use feature ':5.10';
use strict;

use List::MoreUtils qw( natatime  );

my $test_sentence
    = "Perl is a high-level, general-purpose, interpreted, dynamic pro
+gramming language.";

sub uniq_phrases {
    my $sentence = shift;
    my ( $min, $max );
    given ( scalar @_ ) {
        when (2) { ( $min, $max ) = @_; }
        when (1) { ( $min, $max ) = ($_[0], $_[0]); }
        default { ( $min, $max ) = ( 2, 4 ); };
    }

    my @words = split( /\s+/, $sentence );
    my @pairs;
    for my $size ( $min .. $max ) {
        my %seen;
        for my $window ( 0 .. ( $#words - $size ) ) {
            my $it = natatime $size, @words[ $window .. $#words ];
            while ( my @p = $it->() ) {
                next if @p != $size;
                my $p = join( " ", @p );
                next if $seen{$p}++;
                push @pairs, $p;
            }
        }
    }

    return wantarray ? @pairs : \@pairs;
}

say join( "\n", sort { $a cmp $b } uniq_phrases( $test_sentence, 4 ) )
+;

__END__

[download]
Or . . . 
(use '[clojure.contrib.str-utils :only (re-split str-join)])

(def test-sentence
  "Perl is a high-level, general-purpose, interpreted, dynamic program
+ming language.")

(defn uniq-phrases
  "Find unique phrases of the given lengths (def 2-4 words; max may be
+ omitted)"
  ([sentence] (uniq-phrases sentence 2 4))
  ([sentence len] (uniq-phrases sentence len len))
  ([sentence min-len max-len]
    (let [words (re-split #"\s+" sentence)
          pairs (set (mapcat #(partition %1 1 words) (range min-len (i
+nc max-len))))]
      (map #(str-join " " %) pairs))))

(defn print-phrases [p]
  (println (str-join "\n" (sort p))))

(print-phrases (uniq-phrases test-sentence 2 9))

; user=> (time (print-phrases (uniq-phrases test-sentence 4 4)))
; Perl is a high-level,
; a high-level, general-purpose, interpreted,
; general-purpose, interpreted, dynamic programming
; high-level, general-purpose, interpreted, dynamic
; interpreted, dynamic programming language.
; is a high-level, general-purpose,
; "Elapsed time: 1.227 msecs"

[download]

The cake is a lie.
The cake is a lie.
The cake is a lie.

In reply to Re: extract phrases of n-words length by Fletch
in thread extract phrases of n-words length by arun_kom

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


  • Posts are HTML formatted. Put <p> </p> tags around your paragraphs. Put <code> </code> tags around your code and data!
  • Titles consisting of a single word are discouraged, and in most cases are disallowed outright.
  • Read Where should I post X? if you're not absolutely sure you're posting in the right place.
  • Please read these before you post! —
  • Posts may use any of the Perl Monks Approved HTML tags:
    a, abbr, b, big, blockquote, br, caption, center, col, colgroup, dd, del, details, div, dl, dt, em, font, h1, h2, h3, h4, h5, h6, hr, i, ins, li, ol, p, pre, readmore, small, span, spoiler, strike, strong, sub, summary, sup, table, tbody, td, tfoot, th, thead, tr, tt, u, ul, wbr
  • You may need to use entities for some characters, as follows. (Exception: Within code tags, you can put the characters literally.)
            For:     Use:
    & &amp;
    < &lt;
    > &gt;
    [ &#91;
    ] &#93;
  • Link using PerlMonks shortcuts! What shortcuts can I use for linking?
  • See Writeup Formatting Tips and other pages linked from there for more info.