-#!/usr/bin/env perl
+# Copyright Tamil 2011
+#
+# This file is part of Koha.
+#
+# Koha is free software; you can redistribute it and/or modify it
+# under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# Koha is distributed in the hope that it will be useful, but
+# WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with Koha; if not, see <http://www.gnu.org/licenses>.
+
#simple parser for HTML with Template Toolkit directives. Tokens are put into @tokens and are accesible via next_token and peep_token
package C4::TTParser;
use base qw(HTML::Parser);
sub build_tokens{
my ($self, $filename) = @_;
$self->{filename} = $filename;
- $self->handler(start => "start", "self, line, tagname, attr, text"); #signature is start( self, linenumber, tagname, hash of attributes, origional text )
- $self->handler(text => "text", "self, line, text, is_cdata"); #signature is text( self, linenumber, origional text, is_cdata )
- $self->handler(end => "end", "self, line, tag, attr, text"); #signature is end( self, linenumber, tagename, origional text )
+ $self->handler(start => "start", "self, line, tagname, attr, text"); #signature is start( self, linenumber, tagname, hash of attributes, original text )
+ $self->handler(text => "text", "self, line, text, is_cdata"); #signature is text( self, linenumber, original text, is_cdata )
+ $self->handler(end => "end", "self, line, tag, attr, text"); #signature is end( self, linenumber, tagename, original text )
$self->handler(declaration => "declaration", "self, line, text, is_cdata"); # declaration
$self->handler(comment => "comment", "self, line, text, is_cdata"); # comments
+ $self->handler(process => "process", "self, line, text, is_cdata"); # processing statement <?...?>
# $self->handler(default => "default", "self, line, text, is_cdata"); # anything else
$self->marked_sections(1); #treat anything inside CDATA tags as text, should really make it a C4::TmplTokenType::CDATA
$self->unbroken_text(1); #make contiguous whitespace into a single token (can span multiple lines)
- $self->parse_file($filename);
+ open(my $fh, "<:encoding(utf8)", $filename) || die "Cannot open $filename ($!)";
+ $self->parse_file($fh);
return $self;
}
my $is_cdata = shift;
while($work){
# if there is a template_toolkit tag
- if( $work =~ m/\[%.*?\]/ ){
+ if( $work =~ m/\[%.*?%\]/ ){
#everything before this tag is text (or possibly CDATA), add a text token to tokens if $`
if( $` ){
my $t = C4::TmplToken->new( $`, ($is_cdata? C4::TmplTokenType::CDATA : C4::TmplTokenType::TEXT), $line, $self->{filename} );
push @tokens, $t;
}
+sub process {
+ my $self = shift;
+ my $line = shift;
+ my $work = shift; #original text
+ my $is_cdata = shift;
+ my $t = C4::TmplToken->new( $work, ($is_cdata? C4::TmplTokenType::CDATA : C4::TmplTokenType::TEXT), $line, $self->{filename} );
+ push @tokens, $t;
+}
+
sub default {
my $self = shift;
my $line = shift;
my $line = shift;
my $tag = shift;
my $hash = shift; #hash of attr/value pairs
- my $text = shift; #origional text
+ my $text = shift; #original text
my $t = C4::TmplToken->new( $text, C4::TmplTokenType::TAG, $line, $self->{filename});
my %attr;
# tags seem to be uses in an 'interesting' way elsewhere..