Natural sorting

class String {
    # Sort groups of digits in number order. Sort by order of magnitude then lexically.
    -> naturally { self.lc.gsub(/(\d+)/, {|s1| "0" + s1.len.chr + s1 }) + "\x0" + self };
 
    # Collapse multiple ws characters to a single.
    -> collapse { self.gsub(/(\s)\1+/, {|s1| s1 }) };
 
    # Convert all ws characters to a space.
    -> normalize { self.gsub(/(\s)/, ' ') };
 
    # Ignore common leading articles for title sorts
    -> title { self.sub(/^(?:a|an|the)\b\s*/i, '') };
 
    # Decompose ISO-Latin1 glyphs to their base character.
    -> latin1_decompose {
        static tr = Hash.new(%w(
           Æ AE æ ae Þ TH þ th Ð TH ð th ß ss À A Á A Â A Ã A Ä A Å A à a á a
            â a ã a ä a å a Ç C ç c È E É E Ê E Ë E è e é e ê e ë e Ì I Í I Î
            I Ï I ì i í i î i ï i Ò O Ó O Ô O Õ O Ö O Ø O ò o ó o ô o õ o ö o
            ø o Ñ N ñ n Ù U Ú U Û U Ü U ù u ú u û u ü u Ý Y ÿ y ý y
        )...);
 
        var re = Regex.new('(' + tr.keys.join('|') + ')');
        self.gsub(re, {|s1| tr{s1} });
    }
}

Tests:

Output:

PreviousNative shebangNextNegative base numbers

Last updated

Was this helpful?