Created
November 24, 2009 19:04
-
-
Save fabioyamate/242115 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
require 'grammar_wirth' | |
require 'pp' | |
NONTERMINAL = /[a-zA-Z][a-zA-Z_]*/ | |
TERMINAL = /".+"/ | |
RULES = /.*\./ | |
RULE = /(?:([a-zA-Z][a-zA-Z_]*)\s*=)?\s*(.+\.)\n?/ | |
TOKENS = { | |
"(" => "LPAR", | |
")" => "RPAR", | |
"{" => "LCUR", | |
"}" => "RCUR", | |
"[" => "LBRA", | |
"]" => "RBRA", | |
"=" => "ASSIGN", | |
"+=" => "ADD_ASSIGN", | |
"-=" => "SUB_ASSIGN", | |
"*=" => "MULT_ASSIGN", | |
"/=" => "DIV_ASSIGN", | |
"**=" => "PWR_ASSIGN", | |
"%=" => "MOD_ASSIGN", | |
"<" => "LT", | |
">" => "GT", | |
"<=" => "LE", | |
">=" => "GE", | |
"!=" => "NE", | |
"==" => "EQ", | |
"*" => "MULT", | |
"+" => "ADD", | |
"-" => "SUB", | |
"/" => "DIV", | |
"%" => "MOD", | |
"**" => "PWR", | |
".." => "RANGE" | |
} | |
TEMPLATE = <<-CODE | |
void %nonterminal%() | |
{ | |
while (true) { | |
int current_state = 0; | |
switch (current_state) { | |
%transitions% | |
default: | |
fatal_error("unexpected state"); | |
break; | |
} | |
} | |
} | |
CODE | |
def submachine_codegen(input, to) | |
<<-EOF | |
#{input}(); /* CALL SUB MACHINE */ | |
current_state = #{to}; | |
EOF | |
end | |
def token_codegen(input, to) | |
if input.eql?("ANY_CHAR") | |
<<-EOF | |
if (' ' <= ch && ch <= '~') | |
current_state = #{to}; | |
EOF | |
else | |
input = TOKENS[input] if TOKENS.has_key?(input) | |
input = '"\""' if input.eql?('"') | |
input = %q["'"] if input.eql?("'") | |
<<-EOF | |
if (token->class == #{input}) | |
current_state = #{to}; | |
EOF | |
end | |
end | |
lexer = <<-LEXER | |
string = """ { "any_char" } """ | "'" { "any_char" } "'". | |
op_assign = "=" | "+=" | "/=" | "-=" | "%=" | "**=" . | |
op_expr = "<" | ">" | ">=" | "<=" | "!=" | "==" | "+" | "-" | "/" | "*" | "%" | "**" | "..". | |
integer = digit { digit }. | |
float = digit { digit } "." digit { digit }. | |
operation = identifier [ "!" | "?" ]. | |
identifier = ( "_" | letter | letter ) { "_" | letter | digit }. | |
number = digit { digit }. | |
LEXER | |
file = File.new("lexer.c", "w") | |
output = "" | |
lexer.scan(RULES).each do |r| | |
name, decl = RULE.match(r).captures | |
w = Grammar::Wirth.new(decl) | |
dfa = w.minimized_dfa | |
dfa[:states].each do |state| | |
output << " case #{state}:\n" | |
moves = [] | |
first = true | |
dfa[:transitions][state].each do |transition| | |
input, to = transition | |
data = /"(.+)"/.match(input) | |
if first | |
output << " ch = readc(in);\n" | |
first = false | |
end | |
if not data.nil? | |
moves << token_codegen(data.captures.first.upcase, to) | |
else | |
moves << submachine_codegen(input, to) | |
end | |
end | |
output << moves.join(' else ') | |
if moves.size > 1 | |
output << %q[ else | |
fatal_error("Syntax Error"); | |
] | |
end | |
output << " return; /* ACCEPT */\n" if dfa[:final].include?(state) | |
output << " break;\n" | |
end | |
file << TEMPLATE.sub('%nonterminal%', name).sub('%transitions%', output).gsub(/else\s+if/, "else if") | |
end | |
file.close |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment