; SuBAsm
; The Sux Bootstrapped Assembler.
;
; by mr b0nk 500 <b0nk@b0nk.xyz>

MAX_SYM = $800		; Max symbol size.

.include "lexer.s"
.include "utils.s"

.org incl
; String Constants.
asm_name:
	.byte "SuBAsm"
asm_ver:
	.byte "0.1"

; Directives.
dir:
	.byte "org"
	.byte "byte"
	.byte "word"
	.byte "dword"
	.byte "qword"
	.byte "include"

; Short form Commands.
sh_cmds:
	.byte "vlahirs"

; Commands.
cmds:
	.byte "viewmem"
	.byte "list"
	.byte "asm"
	.byte "help"
	.byte "inst"
	.byte "run"
	.byte "set"

; Instruction mnemonics, and opcodes.

; Legend.
; mne = Mnemonic.
; imm = Immediate data.
; zm  = Zero Matrix.
; zmx = Zero Matrix, indexed with X.
; zmy = Zero Matrix, indexed with Y.
; ind = Indirect.
; idx = Indexed Indirect.
; idy = Indirect Indexed.
; abs = Absolute.
; imp = Implied.

mne:
;	       mne   imm,  zm, zmx, zmy, ind, idx, idy, abs, imp
	.byte "CPS", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $00
	.byte "ADC", $01, $06, $FF, $FF, $FF, $FF, $FF, $04, $FF
	.byte "AAB", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $02
	.byte "PHP", $08, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF
	.byte "CPB", $09, $2D, $FF, $FF, $55, $AD, $AC, $2C, $FF
	.byte "PHB", $0A, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF
	.byte "DEC", $FF, $0D, $FF, $FF, $FF, $FF, $FF, $0C, $E5
	.byte "JMP", $FF, $0E, $FF, $FF, $CE, $FF, $FF, $10, $FF
	.byte "SBC", $11, $16, $FF, $FF, $FF, $FF, $FF, $14, $FF
	.byte "SAB", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $12
	.byte "ENT", $18, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF
	.byte "CPY", $19, $3D, $FF, $FF, $85, $FF, $FF, $4C, $FF
	.byte "PLB", $1A, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF
	.byte "INC", $FF, $1D, $FF, $FF, $FF, $FF, $FF, $1C, $F5
	.byte "JSR", $FF, $1E, $FF, $FF, $BE, $FF, $FF, $20, $FF
	.byte "AND", $21, $26, $FF, $FF, $FF, $FF, $FF, $24, $FF
	.byte "ABA", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $22
	.byte "PLP", $28, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF
	.byte "CPX", $29, $4D, $FF, $FF, $B5, $FF, $FF, $3C, $FF
	.byte "PHY", $2A, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF
	.byte "BPO", $FF, $2E, $FF, $FF, $FF, $FF, $FF, $30, $FF
	.byte "ORA", $31, $36, $FF, $FF, $FF, $FF, $FF, $34, $FF
	.byte "OAB", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $32
	.byte "STT", $38, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF
	.byte "PLY", $3A, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF
	.byte "BNG", $FF, $3E, $FF, $FF, $FF, $FF, $FF, $40, $FF
	.byte "XOR", $41, $46, $FF, $FF, $FF, $FF, $FF, $44, $FF
	.byte "XAB", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $42
	.byte "PHA", $48, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF
	.byte "PHX", $4A, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF
	.byte "BCS", $FF, $4E, $FF, $FF, $FF, $FF, $FF, $50, $FF
	.byte "LSL", $51, $56, $FF, $FF, $FF, $FF, $FF, $54, $FF
	.byte "LLB", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $52
	.byte "CLC", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $58
	.byte "PLX", $5A, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF
	.byte "BCC", $FF, $5E, $FF, $FF, $FF, $FF, $FF, $60, $FF
	.byte "LSR", $61, $66, $FF, $FF, $FF, $FF, $FF, $64, $FF
	.byte "LRB", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $62
	.byte "PLA", $68, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF
	.byte "TAB", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $6A
	.byte "BEQ", $FF, $6E, $FF, $FF, $FF, $FF, $FF, $70, $FF
	.byte "ROL", $71, $76, $FF, $FF, $FF, $FF, $FF, $74, $FF
	.byte "RLB", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $72
	.byte "SEC", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $78
	.byte "TBA", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $7A
	.byte "BNE", $FF, $7E, $FF, $FF, $FF, $FF, $FF, $80, $FF
	.byte "ROR", $81, $86, $FF, $FF, $FF, $FF, $FF, $84, $FF
	.byte "RRB", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $82
	.byte "DEY", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $88
	.byte "TAY", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $8A
	.byte "BVS", $FF, $8E, $FF, $FF, $FF, $FF, $FF, $90, $FF
	.byte "MUL", $91, $96, $FF, $FF, $FF, $FF, $FF, $94, $FF
	.byte "MAB", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $92
	.byte "CLI", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $98
	.byte "TYA", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $9A
	.byte "BVC", $FF, $9E, $FF, $FF, $FF, $FF, $FF, $A0, $FF
	.byte "DIV", $A1, $A6, $FF, $FF, $FF, $FF, $FF, $A4, $FF
	.byte "DAB", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $A2
	.byte "INY", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $A8
	.byte "TAX", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $AA
	.byte "RTS", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $AE
	.byte "CMP", $B1, $B6, $FF, $FF, $25, $7D, $7C, $B4, $FF
	.byte "CAB", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $B2
	.byte "SEI", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $B8
	.byte "LDX", $B9, $BD, $FF, $C9, $95, $FF, $FF, $BC, $FF
	.byte "TXA", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $BA
	.byte "RTI", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $C0
	.byte "LDA", $C1, $C6, $79, $39, $05, $5D, $5C, $C4, $FF
	.byte "DEX", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $C5
	.byte "CLV", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $C8
	.byte "TYX", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $CA
	.byte "STA", $FF, $CD, $89, $49, $15, $6D, $6C, $CC, $FF
	.byte "TSX", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $D0
	.byte "LDB", $D1, $D6, $99, $59, $35, $8D, $8C, $D4, $FF
	.byte "INX", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $D5
	.byte "WAI", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $D8
	.byte "TXY", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $DA
	.byte "STB", $FF, $DD, $A9, $69, $45, $9D, $9C, $DC, $FF
	.byte "TXS", $E0, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF
	.byte "LDY", $E1, $E6, $E9, $FF, $65, $FF, $FF, $E4, $FF
	.byte "BRK", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $E8
	.byte "NOP", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $EA
	.byte "STY", $FF, $ED, $F9, $FF, $75, $FF, $FF, $EC, $FF
	.byte "DEB", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $EE
	.byte "ASR", $F1, $F6, $FF, $FF, $FF, $FF, $FF, $F4, $FF
	.byte "ARB", $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $F2
	.byte "STX", $FF, $FD, $FF, $D9, $A5, $FF, $FF, $FC, $FF
	.byte "INB"  $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FF, $FE

; Command subroutine table.
cmd_srt:
	.word viewmem
	.word list
	.word asm
	.word help
	.word inst
	.word run
	.word set

; Data entry point for the lexer.
lexer_data:


; Token table.
.org $20000
tokline:

.org cmd_buf+$400
; Program Counter.
prg_cnt:
	.qword 0
; Hex digit string buffer.
hex_str:
	.qword 0, 0
; String buffer.
strbuf:

.org strbuf+$80
; Subroutine pointer.
sub_ptr:
	.word 0

; Indecies.
idx0:
	.qword 0
idx1:
	.qword 0
idx2:
	.qword 0
idx3:
	.qword 0

; Current token line.
ctok:
	.word 0

; Last token line.
ltok:
	.word 0

; Lexeme string.
lexeme:

; Symbol table.
.org lexeme+$100
sym:

; Fixup table.
; Fixups are unresolved symbols.
.org sym+$8000
fix:


; Start of program code.
.org parser
subasm:
	ldb #0		; Set the first pointer
	lda.d #cmd_buf	; to the command buffer.
	jsr set_ptr	;
	tba		; Reset A.
	tax		; Reset X.
	jsr chk_shcmd	; Did we get a shortend command?
	bne @cmd	; Yes, so skip everything else.
	jsr chk_cmd	; No, but did we get a full command?
	bne @cmd	; Yes, so skip everything else.
	jsr lex		; No, so start lexing this line.
	jmp @end	; We are done.
@cmd:
	ldb #1		; Set the second pointer
	lda.d #cmd_srt	; to the command subroutine table.
	jsr set_ptr	;
	deb		; Reset B.
	tba		; Reset A.
	lda f		; Get the command ID.
	cmp #8		; Is the command ID greater than the command count?
	bcs @end	; Yes, so we're done.
	lsl #1		; No, so multiply the command ID by two.
	phy #2		; Preserve the screen buffer position.
	tay		; Set the index to the offset that we just calculated.
	lda.w (ptr2), y	; Get the command subroutine, from the command subroutine table.
	ply #2		; Get back the screen buffer position.
	ldb #2		; Save it in the third pointer.
	jsr set_ptr	;
	ldb #0		; Reset B.
	jsr (ptr3)	; Run the command's subroutine.
@end:
	rts		; End of subasm.

chk_shcmd:
	tba		; Reset A.
	inb		; Set the second pointer
	lda.w #sh_cmds	; to the shortend command table.
	jsr set_ptr	;
	deb		; Reset B.
	tba		; Reset A.
	phy #2		; Preserve the screen buffer position.
	txy		; Set our index to zero.
	lda (ptr), y	; Is there nothing in the command buffer?
	beq @false	; Yes, so return that we failed.
	cmp #' '	; No, but is this character, a space?
	beq @false	; Yes, so return that we failed.
	jsr tolower	; No, so convert it to lowercase.
@loop:
	ldb (ptr2), y	; Are we at the end of the table?
	beq @false	; Yes, so return that we failed.
	cab		; No, so did the character match?
	beq @found	; Yes, so check if there are any arguments.
	iny		; No, so check the next command.
	jmp @loop	; Keep looping.
@found:
	sty f		; Save the command ID.
	ldy #1		; Check the next character in the command buffer.
	lda (ptr), y	; Is this the end of the buffer?
	beq @true	; Yes, so return that we succeded.
	cmp #' '	; No, but is this a space?
	beq @true	; Yes, so return that we succeded.
	jmp @false	; No, so return that we failed.
@true:
	lda #1		; Return true.
	jmp @end	; We are done.
@false:
	ldb #0		; Reset B.
	tba		; Return false.
	tax		; Reset X.
@end:
	ply #2		; Get back the screen buffer position.
	rts		; End of chk_shcmd.


chk_cmd:
	tba		; Reset A.
	tax		; Reset X.
	sta.q idx0	; Reset the first index.
	sta.q idx1	; Reset the second index.
@loop:
	lda.w #cmds	; Get pointer to the start of the command table.
	clc		; Prepare for a non carrying add.
	adc.w idx0	; Offset the pointer, by the length of the previous string.
	pha #8		; Preserve the command string pointer.
	jsr strcasecmp	; Is the command buffer, the same as the command string?
	pla #8		; Get the command string pointer back.
	beq @true	; Yes, so return true.
	ldb idx1	; No, so Get the command ID.
	cpb #7		; Have we reached the end of the command table?
	beq @false	; Yes, so return false.
	inc idx1	; No, so increment the command ID.
@getlen:
	jsr strlen	; Get the string's length.
	inx		; Add one to the length.
	txa		; Place it in the accumulator.
	clc		; Prepare for a non carrying add.
	adc.w idx0	; Add the string offset to the current length
	sta.w idx0	; Save the offset in the first index.
	jmp @loop	; Keep looping.
@true:
	ldb idx1	; Get the command ID.
	stb f		; Return the command ID.
	ldb #1		; Return true.
	jmp @end	; We are done.
@false:
	ldb #0		; Return false.
@end:
	rts		; End of chk_cmd.

viewmem:
	lda.q prg_cnt	; Get the program counter.
	sta.q idx0	; Save the address in the first index.
	and #$F0	; Clear the first four bits of the address.
	sta idx0	; Overwrite the first byte, with the masked byte.
	lda #19		; Move the cursor to the right, by 19 columns.
	sta scr_col	;
	jsr update_pos	;
	jsr print_lo	; Print the low nibble offsets.
	ldx #0		; Reset X.
	ldb #0		; Reset B.
	stb idx1	; Reset the byte count.
@loop:
	lda #'\n'	; Print a newline.
	jsr print_char	;
	jsr print_hi	; Place the address in the string buffer.
	jsr print_chunk	; Place the next 16 bytes in the string buffer.
	lda.d #strbuf	; Print the string buffer.
	jsr print_str	;
	inc idx1	; Increment the chunk count.
	ldb idx1	; Get the chunk count.
	cpb #$10	; Did we print 16 chunks?
	beq @end	; Yes, so we're done.
	lda.q idx0	; No, so get the address index.
	clc		; Prepare for a non carrying add.
	adc #$10	; Add 16 to the address.
	sta.q idx0	; Put it back into the address.
	and #0		; Reset A.
	jmp @loop	; Keep looping.
@end:
	lda #'\n'	; Print a newline.
	jsr print_char	;
	and #0		; Reset A.
	rts		; End of viewmem.


list:
	nop		;
@end:
	rts		; End of list.
asm:
	nop		;
@end:
	rts		; End of asm.
help:
	nop		;
@end:
	rts		; End of help.
inst:
	nop		;
@end:
	rts		; End of inst.
run:
	nop		;
@end:
	rts		; End of run.
set:
	nop		;
@end:
	rts		; End of set.

; Entry point for utility subroutines.
lexer: