File Coverage

File:blib/lib/CSS/Grammar/CSS20.pm
Coverage:100.0%

linestmtbrancondsubtimecode
1package CSS::Grammar::CSS20;
2
3
4
4
4
4
21
7
22
use strict;
4
4
4
4
4
23
101
20
use warnings;
5
6
4
4
4
4
26
8
24
use base 'CSS::Grammar';
7
8#
9# http://www.w3.org/TR/1998/REC-CSS2-19980512/Overview.html
10# http://www.w3.org/TR/REC-CSS2/grammar.html
11# http://www.w3.org/TR/REC-CSS2/syndata.html#parsing-errors
12#
13
14sub init {
15
4
4
11
        my ($self) = @_;
16
17
4
8
        my %rx;
18
19        #####################################################################################
20
21        #%option case-insensitive
22
23
4
10
        $self->{case_insensitive} = 1;
24
25
26        #####################################################################################
27
28        #h [0-9a-f]
29        #nonascii [\200-\377]
30        #unicode \\{h}{1,6}[ \t\r\n\f]?
31        #escape {unicode}|\\[ -~\200-\377]
32        #w [ \t\r\n\f]*
33        #nl \n|\r\n|\r|\f
34
35
4
13
        $rx{h} = '[0-9a-f]';
36
4
11
        $rx{nonascii} = '[\\x80-\\xff]';
37
4
20
        $rx{unicode} = '(\\'.$rx{h}.'{1,6}(\\r\\n|[ \\t\\r\\n\\f])?)';
38
4
18
        $rx{escape} = '('.$rx{unicode}.'|\\\\[ -~\\x80-\\xff])';
39
4
11
        $rx{w} = '[ \t\r\n\f]*';
40
4
12
        $rx{nl} = '(\\n|\\r\\n|\\r|\\f)';
41
42
43        #nmstart [a-z]|{nonascii}|{escape}
44        #nmchar [a-z0-9-]|{nonascii}|{escape}
45        #string1 \"([\t !#$%&(-~]|\\{nl}|\'|{nonascii}|{escape})*\"
46        #string2 \'([\t !#$%&(-~]|\\{nl}|\"|{nonascii}|{escape})*\'
47
48
4
24
        $rx{nmstart} = '([_a-z]|'.$rx{nonascii}.'|'.$rx{escape}.')';
49
4
26
        $rx{nmchar} = '([_a-zA-Z0-9-]|'.$rx{nonascii}.'|'.$rx{escape}.')';
50
4
29
        $rx{string1} = '("([\\t !#$%&(-~]|\\\\('.$rx{nl}.')|\'|('.$rx{nonascii}.')|('.$rx{escape}.'))*")';
51
4
27
        $rx{string2} = '(\'([\\t !#$%&(-~]|\\\\('.$rx{nl}.')|"|('.$rx{nonascii}.')|('.$rx{escape}.'))*\')';
52
53
54        #ident {nmstart}{nmchar}*
55        #name {nmchar}+
56        #num [0-9]+|[0-9]*"."[0-9]+
57        #string {string1}|{string2}
58        #url ([!#$%&*-~]|{nonascii}|{escape})*
59        #range \?{1,6}|{h}(\?{0,5}|{h}(\?{0,4}|{h}(\?{0,3}|{h}(\?{0,2}|{h}(\??|{h})))))
60
61
4
20
        $rx{ident} = "$rx{nmstart}$rx{nmchar}*";
62
4
20
        $rx{name} = "$rx{nmchar}+";
63
4
11
        $rx{num} = '([0-9]+|[0-9]*\\.[0-9]+)';
64
4
24
        $rx{string} = "($rx{string1}|$rx{string2})";
65
4
23
        $rx{url} = "(([!#\$%&*-~]|$rx{nonascii}|$rx{escape})*)";
66
4
48
        $rx{range} = "(\\?{1,6}|$rx{h}(\\?{0,5}|$rx{h}(\\?{0,4}|$rx{h}(\\?{0,3}|$rx{h}(\\?{0,2}|$rx{h}(\\??|$rx{h}))))))";
67
68
69        #####################################################################################
70
71        #[ \t\r\n\f]+ {return S;}
72        #"<!--" {return CDO;}
73        #"-->" {return CDC;}
74        #"~=" {return INCLUDES;}
75        #"|=" {return DASHMATCH;}
76        #{string} {return STRING;}
77        #{ident} {return IDENT;}
78        #"#"{name} {return HASH;}
79
80
4
19
        $self->add_toke_rule('S' , "[ \t\r\n\f]+");
81
4
14
        $self->add_toke_rule('CDO' , '<!--');
82
4
15
        $self->add_toke_rule('CDC' , '-->');
83
4
14
        $self->add_toke_rule('INCLUDES' , '~=');
84
4
15
        $self->add_toke_rule('DASHMATCH' , '\\|=');
85
4
17
        $self->add_toke_rule('STRING' , $rx{string});
86
4
18
        $self->add_toke_rule('IDENT' , $rx{ident});
87
4
23
        $self->add_toke_rule('HASH' , "#$rx{name}");
88
89
90        #"@import" {return IMPORT_SYM;}
91        #"@page" {return PAGE_SYM;}
92        #"@media" {return MEDIA_SYM;}
93        #"@font-face" {return FONT_FACE_SYM;}
94        #"@charset" {return CHARSET_SYM;}
95        #"@"{ident} {return ATKEYWORD;}
96        #"!{w}important" {return IMPORTANT_SYM;}
97
98
4
15
        $self->add_toke_rule('IMPORT_SYM' , '@import');
99
4
15
        $self->add_toke_rule('PAGE_SYM' , '@page');
100
4
15
        $self->add_toke_rule('MEDIA_SYM' , '@media');
101
4
15
        $self->add_toke_rule('FONT_FACE_SYM' , '@font-face');
102
4
17
        $self->add_toke_rule('CHARSET_SYM' , '@charset');
103
4
23
        $self->add_toke_rule('ATKEYWORD' , "\@$rx{ident}"); # this rule isn't in the lexer, as per the spec
104
4
23
        $self->add_toke_rule('IMPORTANT_SYM' , "!$rx{w}important");
105
106
107        #{num}em {return EMS;}
108        #{num}ex {return EXS;}
109        #{num}px {return LENGTH;}
110        #{num}cm {return LENGTH;}
111        #{num}mm {return LENGTH;}
112        #{num}in {return LENGTH;}
113        #{num}pt {return LENGTH;}
114        #{num}pc {return LENGTH;}
115        #{num}deg {return ANGLE;}
116        #{num}rad {return ANGLE;}
117        #{num}grad {return ANGLE;}
118        #{num}ms {return TIME;}
119        #{num}s {return TIME;}
120        #{num}Hz {return FREQ;}
121        #{num}kHz {return FREQ;}
122        #{num}{ident} {return DIMEN;}
123        #{num}% {return PERCENTAGE;}
124        #{num} {return NUMBER;}
125
126
4
23
        $self->add_toke_rule('EMS' , "$rx{num}em");
127
4
21
        $self->add_toke_rule('EXS' , "$rx{num}ex");
128
4
19
        $self->add_toke_rule('LENGTH' , "$rx{num}(px|cm|mm|in|pt|pc)");
129
4
20
        $self->add_toke_rule('ANGLE' , "$rx{num}(deg|rad|grad)");
130
4
19
        $self->add_toke_rule('TIME' , "$rx{num}(ms|s)");
131
4
21
        $self->add_toke_rule('FREQ' , "$rx{num}(Hz|kHz)");
132
4
42
        $self->add_toke_rule('DIMEN' , "$rx{num}$rx{ident}");
133
4
21
        $self->add_toke_rule('PERCENTAGE' , "$rx{num}%");
134
4
18
        $self->add_toke_rule('NUMBER' , "$rx{num}");
135
136
137        #"url("{w}{string}{w}")" {return URI;}
138        #"url("{w}{url}{w}")" {return URI;}
139        #{ident}"(" {return FUNCTION;}
140
141
4
41
        $self->add_toke_rule('URI' , "url\\($rx{w}($rx{string}|$rx{url}$rx{w})\\)");
142
4
21
        $self->add_toke_rule('FUNCTION' , "$rx{ident}\\(");
143
144
145        #####################################################################################
146
147
4
111
        $self->add_toke_rule('_BRACE_OPEN' , '{');
148
4
15
        $self->add_toke_rule('_PLUS' , '\\+');
149
4
16
        $self->add_toke_rule('_GREATER_THAN' , '>');
150
4
15
        $self->add_toke_rule('_COMMA' , ',');
151
4
16
        $self->add_toke_rule('_SEMICOLON' , ';');
152
4
17
        $self->add_toke_rule('_BRACE_CLOSE' , '}');
153
4
16
        $self->add_toke_rule('_COLON' , ':');
154
4
17
        $self->add_toke_rule('_SLASH' , '/');
155
4
17
        $self->add_toke_rule('_MINUS' , '-');
156
4
14
        $self->add_toke_rule('_PERIOD' , '\\.');
157
4
18
        $self->add_toke_rule('_STAR' , '\\*');
158
4
15
        $self->add_toke_rule('_SQUARE_OPEN' , '\\[');
159
4
26
        $self->add_toke_rule('_SQUARE_CLOSE' , '\\]');
160
4
16
        $self->add_toke_rule('_EQUALS' , '=');
161
4
14
        $self->add_toke_rule('_ROUND_CLOSE' , '\\)');
162
163
164        #####################################################################################
165
166        #stylesheet
167        # : [ CHARSET_SYM S* STRING S* ';' ]?
168        # [S|CDO|CDC]* [ import [S|CDO|CDC]* ]*
169        # [ [ ruleset | media | page | font_face ] [S|CDO|CDC]* ]*
170        # ;
171        #import
172        # : IMPORT_SYM S*
173        # [STRING|URI] S* [ medium [ ',' S* medium]* ]? ';' S*
174        # ;
175        #media
176        # : MEDIA_SYM S* medium [ ',' S* medium ]* '{' S* ruleset* '}' S*
177        # ;
178
179
4
25
        $self->add_lex_rule('stylesheet', '[ CHARSET_SYM S* STRING S* _SEMICOLON ]? [S|CDO|CDC]* [ import [S|CDO|CDC]* ]* [ [ ruleset | media | '.
180                'page | font_face ] [S|CDO|CDC]* ]*');
181
4
15
        $self->add_lex_rule('import', 'IMPORT_SYM S* [STRING|URI] S* [ medium [ _COMMA S* medium]* ]? _SEMICOLON S*');
182
4
15
        $self->add_lex_rule('media', 'MEDIA_SYM S* medium [ _COMMA S* medium ]* _BRACE_OPEN S* ruleset* _BRACE_CLOSE S*');
183
184
185        #medium
186        # : IDENT S*
187        # ;
188        #page
189        # : PAGE_SYM S* IDENT? pseudo_page? S*
190        # '{' S* declaration [ ';' S* declaration ]* '}' S*
191        # ;
192        #pseudo_page
193        # : ':' IDENT
194        # ;
195        #font_face
196        # : FONT_FACE_SYM S*
197        # '{' S* declaration [ ';' S* declaration ]* '}' S*
198        # ;
199
200
4
15
        $self->add_lex_rule('medium', 'IDENT S*');
201
4
15
        $self->add_lex_rule('page', 'PAGE_SYM S* IDENT? pseudo_page? S* _BRACE_OPEN S* declaration [ _SEMICOLON S* declaration ]* _BRACE_CLOSE S*');
202
4
15
        $self->add_lex_rule('pseudo_page', '_COLON IDENT');
203
4
16
        $self->add_lex_rule('font_face', 'FONT_FACE_SYM S* _BRACE_OPEN S* declaration [ _SEMICOLON S* declaration ]* _BRACE_CLOSE S*');
204
205
206        #operator
207        # : '/' S* | ',' S* | /* empty */
208        # ;
209        #combinator
210        # : '+' S* | '>' S* | /* empty */
211        # ;
212        #unary_operator
213        # : '-' | '+'
214        # ;
215        #property
216        # : IDENT S*
217        # ;
218
219
4
14
        $self->add_lex_rule('operator', '_SLASH S* | _COMMA S* |');
220
4
17
        $self->add_lex_rule('combinator', '_PLUS S* | _GREATER_THAN S* |');
221
4
16
        $self->add_lex_rule('unary_operator', '_MINUS | _PLUS');
222
4
15
        $self->add_lex_rule('property', 'IDENT S*');
223
224
225        #ruleset
226        # : selector [ ',' S* selector ]*
227        # '{' S* declaration [ ';' S* declaration ]* '}' S*
228        # ;
229        #selector
230        # : simple_selector [ combinator simple_selector ]*
231        # ;
232        #simple_selector
233        # : element_name? [ HASH | class | attrib | pseudo ]* S*
234        # ;
235        #class
236        # : '.' IDENT
237        # ;
238
239
4
15
        $self->add_lex_rule('ruleset', 'selector [ _COMMA S* selector ]* _BRACE_OPEN S* declaration [ _SEMICOLON S* declaration ]* _BRACE_CLOSE S*');
240
4
16
        $self->add_lex_rule('selector', 'simple_selector [ combinator simple_selector ]*');
241
4
16
        $self->add_lex_rule('simple_selector', 'element_name? [ HASH | class | attrib | pseudo ]* S*');
242
4
16
        $self->add_lex_rule('class', '_PERIOD IDENT');
243
244
245        #element_name
246        # : IDENT | '*'
247        # ;
248        #attrib
249        # : '[' S* IDENT S* [ [ '=' | INCLUDES | DASHMATCH ] S*
250        # [ IDENT | STRING ] S* ]? ']'
251        # ;
252        #pseudo
253        # : ':' [ IDENT | FUNCTION S* IDENT S* ')' ]
254        # ;
255        #declaration
256        # : property ':' S* expr prio?
257        # | /* empty */
258        # ;
259
260
4
16
        $self->add_lex_rule('element_name', 'IDENT | _STAR');
261
4
15
        $self->add_lex_rule('attrib', '_SQUARE_OPEN S* IDENT S* [ [ _EQUALS | INCLUDES | DASHMATCH ] S* [ IDENT | STRING ] S* ]? _SQUARE_CLOSE');
262
4
17
        $self->add_lex_rule('pseudo', '_COLON [ IDENT | FUNCTION S* IDENT S* _ROUND_CLOSE ]');
263
4
14
        $self->add_lex_rule('declaration', 'property _COLON S* expr prio? |');
264
265
266        #prio
267        # : IMPORTANT_SYM S*
268        # ;
269        #expr
270        # : term [ operator term ]*
271        # ;
272        #term
273        # : unary_operator?
274        # [ NUMBER S* | PERCENTAGE S* | LENGTH S* | EMS S* | EXS S* | ANGLE S* |
275        # TIME S* | FREQ S* | function ]
276        # | STRING S* | IDENT S* | URI S* | RGB S* | UNICODERANGE S* | hexcolor
277        # ;
278
279
4
15
        $self->add_lex_rule('prio', 'IMPORTANT_SYM S*');
280
4
14
        $self->add_lex_rule('expr', 'term [ operator term ]*');
281
4
16
        $self->add_lex_rule('term', 'unary_operator? [ NUMBER S* | PERCENTAGE S* | LENGTH S* | EMS S* | EXS S* | ANGLE S* | TIME S* | FREQ S* | function ] '.
282                '| STRING S* | IDENT S* | URI S* | RGB S* | UNICODERANGE S* | hexcolor');
283
284
285        #function
286        # : FUNCTION S* expr ')' S*
287        # ;
288        #hexcolor
289        # : HASH S*
290        # ;
291
292
4
16
        $self->add_lex_rule('function', 'FUNCTION S* expr _ROUND_CLOSE S*');
293
4
16
        $self->add_lex_rule('hexcolor', 'HASH S*');
294
295
296        #####################################################################################
297
298
4
27
        $self->set_base('stylesheet');
299}
300
301sub toke {
302
3
3
20
        my ($self, $input) = @_;
303
304        # strip comments first
305
3
8
        $input =~ s!/\*[^*]*\*+([^/*][^*]*\*+)*/!!g;
306
307
3
27
        $self->SUPER::toke($input);
308}
309
3101;