http://qs321.pair.com?node_id=128925
Category: Text Processing
Author/Contact Info dws
Description: A demonstration of how to grep through huge files using a sliding window (buffer) technique. The code below has rough edges, but works for simple regular express fragments. Treat it as a starting point.

I've seen this done somewhere before, but couldn't find a working example, so I whipped this one up. A pointer to a more authoritative version will be appreciated.

#!/usr/bin/perl -w
#
# Proof-of-concept for using minimal memory to search huge
# files, using a sliding window, matching within the window,
# and using on /gc and pos() to restart the search at the
# correct spot whenever we slide the window.
#
# Doesn't correctly handle potential matches that overlap;
# the first fragment that matches wins.
#

use strict;
use constant BLOCKSIZE => (8 * 1024);

&search("bighuge.log",
        sub { print $_[0], "\n" },
        "<img[^>]*>");

sub search {
    my ($file, $callback, @fragments) = @_;

    local *F;
    open(F, "<", $file) or die "$file: $!";
    binmode(F);

    # prime the window with two blocks (if possible)
    my $nbytes = read(F, my $window, 2 * BLOCKSIZE);

    my $re = "(" . join("|", @fragments) . ")";

    while ( $nbytes > 0 ) {

        # match as many times as we can within the
        # window, remembering the position of the
        # final match (if any).
        while ( $window =~ m/$re/oigcs ) {
            &$callback($1);
        }
        my $pos = pos($window);

        # grab the next block
        $nbytes = read(F, my $block, BLOCKSIZE);
        last if $nbytes == 0;

        # slide the window by discarding the initial
        # block and appending the next. then reset
        # the starting position for matching.
        substr($window, 0, BLOCKSIZE) = '';
        $window .= $block;
        $pos -= BLOCKSIZE;
        pos($window) = $pos > 0 ? $pos : 0;
    }

    close(F);
}