source: gs2-extensions/music-ir-src/trunk/perllib/plugins/jSongMinerExtractor.pm@ 28549

###########################################################################
#
# jSongMinerExtractor - helper plugin that identifies audio through
#                       external web services based on either an audio
#                       computed fingerprint or ID3 title and album
#
# A component of the Greenstone digital library software
# from the New Zealand Digital Library Project at the 
# University of Waikato, New Zealand.
#
# Copyright (C) 2010 New Zealand Digital Library Project
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
#
###########################################################################
package jSongMinerExtractor;

use BaseMediaConverter;

use Cwd;
use URI::Escape;

use strict;
no strict 'refs'; # allow filehandles to be variables and viceversa


BEGIN {
    @jSongMinerExtractor::ISA = ('BaseMediaConverter');
}


my $arguments = [
    { 'name' => "track_identification",
      'desc' => "{jSongMinerExtractor.track_identification}",
      'type' => "enum",
      'list' => [{'name' => "Fingerprint then ID3 tags", 'desc' => "{jSongMinerExtractor.fingerprint_first}"},
         {'name' => "ID3 tags only", 'desc' => "{jSongMinerExtractor.only_ids}"},
         {'name' => "Disabled",     'desc' => "{jSongMinerExtractor.off}"} ],
      'deft' => 'Fingerprint then ID3 tags',
      'reqd' => "no" }
    ];

my $options = { 'name' => "jSongMinerExtractor",
        'desc' => "{jSongMinerExtractor.desc}",
        'abstract' => "yes",
        'inherits' => "yes",
        'args' => $arguments };

sub new {
    my ($class) = shift (@_);
    my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
    push(@$pluginlist, $class);

    push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
    push(@{$hashArgOptLists->{"OptList"}},$options);

    my $self = new BaseMediaConverter($pluginlist, $inputargs, $hashArgOptLists, 1);

    # Set controlling variables
    my $gsdl_home = $ENV{'GSDLHOME'};
    my $music_ir_home = $ENV{'GEXT_MUSICIR'};

    $self->{'jmir_directory'} = &util::filename_cat($music_ir_home,"lib","java"); # Set the directory holding the jMIR .jar files

    return bless $self, $class;
}

sub urlEncode{
    # ARG 1: $to_encode is the string to URL encode
    my ($to_encode) = @_;
    return uri_escape($to_encode);
}

# URL Decode the given string
sub urlDecode{
    # ARG 1: $to_decode is the string to URL decode
    my ($to_decode) = @_;
    my $decoded= uri_unescape($to_decode);

    return $decoded;
}

sub map_id3v1_genre_num
{
    my ($genre_num) = @_;

    $genre_num =~ s/(/\(/g;
    $genre_num =~ s/)/\)/g;
    $genre_num =~ s/^[\(\[\{](.*)[\)\]\}]$/$1/;

    if (($genre_num =~ m/^\d+$/) && ($genre_num >= 148)) {
    return "Unknown";
    }

    my $lookup_id3v1_genre = {
    "0"  => "Blues",
    "1"  => "Classic Rock",
    "2"  => "Country",
    "3"  => "Dance",
    "4"  => "Disco",
    "5"  => "Funk",
    "6"  => "Grunge",
    "7"  => "Hip-Hop",
    "8"  => "Jazz",
    "9"  => "Metal",
    "10" => "New Age",
    "11" => "Oldies",
    "12" => "Other",
    "13" => "Pop",
    "14" => "R&B",
    "15" => "Rap",
    "16" => "Reggae",
    "17" => "Rock",
    "18" => "Techno",
    "19" => "Industrial",
    "20" => "Alternative",
    "21" => "Ska",
    "22" => "Death Metal",
    "23" => "Pranks",
    "24" => "Soundtrack",
    "25" => "Euro-Techno",
    "26" => "Ambient",
    "27" => "Trip-Hop",
    "28" => "Vocal",
    "29" => "Jazz+Funk",
    "30" => "Fusion",
    "31" => "Trance",
    "32" => "Classical",
    "33" => "Instrumental",
    "34" => "Acid",
    "35" => "House",
    "36" => "Game",
    "37" => "Sound Clip",
    "38" => "Gospel",
    "39" => "Noise",
    "40" => "Alternative Rock",
    "41" => "Bass",
    "42" => "Soul",
    "43" => "Punk",
    "44" => "Space",
    "45" => "Meditative",
    "46" => "Instrumental Pop",
    "47" => "Instrumental Rock",
    "48" => "Ethnic",
    "49" => "Gothic",
    "50" => "Darkwave",
    "51" => "Techno-Industrial",
    "52" => "Electronic",
    "53" => "Pop-Folk",
    "54" => "Eurodance",
    "55" => "Dream",
    "56" => "Southern Rock",
    "57" => "Comedy",
    "58" => "Cult",
    "59" => "Gangsta",
    "60" => "Top 40",
    "61" => "Christian Rap",
    "62" => "Pop/Funk",
    "63" => "Jungle",
    "64" => "Native US",
    "65" => "Cabaret",
    "66" => "New Wave",
    "67" => "Psychadelic",
    "68" => "Rave",
    "69" => "Showtunes",
    "70" => "Trailer",
    "71" => "Lo-Fi",
    "72" => "Tribal",
    "73" => "Acid Punk",
    "74" => "Acid Jazz",
    "75" => "Polka",
    "76" => "Retro",
    "77" => "Musical",
    "78" => "Rock & Roll",
    "79" => "Hard Rock",
    "80" => "Folk",
    "81" => "Folk-Rock",
    "82" => "National Folk",
    "83" => "Swing",
    "84" => "Fast Fusion",
    "85" => "Bebob",
    "86" => "Latin",
    "87" => "Revival",
    "88" => "Celtic",
    "89" => "Bluegrass",
    "90" => "Avantgarde",
    "91" => "Gothic Rock",
    "92" => "Progressive Rock",
    "93" => "Psychedelic Rock",
    "94" => "Symphonic Rock",
    "95" => "Slow Rock",
    "96" => "Big Band",
    "97" => "Chorus",
    "98" => "Easy Listening",
    "99" => "Acoustic",
    "100" => "Humour",
    "101" => "Speech",
    "102" => "Chanson",
    "103" => "Opera",
    "104" => "Chamber Music",
    "105" => "Sonata",
    "106" => "Symphony",
    "107" => "Booty Bass",
    "108" => "Primus",
    "109" => "Porn Groove",
    "110" => "Satire",
    "111" => "Slow Jam",
    "112" => "Club",
    "113" => "Tango",
    "114" => "Samba",
    "115" => "Folklore",
    "116" => "Ballad",
    "117" => "Power Ballad",
    "118" => "Rhythmic Soul",
    "119" => "Freestyle",
    "120" => "Duet",
    "121" => "Punk Rock",
    "122" => "Drum Solo",
    "123" => "Acapella",
    "124" => "Euro-House",
    "125" => "Dance Hall",
    "126" => "Goa",
    "127" => "Drum & Bass",
    "128" => "Club - House",
    "129" => "Hardcore",
    "130" => "Terror",
    "131" => "Indie",
    "132" => "BritPop",
    "133" => "Negerpunk",
    "134" => "Polsk Punk",
    "135" => "Beat",
    "136" => "Christian Gangsta Rap",
    "137" => "Heavy Metal",
    "138" => "Black Metal",
    "139" => "Crossover",
    "140" => "Contemporary Christian",
    "141" => "Christian Rock",
    "142" => "Merengue",
    "143" => "Salsa",
    "144" => "Thrash Metal",
    "145" => "Anime",
    "146" => "JPop",
    "147" => "Synthpop" 
    };

    my $mapped_genre;

    if (defined $lookup_id3v1_genre->{$genre_num}) {
    print STDERR "*** changing $genre_num -> ", $lookup_id3v1_genre->{$genre_num}, "\n";
    $mapped_genre = $lookup_id3v1_genre->{$genre_num};
    }
    else {
    $mapped_genre = $genre_num;
    }

    return $mapped_genre;
}

sub check_for_existing_id3_genre
{
    my $self = shift @_;
    my ($doc_obj) = @_;

    my $top_section=$doc_obj->get_top_section();

    # Look for ex.ID3.Genre as well, as special case
    my $genre_md_list = $doc_obj->get_metadata($top_section,"ex.ID3.Genre");
    my @new_genre_md_list = ();
    
    foreach my $gv (@$genre_md_list) {
    print STDERR "*** got match on ex.ID3.Genre -> '$gv'\n";
    my $new_gv = map_id3v1_genre_num($gv);
        
    push(@new_genre_md_list,$new_gv);
    }
    
    $doc_obj->delete_metadata($top_section,"ex.ID3.Genre");
    foreach my $gv (@new_genre_md_list) {
    $doc_obj->add_utf8_metadata($top_section,"ex.ID3.Genre",$gv);
    }
}


sub parse_txt_metadata
{
    my $self = shift @_;
    my ($doc_obj,$target_txt_file_path) = @_;

    print STDERR "**#####** jSongMiner parsing txt metadata\n";

    if (open(MIN,"<$target_txt_file_path")) {

    my ($md_name, $md_value);

    while (defined($md_name=<MIN>) && defined($md_value=<MIN>)) {

        chomp $md_name;
        chomp $md_value;

        my $top_section=$doc_obj->get_top_section();

        $md_name =~ s/\+//g;
        $md_value =~ s/\+/ /g;
        
        $md_name = urlDecode($md_name);
        $md_value = urlDecode($md_value);

        # $md_name =~ s/\s+/ /sg;
        $md_name =~ s/\(.*?\)$//s; # can stretch over multiple lines
        $md_name =~ s/Last\.FM/LastFM/g;
        $md_name =~ s/:/^/g;
        $md_name =~ s/(API)?\^/./;

#       print STDERR "*** md_name = '$md_name'\n";

        if ($md_name =~ m/genre$/i) {
        print STDERR "*** got match on $md_name -> $md_value\n";
        $md_value = map_id3v1_genre_num($md_value);
        }

        $doc_obj->add_utf8_metadata($top_section,$md_name,$md_value);
    }

    close(MIN);

    $self->check_for_existing_id3_genre($doc_obj);

    }
    else {
    print STDERR "Error: Failed to open $target_txt_file_path\n";
    print STDERR "       !$\n";
    }
}


sub retrieve_metadata
{
    my $self = shift(@_);
    my ($source_file_path,$id3_title,$id3_artist,$convert_options) = @_;

    $convert_options = "" if (!defined $convert_options);

    my $outhandle = $self->{'outhandle'};
    my $verbosity = $self->{'verbosity'};

    my $source_file_no_path = &File::Basename::basename($source_file_path);

    $self->init_cache_for_file($source_file_path);

    my $target_txt_file_path;
    my $target_acexml_file_path;

    if ($self->{'enable_cache'}) {
    my $cached_dir = $self->{'cached_dir'};
    my $file_root = $self->{'cached_file_root'};

    my $target_txt_file = "${file_root}_metadata.txt";
    my $target_acexml_file = "${file_root}.xml";

    $target_txt_file_path = &util::filename_cat($cached_dir,$target_txt_file);
    $target_acexml_file_path = &util::filename_cat($cached_dir,$target_acexml_file);
    }
    else {
    $target_txt_file_path = &util::get_tmp_filename("_metadata.txt");
    $target_acexml_file_path = &util::get_tmp_filename(".xml");
    }

    my $jmir_directory = $self->{'jmir_directory'};


    my $store_cwd = cwd();

    if (!-d $jmir_directory) {
    print STDERR "Error: Unable able to find directory '$jmir_directory'\n";
    print STDERR "       Cannot run jAudio\n";
    }
    elsif (chdir($jmir_directory)) {

    my $source_file_path_os = $source_file_path;
    if ($^O eq "cygwin") {
        $source_file_path_os = `cygpath -w "$source_file_path"`;
        $source_file_path_os =~ s/\s+$//;
    }
    my $target_txt_file_path_os = $target_txt_file_path;
    if ($^O eq "cygwin") {
        $target_txt_file_path_os = `cygpath -w "$target_txt_file_path"`;
        $target_txt_file_path_os =~ s/\s+$//;
    }
    my $target_acexml_file_path_os = $target_acexml_file_path;
    if ($^O eq "cygwin") {
        $target_acexml_file_path_os = `cygpath -w "$target_acexml_file_path"`;
        $target_acexml_file_path_os =~ s/\s+$//;
    }

    my $jsongminer_cmd = "java -Xmx1024M -jar jSongMiner.jar $convert_options";
    $jsongminer_cmd .= " -title \"$id3_title\"" if defined $id3_title;
    $jsongminer_cmd .= " -artist \"$id3_artist\"" if defined $id3_artist;
    $jsongminer_cmd .= " -audio \"$source_file_path_os\"";
    $jsongminer_cmd .= " -savetxtfile \"$target_txt_file_path_os\"";
    $jsongminer_cmd .= " -saveacexmlfile \"$target_acexml_file_path_os\"";
    
    if ($verbosity>2) {
        print $outhandle "jSongMinerExtractor: Running ...\n";
        print $outhandle "jSongMinerExtractor:   $jsongminer_cmd\n";
    }
    
    my $print_info = { 'message_prefix' => "jSongMiner",
               'message' => "jSongMinerExtractor: Retrieving audio metadata for $source_file_no_path" };
    
    my ($regenerated,$result,$had_error) 
        = $self->autorun_general_cmd($jsongminer_cmd,$source_file_path,$target_txt_file_path,$print_info);
    
    if ($verbosity>2) {
        print $outhandle "jSongMinerExtractor: ...done\n";
    }
    }
    else {
    print STDERR "Error: failed to change directory to '$jmir_directory'\n";
    print STDERR "       Cannot run jAudio\n";
    }

    chdir($store_cwd);

    return ($target_acexml_file_path,$target_txt_file_path);
}
    



1;