Ignore:
Timestamp:
06/28/17 20:39:16 (4 years ago)
Author:
ak19
Message:

Fixed the earlier problems, which, it turned out, had to do with the order in which the superclass plugin instances were merged to create the subclass plugin. I can run the PDFBox command via UnknownConverterPlugin now at last, but while the text does go into doc.xml, previewing doesn't give me access to the HTML file. Not sure if this is requires fixing up a Formatting statement, or I'm not doing enough in the plugin.

File:
1 edited

Legend:

Unmodified
Added
Removed
  • main/trunk/greenstone2/perllib/plugins/UnknownConverterPlugin.pm.bak

    r31745 r31757  
    4545# At present, a file or folder of files is assumed.
    4646# Need to look in there for files with extension process_ext.
     47# Support html_multi as output? Then a folder of html files is generated per document? OR Flag that indicates whether an html file + associated folder (such as of images) gets generated. And name of assoc folder. Such output gets generated for instance when a doc file is replaced by its html version.
    4748
    4849sub BEGIN {
     
    7879    'desc' => "{UnknownConverterPlugin.output_file_or_dir_name}",
    7980    'type' => "string",
    80     'reqd' => "yes",
     81    'reqd' => "no",
    8182    'deft' => "" } ];
    8283
     
    9697    push(@{$hashArgOptLists->{"OptList"}},$options);
    9798
     99    my $unknown_converter_self = new UnknownPlugin($pluginlist, $inputargs, $hashArgOptLists);
    98100    my $cbf_self = new ConvertBinaryFile($pluginlist, $inputargs, $hashArgOptLists);
    99     my $unknown_converter_self = new UnknownPlugin($pluginlist, $inputargs, $hashArgOptLists);
    100     my $self = BaseImporter::merge_inheritance($cbf_self, $unknown_converter_self);
     101   
     102    # Need to feed the superclass plugins to merge_inheritance() below in the order that the
     103    # superclass plugins were declared in the ISA listing earlier in this file:
     104    my $self = BaseImporter::merge_inheritance($unknown_converter_self, $cbf_self);
    101105
    102106    $self = bless $self, $class;
    103107
    104 $self->{'convert_to'} = "text"; # why do I have to set a value for convert_to here, when a default's already set at start of this file???????
     108my $outhandle = $self->{'outhandle'};
     109    print STDERR "\n\n**** convert_to is |" . $self->{'convert_to'} . "|\n\n";
     110    if(!defined $self->{'convert_to'}) {
     111    $self->{'convert_to'} = "text"; # why do I have to set a value for convert_to here, when a default's already set at the start of this file???????
     112    }
    105113
    106114    # Convert_To set up, including secondary_plugins for processing the text or html generated
     
    173181    my $plugin_name = $self->{'plugin_type'}; # inherited from BaseImporter
    174182
     183    #### COPIED FROM ConvertBinaryFile::tmp_area_convert_file()
     184    my $outhandle = $self->{'outhandle'};
     185    my $convert_to = $self->{'convert_to'};
     186    my $failhandle = $self->{'failhandle'};
     187    my $convert_to_ext = $self->{'convert_to_ext'}; #set by ConvertBinaryFile::set_standard_convert_settings()
     188   
     189
     190    my $upgraded_input_filename = &util::upgrade_if_dos_filename($input_filename);
     191
     192    # derive tmp filename from input filename
     193    my ($tailname, $dirname, $suffix)
     194    = &File::Basename::fileparse($upgraded_input_filename, "\\.[^\\.]+\$");
     195
     196    # softlink to collection tmp dir
     197    my $tmp_dirname = &util::get_timestamped_tmp_folder();
     198    if (defined $tmp_dirname) {
     199    $self->{'tmp_dir'} = $tmp_dirname;
     200    } else {
     201    $tmp_dirname = $dirname;
     202    }
     203   
     204#    # convert to utf-8 otherwise we have problems with the doc.xml file later on
     205#    my $utf8_tailname = (&unicode::check_is_utf8($tailname)) ? $tailname : $self->filepath_to_utf8($tailname);
     206
     207    # make sure filename to be used can be stored OK in a UTF-8 compliant doc.xml file
     208     my $utf8_tailname = &unicode::raw_filename_to_utf8_url_encoded($tailname);
     209
     210
     211    # URLEncode this since htmls with images where the html filename is utf8 don't seem
     212    # to work on Windows (IE or Firefox), as browsers are looking for filesystem-encoded
     213    # files on the filesystem.
     214    $utf8_tailname = &util::rename_file($utf8_tailname, $self->{'file_rename_method'}, "without_suffix");
     215
     216    my $lc_suffix = lc($suffix);
     217    my $tmp_filename = &FileUtils::filenameConcatenate($tmp_dirname, "$utf8_tailname$lc_suffix");
     218   
     219    # If gsdl is remote, we're given relative path to input file, of the form import/utf8_tailname.suffix
     220    # But we can't softlink to relative paths. Therefore, we need to ensure that
     221    # the input_filename is the absolute path, see http://perldoc.perl.org/File/Spec.html
     222    my $ensure_path_absolute = 1; # true
     223    &FileUtils::softLink($input_filename, $tmp_filename, $ensure_path_absolute);
     224    my $verbosity = $self->{'verbosity'};
     225    if ($verbosity > 0) {
     226    print $outhandle "Converting $tailname$suffix to $convert_to format with extension $convert_to_ext\n";
     227    }
     228
     229    my $errlog = &FileUtils::filenameConcatenate($tmp_dirname, "err.log");
     230   
     231 
     232    my $output_type=$self->{'convert_to'};
     233
     234    # store the *actual* output type and return the output filename
     235    # it's possible we requested conversion to html, but only to text succeeded
     236    #$self->{'convert_to_ext'} = $output_type;
     237    if ($output_type =~ /html/i) {
     238    $self->{'converted_to'} = "HTML";
     239    } elsif ($output_type =~ /te?xt/i) {
     240    $self->{'converted_to'} = "Text";
     241    } elsif ($output_type =~ /item/i || $output_type =~ /^pagedimg/){
     242    $self->{'converted_to'} = "PagedImage";
     243    }
     244   
     245    my $output_filename = $tmp_filename;
     246    my $output_dirname;
     247    if ($output_type =~ /item/i || $output_type =~ /^pagedimg/) {
     248    # running under windows
     249    if ($ENV{'GSDLOS'} =~ /^windows$/i) {
     250        $output_dirname = $tmp_dirname . "\\$utf8_tailname\\" . $utf8_tailname;
     251    } else {
     252        $output_dirname = $tmp_dirname . "\/$utf8_tailname\/" . $utf8_tailname;
     253    }
     254    $output_filename .= ".item";
     255    } else {
     256    $output_filename =~ s/$lc_suffix$/.$output_type/;
     257    }
     258
     259    #### END COPIED FROM ConvertBinaryFile::tmp_area_convert_file()
     260
     261    # Execute the conversion command and get the type of the result,
     262    # making sure the converter gives us the appropriate output type
     263
    175264    # On Linux: if the program isn't installed, $? tends to come back with 127, in any case neither 0 nor 1.
    176265    # On Windows: echo %ERRORLEVEL% ends up as 9009 if the program is not installed.
     
    178267    # should produce either a text file or output to stdout.
    179268
    180     my $outhandle=$self->{'outhandle'};
    181 
    182269    my $cmd = $self->{'exec_cmd'};
    183270    if(!$cmd) { # empty string for instance
    184     print $outhandle "$plugin_name Conversion error: invalid cmd $cmd\n";
     271    print $outhandle "$plugin_name Conversion error: a command to execute is required, cmd provided is |$cmd|\n";
    185272    return "";
    186273    }
    187274
    188     # replace occurrences of '*' placeholder in cmd string with input filename
    189     my ($tailname, $dir, $suffix) = &File::Basename::fileparse($input_filename, "\\.[^\\.]+\$");
    190     $cmd =~ s/\*/$tailname/g;
    191     print STDERR "@@@@ $plugin_name: executing conversion cmd $cmd\n";
     275    # HARDCODING CMD FOR NOW
     276    #$cmd ="/Scratch/ak19/gs3-svn-15Nov2016/packages/jre/bin/java -cp \"/Scratch/ak19/gs3-svn-15Nov2016/gs2build/ext/pdf-box/lib/java/pdfbox-app.jar\" -Dline.separator=\"<br />\" org.apache.pdfbox.ExtractText -html \"/Scratch/ak19/tutorial_sample_files/pdfbox/A9-access-best-practices.pdf\" \"/Scratch/ak19/gs3-svn-15Nov2016/pdf-tmp/1.html\"";
     277
     278    #$cmd ="/Scratch/ak19/gs3-svn-15Nov2016/packages/jre/bin/java -cp \"/Scratch/ak19/gs3-svn-15Nov2016/gs2build/ext/pdf-box/lib/java/pdfbox-app.jar\" -Dline.separator=\"<br />\" org.apache.pdfbox.ExtractText -html INPUT_FILE OUTPUT";
     279
     280    # replace occurrences of placeholders in cmd string
     281    #$cmd =~ s@\"@\\"@g;
     282    $cmd =~ s@INPUT_FILE@\"$input_filename\"@g;
     283    if(defined $output_dirname) {
     284    $cmd =~ s@OUTPUT@\"$output_dirname\"@g;
     285    } else {
     286    $cmd =~ s@OUTPUT@\"$output_filename\"@g;
     287    }   
     288
     289    print STDERR "@@@@ $plugin_name: executing conversion cmd \n|$cmd|\n";
     290    print STDERR "   on infile |$input_filename|\n";
     291    print STDERR "   to produce expected $output_filename\n";
    192292    my $status = system($cmd);
    193293
     
    202302    }
    203303
    204     my $output_file_or_dir = $self->{'output_file_or_dir_name'};
    205     if (!-e $output_file_or_dir) {
    206     print $outhandle "$plugin_name Conversion error: Output file/dir $output_file_or_dir doesn't exist\n";
     304    # remove symbolic link to original file
     305    &FileUtils::removeFiles($tmp_filename);
     306
     307
     308    if(defined $output_dirname && -d $output_dirname) {
     309    print $outhandle "$plugin_name Conversion error: Output directory $output_dirname doesn't exist\n";
    207310    return "";
    208311    }
     312    elsif (!-e $output_filename) {
     313    print $outhandle "$plugin_name Conversion error: Output file $output_filename doesn't exist\n";
     314    return "";
     315    }
    209316
    210317    # else, conversion success
    211318   
    212319    # if multiple images were generated by running the conversion
    213     if ($self->{'convert_to'} eq "pagedimg") {
    214     my $item_filename = $self->generate_item_file($output_file_or_dir);
    215     return $item_filename;
    216     }
    217 
    218     return $output_file_or_dir;
     320    if ($self->{'convert_to'} =~ /^pagedimg/) {
     321    my $item_filename = $self->generate_item_file($output_filename); #my $item_filename = $self->generate_item_file($output_file_or_dir);
     322
     323    if (!-e $item_filename) {
     324        print $outhandle "$plugin_name Conversion error: Item file $item_filename was not generated\n";
     325        return "";
     326    }   
     327    $output_filename = $item_filename;
     328    }
     329
     330    $self->{'output_dirname'} = $output_dirname;
     331    $self->{'output_filename'} = $output_filename;
     332   
     333    return $output_filename; #$output_file_or_dir;
    219334}
    220335
     
    230345    return undef unless $self->can_process_this_file($filename_full_path);
    231346   
    232     my $output_file_or_dir = $self->{'output_file_or_dir_name'};
    233     my $is_output_dir = (-d $output_file_or_dir) ? 1 : 0;
     347    my $is_output_dir = (defined $self->{'output_dirname'}) ? 1 : 0;
    234348
    235349    # we are only doing something special if we have a directory of html files
    236     if (!$is_output_dir || $self->{'convert_to'} ne "html") {
     350    #if ($is_output_dir || $self->{'convert_to'} ne "html") {
     351    if ($self->{'convert_to'} ne "html_multi") {
    237352    return $self->BaseImporter::read(@_); # no read in ConvertBinaryFile.pm
    238353    }
     
    320435    # deleted some commented out code here that exists in PowerPointPlugin
    321436
    322     # for UnknownConverterPlugin, don't delete any temp files that the conversion may have created
    323     # as we don't know where it was created
    324     #$self->clean_up_after_doc_obj_processing();
     437    # for UnknownConverterPlugin, don't delete any temp files that the conversion may have created?
     438    # as we don't know where it was created. No. Now creating in tmp.
     439    $self->clean_up_after_doc_obj_processing();
    325440
    326441
     
    333448sub read_into_doc_obj {
    334449    my $self = shift (@_);
    335     $self->ConvertBinaryFile::deinit(@_);
     450    $self->ConvertBinaryFile::read_into_doc_obj(@_);
    336451}
    337452
Note: See TracChangeset for help on using the changeset viewer.