg_passes_exe\n";
    242242    }
     
    284284    if (!$self->{'debug'}) {
    285285    if (!-e "$mg_passes_exe" ||
    286         !open ($handle, "| $mg_passes_exe -K Section -K Paragraph -d $fulltextprefix -f $basefilename -T2 -I2")) {
     286        !open ($handle, "| $mg_passes_exe -K Section -d $fulltextprefix -f $basefilename -T2 -I2")) {
    287287        die "mgppbuilder::compress_text - couldn't run $mg_passes_exe\n";
    288288    }
     
    360360    } else {
    361361    if (!-e "$mg_passes_exe" ||
    362         !open (PIPEOUT, "| $mg_passes_exe -K Section -K Paragraph -d $builddir -f $basefilename -T1")) {
     362        !open (PIPEOUT, "| $mg_passes_exe -K Section -d $builddir -f $basefilename -T1")) {
    363363        die "mgppbuilder::compress_text - couldn't run $mg_passes_exe\n";
    364364    }
     
    396396    if (!$self->{'debug'}) {
    397397        if (!-e "$mg_passes_exe" ||
    398         !open ($handle, "| $mg_passes_exe -K Section -K Paragraph -f $basefilename -d $builddir -T2")) {
     398        !open ($handle, "| $mg_passes_exe -K Section -f $basefilename -d $builddir -T2")) {
    399399        die "mgppbuilder::compress_text - couldn't run $mg_passes_exe\n";
    400400        }
     
    637637    } else {
    638638    if (!-e "$mg_passes_exe" ||
    639         !open (PIPEOUT, "| $mg_passes_exe -K Section -K Paragraph -d $builddir -f $basefilename -I1")) {
     639        !open (PIPEOUT, "| $mg_passes_exe -K Section -d $builddir -f $basefilename -I1")) {
    640640        die "mgppbuilder::build_index - couldn't run $mg_passes_exe\n";
    641641    }
     
    664664
    665665    if (!-e "$mg_passes_exe" ||
    666         !open ($handle, "| $mg_passes_exe -K Section -K Paragraph -d $builddir -f $basefilename -I2")) {
     666        !open ($handle, "| $mg_passes_exe -K Section -d $builddir -f $basefilename -I2")) {
    667667        die "mgppbuilder::build_index - couldn't run $mg_passes_exe\n";
    668668    }
     
    851851    $build_cfg->{'notbuilt'} = $self->{'notbuilt'};
    852852
     853
     854    #store the indexed field information
     855    foreach $field (sort keys %{$self->{'buildproc'}->{'indexfields'}}) {
     856   
     857    push (@{$build_cfg->{'indexfields'}}, $field);
     858    }
    853859    # write out the build information
    854860    &cfgread::write_cfg_file("$self->{'build_dir'}/build.cfg", $build_cfg,
    855861                 '^(builddate|buildtype|numdocs|numbytes)$',
    856                              '^(indexmap|subcollectionmap|languagemap|notbuilt)$');
     862                             '^(indexmap|subcollectionmap|languagemap|notbuilt|indexfields)$');
    857863
    858864}
  • trunk/gsdl/perllib/mgppbuildproc.pm

    r1694 r1772  
    6969
    7070    $self->{'indexing_text'} = 0;
     71    $self->{'indexfields'} = {};
    7172
    7273    return bless $self, $class;
     
    439440
    440441    my $doc_section = 0; # just for this document
    441     my $text = "<Document>\n";
     442    my $text = "";
     443    if ($self->{'num_docs'} == 1) {
     444    $text = "<Document>\n";
     445    }
     446    else {
     447    $text = "</Document><Document>\n";
     448    }
    442449    my $text_extra = "";
    443450
     
    459466            if ($real_field eq "text") {
    460467            #print STDERR "in text bit";
    461             $new_text = "<Paragraph>";
     468            #$new_text = "<Paragraph>";
    462469            $new_text .= $doc_obj->get_text ($section);
    463             $self->find_paragraphs($new_text);
     470            #$self->find_paragraphs($new_text);
    464471            } else { # metadata field
    465472            if ($real_field eq "metadata") { # insert all metadata
     
    474481                    $mfield !~ /^gsdl/ && defined $mvalue && $mvalue ne "") {
    475482                   
    476                     $new_text .= "<Paragraph><$mfield>$mvalue</$mfield>\n";
     483                    $new_text .= "<$mfield>$mvalue</$mfield>\n";
    477484                    #print STDERR "metadata=$mfield:$mvalue";
    478                    
     485                    if (!defined $self->{'indexfields'}->{$mfield}) {
     486                        $self->{'indexfields'}->{$mfield} = 1;
     487                    }                   
    479488                }
    480489                }
     
    482491            }
    483492            else { #individual metadata specified
     493                if (!defined $self->{'indexfields'}->{$real_field}) {
     494                $self->{'indexfields'}->{$real_field} = 1;
     495                }               
    484496                foreach $item (@{$doc_obj->get_metadata ($section, $real_field)}) {
    485                 $new_text .= "<Paragraph><$real_field>$item</$real_field>\n";
     497                $new_text .= "<$real_field>$item</$real_field>\n";
    486498                }
    487499            }
Note: See TracChangeset for help on using the changeset viewer.