Changeset 22565 for main/trunk/greenstone2/perllib/plugins/PagedImagePlugin.pm

Timestamp:

2010-08-04T14:01:35+12:00 (13 years ago)

Author:

kjdon

Message:

removed block exp. now it scans the item file to work out which files to block

File:

• main/trunk/greenstone2/perllib/plugins/PagedImagePlugin.pm (modified) (5 diffs)

main/trunk/greenstone2/perllib/plugins/PagedImagePlugin.pm

@@ -157 +157 @@
     'deft' => &get_default_process_exp(),
     'reqd' => "no" },
-      { 'name' => "block_exp",
-    'desc' => "{BasePlugin.block_exp}",
-    'type' => "string",
-    'deft' => &get_default_block_exp(),
-    'reqd' => "no" },
       { 'name' => "title_sub",
     'desc' => "{HTMLPlugin.title_sub}",
@@ -248 +243 @@
 
 
-# want to block everything except the .item ones 
-# but instead we will block images and txt files
-sub get_default_block_exp {
-    my $self = shift (@_);
-    
-    return q^(?i)(\.jpe?g|\.gif|\.png|\.tif?f|\.te?xt|\.html?|~)$^
-###    return q^(?i)(\.jpe?g|\.gif|\.png|\.tif?f|\.te?xt|\.html?|\.css|\.opd|\.pdf|~)$^
-}
-
-
 # want to use BasePlugin's version of this, not ReadXMLFile's
 sub can_process_this_file {
     my $self = shift(@_);
-    
     return $self->BasePlugin::can_process_this_file(@_);
+}
+
+# instead of a block exp, now we scan the file and record all text and img files mentioned there for blocking.
+sub store_block_files
+{
+    my $self = shift (@_);
+    my ($filename_full_path, $block_hash) = @_;
+
+    my $xml_version = $self->is_xml_item_file($filename_full_path);
+    
+    # do we need to do this? if we do it here, then don't need to do it later
+    $self->tidy_item_file($filename_full_path);
+
+    my ($dir, $file) = $filename_full_path =~ /^(.*?)([^\/\\]*)$/;
+    if ($xml_version) {
+
+    # do something
+    $self->scan_xml_for_files_to_block($filename_full_path, $dir, $block_hash);
+    } else {
+    
+    $self->scan_item_for_files_to_block($filename_full_path, $dir, $block_hash);
+    }
+    
 }
 
@@ -294 +301 @@
     my $xml_version = $self->is_xml_item_file($filename_full_path);
 
-    $self->tidy_item_file($filename_full_path);
+    # have done this already in store_block_files
+    #$self->tidy_item_file($filename_full_path);
     
     my $doc_obj;
@@ -552 +560 @@
 }
 
+sub scan_xml_for_files_to_block
+{
+    my $self = shift (@_);
+    my ($filename_full_path, $dir, $block_hash) = @_;
+
+    open (ITEMFILE, $filename_full_path) || die "couldn't open $filename_full_path to work out which files to block\n";
+    my $line = "";
+    while (defined ($line = <ITEMFILE>)) {
+    next unless $line =~ /\w/;
+
+    if ($line =~ /imgfile=\"([^\"]+)\"/) {
+        $block_hash->{'file_blocks'}->{$dir.$1} = 1;
+    }
+    if ($line =~ /txtfile=\"([^\"]+)\"/) {
+        $block_hash->{'file_blocks'}->{$dir.$1} = 1;
+    }
+    }
+    close ITEMFILE;
+    
+}
+
+sub scan_item_for_files_to_block
+{
+    my $self = shift (@_);
+    my ($filename_full_path, $dir, $block_hash) = @_;
+
+    open (ITEMFILE, $filename_full_path) || die "couldn't open $filename_full_path to work out which files to block\n";
+    my $line = "";
+    while (defined ($line = <ITEMFILE>)) {
+    next unless $line =~ /\w/;
+    chomp $line;
+    next if $line =~ /^#/; # ignore comment lines
+    next if ($line =~ /^<([^>]*)>\s*(.*?)\s*$/); # ignore metadata lines 
+    # line should be like page:imagefilename:textfilename:r 
+    $line =~ s/^\s+//; #remove space at the front
+    $line =~ s/\s+$//; #remove space at the end
+    my ($pagenum, $imgname, $txtname, $rotate) = split /:/, $line;
+        
+    # find the image file if there is one
+    if (defined $imgname && $imgname ne "") {
+        $block_hash->{'file_blocks'}->{$dir.$imgname}=1;
+    }
+    # find the text file if there is one
+    if (defined $txtname && $txtname ne "") {
+        $block_hash->{'file_blocks'}->{$dir.$txtname} = 1;
+    }
+    }
+    close ITEMFILE;
+
+}
 
 sub process_item {
@@ -661 +719 @@
     $text = $1;
 
-    # insert preformat tags and add text to document object
+    # add text to document object
     $doc_obj->add_utf8_text($cursection, "$text");
     }