Lingua::EN::Splitter to the rescue:
#!/usr/bin/perl use strict; use warnings; use Lingua::EN::Splitter; my @strings = ( q|one two 'three'|, q|yes I am 'me'|, ); my %config = ( minlen => 3, maxlen => 32, locale => "en_US.ISO_8859-1", ); my $split = Lingua::EN::Splitter->new; my %count; for my $str (@strings){ print "$str\n"; my $words = $split->words($str); $count{$_}++ for @$words; for my $word (sort @$words) { $_ = length $word; next if $_ < $config{minlen} or $_ > $config{maxlen}; print $word, ' -> ', $count{$word}, "\n" } print '-' x 10, "\n"; } __END__ Output: one two 'three' one -> 1 three -> 1 two -> 1 ---------- yes I am 'me' yes -> 1

--
perl -MO=Deparse -e"u j t S n a t o e h r , e p l r a h k c r e"


In reply to Re: Unpredictable output form Text::ExtractWords by epoptai
in thread Unpredictable output from Text::ExtractWords by wfsp

Title:
Use:  <p> text here (a paragraph) </p>
and:  <code> code here </code>
to format your post; it's "PerlMonks-approved HTML":