short example of abstract compilation performed on JS

compiler.rb

Lex Config for C - http://www.quut.com/c/ANSI-C-grammar-l.html
Bison Config for C - http://www.quut.com/c/ANSI-C-grammar-y.html
ECMA Spec - http://www.ecma-international.org/ecma-262/5.1/#contents
 
# Organization
# Statements (Executes an operation)
# Expressions (Evaluates to a value)
 
js = <<js
function hello() {
  var hello = "Hello";
  world = "World";
  console.log(hello + " " + world);
}
hello();
js
 
# Lexical Tokens
function
identifier (hello)
open_param
close_param
open_curly
var_decl
identifier (hello)
equals
string ("hello")
semicolon
identifier (word)
equals
string ("world")
semicolon
identifier (console)
dot_operator
identifier (log)
open_param
identifier (hello)
plus_sign
string (" ")
plus_sign
identifier (world)
close_param
semicolon
close_curly
identifier (hello)
open_param
close_param
semicolon
 
# Parsing
# Program :: Source Elements
# Source Elments :: Source Element
#                :: Source Elements -> Source Element
require 'rkelly'
RKelly::Parser.new.parse(js)
# =>
#<SourceElementsNode
  @value=[
  #<FunctionDeclNode
    @line=1, @value="hello", @arguments=[], @function_body=#<FunctionBodyNode
      @value=#<SourceElementsNode
        @value=[
          #<VarStatementNode
            @line=2, @value=[
              #<VarDeclNode
                @constant=false, @line=2, @name="hello", @value=#<AssignExprNode
                  @line=2, @value=#<StringNode
                    @line=2, @value="\"Hello\"">>>
            ]>,
          #<ExpressionStatementNode
            @line=2, @value=#<OpEqualNode
              @left=#<ResolveNode
                @line=2, @value="world">,  
              @value=#<StringNode
                @line=2, @value="\"World\"">>>, 
          #<ExpressionStatementNode
            @line=3, @value=#<FunctionCallNode
              @arguments=#<ArgumentsNode
                @line=3, @value=[
                  #<AddNode
                    @left=#<AddNode
                      @left=#<ResolveNode
                        @line=4, @value="hello">,
                      @value=#<StringNode
                        @line=4, @value="\" \"">>,
                    @value=#<ResolveNode
                      @line=4, @value="world">>                  
                ]>,    
              @value=#<DotAccessorNode
                @accessor="log", @line=3, @value=#<ResolveNode
                  @line=3, @value="console">>>>
        ]>>>, 
  #<ExpressionStatementNode
    @line=5, @value=#<FunctionCallNode
      @arguments=#<ArgumentsNode
        @line=5, @value=[]>,    
      @value=#<ResolveNode
        @line=5, @value="hello">>>
  ]>
 
# Compilation
1. Allocate space A to store the program, Ax to store program metadata
2. Allocate space B to store a function, Bx to store function metadata
3. Create a reference in Ax :hello => B
4. Write function preamble to B (This also initiates Bx each time)
5. Write (Create a reference in Bx :hello => "Hello") to B
6. Write (Create a reference in Ax :world => "World") to B
7. Write (Query metadata for console, save to temp1) to B
8. Write (Query temp1 for log, save to temp2) to B
9. Write (Query metadata for :hello (Bx[:hello]), save to temp3) to B
10. Write(Push temp3 onto stack) to B
11. Write(Push " " onto stack) to B
12. Write (Query metadata for :world (Ax[:world]), save to temp4) to B
13. Write (Push temp4 onto stack) to B
14. Write (Call temp2) to B
15. Write function cleanup to B
16. Write (Query metadata for :hello (Ax[:hello]), save to temp5) to A
17. Write (Call temp5) to A
 
## Example Disassembly
# Source Code
#include "stdio.h"

char *foo () {
  return "Hello World";
}

int main () {
  printf(foo());
}

## Compiled Object
# Section Dump
a.o:     file format elf64-x86-64

Contents of section .text:
 0000 554889e5 b8000000 005dc355 4889e5b8  UH.......].UH...
 0010 00000000 e8000000 004889c7 b8000000  .........H......
 0020 00e80000 00005dc3                    ......].        
Contents of section .rodata:
 0000 48656c6c 6f20576f 726c6400           Hello World.    
Contents of section .comment:
 0000 00474343 3a202847 4e552920 342e382e  .GCC: (GNU) 4.8.
 0010 30203230 31333034 31312028 70726572  0 20130411 (prer
 0020 656c6561 73652900                    elease).        
Contents of section .eh_frame:
 0000 14000000 00000000 017a5200 01781001  .........zR..x..
 0010 1b0c0708 90010000 1c000000 1c000000  ................
 0020 00000000 0b000000 00410e10 8602430d  .........A....C.
 0030 06460c07 08000000 1c000000 3c000000  .F..........<...
 0040 00000000 1d000000 00410e10 8602430d  .........A....C.
 0050 06580c07 08000000                    .X......        

# Decompilation
Disassembly of section .text:

0000000000000000 <foo>:
   0: 55                    push   %rbp
   1: 48 89 e5              mov    %rsp,%rbp
   4: b8 00 00 00 00        mov    $0x0,%eax
   9: 5d                    pop    %rbp
   a: c3                    retq   

000000000000000b <main>:
   b: 55                    push   %rbp
   c: 48 89 e5              mov    %rsp,%rbp
   f: b8 00 00 00 00        mov    $0x0,%eax
  14: e8 00 00 00 00        callq  19 <main+0xe>
  19: 48 89 c7              mov    %rax,%rdi
  1c: b8 00 00 00 00        mov    $0x0,%eax
  21: e8 00 00 00 00        callq  26 <main+0x1b>
  26: 5d                    pop    %rbp
  27: c3                    retq   

# Relocation Dump (Used to set execution values in linker)
RELOCATION RECORDS FOR [.text]:
OFFSET           TYPE              VALUE 
0000000000000005 R_X86_64_32       .rodata
0000000000000015 R_X86_64_PC32     foo-0x0000000000000004
0000000000000022 R_X86_64_PC32     printf-0x0000000000000004


RELOCATION RECORDS FOR [.eh_frame]:
OFFSET           TYPE              VALUE 
0000000000000020 R_X86_64_PC32     .text
0000000000000040 R_X86_64_PC32     .text+0x000000000000000b

# Optimized Object
Disassembly of section .text:

0000000000000000 <foo>:
   0: b8 00 00 00 00        mov    $0x0,%eax
   5: c3                    retq   

Disassembly of section .text.startup:

0000000000000000 <main>:
   0: bf 00 00 00 00        mov    $0x0,%edi
   5: 31 c0                 xor    %eax,%eax
   7: e9 00 00 00 00        jmpq   c <main+0xc>

# Optimized Reolcation Data
RELOCATION RECORDS FOR [.text]:
OFFSET           TYPE              VALUE 
0000000000000001 R_X86_64_32       .rodata.str1.1


RELOCATION RECORDS FOR [.text.startup]:
OFFSET           TYPE              VALUE 
0000000000000001 R_X86_64_32       .rodata.str1.1
0000000000000008 R_X86_64_PC32     printf-0x0000000000000004


RELOCATION RECORDS FOR [.eh_frame]:
OFFSET           TYPE              VALUE 
0000000000000020 R_X86_64_PC32     .text
0000000000000034 R_X86_64_PC32     .text.startup

# Symbol Table 
SYMBOL TABLE:
0000000000000000 l    df *ABS*  0000000000000000 a.c
0000000000000000 l    d  .text  0000000000000000 .text
0000000000000000 l    d  .data  0000000000000000 .data
0000000000000000 l    d  .bss 0000000000000000 .bss
0000000000000000 l    d  .rodata  0000000000000000 .rodata
0000000000000000 l    d  .note.GNU-stack  0000000000000000 .note.GNU-stack
0000000000000000 l    d  .eh_frame  0000000000000000 .eh_frame
0000000000000000 l    d  .comment 0000000000000000 .comment
0000000000000000 g     F .text  000000000000000b foo
000000000000000b g     F .text  000000000000001d main
0000000000000000         *UND*  0000000000000000 printf


# Linked Object
0000000000400500 <foo>:
  400500: 55                    push   %rbp
  400501: 48 89 e5              mov    %rsp,%rbp
  400504: b8 b4 05 40 00        mov    $0x4005b4,%eax
  400509: 5d                    pop    %rbp
  40050a: c3                    retq   

000000000040050b <main>:
  40050b: 55                    push   %rbp
  40050c: 48 89 e5              mov    %rsp,%rbp
  40050f: b8 00 00 00 00        mov    $0x0,%eax
  400514: e8 e7 ff ff ff        callq  400500 <foo>
  400519: 48 89 c7              mov    %rax,%rdi
  40051c: b8 00 00 00 00        mov    $0x0,%eax
  400521: e8 ba fe ff ff        callq  4003e0 <printf@plt>
  400526: 5d                    pop    %rbp
  400527: c3                    retq   
  400528: 0f 1f 84 00 00 00 00  nopl   0x0(%rax,%rax,1)
  40052f: 00