/* A sometimes minimal FORTH compiler and tutorial for Linux / i386 systems. -*- asm -*-
By Richard W.M. Jones <rich@annexia.org> http://annexia.org/forth
This is PUBLIC DOMAIN (see public domain release statement below).
- $Id: jonesforth.S,v 1.20 2007-09-15 11:21:09 rich Exp $
+ $Id: jonesforth.S,v 1.40 2007-09-29 22:12:07 rich Exp $
gcc -m32 -nostdlib -static -Wl,-Ttext,0 -o jonesforth jonesforth.S
*/
- .set JONES_VERSION,20
+ .set JONES_VERSION,39
/*
INTRODUCTION ----------------------------------------------------------------------
over every other element in a list of numbers? You can add it to the language. What
about an operator which pulls in variables directly from a configuration file and makes
them available as FORTH variables? Or how about adding Makefile-like dependencies to
- the language? No problem in FORTH. This concept isn't common in programming languages,
+ the language? No problem in FORTH. How about modifying the FORTH compiler to allow
+ complex inlining strategies -- simple. This concept isn't common in programming languages,
but it has a name (in fact two names): "macros" (by which I mean LISP-style macros, not
the lame C preprocessor) and "domain specific languages" (DSLs).
http://wiki.laptop.org/go/Forth_Lessons
+ http://www.albany.net/~hello/simple.htm
+
Here is another "Why FORTH?" essay: http://www.jwdt.com/~paysan/why-forth.html
Discussion and criticism of this FORTH here: http://lambda-the-ultimate.org/node/2452
This code draws heavily on the design of LINA FORTH (http://home.hccnet.nl/a.w.m.van.der.horst/lina.html)
by Albert van der Horst. Any similarities in the code are probably not accidental.
- Also I used this document (http://ftp.funet.fi/pub/doc/IOCCC/1992/buzzard.2.design) which really
- defies easy explanation.
+ Some parts of this FORTH are also based on this IOCCC entry from 1992:
+ http://ftp.funet.fi/pub/doc/IOCCC/1992/buzzard.2.design.
+ I was very proud when Sean Barrett, the original author of the IOCCC entry, commented in the LtU thread
+ http://lambda-the-ultimate.org/node/2452#comment-36818 about this FORTH.
+
+ And finally I'd like to acknowledge the (possibly forgotten?) authors of ARTIC FORTH because their
+ original program which I still have on original cassette tape kept nagging away at me all these years.
+ http://en.wikipedia.org/wiki/Artic_Software
PUBLIC DOMAIN ----------------------------------------------------------------------
assemble and run the code (save this file as 'jonesforth.S') are:
gcc -m32 -nostdlib -static -Wl,-Ttext,0 -o jonesforth jonesforth.S
- ./jonesforth
-
- You will see lots of 'Warning: unterminated string; newline inserted' messages from the
- assembler. That's just because the GNU assembler doesn't have a good syntax for multi-line
- strings (or rather it used to, but the developers removed it!) so I've abused the syntax
- slightly to make things readable. Ignore these warnings.
+ cat jonesforth.f - | ./jonesforth
If you want to run your own FORTH programs you can do:
- ./jonesforth < myprog.f
+ cat jonesforth.f myprog.f | ./jonesforth
If you want to load your own FORTH code and then continue reading user commands, you can do:
- cat myfunctions.f - | ./jonesforth
+ cat jonesforth.f myfunctions.f - | ./jonesforth
ASSEMBLER ----------------------------------------------------------------------
1C 00 00 00 the CALL prefix.
2C 00 00 00
+ On a 16-bit machine like the ones which originally ran FORTH the savings are even greater - 33%.
+
[Historical note: If the execution model that FORTH uses looks strange from the following
paragraphs, then it was motivated entirely by the need to save memory on early computers.
This code compression isn't so important now when our machines have more memory in their L1
+-----> +------------------+
| codeword -------+
+------------------+ |
- now we're | assembly to <------+
+ now we're | assembly to <-----+
executing | implement + |
this | .. |
function | .. |
.bss
/* FORTH return stack. */
-#define RETURN_STACK_SIZE 8192
+ .set RETURN_STACK_SIZE,8192
.align 4096
.space RETURN_STACK_SIZE
return_stack: // Initial top of return stack.
-/* Space for user-defined words. */
-#define USER_DEFS_SIZE 16384
+/* The user definitions area: space for user-defined words and general memory allocations. */
+ .set USER_DEFS_SIZE,65536
.align 4096
user_defs_start:
.space USER_DEFS_SIZE
+/* This is used as a temporary input buffer when reading from files or the terminal. */
+ .set BUFFER_SIZE,4096
+ .align 4096
+buffer:
+_initbufftop:
+ .space BUFFER_SIZE
+buffend:
+currkey:
+ .int buffer
+bufftop:
+ .int _initbufftop
+
/*
BUILT-IN WORDS ----------------------------------------------------------------------
- Remember our dictionary entries (headers). Let's bring those together with the codeword
+ Remember our dictionary entries (headers)? Let's bring those together with the codeword
and data words to see how : DOUBLE DUP + ; really looks in memory.
pointer to previous word
*/
/* Flags - these are discussed later. */
-#define F_IMMED 0x80
-#define F_HIDDEN 0x20
+ .set F_IMMED,0x80
+ .set F_HIDDEN,0x20
+ .set F_LENMASK,0x1f // length mask
// Store the chain of links.
.set link,0
push %ecx
NEXT
+ defcode "?DUP",4,,QDUP // duplicate top of stack if non-zero
+ pop %eax
+ test %eax,%eax
+ jz 1f
+ push %eax
+1: push %eax
+ NEXT
+
defcode "1+",2,,INCR
incl (%esp) // increment top of stack
NEXT
push %eax // ignore overflow
NEXT
- defcode "/",1,,DIV
- xor %edx,%edx
- pop %ebx
- pop %eax
- idivl %ebx
- push %eax // push quotient
- NEXT
+/*
+ In this FORTH, only /MOD is primitive. Later we will define the / and MOD words in
+ terms of the primitive /MOD. The design of the i386 assembly instruction idiv which
+ leaves both quotient and remainder makes this obvious choice.
+*/
- defcode "MOD",3,,MOD
+ defcode "/MOD",4,,DIVMOD
xor %edx,%edx
pop %ebx
pop %eax
idivl %ebx
push %edx // push remainder
+ push %eax // push quotient
NEXT
defcode "=",1,,EQU // top two words are equal?
1: pushl $0
NEXT
+ defcode "<",1,,LT
+ pop %eax
+ pop %ebx
+ cmp %eax,%ebx
+ jl 1f
+ pushl $0
+ NEXT
+1: pushl $1
+ NEXT
+
+ defcode ">",1,,GT
+ pop %eax
+ pop %ebx
+ cmp %eax,%ebx
+ jg 1f
+ pushl $0
+ NEXT
+1: pushl $1
+ NEXT
+
+ defcode "<=",2,,LE
+ pop %eax
+ pop %ebx
+ cmp %eax,%ebx
+ jle 1f
+ pushl $0
+ NEXT
+1: pushl $1
+ NEXT
+
+ defcode ">=",2,,GE
+ pop %eax
+ pop %ebx
+ cmp %eax,%ebx
+ jge 1f
+ pushl $0
+ NEXT
+1: pushl $1
+ NEXT
+
defcode "0=",2,,ZEQU // top of stack equals 0?
pop %eax
test %eax,%eax
1: pushl $1
NEXT
- defcode "AND",3,,AND
+ defcode "0<>",3,,ZNEQU // top of stack not 0?
+ pop %eax
+ test %eax,%eax
+ jnz 1f
+ pushl $0
+ NEXT
+1: pushl $1
+ NEXT
+
+ defcode "0<",2,,ZLT // comparisons with 0
+ pop %eax
+ test %eax,%eax
+ jl 1f
+ pushl $0
+ NEXT
+1: pushl $1
+ NEXT
+
+ defcode "0>",2,,ZGT
+ pop %eax
+ test %eax,%eax
+ jg 1f
+ pushl $0
+ NEXT
+1: pushl $1
+ NEXT
+
+ defcode "0<=",3,,ZLE
+ pop %eax
+ test %eax,%eax
+ jle 1f
+ pushl $0
+ NEXT
+1: pushl $1
+ NEXT
+
+ defcode "0>=",3,,ZGE
+ pop %eax
+ test %eax,%eax
+ jge 1f
+ pushl $0
+ NEXT
+1: pushl $1
+ NEXT
+
+ defcode "AND",3,,AND // bitwise AND
pop %eax
andl %eax,(%esp)
NEXT
- defcode "OR",2,,OR
+ defcode "OR",2,,OR // bitwise OR
pop %eax
orl %eax,(%esp)
NEXT
- defcode "INVERT",6,,INVERT // this is the FORTH "NOT" function
+ defcode "XOR",3,,XOR // bitwise XOR
+ pop %eax
+ xorl %eax,(%esp)
+ NEXT
+
+ defcode "INVERT",6,,INVERT // this is the FORTH bitwise "NOT" function (cf. NEGATE)
notl (%esp)
NEXT
| addr of EXIT |
+------------------+
- And NEXT just completes the job by, well in this case just by calling DOUBLE again :-)
+ And NEXT just completes the job by, well, in this case just by calling DOUBLE again :-)
LITERALS ----------------------------------------------------------------------
subl %eax,(%ebx) // add it
NEXT
-/* ! and @ (STORE and FETCH) store 32-bit words. It's also useful to be able to read and write bytes.
- * I don't know whether FORTH has these words, so I invented my own, called !b and @b.
- * Byte-oriented operations only work on architectures which permit them (i386 is one of those).
- * UPDATE: writing a byte to the dictionary pointer is called C, in FORTH.
+/*
+ ! and @ (STORE and FETCH) store 32-bit words. It's also useful to be able to read and write bytes
+ so we also define standard words C@ and C!.
+
+ Byte-oriented operations only work on architectures which permit them (i386 is one of those).
*/
- defcode "!b",2,,STOREBYTE
+
+ defcode "C!",2,,STOREBYTE
pop %ebx // address to store at
pop %eax // data to store there
movb %al,(%ebx) // store it
NEXT
- defcode "@b",2,,FETCHBYTE
+ defcode "C@",2,,FETCHBYTE
pop %ebx // address to fetch
xor %eax,%eax
movb (%ebx),%al // fetch it
_Y
_Z
S0 Stores the address of the top of the parameter stack.
- R0 Stores the address of the top of the return stack.
- VERSION Is the current version of this FORTH.
+ BASE The current base for printing and reading numbers.
*/
defvar "STATE",5,,STATE
defvar "HERE",4,,HERE,user_defs_start
- defvar "LATEST",6,,LATEST,name_SYSEXIT // SYSEXIT must be last in built-in dictionary
+ defvar "LATEST",6,,LATEST,name_SYSCALL3 // SYSCALL3 must be last in built-in dictionary
defvar "_X",2,,TX
defvar "_Y",2,,TY
defvar "_Z",2,,TZ
defvar "S0",2,,SZ
- defvar "R0",2,,RZ,return_stack
- defvar "VERSION",7,,VERSION,JONES_VERSION
+ defvar "BASE",4,,BASE,10
+
+/*
+ BUILT-IN CONSTANTS ----------------------------------------------------------------------
+
+ It's also useful to expose a few constants to FORTH. When the word is executed it pushes a
+ constant value on the stack.
+
+ The built-in constants are:
+
+ VERSION Is the current version of this FORTH.
+ R0 The address of the top of the return stack.
+ DOCOL Pointer to DOCOL.
+ F_IMMED The IMMEDIATE flag's actual value.
+ F_HIDDEN The HIDDEN flag's actual value.
+ F_LENMASK The length mask in the flags/len byte.
+
+ SYS_* and the numeric codes of various Linux syscalls (from <asm/unistd.h>)
+*/
+
+//#include <asm-i386/unistd.h> // you might need this instead
+#include <asm/unistd.h>
+
+ .macro defconst name, namelen, flags=0, label, value
+ defcode \name,\namelen,\flags,\label
+ push $\value
+ NEXT
+ .endm
+
+ defconst "VERSION",7,,VERSION,JONES_VERSION
+ defconst "R0",2,,RZ,return_stack
+ defconst "DOCOL",5,,__DOCOL,DOCOL
+ defconst "F_IMMED",7,,__F_IMMED,F_IMMED
+ defconst "F_HIDDEN",8,,__F_HIDDEN,F_HIDDEN
+ defconst "F_LENMASK",9,,__F_LENMASK,F_LENMASK
+
+ defconst "SYS_EXIT",8,,SYS_EXIT,__NR_exit
+ defconst "SYS_OPEN",8,,SYS_OPEN,__NR_open
+ defconst "SYS_CLOSE",9,,SYS_CLOSE,__NR_close
+ defconst "SYS_READ",8,,SYS_READ,__NR_read
+ defconst "SYS_WRITE",9,,SYS_WRITE,__NR_write
+ defconst "SYS_CREAT",9,,SYS_CREAT,__NR_creat
/*
RETURN STACK ----------------------------------------------------------------------
exits the program, which is why when you hit ^D the FORTH system cleanly exits.
*/
-#include <asm-i386/unistd.h>
-
defcode "KEY",3,,KEY
call _KEY
push %eax // push return value on stack
What it does in detail is that it first skips any blanks (spaces, tabs, newlines and so on).
Then it calls KEY to read characters into an internal buffer until it hits a blank. Then it
calculates the length of the word it read and returns the address and the length as
- two words on the stack (with address at the top).
+ two words on the stack (with the length at the top of stack).
Notice that WORD has a single internal buffer which it overwrites each time (rather like
a static C string). Also notice that WORD's internal buffer is just 32 bytes long and
defcode "WORD",4,,WORD
call _WORD
- push %ecx // push length
push %edi // push base address
+ push %ecx // push length
NEXT
_WORD:
5: .space 32
/*
- . (also called DOT) prints the top of the stack as an integer. In real FORTH implementations
- it should print it in the current base, but this assembler version is simpler and can only
- print in base 10.
-
- Remember that you can override even built-in FORTH words easily, so if you want to write a
- more advanced DOT then you can do so easily at a later point, and probably in FORTH.
-*/
-
- defcode ".",1,,DOT
- pop %eax // Get the number to print into %eax
- call _DOT // Easier to do this recursively ...
- NEXT
-_DOT:
- mov $10,%ecx // Base 10
-1:
- cmp %ecx,%eax
- jb 2f
- xor %edx,%edx // %edx:%eax / %ecx -> quotient %eax, remainder %edx
- idivl %ecx
- pushl %edx
- call _DOT
- popl %eax
- jmp 1b
-2:
- xor %ah,%ah
- aam $10
- cwde
- addl $'0',%eax
- call _EMIT
- ret
-
-/*
- Almost the opposite of DOT (but not quite), SNUMBER parses a numeric string such as one returned
- by WORD and pushes the number on the parameter stack.
+ As well as reading in words we'll need to read in numbers and for that we are using a function
+ called SNUMBER. This parses a numeric string such as one returned by WORD and pushes the
+ number on the parameter stack.
This function does absolutely no error checking, and in particular the length of the string
must be >= 1 bytes, and should contain only digits 0-9. If it doesn't you'll get random results.
| LINK | 6 | D | O | U | B | L | E | 0 | DOCOL | DUP | + | EXIT |
+---------+---+---+---+---+---+---+---+---+------------+------------+------------+------------+
- See also >CFA which takes a dictionary entry pointer and returns a pointer to the codeword.
+ See also >CFA and >DFA.
FIND doesn't find dictionary entries which are flagged as HIDDEN. See below for why.
*/
defcode "FIND",4,,FIND
- pop %edi // %edi = address
pop %ecx // %ecx = length
+ pop %edi // %edi = address
call _FIND
- push %eax
+ push %eax // %eax = address of dictionary entry (or NULL)
NEXT
_FIND:
// this won't pick the word (the length will appear to be wrong).
xor %eax,%eax
movb 4(%edx),%al // %al = flags+length field
- andb $(F_HIDDEN|0x1f),%al // %al = name length
+ andb $(F_HIDDEN|F_LENMASK),%al // %al = name length
cmpb %cl,%al // Length is the same?
jne 2f
add $4,%edi // Skip link pointer.
movb (%edi),%al // Load flags+len into %al.
inc %edi // Skip flags+len byte.
- andb $0x1f,%al // Just the length, not the flags.
+ andb $F_LENMASK,%al // Just the length, not the flags.
add %eax,%edi // Skip the name.
addl $3,%edi // The codeword is 4-byte aligned.
andl $~3,%edi
ret
/*
+ Related to >CFA is >DFA which takes a dictionary entry address as returned by FIND and
+ returns a pointer to the first data field.
+
+ FIND returns a pointer to this
+ | >CFA converts it to a pointer to this
+ | |
+ | | >DFA converts it to a pointer to this
+ | | |
+ V V V
+ +---------+---+---+---+---+---+---+---+---+------------+------------+------------+------------+
+ | LINK | 6 | D | O | U | B | L | E | 0 | DOCOL | DUP | + | EXIT |
+ +---------+---+---+---+---+---+---+---+---+------------+------------+------------+------------+
+
+ (Note to those following the source of FIG-FORTH / ciforth: My >DFA definition is
+ different from theirs, because they have an extra indirection).
+
+ You can see that >DFA is easily defined in FORTH just by adding 4 to the result of >CFA.
+*/
+
+ defword ">DFA",4,,TDFA
+ .int TCFA // >CFA (get code field address)
+ .int INCR4 // 4+ (add 4 to it to get to next word)
+ .int EXIT // EXIT (return from FORTH word)
+
+/*
COMPILING ----------------------------------------------------------------------
Now we'll talk about how FORTH compiles words. Recall that a word definition looks like this:
: DOUBLE DUP + ;
^
|
- Next byte returned by KEY
+ Next byte returned by KEY will be the 'D' character of DUP
- so the interpreter (now it's in compile mode, so I guess it's really the compiler) reads DUP,
- gets its codeword pointer, and appends it:
+ so the interpreter (now it's in compile mode, so I guess it's really the compiler) reads "DUP",
+ looks it up in the dictionary, gets its codeword pointer, and appends it:
+-- HERE updated to point here.
|
IMMEDIATE flag (F_IMMED in this code). If a word in the dictionary is flagged as
IMMEDIATE then the interpreter runs it immediately _even if it's in compile mode_.
- I hope I don't need to explain that ; (SEMICOLON) is just such a word, flagged as IMMEDIATE.
+ This is how the word ; (SEMICOLON) works -- as a word flagged in the dictionary as IMMEDIATE.
And all it does is append the codeword for EXIT on to the current definition and switch
back to immediate mode (set STATE back to 0). Shortly we'll see the actual definition
of ; and we'll see that it's really a very simple definition, declared IMMEDIATE.
being compiled. This prevents FIND from finding it, and thus in theory stops any
chance of it being called.
- Compared to the description above, the actual definition of : (COLON) is comparatively simple:
+ The above explains how compiling, : (COLON) and ; (SEMICOLON) works and in a moment I'm
+ going to define them. The : (COLON) function can be made a little bit more general by writing
+ it in two parts. The first part, called CREATE, makes just the header:
+
+ +-- Afterwards, HERE points here.
+ |
+ V
+ +---------+---+---+---+---+---+---+---+---+
+ | LINK | 6 | D | O | U | B | L | E | 0 |
+ +---------+---+---+---+---+---+---+---+---+
+ len pad
+
+ and the second part, the actual definition of : (COLON), calls CREATE and appends the
+ DOCOL codeword, so leaving:
+
+ +-- Afterwards, HERE points here.
+ |
+ V
+ +---------+---+---+---+---+---+---+---+---+------------+
+ | LINK | 6 | D | O | U | B | L | E | 0 | DOCOL |
+ +---------+---+---+---+---+---+---+---+---+------------+
+ len pad codeword
+
+ CREATE is a standard FORTH word and the advantage of this split is that we can reuse it to
+ create other types of words (not just ones which contain code, but words which contain variables,
+ constants and other data).
*/
- defcode ":",1,,COLON
+ defcode "CREATE",6,,CREATE
- // Get the word and create a dictionary entry header for it.
+ // Get the word.
call _WORD // Returns %ecx = length, %edi = pointer to word.
mov %edi,%ebx // %ebx = address of the word
+ // Link pointer.
movl var_HERE,%edi // %edi is the address of the header
movl var_LATEST,%eax // Get link pointer
stosl // and store it in the header.
+ // Length byte and the word itself.
mov %cl,%al // Get the length.
- orb $F_HIDDEN,%al // Set the HIDDEN flag on this entry.
stosb // Store the length/flags byte.
push %esi
mov %ebx,%esi // %esi = word
addl $3,%edi // Align to next 4 byte boundary.
andl $~3,%edi
- movl $DOCOL,%eax // The codeword for user-created words is always DOCOL (the interpreter)
- stosl
-
- // Header built, so now update LATEST and HERE.
- // We'll be compiling words and putting them HERE.
+ // Update LATEST and HERE.
movl var_HERE,%eax
movl %eax,var_LATEST
movl %edi,var_HERE
-
- // And go into compile mode by setting STATE to 1.
- movl $1,var_STATE
NEXT
/*
- , (COMMA) is a standard FORTH word which appends a 32 bit integer (normally a codeword
- pointer) to the user data area pointed to by HERE, and adds 4 to HERE.
+ Because I want to define : (COLON) in FORTH, not assembler, we need a few more FORTH words
+ to use.
+
+ The first is , (COMMA) which is a standard FORTH word which appends a 32 bit integer to the user
+ data area pointed to by HERE, and adds 4 to HERE. So the action of , (COMMA) is:
+
+ previous value of HERE
+ |
+ V
+ +---------+---+---+---+---+---+---+---+---+-- - - - - --+------------+
+ | LINK | 6 | D | O | U | B | L | E | 0 | | <data> |
+ +---------+---+---+---+---+---+---+---+---+-- - - - - --+------------+
+ len pad ^
+ |
+ new value of HERE
+
+ and <data> is whatever 32 bit integer was at the top of the stack.
+
+ , (COMMA) is quite a fundamental operation when compiling. It is used to append codewords
+ to the current word that is being compiled.
*/
defcode ",",1,,COMMA
ret
/*
- ; (SEMICOLON) is also elegantly simple. Notice the F_IMMED flag.
+ Our definitions of : (COLON) and ; (SEMICOLON) will need to switch to and from compile mode.
+
+ Immediate mode vs. compile mode is stored in the global variable STATE, and by updating this
+ variable we can switch between the two modes.
+
+ For various reasons which may become apparent later, FORTH defines two standard words called
+ [ and ] (LBRAC and RBRAC) which switch between modes:
+
+ Word Assembler Action Effect
+ [ LBRAC STATE := 0 Switch to immediate mode.
+ ] RBRAC STATE := 1 Switch to compile mode.
+
+ [ (LBRAC) is an IMMEDIATE word. The reason is as follows: If we are in compile mode and the
+ interpreter saw [ then it would compile it rather than running it. We would never be able to
+ switch back to immediate mode! So we flag the word as IMMEDIATE so that even in compile mode
+ the word runs immediately, switching us back to immediate mode.
*/
- defcode ";",1,F_IMMED,SEMICOLON
- movl $EXIT,%eax // EXIT is the final codeword in compiled words.
- call _COMMA // Store it.
- call _HIDDEN // Toggle the HIDDEN flag (unhides the new word).
- xor %eax,%eax // Set STATE to 0 (back to execute mode).
- movl %eax,var_STATE
+ defcode "[",1,F_IMMED,LBRAC
+ xor %eax,%eax
+ movl %eax,var_STATE // Set STATE to 0.
+ NEXT
+
+ defcode "]",1,,RBRAC
+ movl $1,var_STATE // Set STATE to 1.
NEXT
/*
+ Now we can define : (COLON) using CREATE. It just calls CREATE, appends DOCOL (the codeword), sets
+ the word HIDDEN and goes into compile mode.
+*/
+
+ defword ":",1,,COLON
+ .int CREATE // CREATE the dictionary entry / header
+ .int LIT, DOCOL, COMMA // Append DOCOL (the codeword).
+ .int LATEST, FETCH, HIDDEN // Make the word hidden (see below for definition).
+ .int RBRAC // Go into compile mode.
+ .int EXIT // Return from the function.
+
+/*
+ ; (SEMICOLON) is also elegantly simple. Notice the F_IMMED flag.
+*/
+
+ defword ";",1,F_IMMED,SEMICOLON
+ .int LIT, EXIT, COMMA // Append EXIT (so the word will return).
+ .int LATEST, FETCH, HIDDEN // Toggle hidden flag -- unhide the word (see below for definition).
+ .int LBRAC // Go back to IMMEDIATE mode.
+ .int EXIT // Return from the function.
+
+/*
EXTENDING THE COMPILER ----------------------------------------------------------------------
Words flagged with IMMEDIATE (F_IMMED) aren't just for the FORTH compiler to use. You can define
your own IMMEDIATE words too, and this is a crucial aspect when extending basic FORTH, because
it allows you in effect to extend the compiler itself. Does gcc let you do that?
- Standard FORTH words like IF, WHILE, .", [ and so on are all written as extensions to the basic
+ Standard FORTH words like IF, WHILE, ." and so on are all written as extensions to the basic
compiler, and are all IMMEDIATE words.
The IMMEDIATE word toggles the F_IMMED (IMMEDIATE flag) on the most recently defined word,
*/
defcode "IMMEDIATE",9,F_IMMED,IMMEDIATE
- call _IMMEDIATE
- NEXT
-_IMMEDIATE:
movl var_LATEST,%edi // LATEST word.
addl $4,%edi // Point to name/flags byte.
xorb $F_IMMED,(%edi) // Toggle the IMMED bit.
- ret
+ NEXT
/*
- HIDDEN toggles the other flag, F_HIDDEN, of the latest word. Note that words flagged
- as hidden are defined but cannot be called, so this is rarely used.
+ 'addr HIDDEN' toggles the hidden flag (F_HIDDEN) of the word defined at addr. To hide the
+ most recently defined word (used above in : and ; definitions) you would do:
+
+ LATEST @ HIDDEN
+
+ Setting this flag stops the word from being found by FIND, and so can be used to make 'private'
+ words. For example, to break up a large word into smaller parts you might do:
+
+ : SUB1 ... subword ... ;
+ : SUB2 ... subword ... ;
+ : SUB3 ... subword ... ;
+ : MAIN ... defined in terms of SUB1, SUB2, SUB3 ... ;
+ WORD SUB1 FIND HIDDEN \ Hide SUB1
+ WORD SUB2 FIND HIDDEN \ Hide SUB2
+ WORD SUB3 FIND HIDDEN \ Hide SUB3
+
+ After this, only MAIN is 'exported' or seen by the rest of the program.
*/
defcode "HIDDEN",6,,HIDDEN
- call _HIDDEN
- NEXT
-_HIDDEN:
- movl var_LATEST,%edi // LATEST word.
+ pop %edi // Dictionary entry.
addl $4,%edi // Point to name/flags byte.
xorb $F_HIDDEN,(%edi) // Toggle the HIDDEN bit.
- ret
+ NEXT
/*
' (TICK) is a standard FORTH word which returns the codeword pointer of the next word.
NEXT
/*
- PRINTING STRINGS ----------------------------------------------------------------------
+ LITERAL STRINGS ----------------------------------------------------------------------
- LITSTRING and EMITSTRING are primitives used to implement the ." operator (which is
- written in FORTH). See the definition of that operator below.
+ LITSTRING is a primitive used to implement the ." and S" operators (which are written in
+ FORTH). See the definition of those operators later.
+
+ TELL just prints a string. It's more efficient to define this in assembly because we
+ can make it a single Linux syscall.
*/
defcode "LITSTRING",9,,LITSTRING
lodsl // get the length of the string
- push %eax // push it on the stack
push %esi // push the address of the start of the string
+ push %eax // push it on the stack
addl %eax,%esi // skip past the string
addl $3,%esi // but round up to next 4 byte boundary
andl $~3,%esi
NEXT
- defcode "EMITSTRING",10,,EMITSTRING
+ defcode "TELL",4,,TELL
mov $1,%ebx // 1st param: stdout
- pop %ecx // 2nd param: address of string
pop %edx // 3rd param: length of string
+ pop %ecx // 2nd param: address of string
mov $__NR_write,%eax // write syscall
int $0x80
NEXT
description -- see: http://en.wikipedia.org/wiki/REPL).
*/
-
// COLD must not return (ie. must not call EXIT).
defword "COLD",4,,COLD
.int INTERPRETER // call the interpreter loop (never returns)
- .int LIT,1,SYSEXIT // hmmm, but in case it does, exit(1).
/* This interpreter is pretty simple, but remember that in FORTH you can always override
* it later with a more powerful one!
CHAR puts the ASCII code of the first character of the following word on the stack. For example
CHAR A puts 65 on the stack.
- SYSEXIT exits the process using Linux exit syscall.
+ SYSCALL3 makes a standard Linux system call. (See <asm/unistd.h> for a list of system call
+ numbers). This is the form to use when the function takes up to three parameters.
+
+ In this FORTH, SYSCALL3 must be the last word in the built-in (assembler) dictionary because we
+ initialise the LATEST variable to point to it. This means that if you want to extend the assembler
+ part, you must put new words before SYSCALL3, or else change how LATEST is initialised.
*/
defcode "CHAR",4,,CHAR
push %eax // Push it onto the stack.
NEXT
- // NB: SYSEXIT must be the last entry in the built-in dictionary.
- defcode SYSEXIT,7,,SYSEXIT
- pop %ebx
- mov $__NR_exit,%eax
+ defcode "SYSCALL3",8,,SYSCALL3
+ pop %eax // System call number (see <asm/unistd.h>)
+ pop %ebx // First parameter.
+ pop %ecx // Second parameter
+ pop %edx // Third parameter
int $0x80
+ push %eax // Result (negative for -errno)
+ NEXT
/*
START OF FORTH CODE ----------------------------------------------------------------------
words can be written as FORTH itself, including words like IF, THEN, .", etc which in most
languages would be considered rather fundamental.
- As a kind of trick, I prefill the input buffer with the initial FORTH code. Once this code
- has run (when we get to the "OK" prompt), this input buffer is reused for reading any further
- user input.
-
- Some notes about the code:
-
- \ (backslash) is the FORTH way to start a comment which goes up to the next newline. However
- because this is a C-style string, I have to escape the backslash, which is why they appear as
- \\ comment.
-
- Similarly, any backslashes in the code are doubled, and " becomes \" (eg. the definition of ."
- is written as : .\" ... ;)
-
- I use indenting to show structure. The amount of whitespace has no meaning to FORTH however
- except that you must use at least one whitespace character between words, and words themselves
- cannot contain whitespace.
+ I used to append this here in the assembly file, but I got sick of fighting against gas's
+ stupid (lack of) multiline string syntax. So now that is in a separate file called jonesforth.f
- FORTH is case-sensitive. Use capslock!
-
- Enjoy!
+ If you don't already have that file, download it from http://annexia.org/forth in order
+ to continue the tutorial.
*/
- .data
- .align 4096
-buffer:
- // Multi-line constant gives 'Warning: unterminated string; newline inserted' messages which you can ignore.
- .ascii "\
-\\ Define some character constants
-: '\\n' 10 ;
-: 'SPACE' 32 ;
-: '\"' 34 ;
-: ':' 58 ;
-
-\\ CR prints a carriage return
-: CR '\\n' EMIT ;
-
-\\ SPACE prints a space
-: SPACE 'SPACE' EMIT ;
-
-\\ Primitive . (DOT) function doesn't follow with a blank, so redefine it to behave like FORTH.
-\\ Notice how we can trivially redefine existing functions.
-: . . SPACE ;
-
-\\ DUP, DROP are defined in assembly for speed, but this is how you might define them
-\\ in FORTH. Notice use of the scratch variables _X and _Y.
-\\ : DUP _X ! _X @ _X @ ;
-\\ : DROP _X ! ;
-
-\\ The 2... versions of the standard operators work on pairs of stack entries. They're not used
-\\ very commonly so not really worth writing in assembler. Here is how they are defined in FORTH.
-: 2DUP OVER OVER ;
-: 2DROP DROP DROP ;
-
-\\ More standard FORTH words.
-: 2* 2 * ;
-: 2/ 2 / ;
-
-\\ [ and ] allow you to break into immediate mode while compiling a word.
-: [ IMMEDIATE \\ define [ as an immediate word
- 0 STATE ! \\ go into immediate mode
- ;
-
-: ]
- 1 STATE ! \\ go back to compile mode
- ;
-
-\\ LITERAL takes whatever is on the stack and compiles LIT <foo>
-: LITERAL IMMEDIATE
- ' LIT , \\ compile LIT
- , \\ compile the literal itself (from the stack)
- ;
-
-\\ condition IF true-part THEN rest
-\\ compiles to:
-\\ condition 0BRANCH OFFSET true-part rest
-\\ where OFFSET is the offset of 'rest'
-\\ condition IF true-part ELSE false-part THEN
-\\ compiles to:
-\\ condition 0BRANCH OFFSET true-part BRANCH OFFSET2 false-part rest
-\\ where OFFSET if the offset of false-part and OFFSET2 is the offset of rest
-
-\\ IF is an IMMEDIATE word which compiles 0BRANCH followed by a dummy offset, and places
-\\ the address of the 0BRANCH on the stack. Later when we see THEN, we pop that address
-\\ off the stack, calculate the offset, and back-fill the offset.
-: IF IMMEDIATE
- ' 0BRANCH , \\ compile 0BRANCH
- HERE @ \\ save location of the offset on the stack
- 0 , \\ compile a dummy offset
-;
-
-: THEN IMMEDIATE
- DUP
- HERE @ SWAP - \\ calculate the offset from the address saved on the stack
- SWAP ! \\ store the offset in the back-filled location
-;
-
-: ELSE IMMEDIATE
- ' BRANCH , \\ definite branch to just over the false-part
- HERE @ \\ save location of the offset on the stack
- 0 , \\ compile a dummy offset
- SWAP \\ now back-fill the original (IF) offset
- DUP \\ same as for THEN word above
- HERE @ SWAP -
- SWAP !
-;
-
-\\ BEGIN loop-part condition UNTIL
-\\ compiles to:
-\\ loop-part condition 0BRANCH OFFSET
-\\ where OFFSET points back to the loop-part
-\\ This is like do { loop-part } while (condition) in the C language
-: BEGIN IMMEDIATE
- HERE @ \\ save location on the stack
-;
-
-: UNTIL IMMEDIATE
- ' 0BRANCH , \\ compile 0BRANCH
- HERE @ - \\ calculate the offset from the address saved on the stack
- , \\ compile the offset here
-;
-
-\\ BEGIN loop-part AGAIN
-\\ compiles to:
-\\ loop-part BRANCH OFFSET
-\\ where OFFSET points back to the loop-part
-\\ In other words, an infinite loop which can only be returned from with EXIT
-: AGAIN IMMEDIATE
- ' BRANCH , \\ compile BRANCH
- HERE @ - \\ calculate the offset back
- , \\ compile the offset here
-;
-
-\\ BEGIN condition WHILE loop-part REPEAT
-\\ compiles to:
-\\ condition 0BRANCH OFFSET2 loop-part BRANCH OFFSET
-\\ where OFFSET points back to condition (the beginning) and OFFSET2 points to after the whole piece of code
-\\ So this is like a while (condition) { loop-part } loop in the C language
-: WHILE IMMEDIATE
- ' 0BRANCH , \\ compile 0BRANCH
- HERE @ \\ save location of the offset2 on the stack
- 0 , \\ compile a dummy offset2
-;
-
-: REPEAT IMMEDIATE
- ' BRANCH , \\ compile BRANCH
- SWAP \\ get the original offset (from BEGIN)
- HERE @ - , \\ and compile it after BRANCH
- DUP
- HERE @ SWAP - \\ calculate the offset2
- SWAP ! \\ and back-fill it in the original location
-;
-
-\\ With the looping constructs, we can now write SPACES, which writes n spaces to stdout.
-: SPACES
- BEGIN
- SPACE \\ print a space
- 1- \\ until we count down to 0
- DUP 0=
- UNTIL
-;
-
-\\ .S prints the contents of the stack. Very useful for debugging.
-: .S
- DSP@ \\ get current stack pointer
- BEGIN
- DUP @ . \\ print the stack element
- 4+ \\ move up
- DUP S0 @ 4- = \\ stop when we get to the top
- UNTIL
- DROP
-;
-
-\\ DEPTH returns the depth of the stack.
-: DEPTH S0 @ DSP@ - ;
-
-\\ .\" is the print string operator in FORTH. Example: .\" Something to print\"
-\\ The space after the operator is the ordinary space required between words.
-\\ This is tricky to define because it has to do different things depending on whether
-\\ we are compiling or in immediate mode. (Thus the word is marked IMMEDIATE so it can
-\\ detect this and do different things).
-\\ In immediate mode we just keep reading characters and printing them until we get to
-\\ the next double quote.
-\\ In compile mode we have the problem of where we're going to store the string (remember
-\\ that the input buffer where the string comes from may be overwritten by the time we
-\\ come round to running the function). We store the string in the compiled function
-\\ like this:
-\\ ..., LITSTRING, string length, string rounded up to 4 bytes, EMITSTRING, ...
-: .\" IMMEDIATE
- STATE @ \\ compiling?
- IF
- ' LITSTRING , \\ compile LITSTRING
- HERE @ \\ save the address of the length word on the stack
- 0 , \\ dummy length - we don't know what it is yet
- BEGIN
- KEY \\ get next character of the string
- DUP '\"' <>
- WHILE
- HERE @ !b \\ store the character in the compiled image
- 1 HERE +! \\ increment HERE pointer by 1 byte
- REPEAT
- DROP \\ drop the double quote character at the end
- DUP \\ get the saved address of the length word
- HERE @ SWAP - \\ calculate the length
- 4- \\ subtract 4 (because we measured from the start of the length word)
- SWAP ! \\ and back-fill the length location
- HERE @ \\ round up to next multiple of 4 bytes for the remaining code
- 3 +
- 3 INVERT AND
- HERE !
- ' EMITSTRING , \\ compile the final EMITSTRING
- ELSE
- \\ In immediate mode, just read characters and print them until we get
- \\ to the ending double quote. Much simpler than the above code!
- BEGIN
- KEY
- DUP '\"' = IF EXIT THEN
- EMIT
- AGAIN
- THEN
-;
-
-\\ While compiling, [COMPILE] WORD compiles WORD if it would otherwise be IMMEDIATE.
-: [COMPILE] IMMEDIATE
- WORD \\ get the next word
- FIND \\ find it in the dictionary
- >CFA \\ get its codeword
- , \\ and compile that
-;
-
-\\ RECURSE makes a recursive call to the current word that is being compiled.
-\\ Normally while a word is being compiled, it is marked HIDDEN so that references to the
-\\ same word within are calls to the previous definition of the word.
-: RECURSE IMMEDIATE
- LATEST @ >CFA \\ LATEST points to the word being compiled at the moment
- , \\ compile it
-;
-
-\\ ALLOT is used to allocate (static) memory when compiling. It increases HERE by
-\\ the amount given on the stack.
-\\: ALLOT HERE +! ;
-
-
-\\ Finally print the welcome prompt.
-.\" JONESFORTH VERSION \" VERSION @ . CR
-.\" OK \"
-"
-
-_initbufftop:
- .align 4096
-buffend:
-
-currkey:
- .int buffer
-bufftop:
- .int _initbufftop
-
/* END OF jonesforth.S */
git.annexia.org / jonesforth.git / blobdiff