URL
https://opencores.org/ocsvn/zipcpu/zipcpu/trunk
Subversion Repositories zipcpu
[/] [zipcpu/] [trunk/] [sw/] [zasm/] [zasm.l] - Rev 126
Compare with Previous | Blame | View Log
/*******************************************************************************
**
** Filename: zasm.l
**
** Project: Zip CPU -- a small, lightweight, RISC CPU core
**
** Purpose: The lexical analyzer for the assembler. This converts assembler
** input into tokens, to feed the parser.
**
**
** Creator: Dan Gisselquist, Ph.D.
** Gisselquist Technology, LLC
**
********************************************************************************
**
** Copyright (C) 2015, Gisselquist Technology, LLC
**
** This program is free software (firmware): you can redistribute it and/or
** modify it under the terms of the GNU General Public License as published
** by the Free Software Foundation, either version 3 of the License, or (at
** your option) any later version.
**
** This program is distributed in the hope that it will be useful, but WITHOUT
** ANY WARRANTY; without even the implied warranty of MERCHANTIBILITY or
** FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
** for more details.
**
** You should have received a copy of the GNU General Public License along
** with this program. (It's in the $(ROOT)/doc directory, run make with no
** target there if the PDF file isn't present.) If not, see
** <http://www.gnu.org/licenses/> for a copy.
**
** License: GPL, v3, as defined and found on www.gnu.org,
** http://www.gnu.org/licenses/gpl.html
**
**
*******************************************************************************/
%{
#include <stdio.h>
#include "asmdata.h"
#include "zasm.tab.h"
extern "C" int yylex();
extern "C" int yywrap() { return 1;}
extern char *master_input_filename;
extern int decode_char_int(const char *str);
%}
%option yylineno
%option warn
%%
"#line"[ \t]+[0-9]+[ \t]+[\"][^"]*[\"][ \t]*$ {
/* This should really be true *only* at the beginning of a line,
* however such line beginnings aren't matching. My guess is that
* the reason is my line copying code at the bottom that sucks up the
* newline for LEX. Hence, this is what we have.
*/
yylineno = atoi(&yytext[6]);
char *bg, *en;
bg = strchr(yytext, '\"')+1;
en = strchr(bg, '\"'); *en = '\0';
if ((master_input_filename == NULL)||(strcmp(master_input_filename, bg)!=0)) {
if (!master_input_filename) delete[] master_input_filename;
master_input_filename = new char[en-bg+2];
strcpy(master_input_filename, bg);
}
return '\n';
}
"#line"[ \t]+[0-9]+[ \t]*$ { yylineno = atoi(&yytext[6]); return '\n';}
^"#line".*$ { printf("WARNING: Unmatched #line: %s\n", yytext); return '\n'; }
"#line".*$ { printf("WARNING: Unmatched #line, not at beginnning: %s\n", yytext); return '\n'; }
(?i:ur)1[0-5] { yylval.u_reg=(ZPARSER::ZIPREG)(26+yytext[3]-'0');return REG; }
(?i:sr)1[0-5] { yylval.u_reg=(ZPARSER::ZIPREG)(10+yytext[3]-'0');return REG; }
[rR]1[0-5] { yylval.u_reg=(ZPARSER::ZIPREG)(10+yytext[2]-'0');return REG; }
(?i:ur)[0-9] { yylval.u_reg=(ZPARSER::ZIPREG)(16+yytext[2]-'0');return REG; }
(?i:sr)[0-9] { yylval.u_reg=(ZPARSER::ZIPREG)( yytext[2]-'0');return REG; }
[rR][0-9] { yylval.u_reg=(ZPARSER::ZIPREG)( yytext[1]-'0');return REG; }
(?i:upc) { yylval.u_reg = ZPARSER::ZIP_uPC; return REG; }
(?i:spc) { yylval.u_reg = ZPARSER::ZIP_PC; return REG; }
(?i:pc) { yylval.u_reg = ZPARSER::ZIP_PC; return REG; }
(?i:ucc) { yylval.u_reg = ZPARSER::ZIP_uCC; return REG; }
(?i:scc) { yylval.u_reg = ZPARSER::ZIP_CC; return REG; }
(?i:cc) { yylval.u_reg = ZPARSER::ZIP_CC; return REG; }
(?i:usp) { yylval.u_reg = ZPARSER::ZIP_uSP; return REG; }
(?i:ssp) { yylval.u_reg = ZPARSER::ZIP_SP; return REG; }
(?i:sp) { yylval.u_reg = ZPARSER::ZIP_SP; return REG; }
(?i:gbl) { yylval.u_reg = ZPARSER::ZIP_R12; return REG; }
(?i:bra) { yylval.u_op = OP_BRA; return BRANCHOP; }
(?i:brz) { yylval.u_op = OP_BZ; return BRANCHOP; }
(?i:bz) { yylval.u_op = OP_BZ; return BRANCHOP; }
(?i:bnz) { yylval.u_op = OP_BNZ; return BRANCHOP; }
(?i:bne) { yylval.u_op = OP_BNZ; return BRANCHOP; }
(?i:bge) { yylval.u_op = OP_BGE; return BRANCHOP; }
(?i:bgt) { yylval.u_op = OP_BGT; return BRANCHOP; }
(?i:bg) { yylval.u_op = OP_BGT; return BRANCHOP; }
(?i:blt) { yylval.u_op = OP_BLT; return BRANCHOP; }
(?i:bn) { yylval.u_op = OP_BLT; return BRANCHOP; }
(?i:brc) { yylval.u_op = OP_BRC; return BRANCHOP; }
(?i:bc) { yylval.u_op = OP_BRC; return BRANCHOP; }
(?i:brv) { yylval.u_op = OP_BRV; return BRANCHOP; }
(?i:bv) { yylval.u_op = OP_BRV; return BRANCHOP; }
(?i:clr) { yylval.u_op = OP_CLR; return SINGLOP; }
(?i:clrf) { yylval.u_op = OP_CLRF;return SINGLOP; }
(?i:int) { yylval.u_op = OP_TRAP;return SINGLOP; }
(?i:trap) { yylval.u_op = OP_TRAP;return SINGLOP; }
(?i:jmp) { yylval.u_op = OP_JMP; return SINGLOP; }
(?i:neg) { yylval.u_op = OP_NEG; return SINGLOP; }
(?i:not) { yylval.u_op = OP_NOT; return SINGLOP; }
(?i:cmp) { yylval.u_op = OP_CMP; return DUALOP; }
(?i:tst) { yylval.u_op = OP_TST; return DUALOP; }
(?i:mov) { yylval.u_op = OP_MOV; return DUALOP; }
(?i:ldi) { yylval.u_op = OP_LDI; return LDIOP; }
(?i:ldihi) { yylval.u_op =OP_LDIHI; return LDHLOP; }
(?i:lhi) { yylval.u_op =OP_LDIHI; return LDHLOP; }
(?i:ldilo) { yylval.u_op =OP_LDILO; return LDHLOP; }
(?i:llo) { yylval.u_op =OP_LDILO; return LDHLOP; }
(?i:mpyu) { yylval.u_op = OP_MPYU; return DUALOP; }
(?i:mpys) { yylval.u_op = OP_MPYS; return DUALOP; }
(?i:rol) { yylval.u_op = OP_ROL; return DUALOP; }
(?i:sub) { yylval.u_op = OP_SUB; return DUALOP; }
(?i:and) { yylval.u_op = OP_AND; return DUALOP; }
(?i:add) { yylval.u_op = OP_ADD; return DUALOP; }
(?i:or) { yylval.u_op = OP_OR; return DUALOP;; }
(?i:xor) { yylval.u_op = OP_XOR; return DUALOP; }
(?i:lsl) { yylval.u_op = OP_LSL; return DUALOP; }
(?i:asr) { yylval.u_op = OP_ASR; return DUALOP; }
(?i:lsr) { yylval.u_op = OP_LSR; return DUALOP; }
(?i:ljmp) { yylval.u_op = OP_LJMP; return BAREOP; }
(?i:lod) { yylval.u_op = OP_LOD; return LOADOP; }
(?i:sto) { yylval.u_op = OP_STO; return STOROP; }
(?i:halt) { yylval.u_op = OP_HALT; return BAREOP; }
(?i:wait) { yylval.u_op = OP_HALT; return BAREOP; }
(?i:rtu) { yylval.u_op = OP_RTU; return BAREOP; }
(?i:retn) { yylval.u_op = OP_RETN; return BAREOP; }
(?i:ret) { yylval.u_op = OP_RETN; return BAREOP; }
(?i:nop) { yylval.u_op = OP_NOOP; return BAREOP; }
(?i:noop) { yylval.u_op = OP_NOOP; return BAREOP; }
(?i:break) { yylval.u_op = OP_BREAK; return BAREOP; }
(?i:brk) { yylval.u_op = OP_BREAK; return BAREOP; }
(?i:busy) { yylval.u_op = OP_BUSY; return BAREOP; }
(?i:brev) { yylval.u_op = OP_BREV; return DUALOP; }
(?i:popc) { yylval.u_op = OP_POPC; return DUALOP; }
(?i:divu) { yylval.u_op = OP_DIVU; return DUALOP; }
(?i:divs) { yylval.u_op = OP_DIVS; return DUALOP; }
(?i:fpadd) { yylval.u_op = OP_FPADD; return DUALOP; }
(?i:fpsub) { yylval.u_op = OP_FPSUB; return DUALOP; }
(?i:fpmul) { yylval.u_op = OP_FPMUL; return DUALOP; }
(?i:fpdiv) { yylval.u_op = OP_FPDIV; return DUALOP; }
(?i:fpcvt) { yylval.u_op = OP_FPCVT; return DUALOP; }
(?i:fpint) { yylval.u_op = OP_FPINT; return DUALOP; }
(?i:mpyshi) { yylval.u_op = OP_MPYSHI; return DUALOP; }
(?i:mpyuhu) { yylval.u_op = OP_MPYUHI; return DUALOP; }
(?i:mpy) { yylval.u_op = OP_MPY; return DUALOP; }
(?i:equ) { return EQU; }
(?i:fill) { return FILL; }
(?i:word) { return WORD; }
"__"[hH][eE][rR][eE]"__" { return HERE; }
[\.][dD][aA][tT] { return WORD; }
[\.](?i:z)/[ \t\n] { yylval.u_cond = ZPARSER::ZIPC_Z; return COND; }
[\.](?i:ne)/[ \t\n] { yylval.u_cond = ZPARSER::ZIPC_NZ; return COND; }
[\.](?i:nz)/[ \t\n] { yylval.u_cond = ZPARSER::ZIPC_NZ; return COND; }
[\.](?i:ge)/[ \t\n] { yylval.u_cond = ZPARSER::ZIPC_GE; return COND; }
[\.](?i:gt)/[ \t\n] { yylval.u_cond = ZPARSER::ZIPC_GT; return COND; }
[\.](?i:lt)/[ \t\n] { yylval.u_cond = ZPARSER::ZIPC_LT; return COND; }
[\.](?i:n)/[ \t\n] { yylval.u_cond = ZPARSER::ZIPC_LT; return COND; }
[\.](?i:c)/[ \t\n] { yylval.u_cond = ZPARSER::ZIPC_C; return COND; }
[\.](?i:v)/[ \t\n] { yylval.u_cond = ZPARSER::ZIPC_V; return COND; }
[_A-Za-z][_a-zA-Z0-9]* { yylval.u_id = strdup(yytext); return IDENTIFIER; }
"$"?[-]?0[xX][0-9A-Fa-f]+ { yylval.u_ival = strtoul(yytext+(((*yytext)=='$')?1:0),NULL,16);return INT;}
"$"?[-]?0[0-7]+ { yylval.u_ival = strtoul(yytext+(((*yytext)=='$')?1:0),NULL, 8);return INT;}
"$"?[-]?[1-9][0-9]* { yylval.u_ival = strtoul(yytext+(((*yytext)=='$')?1:0),NULL,10);return INT;}
"$"?[-]?[1-9A-Fa-f][0-9A-Fa-f]*h {yylval.u_ival=strtoul(yytext+(((*yytext)=='$')?1:0),NULL,16); return INT;}
"$"?[-]?[0-7]+o { yylval.u_ival = strtoul(yytext+(((*yytext)=='$')?1:0),NULL, 8);return INT;}
"\'"(("\\\'")|([^'\\])|("\\"[0abfnrtv])|("\\\\")|("\\\"")){1,4}"\'" {
yylval.u_ival = decode_char_int(&yytext[1]); return INT; }
"$"?"0" { yylval.u_ival = 0;return INT;}
"$" { return DOLLAR; }
"," { return COMMA; }
"+" { return PLUS; }
"-" { return MINUS; }
"*" { return TIMES; }
"||" { return BOOLEANOR; }
"|" { return BITWISEOR; }
"&&" { return BOOLEANAND; }
"&" { return BITWISEAND; }
"^" { return BITWISEXOR; }
":" { return COLON; }
"." { return DOT; }
"%" { return '%'; }
[ \t]+ { }
[(] { return '('; }
[)] { return ')'; }
\n.* { if (linecp) free(linecp); linecp = strdup(&yytext[1]); yyless(1); return '\n'; }
%%
int decode_char_int(const char *str) {
unsigned r = 0;
// fprintf(stderr, "Decoding character string: \'%s\n", str);
while((*str)&&('\'' != (*str))) {
if ('\\' == (*str)) {
// Process escape characters
str++;
if ('\0' != (*str)) {
r<<=8;
switch(*str) {
case '0': break;
case 'a': r |= '\a'; break;
case 'b': r |= '\b'; break;
case 'n': r |= '\n'; break;
case 'f': r |= '\f'; break;
case 'r': r |= '\r'; break;
case 't': r |= '\t'; break;
case 'v': r |= '\v'; break;
case '\'': r |= '\''; break;
case '\"': r |= '\"'; break;
case '\\': r |= '\\'; break;
} str++;
}
} else {
r = (r<<8)|(*str);
str++;
}
} return r;
}