summaryrefslogtreecommitdiff
path: root/programs/c-ports/subasm.c
diff options
context:
space:
mode:
Diffstat (limited to 'programs/c-ports/subasm.c')
-rw-r--r--programs/c-ports/subasm.c484
1 files changed, 463 insertions, 21 deletions
diff --git a/programs/c-ports/subasm.c b/programs/c-ports/subasm.c
index a996e3a..89d1507 100644
--- a/programs/c-ports/subasm.c
+++ b/programs/c-ports/subasm.c
@@ -1,33 +1,475 @@
#include "subeditor.h"
-int16_t str_cmp(const char *s0, uint16_t i, const char *s1, uint16_t j) {
- for (; s0[i] == s1[j]; i++, j++);
- return i-j;
+
+struct line {
+ uint8_t dir;
+ uint8_t mne;
+ uint8_t am;
+ uint8_t opbase;
+ uint16_t com;
+ uint16_t label;
+ uint64_t op;
+};
+char *label[0x1000];
+uint64_t label_addr[0x1000];
+/*char *comment[0x1000];*/
+/*char *string[0x1000];*/
+
+enum dir {
+ DIR_ORG,
+ DIR_BYTE,
+ DIR_WORD,
+ DIR_DWORD,
+ DIR_QWORD
+};
+
+enum type {
+ TOK_DIR,
+ TOK_LABEL,
+ TOK_STRING,
+ TOK_OPCODE,
+ TOK_COMMENT,
+ TOK_HEX,
+ TOK_DEC,
+ TOK_BIN
+};
+
+enum am {
+ IMPL,
+ IMM,
+ ZM,
+ ZMX,
+ ZMY,
+ ABS,
+ IND,
+ INDX,
+ INDY
+};
+
+enum base {
+ HEX,
+ DEC,
+ BIN
+};
+
+
+char lexeme[0x100];
+uint8_t lex_type;
+struct line tokline[0x1000];
+uint16_t linenum = 10;
+
+static const char *mne_t[90] = {
+ [ 0] = "CPS",
+ [ 1] = "ADC",
+ [ 2] = "AAB",
+ [ 3] = "PHP",
+ [ 4] = "CPB",
+ [ 5] = "PHB",
+ [ 6] = "DEC",
+ [ 7] = "JMP",
+ [ 8] = "SBC",
+ [ 9] = "SAB",
+ [10] = "ENT",
+ [11] = "CPY",
+ [12] = "PLB",
+ [13] = "INC",
+ [14] = "JSR",
+ [15] = "JSL",
+ [16] = "AND",
+ [17] = "ABA",
+ [18] = "PLP",
+ [19] = "CPX",
+ [20] = "PHY",
+ [21] = "BPO",
+ [22] = "ORA",
+ [23] = "OAB",
+ [24] = "STT",
+ [25] = "PLY",
+ [26] = "BNG",
+ [27] = "XOR",
+ [28] = "XAB",
+ [29] = "PHA",
+ [30] = "PHX",
+ [31] = "BCS",
+ [32] = "LSL",
+ [33] = "LLB",
+ [34] = "CLC",
+ [35] = "PLX",
+ [36] = "BCC",
+ [37] = "LSR",
+ [38] = "LRB",
+ [39] = "PLA",
+ [40] = "TAB",
+ [41] = "BEQ",
+ [42] = "ROL",
+ [43] = "RLB",
+ [44] = "SEC",
+ [45] = "TBA",
+ [46] = "BNE",
+ [47] = "ROR",
+ [48] = "RRB",
+ [49] = "DEY",
+ [50] = "TAY",
+ [51] = "BVS",
+ [52] = "MUL",
+ [53] = "MAB",
+ [54] = "CLI",
+ [55] = "TYA",
+ [56] = "BVC",
+ [57] = "DIV",
+ [58] = "DAB",
+ [59] = "INY",
+ [60] = "TAX",
+ [61] = "RTS",
+ [62] = "RTL",
+ [63] = "CMP",
+ [64] = "CAB",
+ [65] = "SEI",
+ [66] = "LDX",
+ [67] = "TXA",
+ [68] = "RTI",
+ [69] = "LDA",
+ [70] = "DEX",
+ [71] = "CLV",
+ [72] = "TYX",
+ [73] = "STA",
+ [74] = "TSX",
+ [75] = "LDB",
+ [76] = "INX",
+ [77] = "WAI",
+ [78] = "TXY",
+ [79] = "STB",
+ [80] = "TXS",
+ [81] = "LDY",
+ [82] = "BRK",
+ [83] = "NOP",
+ [84] = "STY",
+ [85] = "DEB",
+ [86] = "ASR",
+ [87] = "ARB",
+ [88] = "STX",
+ [89] = "INB"
+};
+
+static const char *dir_t[5] = {
+ [0] = "org",
+ [1] = "byte",
+ [2] = "word",
+ [3] = "dword",
+ [4] = "qword"
+};
+
+int isalpha(int c) {
+ return ((unsigned)c|32)-'a' < 26;
+}
+
+int isdigit(int c) {
+ return (unsigned)c-'0' < 10;
+}
+
+int isxdigit(int c) {
+ return isdigit(c) || ((unsigned)c|32)-'a' < 6;
+}
+
+int islower(int c) {
+ return (unsigned)c-'a' < 26;
+}
+
+int isupper(int c) {
+ return (unsigned)c-'A' < 26;
+}
+
+int toupper(int c) {
+ if (islower(c))
+ return c & 0x5F;
+ return c;
+}
+
+uint64_t tohex(char *str) {
+ uint8_t i = 0;
+ uint8_t digit;
+ uint64_t value = 0;
+ for (; str[i] != '\0';) {
+ if (isdigit(str[i])) {
+ digit = str[i] - '0';
+ } else if (isupper(str[i])) {
+ digit = str[i] - ('A' - 10);
+ } else if (islower(str[i])) {
+ digit = str[i] - ('a' - 10);
+ } else {
+ break;
+ }
+ value = (value << 4) + digit;
+ ++i;
+ }
+ return value;
+}
+
+uint64_t todec(char *str) {
+ uint8_t i = 0;
+ uint8_t digit;
+ uint64_t value = 0;
+ for (; str[i] != '\0';) {
+ if (isdigit(str[i])) {
+ digit = str[i] - '0';
+ } else {
+ break;
+ }
+
+ value = (value << 3) + (value << 1) + digit;
+ ++i;
+ }
+ return value;
+}
+
+uint64_t tobin(char *str) {
+ uint8_t i = 0;
+ uint8_t digit;
+ uint64_t value = 0;
+ for (; str[i] != '\0';) {
+ if (isdigit(str[i])) {
+ digit = str[i] - '0';
+ } else {
+ break;
+ }
+ value = (value << 1) + digit;
+ ++i;
+ }
+ return value;
+}
+
+int str_cmp(const char *s0, const char *s1) {
+ for (; *s0 == *s1 && *s0; s0++, s1++);
+ return *s0-*s1;
}
-void tokenize(char *str) {
+int str_casecmp(const char *s0, const char *s1) {
+ for (; *s0 && *s1 && (*s0 == *s1 || toupper(*s0) == toupper(*s1)); s0++, s1++);
+ return toupper(*s0) - toupper(*s1);
+}
+
+uint8_t is_white(char ch) {
+ return (ch == ' ' || ch == '\t');
+}
+
+
+
+uint8_t lex(char *str) {
uint16_t i = 0;
- uint16_t skip = 0;
+ uint16_t j = 0;
+ lex_type = 0xFF;
+ uint8_t k = 0;
+ int line = 40;
+ int16_t ln = -1;
+ int y, x;
+ char lnum[6];
+ uint8_t islinenum;
+ while (isdigit(str[i]) && !is_white(str[i])) {
+ lnum[j++] = str[i++];
+ }
+ islinenum = i;
+ if (i) {
+ lnum[j] = '\0';
+ ln = todec(lnum);
+ j = 0;
+ } else {
+ ln = linenum;
+ }
+ getyx(scr, y, x);
uint8_t done = 0;
- while (!done) {
- if (!cmd_buf[i]) {
- done = 1;
- } else {
- switch (cmd_buf[i]) {
- case '.':
- if (skip = str_cmp(cmd_buf, i+1, "org", 0) > 0) {
- f = TOK_ORG;
- i += skip;
- } else if (skip = str_cmp(cmd_buf, i+1, "byte", 0) > 0) {
- f = TOK_BYTE;
- i+=skip;
- }
- break;
+ while (str[i] != '\0') {
+ if (is_white(str[i])) {
+ while (is_white(str[i])) {
+ i++;
}
}
+ switch (str[i]) {
+ case '.':
+ i++;
+ while (!is_white(str[i])) {
+ lexeme[j++] = str[i++];
+ }
+ lexeme[j] = '\0';
+ for (k = 0; k < 5; k++) {
+ if (!str_casecmp(lexeme, dir_t[k])) {
+ lex_type = TOK_DIR;
+ break;
+ }
+ }
+ i++;
+ tokline[ln].dir = k;
+ break;
+ case '\"':
+ i++;
+ while (str[i] != '\"') {
+ lexeme[j] = str[i];
+ /*string[linenum][j] = str[i];*/
+ j++, i++;
+ }
+ i++;
+ lexeme[j] = '\0';
+ /*string[linenum][j] = '\0';*/
+ lex_type = TOK_STRING;
+ break;
+ case '$':
+ i++;
+ while (isxdigit(str[i]) && str[i] != '\0') {
+ lexeme[j++] = str[i++];
+ }
+ lexeme[j] = '\0';
+ tokline[ln].op = tohex(lexeme);
+ tokline[ln].opbase = HEX;
+ lex_type = TOK_HEX;
+ break;
+ case '%':
+ i++;
+ while (isdigit(str[i]) && str[i] != '\0') {
+ lexeme[j++] = str[i++];
+ }
+ lexeme[j] = '\0';
+ tokline[ln].op = tobin(lexeme);
+ tokline[ln].opbase = BIN;
+ lex_type = TOK_BIN;
+ break;
+ case ';':
+ i++;
+ while (str[i] != '\0') {
+ lexeme[j++] = str[i++];
+ /*comment[linenum][j] = str[i];*/
+ /*j++, i++;*/
+ }
+ lexeme[j] = '\0';
+ /*comment[linenum][j] = '\0';*/
+ lex_type = TOK_COMMENT;
+ break;
+ case '#':
+ lexeme[j] = '#';
+ lexeme[j+1] = '\0';
+ lexeme[j+2] = '\0';
+ tokline[ln].am = IMM;
+ break;
+ case '(':
+ lexeme[j] = '(';
+ lexeme[j+1] = '\0';
+ lexeme[j+2] = '\0';
+ tokline[ln].am = IND;
+ break;
+ case ')':
+ i++;
+ if (str[i] == ',') {
+ i++;
+ while (is_white(str[i])) {
+ lexeme[j++] = str[i++];
+ }
+ if (tokline[ln].am == IND && toupper(str[i]) == 'Y') {
+ lexeme[j++] = 'y';
+ tokline[ln].am = INDY;
+ }
+ lexeme[j] = '\0';
+ } else {
+ lexeme[j] = ')';
+ lexeme[j+1] = '\0';
+ lexeme[j+2] = '\0';
+ }
+ break;
+ case ',':
+ i++;
+ while (is_white(str[i])) {
+ lexeme[j++] = str[i++];
+ }
+ if (tokline[ln].am == IND && toupper(str[i]) == 'X') {
+ tokline[ln].am = INDX;
+ lexeme[j++] = 'x';
+ i++;
+ } else {
+ switch (toupper(str[i])) {
+ case 'X':
+ tokline[ln].am = ZMX;
+ lexeme[j++] = 'x';
+ break;
+ case 'Y':
+ tokline[ln].am = ZMY;
+ lexeme[j++] = 'y';
+ break;
+ }
+ }
+ lexeme[j] = '\0';
+ break;
+ default:
+ if (isalpha(str[i]) || isdigit(str[i])) {
+ while (!is_white(str[i]) && str[i] != '\0') {
+ lexeme[j++] = str[i++];
+ }
+ for (k = 0; k < 90; k++) {
+ if (!str_casecmp(lexeme, mne_t[k])) {
+ lex_type = TOK_OPCODE;
+ tokline[ln].mne = k;
+ break;
+ }
+ }
+ for (k = 0; lexeme[k] != '\0';) {
+ if (isdigit(lexeme[k])) {
+ k++;
+ } else {
+ break;
+ }
+ }
+ if (lexeme[k] == '\0') {
+ tokline[ln].op = todec(lexeme);
+ tokline[ln].opbase = DEC;
+ lex_type = TOK_DEC;
+ }
+
+ }
+ break;
+ }
+ wmove(scr, line++, 0);
+ wclrtoeol(scr);
+ wprintw(scr, "lexeme: %s, lex_type: %u\r", lexeme, lex_type);
+ j = 0, lex_type = 0xFF;
+ /*lex_type = 0xFF;*/
+ if (str[i] != ')' && str[i] != ',') {
+ i++;
+ }
+ }
+ line++;
+ uint16_t ix = 0;
+ wmove(scr, line, 0);
+ wclrtoeol(scr);
+ wprintw(scr, "dir: %u"
+ ", mne: $%02X"
+ ", am: %u"
+ ", opbase: %u"
+ ", com: $%04X"
+ ", label: $%04X"
+ ", op: $%016X"
+ ", ln: %i\r"
+ , tokline[ln].dir
+ , tokline[ln].mne
+ , tokline[ln].am
+ , tokline[ln].opbase
+ , tokline[ln].com
+ , tokline[ln].label
+ , tokline[ln].op
+ , ln);
+ wmove(scr, y, x);
+ wrefresh(scr);
+ if (ln > linenum) {
+ linenum+=(10+(ln & 10));
+ } else if (!islinenum) {
+ linenum += 10;
+ }
+ for (ix = 0; lexeme[ix] != '\0';) {
+ lexeme[ix] = 0;
+ ++ix;
}
+ return i;
}
-void subasm() {
+uint8_t subasm() {
+ uint16_t i;
uint64_t address = 0;
- tokenize(cmd_buf);
+ lex(cmd_buf);
+ /*if (dir != 0xFF) {
+ }*/
+ return 0;
}
generated by cgit v1.2.3-13-gbd6f (git 2.30.0) at 2024-07-05 19:19:25 +0000