Sideway
output.to from Sideway
Draft for Information Only

Content

 CSS Grammar
 The minimal CSS
  Grammar: The productions
 The tokenizer

 CSS Grammar

Source

  • https://www.w3.org/TR/2018/SPSD-CSS1-20180913/#appendix-b last updated 23Jan2019
  • https://www.w3.org/TR/2011/REC-CSS2-20110607/grammar.htmllast updated 23Jan2019

The minimal CSS

Notation

*  : 0 or more
+  : 1 or more
?  : 0 or 1
|  : separates alternatives
[] : grouping

Grammar: The productions

CSS 1CSS 2.1
stylesheet
 : [CDO|CDC]* [ import [CDO|CDC]* ]* [ ruleset [CDO|CDC]* ]*
 ;
import
 : IMPORT_SYM [STRING|URL] ';'		/* E.g., @import url(fun.css); */
 ;
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
 ;
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* media_list? ';' S*
  ;
media
  : MEDIA_SYM S* media_list '{' S* ruleset* '}' S*
  ;
media_list
  : medium [ COMMA S* medium]*
  ;
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*
  ;

The tokenizer

CSS 1CSS 2.1
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;}
"!"{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);}
%option case-insensitive

h		[0-9a-f]
nonascii	[\240-\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})*\'
badstring1      \"([^\n\r\f\\"]|\\{nl}|{escape})*\\?
badstring2      \'([^\n\r\f\\']|\\{nl}|{escape})*\\?
badcomment1     \/\*[^*]*\*+([^/*][^*]*\*+)*
badcomment2     \/\*[^*]*(\*+[^/*][^*]*)*
baduri1         url\({w}([!#$%&*-\[\]-~]|{nonascii}|{escape})*{w}
baduri2         url\({w}{string}{w}
baduri3         url\({w}{badstring}
comment		\/\*[^*]*\*+([^/*][^*]*\*+)*\/
ident		-?{nmstart}{nmchar}*
name		{nmchar}+
num		[0-9]+|[0-9]*"."[0-9]+
string		{string1}|{string2}
badstring       {badstring1}|{badstring2}
badcomment      {badcomment1}|{badcomment2}
baduri          {baduri1}|{baduri2}|{baduri3}
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 */
{badcomment}                         /* unclosed comment at EOF */

""			{return CDC;}
"~="			{return INCLUDES;}
"|="			{return DASHMATCH;}

{string}		{return STRING;}
{badstring}             {return BAD_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;}

"url("{w}{string}{w}")" {return URI;}
"url("{w}{url}{w}")"    {return URI;}
{baduri}                {return BAD_URI;}

{ident}"("		{return FUNCTION;}

.			{return *yytext;}

©sideway

ID: 190400006 Last Updated: 4/6/2019 Revision: 0 Ref:

close

References

  1. http://www.w3.org/TR/1999/REC-html401-1999, 1999, HTML 4.01 Specification: W3C Recommendation, updated 24 December 1999
close

Latest Updated LinksValid XHTML 1.0 Transitional Valid CSS!Nu Html Checker Firefox53 Chromena IExplorerna
IMAGE

Home 5

Business

Management

HBR 3

Information

Recreation

Hobbies 8

Culture

Chinese 1097

English 339

Reference 79

Computer

Hardware 249

Software

Application 213

Digitization 32

Latex 52

Manim 205

KB 1

Numeric 19

Programming

Web 289

Unicode 504

HTML 66

CSS 65

SVG 46

ASP.NET 270

OS 429

DeskTop 7

Python 72

Knowledge

Mathematics

Formulas 8

Algebra 84

Number Theory 206

Trigonometry 31

Geometry 34

Coordinate Geometry 2

Calculus 67

Complex Analysis 21

Engineering

Tables 8

Mechanical

Mechanics 1

Rigid Bodies

Statics 92

Dynamics 37

Fluid 5

Fluid Kinematics 5

Control

Process Control 1

Acoustics 19

FiniteElement 2

Natural Sciences

Matter 1

Electric 27

Biology 1

Geography 1


Copyright © 2000-2024 Sideway . All rights reserved Disclaimers last modified on 06 September 2019