diff --git a/lib/Gscan2pdf/Page.pm b/lib/Gscan2pdf/Page.pm index 0fb2296..a397880 100644 --- a/lib/Gscan2pdf/Page.pm +++ b/lib/Gscan2pdf/Page.pm @@ -111,17 +111,27 @@ sub thaw { sub boxes { my ( $self, @boxes ) = @_; + # Unfortunately, there seems to be a case (tested in t/31_ocropus_utf8.t) + # where decode_entities doesn't work cleanly, so encode/decode to finally + # get good UTF-8 + $self->{hocr} = + decode_utf8( + encode_utf8( HTML::Entities::decode_entities( $self->{hocr} ) ) ); + if ( $self->{hocr} =~ /([\s\S]*)<\/body>/x ) { my $p = HTML::TokeParser->new( \$self->{hocr} ); my ( $x1, $y1, $x2, $y2, $text ); while ( my $token = $p->get_token ) { if ( $token->[0] eq 'S' ) { - if ( $token->[1] eq 'span' + if ( + $token->[1] eq 'span' and defined( $token->[2]{class} ) - and - ( $token->[2]{class} eq 'ocr_line' or $token->[2]{class} eq 'ocr_word' ) + and ( $token->[2]{class} eq 'ocr_line' + or $token->[2]{class} eq 'ocr_word' + or $token->[2]{class} eq 'ocrx_word' ) and defined( $token->[2]{title} ) - and $token->[2]{title} =~ /bbox\ (\d+)\ (\d+)\ (\d+)\ (\d+)/x ) + and $token->[2]{title} =~ /bbox\ (\d+)\ (\d+)\ (\d+)\ (\d+)/x + ) { ( $x1, $y1, $x2, $y2 ) = ( $1, $2, $3, $4 ); } @@ -134,13 +144,7 @@ sub boxes { } } if ( $token->[0] eq 'T' and $token->[1] !~ /^\s*$/x ) { - - # Unfortunately, there seems to be a case (tested in t/31_ocropus_utf8.t) - # where decode_entities doesn't work cleanly, so encode/decode to finally - # get good UTF-8 - $text = - decode_utf8( - encode_utf8( HTML::Entities::decode_entities( $token->[1] ) ) ); + $text = $token->[1]; chomp($text); } if ( $token->[0] eq 'E' ) {