extra/peg/javascript/tokenizer/tokenizer.factor

   1 ! Copyright (C) 2008 Chris Double.
   2 ! See http://factorcode.org/license.txt for BSD license.
   3 USING: kernel sequences strings arrays math.parser peg peg.ebnf peg.javascript.ast ;
   4 IN: peg.javascript.tokenizer
   5
   6 #! Grammar for JavaScript. Based on OMeta-JS example from:
   7 #! http://jarrett.cs.ucla.edu/ometa-js/#JavaScript_Compiler
   8
   9 USE: prettyprint
  10
  11 EBNF: tokenize-javascript
  12 Letter            = [a-zA-Z]
  13 Digit             = [0-9]
  14 Digits            = Digit+
  15 SingleLineComment = "//" (!("\n") .)* "\n" => [[ ignore ]]
  16 MultiLineComment  = "/*" (!("*/") .)* "*/" => [[ ignore ]]
  17 Space             = " " | "\t" | "\r" | "\n" | SingleLineComment | MultiLineComment
  18 Spaces            = Space* => [[ ignore ]]
  19 NameFirst         = Letter | "$" => [[ CHAR: $ ]] | "_" => [[ CHAR: _ ]]
  20 NameRest          = NameFirst | Digit
  21 iName             = NameFirst NameRest* => [[ first2 swap prefix >string ]]
  22 Keyword           =  ("break"
  23                     | "case"
  24                     | "catch"
  25                     | "continue"
  26                     | "default"
  27                     | "delete"
  28                     | "do"
  29                     | "else"
  30                     | "finally"
  31                     | "for"
  32                     | "function"
  33                     | "if"
  34                     | "in"
  35                     | "instanceof"
  36                     | "new"
  37                     | "return"
  38                     | "switch"
  39                     | "this"
  40                     | "throw"
  41                     | "try"
  42                     | "typeof"
  43                     | "var"
  44                     | "void"
  45                     | "while"
  46                     | "with") !(NameRest)
  47 Name              = !(Keyword) iName  => [[ ast-name boa ]]
  48 Number            =   Digits:ws '.' Digits:fs => [[ ws "." fs 3array concat >string string>number ast-number boa ]]
  49                     | Digits => [[ >string string>number ast-number boa ]]
  50
  51 EscapeChar        =   "\\n" => [[ 10 ]]
  52                     | "\\r" => [[ 13 ]]
  53                     | "\\t" => [[ 9 ]]
  54 StringChars1       = (EscapeChar | !('"""') .)* => [[ >string ]]
  55 StringChars2       = (EscapeChar | !('"') .)* => [[ >string ]]
  56 StringChars3       = (EscapeChar | !("'") .)* => [[ >string ]]
  57 Str                =   '"""' StringChars1:cs '"""' => [[ cs ast-string boa ]]
  58                      | '"' StringChars2:cs '"' => [[ cs ast-string boa ]]
  59                      | "'" StringChars3:cs "'" => [[ cs ast-string boa ]]
  60 RegExpFlags        = NameRest* => [[ >string ]]
  61 NonTerminator      = !("\n" | "\r") .
  62 BackslashSequence  = "\\" NonTerminator => [[ second ]]
  63 RegExpFirstChar    =   !("*" | "\\" | "/") NonTerminator
  64                      | BackslashSequence
  65 RegExpChar         =   !("\\" | "/") NonTerminator
  66                      | BackslashSequence
  67 RegExpChars        = RegExpChar*
  68 RegExpBody         = RegExpFirstChar RegExpChars => [[ first2 swap prefix >string ]]
  69 RegExp             = "/" RegExpBody:b "/" RegExpFlags:fl => [[ b fl ast-regexp boa ]]
  70 Special            =   "("    | ")"   | "{"   | "}"   | "["   | "]"   | ","   | ";"
  71                      | "?"    | ":"   | "!==" | "!="  | "===" | "=="  | "="   | ">="
  72                      | ">>>=" | ">>>" | ">>=" | ">>"  | ">"   | "<="  | "<<=" | "<<"
  73                      | "<"    | "++"  | "+="  | "+"   | "--"  | "-="  | "-"   | "*="
  74                      | "*"    | "/="  | "/"   | "%="  | "%"   | "&&=" | "&&"  | "||="
  75                      | "||"   | "."   | "!"   | "&="  | "&"   | "|="  | "|"   | "^="
  76                      | "^"
  77 Tok                = Spaces (Name | Keyword | Number | Str | RegExp | Special )
  78 Toks               = Tok* Spaces
  79 ;EBNF
  80