lang-bootstrap/04a/in04

; add 24 + 16 = 40 to the stack pointer to put argc, argv in the right place
byte 0x48
byte 0x81
byte 0xc4
byte 40
byte 0
byte 0
byte 0

global output_fd

goto main

global defines
global defines_end

function main
	argument argv2
	argument argv1
	argument argv0
	argument argc
	local input_filename
	local output_filename
	
	defines = malloc(4000000)
	defines_end = defines
	
	if argc < 3 goto default_filenames
		input_filename = argv1
		output_filename = argv2
		goto got_filenames
	:default_filenames
		input_filename = .str_default_input_filename
		output_filename = .str_default_output_filename
	:got_filenames
	
	output_fd = syscall(2, output_filename, 0x241, 420) ; 420 = octal 644
	if output_fd >= 0 goto output_file_good
	file_error(output_filename)
	:output_file_good
	preprocess(input_filename, output_fd)
	close(output_fd)
	free(defines)
	exit(0)

:str_default_input_filename
	string in04a
	byte 0

:str_default_output_filename
	string out04a
	byte 0

function preprocess
	argument input_filename
	argument output_fd
	local input_fd
	global 2048 line_buf
	local line
	local b
	local p
	local c
	local line_number
	
	line_number = 0
	line = &line_buf
	
	; first, open the input file
	input_fd = syscall(2, input_filename, 0)
	if input_fd >= 0 goto input_file_good
	file_error(input_filename)
	:input_file_good
	
	; output a line directive
	fputs(output_fd, .str_line1)
	fputs(output_fd, input_filename)
	fputc(output_fd, 10)
	
	:preprocess_loop
		line_number += 1
		b = fgets(input_fd, line, 2000)
		if b == 0 goto preprocess_eof
		b = str_startswith(line, .str_define)
		if b != 0 goto handle_define
		b = str_startswith(line, .str_include)
		if b != 0 goto handle_include
		
		; normal line (not #define or #include)
		p = line
		:normal_line_loop
			c = *1p
			if c == 0 goto normal_line_loop_end
			; optimization: don't look this up if it doesn't start with an uppercase letter
			b = isupper(c)
			if b == 0 goto no_replacement
			b = look_up_define(p)
			if b == 0 goto no_replacement
				; wow! a replacement!
				fputs(output_fd, b)
				; advance p past this identifier
				:advance_loop
					c = *1p
					b = is_ident(c)
					if b == 0 goto normal_line_loop
					p += 1
					goto advance_loop
			:no_replacement
				fputc(output_fd, c)
				p += 1
				goto normal_line_loop
		:normal_line_loop_end
		fputc(output_fd, 10)
		goto preprocess_loop
		
		:handle_define
			local def
			def = line + 8 ; 8 = length of "#define "
			; make sure define name only consists of identifier characters
			p = def
			c = *1p
			b = isupper(c)
			if b == 0 goto bad_define
			:define_check_loop
				c = *1p
				if c == 32 goto define_check_loop_end
				b = is_ident(c)
				if b == 0 goto bad_define
				p += 1
				goto define_check_loop
			:define_check_loop_end
			b = look_up_define(def)
			if b != 0 goto redefinition
			defines_end = strcpy(defines_end, def)
			defines_end += 1
			fputc(output_fd, 10) ; don't screw up line numbers
			goto preprocess_loop
			:bad_define
				fputs(2, .str_bad_define)
				fputs(2, line)
				fputc(2, 10)
				exit(1)
			:redefinition
				fputs(2, .str_redefinition)
				fputs(2, line)
				fputc(2, 10)
				exit(1)
		:handle_include
			local included_filename
			local n
			included_filename = line + 9 ; 9 = length of "#include "
			preprocess(included_filename, output_fd)
			; reset filename and line number
			fputs(output_fd, .str_line)
			n = line_number + 1
			fputn(output_fd, n)
			fputc(output_fd, 32)
			fputs(output_fd, input_filename)
			fputc(output_fd, 10)
			goto preprocess_loop
	:preprocess_eof
	close(input_fd)
	return

:str_redefinition
	string Preprocessor redefinition:
	byte 32
	byte 0
	
:str_bad_define
	string Bad preprocessor definition:
	byte 32
	byte 0

:str_define
	string #define
	byte 32
	byte 0

:str_include
	string #include
	byte 32
	byte 0

:str_line
	string #line
	byte 32
	byte 0

:str_line1
	string #line
	byte 32
	string 1
	byte 32
	byte 0

; returns a pointer to the thing str should be replaced with,
; or 0 if there is no definition for str.
function look_up_define
	argument str
	local lookup
	local p
	local c
	lookup = defines
	:lookup_loop
		c = *1lookup
		if c == 0 goto lookup_not_found	
		c = ident_eq(str, lookup)
		if c == 1 goto lookup_found
		lookup = memchr(lookup, 0)
		lookup += 1
		goto lookup_loop
	:lookup_not_found
	return 0
	:lookup_found
	p = memchr(lookup, 32)
	return p + 1 ; the character after the space following the name is the replacement

; returns 1 if the identifiers s1 and s2 are equal; 0 otherwise
function ident_eq
	argument s1
	argument s2
	local p1
	local p2
	local c1
	local c2
	local b1
	local b2
	p1 = s1
	p2 = s2
	:ident_eq_loop
		c1 = *1p1
		c2 = *1p2
		b1 = is_ident(c1)
		b2 = is_ident(c2)
		if b1 != b2 goto return_0
		if b1 == 0 goto return_1
		if c1 != c2 goto return_0
		p1 += 1
		p2 += 1
		goto ident_eq_loop

function is_ident
	argument c
	if c < '0 goto return_0
	if c <= '9 goto return_1
	if c < 'A goto return_0
	if c <= 'Z goto return_1
	if c == '_ goto return_1
	goto return_0

function file_error
	argument name
	fputs(2, .str_file_error)
	fputs(2, name)
	fputc(2, 10)
	exit(1)
	
:str_file_error
	string Error opening file:
	byte 32
	byte 0

function malloc
	argument size
	local total_size
	local memory
	total_size = size + 8
	memory = syscall(9, 0, total_size, 3, 0x22, -1, 0)
	if memory ] 0xffffffffffff0000 goto malloc_failed
	*8memory = total_size
	return memory + 8

:malloc_failed
	fputs(2, .str_out_of_memory)
	exit(1)
	
:str_out_of_memory
	string Out of memory.
	byte 10
	byte 0

function free
	argument memory
	local psize
	local size
	psize = memory - 8
	size = *8psize
	syscall(11, psize, size)
	return

; returns a pointer to a null-terminated string containing the number given
function itos
	global 32 itos_string
	argument x
	local c
	local p
	p = &itos_string
	p += 30
	:itos_loop
		c = x % 10
		c += '0
		*1p = c
		x /= 10
		if x == 0 goto itos_loop_end
		p -= 1
		goto itos_loop
	:itos_loop_end
	return p


; returns the number at the start of the given string
function stoi
	argument s
	local p
	local n
	local c
	n = 0
	p = s
	:stoi_loop
		c = *1p
		if c < '0 goto stoi_loop_end
		if c > '9 goto stoi_loop_end
		n *= 10
		n += c - '0
		p += 1
		goto stoi_loop
	:stoi_loop_end
	return n

function memchr
	argument mem
	argument c
	local p
	p = mem
	:memchr_loop
		if *1p == c goto memchr_loop_end
		p += 1
		goto memchr_loop
	:memchr_loop_end
	return p

function strlen
	argument s
	local p
	p = s
	:strlen_loop
		if *1p == 0 goto strlen_loop_end
		p += 1
		goto strlen_loop
	:strlen_loop_end
	return p - s

function strcpy
	argument dest
	argument src
	local p
	local q
	local c
	p = dest
	q = src
	:strcpy_loop
		c = *1q
		*1p = c
		if c == 0 goto strcpy_loop_end
		p += 1
		q += 1
		goto strcpy_loop
	:strcpy_loop_end
	return p
	
function str_startswith
	argument s
	argument prefix
	local p
	local q
	local c1
	local c2
	p = s
	q = prefix
	:str_startswith_loop
		c1 = *1p
		c2 = *1q
		if c2 == 0 goto return_1
		if c1 != c2 goto return_0
		p += 1
		q += 1
		goto str_startswith_loop

function fputs
	argument fd
	argument s
	local length
	length = strlen(s)
	syscall(1, fd, s, length)
	return

function puts
	argument s
	fputs(1, s)
	return

function fputn
	argument fd
	argument n
	local s
	s = itos(n)
	fputs(fd, s)
	return

function fputc
	argument fd
	argument c
	syscall(1, fd, &c, 1)
	return

function putc
	argument c
	fputc(1, c)
	return

; returns 0 at end of file
function fgetc
	argument fd
	local c
	c = 0
	syscall(0, fd, &c, 1)
	return c

; read a line from fd as a null-terminated string
; returns 0 at end of file, 1 otherwise
function fgets
	argument fd
	argument buf
	argument size
	local p
	local end
	local c
	p = buf
	end = buf + size
	
	:fgets_loop
		c = fgetc(fd)
		if c == 0 goto fgets_eof
		if c == 10 goto fgets_eol
		*1p = c
		p += 1
		if p == end goto fgets_eob
		goto fgets_loop
		
	:fgets_eol ; end of line
	*1p = 0
	return 1
	:fgets_eof ; end of file
	*1p = 0
	return 0
	:fgets_eob ; end of buffer
	p -= 1
	*1p = 0
	return 1

function close
	argument fd
	syscall(3, fd)
	return

function isupper
	argument c
	if c < 'A goto return_0
	if c <= 'Z goto return_1
	goto return_0

function exit
	argument status_code
	syscall(0x3c, status_code)

:return_0
	return 0
:return_1
	return 1

function syscall
	; I've done some testing, and this should be okay even if
	; rbp-56 goes beyond the end of the stack.
	; mov rax, [rbp-16]
	byte 0x48
	byte 0x8b
	byte 0x85
	byte 0xf0
	byte 0xff
	byte 0xff
	byte 0xff
	; mov rdi, rax
	byte 0x48
	byte 0x89
	byte 0xc7
	
	; mov rax, [rbp-24]
	byte 0x48
	byte 0x8b
	byte 0x85
	byte 0xe8
	byte 0xff
	byte 0xff
	byte 0xff
	; mov rsi, rax
	byte 0x48
	byte 0x89
	byte 0xc6
	
	; mov rax, [rbp-32]
	byte 0x48
	byte 0x8b
	byte 0x85
	byte 0xe0
	byte 0xff
	byte 0xff
	byte 0xff
	; mov rdx, rax
	byte 0x48
	byte 0x89
	byte 0xc2
	
	; mov rax, [rbp-40]
	byte 0x48
	byte 0x8b
	byte 0x85
	byte 0xd8
	byte 0xff
	byte 0xff
	byte 0xff
	; mov r10, rax
	byte 0x49
	byte 0x89
	byte 0xc2
	
	; mov rax, [rbp-48]
	byte 0x48
	byte 0x8b
	byte 0x85
	byte 0xd0
	byte 0xff
	byte 0xff
	byte 0xff
	; mov r8, rax
	byte 0x49
	byte 0x89
	byte 0xc0
	
	; mov rax, [rbp-56]
	byte 0x48
	byte 0x8b
	byte 0x85
	byte 0xc8
	byte 0xff
	byte 0xff
	byte 0xff
	; mov r9, rax
	byte 0x49
	byte 0x89
	byte 0xc1
	
	; mov rax, [rbp-8]
	byte 0x48
	byte 0x8b
	byte 0x85
	byte 0xf8
	byte 0xff
	byte 0xff
	byte 0xff
	
	; syscall
	byte 0x0f
	byte 0x05
	
	return