summaryrefslogtreecommitdiff
path: root/lexer/backup/lexer.c
diff options
context:
space:
mode:
authormrb0nk500 <b0nk@b0nk.xyz>2020-12-04 15:20:28 -0500
committermrb0nk500 <b0nk@b0nk.xyz>2020-12-04 15:20:28 -0500
commit96393257a43ac52f2b911594d106741245dec5f0 (patch)
tree6b9d11c50ed3cd1920444c4dd0ee4027814ef4bd /lexer/backup/lexer.c
parent83ce1151ee1f06ae6b1c5c1018cc2489494e5ea4 (diff)
- Started work on writing the new version of the
assembler. - Did alot of stuff in the emulator. - Did alot of stuff in the SuB Suite.
Diffstat (limited to 'lexer/backup/lexer.c')
-rw-r--r--lexer/backup/lexer.c937
1 files changed, 937 insertions, 0 deletions
diff --git a/lexer/backup/lexer.c b/lexer/backup/lexer.c
new file mode 100644
index 0000000..1654f44
--- /dev/null
+++ b/lexer/backup/lexer.c
@@ -0,0 +1,937 @@
+#include "asmmon.h"
+#include "lexer.h"
+
+uint8_t lex_type;
+uint16_t sym_count = 0;
+token *tokens = NULL;
+token *last_tok = NULL;
+symbol *locals = NULL;
+symbol *last_loc = NULL;
+symbol *cur_sym = NULL;
+symbol *struct_sym = NULL;
+
+line *tmp_line = NULL;
+
+symbol *mksymbol(const char *name, uint64_t val, uint8_t def, uint8_t islocal, uint8_t useid, uint16_t id, uint8_t dbg) {
+ uint16_t i = 0;
+ symbol *s = (!islocal) ? symbols : locals;
+ uint8_t flag = 0;
+ for (; s; s = s->next, i++) {
+ if (!useid && name[0] != s->name[0]) {
+ continue;
+ }
+ flag = (useid) ? (id == s->id) : !strcmp(name, s->name);
+ if (flag) {
+ if (def) {
+ if (s->def) {
+ if (dbg) {
+ printf("mksymbol(): oof, you cannot redefine the symbol: %s\n", name);
+ }
+ defined = 1;
+ } else {
+ defined = 0;
+ }
+ s->def = def;
+ s->val = val;
+ s->id = i;
+ if (dbg) {
+ printf("mksymbol(): def: %u, val: $%016"PRIX64", name: %s\n", def, val, name);
+ printf("mksymbol(): i: $%X, id: $%04X\n", i, s->id);
+ }
+ }
+ return s;
+ }
+ }
+ size_t str_size = strlen(name)+1;
+ s = malloc(sizeof(symbol));
+ s->down = NULL;
+ if (!islocal) {
+ (last_sym) ? (last_sym->next = s) : (symbols = s);
+ if (last_sym) {
+ last_sym->next->prev = last_sym;
+ last_sym->next->up = last_sym->up;
+ last_sym->next->down = NULL;
+ } else {
+ symbols->prev = NULL;
+ symbols->up = NULL;
+ symbols->down = NULL;
+ }
+ } else {
+ (last_loc) ? (last_loc->next = s) : (locals = s);
+ if (last_loc) {
+ last_loc->next->prev = last_loc;
+ last_loc->next->up = last_loc->up;
+ last_loc->next->down = NULL;
+ } else {
+ locals->prev = NULL;
+ locals->down = NULL;
+ }
+ }
+ s->name = malloc(str_size);
+ s->def = def;
+ s->val = val;
+ s->count = 0;
+ s->isstruct = 0;
+ memcpy(s->name, name, str_size);
+ s->next = NULL;
+ s->id = sym_count++;
+ (!islocal) ? (last_sym = s) : (last_loc = s);
+ if (!islocal) {
+ s->down = NULL;
+ /*if (def) {
+ locals = NULL;
+ last_loc = NULL;
+ }*/
+ } else {
+ cur_sym->count++;
+ }
+ defined = 0;
+ if (dbg) {
+ printf("mksymbol(): def: %u, val: $%016"PRIX64", name: %s, id: $%04X\n", def, val, name, sym_count-1);
+ }
+ return s;
+}
+
+uint16_t fixup_cnt = 0;
+symbol *get_sym(const char *name, uint64_t val, token *t, uint8_t islocal, uint8_t dbg) {
+ symbol *s = mksymbol(name, 0, 0, islocal, 0, 0, dbg);
+ if (dbg) {
+ printf("get_sym(): Symbol ID: $%X.\n", s->id);
+ }
+ if (s->def) {
+ return s;
+ } else {
+ if (dbg) {
+ printf("get_sym(): oof, symbol %s, does not exist, yet.\n", name);
+ }
+ fixup *f = malloc(sizeof(fixup));
+ (last_fix) ? (last_fix->next = f) : (fixups = f);
+ f->adr = val;
+ f->t = t;
+ f->s = s;
+ f->next = NULL;
+ last_fix = f;
+ fixup_cnt++;
+ return NULL;
+ }
+}
+
+symbol *find_member(char *name, symbol* root, uint8_t dbg) {
+ /*for (; root->up; root = root->up);*/
+ symbol *s = root;
+ if (s->down == NULL && s->up != NULL) {
+ s = s->up;
+ }
+ do {
+ s = s->down;
+ for (symbol *m = s; m; m = m->next) {
+ size_t len1 = strlen(name);
+ size_t len2 = strlen(m->name);
+ if (len1 == len2 && name[0] == m->name[0] && !strcmp(name, m->name)) {
+ return m;
+ }
+ }
+ for (; s->next && !s->down; s = s->next);
+ } while (s->down);
+ return NULL;
+}
+
+uint16_t reslv_fixups(uint8_t dbg) {
+ fixup *f = fixups;
+ symbol *ls;
+ uint16_t i = 0, j = 0;
+ for (; f; f = f->next) {
+ if (f->s->def) {
+ if (dbg) {
+ printf("reslv_fixups(): Symbol ID: $%X, Symbol Name: %s, Symbol Value: $%"PRIX64".\n", f->s->id, f->s->name, f->s->val);
+ }
+ f->t->sym = f->s;
+ } else {
+ if (dbg) {
+ printf("reslv_fixups(): oof, undefined reference to '%s', at $%016"PRIX64".\n", f->s->name, f->adr);
+ }
+ i++;
+ }
+ }
+ return i;
+
+}
+
+uint16_t get_comment(const char *com, uint8_t dbg) {
+ uint16_t i = 0;
+ for (; comment[i] && i < comidx; i++) {
+ if (com[0] == comment[i][0] && !strcmp(com, comment[i])) {
+ break;
+ }
+ }
+ if (comment[i] == NULL) {
+ if (dbg) {
+ printf("get_comment(): oof, the index $%04X is NULL.\n", i);
+ printf("get_comment(): oof, the comment \"%s\", was not found in the comment table.\n", com);
+ }
+ size_t size = strlen(com)+1;
+ comment[comidx] = malloc(size);
+ memcpy(comment[comidx], com, size);
+ return comidx++;
+
+ }
+ if (dbg) {
+ if (strcmp(com, comment[i])) {
+ printf("get_comment(): oof, the comment \"%s\" is somehow not in the comment table, even though it should be at index $%04X.\n", com, i);
+ }
+ printf("get_comment(): The return value of strcmp(com, comment[$%04X]) is %i.\n", i, strcmp(com, comment[i]));
+ printf("get_comment(): Found comment \"%s\", in the table, at index $%04X.\n", com, i);
+ }
+ return i;
+}
+
+uint16_t get_string(const char *str, uint8_t dbg) {
+ uint16_t i = 0;
+ uint8_t isstr = 0;
+ for (; i < stridx; i++) {
+ if (isstr || string[i] == NULL) {
+ break;
+ } else if (str[0] == string[i][0]) {
+ isstr = !strcmp(str, string[i]);
+ }
+ }
+ if (string[i] == NULL || i == stridx) {
+ if (dbg) {
+ printf("get_string(): oof, the index $%04X is NULL.\n", i);
+ printf("get_string(): oof, the string \"%s\", was not found in the string table.\n", str);
+ }
+ return 0xFFFF;
+ }
+ if (dbg) {
+ printf("get_string(): Found string \"%s\", in the table, at index $%04X.\n", str, i);
+ }
+ return i;
+}
+
+line *find_line(uint32_t ln, uint8_t dbg) {
+ uint32_t i = 0;
+ line *l = lines;
+ for (; l && l->linenum != ln; l = l->next);
+ if (l != NULL) {
+ if (l->linenum == ln) {
+ if (dbg) {
+ printf("find_line(): Found line number %u.\n", ln);
+ }
+ return l;
+ }
+ } else {
+ if (dbg) {
+ printf("find_line(): oof, could not find line number %u.\n", ln);
+ }
+ return NULL;
+ }
+ return l;
+}
+
+int is_struct = 0;
+int is_anon = 0;
+
+void create_struct(symbol *c_sym, line *l, token *t, token *lt, char *name, uint8_t dbg) {
+ uint8_t ismember = !(is_struct == 1 && lt && lt->id == TOK_DIR);
+ mksymbol(name, 0, 1, ismember, 0, 0, dbg);
+ if (isfixup) {
+ isfixup = reslv_fixups(dbg);
+ }
+ t->sym = get_sym(name, 0, t, ismember, dbg);
+ if (lt && lt->id == TOK_DIR) {
+ t->sym->isstruct = 1;
+ t->id = (lt->type == DIR_STRUCT) ? TOK_STRUCT : TOK_UNION;
+ tmp_line = l;
+ } else {
+ t->id = TOK_MEMBER;
+ t->sym->isanon = (is_anon > 0);
+ }
+ isfixup += (t->sym == NULL);
+ int is_top = (c_sym == NULL);
+ c_sym = (!ismember && !c_sym) ? last_sym : c_sym;
+ if (!ismember) {
+ if (!is_top) {
+ c_sym = t->sym;
+ locals = NULL;
+ last_loc = NULL;
+ } else {
+ c_sym->down = locals;
+ }
+ } else {
+ if (lt && lt->id == TOK_DIR) {
+ if (lt->type == DIR_UNION || lt->type == DIR_STRUCT) {
+ c_sym->down = locals;
+ c_sym->down->up = c_sym;
+ last_loc->up = c_sym;
+ c_sym = last_loc;
+ locals = NULL;
+ last_loc = NULL;
+ }
+ }
+ }
+ cur_sym = c_sym;
+}
+
+void end_struct(symbol *c_sym, symbol *s_sym, uint8_t dbg) {
+ int skip = 0;
+ if (is_anon > 0) {
+ if ((c_sym && c_sym->isanon) || (c_sym->up && !c_sym->up->isanon) || (c_sym && s_sym->isanon)) {
+ is_anon--;
+ } else if (is_struct <= 0) {
+ is_anon = 0;
+ }
+ skip = (!is_anon);
+ }
+ if (((is_struct-is_anon) > 0 && !skip) || (is_anon <= 0 && is_struct <= 0)) {
+ symbol *s;
+ for (s = locals; s; s = s->next) {
+ if (s->up == NULL) {
+ s->up = c_sym;
+ }
+ if (dbg) {
+ printf("s: %p, s->up: %p, c_sym: %p, last_loc: %p\n", s, s->up, c_sym, last_loc);
+ }
+ }
+ if (c_sym->down == NULL) {
+ c_sym->down = locals;
+ }
+ }
+ if ((is_anon <= 0 || is_struct <= 0)) {
+ for (s_sym = c_sym; s_sym->prev && !s_sym->isanon; s_sym = s_sym->prev);
+ struct_sym = s_sym;
+ }
+ if ((is_struct-is_anon) > 0 && !skip) {
+ symbol *s = c_sym;
+ for (; s->prev; s = s->prev) {
+ if (s->up == NULL && c_sym->up) {
+ s->up = c_sym->up;
+ }
+ if (dbg) {
+ printf("s: %p, s->up: %p, c_sym->up: %p, last_loc: %p\n", s, s->up, c_sym->up, last_loc);
+ }
+ }
+ if (c_sym->up) {
+ cur_sym = c_sym->up;
+ }
+ for (locals = locals->up; locals->prev; locals = locals->prev);
+ for (last_loc = locals; last_loc->next; last_loc = last_loc->next);
+ }
+}
+
+uint64_t lex(char *str, uint64_t address, uint16_t bline, uint8_t dbg) {
+ char sym[0x100];
+ uint16_t i = 0;
+ uint16_t j = 0;
+ uint16_t comid = 0;
+ uint16_t strid = 0;
+ uint16_t symid = 0;
+ uint64_t value = 0;
+ lex_type = 0xFF;
+
+ uint8_t k = 0;
+ uint8_t k2 = 0;
+ union reg ch;
+ ch.u64 = 0;
+ uint8_t rs = 0;
+ uint8_t of = 0;
+ uint8_t base = 0;
+
+ uint8_t islocal = 0;
+
+ uint8_t isop = 0;
+ int num = 0;
+ int isch = 0;
+ uint8_t isesc = 0;
+ uint8_t islinenum;
+
+ int16_t ln = -1;
+
+ char lnum[6];
+
+ uint8_t space = 0;
+ uint8_t tab = 0;
+ uint8_t fall = 0;
+ uint8_t done = 0;
+
+
+ /*uint8_t is_newcom = 0;*/
+ line *l = NULL;
+ token *st = NULL;
+ token *t = NULL;
+ token *lt = NULL;
+ symbol *tmp_sym = NULL;
+ symbol *tsym = NULL;
+
+ while (isdigit(str[i]) && isdelm(str[i], dbg) != 16) {
+ lnum[j++] = str[i++];
+ }
+ islinenum = i;
+ if (i) {
+ lnum[j] = '\0';
+ ln = strtol(lnum, NULL, 10);
+ j = 0;
+ l = find_line(ln, dbg);
+ } else {
+ ln = linenum;
+ l = NULL;
+ }
+ if (l) {
+ address = l->addr;
+ } else {
+ l = malloc(sizeof(line));
+ (last_line) ? (last_line->next = l) : (lines = l);
+ l->tok = NULL;
+ l->next = NULL;
+ l->count = 0;
+ l->bline = bline;
+ last_line = l;
+
+ }
+ l->addr = address;
+ while (isdelm(str[i], dbg) != 1) {
+ uint8_t offset = 0;
+ base = 0;
+ space = 0;
+ tab = 0;
+ while (isdelm(str[i+j], dbg) == 16) {
+ tab += str[i+j] == '\t';
+ space += str[i+j] == ' ';
+ j++;
+ }
+ j = 0;
+ if (dbg) {
+ printf("lex(): tab: %u, space: %u\n", tab, space);
+ }
+ if (isdelm(str[i], dbg) == 16) {
+ for (; isdelm(str[i], dbg) == 16; i++);
+ }
+ uint8_t ptok = get_ptok(str[i], dbg);
+ if (is_altok(ptok, dbg)) {
+ offset++;
+ if (((ptok == PTOK_S || ptok == PTOK_B) && toupper(str[i+1]) == 'P') || (ptok == PTOK_P && toupper(str[i+1]) == 'C')) {
+ offset++;
+ }
+ switch (get_ptok(str[i+offset], dbg)) {
+ case PTOK_B :
+ case PTOK_E :
+ case PTOK_X :
+ case PTOK_Y :
+ case PTOK_S :
+ case PTOK_P :
+ case PTOK_A :
+ case PTOK_C :
+ case PTOK_D :
+ case PTOK_F :
+ case PTOK_R :
+ case PTOK_ALPHA : ptok = PTOK_ALPHA; break;
+ case PTOK_NUMBER:
+ if (ptok == PTOK_R) {
+ char reg_num[3];
+ for (int isnum = 0; isdigit(str[i+offset]) && !(isdelm(str[i+offset], dbg) & 0x03) && isnum < 2; offset++, isnum++) {
+ reg_num[isnum] = str[i+offset];
+ }
+ reg_num[isnum] = '\0';
+ if (isnum == 2) {
+ int regnum = strtoul(reg_num, NULL, 10);
+ ptok = (regnum < 11 || regnum > 15) ? PTOK_ALPHA : ptok;
+ } else {
+ ptok = PTOK_ALPHA;
+ }
+ } else {
+ ptok = PTOK_ALPHA;
+ }
+ break;
+ }
+ if ((ptok == PTOK_S && str[i+1] && toupper(str[i+1]) != 'P') || (ptok == PTOK_P && toupper(str[i+1]) != 'C')) {
+ ptok = PTOK_ALPHA;
+ }
+ }
+ /*i = ptok_handler[ptok](str, i, lex_type, l, t, dbg);*/
+ switch (ptok) {
+ case PTOK_DOT:
+ i++;
+ for (; !(isdelm(str[i+j], dbg) & 17); j++);
+ memcpy(lexeme, str+i, j);
+ lexeme[j] = '\0';
+ i += j;
+ if (!isop) {
+ for (k = 0; k < 11; k++) {
+ if (tolower(lexeme[0]) == dir_t[k][0] && !strcasecmp(lexeme, dir_t[k])) {
+ lex_type = TOK_DIR;
+ uint16_t tmp = j;
+ for (j = 0; isdelm(str[i+j], dbg) & 16; j++);
+ uint8_t ret = get_ptok(str[i+j], dbg);
+ j = tmp;
+
+ if ((k == DIR_STRUCT || k == DIR_UNION) && (ret != PTOK_ALPHA || (is_anon && ret == PTOK_ALPHA))) {
+ is_anon++;
+ }
+ is_struct += (k == DIR_STRUCT || k == DIR_UNION);
+ is_struct -= (k == DIR_ENDSTRUCT || k == DIR_ENDUNION);
+ if ((k == DIR_ENDSTRUCT || k == DIR_ENDUNION)) {
+ end_struct(cur_sym, struct_sym, dbg);
+ }
+ break;
+ }
+ }
+ if (lex_type != TOK_DIR && lt && lt->id == TOK_SYM) {
+ lex_type = TOK_MEMBER;
+ i -= j;
+ } else {
+ l->count++;
+ t = make_token(lex_type, k, space, tab, 0, "", NULL);
+ }
+ } else {
+ lex_type = TOK_RS;
+ switch (tolower(lexeme[j-1])) {
+ case '2':
+ case 'w':
+ rs = 1;
+ break;
+ case '4':
+ case 'd':
+ rs = 2;
+ break;
+ case '8':
+ case 'q':
+ rs = 3;
+ break;
+ }
+ l->count++;
+ t = make_token(lex_type, rs, space, tab, 0, "", NULL);
+ isop = 0;
+ }
+ break;
+ case PTOK_DQUOTE:
+ i++;
+ for (; isdelm(str[i+j], dbg) != 4 || isesc; j++) {
+ isesc = (str[i+j] == '\\' && str[i+(j-1)] != '\\');
+ }
+ memcpy(lexeme, str+i, j);
+ lexeme[j] = '\0';
+ i += j;
+ strid = get_string(lexeme, dbg);
+ if (strid == 0xFFFF) {
+ strid = stridx;
+ string[strid] = malloc(j+1);
+ memcpy(string[strid], lexeme, j+1);
+ stridx++;
+ } else {
+ }
+ if (dbg) {
+ printf("lex(): str[0x%04X]: %s\n", strid, string[strid]);
+ }
+ if (lt->id == TOK_DIR && lt->type == DIR_INCLUDE) {
+ incl[inc_count+inc_file] = strid;
+ inc_file++;
+ }
+ lex_type = TOK_STRING;
+ l->count++;
+ t = make_token(lex_type, 0, space, tab, 0, string[strid], NULL);
+ break;
+ case PTOK_DOLLAR:
+ case PTOK_PERCENT:
+ case PTOK_NUMBER:
+ value = 0;
+ switch (ptok) {
+ case PTOK_DOLLAR : base = 16; lex_type = TOK_HEX; i++; break;
+ case PTOK_PERCENT: base = 2; lex_type = TOK_BIN; i++; break;
+ case PTOK_NUMBER : base = 10; lex_type = TOK_DEC; /**/ break;
+ }
+ for (; isxdigit(str[i+j]) && !(isdelm(str[i+j], dbg) & 0x03); j++);
+ memcpy(lexeme, str+i, j);
+ lexeme[j] = '\0';
+ i += j;
+ value = strtoull(lexeme, NULL, base);
+ if (lt->id == TOK_SYM) {
+ tsym = mksymbol(sym, value, 1, islocal, 0, 0, dbg);
+ if (lt) {
+ lt->sym = get_sym(sym, address, lt, islocal, dbg);
+ }
+ if (!islocal) {
+ cur_sym = last_sym;
+ }
+ tsym = NULL;
+ islocal = 0;
+ isfixup += (lt->sym == NULL);
+ if (dbg) {
+ printf("lex(): isfixup: %u\n", isfixup);
+ }
+ }
+ l->count++;
+ t = make_token(lex_type, 0, space, tab, value, "", NULL);
+ t->digits = (lt->id != TOK_SYM) ? j : 0;
+ break;
+ case PTOK_SQUOTE:
+ i++;
+ k = 0;
+ j = 0;
+ while (isdelm(str[i], dbg) != 8 || isesc) {
+ isesc = (str[i] == '\\' && str[i-1] != '\\');
+ lexeme[j++] = str[i++];
+ }
+ isesc = 0;
+ lexeme[j] = '\0';
+ for (j = 0; lexeme[k] != '\0' && j < 7; k++) {
+ switch (lexeme[k]) {
+ case '\\':
+ switch (lexeme[++k]) {
+ case 'n' : ch.u8[j++] = '\n'; break;
+ case 'r' : ch.u8[j++] = '\r'; break;
+ case 't' : ch.u8[j++] = '\t'; break;
+ case 'b' : ch.u8[j++] = '\b'; break;
+ case '\'': ch.u8[j++] = '\''; break;
+ case '\"': ch.u8[j++] = '\"'; break;
+ case '\\': ch.u8[j++] = '\\'; break;
+ }
+ break;
+ default: ch.u8[j++] = lexeme[k];
+ }
+ }
+ lex_type = TOK_CHAR;
+ l->count++;
+ t = make_token(lex_type, 0, space, tab, ch.u64, "", NULL);
+ break;
+ case PTOK_LBRACK:
+ case PTOK_HASH :
+ /*l->tok->type = (ptok == PTOK_LBRACK) ? IND : IMM;
+ lex_type = (ptok == PTOK_LBRACK) ? TOK_IND : TOK_IMM;*/
+ lex_type = TOK_MEM;
+ value = (ptok == PTOK_LBRACK) ? MEM_IND : MEM_IMM;
+ l->count++;
+ t = make_token(lex_type, value, space, tab, 0, "", NULL);
+ lex_type = (ptok == PTOK_LBRACK) ? TOK_IND : TOK_IMM;
+ memset(lexeme, 0, strlen(lexeme)+1);
+ lexeme[j++] = str[i];
+ /*(t) ? (t->subspace = space) : (lt->subspace = space);
+ (t) ? (t->subtab = tab) : (lt->subtab = tab);*/
+ break;
+ case PTOK_PLUS:
+ case PTOK_MINUS:
+ case PTOK_GT:
+ case PTOK_LT:
+ case PTOK_PIPE:
+ lex_type = TOK_EXPR;
+ switch (ptok) {
+ case PTOK_PLUS : value = EXPR_PLUS ; break;
+ case PTOK_MINUS: value = EXPR_MINUS; break;
+ case PTOK_PIPE : value = EXPR_OR ; break;
+ case PTOK_GT : value = (get_ptok(str[i+1], dbg) == PTOK_GT) ? (EXPR_RSHFT) : (EXPR_LOW) ; break;
+ case PTOK_LT : value = (get_ptok(str[i+1], dbg) == PTOK_LT) ? (EXPR_LSHFT) : (EXPR_HIGH); break;
+ }
+ l->count++;
+ t = make_token(lex_type, value, space, tab, 0, "", NULL);
+ memset(lexeme, 0, strlen(lexeme)+1);
+ lexeme[j++] = str[i];
+ if (value == EXPR_LSHFT || value == EXPR_RSHFT) {
+ lexeme[j++] = str[++i];
+ }
+ break;
+ case PTOK_EQU:
+ i++;
+ lex_type = TOK_SYM;
+ memset(lexeme, 0, strlen(lexeme)+1);
+ lexeme[j] = str[i];
+ (t) ? (t->subspace = space) : (lt->subspace = space);
+ (t) ? (t->subtab = tab) : (lt->subtab = tab);
+ break;
+ case PTOK_RBRACK:
+ i++;
+ lex_type = TOK_IND;
+ lexeme[j] = ')';
+ lexeme[j+1] = '\0';
+ lexeme[j+2] = '\0';
+ (t) ? (t->subspace = space) : (lt->subspace = space);
+ (t) ? (t->subtab = tab) : (lt->subtab = tab);
+ break;
+ case PTOK_COMMA:
+ i++;
+ if (lex_type != TOK_IND && lex_type != TOK_OF) {
+ lex_type = TOK_CSV;
+ }
+ lexeme[j] = ',';
+ lexeme[j+1] = '\0';
+ lexeme[j+2] = '\0';
+ break;
+ case PTOK_B:
+ case PTOK_E:
+ case PTOK_X:
+ case PTOK_Y:
+ case PTOK_S:
+ case PTOK_A:
+ case PTOK_C:
+ case PTOK_D:
+ case PTOK_F:
+ case PTOK_R:
+ lexeme[j+0] = str[i++];
+ lexeme[j+1] = (ptok == PTOK_R || ((ptok == PTOK_S || ptok == PTOK_B) && get_ptok(str[i], dbg) == PTOK_P)) ? str[i++] : '\0';
+ lexeme[j+2] = (ptok == PTOK_R) ? str[i++] : '\0';
+ lexeme[j+3] = '\0';
+ lex_type = TOK_REG;
+ switch (ptok) {
+ case PTOK_A: value = REG_A; break;
+ case PTOK_X: value = REG_X; break;
+ case PTOK_Y: value = REG_Y; break;
+ case PTOK_E: value = REG_E; break;
+ case PTOK_C: value = REG_C; break;
+ case PTOK_D: value = REG_D; break;
+ case PTOK_S:
+ case PTOK_B:
+ if (get_ptok(lexeme[j+1], dbg) == PTOK_P) {
+ value = (ptok == PTOK_S) ? REG_SP : REG_BP;
+ } else {
+ value = (ptok == PTOK_S) ? REG_S : REG_B;
+ }
+ break;
+ case PTOK_F: value = REG_F; break;
+ case PTOK_R: value = strtoull(lexeme+j+1, NULL, 10); break;
+ }
+ l->count++;
+ t = make_token(lex_type, value, space, tab, 0, "", NULL);
+ /*(t) ? (t->subspace = space) : (lt->subspace = space);
+ (t) ? (t->subtab = tab) : (lt->subtab = tab);*/
+ break;
+ case PTOK_P:
+ lexeme[j] = str[i++];
+ lexeme[j+1] = (str[i] != ',') ? str[i++] : '\0';
+ lexeme[j+2] = '\0';
+ /*switch (ptok) {
+ case PTOK_S: of = 1; break;
+ case PTOK_P: of = 2; break;
+ }*/
+ of = 2;
+ lex_type = TOK_OF;
+ l->count++;
+ t = make_token(lex_type, of, space, tab, 0, "", NULL);
+ break;
+ case PTOK_AT:
+ memset(lexeme, 0, strlen(lexeme)+1);
+ lexeme[j] = '@';
+ islocal = 1;
+ lex_type = TOK_LOCAL;
+ if (lt || t) {
+ (t) ? (t->subspace = space) : (lt->subspace = space);
+ (t) ? (t->subtab = tab) : (lt->subtab = tab);
+ }
+ break;
+ case PTOK_COLON:
+ i++;
+ lexeme[j] = ':';
+ lexeme[j+1] = '\0';
+ lex_type = TOK_LABEL;
+ tsym = mksymbol(sym, address, 1, islocal, 0, 0, dbg);
+ if (isfixup) {
+ isfixup = reslv_fixups(dbg);
+ }
+ if (lt) {
+ lt->id = lex_type;
+ lt->type = islocal;
+ lt->sym = get_sym(sym, address, t, islocal, dbg);
+ isfixup += (lt->sym == NULL);
+ }
+ if (!islocal) {
+ cur_sym = last_sym;
+ locals = NULL;
+ last_loc = NULL;
+ } else if (cur_sym->down == NULL && cur_sym == last_sym) {
+ cur_sym->down = locals;
+ cur_sym->down->up = cur_sym;
+ }
+ tsym = NULL;
+ islocal = 0;
+ if (dbg) {
+ printf("lex(): isfixup: %u\n", isfixup);
+ }
+ break;
+ case PTOK_SCOLON:
+ i++;
+ for (; isdelm(str[i+j], dbg) != 1; j++);
+ if (!j) {
+ lexeme[j] = ' ';
+ lexeme[j+1] = '\0';
+
+ } else {
+ memcpy(lexeme, str+i, j);
+ lexeme[j] = '\0';
+ i += j;
+ comid = get_comment(lexeme, dbg);
+ /*is_newcom = (comid == 0xFFFF);
+ if (comid == 0xFFFF) {
+ if (line != lineidx && l[line].com != 0xFFFF) {
+ comid = l[line].com;
+ } else {
+ comid = comidx;
+ }
+ comid = comidx;
+ comment[comid] = malloc(j+1);
+ memcpy(comment[comid], lexeme, j+1);
+ comidx++;
+ }*/
+ if (dbg) {
+ printf("lex(): com[0x%04X]: %s\n", comid, comment[comid]);
+ }
+ }
+ lex_type = TOK_COMMENT;
+ l->count++;
+ if (j) {
+ t = make_token(lex_type, 0, space, tab, 0, comment[comid], NULL);
+ } else {
+ t = make_token(lex_type, 0, space, tab, 0, "" , NULL);
+ }
+
+ break;
+ case PTOK_ALPHA:
+ for (; !isdelm2(str[i+j], dbg); j++);
+ memcpy(lexeme, str+i, j);
+ lexeme[j] = '\0';
+ i += j;
+ isch = 0;
+ isop = 0;
+ if (j == 3 && str[i] != ':' && !is_struct) {
+ for (k = 0; k < OPNUM; k++) {
+ int find_ext = (k < EXT_OPNUM);
+ int find_ortho = (k < ORTHO_OPNUM);
+ int upper = toupper(lexeme[0]);
+ int isbase = (upper == mne[k][0]);
+ int isext = (find_ext && upper == ext_mne[k][0]);
+ int isortho = (find_ortho && upper == ortho_mne[k][0]);
+
+ if (isbase || isext || isortho) {
+ int is_base = !strcasecmp(lexeme, mne[k]);
+ int is_ext = (find_ext && !strcasecmp(lexeme, ext_mne[k]));
+ int is_ortho = (find_ortho && !strcasecmp(lexeme, ortho_mne[k]));
+ if (is_base || is_ext || is_ortho) {
+ lex_type = (is_base) ? TOK_OPCODE : lex_type;
+ lex_type = (is_ext) ? TOK_EXTOP : lex_type;
+ lex_type = (is_ortho) ? TOK_ORTHO : lex_type;
+ isop = 1;
+ l->count++;
+ t = make_token(lex_type, 0xFF, space, tab, k, "", NULL);
+ break;
+ }
+ }
+ }
+ }
+ if (!isop) {
+ uint8_t spaces = 0;
+ if (l->tok->type == TOK_ORTHO && l->tok->byte == SET) {
+ for (k = 0; k < 8; k++) {
+ int upper = toupper(lexeme[0]);
+ if (upper == set_cc[k][0]) {
+ if (!strcasecmp(lexeme, set_cc[k])) {
+ lex_type = TOK_CC;
+ l->count++;
+ t = make_token(lex_type, 0xFF, space, tab, k, "", NULL);
+ }
+ }
+ }
+ }
+ for (; isdelm(str[i+spaces], dbg) == 16; spaces++);
+ uint8_t ret = get_ptok(str[i+spaces], dbg);
+ if (ret == PTOK_COLON || ret == PTOK_EQU) {
+ islocal = (lex_type == TOK_LOCAL);
+ }
+ lex_type = TOK_SYM;
+ l->count++;
+ t = make_token(lex_type, islocal, space, tab, 0, "", NULL);
+ memcpy(sym, lexeme, j+1);
+ if (dbg) {
+ printf("lex(): spaces: %u\n", spaces);
+ }
+ if (is_struct) {
+ create_struct(cur_sym, l, t, lt, sym, dbg);
+ islocal = 0;
+ } else if ((str[i+spaces] != ':' && str[i+spaces] != '=')) {
+ uint8_t sym_struct = 0;
+ symbol *s;
+ /*tmp_sym = (s && s->isstruct) ? NULL : tmp_sym;*/
+ if (tmp_sym) {
+ t->sym = find_member(lexeme, tmp_sym, dbg);
+ tmp_sym = NULL;
+ } else {
+ t->sym = get_sym(lexeme, address, t, islocal, dbg);
+ }
+ isfixup += (t && t->sym == NULL);
+ islocal = 0;
+ if (dbg) {
+ printf("lex(): isfixup: %u\n", isfixup);
+ }
+ }
+ if (!is_struct && t && t->sym && t->sym->isstruct) {
+ tmp_sym = t->sym;
+ }
+ }
+ break;
+ }
+ if (!l->tok && t) {
+ l->tok = tokens;
+ }
+ if (dbg) {
+ printf("lex(): lexeme: %s, lex_type: %s\n", lexeme, (lex_type != 0xFF) ? lex_tok[lex_type] : "TOK_NONE");
+ }
+ j = 0;
+ if ((lex_type == TOK_OPCODE || lex_type == TOK_EXTOP) && !isop) {
+ j = 0;
+ } else if (lex_type == TOK_EXPR || (lex_type != TOK_MEMBER && !isdelm2(str[i], dbg))) {
+ i++;
+ }
+ switch (lex_type) {
+ default:
+ lex_type = 0xFF;
+ case TOK_CSV:
+ case TOK_IND:
+ case TOK_LOCAL:
+ memset(lexeme, 0, strlen(lexeme)+1);
+ case TOK_SYM:
+ break;
+ }
+ if (t) {
+ lt = t;
+ t = t->next;
+ }
+ }
+ if (i) {
+ l->tok = tokens;
+ token *tok = tokens;
+ if (tok->id == TOK_SYM && tok->next) {
+ symbol *s = tok->sym;
+ for (; tok; tok = tok->next) {
+ switch (tok->id) {
+ case TOK_HEX :
+ case TOK_BIN :
+ case TOK_DEC :
+ case TOK_CHAR:
+ case TOK_EXPR:
+ s->val = get_val(tok, address, 3, dbg);
+ if (tok->next) {
+ tok = skip_expr(tok, dbg);
+ }
+ break;
+ }
+ }
+ }
+ tokens = NULL;
+ last_tok = NULL;
+ bytecount dummy;
+ if (!is_struct) {
+ l = (tmp_line) ? tmp_line : l;
+ address = parse_tokens(l->tok, &l, &dummy, 0, address, dbg);
+ if (tmp_line) {
+ tmp_line = NULL;
+ }
+ }
+ if (dbg) {
+ printf("lex(): Next address: $%"PRIX64"\n", address);
+ }
+ if (ln > linenum || islinenum) {
+ l->linenum = ln;
+ if (ln > linenum) {
+ linenum+=(10+(ln & 10));
+ }
+ } else if (!islinenum) {
+ l->linenum = linenum;
+ linenum += 10;
+ }
+ }
+ return address;
+}