| 5 |
|
|
| 6 |
=head1 NAME |
=head1 NAME |
| 7 |
|
|
| 8 |
WebPAC::Input - The great new WebPAC::Input! |
WebPAC::Input - core module for input file format |
| 9 |
|
|
| 10 |
=head1 VERSION |
=head1 VERSION |
| 11 |
|
|
| 17 |
|
|
| 18 |
=head1 SYNOPSIS |
=head1 SYNOPSIS |
| 19 |
|
|
| 20 |
Quick summary of what the module does. |
This module will load particular loader module and execute it's functions. |
| 21 |
|
|
| 22 |
Perhaps a little code snippet. |
Perhaps a little code snippet. |
| 23 |
|
|
| 24 |
use WebPAC::Input; |
use WebPAC::Input; |
| 25 |
|
|
| 26 |
my $foo = WebPAC::Input->new(); |
my $db = WebPAC::Input->new( |
| 27 |
... |
format => 'NULL', |
| 28 |
|
config => $config, |
| 29 |
|
lookup => $lookup_obj, |
| 30 |
|
low_mem => 1, |
| 31 |
|
); |
| 32 |
|
|
| 33 |
|
$db->open('/path/to/database'); |
| 34 |
|
print "database size: ",$db->size,"\n"; |
| 35 |
|
while (my $row = $db->fetch) { |
| 36 |
|
... |
| 37 |
|
} |
| 38 |
|
$db->close; |
| 39 |
|
|
| 40 |
=head1 EXPORT |
=head1 FUNCTIONS |
| 41 |
|
|
| 42 |
A list of functions that can be exported. You can delete this section |
=head2 new |
|
if you don't export anything, such as for a purely object-oriented module. |
|
| 43 |
|
|
| 44 |
=head1 FUNCTIONS |
Create new input database object. |
| 45 |
|
|
| 46 |
|
my $db = new WebPAC::Input( |
| 47 |
|
format => 'NULL' |
| 48 |
|
code_page => 'ISO-8859-2', |
| 49 |
|
low_mem => 1, |
| 50 |
|
); |
| 51 |
|
|
| 52 |
=head2 function1 |
Optional parametar C<code_page> specify application code page (which will be |
| 53 |
|
used internally). This should probably be your terminal encoding, and by |
| 54 |
|
default, it C<ISO-8859-2>. |
| 55 |
|
|
| 56 |
|
Default is not to use C<low_mem> options (see L<MEMORY USAGE> below). |
| 57 |
|
|
| 58 |
=cut |
=cut |
| 59 |
|
|
| 60 |
sub function1 { |
sub new { |
| 61 |
} |
my $class = shift; |
| 62 |
|
my $self = {@_}; |
| 63 |
|
bless($self, $class); |
| 64 |
|
|
| 65 |
=head2 function2 |
$self->{'code_page'} ||= 'ISO-8859-2'; |
| 66 |
|
|
| 67 |
=cut |
my $log = $self->_get_logger; |
| 68 |
|
|
| 69 |
|
# running with low_mem flag? well, use DBM::Deep then. |
| 70 |
|
if ($self->{'low_mem'}) { |
| 71 |
|
$log->info("running with low_mem which impacts performance (<32 Mb memory usage)"); |
| 72 |
|
|
| 73 |
|
my $db_file = "data.db"; |
| 74 |
|
|
| 75 |
|
if (-e $db_file) { |
| 76 |
|
unlink $db_file or $log->logdie("can't remove '$db_file' from last run"); |
| 77 |
|
$log->debug("removed '$db_file' from last run"); |
| 78 |
|
} |
| 79 |
|
|
| 80 |
sub function2 { |
require DBM::Deep; |
| 81 |
|
|
| 82 |
|
my $db = new DBM::Deep $db_file; |
| 83 |
|
|
| 84 |
|
$log->logdie("DBM::Deep error: $!") unless ($db); |
| 85 |
|
|
| 86 |
|
if ($db->error()) { |
| 87 |
|
$log->logdie("can't open '$db_file' under low_mem: ",$db->error()); |
| 88 |
|
} else { |
| 89 |
|
$log->debug("using file '$db_file' for DBM::Deep"); |
| 90 |
|
} |
| 91 |
|
|
| 92 |
|
$self->{'db'} = $db; |
| 93 |
|
} |
| 94 |
|
|
| 95 |
|
$self ? return $self : return undef; |
| 96 |
} |
} |
| 97 |
|
|
| 98 |
=head1 AUTHOR |
=head1 MEMORY USAGE |
| 99 |
|
|
| 100 |
Dobrica Pavlinusic, C<< <dpavlin@rot13.org> >> |
C<low_mem> options is double-edged sword. If enabled, WebPAC |
| 101 |
|
will run on memory constraint machines (which doesn't have enough |
| 102 |
|
physical RAM to create memory structure for whole source database). |
| 103 |
|
|
| 104 |
|
If your machine has 512Mb or more of RAM and database is around 10000 records, |
| 105 |
|
memory shouldn't be an issue. If you don't have enough physical RAM, you |
| 106 |
|
might consider using virtual memory (if your operating system is handling it |
| 107 |
|
well, like on FreeBSD or Linux) instead of dropping to L<DBM::Deep> to handle |
| 108 |
|
parsed structure of ISIS database (this is what C<low_mem> option does). |
| 109 |
|
|
| 110 |
|
Hitting swap at end of reading source database is probably o.k. However, |
| 111 |
|
hitting swap before 90% will dramatically decrease performance and you will |
| 112 |
|
be better off with C<low_mem> and using rest of availble memory for |
| 113 |
|
operating system disk cache (Linux is particuallary good about this). |
| 114 |
|
However, every access to database record will require disk access, so |
| 115 |
|
generation phase will be slower 10-100 times. |
| 116 |
|
|
| 117 |
|
Parsed structures are essential - you just have option to trade RAM memory |
| 118 |
|
(which is fast) for disk space (which is slow). Be sure to have planty of |
| 119 |
|
disk space if you are using C<low_mem> and thus L<DBM::Deep>. |
| 120 |
|
|
| 121 |
|
However, when WebPAC is running on desktop machines (or laptops :-), it's |
| 122 |
|
highly undesireable for system to start swapping. Using C<low_mem> option can |
| 123 |
|
reduce WecPAC memory usage to around 64Mb for same database with lookup |
| 124 |
|
fields and sorted indexes which stay in RAM. Performance will suffer, but |
| 125 |
|
memory usage will really be minimal. It might be also more confortable to |
| 126 |
|
run WebPAC reniced on those machines. |
| 127 |
|
|
|
=head1 BUGS |
|
| 128 |
|
|
| 129 |
Please report any bugs or feature requests to |
=head1 AUTHOR |
|
C<bug-webpac-input@rt.cpan.org>, or through the web interface at |
|
|
L<http://rt.cpan.org/NoAuth/ReportBug.html?Queue=WebPAC>. |
|
|
I will be notified, and then you'll automatically be notified of progress on |
|
|
your bug as I make changes. |
|
| 130 |
|
|
| 131 |
=head1 ACKNOWLEDGEMENTS |
Dobrica Pavlinusic, C<< <dpavlin@rot13.org> >> |
| 132 |
|
|
| 133 |
=head1 COPYRIGHT & LICENSE |
=head1 COPYRIGHT & LICENSE |
| 134 |
|
|
Parent Directory
| 
Revision Log
| 
Patch