/* 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 1.26 2007-09-23 23:17:56 rich Exp $
+ $Id: jonesforth.S,v 1.41 2007-09-29 23:11:27 rich Exp $
gcc -m32 -nostdlib -static -Wl,-Ttext,0 -o jonesforth jonesforth.S
*/
- .set JONES_VERSION,26
+ .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).
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 ----------------------------------------------------------------------
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
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 $1
NEXT
- defcode "0<",2,,ZLT
+ defcode "0<",2,,ZLT // comparisons with 0
pop %eax
test %eax,%eax
jl 1f
1: pushl $1
NEXT
- defcode "AND",3,,AND
+ 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 "XOR",3,,XOR
+ defcode "XOR",3,,XOR // bitwise XOR
pop %eax
xorl %eax,(%esp)
NEXT
- defcode "INVERT",6,,INVERT // this is the FORTH bitwise "NOT" function
+ 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
*/
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
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.
+ 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
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
+
+ defconst "O_RDONLY",8,,__O_RDONLY,0
+ defconst "O_WRONLY",8,,__O_WRONLY,1
+ defconst "O_RDWR",6,,__O_RDWR,2
+ defconst "O_CREAT",7,,__O_CREAT,0100
+ defconst "O_EXCL",6,,__O_EXCL,0200
+ defconst "O_TRUNC",7,,__O_TRUNC,01000
+ defconst "O_APPEND",8,,__O_APPEND,02000
+ defconst "O_NONBLOCK",10,,__O_NONBLOCK,04000
+
/*
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 the current BASE.
-*/
-
- defcode ".",1,,DOT
- pop %eax // Get the number to print into %eax
- call _DOT // Easier to do this recursively ...
- NEXT
-_DOT:
- mov var_BASE,%ecx // Get current BASE
-1:
- cmp %ecx,%eax // %eax < BASE? If so jump to print immediately.
- jb 2f
- xor %edx,%edx // %edx:%eax / %ecx -> quotient %eax, remainder %edx
- idivl %ecx
- pushl %edx // Print quotient (top half) first ...
- call _DOT
- popl %eax // ... then loop to print remainder
- jmp 1b
-2: // %eax < BASE so print immediately.
- movl $digits,%edx
- addl %eax,%edx
- movb (%edx),%al // Note top bits are already zero.
- call _EMIT
- ret
- .section .rodata
-digits: .ascii "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ"
-
-/*
- 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.
*/
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:
NEXT
/*
- PRINTING STRINGS ----------------------------------------------------------------------
+ LITERAL STRINGS ----------------------------------------------------------------------
- LITSTRING and EMITSTRING are primitives used to implement the ." and S" operators
- (which are written in FORTH). See the definition of those operators 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
// 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, SYSEXIT must be the last word in the built-in (assembler) dictionary because we
+ 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 SYSEXIT, or else change how LATEST is initialised.
+ 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.
+ 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
- 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.
-
- 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 ;
-
-\\ CR prints a carriage return
-: CR '\\n' EMIT ;
-
-\\ SPACE prints a space
-: SPACE 'SPACE' EMIT ;
-
-\\ 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 built-in . (DOT) function doesn't print a space after the number (unlike the real FORTH word).
-\\ However this is very easily fixed by redefining . (DOT). Any built-in word can be redefined.
-: .
- . \\ this refers back to the previous definition (but see also RECURSE below)
- SPACE
-;
-
-\\ 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 / ;
-
-\\ Standard words for manipulating BASE.
-: DECIMAL 10 BASE ! ;
-: HEX 16 BASE ! ;
-
-\\ Standard words for booleans.
-: TRUE 1 ;
-: FALSE 0 ;
-: NOT 0= ;
-
-\\ LITERAL takes whatever is on the stack and compiles LIT <foo>
-: LITERAL IMMEDIATE
- ' LIT , \\ compile LIT
- , \\ compile the literal itself (from the stack)
- ;
-
-\\ Now we can use [ and ] to insert literals which are calculated at compile time.
-\\ Within definitions, use [ ... ] LITERAL anywhere that '...' is a constant expression which you
-\\ would rather only compute once (at compile time, rather than calculating it each time your word runs).
-: ':'
- [ \\ go into immediate mode temporarily
- CHAR : \\ push the number 58 (ASCII code of colon) on the stack
- ] \\ go back to compile mode
- LITERAL \\ compile LIT 58 as the definition of ':' word
-;
-
-\\ A few more character constants defined the same way as above.
-: '(' [ CHAR ( ] LITERAL ;
-: ')' [ CHAR ) ] LITERAL ;
-: '\"' [ CHAR \" ] LITERAL ;
-
-\\ So far we have defined only very simple definitions. Before we can go further, we really need to
-\\ make some control structures, like IF ... THEN and loops. Luckily we can define arbitrary control
-\\ structures directly in FORTH.
-\\
-\\ Please note that the control structures as I have defined them here will only work inside compiled
-\\ words. If you try to type in expressions using IF, etc. in immediate mode, then they won't work.
-\\ Making these work in immediate mode is left as an exercise for the reader.
-
-\\ 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
-;
-
-\\ FORTH allows ( ... ) as comments within function definitions. This works by having an IMMEDIATE
-\\ word called ( which just drops input characters until it hits the corresponding ).
-: ( IMMEDIATE
- 1 \\ allowed nested parens by keeping track of depth
- BEGIN
- KEY \\ read next character
- DUP '(' = IF \\ open paren?
- DROP \\ drop the open paren
- 1+ \\ depth increases
- ELSE
- ')' = IF \\ close paren?
- 1- \\ depth decreases
- THEN
- THEN
- DUP 0= UNTIL \\ continue until we reach matching close paren, depth 0
- DROP \\ drop the depth counter
-;
-
-(
- From now on we can use ( ... ) for comments.
-
- In FORTH style we can also use ( ... -- ... ) to show the effects that a word has on the
- parameter stack. For example:
-
- ( n -- ) means that the word consumes an integer (n) from the parameter stack.
- ( b a -- c ) means that the word uses two integers (a and b, where a is at the top of stack)
- and returns a single integer (c).
- ( -- ) means the word has no effect on the stack
-)
-
-( With the looping constructs, we can now write SPACES, which writes n spaces to stdout. )
-: SPACES ( n -- )
- BEGIN
- DUP 0> ( while n > 0 )
- WHILE
- SPACE ( print a space )
- 1- ( until we count down to 0 )
- REPEAT
- DROP
-;
-
-( c a b WITHIN returns true if a <= c and c < b )
-: WITHIN
- ROT ( b c a )
- OVER ( b c a c )
- <= IF
- > IF ( b c -- )
- TRUE
- ELSE
- FALSE
- THEN
- ELSE
- 2DROP ( b c -- )
- FALSE
- THEN
-;
-
-( .S prints the contents of the stack. Very useful for debugging. )
-: .S ( -- )
- DSP@ ( get current stack pointer )
- BEGIN
- DUP S0 @ <
- WHILE
- DUP @ . ( print the stack element )
- 4+ ( move up )
- REPEAT
- DROP
-;
-
-( DEPTH returns the depth of the stack. )
-: DEPTH ( -- n )
- S0 @ DSP@ -
- 4- ( adjust because S0 was on the stack when we pushed DSP )
-;
-
-(
- [NB. The following may be a bit confusing because of the need to use backslash before
- each double quote character. The backslashes are there to keep the assembler happy.
- They are NOT part of the final output. So here we are defining a function called
- 'S double-quote' (not 'S backslash double-quote').]
-
- S\" string\" is used in FORTH to define strings. It leaves the address of the string and
- its length on the stack with the address at the top.
-
- In compile mode we append
- LITSTRING <string length> <string rounded up 4 bytes>
- to the current word. The primitive LITSTRING does the right thing when the current
- word is executed.
-
- In immediate mode there isn't a particularly good place to put the string, but in this
- case we put the string at HERE (but we _don't_ change HERE). This is meant as a temporary
- location, likely to be overwritten soon after.
-)
-: S\" IMMEDIATE ( -- len addr )
- STATE @ IF ( compiling? )
- ' 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 !
- ELSE ( immediate mode )
- HERE @ ( get the start address of the temporary space )
- BEGIN
- KEY
- DUP '\"' <>
- WHILE
- OVER !b ( save next character )
- 1+ ( increment address )
- REPEAT
- HERE @ - ( calculate the length )
- HERE @ ( push the start address )
- THEN
-;
-
-(
- .\" 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 @ IF ( compiling? )
- ' 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
- DROP ( drop the double quote character )
- EXIT ( return from this function )
- THEN
- EMIT
- AGAIN
- THEN
-;
-
-(
- In FORTH, global constants and variables are defined like this:
-
- 10 CONSTANT TEN when TEN is executed, it leaves the integer 10 on the stack
- VARIABLE VAR when VAR is executed, it leaves the address of VAR on the stack
-
- Constants can be read by not written, eg:
-
- TEN . CR prints 10
-
- You can read a variable (in this example called VAR) by doing:
-
- VAR @ leaves the value of VAR on the stack
- VAR @ . CR prints the value of VAR
-
- and update the variable by doing:
-
- 20 VAR ! sets VAR to 20
-
- Note that variables are uninitialised (but see VALUE later on which provides initialised
- variables with a slightly simpler syntax).
-
- How can we define the words CONSTANT and VARIABLE?
-
- The trick is to define a new word for the variable itself (eg. if the variable was called
- 'VAR' then we would define a new word called VAR). This is easy to do because we exposed
- dictionary entry creation through the CREATE word (part of the definition of : above).
- A call to CREATE TEN leaves the dictionary entry:
-
- +--- HERE
- |
- V
- +---------+---+---+---+---+
- | LINK | 3 | T | E | N |
- +---------+---+---+---+---+
- len
-
- For CONSTANT we can continue by appending DOCOL (the codeword), then LIT followed by
- the constant itself and then EXIT, forming a little word definition that returns the
- constant:
-
- +---------+---+---+---+---+------------+------------+------------+------------+
- | LINK | 3 | T | E | N | DOCOL | LIT | 10 | EXIT |
- +---------+---+---+---+---+------------+------------+------------+------------+
- len codeword
-
- Notice that this word definition is exactly the same as you would have got if you had
- written : TEN 10 ;
-)
-: CONSTANT
- CREATE ( make the dictionary entry (the name follows CONSTANT) )
- DOCOL , ( append DOCOL (the codeword field of this word) )
- ' LIT , ( append the codeword LIT )
- , ( append the value on the top of the stack )
- ' EXIT , ( append the codeword EXIT )
-;
-
-(
- VARIABLE is a little bit harder because we need somewhere to put the variable. There is
- nothing particularly special about the 'user definitions area' (the area of memory pointed
- to by HERE where we have previously just stored new word definitions). We can slice off
- bits of this memory area to store anything we want, so one possible definition of
- VARIABLE might create this:
-
- +--------------------------------------------------------------+
- | |
- V |
- +---------+---------+---+---+---+---+------------+------------+---|--------+------------+
- | <var> | LINK | 3 | V | A | R | DOCOL | LIT | <addr var> | EXIT |
- +---------+---------+---+---+---+---+------------+------------+------------+------------+
- len codeword
-
- where <var> is the place to store the variable, and <addr var> points back to it.
-
- To make this more general let's define a couple of words which we can use to allocate
- arbitrary memory from the user definitions area.
-
- First ALLOT, where n ALLOT allocates n bytes of memory. (Note when calling this that
- it's a very good idea to make sure that n is a multiple of 4, or at least that next time
- a word is compiled that n has been left as a multiple of 4).
-)
-: ALLOT ( n -- addr )
- HERE @ SWAP ( here n -- )
- HERE +! ( adds n to HERE, after this the old value of HERE is still on the stack )
-;
-
-(
- Second, CELLS. In FORTH the phrase 'n CELLS ALLOT' means allocate n integers of whatever size
- is the natural size for integers on this machine architecture. On this 32 bit machine therefore
- CELLS just multiplies the top of stack by 4.
-)
-: CELLS ( n -- n ) 4 * ;
-
-(
- So now we can define VARIABLE easily in much the same way as CONSTANT above. Refer to the
- diagram above to see what the word that this creates will look like.
-)
-: VARIABLE
- 1 CELLS ALLOT ( allocate 1 cell of memory, push the pointer to this memory )
- CREATE ( make the dictionary entry (the name follows VARIABLE) )
- DOCOL , ( append DOCOL (the codeword field of this word) )
- ' LIT , ( append the codeword LIT )
- , ( append the pointer to the new memory )
- ' EXIT , ( append the codeword EXIT )
-;
-
-(
- VALUEs are like VARIABLEs but with a simpler syntax. You would generally use them when you
- want a variable which is read often, and written infrequently.
-
- 20 VALUE VAL creates VAL with initial value 20
- VAL pushes the value directly on the stack
- 30 TO VAL updates VAL, setting it to 30
-
- Notice that 'VAL' on its own doesn't return the address of the value, but the value itself,
- making values simpler and more obvious to use than variables (no indirection through '@').
- The price is a more complicated implementation, although despite the complexity there is no
- particular performance penalty at runtime.
-
- A naive implementation of 'TO' would be quite slow, involving a dictionary search each time.
- But because this is FORTH we have complete control of the compiler so we can compile TO more
- efficiently, turning:
- TO VAL
- into:
- LIT <addr> !
- and calculating <addr> (the address of the value) at compile time.
-
- Now this is the clever bit. We'll compile our value like this:
-
- +---------+---+---+---+---+------------+------------+------------+------------+
- | LINK | 3 | V | A | L | DOCOL | LIT | <value> | EXIT |
- +---------+---+---+---+---+------------+------------+------------+------------+
- len codeword
-
- where <value> is the actual value itself. Note that when VAL executes, it will push the
- value on the stack, which is what we want.
-
- But what will TO use for the address <addr>? Why of course a pointer to that <value>:
-
- code compiled - - - - --+------------+------------+------------+-- - - - -
- by TO VAL | LIT | <addr> | ! |
- - - - - --+------------+-----|------+------------+-- - - - -
- |
- V
- +---------+---+---+---+---+------------+------------+------------+------------+
- | LINK | 3 | V | A | L | DOCOL | LIT | <value> | EXIT |
- +---------+---+---+---+---+------------+------------+------------+------------+
- len codeword
-
- In other words, this is a kind of self-modifying code.
-
- (Note to the people who want to modify this FORTH to add inlining: values defined this
- way cannot be inlined).
-)
-: VALUE ( n -- )
- CREATE ( make the dictionary entry (the name follows VALUE) )
- DOCOL , ( append DOCOL )
- ' LIT , ( append the codeword LIT )
- , ( append the initial value )
- ' EXIT , ( append the codeword EXIT )
-;
-
-: TO IMMEDIATE ( n -- )
- WORD ( get the name of the value )
- FIND ( look it up in the dictionary )
- >DFA ( get a pointer to the first data field (the 'LIT') )
- 4+ ( increment to point at the value )
- STATE @ IF ( compiling? )
- ' LIT , ( compile LIT )
- , ( compile the address of the value )
- ' ! , ( compile ! )
- ELSE ( immediate mode )
- ! ( update it straightaway )
- THEN
-;
-
-( x +TO VAL adds x to VAL )
-: +TO IMMEDIATE
- WORD ( get the name of the value )
- FIND ( look it up in the dictionary )
- >DFA ( get a pointer to the first data field (the 'LIT') )
- 4+ ( increment to point at the value )
- STATE @ IF ( compiling? )
- ' LIT , ( compile LIT )
- , ( compile the address of the value )
- ' +! , ( compile +! )
- ELSE ( immediate mode )
- +! ( update it straightaway )
- THEN
-;
-
-(
- ID. takes an address of a dictionary entry and prints the word's name.
-
- For example: LATEST @ ID. would print the name of the last word that was defined.
-)
-: ID.
- 4+ ( skip over the link pointer )
- DUP @b ( get the flags/length byte )
- F_LENMASK AND ( mask out the flags - just want the length )
-
- BEGIN
- DUP 0> ( length > 0? )
- WHILE
- SWAP 1+ ( addr len -- len addr+1 )
- DUP @b ( len addr -- len addr char | get the next character)
- EMIT ( len addr char -- len addr | and print it)
- SWAP 1- ( len addr -- addr len-1 | subtract one from length )
- REPEAT
- 2DROP ( len addr -- )
-;
-
-(
- 'WORD word FIND ?HIDDEN' returns true if 'word' is flagged as hidden.
-
- 'WORD word FIND ?IMMEDIATE' returns true if 'word' is flagged as immediate.
-)
-: ?HIDDEN
- 4+ ( skip over the link pointer )
- @b ( get the flags/length byte )
- F_HIDDEN AND ( mask the F_HIDDEN flag and return it (as a truth value) )
-;
-: ?IMMEDIATE
- 4+ ( skip over the link pointer )
- @b ( get the flags/length byte )
- F_IMMED AND ( mask the F_IMMED flag and return it (as a truth value) )
-;
-
-(
- WORDS prints all the words defined in the dictionary, starting with the word defined most recently.
- However it doesn't print hidden words.
-
- The implementation simply iterates backwards from LATEST using the link pointers.
-)
-: WORDS
- LATEST @ ( start at LATEST dictionary entry )
- BEGIN
- DUP 0<> ( while link pointer is not null )
- WHILE
- DUP ?HIDDEN NOT IF
- DUP ID. ( print the word )
- THEN
- SPACE
- @ ( dereference the link pointer - go to previous word )
- REPEAT
- DROP
- CR
-;
-
-(
- So far we have only allocated words and memory. FORTH provides a rather primitive method
- to deallocate.
-
- 'FORGET word' deletes the definition of 'word' from the dictionary and everything defined
- after it, including any variables and other memory allocated after.
-
- The implementation is very simple - we look up the word (which returns the dictionary entry
- address). Then we set HERE to point to that address, so in effect all future allocations
- and definitions will overwrite memory starting at the word. We also need to set LATEST to
- point to the previous word.
-
- Note that you cannot FORGET built-in words (well, you can try but it will probably cause
- a segfault).
-
- XXX: Because we wrote VARIABLE to store the variable in memory allocated before the word,
- in the current implementation VARIABLE FOO FORGET FOO will leak 1 cell of memory.
-)
-: FORGET
- WORD FIND ( find the word, gets the dictionary entry address )
- DUP @ LATEST ! ( set LATEST to point to the previous word )
- HERE ! ( and store HERE with the dictionary address )
-;
-
-(
- 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. However we still have
- access to the word which we are currently compiling through the LATEST pointer so we
- can use that to compile a recursive call.
-)
-: RECURSE IMMEDIATE
- LATEST @ >CFA ( LATEST points to the word being compiled at the moment )
- , ( compile it )
-;
-
-(
- DUMP is used to dump out the contents of memory, in the 'traditional' hexdump format.
-)
-: DUMP ( addr len -- )
- BASE @ ROT ( save the current BASE at the bottom of the stack )
- HEX ( and switch the hexadecimal mode )
-
- BEGIN
- DUP 0> ( while len > 0 )
- WHILE
- OVER . ( print the address )
- SPACE
-
- ( print up to 16 words on this line )
- 2DUP ( addr len addr len )
- 1- 15 AND 1+ ( addr len addr linelen )
- BEGIN
- DUP 0> ( while linelen > 0 )
- WHILE
- SWAP ( addr len linelen addr )
- DUP @b ( addr len linelen addr byte )
- . SPACE ( print the byte )
- 1+ SWAP 1- ( addr len linelen addr -- addr len addr+1 linelen-1 )
- REPEAT
- 2DROP ( addr len )
-
- ( print the ASCII equivalents )
- 2DUP 1- 15 AND 1+ ( addr len addr linelen )
- BEGIN
- DUP 0> ( while linelen > 0)
- WHILE
- SWAP ( addr len linelen addr )
- DUP @b ( addr len linelen addr byte )
- DUP 32 128 WITHIN IF ( 32 <= c < 128? )
- EMIT
- ELSE
- DROP [ CHAR ? ] LITERAL EMIT
- THEN
- 1+ SWAP 1- ( addr len linelen addr -- addr len addr+1 linelen-1 )
- REPEAT
- 2DROP ( addr len )
- CR
-
- DUP 1- 15 AND 1+ ( addr len linelen )
- DUP ( addr len linelen linelen )
- ROT ( addr linelen len linelen )
- - ( addr linelen len-linelen )
- ROT ( len-linelen addr linelen )
- + ( len-linelen addr+linelen )
- SWAP ( addr-linelen len-linelen )
- REPEAT
-
- 2DROP ( restore stack )
- BASE ! ( restore saved BASE )
-;
-
-( 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