Created
May 13, 2025 11:38
A more modern cw.pl
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/perl | |
use strict; | |
use warnings; | |
use feature 'say'; | |
# Global variables | |
my %word_frequency; | |
my %paragraph_stats; | |
# Main program | |
die "Usage: $0 file1 file2 ...\n" unless @ARGV; | |
foreach my $filename (@ARGV) { | |
process_file($filename); | |
} | |
# Display word frequency results | |
display_word_frequencies(); | |
# Display paragraph statistics | |
display_paragraph_stats(); | |
# Subroutines | |
sub process_file { | |
my $filename = shift; | |
open(my $fh, '<', $filename) or die "Could not open '$filename': $!\n"; | |
my $line_number = 1; | |
while (my $line = <$fh>) { | |
my $length = length($line); | |
if ($length > 1) { | |
$paragraph_stats{$length}{occurrence}++; | |
$paragraph_stats{$length}{file} = $filename; | |
$paragraph_stats{$length}{line} = $line_number; | |
} | |
# Split on whitespace and punctuation | |
foreach my $word (split(/[\s\'\\\{\}\.\,\;\:\?\!\`\[\]]/, $line)) { | |
if (length $word) { | |
$word_frequency{lc($word)}++; | |
} | |
} | |
$line_number++; | |
} | |
close $fh; | |
} | |
sub display_word_frequencies { | |
my @sorted_words = reverse sort { $word_frequency{$a} <=> $word_frequency{$b} } keys %word_frequency; | |
my $current_count = $word_frequency{$sorted_words[0]}; | |
print "$current_count: "; | |
my $display_count = 0; | |
foreach my $word (@sorted_words) { | |
if ($word_frequency{$word} != $current_count) { | |
$current_count = $word_frequency{$word}; | |
$display_count = 0; | |
print "\n$current_count: "; | |
} | |
if (++$display_count == 10) { | |
print "more..."; | |
} elsif ($display_count < 10) { | |
print "$word "; | |
} | |
} | |
print "\n"; | |
} | |
sub display_paragraph_stats { | |
say "\nLONGEST PARAGRAPHS\n"; | |
my @sorted_lengths = reverse sort { $a <=> $b } keys %paragraph_stats; | |
my $count = 0; | |
foreach my $length (@sorted_lengths) { | |
if ($count++ < 10) { | |
say "$length ", $paragraph_stats{$length}{occurrence}, | |
" ", $paragraph_stats{$length}{file}, | |
" ", $paragraph_stats{$length}{line}; | |
} else { | |
say "more..."; | |
last; | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment