1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
|
CSS grammar according to mobileOK Basic 1.0
* *: 0 or more
* +: 1 or more
* ?: 0 or 1
* |: separates alternatives
* [ ]: grouping
The productions are:
stylesheet
: [S|CDO|CDC]* [ import [S|CDO|CDC]* ]* [ [ ruleset | media ] [S|CDO|CDC]* ]*
;
import
: IMPORT_SYM S*
[STRING|URI] S* [ medium [ ',' S* medium]* ]? ';' S*
;
media
: MEDIA_SYM S* medium [ ',' S* medium ]* '{' S* ruleset* '}' S*
;
medium
: IDENT S*
;
unary_operator
: '-' | '+'
;
operator
: '/' | ',' | /* empty */
;
property
: IDENT
;
ruleset
: selector [ ',' selector ]*
'{' declaration [ ';' declaration ]* '}'
;
selector
: simple_selector+ [ pseudo_element | solitary_pseudo_element ]?
| solitary_pseudo_element
;
/* An "id" is an ID that is attached to an element type
** on its left, as in: P#p007
** A "solitary_id" is an ID that is not so attached,
** as in: #p007
** Analogously for classes and pseudo-classes.
*/
simple_selector
: element_name id? class? pseudo_class? /* eg: H1.subject */
| solitary_id class? pseudo_class? /* eg: #xyz33 */
| solitary_class pseudo_class? /* eg: .author */
| solitary_pseudo_class /* eg: :link */
;
element_name
: IDENT
;
pseudo_class /* as in: A:link */
: LINK_PSCLASS_AFTER_IDENT
| VISITED_PSCLASS_AFTER_IDENT
| ACTIVE_PSCLASS_AFTER_IDENT
;
solitary_pseudo_class /* as in: :link */
: LINK_PSCLASS
| VISITED_PSCLASS
| ACTIVE_PSCLASS
;
class /* as in: P.note */
: CLASS_AFTER_IDENT
;
solitary_class /* as in: .note */
: CLASS
;
pseudo_element /* as in: P:first-line */
: FIRST_LETTER_AFTER_IDENT
| FIRST_LINE_AFTER_IDENT
;
solitary_pseudo_element /* as in: :first-line */
: FIRST_LETTER
| FIRST_LINE
;
/* There is a constraint on the id and solitary_id that the
** part after the "#" must be a valid HTML ID value;
** e.g., "#x77" is OK, but "#77" is not.
*/
id
: HASH_AFTER_IDENT
;
solitary_id
: HASH
;
declaration
: property ':' expr prio?
| /* empty */ /* Prevents syntax errors... */
;
prio
: IMPORTANT_SYM /* !important */
;
expr
: term [ operator term ]*
;
term
: unary_operator?
[ NUMBER | STRING | PERCENTAGE | LENGTH | EMS | EXS
| IDENT | hexcolor | URL | RGB ]
;
/* There is a constraint on the color that it must
** have either 3 or 6 hex-digits (i.e., [0-9a-fA-F])
** after the "#"; e.g., "#000" is OK, but "#abcd" is not.
*/
hexcolor
: HASH | HASH_AFTER_IDENT
;
The following is the tokenizer, written in flex [16] notation. Note that this assumes an 8-bit implementation of flex. The tokenizer is case-insensitive (flex command line option -i).
unicode \\[0-9a-f]{1,4}
latin1 [¡-ÿ]
escape {unicode}|\\[ -~¡-ÿ]
stringchar {escape}|{latin1}|[ !#$%&(-~]
nmstrt [a-z]|{latin1}|{escape}
nmchar [-a-z0-9]|{latin1}|{escape}
ident {nmstrt}{nmchar}*
name {nmchar}+
d [0-9]
notnm [^-a-z0-9\\]|{latin1}
w [ \t\n]*
num {d}+|{d}*\.{d}+
string \"({stringchar}|\')*\"|\'({stringchar}|\")*\'
%x COMMENT
%s AFTER_IDENT
%%
"/*" {BEGIN(COMMENT);}
<COMMENT>"*/" {BEGIN(0);}
<COMMENT>\n {/* ignore */}
<COMMENT>. {/* ignore */}
@import {BEGIN(0); return IMPORT_SYM;}
@media {BEGIN(0); return MEDIA_SYM;}
"!"{w}important {BEGIN(0); return IMPORTANT_SYM;}
{ident} {BEGIN(AFTER_IDENT); return IDENT;}
{string} {BEGIN(0); return STRING;}
{num} {BEGIN(0); return NUMBER;}
{num}"%" {BEGIN(0); return PERCENTAGE;}
{num}pt/{notnm} {BEGIN(0); return LENGTH;}
{num}mm/{notnm} {BEGIN(0); return LENGTH;}
{num}cm/{notnm} {BEGIN(0); return LENGTH;}
{num}pc/{notnm} {BEGIN(0); return LENGTH;}
{num}in/{notnm} {BEGIN(0); return LENGTH;}
{num}px/{notnm} {BEGIN(0); return LENGTH;}
{num}em/{notnm} {BEGIN(0); return EMS;}
{num}ex/{notnm} {BEGIN(0); return EXS;}
<AFTER_IDENT>":"link {return LINK_PSCLASS_AFTER_IDENT;}
<AFTER_IDENT>":"visited {return VISITED_PSCLASS_AFTER_IDENT;}
<AFTER_IDENT>":"active {return ACTIVE_PSCLASS_AFTER_IDENT;}
<AFTER_IDENT>":"first-line {return FIRST_LINE_AFTER_IDENT;}
<AFTER_IDENT>":"first-letter {return FIRST_LETTER_AFTER_IDENT;}
<AFTER_IDENT>"#"{name} {return HASH_AFTER_IDENT;}
<AFTER_IDENT>"."{name} {return CLASS_AFTER_IDENT;}
":"link {BEGIN(AFTER_IDENT); return LINK_PSCLASS;}
":"visited {BEGIN(AFTER_IDENT); return VISITED_PSCLASS;}
":"active {BEGIN(AFTER_IDENT); return ACTIVE_PSCLASS;}
":"first-line {BEGIN(AFTER_IDENT); return FIRST_LINE;}
":"first-letter {BEGIN(AFTER_IDENT); return FIRST_LETTER;}
"#"{name} {BEGIN(AFTER_IDENT); return HASH;}
"."{name} {BEGIN(AFTER_IDENT); return CLASS;}
url\({w}{string}{w}\) |
url\({w}([^ \n\'\")]|\\\ |\\\'|\\\"|\\\))+{w}\) {BEGIN(0); return URL;}
rgb\({w}{num}%?{w}\,{w}{num}%?{w}\,{w}{num}%?{w}\) {BEGIN(0); return RGB;}
[-/+{};,#:] {BEGIN(0); return *yytext;}
[ \t]+ {BEGIN(0); /* ignore whitespace */}
\n {BEGIN(0); /* ignore whitespace */}
\<\!\-\- {BEGIN(0); return CDO;}
\-\-\> {BEGIN(0); return CDC;}
. {fprintf(stderr, "%d: Illegal character (%d)\n",
lineno, *yytext);}
|
