#!/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) ; my $expr = qr /($regex)/; my $get_length = 100; # Characters before and after the end of match t +o grab. my (@found_pos, @grab_pos); while ($text =~ /($expr)/sg) # Find matches and save the positions [pr +e,post] in @found_pos, { my $ipos = pos($text); my $prepos = $ipos - $get_length > 0 ? $ipos - $get_length : 0; my $postpos = $ipos + $get_length < length($text) ? $ipos + $get_len +gth : length($text) ; push @found_pos, [$prepos,$postpos]; } my $first = shift @found_pos; # Get the first "span" while (@found_pos){ my $n = shift @found_pos; # Get the next "span" if ($first->[1] > $n->[0]){ # Overlap? $first->[1] = $n->[1]; # compact push @grab_pos, $first unless @found_pos; }else{ push @grab_pos, [@$first],$n; # No, seperate, push them onto sta +ck $first = $n; } } foreach (@grab_pos){ my $chunk = substr($text,$_->[0],$_->[1]) ; $chunk=~s/\b($expr)\b/[$1]/igs; print ">>>",$chunk,"<<<\n"; } __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
In reply to Re^6: Regex: Matching around a word(s)
by shotgunefx
in thread Regex: Matching around a word(s)
by shotgunefx
| For: | Use: | ||
| & | & | ||
| < | < | ||
| > | > | ||
| [ | [ | ||
| ] | ] |