/[suikacvs]/markup/html/whatpm/Whatpm/CSS/Tokenizer.pm
Suika

Diff of /markup/html/whatpm/Whatpm/CSS/Tokenizer.pm

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

revision 1.11 by wakaba, Sat Sep 8 15:20:41 2007 UTC revision 1.18 by wakaba, Sun Jan 20 06:15:20 2008 UTC
# Line 1  Line 1 
1  package Whatpm::CSS::Tokenizer;  package Whatpm::CSS::Tokenizer;
2  use strict;  use strict;
3    our $VERSION=do{my @r=(q$Revision$=~/\d+/g);sprintf "%d."."%02d" x $#r,@r};
4    
5    require Exporter;
6    push our @ISA, 'Exporter';
7    
8  sub BEFORE_TOKEN_STATE () { 0 }  sub BEFORE_TOKEN_STATE () { 0 }
9  sub BEFORE_NMSTART_STATE () { 1 }  sub BEFORE_NMSTART_STATE () { 1 }
# Line 59  sub CDC_TOKEN () { 35 } Line 63  sub CDC_TOKEN () { 35 }
63  sub COMMENT_TOKEN () { 36 }  sub COMMENT_TOKEN () { 36 }
64  sub COMMENT_INVALID_TOKEN () { 37 }  sub COMMENT_INVALID_TOKEN () { 37 }
65  sub EOF_TOKEN () { 38 }  sub EOF_TOKEN () { 38 }
66    sub MINUS_TOKEN () { 39 }
67    sub STAR_TOKEN () { 40 }
68    sub VBAR_TOKEN () { 41 }
69    sub DOT_TOKEN () { 42 }
70    sub COLON_TOKEN () { 43 }
71    sub MATCH_TOKEN () { 44 }
72    sub EXCLAMATION_TOKEN () { 45 }
73    
74  our @TokenName = qw(  our @TokenName = qw(
75    0 IDENT ATKEYWORD HASH FUNCTION URI URI_INVALID URI_PREFIX URI_PREFIX_INVALID    0 IDENT ATKEYWORD HASH FUNCTION URI URI_INVALID URI_PREFIX URI_PREFIX_INVALID
# Line 66  our @TokenName = qw( Line 77  our @TokenName = qw(
77    0 DELIM PLUS GREATER COMMA TILDE DASHMATCH    0 DELIM PLUS GREATER COMMA TILDE DASHMATCH
78    PREFIXMATCH SUFFIXMATCH SUBSTRINGMATCH INCLUDES SEMICOLON    PREFIXMATCH SUFFIXMATCH SUBSTRINGMATCH INCLUDES SEMICOLON
79    LBRACE RBRACE LPAREN RPAREN LBRACKET RBRACKET S CDO CDC COMMENT    LBRACE RBRACE LPAREN RPAREN LBRACKET RBRACKET S CDO CDC COMMENT
80    COMMENT_INVALID EOF    COMMENT_INVALID EOF MINUS STAR VBAR DOT COLON MATCH EXCLAMATION
81    );
82    
83    our @EXPORT_OK = qw(
84      IDENT_TOKEN ATKEYWORD_TOKEN HASH_TOKEN FUNCTION_TOKEN URI_TOKEN
85      URI_INVALID_TOKEN URI_PREFIX_TOKEN URI_PREFIX_INVALID_TOKEN
86      STRING_TOKEN INVALID_TOKEN NUMBER_TOKEN DIMENSION_TOKEN PERCENTAGE_TOKEN
87      UNICODE_RANGE_TOKEN DELIM_TOKEN PLUS_TOKEN GREATER_TOKEN COMMA_TOKEN
88      TILDE_TOKEN DASHMATCH_TOKEN PREFIXMATCH_TOKEN SUFFIXMATCH_TOKEN
89      SUBSTRINGMATCH_TOKEN INCLUDES_TOKEN SEMICOLON_TOKEN LBRACE_TOKEN
90      RBRACE_TOKEN LPAREN_TOKEN RPAREN_TOKEN LBRACKET_TOKEN RBRACKET_TOKEN
91      S_TOKEN CDO_TOKEN CDC_TOKEN COMMENT_TOKEN COMMENT_INVALID_TOKEN EOF_TOKEN
92      MINUS_TOKEN STAR_TOKEN VBAR_TOKEN DOT_TOKEN COLON_TOKEN MATCH_TOKEN
93      EXCLAMATION_TOKEN
94  );  );
95    
96    our %EXPORT_TAGS = ('token' => [@EXPORT_OK]);
97    
98  sub new ($) {  sub new ($) {
99    my $self = bless {token => [], get_char => sub { -1 },    my $self = bless {token => [], get_char => sub { -1 }}, shift;
                     onerror => sub { }}, shift;  
100    return $self;    return $self;
101  } # new  } # new
102    
# Line 102  sub get_next_token ($) { Line 127  sub get_next_token ($) {
127      if ($self->{state} == BEFORE_TOKEN_STATE) {      if ($self->{state} == BEFORE_TOKEN_STATE) {
128        if ($self->{c} == 0x002D) { # -        if ($self->{c} == 0x002D) { # -
129          ## NOTE: |-| in |ident| in |IDENT|          ## NOTE: |-| in |ident| in |IDENT|
130          $self->{t} = {type => IDENT_TOKEN, value => '-', hyphen => 1};          $self->{t} = {type => IDENT_TOKEN, value => '-', hyphen => 1,
131                          line => $self->{line}, column => $self->{column}};
132          $self->{state} = BEFORE_NMSTART_STATE;          $self->{state} = BEFORE_NMSTART_STATE;
133          $self->{c} = $self->{get_char}->();          $self->{c} = $self->{get_char}->();
134          redo A;          redo A;
135        } elsif ($self->{c} == 0x0055 or $self->{c} == 0x0075) { # U or u        } elsif ($self->{c} == 0x0055 or $self->{c} == 0x0075) { # U or u
136          $self->{t} = {type => IDENT_TOKEN, value => chr $self->{c}};          $self->{t} = {type => IDENT_TOKEN, value => chr $self->{c},
137                          line => $self->{line}, column => $self->{column}};
138          $self->{c} = $self->{get_char}->();          $self->{c} = $self->{get_char}->();
139          if ($self->{c} == 0x002B) { # +          if ($self->{c} == 0x002B) { # +
140              my ($l, $c) = ($self->{line}, $self->{column});
141            $self->{c} = $self->{get_char}->();            $self->{c} = $self->{get_char}->();
142            if ((0x0030 <= $self->{c} and $self->{c} <= 0x0039) or # 0..9            if ((0x0030 <= $self->{c} and $self->{c} <= 0x0039) or # 0..9
143                (0x0041 <= $self->{c} and $self->{c} <= 0x0046) or # A..F                (0x0041 <= $self->{c} and $self->{c} <= 0x0046) or # A..F
144                (0x0061 <= $self->{c} and $self->{c} <= 0x0066) or # a..f                (0x0061 <= $self->{c} and $self->{c} <= 0x0066) or # a..f
145                $self->{c} == 0x003F) { # ?                $self->{c} == 0x003F) { # ?
146              $self->{t}->{value} .= '+' . chr $self->{c};              $self->{t}->{value} = chr $self->{c};
147              $self->{t}->{type} = UNICODE_RANGE_TOKEN;              $self->{t}->{type} = UNICODE_RANGE_TOKEN;
148              $self->{c} = $self->{get_char}->();              $self->{c} = $self->{get_char}->();
149              C: for (2..6) {              C: for (2..6) {
# Line 151  sub get_next_token ($) { Line 179  sub get_next_token ($) {
179                  #                  #
180                } else {                } else {
181                  my $token = $self->{t};                  my $token = $self->{t};
182                  $self->{t} = {type => IDENT_TOKEN, value => '-'};                  $self->{t} = {type => IDENT_TOKEN, value => '-',
183                                  line => $self->{line},
184                                  column => $self->{column}};
185                  $self->{state} = BEFORE_NMSTART_STATE;                  $self->{state} = BEFORE_NMSTART_STATE;
186                  # reprocess                  # reprocess
187                  return $token;                  return $token;
# Line 164  sub get_next_token ($) { Line 194  sub get_next_token ($) {
194              return $self->{t};              return $self->{t};
195              #redo A;              #redo A;
196            } else {            } else {
197              unshift @{$self->{token}}, {type => PLUS_TOKEN};              unshift @{$self->{token}},
198                    {type => PLUS_TOKEN, line => $l, column => $c};
199              $self->{state} = BEFORE_TOKEN_STATE;              $self->{state} = BEFORE_TOKEN_STATE;
200              # reprocess              # reprocess
201              return $self->{t};              return $self->{t};
# Line 180  sub get_next_token ($) { Line 211  sub get_next_token ($) {
211                 $self->{c} == 0x005F or # _                 $self->{c} == 0x005F or # _
212                 $self->{c} > 0x007F) { # nonascii                 $self->{c} > 0x007F) { # nonascii
213          ## NOTE: |nmstart| in |ident| in |IDENT|          ## NOTE: |nmstart| in |ident| in |IDENT|
214          $self->{t} = {type => IDENT_TOKEN, value => chr $self->{c}};          $self->{t} = {type => IDENT_TOKEN, value => chr $self->{c},
215                          line => $self->{line}, column => $self->{column}};
216          $self->{state} = NAME_STATE;          $self->{state} = NAME_STATE;
217          $self->{c} = $self->{get_char}->();          $self->{c} = $self->{get_char}->();
218          redo A;          redo A;
219        } elsif ($self->{c} == 0x005C) { # \        } elsif ($self->{c} == 0x005C) { # \
220          ## NOTE: |nmstart| in |ident| in |IDENT|          ## NOTE: |nmstart| in |ident| in |IDENT|
221          $self->{t} = {type => IDENT_TOKEN, value => ''};          $self->{t} = {type => IDENT_TOKEN, value => '',
222                          line => $self->{line}, column => $self->{column}};
223          $self->{state} = ESCAPE_OPEN_STATE; $q = 0;          $self->{state} = ESCAPE_OPEN_STATE; $q = 0;
224          $self->{c} = $self->{get_char}->();          $self->{c} = $self->{get_char}->();
225          redo A;          redo A;
226        } elsif ($self->{c} == 0x0040) { # @        } elsif ($self->{c} == 0x0040) { # @
227          ## NOTE: |@| in |ATKEYWORD|          ## NOTE: |@| in |ATKEYWORD|
228          $self->{t} = {type => ATKEYWORD_TOKEN, value => ''};          $self->{t} = {type => ATKEYWORD_TOKEN, value => '',
229                          line => $self->{line}, column => $self->{column}};
230          $self->{state} = AFTER_AT_STATE;          $self->{state} = AFTER_AT_STATE;
231          $self->{c} = $self->{get_char}->();          $self->{c} = $self->{get_char}->();
232          redo A;          redo A;
233        } elsif ($self->{c} == 0x0022 or $self->{c} == 0x0027) { # " or '        } elsif ($self->{c} == 0x0022 or $self->{c} == 0x0027) { # " or '
234          $self->{t} = {type => STRING_TOKEN, value => ''};          $self->{t} = {type => STRING_TOKEN, value => '',
235                          line => $self->{line}, column => $self->{column}};
236          $self->{state} = STRING_STATE; $q = $self->{c};          $self->{state} = STRING_STATE; $q = $self->{c};
237          $self->{c} = $self->{get_char}->();          $self->{c} = $self->{get_char}->();
238          redo A;          redo A;
239        } elsif ($self->{c} == 0x0023) { # #        } elsif ($self->{c} == 0x0023) { # #
240          ## NOTE: |#| in |HASH|.          ## NOTE: |#| in |HASH|.
241          $self->{t} = {type => HASH_TOKEN, value => ''};          $self->{t} = {type => HASH_TOKEN, value => '',
242                          line => $self->{line}, column => $self->{column}};
243          $self->{state} = HASH_OPEN_STATE;          $self->{state} = HASH_OPEN_STATE;
244          $self->{c} = $self->{get_char}->();          $self->{c} = $self->{get_char}->();
245          redo A;          redo A;
246        } elsif (0x0030 <= $self->{c} and $self->{c} <= 0x0039) { # 0..9        } elsif (0x0030 <= $self->{c} and $self->{c} <= 0x0039) { # 0..9
247          ## NOTE: |num|.          ## NOTE: |num|.
248          $self->{t} = {type => NUMBER_TOKEN, value => chr $self->{c}};          $self->{t} = {type => NUMBER_TOKEN, value => chr $self->{c},
249                          line => $self->{line}, column => $self->{column}};
250          $self->{state} = NUMBER_STATE;          $self->{state} = NUMBER_STATE;
251          $self->{c} = $self->{get_char}->();          $self->{c} = $self->{get_char}->();
252          redo A;          redo A;
253        } elsif ($self->{c} == 0x002E) { # .        } elsif ($self->{c} == 0x002E) { # .
254          ## NOTE: |num|.          ## NOTE: |num|.
255          $self->{t} = {type => NUMBER_TOKEN, value => '0'};          $self->{t} = {type => NUMBER_TOKEN, value => '0',
256                          line => $self->{line}, column => $self->{column}};
257          $self->{state} = NUMBER_FRACTION_STATE;          $self->{state} = NUMBER_FRACTION_STATE;
258          $self->{c} = $self->{get_char}->();          $self->{c} = $self->{get_char}->();
259          redo A;          redo A;
260        } elsif ($self->{c} == 0x002F) { # /        } elsif ($self->{c} == 0x002F) { # /
261            my ($l, $c) = ($self->{line}, $self->{column});
262          $self->{c} = $self->{get_char}->();          $self->{c} = $self->{get_char}->();
263          if ($self->{c} == 0x002A) { # *          if ($self->{c} == 0x002A) { # *
264            C: {            C: {
# Line 251  sub get_next_token ($) { Line 290  sub get_next_token ($) {
290          } else {          } else {
291            # stay in the state.            # stay in the state.
292            # reprocess            # reprocess
293            return {type => DELIM_TOKEN, value => '/'};            return {type => DELIM_TOKEN, value => '/', line => $l, column => $c};
294            #redo A;            #redo A;
295          }                  }        
296        } elsif ($self->{c} == 0x003C) { # <        } elsif ($self->{c} == 0x003C) { # <
297            my ($l, $c) = ($self->{line}, $self->{column});
298          ## NOTE: |CDO|          ## NOTE: |CDO|
299          $self->{c} = $self->{get_char}->();          $self->{c} = $self->{get_char}->();
300          if ($self->{c} == 0x0021) { # !          if ($self->{c} == 0x0021) { # !
# Line 264  sub get_next_token ($) { Line 304  sub get_next_token ($) {
304              if ($self->{c} == 0x002D) { # -              if ($self->{c} == 0x002D) { # -
305                $self->{state} = BEFORE_TOKEN_STATE;                $self->{state} = BEFORE_TOKEN_STATE;
306                $self->{c} = $self->{get_char}->();                $self->{c} = $self->{get_char}->();
307                return {type => CDO_TOKEN};                return {type => CDO_TOKEN, line => $l, column => $c};
308                #redo A;                #redo A;
309              } else {              } else {
310                unshift @{$self->{token}}, {type => DELIM_TOKEN, value => '!'};                unshift @{$self->{token}},
311                      {type => EXCLAMATION_TOKEN, line => $l, column => $c + 1};
312                ## NOTE: |-| in |ident| in |IDENT|                ## NOTE: |-| in |ident| in |IDENT|
313                $self->{t} = {type => IDENT_TOKEN, value => '-'};                $self->{t} = {type => IDENT_TOKEN, value => '-',
314                                line => $l, column => $c + 2};
315                $self->{state} = BEFORE_NMSTART_STATE;                $self->{state} = BEFORE_NMSTART_STATE;
316                #reprocess                #reprocess
317                return {type => DELIM_TOKEN, value => '<'};                return {type => DELIM_TOKEN, value => '<',
318                          line => $l, column => $c};
319                #redo A;                #redo A;
320              }              }
321            } else {            } else {
322              unshift @{$self->{token}}, {type => DELIM_TOKEN, value => '!'};              unshift @{$self->{token}}, {type => EXCLAMATION_TOKEN,
323                                            line => $l, column => $c + 1};
324              $self->{state} = BEFORE_TOKEN_STATE;              $self->{state} = BEFORE_TOKEN_STATE;
325              #reprocess              #reprocess
326              return {type => DELIM_TOKEN, value => '<'};              return {type => DELIM_TOKEN, value => '<',
327                        line => $l, column => $c};
328              #redo A;              #redo A;
329            }            }
330          } else {          } else {
331            $self->{state} = BEFORE_TOKEN_STATE;            $self->{state} = BEFORE_TOKEN_STATE;
332            #reprocess            #reprocess
333            return {type => DELIM_TOKEN, value => '<'};            return {type => DELIM_TOKEN, value => '<',
334                      line => $l, column => $c};
335            #redo A;            #redo A;
336          }          }
337        } elsif (my $t = {        } elsif (my $t = {
338                  0x003B => SEMICOLON_TOKEN, # ;                          0x0021 => EXCLAMATION_TOKEN, # !
339                  0x007B => LBRACE_TOKEN, # {                          0x002D => MINUS_TOKEN, # -
340                  0x007D => RBRACE_TOKEN, # }                          0x002E => DOT_TOKEN, # .
341                  0x0028 => LPAREN_TOKEN, # (                          0x003A => COLON_TOKEN, # :
342                  0x0029 => RPAREN_TOKEN, # )                          0x003B => SEMICOLON_TOKEN, # ;
343                  0x005B => LBRACKET_TOKEN, # [                          0x003D => MATCH_TOKEN, # =
344                  0x005D => RBRACKET_TOKEN, # ]                          0x007B => LBRACE_TOKEN, # {
345                            0x007D => RBRACE_TOKEN, # }
346                            0x0028 => LPAREN_TOKEN, # (
347                            0x0029 => RPAREN_TOKEN, # )
348                            0x005B => LBRACKET_TOKEN, # [
349                            0x005D => RBRACKET_TOKEN, # ]
350                 }->{$self->{c}}) {                 }->{$self->{c}}) {
351            my ($l, $c) = ($self->{line}, $self->{column});
352          # stay in the state          # stay in the state
353          $self->{c} = $self->{get_char}->();          $self->{c} = $self->{get_char}->($self);
354          return {type => $t};          return {type => $t, line => $l, column => $c};
355          # redo A;          # redo A;
356        } elsif ({        } elsif ({
357                  0x0020 => 1, # SP                  0x0020 => 1, # SP
# Line 308  sub get_next_token ($) { Line 360  sub get_next_token ($) {
360                  0x000A => 1, # \n                  0x000A => 1, # \n
361                  0x000C => 1, # \f                  0x000C => 1, # \f
362                 }->{$self->{c}}) {                 }->{$self->{c}}) {
363            my ($l, $c) = ($self->{line}, $self->{column});
364          W: {          W: {
365            $self->{c} = $self->{get_char}->();            $self->{c} = $self->{get_char}->();
366            if ({            if ({
# Line 324  sub get_next_token ($) { Line 377  sub get_next_token ($) {
377                              0x002C => COMMA_TOKEN, # ,                              0x002C => COMMA_TOKEN, # ,
378                              0x007E => TILDE_TOKEN, # ~                              0x007E => TILDE_TOKEN, # ~
379                             }->{$self->{c}}) {                             }->{$self->{c}}) {
380                my ($l, $c) = ($self->{line}, $self->{column});
381              # stay in the state              # stay in the state
382              $self->{c} = $self->{get_char}->();              $self->{c} = $self->{get_char}->();
383              return {type => $v};              return {type => $v, line => $l, column => $c};
384              #redo A;              #redo A;
385            } else {            } else {
386              # stay in the state              # stay in the state
387              # reprocess              # reprocess
388              return {type => S_TOKEN};              return {type => S_TOKEN, line => $l, column => $c};
389              #redo A;              #redo A;
390            }            }
391          } # W          } # W
# Line 341  sub get_next_token ($) { Line 395  sub get_next_token ($) {
395                          0x0024 => SUFFIXMATCH_TOKEN, # $                          0x0024 => SUFFIXMATCH_TOKEN, # $
396                          0x002A => SUBSTRINGMATCH_TOKEN, # *                          0x002A => SUBSTRINGMATCH_TOKEN, # *
397                         }->{$self->{c}}) {                         }->{$self->{c}}) {
398            my ($line, $column) = ($self->{line}, $self->{column});
399          my $c = $self->{c};          my $c = $self->{c};
400          $self->{c} = $self->{get_char}->();          $self->{c} = $self->{get_char}->();
401          if ($self->{c} == 0x003D) { # =          if ($self->{c} == 0x003D) { # =
402            # stay in the state            # stay in the state
403            $self->{c} = $self->{get_char}->();            $self->{c} = $self->{get_char}->();
404            return {type => $v};            return {type => $v, line => $line, column => $column};
405              #redo A;
406            } elsif ($v = {
407                           0x002A => STAR_TOKEN, # *
408                           0x007C => VBAR_TOKEN, # |
409                          }->{$c}) {
410              # stay in the state.
411              # reprocess
412              return {type => $v, line => $line, column => $column};
413            #redo A;            #redo A;
414          } else {          } else {
415            # stay in the state            # stay in the state
416            # reprocess            # reprocess
417            return {type => DELIM_TOKEN, value => chr $c};            return {type => DELIM_TOKEN, value => chr $c,
418                      line => $line, column => $column};
419            #redo A;            #redo A;
420          }          }
421        } elsif ($self->{c} == 0x002B) { # +        } elsif ($self->{c} == 0x002B) { # +
422            my ($l, $c) = ($self->{line}, $self->{column});
423          # stay in the state          # stay in the state
424          $self->{c} = $self->{get_char}->();          $self->{c} = $self->{get_char}->();
425          return {type => PLUS_TOKEN};          return {type => PLUS_TOKEN, line => $l, column => $c};
426          #redo A;          #redo A;
427        } elsif ($self->{c} == 0x003E) { # >        } elsif ($self->{c} == 0x003E) { # >
428            my ($l, $c) = ($self->{line}, $self->{column});
429          # stay in the state          # stay in the state
430          $self->{c} = $self->{get_char}->();          $self->{c} = $self->{get_char}->();
431          return {type => GREATER_TOKEN};          return {type => GREATER_TOKEN, line => $l, column => $c};
432          #redo A;          #redo A;
433        } elsif ($self->{c} == 0x002C) { # ,        } elsif ($self->{c} == 0x002C) { # ,
434            my ($l, $c) = ($self->{line}, $self->{column});
435          # stay in the state          # stay in the state
436          $self->{c} = $self->{get_char}->();          $self->{c} = $self->{get_char}->();
437          return {type => COMMA_TOKEN};          return {type => COMMA_TOKEN, line => $l, column => $c};
438          #redo A;          #redo A;
439        } elsif ($self->{c} == 0x007E) { # ~        } elsif ($self->{c} == 0x007E) { # ~
440            my ($l, $c) = ($self->{line}, $self->{column});
441          $self->{c} = $self->{get_char}->();          $self->{c} = $self->{get_char}->();
442          if ($self->{c} == 0x003D) { # =          if ($self->{c} == 0x003D) { # =
443            # stay in the state            # stay in the state
444            $self->{c} = $self->{get_char}->();            $self->{c} = $self->{get_char}->();
445            return {type => INCLUDES_TOKEN};            return {type => INCLUDES_TOKEN, line => $l, column => $c};
446            #redo A;            #redo A;
447          } else {          } else {
448            # stay in the state            # stay in the state
449            # reprocess            # reprocess
450            return {type => TILDE_TOKEN};            return {type => TILDE_TOKEN, line => $l, column => $c};
451            #redo A;            #redo A;
452          }          }
453        } elsif ($self->{c} == -1) {        } elsif ($self->{c} == -1) {
454          # stay in the state          # stay in the state
455          $self->{c} = $self->{get_char}->();          $self->{c} = $self->{get_char}->();
456          return {type => EOF_TOKEN};          return {type => EOF_TOKEN,
457                    line => $self->{line}, column => $self->{column}};
458          #redo A;          #redo A;
459        } else {        } else {
460          # stay in the state          # stay in the state
461          $self->{t} = {type => DELIM_TOKEN, value => chr $self->{c}};          $self->{t} = {type => DELIM_TOKEN, value => chr $self->{c},
462                          line => $self->{line}, column => $self->{column}};
463          $self->{c} = $self->{get_char}->();          $self->{c} = $self->{get_char}->();
464          return $self->{t};          return $self->{t};
465          #redo A;          #redo A;
# Line 417  sub get_next_token ($) { Line 487  sub get_next_token ($) {
487            if ($self->{c} == 0x003E) { # >            if ($self->{c} == 0x003E) { # >
488              $self->{state} = BEFORE_TOKEN_STATE;              $self->{state} = BEFORE_TOKEN_STATE;
489              $self->{c} = $self->{get_char}->();              $self->{c} = $self->{get_char}->();
490              return {type => CDC_TOKEN};              return {type => CDC_TOKEN,
491                        line => $self->{t}->{line},
492                        column => $self->{t}->{column}};
493              #redo A;              #redo A;
494            } else {            } else {
495              ## NOTE: |-|, |-|, $self->{c}              ## NOTE: |-|, |-|, $self->{c}
496              #$self->{t} = {type => IDENT_TOKEN, value => '-'};              #$self->{t} = {type => IDENT_TOKEN, value => '-'};
497                $self->{t}->{column}++;
498              # stay in the state              # stay in the state
499              # reconsume              # reconsume
500              return {type => DELIM_TOKEN, value => '-'};              return {type => MINUS_TOKEN,
501                        line => $self->{t}->{line},
502                        column => $self->{t}->{column} - 1};
503              #redo A;              #redo A;
504            }            }
505          } elsif ($self->{t}->{type} == DIMENSION_TOKEN) {          } elsif ($self->{t}->{type} == DIMENSION_TOKEN) {
506              my ($l, $c) = ($self->{line}, $self->{column}); # second '-'
507            $self->{c} = $self->{get_char}->();            $self->{c} = $self->{get_char}->();
508            if ($self->{c} == 0x003E) { # >            if ($self->{c} == 0x003E) { # >
509              unshift @{$self->{token}}, {type => CDC_TOKEN};              unshift @{$self->{token}}, {type => CDC_TOKEN};
# Line 438  sub get_next_token ($) { Line 514  sub get_next_token ($) {
514              return $self->{t};              return $self->{t};
515              #redo A;              #redo A;
516            } else {            } else {
517              ## NOTE: |-|, |-|, $self->{c}              ## NOTE: NUMBER, |-|, |-|, $self->{c}
518              my $t = $self->{t};              my $t = $self->{t};
519              $t->{type} = NUMBER_TOKEN;              $t->{type} = NUMBER_TOKEN;
520              $t->{value} = '';              $t->{value} = '';
521              $self->{t} = {type => IDENT_TOKEN, value => '-', hyphen => 1};              $self->{t} = {type => IDENT_TOKEN, value => '-', hyphen => 1,
522              unshift @{$self->{token}}, {type => DELIM_TOKEN, value => '-'};                            line => $l, column => $c};
523                unshift @{$self->{token}}, {type => MINUS_TOKEN,
524                                            line => $l, column => $c - 1};
525              # stay in the state              # stay in the state
526              # reconsume              # reconsume
527              return $t;              return $t;
# Line 458  sub get_next_token ($) { Line 536  sub get_next_token ($) {
536                
537        if ($self->{t}->{type} == DIMENSION_TOKEN) {        if ($self->{t}->{type} == DIMENSION_TOKEN) {
538          ## NOTE: |-| after |NUMBER|.          ## NOTE: |-| after |NUMBER|.
539          unshift @{$self->{token}}, {type => DELIM_TOKEN, value => '-'};          unshift @{$self->{token}}, {type => MINUS_TOKEN,
540                                        line => $self->{line},
541                                        column => $self->{column} - 1};
542            ## BUG: column might be wrong if on the line boundary.
543          $self->{state} = BEFORE_TOKEN_STATE;          $self->{state} = BEFORE_TOKEN_STATE;
544          # reprocess          # reprocess
545          $self->{t}->{type} = NUMBER_TOKEN;          $self->{t}->{type} = NUMBER_TOKEN;
# Line 468  sub get_next_token ($) { Line 549  sub get_next_token ($) {
549          ## NOTE: |-| not followed by |nmstart|.          ## NOTE: |-| not followed by |nmstart|.
550          $self->{state} = BEFORE_TOKEN_STATE;          $self->{state} = BEFORE_TOKEN_STATE;
551          # reprocess          # reprocess
552          return {type => DELIM_TOKEN, value => '-'};          return {type => MINUS_TOKEN,
553                    line => $self->{line}, column => $self->{column} - 1};
554            ## BUG: column might be wrong if on the line boundary.
555        }        }
556      } elsif ($self->{state} == AFTER_AT_STATE) {      } elsif ($self->{state} == AFTER_AT_STATE) {
557        if ((0x0041 <= $self->{c} and $self->{c} <= 0x005A) or # A..Z        if ((0x0041 <= $self->{c} and $self->{c} <= 0x005A) or # A..Z
# Line 491  sub get_next_token ($) { Line 574  sub get_next_token ($) {
574        } else {        } else {
575          $self->{state} = BEFORE_TOKEN_STATE;          $self->{state} = BEFORE_TOKEN_STATE;
576          # reprocess          # reprocess
577          return {type => DELIM_TOKEN, value => '@'};          return {type => DELIM_TOKEN, value => '@',
578                    line => $self->{t}->{line},
579                    column => $self->{t}->{column}};
580        }        }
581      } elsif ($self->{state} == AFTER_AT_HYPHEN_STATE) {      } elsif ($self->{state} == AFTER_AT_HYPHEN_STATE) {
582        if ((0x0041 <= $self->{c} and $self->{c} <= 0x005A) or # A..Z        if ((0x0041 <= $self->{c} and $self->{c} <= 0x005A) or # A..Z
# Line 511  sub get_next_token ($) { Line 596  sub get_next_token ($) {
596            return {type => DELIM_TOKEN, value => '@'};            return {type => DELIM_TOKEN, value => '@'};
597            #redo A;            #redo A;
598          } else {          } else {
599            unshift @{$self->{token}}, {type => DELIM_TOKEN, value => '-'};            unshift @{$self->{token}}, {type => MINUS_TOKEN};
600            $self->{t} = {type => IDENT_TOKEN, value => '-'};            $self->{t} = {type => IDENT_TOKEN, value => '-'};
601            $self->{state} = BEFORE_NMSTART_STATE;            $self->{state} = BEFORE_NMSTART_STATE;
602            # reprocess            # reprocess
# Line 524  sub get_next_token ($) { Line 609  sub get_next_token ($) {
609          $self->{c} = $self->{get_char}->();          $self->{c} = $self->{get_char}->();
610          redo A;          redo A;
611        } else {        } else {
612          unshift @{$self->{token}}, {type => DELIM_TOKEN, value => '-'};          unshift @{$self->{token}}, {type => MINUS_TOKEN};
613          $self->{state} = BEFORE_TOKEN_STATE;          $self->{state} = BEFORE_TOKEN_STATE;
614          # reprocess          # reprocess
615          return {type => DELIM_TOKEN, value => '@'};          return {type => DELIM_TOKEN, value => '@'};
# Line 586  sub get_next_token ($) { Line 671  sub get_next_token ($) {
671        } else {        } else {
672          $self->{state} = BEFORE_TOKEN_STATE;          $self->{state} = BEFORE_TOKEN_STATE;
673          # reprocess          # reprocess
674          return {type => DELIM_TOKEN, value => '#'};          return {type => DELIM_TOKEN, value => '#',
675                    line => $self->{t}->{line},
676                    column => $self->{t}->{column}};
677          #redo A;          #redo A;
678        }        }
679      } elsif ($self->{state} == NAME_STATE) {      } elsif ($self->{state} == NAME_STATE) {
# Line 816  sub get_next_token ($) { Line 903  sub get_next_token ($) {
903            redo A;            redo A;
904          } else {          } else {
905            ## Note: In |nl| in ... in |string| or |ident|.            ## Note: In |nl| in ... in |string| or |ident|.
           $self->{t}->{value} .= chr $self->{c};  
906            $self->{state} = STRING_STATE;            $self->{state} = STRING_STATE;
907            $self->{c} = $self->{get_char}->();            $self->{c} = $self->{get_char}->();
908            redo A;            redo A;
# Line 832  sub get_next_token ($) { Line 918  sub get_next_token ($) {
918                URI_PREFIX_TOKEN, URI_PREFIX_INVALID_TOKEN,                URI_PREFIX_TOKEN, URI_PREFIX_INVALID_TOKEN,
919                URI_PREFIX_INVALID_TOKEN, URI_PREFIX_INVALID_TOKEN,                URI_PREFIX_INVALID_TOKEN, URI_PREFIX_INVALID_TOKEN,
920            }->{$self->{t}->{type}};            }->{$self->{t}->{type}};
           $self->{t}->{value} .= "\x0D";  
921            $self->{state} = ESCAPE_BEFORE_LF_STATE;            $self->{state} = ESCAPE_BEFORE_LF_STATE;
922            $self->{c} = $self->{get_char}->();            $self->{c} = $self->{get_char}->();
923            redo A;            redo A;
924          } else {          } else {
925            ## Note: In |nl| in ... in |string| or |ident|.            ## Note: In |nl| in ... in |string| or |ident|.
           $self->{t}->{value} .= "\x0D";  
926            $self->{state} = ESCAPE_BEFORE_LF_STATE;            $self->{state} = ESCAPE_BEFORE_LF_STATE;
927            $self->{c} = $self->{get_char}->();            $self->{c} = $self->{get_char}->();
928            redo A;            redo A;
# Line 859  sub get_next_token ($) { Line 943  sub get_next_token ($) {
943            if ($self->{t}->{hyphen} and $self->{t}->{value} eq '-') {            if ($self->{t}->{hyphen} and $self->{t}->{value} eq '-') {
944              $self->{state} = BEFORE_TOKEN_STATE;              $self->{state} = BEFORE_TOKEN_STATE;
945              # reprocess              # reprocess
946              unshift @{$self->{token}}, {type => DELIM_TOKEN, value => '\\'};              unshift @{$self->{token}}, {type => DELIM_TOKEN, value => '\\',
947              unshift @{$self->{token}}, {type => DELIM_TOKEN, value => '-'};                                          line => $self->{line},
948                                            column => $self->{column} - 2};
949                unshift @{$self->{token}}, {type => MINUS_TOKEN,
950                                            line => $self->{line},
951                                            column => $self->{column} - 1};
952                ## BUG: line and column might be wrong if they are on the
953                ## line boundary.
954              $self->{t}->{type} = NUMBER_TOKEN;              $self->{t}->{type} = NUMBER_TOKEN;
955              $self->{t}->{value} = '';              $self->{t}->{value} = '';
956              return $self->{t};              return $self->{t};
# Line 868  sub get_next_token ($) { Line 958  sub get_next_token ($) {
958            } elsif (length $self->{t}->{value}) {            } elsif (length $self->{t}->{value}) {
959              $self->{state} = BEFORE_TOKEN_STATE;              $self->{state} = BEFORE_TOKEN_STATE;
960              # reprocess              # reprocess
961              unshift @{$self->{token}}, {type => DELIM_TOKEN, value => '\\'};              unshift @{$self->{token}}, {type => DELIM_TOKEN, value => '\\',
962                                            line => $self->{line},
963                                            column => $self->{column} - 1};
964                ## BUG: line and column might be wrong if they are on the
965                ## line boundary.
966              return $self->{t};              return $self->{t};
967              #redo A;              #redo A;
968            } else {            } else {
969              $self->{state} = BEFORE_TOKEN_STATE;              $self->{state} = BEFORE_TOKEN_STATE;
970              # reprocess              # reprocess
971              unshift @{$self->{token}}, {type => DELIM_TOKEN, value => '\\'};              unshift @{$self->{token}}, {type => DELIM_TOKEN, value => '\\',
972                                            line => $self->{line},
973                                            column => $self->{column} - 1};
974                ## BUG: line and column might be wrong if they are on the
975                ## line boundary.
976              $self->{t}->{type} = NUMBER_TOKEN;              $self->{t}->{type} = NUMBER_TOKEN;
977              $self->{t}->{value} = '';              $self->{t}->{value} = '';
978              return $self->{t};              return $self->{t};
# Line 884  sub get_next_token ($) { Line 982  sub get_next_token ($) {
982            if ($self->{t}->{hyphen} and $self->{t}->{value} eq '-') {            if ($self->{t}->{hyphen} and $self->{t}->{value} eq '-') {
983              $self->{state} = BEFORE_TOKEN_STATE;              $self->{state} = BEFORE_TOKEN_STATE;
984              # reprocess              # reprocess
985              unshift @{$self->{token}}, {type => DELIM_TOKEN, value => '\\'};              unshift @{$self->{token}}, {type => DELIM_TOKEN, value => '\\',
986              return {type => DELIM_TOKEN, value => '-'};                                          line => $self->{line},
987                                            column => $self->{column} - 2};
988                return {type => MINUS_TOKEN,
989                        line => $self->{line},
990                        column => $self->{column} - 1};
991                ## BUG: line and column might be wrong if they are on the
992                ## line boundary.
993              #redo A;              #redo A;
994            } elsif (length $self->{t}->{value}) {            } elsif (length $self->{t}->{value}) {
995              $self->{state} = BEFORE_TOKEN_STATE;              $self->{state} = BEFORE_TOKEN_STATE;
996              # reprocess              # reprocess
997              unshift @{$self->{token}}, {type => DELIM_TOKEN, value => '\\'};              unshift @{$self->{token}}, {type => DELIM_TOKEN, value => '\\',
998                                            line => $self->{line},
999                                            column => $self->{column} - 1};
1000                ## BUG: line and column might be wrong if they are on the
1001                ## line boundary.
1002              return $self->{t};              return $self->{t};
1003              #redo A;              #redo A;
1004            } else {            } else {
1005              $self->{state} = BEFORE_TOKEN_STATE;              $self->{state} = BEFORE_TOKEN_STATE;
1006              # reprocess              # reprocess
1007              return {type => DELIM_TOKEN, value => '\\'};              return {type => DELIM_TOKEN, value => '\\',
1008                        line => $self->{line},
1009                        column => $self->{column} - 1};
1010                ## BUG: line and column might be wrong if they are on the
1011                ## line boundary.
1012              #redo A;              #redo A;
1013            }            }
1014          }          }
# Line 905  sub get_next_token ($) { Line 1017  sub get_next_token ($) {
1017          $self->{c} = $self->{get_char}->();          $self->{c} = $self->{get_char}->();
1018          redo A;          redo A;
1019        } else {        } else {
1020          unshift @{$self->{token}}, {type => DELIM_TOKEN, value => '\\'};          unshift @{$self->{token}}, {type => DELIM_TOKEN, value => '\\',
1021                                        line => $self->{line},
1022                                        column => $self->{column} - 1};
1023            ## BUG: line and column might be wrong if they are on the
1024            ## line boundary.
1025          $self->{t}->{type} = {          $self->{t}->{type} = {
1026            STRING_TOKEN, INVALID_TOKEN,            STRING_TOKEN, INVALID_TOKEN,
1027            URI_TOKEN, URI_INVALID_TOKEN,            URI_TOKEN, URI_INVALID_TOKEN,
# Line 976  sub get_next_token ($) { Line 1092  sub get_next_token ($) {
1092          redo A;          redo A;
1093        }        }
1094      } elsif ($self->{state} == ESCAPE_BEFORE_LF_STATE) {      } elsif ($self->{state} == ESCAPE_BEFORE_LF_STATE) {
1095        ## NOTE: |\n| in |\r\n| in |unicode| in |escape|.        ## NOTE: |\n| in |\r\n| in |nl| in |escape|.
1096        if ($self->{c} == 0x000A) { # \n        if ($self->{c} == 0x000A) { # \n
         $self->{t}->{value} .= chr $self->{c};  
1097          $self->{state} = $q == 0 ? NAME_STATE :          $self->{state} = $q == 0 ? NAME_STATE :
1098              $q == 1 ? URI_UNQUOTED_STATE : STRING_STATE;              $q == 1 ? URI_UNQUOTED_STATE : STRING_STATE;
1099          $self->{c} = $self->{get_char}->();          $self->{c} = $self->{get_char}->();
# Line 1057  sub get_next_token ($) { Line 1172  sub get_next_token ($) {
1172          $self->{c} = $self->{get_char}->();          $self->{c} = $self->{get_char}->();
1173          redo A;          redo A;
1174        } else {        } else {
1175          unshift @{$self->{token}}, {type => DELIM_TOKEN, value => '.'};          unshift @{$self->{token}}, {type => DOT_TOKEN};
1176          $self->{t}->{number} = $self->{t}->{value};          $self->{t}->{number} = $self->{t}->{value};
1177          $self->{t}->{value} = '';          $self->{t}->{value} = '';
1178          $self->{state} = BEFORE_TOKEN_STATE;          $self->{state} = BEFORE_TOKEN_STATE;
# Line 1075  sub get_next_token ($) { Line 1190  sub get_next_token ($) {
1190        } else {        } else {
1191          $self->{state} = BEFORE_TOKEN_STATE;          $self->{state} = BEFORE_TOKEN_STATE;
1192          # reprocess          # reprocess
1193          return {type => DELIM_TOKEN, value => '.'};          return {type => DOT_TOKEN,
1194                    line => $self->{line}, column => $self->{column} - 1};
1195            ## BUG: line and column might be wrong if they are on the
1196            ## line boundary.
1197          #redo A;          #redo A;
1198        }        }
1199      } elsif ($self->{state} == NUMBER_DOT_NUMBER_STATE) {      } elsif ($self->{state} == NUMBER_DOT_NUMBER_STATE) {
# Line 1098  sub get_next_token ($) { Line 1216  sub get_next_token ($) {
1216    } # A    } # A
1217  } # get_next_token  } # get_next_token
1218    
1219    sub serialize_token ($$) {
1220      shift;
1221      my $t = shift;
1222    
1223      ## NOTE: This function is not intended for roundtrip-able serialization.
1224    
1225      if ($t->{type} == IDENT_TOKEN) {
1226        return $t->{value};
1227      } elsif ($t->{type} == ATKEYWORD_TOKEN) {
1228        return '@' . $t->{value};
1229      } elsif ($t->{type} == HASH_TOKEN) {
1230        return '#' . $t->{value};
1231      } elsif ($t->{type} == FUNCTION_TOKEN) {
1232        return $t->{value} . '(';
1233      } elsif ($t->{type} == URI_TOKEN) {
1234        return 'url(' . $t->{value} . ')';
1235      } elsif ($t->{type} == URI_INVALID_TOKEN) {
1236        return 'url(' . $t->{value};
1237      } elsif ($t->{type} == URI_PREFIX_TOKEN) {
1238        return 'url-prefix(' . $t->{value} . ')';
1239      } elsif ($t->{type} == URI_PREFIX_INVALID_TOKEN) {
1240        return 'url-prefix(' . $t->{value};
1241      } elsif ($t->{type} == STRING_TOKEN) {
1242        return '"' . $t->{value} . '"';
1243      } elsif ($t->{type} == INVALID_TOKEN) {
1244        return '"' . $t->{value};
1245      } elsif ($t->{type} == NUMBER_TOKEN) {
1246        return $t->{number};
1247      } elsif ($t->{type} == DIMENSION_TOKEN) {
1248        return $t->{number} . $t->{value};
1249      } elsif ($t->{type} == PERCENTAGE_TOKEN) {
1250        return $t->{number} . '%';
1251      } elsif ($t->{type} == UNICODE_RANGE_TOKEN) {
1252        return 'U+' . $t->{value};
1253      } elsif ($t->{type} == DELIM_TOKEN) {
1254        return $t->{value};
1255      } elsif ($t->{type} == PLUS_TOKEN) {
1256        return '+';
1257      } elsif ($t->{type} == GREATER_TOKEN) {
1258        return '>';
1259      } elsif ($t->{type} == COMMA_TOKEN) {
1260        return ',';
1261      } elsif ($t->{type} == TILDE_TOKEN) {
1262        return '~';
1263      } elsif ($t->{type} == DASHMATCH_TOKEN) {
1264        return '|=';
1265      } elsif ($t->{type} == PREFIXMATCH_TOKEN) {
1266        return '^=';
1267      } elsif ($t->{type} == SUFFIXMATCH_TOKEN) {
1268        return '$=';
1269      } elsif ($t->{type} == SUBSTRINGMATCH_TOKEN) {
1270        return '*=';
1271      } elsif ($t->{type} == INCLUDES_TOKEN) {
1272        return '~=';
1273      } elsif ($t->{type} == SEMICOLON_TOKEN) {
1274        return ';';
1275      } elsif ($t->{type} == LBRACE_TOKEN) {
1276        return '{';
1277      } elsif ($t->{type} == RBRACE_TOKEN) {
1278        return '}';
1279      } elsif ($t->{type} == LPAREN_TOKEN) {
1280        return '(';
1281      } elsif ($t->{type} == RPAREN_TOKEN) {
1282        return ')';
1283      } elsif ($t->{type} == LBRACKET_TOKEN) {
1284        return '[';
1285      } elsif ($t->{type} == RBRACKET_TOKEN) {
1286        return ']';
1287      } elsif ($t->{type} == S_TOKEN) {
1288        return ' ';
1289      } elsif ($t->{type} == CDO_TOKEN) {
1290        return '<!--';
1291      } elsif ($t->{type} == CDC_TOKEN) {
1292        return '-->';
1293      } elsif ($t->{type} == COMMENT_TOKEN) {
1294        return '/**/';
1295      } elsif ($t->{type} == COMMENT_INVALID_TOKEN) {
1296        return '/*';
1297      } elsif ($t->{type} == EOF_TOKEN) {
1298        return '{EOF}';
1299      } elsif ($t->{type} == MINUS_TOKEN) {
1300        return '-';
1301      } elsif ($t->{type} == STAR_TOKEN) {
1302        return '*';
1303      } elsif ($t->{type} == VBAR_TOKEN) {
1304        return '|';
1305      } elsif ($t->{type} == COLON_TOKEN) {
1306        return ':';
1307      } elsif ($t->{type} == MATCH_TOKEN) {
1308        return '=';
1309      } elsif ($t->{type} == EXCLAMATION_TOKEN) {
1310        return '!';
1311      } else {
1312        return '{'.$t->{type}.'}';
1313      }
1314    } # serialize_token
1315    
1316    =head1 LICENSE
1317    
1318    Copyright 2007 Wakaba <w@suika.fam.cx>
1319    
1320    This library is free software; you can redistribute it
1321    and/or modify it under the same terms as Perl itself.
1322    
1323    =cut
1324    
1325  1;  1;
1326  # $Date$  # $Date$
Legend:
Removed from v.1.11  
changed lines
  Added in v.1.18
admin@suikawiki.org
 ViewVC Help
Powered by ViewVC 1.1.24