#!/usr/bin/perl

use strict;
use warnings;

die "No search terms supplied!" unless @ARGV;
my @words = @ARGV;

my $text;
{
    local $/ = undef;
    $text = <DATA>;
}


my $regex = join ( "|", @words ); # Words to highlight
my $expr = qr /(?i)($regex)/;     # Compile regex
my $glen = 20;                    # Characters before and after the en
+d of match to grab.


{
  no warnings 'uninitialized'; 
  my ( $ls, $le, @results );  # $ls=prev span start, $le=prev span end
+, @results, results destination
  
  # Markup any matches or exit block.
  last unless $text =~ s/\b($expr)\b/[$1]/gi; 

  while ( $text =~ m/\b($expr)\b/sg or $le <= length ($text) ) {    
    my ($ipos,$spos,$epos); # char span positions
    
    if ($ipos  = pos($text)) { # If the last match succeded
        $spos  = $ipos - $glen > 0 ? $ipos - $glen : 0;       # Range 
+check
        $epos = $ipos + $glen < length($text) ? $ipos + $glen : length
+($text);

        # Assign to ($ls,$le) if this is our first time through and ne
+xt.
        ( $ls, $le ) = ( $spos, $epos ) and next unless $le;  
    }

    if ( $spos and $spos < $le ) {    # If we have a match and it inte
+rsects the last match
        $le = $epos;                  # merge  overlapping char spans
    }
    else {
        # Lose the first word(possible fragment) unless the match is t
+he first word.
        $ls = index($text," ", $ls) + 1  unless ($ls == 0); 
        push @results,substr( $text, $ls, $le - $ls ) ;
        ( $ls, $le ) = ( $spos, $epos );                    # Set "las
+t position" to current.
    }
    last unless defined $spos;                              # End unle
+ss we have one more match                          
  }                                                     

  print '"',$_,'..."', "\n" foreach @results;
}
__DATA__
Regular expressions have always been a weak spot for me, and I've got 
+a
 question that's got me stumped. Here's the problem I'm trying to solv
+e.
 I have somewhat large articles of text (returned from a search), what
+ I'd
 like to do is capture the word and X number of words before and after
+ it
 while tagging the matching word in the captured text. My inital thoug
+ht
 was to try something like this. The problem I have is that if there i
+s
 more than one term and they overlap, the nth term will not be annotat
+ed.
 So my next thought is lookahead/lookbehind, but they don't capture.
 Is there a way to do this with a single regex? Is a regex even the be
+st
 way to do this? Thanks, -Lee
[download]