/[suikacvs]/markup/html/whatpm/Whatpm/HTML.pm.src
Suika

Diff of /markup/html/whatpm/Whatpm/HTML.pm.src

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 1.188 by wakaba, Sat Sep 20 10:20:47 2008 UTC revision 1.191 by wakaba, Mon Sep 22 06:04:29 2008 UTC
# Line 323  my $foreign_attr_xname = { Line 323  my $foreign_attr_xname = {
323    
324  ## ISSUE: xmlns:xlink="non-xlink-ns" is not an error.  ## ISSUE: xmlns:xlink="non-xlink-ns" is not an error.
325    
326  my $c1_entity_char = {  my $charref_map = {
327      0x0D => 0x000A,
328    0x80 => 0x20AC,    0x80 => 0x20AC,
329    0x81 => 0xFFFD,    0x81 => 0xFFFD,
330    0x82 => 0x201A,    0x82 => 0x201A,
# Line 356  my $c1_entity_char = { Line 357  my $c1_entity_char = {
357    0x9D => 0xFFFD,    0x9D => 0xFFFD,
358    0x9E => 0x017E,    0x9E => 0x017E,
359    0x9F => 0x0178,    0x9F => 0x0178,
360  }; # $c1_entity_char  }; # $charref_map
361    $charref_map->{$_} = 0xFFFD
362        for 0x0000..0x0008, 0x000B, 0x000E..0x001F, 0x007F,
363            0xD800..0xDFFF, 0xFDD0..0xFDDF, ## ISSUE: 0xFDEF
364            0xFFFE, 0xFFFF, 0x1FFFE, 0x1FFFF, 0x2FFFE, 0x2FFFF, 0x3FFFE, 0x3FFFF,
365            0x4FFFE, 0x4FFFF, 0x5FFFE, 0x5FFFF, 0x6FFFE, 0x6FFFF, 0x7FFFE,
366            0x7FFFF, 0x8FFFE, 0x8FFFF, 0x9FFFE, 0x9FFFF, 0xAFFFE, 0xAFFFF,
367            0xBFFFE, 0xBFFFF, 0xCFFFE, 0xCFFFF, 0xDFFFE, 0xDFFFF, 0xEFFFE,
368            0xEFFFF, 0xFFFFE, 0xFFFFF, 0x10FFFE, 0x10FFFF;
369    
370  sub parse_byte_string ($$$$;$) {  sub parse_byte_string ($$$$;$) {
371    my $self = shift;    my $self = shift;
# Line 401  sub parse_byte_stream ($$$$;$$) { Line 410  sub parse_byte_stream ($$$$;$$) {
410            ## TODO: Is this ok?  Transfer protocol's parameter should be            ## TODO: Is this ok?  Transfer protocol's parameter should be
411            ## interpreted in its semantics?            ## interpreted in its semantics?
412    
       ## ISSUE: Unsupported encoding is not ignored according to the spec.  
413        ($char_stream, $e_status) = $charset->get_decode_handle        ($char_stream, $e_status) = $charset->get_decode_handle
414            ($byte_stream, allow_error_reporting => 1,            ($byte_stream, allow_error_reporting => 1,
415             allow_fallback => 1);             allow_fallback => 1);
# Line 409  sub parse_byte_stream ($$$$;$$) { Line 417  sub parse_byte_stream ($$$$;$$) {
417          $self->{confident} = 1;          $self->{confident} = 1;
418          last SNIFFING;          last SNIFFING;
419        } else {        } else {
420          ## TODO: unsupported error          !!!parse-error (type => 'charset:not supported',
421                            layer => 'encode',
422                            line => 1, column => 1,
423                            value => $charset_name,
424                            level => $self->{level}->{uncertain});
425        }        }
426      }      }
427    
# Line 3171  sub _get_next_token ($) { Line 3183  sub _get_next_token ($) {
3183        my $code = $self->{s_kwd};        my $code = $self->{s_kwd};
3184        my $l = $self->{line_prev};        my $l = $self->{line_prev};
3185        my $c = $self->{column_prev};        my $c = $self->{column_prev};
3186        if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) {        if ($charref_map->{$code}) {
3187          !!!cp (1015);          !!!cp (1015);
3188          !!!parse-error (type => 'invalid character reference',          !!!parse-error (type => 'invalid character reference',
3189                          text => (sprintf 'U+%04X', $code),                          text => (sprintf 'U+%04X', $code),
3190                          line => $l, column => $c);                          line => $l, column => $c);
3191          $code = 0xFFFD;          $code = $charref_map->{$code};
3192        } elsif ($code > 0x10FFFF) {        } elsif ($code > 0x10FFFF) {
3193          !!!cp (1016);          !!!cp (1016);
3194          !!!parse-error (type => 'invalid character reference',          !!!parse-error (type => 'invalid character reference',
3195                          text => (sprintf 'U-%08X', $code),                          text => (sprintf 'U-%08X', $code),
3196                          line => $l, column => $c);                          line => $l, column => $c);
3197          $code = 0xFFFD;          $code = 0xFFFD;
       } elsif ($code == 0x000D) {  
         !!!cp (1017);  
         !!!parse-error (type => 'CR character reference',  
                         line => $l, column => $c);  
         $code = 0x000A;  
       } elsif (0x80 <= $code and $code <= 0x9F) {  
         !!!cp (1018);  
         !!!parse-error (type => 'C1 character reference',  
                         text => (sprintf 'U+%04X', $code),  
                         line => $l, column => $c);  
         $code = $c1_entity_char->{$code};  
3198        }        }
3199    
3200        if ($self->{prev_state} == DATA_STATE) {        if ($self->{prev_state} == DATA_STATE) {
# Line 3290  sub _get_next_token ($) { Line 3291  sub _get_next_token ($) {
3291        my $code = $self->{s_kwd};        my $code = $self->{s_kwd};
3292        my $l = $self->{line_prev};        my $l = $self->{line_prev};
3293        my $c = $self->{column_prev};        my $c = $self->{column_prev};
3294        if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) {        if ($charref_map->{$code}) {
3295          !!!cp (1008);          !!!cp (1008);
3296          !!!parse-error (type => 'invalid character reference',          !!!parse-error (type => 'invalid character reference',
3297                          text => (sprintf 'U+%04X', $code),                          text => (sprintf 'U+%04X', $code),
3298                          line => $l, column => $c);                          line => $l, column => $c);
3299          $code = 0xFFFD;          $code = $charref_map->{$code};
3300        } elsif ($code > 0x10FFFF) {        } elsif ($code > 0x10FFFF) {
3301          !!!cp (1009);          !!!cp (1009);
3302          !!!parse-error (type => 'invalid character reference',          !!!parse-error (type => 'invalid character reference',
3303                          text => (sprintf 'U-%08X', $code),                          text => (sprintf 'U-%08X', $code),
3304                          line => $l, column => $c);                          line => $l, column => $c);
3305          $code = 0xFFFD;          $code = 0xFFFD;
       } elsif ($code == 0x000D) {  
         !!!cp (1010);  
         !!!parse-error (type => 'CR character reference', line => $l, column => $c);  
         $code = 0x000A;  
       } elsif (0x80 <= $code and $code <= 0x9F) {  
         !!!cp (1011);  
         !!!parse-error (type => 'C1 character reference', text => (sprintf 'U+%04X', $code), line => $l, column => $c);  
         $code = $c1_entity_char->{$code};  
3306        }        }
3307    
3308        if ($self->{prev_state} == DATA_STATE) {        if ($self->{prev_state} == DATA_STATE) {
# Line 6816  sub _tree_construction_main ($) { Line 6809  sub _tree_construction_main ($) {
6809            } elsif ($token->{attributes}->{content}) {            } elsif ($token->{attributes}->{content}) {
6810              if ($token->{attributes}->{content}->{value}              if ($token->{attributes}->{content}->{value}
6811                  =~ /[Cc][Hh][Aa][Rr][Ss][Ee][Tt]                  =~ /[Cc][Hh][Aa][Rr][Ss][Ee][Tt]
6812                      [\x09-\x0D\x20]*=                      [\x09\x0A\x0C\x0D\x20]*=
6813                      [\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'|                      [\x09\x0A\x0C\x0D\x20]*(?>"([^"]*)"|'([^']*)'|
6814                      ([^"'\x09-\x0D\x20][^\x09-\x0D\x20\x3B]*))/x) {                      ([^"'\x09\x0A\x0C\x0D\x20][^\x09\x0A\x0C\x0D\x20\x3B]*))
6815                       /x) {
6816                !!!cp ('t336');                !!!cp ('t336');
6817                ## NOTE: Whether the encoding is supported or not is handled                ## NOTE: Whether the encoding is supported or not is handled
6818                ## in the {change_encoding} callback.                ## in the {change_encoding} callback.
Legend:
Removed from v.1.188  
changed lines
  Added in v.1.191
[email protected]
 ViewVC Help
Powered by ViewVC 1.1.24