joepie91
/
pegjs
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Formatted all grammars more consistently and transparently

Browse Source 
This is purely cosmetical change, no functionality was affected
(hopefully).
redux
David Majda 14 years ago
parent 698564a3c2
commit 409ddf2ae8
6 changed files with 1529 additions and 1203 deletions
Show Stats Download Patch File Download Diff File

21
examples/arithmetics.pegjs
Unescape Escape View File

@ -3,15 +3,20 @@
* "2*(3+4)". The parser generated from this grammar then computes their value. * "2*(3+4)". The parser generated from this grammar then computes their value.
*/ */
start = additive start
= additive
additive = multiplicative "+" additive { return $1 + $3; } additive
/ multiplicative = multiplicative "+" additive { return $1 + $3; }
/ multiplicative
multiplicative = primary "*" multiplicative { return $1 * $3; } multiplicative
/ primary = primary "*" multiplicative { return $1 * $3; }
/ primary
primary = integer primary
/ "(" additive ")" { return $2; } = integer
/ "(" additive ")" { return $2; }
integer "integer" = [0-9]+ { return parseInt($1.join(""), 10); } integer "integer"
= [0-9]+ { return parseInt($1.join(""), 10); }

508
examples/css.pegjs
Unescape Escape View File

@ -14,73 +14,79 @@
/* ===== Syntactical Elements ===== */ /* ===== Syntactical Elements ===== */
start = stylesheet comment* { return $1; } start
= stylesheet comment* { return $1; }
stylesheet =
(CHARSET_SYM STRING ";")? (S / CDO / CDC)* stylesheet
(import (CDO S* / CDC S*)*)* = (CHARSET_SYM STRING ";")? (S / CDO / CDC)*
((ruleset / media / page) (CDO S* / CDC S*)*)* (import (CDO S* / CDC S*)*)*
{ ((ruleset / media / page) (CDO S* / CDC S*)*)* {
var imports = []; var imports = [];
for (var i = 0; i < $3.length; i++) { for (var i = 0; i < $3.length; i++) {
imports.push($3[i][0]); imports.push($3[i][0]);
}
var rules = [];
for (i = 0; i < $4.length; i++) {
rules.push($4[i][0]);
}
return {
type: "stylesheet",
charset: $1 !== "" ? $1[1] : null,
imports: imports,
rules: rules
};
} }
var rules = []; import
for (i = 0; i < $4.length; i++) { = IMPORT_SYM S* (STRING / URI) S* media_list? ";" S* {
rules.push($4[i][0]); return {
type: "import_rule",
href: $3,
media: $5 !== "" ? $5 : []
};
} }
return { media
type: "stylesheet", = MEDIA_SYM S* media_list "{" S* ruleset* "}" S* {
charset: $1 !== "" ? $1[1] : null, return {
imports: imports, type: "media_rule",
rules: rules media: $3,
}; rules: $6
} };
import = IMPORT_SYM S* (STRING / URI) S* media_list? ";" S* {
return {
type: "import_rule",
href: $3,
media: $5 !== "" ? $5 : []
};
}
media = MEDIA_SYM S* media_list "{" S* ruleset* "}" S* {
return {
type: "media_rule",
media: $3,
rules: $6
};
}
media_list = medium ("," S* medium)* {
var result = [$1];
for (var i = 0; i < $2.length; i++) {
result.push($2[i][2]);
}
return result;
}
medium = IDENT S* { return $1; }
page = PAGE_SYM S* pseudo_page? "{" S* declaration? (";" S* declaration?)* "}" S* {
var declarations = $6 !== "" ? [$6] : [];
for (var i = 0; i < $7.length; i++) {
if ($7[i][2] !== "") {
declarations.push($7[i][2]);
} }
}
return { media_list
type: "page_rule", = medium ("," S* medium)* {
qualifier: $3 !== "" ? $3 : null, var result = [$1];
declarations: declarations for (var i = 0; i < $2.length; i++) {
}; result.push($2[i][2]);
} }
return result;
}
pseudo_page = ":" IDENT S* { return $2; } medium
= IDENT S* { return $1; }
page
= PAGE_SYM S* pseudo_page? "{" S* declaration? (";" S* declaration?)* "}" S* {
var declarations = $6 !== "" ? [$6] : [];
for (var i = 0; i < $7.length; i++) {
if ($7[i][2] !== "") {
declarations.push($7[i][2]);
}
}
return {
type: "page_rule",
qualifier: $3 !== "" ? $3 : null,
declarations: declarations
};
}
pseudo_page
= ":" IDENT S* { return $2; }
operator operator
= "/" S* { return $1; } = "/" S* { return $1; }
@ -90,29 +96,34 @@ combinator
= "+" S* { return $1; } = "+" S* { return $1; }
/ ">" S* { return $1; } / ">" S* { return $1; }
unary_operator = "+" / "-" unary_operator
= "+"
/ "-"
property = IDENT S* { return $1; } property
= IDENT S* { return $1; }
ruleset = selector ("," S* selector)* "{" S* declaration? (";" S* declaration?)* "}" S* { ruleset
var selectors = [$1]; = selector ("," S* selector)*
for (var i = 0; i < $2.length; i++) { "{" S* declaration? (";" S* declaration?)* "}" S* {
selectors.push($2[i][2]); var selectors = [$1];
} for (var i = 0; i < $2.length; i++) {
selectors.push($2[i][2]);
}
var declarations = $5 !== "" ? [$5] : []; var declarations = $5 !== "" ? [$5] : [];
for (i = 0; i < $6.length; i++) { for (i = 0; i < $6.length; i++) {
if ($6[i][2] !== "") { if ($6[i][2] !== "") {
declarations.push($6[i][2]); declarations.push($6[i][2]);
} }
} }
return { return {
type: "ruleset", type: "ruleset",
selectors: selectors, selectors: selectors,
declarations: declarations declarations: declarations
}; };
} }
selector selector
= simple_selector S* combinator selector { = simple_selector S* combinator selector {
@ -160,66 +171,71 @@ simple_selector
}; };
} }
class = "." IDENT { return { type: "class_selector", "class": $2 }; } class
= "." IDENT { return { type: "class_selector", "class": $2 }; }
element_name = IDENT / '*'
element_name
attrib = "[" S* IDENT S* (('=' / INCLUDES / DASHMATCH) S* (IDENT / STRING) S*)? "]" { = IDENT / '*'
return {
type: "attribute_selector", attrib
attribute: $3, = "[" S* IDENT S* (('=' / INCLUDES / DASHMATCH) S* (IDENT / STRING) S*)? "]" {
operator: $5 !== "" ? $5[0] : null, return {
value: $5 !== "" ? $5[2] : null type: "attribute_selector",
}; attribute: $3,
} operator: $5 !== "" ? $5[0] : null,
value: $5 !== "" ? $5[2] : null
pseudo = };
":" }
(
FUNCTION S* (IDENT S*)? ")" { pseudo
return { = ":"
type: "function", (
name: $1, FUNCTION S* (IDENT S*)? ")" {
params: $3 !== "" ? [$3[0]] : [] return {
type: "function",
name: $1,
params: $3 !== "" ? [$3[0]] : []
};
}
/ IDENT
) {
/*
* The returned object has somewhat vague property names and values because
* the rule matches both pseudo-classes and pseudo-elements (they look the
* same at the syntactic level).
*/
return {
type: "pseudo_selector",
value: $2
};
}
declaration
= property ":" S* expr prio? {
return {
type: "declaration",
property: $1,
expression: $4,
important: $5 !== "" ? true : false
};
}
prio
= IMPORTANT_SYM S*
expr
= term (operator? term)* {
var result = $1;
for (var i = 0; i < $2.length; i++) {
result = {
type: "expression",
operator: $2[i][0],
left: result,
right: $2[i][1]
}; };
} }
/ IDENT return result;
) }
{
/*
* The returned object has somewhat vague property names and values because
* the rule matches both pseudo-classes and pseudo-elements (they look the
* same at the syntactic level).
*/
return {
type: "pseudo_selector",
value: $2
};
}
declaration = property ":" S* expr prio? {
return {
type: "declaration",
property: $1,
expression: $4,
important: $5 !== "" ? true : false
};
}
prio = IMPORTANT_SYM S*
expr = term (operator? term)* {
var result = $1;
for (var i = 0; i < $2.length; i++) {
result = {
type: "expression",
operator: $2[i][0],
left: result,
right: $2[i][1]
};
}
return result;
}
term term
= unary_operator? = unary_operator?
@ -239,69 +255,127 @@ term
/ STRING S* { return { type: "string", value: $1 }; } / STRING S* { return { type: "string", value: $1 }; }
/ IDENT S* { return { type: "ident", value: $1 }; } / IDENT S* { return { type: "ident", value: $1 }; }
function = FUNCTION S* expr ")" S* { function
return { = FUNCTION S* expr ")" S* {
type: "function", return {
name: $1, type: "function",
params: $3 name: $1,
}; params: $3
} };
}
hexcolor = HASH S* { return { type: "hexcolor", value: $1}; } hexcolor
= HASH S* { return { type: "hexcolor", value: $1}; }
/* ===== Lexical Elements ===== */ /* ===== Lexical Elements ===== */
/* Macros */ /* Macros */
h = [0-9a-fA-F] h
nonascii = [\x80-\xFF] = [0-9a-fA-F]
unicode = "\\" h h? h? h? h? h? ("\r\n" / [ \t\r\n\f])? {
return String.fromCharCode(parseInt("0x" + $2 + $3 + $4 + $5 + $6 + $7)); nonascii
} = [\x80-\xFF]
escape = unicode / "\\" [^\r\n\f0-9a-fA-F] { return $2; }
nmstart = [_a-zA-Z] / nonascii / escape unicode
nmchar = [_a-zA-Z0-9-] / nonascii / escape = "\\" h h? h? h? h? h? ("\r\n" / [ \t\r\n\f])? {
integer = [0-9]+ { return parseInt($1.join("")); } return String.fromCharCode(parseInt("0x" + $2 + $3 + $4 + $5 + $6 + $7));
float = [0-9]* "." [0-9]+ { return parseFloat($1.join("") + $2 + $3.join("")); } }
string1 = '"' ([^\n\r\f\\"] / "\\" nl { return $2 } / escape)* '"' { return $2.join(""); }
string2 = "'" ([^\n\r\f\\'] / "\\" nl { return $2 } / escape)* "'" { return $2.join(""); } escape
= unicode
comment = "/*" [^*]* "*"+ ([^/*] [^*]* "*"+)* "/" / "\\" [^\r\n\f0-9a-fA-F] { return $2; }
ident = "-"? nmstart nmchar* { return $1 + $2 + $3.join(""); }
name = nmchar+ { return $1.join(""); } nmstart
num = float / integer = [_a-zA-Z]
string = string1 / string2 / nonascii
url = ([!#$%&*-~] / nonascii / escape)* { return $1.join(""); } / escape
s = [ \t\r\n\f]+
w = s? nmchar
nl = "\n" / "\r\n" / "\r" / "\f" = [_a-zA-Z0-9-]
/ nonascii
/ escape
integer
= [0-9]+ { return parseInt($1.join("")); }
float
= [0-9]* "." [0-9]+ { return parseFloat($1.join("") + $2 + $3.join("")); }
string1
= '"' ([^\n\r\f\\"] / "\\" nl { return $2 } / escape)* '"' {
return $2.join("");
}
string2
= "'" ([^\n\r\f\\'] / "\\" nl { return $2 } / escape)* "'" {
return $2.join("");
}
comment
= "/*" [^*]* "*"+ ([^/*] [^*]* "*"+)* "/"
ident
= "-"? nmstart nmchar* { return $1 + $2 + $3.join(""); }
name
= nmchar+ { return $1.join(""); }
num
= float
/ integer
string
= string1
/ string2
url
= ([!#$%&*-~] / nonascii / escape)* { return $1.join(""); }
s
= [ \t\r\n\f]+
w
= s?
nl
= "\n"
/ "\r\n"
/ "\r"
/ "\f"
A A
= [aA] = [aA]
/ "\\" "0"? "0"? "0"? "0"? "41" ("\r\n" / [ \t\r\n\f])? { return "A"; } / "\\" "0"? "0"? "0"? "0"? "41" ("\r\n" / [ \t\r\n\f])? { return "A"; }
/ "\\" "0"? "0"? "0"? "0"? "61" ("\r\n" / [ \t\r\n\f])? { return "a"; } / "\\" "0"? "0"? "0"? "0"? "61" ("\r\n" / [ \t\r\n\f])? { return "a"; }
C C
= [cC] = [cC]
/ "\\" "0"? "0"? "0"? "0"? "43" ("\r\n" / [ \t\r\n\f])? { return "C"; } / "\\" "0"? "0"? "0"? "0"? "43" ("\r\n" / [ \t\r\n\f])? { return "C"; }
/ "\\" "0"? "0"? "0"? "0"? "63" ("\r\n" / [ \t\r\n\f])? { return "c"; } / "\\" "0"? "0"? "0"? "0"? "63" ("\r\n" / [ \t\r\n\f])? { return "c"; }
D D
= [dD] = [dD]
/ "\\" "0"? "0"? "0"? "0"? "44" ("\r\n" / [ \t\r\n\f])? { return "D"; } / "\\" "0"? "0"? "0"? "0"? "44" ("\r\n" / [ \t\r\n\f])? { return "D"; }
/ "\\" "0"? "0"? "0"? "0"? "64" ("\r\n" / [ \t\r\n\f])? { return "d"; } / "\\" "0"? "0"? "0"? "0"? "64" ("\r\n" / [ \t\r\n\f])? { return "d"; }
E E
= [eE] = [eE]
/ "\\" "0"? "0"? "0"? "0"? "45" ("\r\n" / [ \t\r\n\f])? { return "E"; } / "\\" "0"? "0"? "0"? "0"? "45" ("\r\n" / [ \t\r\n\f])? { return "E"; }
/ "\\" "0"? "0"? "0"? "0"? "65" ("\r\n" / [ \t\r\n\f])? { return "e"; } / "\\" "0"? "0"? "0"? "0"? "65" ("\r\n" / [ \t\r\n\f])? { return "e"; }
G G
= [gG] = [gG]
/ "\\" "0"? "0"? "0"? "0"? "47" ("\r\n" / [ \t\r\n\f])? { return "G"; } / "\\" "0"? "0"? "0"? "0"? "47" ("\r\n" / [ \t\r\n\f])? { return "G"; }
/ "\\" "0"? "0"? "0"? "0"? "67" ("\r\n" / [ \t\r\n\f])? { return "g"; } / "\\" "0"? "0"? "0"? "0"? "67" ("\r\n" / [ \t\r\n\f])? { return "g"; }
/ "\\" [gG] { return $2; } / "\\" [gG] { return $2; }
H H
= [hH] = [hH]
/ "\\" "0"? "0"? "0"? "0"? "48" ("\r\n" / [ \t\r\n\f])? { return "H"; } / "\\" "0"? "0"? "0"? "0"? "48" ("\r\n" / [ \t\r\n\f])? { return "H"; }
/ "\\" "0"? "0"? "0"? "0"? "68" ("\r\n" / [ \t\r\n\f])? { return "h"; } / "\\" "0"? "0"? "0"? "0"? "68" ("\r\n" / [ \t\r\n\f])? { return "h"; }
/ "\\" [hH] { return $2; } / "\\" [hH] { return $2; }
I I
= [iI] = [iI]
/ "\\" "0"? "0"? "0"? "0"? "49" ("\r\n" / [ \t\r\n\f])? { return "I"; } / "\\" "0"? "0"? "0"? "0"? "49" ("\r\n" / [ \t\r\n\f])? { return "I"; }
@ -313,56 +387,67 @@ K
/ "\\" "0"? "0"? "0"? "0"? "4" [bB] ("\r\n" / [ \t\r\n\f])? { return "K"; } / "\\" "0"? "0"? "0"? "0"? "4" [bB] ("\r\n" / [ \t\r\n\f])? { return "K"; }
/ "\\" "0"? "0"? "0"? "0"? "6" [bB] ("\r\n" / [ \t\r\n\f])? { return "k"; } / "\\" "0"? "0"? "0"? "0"? "6" [bB] ("\r\n" / [ \t\r\n\f])? { return "k"; }
/ "\\" [kK] { return $2; } / "\\" [kK] { return $2; }
L L
= [lL] = [lL]
/ "\\" "0"? "0"? "0"? "0"? "4" [cC] ("\r\n" / [ \t\r\n\f])? { return "L"; } / "\\" "0"? "0"? "0"? "0"? "4" [cC] ("\r\n" / [ \t\r\n\f])? { return "L"; }
/ "\\" "0"? "0"? "0"? "0"? "6" [cC] ("\r\n" / [ \t\r\n\f])? { return "l"; } / "\\" "0"? "0"? "0"? "0"? "6" [cC] ("\r\n" / [ \t\r\n\f])? { return "l"; }
/ "\\" [lL] { return $2; } / "\\" [lL] { return $2; }
M M
= [mM] = [mM]
/ "\\" "0"? "0"? "0"? "0"? "4" [dD] ("\r\n" / [ \t\r\n\f])? { return "M"; } / "\\" "0"? "0"? "0"? "0"? "4" [dD] ("\r\n" / [ \t\r\n\f])? { return "M"; }
/ "\\" "0"? "0"? "0"? "0"? "6" [dD] ("\r\n" / [ \t\r\n\f])? { return "m"; } / "\\" "0"? "0"? "0"? "0"? "6" [dD] ("\r\n" / [ \t\r\n\f])? { return "m"; }
/ "\\" [mM] { return $2; } / "\\" [mM] { return $2; }
N N
= [nN] = [nN]
/ "\\" "0"? "0"? "0"? "0"? "4" [eE] ("\r\n" / [ \t\r\n\f])? { return "N"; } / "\\" "0"? "0"? "0"? "0"? "4" [eE] ("\r\n" / [ \t\r\n\f])? { return "N"; }
/ "\\" "0"? "0"? "0"? "0"? "6" [eE] ("\r\n" / [ \t\r\n\f])? { return "n"; } / "\\" "0"? "0"? "0"? "0"? "6" [eE] ("\r\n" / [ \t\r\n\f])? { return "n"; }
/ "\\" [nN] { return $2; } / "\\" [nN] { return $2; }
O O
= [oO] = [oO]
/ "\\" "0"? "0"? "0"? "0"? "4" [fF] ("\r\n" / [ \t\r\n\f])? { return "O"; } / "\\" "0"? "0"? "0"? "0"? "4" [fF] ("\r\n" / [ \t\r\n\f])? { return "O"; }
/ "\\" "0"? "0"? "0"? "0"? "6" [fF] ("\r\n" / [ \t\r\n\f])? { return "o"; } / "\\" "0"? "0"? "0"? "0"? "6" [fF] ("\r\n" / [ \t\r\n\f])? { return "o"; }
/ "\\" [oO] { return $2; } / "\\" [oO] { return $2; }
P P
= [pP] = [pP]
/ "\\" "0"? "0"? "0"? "0"? "50" ("\r\n" / [ \t\r\n\f])? { return "P"; } / "\\" "0"? "0"? "0"? "0"? "50" ("\r\n" / [ \t\r\n\f])? { return "P"; }
/ "\\" "0"? "0"? "0"? "0"? "70" ("\r\n" / [ \t\r\n\f])? { return "p"; } / "\\" "0"? "0"? "0"? "0"? "70" ("\r\n" / [ \t\r\n\f])? { return "p"; }
/ "\\" [pP] { return $2; } / "\\" [pP] { return $2; }
R R
= [rR] = [rR]
/ "\\" "0"? "0"? "0"? "0"? "52" ("\r\n" / [ \t\r\n\f])? { return "R"; } / "\\" "0"? "0"? "0"? "0"? "52" ("\r\n" / [ \t\r\n\f])? { return "R"; }
/ "\\" "0"? "0"? "0"? "0"? "72" ("\r\n" / [ \t\r\n\f])? { return "r"; } / "\\" "0"? "0"? "0"? "0"? "72" ("\r\n" / [ \t\r\n\f])? { return "r"; }
/ "\\" [rR] { return $2; } / "\\" [rR] { return $2; }
S_ S_
= [sS] = [sS]
/ "\\" "0"? "0"? "0"? "0"? "53" ("\r\n" / [ \t\r\n\f])? { return "S"; } / "\\" "0"? "0"? "0"? "0"? "53" ("\r\n" / [ \t\r\n\f])? { return "S"; }
/ "\\" "0"? "0"? "0"? "0"? "73" ("\r\n" / [ \t\r\n\f])? { return "s"; } / "\\" "0"? "0"? "0"? "0"? "73" ("\r\n" / [ \t\r\n\f])? { return "s"; }
/ "\\" [sS] { return $2; } / "\\" [sS] { return $2; }
T T
= [tT] = [tT]
/ "\\" "0"? "0"? "0"? "0"? "54" ("\r\n" / [ \t\r\n\f])? { return "T"; } / "\\" "0"? "0"? "0"? "0"? "54" ("\r\n" / [ \t\r\n\f])? { return "T"; }
/ "\\" "0"? "0"? "0"? "0"? "74" ("\r\n" / [ \t\r\n\f])? { return "t"; } / "\\" "0"? "0"? "0"? "0"? "74" ("\r\n" / [ \t\r\n\f])? { return "t"; }
/ "\\" [tT] { return $2; } / "\\" [tT] { return $2; }
U U
= [uU] = [uU]
/ "\\" "0"? "0"? "0"? "0"? "55" ("\r\n" / [ \t\r\n\f])? { return "U"; } / "\\" "0"? "0"? "0"? "0"? "55" ("\r\n" / [ \t\r\n\f])? { return "U"; }
/ "\\" "0"? "0"? "0"? "0"? "75" ("\r\n" / [ \t\r\n\f])? { return "u"; } / "\\" "0"? "0"? "0"? "0"? "75" ("\r\n" / [ \t\r\n\f])? { return "u"; }
/ "\\" [uU] { return $2; } / "\\" [uU] { return $2; }
X X
= [xX] = [xX]
/ "\\" "0"? "0"? "0"? "0"? "58" ("\r\n" / [ \t\r\n\f])? { return "X"; } / "\\" "0"? "0"? "0"? "0"? "58" ("\r\n" / [ \t\r\n\f])? { return "X"; }
/ "\\" "0"? "0"? "0"? "0"? "78" ("\r\n" / [ \t\r\n\f])? { return "x"; } / "\\" "0"? "0"? "0"? "0"? "78" ("\r\n" / [ \t\r\n\f])? { return "x"; }
/ "\\" [xX] { return $2; } / "\\" [xX] { return $2; }
Z Z
= [zZ] = [zZ]
/ "\\" "0"? "0"? "0"? "0"? "5" [aA] ("\r\n" / [ \t\r\n\f])? { return "Z"; } / "\\" "0"? "0"? "0"? "0"? "5" [aA] ("\r\n" / [ \t\r\n\f])? { return "Z"; }
@ -371,36 +456,77 @@ Z
/* Tokens */ /* Tokens */
S "whitespace" = comment* s S "whitespace"
= comment* s
CDO "<!--"
= comment* "<!--"
CDC "-->"
= comment* "-->"
INCLUDES "~="
= comment* "~="
DASHMATCH "|="
= comment* "|="
CDO "<!--" = comment* "<!--" STRING "string"
CDC "-->" = comment* "-->" = comment* string { return $2; }
INCLUDES "~=" = comment* "~="
DASHMATCH "|=" = comment* "|="
STRING "string" = comment* string { return $2; } IDENT "identifier"
= comment* ident { return $2; }
IDENT "identifier" = comment* ident { return $2; } HASH "hash"
= comment* "#" name { return $2 + $3; }
HASH "hash" = comment* "#" name { return $2 + $3; } IMPORT_SYM "@import"
= comment* "@" I M P O R T
PAGE_SYM "@page"
= comment* "@" P A G E
MEDIA_SYM "@media"
= comment* "@" M E D I A
CHARSET_SYM "@charset"
= comment* "@charset "
IMPORT_SYM "@import" = comment* "@" I M P O R T
PAGE_SYM "@page" = comment* "@" P A G E
MEDIA_SYM "@media" = comment* "@" M E D I A
CHARSET_SYM "@charset" = comment* "@charset "
/* Note: We replace "w" with "s" here to avoid infinite recursion. */ /* Note: We replace "w" with "s" here to avoid infinite recursion. */
IMPORTANT_SYM "!important" = comment* "!" (s / comment)* I M P O R T A N T { return "!important"; } IMPORTANT_SYM "!important"
= comment* "!" (s / comment)* I M P O R T A N T { return "!important"; }
EMS "length"
= comment* num E M { return $2 + $3 + $4; }
EXS "length"
= comment* num E X { return $2 + $3 + $4; }
LENGTH "length"
= comment* num (P X / C M / M M / I N / P T / P C) {
return $2 + $3.join("");
}
ANGLE "angle"
= comment* num (D E G / R A D / G R A D) { return $2 + $3.join(""); }
TIME "time"
= comment* num (M S_ { return $1 + $2; } / S_) { return $2 + $3; }
FREQ "frequency"
= comment* num (H Z / K H Z) { return $2 + $3.join(""); }
DIMENSION "dimension"
= comment* num ident { return $2 + $3; }
PERCENTAGE "percentage"
= comment* num "%" { return $2 + $3; }
EMS "length" = comment* num E M { return $2 + $3 + $4; } NUMBER "number"
EXS "length" = comment* num E X { return $2 + $3 + $4; } = comment* num { return $2; }
LENGTH "length" = comment* num (P X / C M / M M / I N / P T / P C) { return $2 + $3.join(""); }
ANGLE "angle" = comment* num (D E G / R A D / G R A D) { return $2 + $3.join(""); }
TIME "time" = comment* num (M S_ { return $1 + $2; } / S_) { return $2 + $3; }
FREQ "frequency" = comment* num (H Z / K H Z) { return $2 + $3.join(""); }
DIMENSION "dimension" = comment* num ident { return $2 + $3; }
PERCENTAGE "percentage" = comment* num "%" { return $2 + $3; }
NUMBER "number" = comment* num { return $2; }
URI "uri" = comment* U R L "(" w (string / url) w ")" { return $7; } URI "uri"
= comment* U R L "(" w (string / url) w ")" { return $7; }
FUNCTION "function" = comment* ident "(" { return $2; } FUNCTION "function"
= comment* ident "(" { return $2; }

1735
examples/javascript.pegjs
View File

File diff suppressed because it is too large Load Diff

68
examples/json.pegjs
Unescape Escape View File

@ -2,34 +2,38 @@
/* ===== Syntactical Elements ===== */ /* ===== Syntactical Elements ===== */
start = _ object { return $2; } start
= _ object { return $2; }
object object
= "{" _ "}" _ { return {}; } = "{" _ "}" _ { return {}; }
/ "{" _ members "}" _ { return $3; } / "{" _ members "}" _ { return $3; }
members = pair ("," _ pair)* { members
var result = {}; = pair ("," _ pair)* {
result[$1[0]] = $1[1]; var result = {};
for (var i = 0; i < $2.length; i++) { result[$1[0]] = $1[1];
result[$2[i][2][0]] = $2[i][2][1]; for (var i = 0; i < $2.length; i++) {
} result[$2[i][2][0]] = $2[i][2][1];
return result; }
} return result;
}
pair = string ":" _ value { return [$1, $4]; } pair
= string ":" _ value { return [$1, $4]; }
array array
= "[" _ "]" _ { return []; } = "[" _ "]" _ { return []; }
/ "[" _ elements "]" _ { return $3; } / "[" _ elements "]" _ { return $3; }
elements = value ("," _ value)* { elements
var result = [$1]; = value ("," _ value)* {
for (var i = 0; i < $2.length; i++) { var result = [$1];
result.push($2[i][2]); for (var i = 0; i < $2.length; i++) {
} result.push($2[i][2]);
return result; }
} return result;
}
value value
= string = string
@ -47,7 +51,8 @@ string "string"
= '"' '"' _ { return ""; } = '"' '"' _ { return ""; }
/ '"' chars '"' _ { return $2; } / '"' chars '"' _ { return $2; }
chars = char+ { return $1.join(""); } chars
= char+ { return $1.join(""); }
char char
// In the original JSON grammar: "any-Unicode-character-except-"-or-\-or-control-character" // In the original JSON grammar: "any-Unicode-character-except-"-or-\-or-control-character"
@ -76,13 +81,17 @@ int
/ "-" digit19 digits { return $1 + $2 + $3; } / "-" digit19 digits { return $1 + $2 + $3; }
/ "-" digit { return $1 + $2; } / "-" digit { return $1 + $2; }
frac = "." digits { return $1 + $2; } frac
= "." digits { return $1 + $2; }
exp = e digits { return $1 + $2; } exp
= e digits { return $1 + $2; }
digits = digit+ { return $1.join(""); } digits
= digit+ { return $1.join(""); }
e = [eE] [+-]? { return $1 + $2; } e
= [eE] [+-]? { return $1 + $2; }
/* /*
* The following rules are not present in the original JSON gramar, but they are * The following rules are not present in the original JSON gramar, but they are
@ -91,16 +100,21 @@ e = [eE] [+-]? { return $1 + $2; }
* FIXME: Define them according to ECMA-262, 5th ed. * FIXME: Define them according to ECMA-262, 5th ed.
*/ */
digit = [0-9] digit
= [0-9]
digit19 = [1-9] digit19
= [1-9]
hexDigit = [0-9a-fA-F] hexDigit
= [0-9a-fA-F]
/* ===== Whitespace ===== */ /* ===== Whitespace ===== */
_ "whitespace" = whitespace* _ "whitespace"
= whitespace*
// Whitespace is undefined in the original JSON grammar, so I assume a simple // Whitespace is undefined in the original JSON grammar, so I assume a simple
// conventional definition consistent with ECMA-262, 5th ed. // conventional definition consistent with ECMA-262, 5th ed.
whitespace = [ \t\n\r] whitespace
= [ \t\n\r]

138
lib/metagrammar.js
Unescape Escape View File

@ -86,10 +86,10 @@ PEG.grammarParser = (function(){
} }
var result0 = result1 !== null var result0 = result1 !== null
? (function($1, $2) { ? (function($1, $2) {
var result = {}; var result = {};
PEG.ArrayUtils.each($2, function(rule) { result[rule.name] = rule; }); PEG.ArrayUtils.each($2, function(rule) { result[rule.name] = rule; });
return result; return result;
}).apply(null, result1) }).apply(null, result1)
: null; : null;
@ -158,13 +158,13 @@ PEG.grammarParser = (function(){
} }
var result5 = result6 !== null var result5 = result6 !== null
? (function($1, $2, $3, $4) { ? (function($1, $2, $3, $4) {
return { return {
type: "rule", type: "rule",
name: $1, name: $1,
displayName: $2 !== "" ? $2 : null, displayName: $2 !== "" ? $2 : null,
expression: $4 expression: $4
}; };
}).apply(null, result6) }).apply(null, result6)
: null; : null;
@ -234,19 +234,19 @@ PEG.grammarParser = (function(){
} }
var result13 = result14 !== null var result13 = result14 !== null
? (function($1, $2) { ? (function($1, $2) {
if ($2.length > 0) { if ($2.length > 0) {
var alternatives = [$1].concat(PEG.ArrayUtils.map( var alternatives = [$1].concat(PEG.ArrayUtils.map(
$2, $2,
function(element) { return element[1]; } function(element) { return element[1]; }
)); ));
return { return {
type: "choice", type: "choice",
alternatives: alternatives alternatives: alternatives
} }
} else { } else {
return $1; return $1;
} }
}).apply(null, result14) }).apply(null, result14)
: null; : null;
@ -1421,8 +1421,8 @@ PEG.grammarParser = (function(){
} }
var result129 = result130 !== null var result129 = result130 !== null
? (function($1, $2, $3) { ? (function($1, $2, $3) {
return $1 + $2.join(""); return $1 + $2.join("");
}).apply(null, result130) }).apply(null, result130)
: null; : null;
context.reportMatchFailures = savedReportMatchFailures; context.reportMatchFailures = savedReportMatchFailures;
if (context.reportMatchFailures && result129 === null) { if (context.reportMatchFailures && result129 === null) {
@ -1991,20 +1991,22 @@ PEG.grammarParser = (function(){
} }
var result190 = result191 !== null var result190 = result191 !== null
? (function($1, $2, $3, $4, $5) { ? (function($1, $2, $3, $4, $5) {
parts = PEG.ArrayUtils.map($3, function(part) { return part.data; }); parts = PEG.ArrayUtils.map($3, function(part) { return part.data; });
rawText = "[" rawText = "["
+ $2 + $2
+ PEG.ArrayUtils.map($3, function(part) { return part.rawText; }).join("") + PEG.ArrayUtils.map($3, function(part) {
+ "]"; return part.rawText;
}).join("")
+ "]";
return { return {
type: "class", type: "class",
inverted: $2 === "^", inverted: $2 === "^",
parts: parts, parts: parts,
// FIXME: Get the raw text from the input directly. // FIXME: Get the raw text from the input directly.
rawText: rawText rawText: rawText
}; };
}).apply(null, result191) }).apply(null, result191)
: null; : null;
context.reportMatchFailures = savedReportMatchFailures; context.reportMatchFailures = savedReportMatchFailures;
if (context.reportMatchFailures && result190 === null) { if (context.reportMatchFailures && result190 === null) {
@ -2059,18 +2061,18 @@ PEG.grammarParser = (function(){
} }
var result201 = result202 !== null var result201 = result202 !== null
? (function($1, $2, $3) { ? (function($1, $2, $3) {
if ($1.data.charCodeAt(0) > $3.data.charCodeAt(0)) { if ($1.data.charCodeAt(0) > $3.data.charCodeAt(0)) {
throw new this.SyntaxError( throw new this.SyntaxError(
"Invalid character range: " + $1.rawText + "-" + $3.rawText + "." "Invalid character range: " + $1.rawText + "-" + $3.rawText + "."
); );
} }
return { return {
data: [$1.data, $3.data], data: [$1.data, $3.data],
// FIXME: Get the raw text from the input directly. // FIXME: Get the raw text from the input directly.
rawText: $1.rawText + "-" + $3.rawText rawText: $1.rawText + "-" + $3.rawText
} }
}).apply(null, result202) }).apply(null, result202)
: null; : null;
@ -2096,12 +2098,12 @@ PEG.grammarParser = (function(){
var result207 = this._parse_bracketDelimitedCharacter(context); var result207 = this._parse_bracketDelimitedCharacter(context);
var result206 = result207 !== null var result206 = result207 !== null
? (function($1) { ? (function($1) {
return { return {
data: $1, data: $1,
// FIXME: Get the raw text from the input directly. // FIXME: Get the raw text from the input directly.
rawText: PEG.RegExpUtils.quoteForClass($1) rawText: PEG.RegExpUtils.quoteForClass($1)
}; };
})(result207) })(result207)
: null; : null;
@ -2347,14 +2349,14 @@ PEG.grammarParser = (function(){
} }
var result223 = result224 !== null var result223 = result224 !== null
? (function($1, $2, $3) { ? (function($1, $2, $3) {
return $3 return $3
.replace("b", "\b") .replace("b", "\b")
.replace("f", "\f") .replace("f", "\f")
.replace("n", "\n") .replace("n", "\n")
.replace("r", "\r") .replace("r", "\r")
.replace("t", "\t") .replace("t", "\t")
.replace("v", "\x0B") // IE does not recognize "\v". .replace("v", "\x0B") // IE does not recognize "\v".
}).apply(null, result224) }).apply(null, result224)
: null; : null;
@ -2463,8 +2465,8 @@ PEG.grammarParser = (function(){
} }
var result238 = result239 !== null var result238 = result239 !== null
? (function($1, $2, $3) { ? (function($1, $2, $3) {
return String.fromCharCode(parseInt("0x" + $2 + $3)); return String.fromCharCode(parseInt("0x" + $2 + $3));
}).apply(null, result239) }).apply(null, result239)
: null; : null;
@ -2529,8 +2531,8 @@ PEG.grammarParser = (function(){
} }
var result243 = result244 !== null var result243 = result244 !== null
? (function($1, $2, $3, $4, $5) { ? (function($1, $2, $3, $4, $5) {
return String.fromCharCode(parseInt("0x" + $2 + $3 + $4 + $5)); return String.fromCharCode(parseInt("0x" + $2 + $3 + $4 + $5));
}).apply(null, result244) }).apply(null, result244)
: null; : null;

262
lib/metagrammar.pegjs
Unescape Escape View File

@ -1,34 +1,38 @@
grammar = __ rule+ { grammar
var result = {}; = __ rule+ {
PEG.ArrayUtils.each($2, function(rule) { result[rule.name] = rule; }); var result = {};
return result; PEG.ArrayUtils.each($2, function(rule) { result[rule.name] = rule; });
} return result;
}
rule = identifier (literal / "") equals expression {
return { rule
type: "rule", = identifier (literal / "") equals expression {
name: $1, return {
displayName: $2 !== "" ? $2 : null, type: "rule",
expression: $4 name: $1,
}; displayName: $2 !== "" ? $2 : null,
} expression: $4
};
expression = choice }
choice = sequence (slash sequence)* { expression
if ($2.length > 0) { = choice
var alternatives = [$1].concat(PEG.ArrayUtils.map(
$2, choice
function(element) { return element[1]; } = sequence (slash sequence)* {
)); if ($2.length > 0) {
return { var alternatives = [$1].concat(PEG.ArrayUtils.map(
type: "choice", $2,
alternatives: alternatives function(element) { return element[1]; }
));
return {
type: "choice",
alternatives: alternatives
}
} else {
return $1;
}
} }
} else {
return $1;
}
}
sequence sequence
= prefixed* action { = prefixed* action {
@ -73,13 +77,17 @@ primary
/* "Lexical" elements */ /* "Lexical" elements */
action "action" = braced __ { return $1.substr(1, $1.length - 2); } action "action"
= braced __ { return $1.substr(1, $1.length - 2); }
braced = "{" (braced / nonBraceCharacter)* "}" { return $1 + $2.join("") + $3; } braced
= "{" (braced / nonBraceCharacter)* "}" { return $1 + $2.join("") + $3; }
nonBraceCharacters = nonBraceCharacter+ { return $1.join(""); } nonBraceCharacters
= nonBraceCharacter+ { return $1.join(""); }
nonBraceCharacter: [^{}] nonBraceCharacter
= [^{}]
equals = "=" __ { return $1; } equals = "=" __ { return $1; }
slash = "/" __ { return $1; } slash = "/" __ { return $1; }
@ -107,17 +115,20 @@ dot = "." __ { return $1; }
* The simplifications were made just to make the implementation little bit * The simplifications were made just to make the implementation little bit
* easier, there is no "philosophical" reason behind them. * easier, there is no "philosophical" reason behind them.
*/ */
identifier "identifier" = (letter / "_" / "$") (letter / digit / "_" / "$")* __ { identifier "identifier"
return $1 + $2.join(""); = (letter / "_" / "$") (letter / digit / "_" / "$")* __ {
} return $1 + $2.join("");
}
/* /*
* Modelled after ECMA-262, 5th ed., 7.8.4. (syntax & semantics, rules only * Modelled after ECMA-262, 5th ed., 7.8.4. (syntax & semantics, rules only
* vaguely). * vaguely).
*/ */
literal "literal" = (doubleQuotedLiteral / singleQuotedLiteral) __ { return $1; } literal "literal"
= (doubleQuotedLiteral / singleQuotedLiteral) __ { return $1; }
doubleQuotedLiteral = '"' doubleQuotedCharacter* '"' { return $2.join(""); } doubleQuotedLiteral
= '"' doubleQuotedCharacter* '"' { return $2.join(""); }
doubleQuotedCharacter doubleQuotedCharacter
= simpleDoubleQuotedCharacter = simpleDoubleQuotedCharacter
@ -127,9 +138,11 @@ doubleQuotedCharacter
/ unicodeEscapeSequence / unicodeEscapeSequence
/ eolEscapeSequence / eolEscapeSequence
simpleDoubleQuotedCharacter = !('"' / "\\" / eolChar) . { return $2; } simpleDoubleQuotedCharacter
= !('"' / "\\" / eolChar) . { return $2; }
singleQuotedLiteral = "'" singleQuotedCharacter* "'" { return $2.join(""); } singleQuotedLiteral
= "'" singleQuotedCharacter* "'" { return $2.join(""); }
singleQuotedCharacter singleQuotedCharacter
= simpleSingleQuotedCharacter = simpleSingleQuotedCharacter
@ -139,45 +152,51 @@ singleQuotedCharacter
/ unicodeEscapeSequence / unicodeEscapeSequence
/ eolEscapeSequence / eolEscapeSequence
simpleSingleQuotedCharacter = !("'" / "\\" / eolChar) . { return $2; } simpleSingleQuotedCharacter
= !("'" / "\\" / eolChar) . { return $2; }
class "character class" = "[" "^"? (classCharacterRange / classCharacter)* "]" __ {
parts = PEG.ArrayUtils.map($3, function(part) { return part.data; }); class "character class"
rawText = "[" = "[" "^"? (classCharacterRange / classCharacter)* "]" __ {
+ $2 parts = PEG.ArrayUtils.map($3, function(part) { return part.data; });
+ PEG.ArrayUtils.map($3, function(part) { return part.rawText; }).join("") rawText = "["
+ "]"; + $2
+ PEG.ArrayUtils.map($3, function(part) {
return { return part.rawText;
type: "class", }).join("")
inverted: $2 === "^", + "]";
parts: parts,
// FIXME: Get the raw text from the input directly. return {
rawText: rawText type: "class",
}; inverted: $2 === "^",
} parts: parts,
// FIXME: Get the raw text from the input directly.
classCharacterRange = classCharacter "-" classCharacter { rawText: rawText
if ($1.data.charCodeAt(0) > $3.data.charCodeAt(0)) { };
throw new this.SyntaxError( }
"Invalid character range: " + $1.rawText + "-" + $3.rawText + "."
); classCharacterRange
} = classCharacter "-" classCharacter {
if ($1.data.charCodeAt(0) > $3.data.charCodeAt(0)) {
return { throw new this.SyntaxError(
data: [$1.data, $3.data], "Invalid character range: " + $1.rawText + "-" + $3.rawText + "."
// FIXME: Get the raw text from the input directly. );
rawText: $1.rawText + "-" + $3.rawText }
}
} return {
data: [$1.data, $3.data],
classCharacter = bracketDelimitedCharacter { // FIXME: Get the raw text from the input directly.
return { rawText: $1.rawText + "-" + $3.rawText
data: $1, }
// FIXME: Get the raw text from the input directly. }
rawText: PEG.RegExpUtils.quoteForClass($1)
}; classCharacter
} = bracketDelimitedCharacter {
return {
data: $1,
// FIXME: Get the raw text from the input directly.
rawText: PEG.RegExpUtils.quoteForClass($1)
};
}
bracketDelimitedCharacter bracketDelimitedCharacter
= simpleBracketDelimitedCharacter = simpleBracketDelimitedCharacter
@ -187,53 +206,76 @@ bracketDelimitedCharacter
/ unicodeEscapeSequence / unicodeEscapeSequence
/ eolEscapeSequence / eolEscapeSequence
simpleBracketDelimitedCharacter = !("]" / "\\" / eolChar) . { return $2; } simpleBracketDelimitedCharacter
= !("]" / "\\" / eolChar) . { return $2; }
simpleEscapeSequence = "\\" !(digit / "x" / "u" / eolChar) . {
return $3 simpleEscapeSequence
.replace("b", "\b") = "\\" !(digit / "x" / "u" / eolChar) . {
.replace("f", "\f") return $3
.replace("n", "\n") .replace("b", "\b")
.replace("r", "\r") .replace("f", "\f")
.replace("t", "\t") .replace("n", "\n")
.replace("v", "\x0B") // IE does not recognize "\v". .replace("r", "\r")
} .replace("t", "\t")
.replace("v", "\x0B") // IE does not recognize "\v".
}
zeroEscapeSequence = "\\0" !digit { return "\0"; } zeroEscapeSequence
= "\\0" !digit { return "\0"; }
hexEscapeSequence = "\\x" hexDigit hexDigit { hexEscapeSequence
return String.fromCharCode(parseInt("0x" + $2 + $3)); = "\\x" hexDigit hexDigit {
} return String.fromCharCode(parseInt("0x" + $2 + $3));
}
unicodeEscapeSequence = "\\u" hexDigit hexDigit hexDigit hexDigit { unicodeEscapeSequence
return String.fromCharCode(parseInt("0x" + $2 + $3 + $4 + $5)); = "\\u" hexDigit hexDigit hexDigit hexDigit {
} return String.fromCharCode(parseInt("0x" + $2 + $3 + $4 + $5));
}
eolEscapeSequence = "\\" eol { return $2; } eolEscapeSequence
= "\\" eol { return $2; }
digit = [0-9] digit
= [0-9]
hexDigit = [0-9a-fA-F] hexDigit
= [0-9a-fA-F]
letter = lowerCaseLetter / upperCaseLetter letter
= lowerCaseLetter
/ upperCaseLetter
lowerCaseLetter = [a-z] lowerCaseLetter
= [a-z]
upperCaseLetter = [A-Z] upperCaseLetter
= [A-Z]
__ = (whitespace / eol / comment)* __ = (whitespace / eol / comment)*
/* Modelled after ECMA-262, 5th ed., 7.4. */ /* Modelled after ECMA-262, 5th ed., 7.4. */
comment "comment" = singleLineComment / multiLineComment comment "comment"
= singleLineComment
/ multiLineComment
singleLineComment = "//" (!eolChar .)* singleLineComment
= "//" (!eolChar .)*
multiLineComment = "/*" (!"*/" .)* "*/" multiLineComment
= "/*" (!"*/" .)* "*/"
/* Modelled after ECMA-262, 5th ed., 7.3. */ /* Modelled after ECMA-262, 5th ed., 7.3. */
eol "end of line" = "\n" / "\r\n" / "\r" / "\u2028" / "\u2029" eol "end of line"
= "\n"
/ "\r\n"
/ "\r"
/ "\u2028"
/ "\u2029"
eolChar = [\n\r\u2028\u2029] eolChar
= [\n\r\u2028\u2029]
/* Modelled after ECMA-262, 5th ed., 7.2. */ /* Modelled after ECMA-262, 5th ed., 7.2. */
whitespace "whitespace" = [ \t\v\f\u00A0\uFEFF\u1680\u180E\u2000-\u200A\u202F\u205F\u3000] whitespace "whitespace"
= [ \t\v\f\u00A0\uFEFF\u1680\u180E\u2000-\u200A\u202F\u205F\u3000]

Write Preview
Loading…
Cancel
Save