/[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 1.73 by wakaba, Sun Mar 2 23:38:37 2008 UTC revision 1.76 by wakaba, Mon Mar 3 09:17:10 2008 UTC
# Line 179  sub parse_string ($$$;$) { Line 179  sub parse_string ($$$;$) {
179    my $i = 0;    my $i = 0;
180    my $line = 1;    my $line = 1;
181    my $column = 0;    my $column = 0;
182    $self->{set_next_input_character} = sub {    $self->{set_next_char} = sub {
183      my $self = shift;      my $self = shift;
184    
185      pop @{$self->{prev_input_character}};      pop @{$self->{prev_char}};
186      unshift @{$self->{prev_input_character}}, $self->{next_input_character};      unshift @{$self->{prev_char}}, $self->{next_char};
187    
188      $self->{next_input_character} = -1 and return if $i >= length $$s;      $self->{next_char} = -1 and return if $i >= length $$s;
189      $self->{next_input_character} = ord substr $$s, $i++, 1;      $self->{next_char} = ord substr $$s, $i++, 1;
190      $column++;      $column++;
191            
192      if ($self->{next_input_character} == 0x000A) { # LF      if ($self->{next_char} == 0x000A) { # LF
193        $line++;        $line++;
194        $column = 0;        $column = 0;
195      } elsif ($self->{next_input_character} == 0x000D) { # CR      } elsif ($self->{next_char} == 0x000D) { # CR
196        $i++ if substr ($$s, $i, 1) eq "\x0A";        $i++ if substr ($$s, $i, 1) eq "\x0A";
197        $self->{next_input_character} = 0x000A; # LF # MUST        $self->{next_char} = 0x000A; # LF # MUST
198        $line++;        $line++;
199        $column = 0;        $column = 0;
200      } elsif ($self->{next_input_character} > 0x10FFFF) {      } elsif ($self->{next_char} > 0x10FFFF) {
201        $self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST        $self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST
202      } elsif ($self->{next_input_character} == 0x0000) { # NULL      } elsif ($self->{next_char} == 0x0000) { # NULL
203        !!!parse-error (type => 'NULL');        !!!parse-error (type => 'NULL');
204        $self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST        $self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST
205      }      }
206    };    };
207    $self->{prev_input_character} = [-1, -1, -1];    $self->{prev_char} = [-1, -1, -1];
208    $self->{next_input_character} = -1;    $self->{next_char} = -1;
209    
210    my $onerror = $_[2] || sub {    my $onerror = $_[2] || sub {
211      my (%opt) = @_;      my (%opt) = @_;
# Line 226  sub parse_string ($$$;$) { Line 226  sub parse_string ($$$;$) {
226  sub new ($) {  sub new ($) {
227    my $class = shift;    my $class = shift;
228    my $self = bless {}, $class;    my $self = bless {}, $class;
229    $self->{set_next_input_character} = sub {    $self->{set_next_char} = sub {
230      $self->{next_input_character} = -1;      $self->{next_char} = -1;
231    };    };
232    $self->{parse_error} = sub {    $self->{parse_error} = sub {
233      #      #
# Line 333  sub _initialize_tokenizer ($) { Line 333  sub _initialize_tokenizer ($) {
333    undef $self->{last_emitted_start_tag_name};    undef $self->{last_emitted_start_tag_name};
334    undef $self->{last_attribute_value_state};    undef $self->{last_attribute_value_state};
335    $self->{char} = [];    $self->{char} = [];
336    # $self->{next_input_character}    # $self->{next_char}
337    !!!next-input-character;    !!!next-input-character;
338    $self->{token} = [];    $self->{token} = [];
339    # $self->{escape}    # $self->{escape}
# Line 346  sub _initialize_tokenizer ($) { Line 346  sub _initialize_tokenizer ($) {
346  ##   ->{tag_name} (START_TAG_TOKEN, END_TAG_TOKEN)  ##   ->{tag_name} (START_TAG_TOKEN, END_TAG_TOKEN)