Created
October 9, 2012 05:56
-
-
Save vovkasm/3856881 to your computer and use it in GitHub Desktop.
HTML::Tidy: fix inversed utf8::encode logic
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| diff --git a/lib/HTML/Tidy.pm b/lib/HTML/Tidy.pm | |
| index 26ee3b0..6393b00 100644 | |
| --- a/lib/HTML/Tidy.pm | |
| +++ b/lib/HTML/Tidy.pm | |
| @@ -223,7 +223,7 @@ sub parse { | |
| } | |
| my $html = join( '', @_ ); | |
| - utf8::encode($html) unless utf8::is_utf8($html); | |
| + utf8::encode($html) if utf8::is_utf8($html); | |
| my ($errorblock,$newline) = _tidy_messages( $html, | |
| $self->{config_file}, | |
| $self->{tidy_options} | |
| @@ -308,7 +308,7 @@ sub clean { | |
| } | |
| my $text = join( '', @_ ); | |
| - utf8::encode($text) unless utf8::is_utf8($text); | |
| + utf8::encode($text) if utf8::is_utf8($text); | |
| if ( defined $text ) { | |
| $text .= "\n"; | |
| } | |
| diff --git a/t/unicode.t b/t/unicode.t | |
| index 811b6fa..b88dcfd 100644 | |
| --- a/t/unicode.t | |
| +++ b/t/unicode.t | |
| @@ -4,7 +4,8 @@ | |
| use warnings; | |
| use strict; | |
| -use Test::More tests => 7; | |
| +use Test::More tests => 10; | |
| +use Encode (); | |
| BEGIN { | |
| use_ok( 'HTML::Tidy' ); | |
| @@ -43,6 +44,15 @@ $tidy->parse( '', $html ); | |
| @messages = $tidy->messages; | |
| is( scalar @messages, 0, q{There still shouldn't be any errors}); | |
| +# try send bytes to clean method | |
| +my $html2 = Encode::encode('utf8',$html); | |
| +ok(!utf8::is_utf8($html2), 'html2 is row bytes'); | |
| +my $clean2 = $tidy->clean( $html2 ); | |
| +ok(utf8::is_utf8($clean2), 'but cleaned output is string'); | |
| +$clean2 =~ s/"HTML Tidy.+w3\.org"/"Tidy"/; | |
| +$clean2 =~ s/"(HTML Tidy|tidyp).+w3\.org"/"Tidy"/; | |
| +is($clean2, $reference, q{Cleanup didn't break anything}); | |
| + | |
| __DATA__ | |
| <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN"> | |
| <html> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment