Bug 12072: DBRev 3.21.00.056
[koha.git] / C4 / TTParser.pm
blob4c3a4a0d001e06c03a567bd1b898716828281920
1 #!/usr/bin/env perl
3 # Copyright Tamil 2011
5 # This file is part of Koha.
7 # Koha is free software; you can redistribute it and/or modify it
8 # under the terms of the GNU General Public License as published by
9 # the Free Software Foundation; either version 3 of the License, or
10 # (at your option) any later version.
12 # Koha is distributed in the hope that it will be useful, but
13 # WITHOUT ANY WARRANTY; without even the implied warranty of
14 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15 # GNU General Public License for more details.
17 # You should have received a copy of the GNU General Public License
18 # along with Koha; if not, see <http://www.gnu.org/licenses>.
20 #simple parser for HTML with Template Toolkit directives. Tokens are put into @tokens and are accesible via next_token and peep_token
21 package C4::TTParser;
22 use base qw(HTML::Parser);
23 use C4::TmplToken;
24 use strict;
25 use warnings;
27 #seems to be handled post tokenizer
28 ##hash where key is tag we are interested in and the value is a hash of the attributes we want
29 #my %interesting_tags = (
30 # img => { alt => 1 },
31 #);
33 #tokens found so far (used like a stack)
34 my ( @tokens );
36 #shiftnext token or undef
37 sub next_token{
38 return shift @tokens;
41 #unshift token back on @tokens
42 sub unshift_token{
43 my $self = shift;
44 unshift @tokens, shift;
47 #have a peep at next token
48 sub peep_token{
49 return $tokens[0];
52 #wrapper for parse
53 #please use this method INSTEAD of the HTML::Parser->parse_file method (and HTML::Parser->parse)
54 #signature build_tokens( self, filename)
55 sub build_tokens{
56 my ($self, $filename) = @_;
57 $self->{filename} = $filename;
58 $self->handler(start => "start", "self, line, tagname, attr, text"); #signature is start( self, linenumber, tagname, hash of attributes, original text )
59 $self->handler(text => "text", "self, line, text, is_cdata"); #signature is text( self, linenumber, original text, is_cdata )
60 $self->handler(end => "end", "self, line, tag, attr, text"); #signature is end( self, linenumber, tagename, original text )
61 $self->handler(declaration => "declaration", "self, line, text, is_cdata"); # declaration
62 $self->handler(comment => "comment", "self, line, text, is_cdata"); # comments
63 # $self->handler(default => "default", "self, line, text, is_cdata"); # anything else
64 $self->marked_sections(1); #treat anything inside CDATA tags as text, should really make it a C4::TmplTokenType::CDATA
65 $self->unbroken_text(1); #make contiguous whitespace into a single token (can span multiple lines)
66 $self->parse_file($filename);
67 return $self;
70 #handle parsing of text
71 sub text{
72 my $self = shift;
73 my $line = shift;
74 my $work = shift; # original text
75 my $is_cdata = shift;
76 while($work){
77 # if there is a template_toolkit tag
78 if( $work =~ m/\[%.*?%\]/ ){
79 #everything before this tag is text (or possibly CDATA), add a text token to tokens if $`
80 if( $` ){
81 my $t = C4::TmplToken->new( $`, ($is_cdata? C4::TmplTokenType::CDATA : C4::TmplTokenType::TEXT), $line, $self->{filename} );
82 push @tokens, $t;
85 #the match itself is a DIRECTIVE $&
86 my $t = C4::TmplToken->new( $&, C4::TmplTokenType::DIRECTIVE, $line, $self->{filename} );
87 push @tokens, $t;
89 # put work still to do back into work
90 $work = $' ? $' : 0;
91 } else {
92 # If there is some left over work, treat it as text token
93 my $t = C4::TmplToken->new( $work, ($is_cdata? C4::TmplTokenType::CDATA : C4::TmplTokenType::TEXT), $line, $self->{filename} );
95 push @tokens, $t;
96 last;
101 sub declaration {
102 my $self = shift;
103 my $line = shift;
104 my $work = shift; #original text
105 my $is_cdata = shift;
106 my $t = C4::TmplToken->new( $work, ($is_cdata? C4::TmplTokenType::CDATA : C4::TmplTokenType::TEXT), $line, $self->{filename} );
107 push @tokens, $t;
110 sub comment {
111 my $self = shift;
112 my $line = shift;
113 my $work = shift; #original text
114 my $is_cdata = shift;
115 my $t = C4::TmplToken->new( $work, ($is_cdata? C4::TmplTokenType::CDATA : C4::TmplTokenType::TEXT), $line, $self->{filename} );
116 push @tokens, $t;
119 sub default {
120 my $self = shift;
121 my $line = shift;
122 my $work = shift; #original text
123 my $is_cdata = shift;
124 my $t = C4::TmplToken->new( $work, ($is_cdata? C4::TmplTokenType::CDATA : C4::TmplTokenType::TEXT), $line, $self->{filename} );
125 push @tokens, $t;
129 #handle opening html tags
130 sub start{
131 my $self = shift;
132 my $line = shift;
133 my $tag = shift;
134 my $hash = shift; #hash of attr/value pairs
135 my $text = shift; #original text
136 my $t = C4::TmplToken->new( $text, C4::TmplTokenType::TAG, $line, $self->{filename});
137 my %attr;
138 # tags seem to be uses in an 'interesting' way elsewhere..
139 for my $key( %$hash ) {
140 next unless defined $hash->{$key};
141 if ($key eq "/"){
142 $attr{+lc($key)} = [ $key, $hash->{$key}, $key."=".$hash->{$key}, 1 ];
144 else {
145 $attr{+lc($key)} = [ $key, $hash->{$key}, $key."=".$hash->{$key}, 0 ];
148 $t->set_attributes( \%attr );
149 push @tokens, $t;
152 #handle closing html tags
153 sub end{
154 my $self = shift;
155 my $line = shift;
156 my $tag = shift;
157 my $hash = shift;
158 my $text = shift;
159 # what format should this be in?
160 my $t = C4::TmplToken->new( $text, C4::TmplTokenType::TAG, $line, $self->{filename} );
161 my %attr;
162 # tags seem to be uses in an 'interesting' way elsewhere..
163 for my $key( %$hash ) {
164 next unless defined $hash->{$key};
165 $attr{+lc($key)} = [ $key, $hash->{$key}, $key."=".$hash->{$key}, 0 ];
167 $t->set_attributes( \%attr );
168 push @tokens, $t;