script for parsing the filenames of comic books, manga, etc, i.e. cbz files. It will find the series names and mostly parses the other metadata found in filenames. A later version of it generates ComicInfo.xml. It will sort files into directories based on Series names. Chapter number is not 100%

decode_series_name.pl

#!/usr/bin/perl
use strict;
use warnings;
use File::Path qw(make_path);
use File::Copy qw(move);

# Script version number
my $VERSION = "1.1.16-2024.08.12.00.00";

# Initialize default minimum group size
my $min_group_size = 2;
my $create_shift = 0;  # Flag to determine if we should create directories and move files
my $show_help = 0;     # Flag to determine if help should be shown
my $debug_mode = 0;    # Flag to determine if debug information should be printed

# Declare the global hash for storing series information
my %series_groups;

# Custom argument parsing to handle +N, -N, --create-shift, --help, and --debug options
foreach my $arg (@ARGV) {
    if ($arg =~ /^\+(\d+)$/) {
        $min_group_size = $1;
    } elsif ($arg =~ /^-(\d+)$/) {
        $min_group_size = -$1;
    } elsif ($arg eq '--create-shift') {
        $create_shift = 1;
    } elsif ($arg eq '--help') {
        $show_help = 1;
    } elsif ($arg eq '--debug') {
        $debug_mode = 1;
    }
}

# Remove the custom options from @ARGV
@ARGV = grep { !/^[+-]\d+$/ && $_ ne '--create-shift' && $_ ne '--help' && $_ ne '--debug' } @ARGV;

# Function to print help message
sub print_help {
    print <<"END_HELP";
Usage: $0 [options] *.cbz

Options:
  +N              Only print groups with N or more files.
  -N              Only print groups with fewer than N files.
  --create-shift  Create directories based on the series name and move files into them.
  --debug         Print debug information such as Resolution, ScanInformation, Publisher, Title, Volume, Chapter, Publishing Date, and LanguageISO.
  --help          Display this help message.

Version: $VERSION
END_HELP
}

# Show help if no arguments are provided or if --help is used
if ($show_help || !@ARGV) {
    print_help();
    exit;
}

# Function to extract the series name, title, publisher, ScanInformation, LanguageISO, volume, chapter, and publishing date from a cbz filename
sub extract_series_name {
    my ($filename, $info) = @_;

    # Extract and remove ScanInformation (e.g., [ScanGroup]) at the start of the filename
    if ($filename =~ s/^\[([^\]]+)\]\s*//) {
        $info->{scan_info} = $1;
    }

    # Remove the file extension (.cbz)
    $filename =~ s/\.cbz$//i;

    # Extract and remove resolution info (e.g., (x3200))
    if ($filename =~ s/\(x(\d+)\)//) {
        $info->{resolution} = $1;
    }

    # Extract and remove the exact string "ENGLISH" surrounded by [] or () and store in LanguageISO
    if ($filename =~ s/[\[\(]ENGLISH[\]\)]//i) {
        $info->{language_iso} = "EN";
    }

    # Extract and remove (PNG) or [PNG] in any case and store in format
    if ($filename =~ s/[\(\[]png[\)\]]//i) {
        $info->{format} = "PNG";
    }
    # Extract and remove publisher information anchored at the end of the string (either [] or ())
    if ($filename =~ s/\s*[\[\(]([^\]\)]+)[\]\)]\s*$//) {
        $info->{publisher_info} = $1;
    }

    # Extract and remove volume information (e.g., Vol. 5, Vol. 2.0, v02, v02.5)
    if ($filename =~ s/\b(?:Volume|Vol|Vol\.)\s*(\d+(\.\d+)?|v0{0,4}(\d{1,5}(?:\.\d+)?))\b//i) {
        $info->{volume} = $3 || $1;  # Store only the numeric part
    } elsif ($filename =~ s/\bv0{0,4}(\d{1,5}(\.\d+)?)\b//i) {
        $info->{volume} = $1;  # Store only the numeric part
    }

    # Remove chapter/episode/operation information before extracting the title
    if ($filename =~ s/\b(?:Chapter|Ch\.?|Part|Ep|Ep\.|Episode|Op|Op\.)\s*(\d+|EX\d+)\b//i) {
        $info->{chapter} = $1;
    } elsif ($filename =~ s/\b(EX\d+)\b//i) {
        $info->{chapter} = $1;
    }

    # Going from right to left, look for a title after " - " and remove it from the series name
    if ($filename =~ s/\s-\s(.+)$//) {  # Match " - " and capture everything after it
        $info->{title} = $1;
    }

    # If the title is still empty and the filename does not start with "re:" (case-insensitive)
    if (!$info->{title} && $filename !~ /^re꞉/i && $filename =~ s/꞉\s(.+)$//) {
        $info->{title} = $1;
    }

    # If the title is still empty, look for titles surrounded by ~ ~
    if (!$info->{title} && $filename =~ s/~([^~]+)~//) {
        $info->{title} = $1;
    }

    # Extract and remove publishing year/month (e.g., 2024-02)
    if ($filename =~ s/\b(20\d{2}-\d{2})\b$//) {
        $info->{publishing_date} = $1;
    }

    # Assign the cleaned filename to series_name
    $info->{series_name} = $filename;

    # Trim trailing spaces
    $info->{series_name} =~ s/\s+$//;
}

# Main script to decode series names from multiple cbz filenames
foreach my $filename (@ARGV) {
    # Check if the provided file has a .cbz extension
    if ($filename =~ /\.cbz$/i) {
        my %info;
        extract_series_name($filename, \%info);
        my $normalized_name = uc($info{series_name});  # Convert series name to uppercase for comparison

        # Store the original series name and its corresponding file information
        push @{$series_groups{$normalized_name}{files}}, {
            filename => $filename,
            %info,
        };

        # Increment the count for this original series name
        $series_groups{$normalized_name}{count}{$info{series_name}}++;
    } else {
        print "Warning: '$filename' is not a .cbz file. Skipping...\n";
    }
}

# Determine the most common original series name for each group
foreach my $normalized_name (keys %series_groups) {
    my $most_common_name = (sort { $series_groups{$normalized_name}{count}{$b} <=> $series_groups{$normalized_name}{count}{$a} } keys %{$series_groups{$normalized_name}{count}})[0];
    $series_groups{$normalized_name}{most_common_name} = $most_common_name;
}

# Sort series names and process the files based on the min_group_size
foreach my $normalized_name (sort keys %series_groups) {
    my @files = @{$series_groups{$normalized_name}{files}};
    next if ($min_group_size > 0 && @files < $min_group_size);   # Skip groups with fewer than the specified minimum number of files
    next if ($min_group_size < 0 && @files >= abs($min_group_size));  # Skip groups with equal to or more than the specified negative minimum number of files

    my $most_common_name = $series_groups{$normalized_name}{most_common_name};

    print "Series: $most_common_name\n";
    foreach my $file_info (@files) {
        my $file = $file_info->{filename};
        my $resolution = $file_info->{resolution};
        my $scan_info = $file_info->{scan_info};
        my $publisher_info = $file_info->{publisher_info};
        my $title = $file_info->{title};
        my $volume = $file_info->{volume};
        my $chapter = $file_info->{chapter};
        my $publishing_date = $file_info->{publishing_date};
        my $language_iso = $file_info->{language_iso};

        print "  File: $file\n";

        if ($debug_mode) {
            print "    Resolution: $resolution\n" if $resolution;
            print "    ScanInformation: $scan_info\n" if $scan_info;
            print "    Publisher: $publisher_info\n" if $publisher_info;
            print "    Title: $title\n" if $title;
            print "    Volume: $volume\n" if $volume;
            print "    Chapter: $chapter\n" if $chapter;
            print "    Publishing Date: $publishing_date\n" if $publishing_date;
            print "    LanguageISO: $language_iso\n" if $language_iso;
        }
    }
    print "\n";

    # If --create-shift is specified, create the directory and move the files
    if ($create_shift) {
        my $dir_name = $most_common_name;  # Use the most common series name directly as the directory name
        unless (-d $dir_name) {
            make_path($dir_name) or die "Failed to create directory '$dir_name': $!";
        }
        foreach my $file_info (@files) {
            my $file = $file_info->{filename};
            move($file, "$dir_name/") or die "Failed to move file '$file' to '$dir_name': $!";
        }
        print "Moved files to directory: $dir_name\n";
    }
}