13 |
|
|
14 |
=head1 NAME |
=head1 NAME |
15 |
|
|
16 |
WebPAC::Parser - parse perl normalization configuration files and mungle it |
WebPAC::Parser - parse perl normalization configuration files (rules) and mungle it |
17 |
|
|
18 |
=head1 VERSION |
=head1 VERSION |
19 |
|
|
20 |
Version 0.06 |
Version 0.07 |
21 |
|
|
22 |
=cut |
=cut |
23 |
|
|
24 |
our $VERSION = '0.06'; |
our $VERSION = '0.07'; |
25 |
|
|
26 |
=head1 SYNOPSIS |
=head1 SYNOPSIS |
27 |
|
|
28 |
This module will parse L<WebPAC::Normalize/lookup> directives and generate source |
This module will parse L<WebPAC::Normalize/lookup> directives and generate source |
29 |
to produce lookups and normalization. |
to produce lookups and normalization. It will also parse other parts of |
30 |
|
source to produce some of DWIM (I<Do What I Mean>) magic |
31 |
|
(like producing MARC oputput using L<WebPAC::Output::MARC> if there are C<marc_*> |
32 |
|
rules in normalisation). |
33 |
|
|
34 |
It's written using L<PPI>, pure-perl parser for perl and heavily influenced by |
It's written using L<PPI>, pure-perl parser for perl and heavily influenced by |
35 |
reading about LISP. It might be a bit over-the board, but at least it removed |
reading about LISP. It might be a bit over-the board, but at least it removed |
168 |
return $self->{_normalize_source}->{ _q($database) }->{ _q($input) }; |
return $self->{_normalize_source}->{ _q($database) }->{ _q($input) }; |
169 |
} |
} |
170 |
|
|
171 |
|
|
172 |
|
=head2 generate_marc |
173 |
|
|
174 |
|
my $do_marc = $parser->generate_marc($database, $input); |
175 |
|
|
176 |
|
This function will return hash containing count of all found C<marc_*> directives. |
177 |
|
|
178 |
|
=cut |
179 |
|
|
180 |
|
sub generate_marc { |
181 |
|
my $self = shift; |
182 |
|
my ($database,$input) = @_; |
183 |
|
$input = _input_name($input); |
184 |
|
return unless ( |
185 |
|
defined( $self->{_generate_marc}->{ _q($database) } ) && |
186 |
|
defined( $self->{_generate_marc}->{ _q($database) }->{ _q($input) } ) |
187 |
|
); |
188 |
|
return $self->{_generate_marc}->{ _q($database) }->{ _q($input) }; |
189 |
|
} |
190 |
|
|
191 |
|
|
192 |
=head1 PRIVATE |
=head1 PRIVATE |
193 |
|
|
194 |
=head2 _read_sources |
=head2 _read_sources |
206 |
|
|
207 |
my $nr = 0; |
my $nr = 0; |
208 |
|
|
209 |
my @lookups; |
my @sources; |
210 |
|
|
211 |
$self->{config}->iterate_inputs( sub { |
$self->{config}->iterate_inputs( sub { |
212 |
my ($input, $database) = @_; |
my ($input, $database) = @_; |
229 |
|
|
230 |
$self->{valid_inputs}->{$database}->{$input_name}++; |
$self->{valid_inputs}->{$database}->{$input_name}++; |
231 |
|
|
232 |
push @lookups, sub { |
push @sources, sub { |
233 |
$self->_parse_lookups( $database, $input_name, $full, $s ); |
$self->_parse_source( $database, $input_name, $full, $s ); |
234 |
}; |
}; |
235 |
|
|
236 |
$nr++; |
$nr++; |
239 |
|
|
240 |
$log->debug("found $nr source files"); |
$log->debug("found $nr source files"); |
241 |
|
|
242 |
# parse all lookups |
# parse all sources |
243 |
$_->() foreach (@lookups); |
$_->() foreach (@sources); |
244 |
|
|
245 |
return $nr; |
return $nr; |
246 |
} |
} |
247 |
|
|
248 |
=head2 _parse_lookups |
=head2 _parse_source |
249 |
|
|
250 |
$parser->_parse_lookups($database,$input,$path,$source); |
$parser->_parse_source($database,$input,$path,$source); |
251 |
|
|
252 |
Called for each normalize source (rules) in each input by L</_read_sources> |
Called for each normalize source (rules) in each input by L</_read_sources> |
253 |
|
|
255 |
|
|
256 |
=cut |
=cut |
257 |
|
|
258 |
sub _parse_lookups { |
sub _parse_source { |
259 |
my $self = shift; |
my $self = shift; |
260 |
my ($database, $input, $path, $source) = @_; |
my ($database, $input, $path, $source) = @_; |
261 |
|
|
386 |
|
|
387 |
$log->error("Parser errors:\n", join("\n",@{ $self->{_lookup_errors} }) ) if ($self->{_lookup_errors}); |
$log->error("Parser errors:\n", join("\n",@{ $self->{_lookup_errors} }) ) if ($self->{_lookup_errors}); |
388 |
|
|
389 |
|
$Document->find( sub { |
390 |
|
my ($Document,$Element) = @_; |
391 |
|
|
392 |
|
$Element->isa('PPI::Token::Word') or return ''; |
393 |
|
$Element->content =~ m/^marc/ or return ''; |
394 |
|
|
395 |
|
$log->debug("found marc output generation for $database/$input"); |
396 |
|
$self->{_generate_marc}->{ $database }->{ $input }->{ $Element->content }++; |
397 |
|
}); |
398 |
|
|
399 |
return 1; |
return 1; |
400 |
} |
} |
401 |
|
|