RosettaCodeData/Task/LZW-compression/Raku/lzw-compression.raku
2023-07-01 13:44:08 -04:00

46 lines
1.2 KiB
Raku
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# 20200421 Updated Raku programming solution ; add unicode support
sub compress(Str $uncompressed --> Seq) {
my $dict-size = 256;
my %dictionary = (.chr => .chr for ^$dict-size);
my $w = "";
gather {
for $uncompressed.encode('utf8').list.chrs.comb -> $c {
my $wc = $w ~ $c;
if %dictionary{$wc}:exists { $w = $wc }
else {
take %dictionary{$w};
%dictionary{$wc} = +%dictionary;
$w = $c;
}
}
take %dictionary{$w} if $w.chars;
}
}
sub decompress(@compressed --> Str) {
my $dict-size = 256;
my %dictionary = (.chr => .chr for ^$dict-size);
my $w = shift @compressed;
( Blob.new: flat ( gather {
take $w;
for @compressed -> $k {
my $entry;
if %dictionary{$k}:exists { take $entry = %dictionary{$k} }
elsif $k == $dict-size { take $entry = $w ~ $w.substr(0,1) }
else { die "Bad compressed k: $k" }
%dictionary{$dict-size++} = $w ~ $entry.substr(0,1);
$w = $entry;
}
} )».ords ).decode('utf-8')
}
say my @compressed = compress('TOBEORNOTTOBEORTOBEORNOT');
say decompress(@compressed);
@compressed = compress('𝒳𝒴𝒵𝒳𝒴𝒵𝒳𝒴𝒵');
say decompress(@compressed);