view release on metacpan or  search on metacpan

sa-compile.raw  view on Meta::CPAN

my $RE2C_BIN        = '@@RE2C_BIN@@';           # substituted at 'make' time
use lib '@@INSTALLSITELIB@@';                   # substituted at 'make' time

use Errno qw(EBADF);
use File::Spec;
use Config;
use POSIX qw(locale_h setsid sigprocmask _exit);

POSIX::setlocale(LC_TIME,'C');

BEGIN {                          # see comments in "spamassassin.raw" for doco
  my @bin = File::Spec->splitpath($0);
  my $bin = ($bin[0] ? File::Spec->catpath(@bin[0..1], '') : $bin[1])
            || File::Spec->curdir;

  if (-e $bin.'/lib/Mail/SpamAssassin.pm'
        || !-e '@@INSTALLSITELIB@@/Mail/SpamAssassin.pm' )
  {
    my $searchrelative;
    $searchrelative = 1;    # disabled during "make install": REMOVEFORINST
    if ($searchrelative && $bin eq '../' && -e '../blib/lib/Mail/SpamAssassin.pm')
    {
      unshift ( @INC, '../blib/lib' );
    } else {
      foreach ( qw(lib ../lib/site_perl
                ../lib/spamassassin ../share/spamassassin/lib))
      {
        my $dir = File::Spec->catdir( $bin, split ( '/', $_ ) );
        if ( -f File::Spec->catfile( $dir, "Mail", "SpamAssassin.pm" ) )
        { unshift ( @INC, $dir ); last; }
      }
    }
  }
}

use Mail::SpamAssassin;
use Mail::SpamAssassin::Util qw(untaint_var exit_status_str);
use Mail::SpamAssassin::Logger;
use Getopt::Long;
use File::Copy;
use File::Path;
use Pod::Usage;
use Data::Dumper;

our %opt;
Mail::SpamAssassin::Util::clean_path_in_taint_mode();
untaint_var( \%ENV );

Getopt::Long::Configure(
  qw(bundling no_getopt_compat
    permute no_auto_abbrev no_ignore_case)
);

GetOptions(
  'list'		=> \$opt{'list'},
  'sudo'		=> \$opt{'sudo'},
  'quiet'               => \$opt{'quiet'},
  'keep-tmps'		=> \$opt{'keep-tmps'},

  'configpath|config-file|config-dir|c|C=s' => \$opt{'configpath'},
  'prefspath|prefs-file|p=s'                => \$opt{'prefspath'},
  'siteconfigpath=s'                        => \$opt{'siteconfigpath'},
  'updatedir=s'                             => \$opt{'updatedir'},
  'cf=s'                                    => \@{$opt{'cf'}},
  'debug|D:s'       => \$opt{'debug'},
  'help|h|?'        => \$opt{'help'},
  'version|V'       => \$opt{'version'},
  )
  or usage( 0, "Unknown option!" );

if ( defined $opt{'help'} ) {
  usage( 0, "For more information read the manual page" );
}
if ( defined $opt{'version'} ) {
  print "SpamAssassin version " . Mail::SpamAssassin::Version() . "\n"
    or die "error writing: $!";
  exit 0;
}

# Check for some dependencies and provide useful error messages if they aren't
# present
eval("use ExtUtils::MakeMaker");
if ($@) {
  print "$0 requires ExtUtils::MakeMaker for proper operation.\n"
    or die "error writing: $!";
  exit 1;
}
unless (qx($RE2C_BIN -V)) {
  print "$0 requires $RE2C_BIN for proper operation.\n"
    or die "error writing: $!";
  exit 1;
}

sub usage {
  my ( $exitval, $message ) = @_;
  $exitval ||= 64;

  if ($exitval == 0) {
    print_version();
    print("\n")  or die "error writing: $!";
  }
  pod2usage(
    -verbose => 0,
    -message => $message,
    -exitval => $exitval,
  );
}

# set debug areas, if any specified (only useful for command-line tools)
if (defined $opt{'debug'}) {
  $opt{'debug'} ||= 'all';
}

# at least info
$opt{'debug'} ||= 'info';

my $quiet = $opt{'quiet'} || 0;

# ensure the body-rule base extractor plugin is loaded, we use that
my $post_config = q(
  loadplugin Mail::SpamAssassin::Plugin::BodyRuleBaseExtractor

).join("\n", @{$opt{'cf'}})."\n";

my $spamtest = Mail::SpamAssassin->new(
  {
    rules_filename      => $opt{'configpath'},
    site_rules_filename => $opt{'siteconfigpath'},
    userprefs_filename  => $opt{'prefspath'},
    debug               => $opt{'debug'},
    local_tests_only    => 1,
    dont_copy_prefs     => 1,
    PREFIX              => $PREFIX,
    DEF_RULES_DIR       => $DEF_RULES_DIR,
    LOCAL_RULES_DIR     => $LOCAL_RULES_DIR,
    LOCAL_STATE_DIR     => $LOCAL_STATE_DIR,
    post_config_text    => $post_config,
  }
);

# appropriate BodyRuleBaseExtractor settings for rule2xs usage
$spamtest->{base_extract} = 1;
$spamtest->{bases_must_be_casei} = 1;
$spamtest->{bases_can_use_alternations} = 0;
$spamtest->{bases_can_use_quantifiers} = 0;
$spamtest->{bases_can_use_char_classes} = 0;
$spamtest->{bases_split_out_alternations} = 1;
$spamtest->{base_quiet} = $quiet;

if (defined $opt{'updatedir'}) {
  $opt{'updatedir'} = Mail::SpamAssassin::Util::untaint_file_path($opt{'updatedir'});
}
else {
  $opt{'updatedir'} = $spamtest->sed_path('__local_state_dir__/compiled/__perl_major_ver__/__version__');
}
my $installdir = $opt{'updatedir'};
if ((!defined $opt{'list'})
        && !$opt{'sudo'}
        && -d $installdir && !-w $installdir)
{
  die "sa-compile: cannot write to $installdir, aborting\n";
}

$spamtest->{bases_cache_dir} = $spamtest->get_and_create_userstate_dir()
                        ."/sa-compile.cache";

$spamtest->init(1);
my $conf = $spamtest->{conf};

# this actually extracts the base rules in the plugin, as a side-effect
my $res = $spamtest->lint_rules();
if ($res) {
  die "sa-compile: not compiling; 'spamassassin --lint' check failed!\n";
}

if ( defined $opt{'list'} ) {
  foreach my $ruletype (sort keys %{$conf->{base_orig}}) {
    print dump_base_strings($ruletype);
  }
}
else {
  compile_base_strings();
}

$spamtest->finish();

# make sure we notice any write errors while flushing output buffer
close STDOUT  or die "error closing STDOUT: $!";
close STDIN   or die "error closing STDIN: $!";

exit;

sa-compile.raw  view on Meta::CPAN

  $has_rules
};

XSLoader::load '$modname', \$VERSION;
}

1;
fnord__END__

fnord=head1 NAME

$modname - Efficient string matching for regexps found in $FILE

fnord=head1 SYNOPSIS

  use $modname;
  
  ...
  my \$match = ${modname}::scan(\$string);

fnord=head1 DESCRIPTION

This module was created by SpamAssassin with the aid of re2xs, which uses re2c
to create an XS library capable of scanning through a bunch of regular
expressions as defined in F<$FILE>.

See C<sa-compile> for more details.

fnord=cut
EOT

  $str =~ s/^fnord//gm;
  print FILE $str  or die "error writing to $PMFILE: $!";
  close FILE  or die "error closing $PMFILE: $!";
}

sub handle_fixup_error {
  my ($strat, $regexp, $reason) = @_;
  if ($strat) {
    warn "skipped: $regexp: $strat";
  }
}

##############################################################################

=head1 NAME

sa-compile - compile SpamAssassin ruleset into native code

=head1 SYNOPSIS

B<sa-compile> [options]

Options:

  --list                        Output base string list to STDOUT
  --sudo                        Use 'sudo' for privilege escalation
  --keep-tmps                   Keep temporary files instead of deleting
  -C path, --configpath=path, --config-file=path
                                Path to standard configuration dir
  -p prefs, --prefspath=file, --prefs-file=file
                                Set user preferences file
  --siteconfigpath=path         Path for site configs
                                (default: @@PREFIX@@/etc/mail/spamassassin)
  --updatedir=path              Directory to place updates
          (default: @@LOCAL_STATE_DIR@@/compiled/<perlversion>/@@VERSION@@)
  --cf='config line'            Additional line of configuration
  -D, --debug [area=n,...]	Print debugging messages
  -V, --version			Print version
  -h, --help			Print usage message

=head1 DESCRIPTION

sa-compile uses C<re2c> to compile the site-wide parts of the SpamAssassin
ruleset. No part of user_prefs or any files included from user_prefs can be
built into the compiled set.

This compiled set is then used by the 
C<Mail::SpamAssassin::Plugin::Rule2XSBody> plugin to speed up
SpamAssassin's operation, where possible, and when that plugin is loaded.

C<re2c> can match strings much faster than perl code, by constructing a DFA to
match many simple strings in parallel, and compiling that to native object
code.  Not all SpamAssassin rules are amenable to this conversion, however.

This requires C<re2c> (see C<https://re2c.org/>), and the C
compiler used to build Perl XS modules, be installed.

Note that running this, and creating a compiled ruleset, will have no
effect on SpamAssassin scanning speeds unless you also edit your C<v320.pre>
file and ensure this line is uncommented:

  loadplugin Mail::SpamAssassin::Plugin::Rule2XSBody

Additionally, "sa-compile" will not restart "spamd" or otherwise cause a scanner to
reload the now-compiled ruleset automatically.

=head1 OPTIONS

=over 4

=item B<--list>

Output the extracted base strings to STDOUT, instead of generating
the C extension code.

=item B<--sudo>

Use C<sudo(8)> to run code as 'root' when writing files to the compiled-rules
storage area (which is C<@@LOCAL_STATE_DIR@@/compiled/@@PERL_MAJOR_VER@@/@@VERSION@@> by default).

=item B<--quiet>

Produce less diagnostic output.  Errors will still be displayed.

=item B<--keep-tmps>

Keep temporary files after the script completes, instead of
deleting them.

=item B<-C> I<path>, B<--configpath>=I<path>, B<--config-file>=I<path>

Use the specified path for locating the distributed configuration files.
Ignore the default directories (usually C</usr/share/spamassassin> or similar).

=item B<--siteconfigpath>=I<path>

Use the specified path for locating site-specific configuration files.  Ignore
the default directories (usually C</etc/mail/spamassassin> or similar).

=item B<--updatedir>

By default, C<sa-compile> will use the system-wide rules update directory:

        @@LOCAL_STATE_DIR@@/compiled/@@PERL_MAJOR_VER@@/@@VERSION@@

If the updates should be stored in another location, specify it here.

Note that use of this option is not recommended; if sa-compile is placing the
compiled rules the wrong directory, you probably need to rebuild SpamAssassin
with different C<Makefile.PL> arguments, instead of overriding sa-compile's
runtime behaviour.

=item B<--cf='config line'>

Add additional lines of configuration directly from the command-line, parsed
after the configuration files are read.   Multiple B<--cf> arguments can be
used, and each will be considered a separate line of configuration.

=item B<-p> I<prefs>, B<--prefspath>=I<prefs>, B<--prefs-file>=I<prefs>

Read user score preferences from I<prefs> (usually
C<$HOME/.spamassassin/user_prefs>) .

=item B<-D> [I<area,...>], B<--debug> [I<area,...>]

Produce debugging output.  If no areas are listed, all debugging information is
printed.  Diagnostic output can also be enabled for each area individually;
I<area> is the area of the code to instrument.

For more information about which areas (also known as channels) are
available, please see the documentation at
L<https://wiki.apache.org/spamassassin/DebugChannels>.

=item B<-h>, B<--help>

Print help message and exit.

=item B<-V>, B<--version>

Print sa-compile version and exit.

=back

=head1 SEE ALSO

Mail::SpamAssassin(3)
spamassassin(1)
spamd(1)

=head1 PREREQUISITES

C<Mail::SpamAssassin>
C<re2c>
C<Mail::SpamAssassin::Plugin::Rule2XSBody>

=head1 BUGS

See E<lt>https://bz.apache.org/SpamAssassin/E<gt>

=head1 AUTHORS

The Apache SpamAssassin(tm) Project E<lt>https://spamassassin.apache.org/E<gt>

=head1 LICENSE AND COPYRIGHT

SpamAssassin is distributed under the Apache License, Version 2.0, as
described in the file C<LICENSE> included with the distribution.

Copyright (C) 2015 The Apache Software Foundation


=cut