For a bit of fun, I'd recommend starting off with an ugly bash script when you j...

ParetoOptimal · on April 20, 2023

Seems fun, let's try it.

> ChatGPT> Rewrite the following as concisely as possible in perl, perl 6, J, Haskell, with no explanation and only code:

    history | awk '{a[$2]++}END{for(i in a){print a[i] " " i}}' | sort -rn | head

Perl:

    `history | perl -ne '/^\s*\d+\s+(\w+)/ && $a{$1}++; END { for $i (sort {$a cmp $b} keys %a) { print $a{$i}." ".$i."\n"; } }' | sort -rn | head`

Perl 6:

    `history | perl6 -ne '/^\s*\d+\s+(\w+)/ && $a{$1}++; END { for $i (sort keys %a) { say $a{$i}." ".$i; } }' | sort -rn | head`

J:

    `head sort |. |:+/ ,.~ [: ~. stdin -: i.0"1 <@:". ]

Haskell:

    `reverse . take 10 . sort . map (\x -> (length x, head x)) . group . sort . map (words) $ lines <$> readFile ".history"`

from https://www.commandlinefu.com/commands/view/604/list-of-comm...

tankenmate · on April 21, 2023

Both of those Perl solutions could be shorter (and probably quicker) in that you don't need the "sort -rn" as you can do that sort directly in Perl.

tankenmate · on April 21, 2023

Something similar to this;

history | perl -ne '/^\s*\d+\s+(\w+)/ && $a{$1}++; END { map { print "$a{$_} $_\n" } splice((sort {$b <=> $a} keys %a),0,10) }'

Oops, just realised it should be sorted by the value and not the key so...

history | perl -ne '/^\s*\d+\s+(\w+)/ && $a{$1}++; END { map { print "$a{$_} $_\n" } splice((sort {$a{$b} <=> $a{$a}} keys %a),0,10) }'

Also noticed that splice() isn't setting wantarray() so you'll need to use direct indexing which is probably easier to write too...

history | perl -ne '/^\s*\d+\s+(\w+)/ && $a{$1}++; END { map { print "$a{$_} $_\n" } (sort {$a{$b} <=> $a{$a}} (keys %a))[0..9] }'

bregma · on April 21, 2023

Usually line noise like that is quickly followed by a "Remote disconnected..." message and I have to dial in again.

tankenmate · on April 21, 2023

Sure, the same thing could be said about Chinese logograms if you don't understand it. Personally I prefer the compact symbology, it's somewhat like Lempel-Ziv tokenisation; it's a form of compression.

poulpy123 · on April 21, 2023

For comparison, here the answer from Bing AI

Here are the rewrites in Perl, Perl 6, J and Haskell:

Perl:

> perl -e 'while(<>){$a{$F[1]}++}for(sort{$a{$b}<=>$a{$a}}keys%a){print"$a{$_} $_\n"}' <(history)

Perl 6:

> my %h; for lines() { %h{.[1]}++; }; for %h.sort(-*.value) { .say }' <(history)

J:

> echo 'history' | jconsole -e '10 {. /:~ [: >: [: +/"1 [: =/ [: ;: [: >: [: ;: [: cut ;._2 ] ] ] ] ]'

Haskell:

> import Data.List

> import Data.Ord

> import System.Process

> main = do

    h <- readProcess "history" [] []

    let l = map (head . tail . words) $ lines h

    mapM_ print $ take 10 $ sortBy (flip $ comparing snd) $ map (\x -> (head x, length x)) $ group $ sort l

poulpy123 · on April 21, 2023

and answers by phind

# Perl perl -e 'print sort { $b <=> $a } map { /^.\s(.)$/; \$1 } <>' <(history | awk '{a[\$2]++}END{for(i in a){print a[i] " " i}}')

# Perl 6 (Raku) perl6 -e 'lines().map({m/^.\s(.)$/; \$0}).sort({-$^a}).say()' <(history | awk '{a[\$2]++}END{for(i in a){print a[i] " " i}}')

# J history | awk '{a[\$2]++}END{for(i in a){print a[i] " " i}}' | jconsole -je 'echo/:~1!:1]fread'''''

# Haskell ghc -e 'interact $ unlines . take 10 . reverse . sort . lines' <(history | awk '{a[\$2]++}END{for(i in a){print a[i] " " i}}')

poulpy123 · on April 21, 2023

I was able to try the perl versions and only the chatgpt is working (I have no experience in perl to check myself)

tankenmate · on April 21, 2023

The Haskell one has a bug, it should be "take10 . reverse . sort". And I suspect the second sort isn't needed but I'm not a Haskell programmer so not as sure about this.