- From: Bert Bos <bert@w3.org>
- Date: Mon, 10 Aug 2009 18:03:04 +0200
- To: www-style@w3.org
- Cc: Yves Lafon <ylafon@w3.org>, Andrey Mikhalev <amikhal@abisoft.spb.ru>
- Message-Id: <200908101803.05437.bert@w3.org>
I've tried to improve the grammar of appendix G and I think I now have a version that defines the same language as before, but is LL(1). It has no ambiguities and no nullable non-terminals (except for the start symbol: "stylesheet" can of course still be empty). Compared to the last edits in response to Yves's suggestions, I've only further changed "selector" and "combinator". I'd like the grammar of appendix G to be as useful as possible, even though I know not many programs can use it. (Maybe it serves a validator, but all other programs will have to accept the forward compatible grammar instead.) I'd like to ask especially Andrey and Yves to take a look... I tested the grammar with an LL(1) parser generator and, after carefully expanding the rules, with Yacc. And it seems to work: neither complains about ambiguities and the resulting programs accept my various tests. Bert -- Bert Bos ( W 3 C ) http://www.w3.org/ http://www.w3.org/people/bos W3C/ERCIM bert@w3.org 2004 Rt des Lucioles / BP 93 +33 (0)4 92 38 76 92 06902 Sophia Antipolis Cedex, France
stylesheet
: [ CHARSET_SYM STRING ';' ]?
[S|CDO|CDC]* [ import [ CDO S* | CDC S* ]* ]*
[ [ ruleset | media | page ] [ CDO S* | CDC S* ]* ]*
;
import
: IMPORT_SYM S*
[STRING|URI] S* [ medium [ ',' S* medium]* ]? ';' S*
;
media
: MEDIA_SYM S* medium [ ',' S* medium ]* '{' S* ruleset* '}' S*
;
medium
: IDENT S*
;
page
: PAGE_SYM S* pseudo_page?
'{' S* declaration? [ ';' S* declaration? ]* '}' S*
;
pseudo_page
: ':' IDENT S*
;
operator
: '/' S* | ',' S*
;
combinator
: '+' S*
| '>' S*
;
unary_operator
: '-' | '+'
;
property
: IDENT S*
;
ruleset
: selector [ ',' S* selector ]*
'{' S* declaration? [ ';' S* declaration? ]* '}' S*
;
selector
: simple_selector [ combinator selector | S+ [ combinator? selector ]? ]?
;
simple_selector
: element_name [ HASH | class | attrib | pseudo ]*
| [ HASH | class | attrib | pseudo ]+
;
class
: '.' IDENT
;
element_name
: IDENT | '*'
;
attrib
: '[' S* IDENT S* [ [ '=' | INCLUDES | DASHMATCH ] S*
[ IDENT | STRING ] S* ]? ']'
;
pseudo
: ':' [ IDENT | FUNCTION S* [IDENT S*]? ')' ]
;
declaration
: property ':' S* expr prio?
;
prio
: IMPORTANT_SYM S*
;
expr
: term [ operator? term ]*
;
term
: unary_operator?
[ NUMBER S* | PERCENTAGE S* | LENGTH S* | EMS S* | EXS S* | ANGLE S* |
TIME S* | FREQ S* ]
| STRING S* | IDENT S* | URI S* | hexcolor | function
;
function
: FUNCTION S* expr ')' S*
;
/*
* 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 S*
;
%option case-insensitive
h [0-9a-f]
nonascii [\200-\377]
unicode \\{h}{1,6}(\r\n|[ \t\r\n\f])?
escape {unicode}|\\[^\r\n\f0-9a-f]
nmstart [_a-z]|{nonascii}|{escape}
nmchar [_a-z0-9-]|{nonascii}|{escape}
string1 \"([^\n\r\f\\"]|\\{nl}|{escape})*\"
string2 \'([^\n\r\f\\']|\\{nl}|{escape})*\'
invalid1 \"([^\n\r\f\\"]|\\{nl}|{escape})*
invalid2 \'([^\n\r\f\\']|\\{nl}|{escape})*
comment \/\*[^*]*\*+([^/*][^*]*\*+)*\/
ident -?{nmstart}{nmchar}*
name {nmchar}+
num [0-9]+|[0-9]*"."[0-9]+
string {string1}|{string2}
invalid {invalid1}|{invalid2}
url ([!#$%&*-~]|{nonascii}|{escape})*
s [ \t\r\n\f]+
w {s}?
nl \n|\r\n|\r|\f
A a|\\0{0,4}(41|61)(\r\n|[ \t\r\n\f])?
C c|\\0{0,4}(43|63)(\r\n|[ \t\r\n\f])?
D d|\\0{0,4}(44|64)(\r\n|[ \t\r\n\f])?
E e|\\0{0,4}(45|65)(\r\n|[ \t\r\n\f])?
G g|\\0{0,4}(47|67)(\r\n|[ \t\r\n\f])?|\\g
H h|\\0{0,4}(48|68)(\r\n|[ \t\r\n\f])?|\\h
I i|\\0{0,4}(49|69)(\r\n|[ \t\r\n\f])?|\\i
K k|\\0{0,4}(4b|6b)(\r\n|[ \t\r\n\f])?|\\k
L l|\\0{0,4}(4c|6c)(\r\n|[ \t\r\n\f])?|\\l
M m|\\0{0,4}(4d|6d)(\r\n|[ \t\r\n\f])?|\\m
N n|\\0{0,4}(4e|6e)(\r\n|[ \t\r\n\f])?|\\n
O o|\\0{0,4}(4f|6f)(\r\n|[ \t\r\n\f])?|\\o
P p|\\0{0,4}(50|70)(\r\n|[ \t\r\n\f])?|\\p
R r|\\0{0,4}(52|72)(\r\n|[ \t\r\n\f])?|\\r
S s|\\0{0,4}(53|73)(\r\n|[ \t\r\n\f])?|\\s
T t|\\0{0,4}(54|74)(\r\n|[ \t\r\n\f])?|\\t
U u|\\0{0,4}(55|75)(\r\n|[ \t\r\n\f])?|\\u
X x|\\0{0,4}(58|78)(\r\n|[ \t\r\n\f])?|\\x
Z z|\\0{0,4}(5a|7a)(\r\n|[ \t\r\n\f])?|\\z
%%
{s} {return S;}
\/\*[^*]*\*+([^/*][^*]*\*+)*\/ /* ignore comments */
"<!--" {return CDO;}
"-->" {return CDC;}
"~=" {return INCLUDES;}
"|=" {return DASHMATCH;}
{string} {return STRING;}
{invalid} {return INVALID; /* unclosed string */}
{ident} {return IDENT;}
"#"{name} {return HASH;}
@{I}{M}{P}{O}{R}{T} {return IMPORT_SYM;}
@{P}{A}{G}{E} {return PAGE_SYM;}
@{M}{E}{D}{I}{A} {return MEDIA_SYM;}
"@charset " {return CHARSET_SYM;}
"!"({w}|{comment})*{I}{M}{P}{O}{R}{T}{A}{N}{T} {return IMPORTANT_SYM;}
{num}{E}{M} {return EMS;}
{num}{E}{X} {return EXS;}
{num}{P}{X} {return LENGTH;}
{num}{C}{M} {return LENGTH;}
{num}{M}{M} {return LENGTH;}
{num}{I}{N} {return LENGTH;}
{num}{P}{T} {return LENGTH;}
{num}{P}{C} {return LENGTH;}
{num}{D}{E}{G} {return ANGLE;}
{num}{R}{A}{D} {return ANGLE;}
{num}{G}{R}{A}{D} {return ANGLE;}
{num}{M}{S} {return TIME;}
{num}{S} {return TIME;}
{num}{H}{Z} {return FREQ;}
{num}{K}{H}{Z} {return FREQ;}
{num}{ident} {return DIMENSION;}
{num}% {return PERCENTAGE;}
{num} {return NUMBER;}
{U}{R}{L}"("{w}{string}{w}")" {return URI;}
{U}{R}{L}"("{w}{url}{w}")" {return URI;}
{ident}"(" {return FUNCTION;}
. {return *yytext;}
Received on Monday, 10 August 2009 16:03:44 UTC