start C compiler

7 files changed, 528 insertions, 0 deletions

diff --git a/05/.gitignore b/05/.gitignore
new file mode 100644
index 0000000..f4c3e60
--- /dev/null
+++ b/05/.gitignore
@@ -0,0 +1 @@
+in04
diff --git a/05/Makefile b/05/Makefile
new file mode 100644
index 0000000..7242404
--- /dev/null
+++ b/05/Makefile
@@ -0,0 +1,11 @@
+all: out04
+in04: *.b ../04a/out04
+	../04a/out04 main.b in04
+out04: in04 ../04/out03
+	../04/out03 in04 out04
+%.html: %.md ../markdown
+	../markdown $<
+%.out: %.c
+	./out04 $< $@
+clean:
+	rm -f out* README.html *.out
diff --git a/05/constants.b b/05/constants.b
new file mode 100644
index 0000000..691fe65
--- /dev/null
+++ b/05/constants.b
@@ -0,0 +1,32 @@
+; #define KEYWORD_AUTO 101  (auto only exists in C for legacy reasons and doesn't appear in TCC's source code)
+#define KEYWORD_DOUBLE 102
+#define KEYWORD_INT 103
+#define KEYWORD_STRUCT 104
+#define KEYWORD_BREAK 105
+#define KEYWORD_ELSE 106
+#define KEYWORD_LONG 107
+#define KEYWORD_SWITCH 108
+#define KEYWORD_CASE 109
+#define KEYWORD_ENUM 110
+#define KEYWORD_REGISTER 111
+#define KEYWORD_TYPEDEF 112
+#define KEYWORD_CHAR 113
+#define KEYWORD_EXTERN 114
+#define KEYWORD_RETURN 115
+#define KEYWORD_UNION 116
+; #define KEYWORD_CONST 117 (we can just #define const)
+#define KEYWORD_FLOAT 118
+#define KEYWORD_SHORT 119
+#define KEYWORD_UNSIGNED 120
+#define KEYWORD_CONTINUE 121
+#define KEYWORD_FOR 122
+; #define KEYWORD_SIGNED 123 (again, just #define signed)
+#define KEYWORD_VOID 124
+#define KEYWORD_DEFAULT 125
+#define KEYWORD_GOTO 126
+#define KEYWORD_SIZEOF 127
+; #define KEYWORD_VOLATILE 128 (just #define volatile if need be)
+#define KEYWORD_DO 129
+#define KEYWORD_IF 130
+#define KEYWORD_STATIC 131
+#define KEYWORD_WHILE 132
diff --git a/05/main.b b/05/main.b
new file mode 100644
index 0000000..6239f71
--- /dev/null
+++ b/05/main.b
@@ -0,0 +1,46 @@
+; 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
+goto main
+
+#include util.b
+#include constants.b
+#include preprocess.b
+
+function main
+	argument argv2
+	argument argv1
+	argument argv0
+	argument argc
+	local input_filename
+	local output_filename
+	
+	input_filename = .str_default_input_filename
+	output_filename = .str_default_output_filename
+	if argc == 1 goto have_filenames
+	if argc != 3 goto usage_error
+	input_filename = argv1
+	output_filename = argv2
+	:have_filenames
+	split_into_preprocessing_tokens(input_filename)
+	exit(0)
+
+:usage_error
+	fputs(2, .str_usage_error)
+	exit(1)
+
+:str_usage_error
+	string Please either specify no arguments or an input and output file.
+
+:str_default_input_filename
+	string main.c
+	byte 0
+	
+:str_default_output_filename
+	string a.out
+	byte 0
diff --git a/05/main.c b/05/main.c
new file mode 100644
index 0000000..fedd283
--- /dev/null
+++ b/05/main.c
@@ -0,0 +1,6 @@
+test\
+ing/*
+I am */testing
+that this is working
+hello \
+there.
diff --git a/05/preprocess.b b/05/preprocess.b
new file mode 100644
index 0000000..36fcbd2
--- /dev/null
+++ b/05/preprocess.b
@@ -0,0 +1,75 @@
+; returns a string of null character-separated preprocessing tokens
+; this corresponds to translation phases 1-3 in the C89 standard
+function split_into_preprocessing_tokens
+	argument filename
+	local fd
+	local file_contents
+	local pptokens
+	local p
+	local c
+	local in
+	local out
+	local n
+	
+	fd = open_r(filename)
+	file_contents = malloc(2000000)
+	pptokens = malloc(2000000)
+	p = file_contents
+	:pptokens_read_loop
+		n = syscall(0, fd, p, 4096)
+		if n == 0 goto pptokens_read_loop_end
+		p += n
+	:pptokens_read_loop_end
+	
+	; okay we read the file. first, delete every backslash-newline sequence (phase 2)
+	local newlines ; we add more newlines to keep line numbers right
+	newlines = 1
+	in = file_contents
+	out = file_contents
+	:backslashnewline_loop
+		c = *1in
+		if c == 0 goto backslashnewline_loop_end
+		if c == 10 goto proper_newline_loop
+		if c != '\ goto not_backslashnewline
+			p = in + 1
+			c = *1p
+			if c != 10 goto not_backslashnewline
+				in += 2 ; skip backlash and newline
+				newlines += 1 ; add one additional newline the next time around to compensate
+				goto backslashnewline_loop
+		:not_backslashnewline
+			*1out = *1in
+			out += 1
+			in += 1
+			goto backslashnewline_loop
+		:proper_newline_loop
+			if newlines == 0 goto proper_newline_loop_end
+			; output a newline
+			*1out = 10
+			out += 1
+			newlines -= 1
+			goto proper_newline_loop
+		:proper_newline_loop_end
+			newlines = 1
+			in += 1
+			goto backslashnewline_loop
+	:backslashnewline_loop_end
+	*1out = 0
+	
+	in = file_contents
+	
+	fputs(1, file_contents)
+	
+	free(file_contents)
+	close(fd)
+	return
+	
+	:unterminated_comment
+		fputs(2, .str_unterminated_comment)
+		fputs(2, filename)
+		fputc(2, 10)
+		exit(1)
+	:str_unterminated_comment
+		string Unterminated comment in file
+		byte 32
+		byte 0
diff --git a/05/util.b b/05/util.b
new file mode 100644
index 0000000..13fed4d
--- /dev/null
+++ b/05/util.b
@@ -0,0 +1,357 @@
+
+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
+	local a
+	p = mem
+	:memchr_loop
+		a = *1p
+		if a == c goto memchr_loop_end
+		p += 1
+		goto memchr_loop
+	:memchr_loop_end
+	return p
+
+function strlen
+	argument s
+	local c
+	local p
+	p = s
+	:strlen_loop
+		c = *1p
+		if c == 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
+	local p
+	p = &c
+	syscall(1, fd, p, 1)
+	return
+
+function putc
+	argument c
+	fputc(1, c)
+	return
+
+; returns 0 at end of file
+function fgetc
+	argument fd
+	local c
+	local p
+	c = 0
+	p = &c
+	syscall(0, fd, p, 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
+
+; open the given file for reading
+function open_r
+	argument filename
+	local fd
+	fd = syscall(2, filename, 0)
+	if fd < 0 goto open_r_error
+		return fd
+	:open_r_error
+		file_error(filename)
+		return -1
+
+; open the given file for writing with the given mode
+function open_w
+	argument filename
+	argument mode
+	local fd
+	fd = syscall(2, filename, 0x241, mode)
+	if fd < 0 goto open_w_error
+		return fd
+	:open_w_error
+		file_error(filename)
+		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