Changeset 23387 for main/trunk/greenstone2/perllib/plugins/ConvertBinaryFile.pm

Timestamp:

2010-12-06T13:15:10+13:00 (13 years ago)

Author:

davidb

Message:

Further changes to deal with documents that use different filename encodings on the file-system. Now sets UTF8URL metadata to perform the cross-document look up. Files stored in doc.pm as associated files are now always raw filenames (rather than potentially UTF8 encoded). Storing of filenames seen by HTMLPlug when scanning for files to block on is now done in Unicode aware strings rather than utf8 but unware strings.

File:

• main/trunk/greenstone2/perllib/plugins/ConvertBinaryFile.pm (modified) (6 diffs)

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

@@ -226 +226 @@
     my $convert_to_ext = $self->{'convert_to_ext'};
     
+
+    my $upgraded_input_filename = &util::upgrade_if_dos_filename($input_filename);
+
     # derive tmp filename from input filename
     my ($tailname, $dirname, $suffix)
-    = &File::Basename::fileparse($input_filename, "\\.[^\\.]+\$");
+    = &File::Basename::fileparse($upgraded_input_filename, "\\.[^\\.]+\$");
 
     # softlink to collection tmp dir
@@ -238 +241 @@
     }
     
-    # convert to utf-8 otherwise we have problems with the doc.xml file later on
-#    print STDERR "**** filename $tailname$suffix is already UTF8\n" if &unicode::check_is_utf8($tailname);
-    $tailname = $self->SUPER::filepath_to_utf8($tailname) unless &unicode::check_is_utf8($tailname);
+#    # convert to utf-8 otherwise we have problems with the doc.xml file later on
+#    my $utf8_tailname = (&unicode::check_is_utf8($tailname)) ? $tailname : $self->filepath_to_utf8($tailname);
+
+    # make sure filename to be used can be stored OK in a UTF-8 compliant doc.xml file
+     my $utf8_tailname = &unicode::raw_filename_to_utf8_url_encoded($tailname);
+
 
     # URLEncode this since htmls with images where the html filename is utf8 don't seem
     # to work on Windows (IE or Firefox), as browsers are looking for filesystem-encoded
     # files on the filesystem.
-    $tailname = &util::rename_file($tailname, $self->{'file_rename_method'}, "without_suffix");
-
-    $suffix = lc($suffix);
-    my $tmp_filename = &util::filename_cat($tmp_dirname, "$tailname$suffix");
+    $utf8_tailname = &util::rename_file($utf8_tailname, $self->{'file_rename_method'}, "without_suffix");
+
+    my $lc_suffix = lc($suffix);
+    my $tmp_filename = &util::filename_cat($tmp_dirname, "$utf8_tailname$lc_suffix");
     
     # If gsdl is remote, we're given relative path to input file, of the form import/tailname.suffix
@@ -324 +330 @@
     }
     } else {
-    $output_filename =~ s/$suffix$/.$output_type/;
+    $output_filename =~ s/$lc_suffix$/.$output_type/;
     }
     
@@ -446 +452 @@
     # need to check that not empty
     my ($doc_ext) = $file =~ /\.(\w+)$/;
+    $doc_ext = lc($doc_ext);
     my $file_type = "unknown";
     $file_type = $self->{'file_type'} if defined $self->{'file_type'};
@@ -458 +465 @@
     $assocfilename = $doc_obj->get_assocfile_from_sourcefile();
     }
+
     $doc_obj->associate_file($filename, $assocfilename, undef, $cursection);
 
@@ -476 +484 @@
      my $tmp_dir = $self->{'tmp_dir'};
      if (defined $tmp_dir && -d $tmp_dir) {
+##   print STDERR "**** Supressing clean up of tmp dir\n";
      &util::rm_r($tmp_dir);
      $self->{'tmp_dir'} = undef;