File Coverage

blib/lib/Regexp/Log/Common.pm

Criterion	Covered	Total	%
statement	12	12	100.0
branch			n/a
condition			n/a
subroutine	4	4	100.0
pod			n/a
total	16	16	100.0

package Regexp::Log::Common;

use warnings;
use strict;
use base qw( Regexp::Log );
use vars qw( $VERSION %DEFAULT %FORMAT %REGEXP );

$VERSION = '0.10';

=head1 NAME

Regexp::Log::Common - A regular expression parser for the Common Log Format

=head1 SYNOPSIS

    my $foo = Regexp::Log::Common->new(
        format  => '%date %request',
        capture => [qw( ts request )],
    );

    # the format() and capture() methods can be used to set or get
    $foo->format('%date %request %status %bytes');
    $foo->capture(qw( ts req ));

    # this is necessary to know in which order
    # we will receive the captured fields from the regexp
    my @fields = $foo->capture;

    # the all-powerful capturing regexp :-)
    my $re = $foo->regexp;

    while (<>) {
        my %data;
        @data{@fields} = /$re/;    # no need for /o, it's a compiled regexp

        # now munge the fields
        ...
    }

=head1 DESCRIPTION

Regexp::Log::Common uses Regexp::Log as a base class, to generate regular
expressions for performing the usual data munging tasks on log files that
cannot be simply split().

This specific module enables the computation of regular expressions for
parsing the log files created using the Common Log Format. An example of
this format are the logs generated by the httpd web server using the
keyword 'common'.

The module also allows for the use of the Extended Common Log Format.

For more information on how to use this module, please see Regexp::Log.

=head1 ABSTRACT

Enables simple parsing of log files created using the Common Log Format or the
Extended Common Log Format, such as the logs generated by the httpd/Apache web
server using the keyword 'common'.

=cut

# default values
%DEFAULT = (
    format  => '%host %rfc %authuser %date %request %status %bytes %referer %useragent',
    capture => [ 'host', 'rfc', 'authuser', 'date', 'ts', 'request', 'req',
                 'status', 'bytes', 'referer', 'ref', 'useragent', 'ua' ],
);

# predefined format strings
%FORMAT = (
    ':default'  => '%host %rfc %authuser %date %request %status %bytes',
    ':common'   => '%host %rfc %authuser %date %request %status %bytes',
    ':extended' => '%host %rfc %authuser %date %request %status %bytes %referer %useragent',
);

# the regexps that match the various fields
%REGEXP = (
#   %a  Remote IP-address
#   %A  Local IP-address
    '%a'            => '(?#=a)\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}(?#!a)',
    '%A'            => '(?#=A)\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}(?#!A)',
    '%remoteip'     => '(?#=remoteip)\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}(?#!remoteip)',
    '%localip'      => '(?#=localip)\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}(?#!localip)',

#   %B  Size of response in bytes, excluding HTTP headers.
#   %b  Size of response in bytes, excluding HTTP headers. In CLF format, i.e. a '-' rather than a 0 when no bytes are sent.
    '%B'            => '(?#=B)\d+(?#!B)',                                   # bytes (non-CLF format)
    '%b'            => '(?#=b)-|\d+(?#!b)',                                 # bytes (CLF format)
    '%bytes'        => '(?#=bytes)-|\d+(?#!bytes)',                         # bytes (CLF and non-CLF format)

#   %D  The time taken to serve the request, in microseconds.
    '%D'            => '(?#=D)\d+(?#!D)',                                   # response time (in microseconds)
    '%time'         => '(?#=time)\d+(?#!time)',                             # response time (in microseconds)

#   %f  Filename
    '%F'            => '(?#=F)\S+(?#!F)',                                   # filename
    '%filename'     => '(?#=filename)\S+(?#!filename)',                     # filename

#   %h  Remote host
    '%h'            => '(?#=h)\S+(?#!h)',                                   # numeric or name of remote host
    '%host'         => '(?#=host)\S+(?#!host)',                             # numeric or name of remote host
    '%remotehost'   => '(?#=remotehost)\S+(?#!remotehost)',                 # numeric or name of remote host

#   %H  The request protocol
    '%H'            => '(?#=H)\S+(?#!H)',                                   # protocol
    '%protcol'      => '(?#=protocol)\S+(?#!protocol)',                     # protocol

#   %{Foobar}i  The contents of Foobar: header line(s) in the request sent to the server.
    '%referer'      => '(?#=referer)\"(?#=ref).*?(?#!ref)\"(?#!referer)',   # "referer"     from \"%{Referer}i\"
    '%useragent'    => '(?#=useragent)\"(?#=ua).*?(?#!ua)\"(?#!useragent)', # "user_agent"  from \"%{User-Agent}i\"

#   %k  Number of keepalive requests handled on this connection. Interesting if KeepAlive is being used, so that, for example, a '1' means the first keepalive request after the initial one, '2' the second, etc...; otherwise this is always 0 (indicating the initial request). Available in versions 2.2.11 and later.
    '%k'            => '(?#=k)\d+(?#!k)',                                   # keep alive requests
    '%keepalive'    => '(?#=keepalive)\d+(?#!keepalive)',                   # keep alive requests

#   %l  Remote logname (from identd, if supplied). This will return a dash unless mod_ident is present and IdentityCheck is set On.
    '%l'            => '(?#=F)\S+(?#!F)',                                   # logname
    '%logname'      => '(?#=logname)\S+(?#!logname)',                       # logname
    '%rfc'          => '(?#=rfc)\S+(?#!rfc)',                               # rfc931

#   %m  The request method
    '%m'            => '(?#=F)\S+(?#!F)',                                   # request method
    '%method'       => '(?#=method)\S+(?#!method)',                         # request method

#   %p  The canonical port of the server serving the request
    '%p'            => '(?#=p)\d+(?#!p)',                                   # port
    '%port'         => '(?#=port)\d+(?#!port)',                             # port

#   %P  The process ID of the child that serviced the request.
    '%P'            => '(?#=P)\d+(?#!P)',                                   # process id
    '%pid'          => '(?#=pid)\d+(?#!pid)',                               # process id

#   %q  The query string (prepended with a ? if a query string exists, otherwise an empty string)
    '%q'            => '(?#=q)\".*?\"(?#!q)',                                   # "query string"
    '%queryatring'  => '(?#=queryatring)\"(?#=qs).*?(?#!qs)\"(?#!queryatring)', # "query string"

#   %r  First line of request
    '%r'            => '(?#=r)\".*?\"(?#!r)',                               # "request"
    '%request'      => '(?#=request)\"(?#=req).*?(?#!req)\"(?#!request)',   # "request"

#   %s  Status. For requests that got internally redirected, this is the status of the *original* request --- %>s for the last.
    '%s'            => '(?#=s)\d+(?#!s)',                                   # status
    '%status'       => '(?#=status)\d+(?#!status)',                         # status

#   %t  Time the request was received (standard english format)
    '%t'            => '(?#=t)\[\d{2}\/\w{3}\/\d{4}(?::\d{2}){3} [-+]\d{4}\](?#!t)',                        # [date] (see note 1)
    '%date'         => '(?#=date)\[(?#=ts)\d{2}\/\w{3}\/\d{4}(?::\d{2}){3} [-+]\d{4}(?#!ts)\](?#!date)',    # [date] (see note 1)

#   %T  The time taken to serve the request, in seconds.
    '%T'            => '(?#=T)\d+(?#!T)',                                   # response time (in seconds)
    '%seconds'         => '(?#=seconds)\d+(?#!seconds)',                    # response time (in seconds)

#   %u  Remote user (from auth; may be bogus if return status (%s) is 401)
    '%u'            => '(?#=u)\S+(?#!u)',                                   # authuser
    '%authuser'     => '(?#=authuser)\S+(?#!authuser)',                     # authuser

#   %U  The URL path requested, not including any query string.
    '%U'            => '(?#U)\".*?\"(?#!U)',                                # request
    '%request'      => '(?#=request)\"(?#=req).*?(?#!req)\"(?#!request)',   # "request"

#   %v  The canonical ServerName of the server serving the request.
#   %V  The server name according to the UseCanonicalName setting.
    '%v'            => '(?#=v)\S+(?#!v)',                                   # server name
    '%V'            => '(?#=V)\S+(?#!V)',                                   # server name
    '%servername'   => '(?#=servername)\S+(?#!servername)',                 # server name


#   %X  Connection status when response is completed:
    '%X'            => '(?#=X)\S+(?#!X)',                                   # connection status (X, + or -)
    '%connection'   => '(?#=connection)\S+(?#!connection)',                 # connection status (X, + or -)

#   %I  Bytes received, including request and headers, cannot be zero. You need to enable mod_logio to use this.
#   %O  Bytes sent, including headers, cannot be zero. You need to enable mod_logio to use this.
    '%I'            => '(?#=I)\S+(?#!I)',                                   # Bytes recieved
    '%O'            => '(?#=O)\S+(?#!O)',                                   # Bytes sent
);

# note 1: date is in the format [01/Jan/1997:13:07:21 -0600]

1;

__END__