projects/06/assembler1/assembler1.c
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 |
#include <stdbool.h> #include <stdint.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include "../bindump.h" #define DEBUG(x) printf(x) void die(const char *err_msg, int exit_val) { perror(err_msg); exit(exit_val); } void alert(const char *err_msg) { fprintf(stderr, "%s", err_msg); } bool parse_a_type(const char *line, uint16_t *instruction) { DEBUG("parse_a_type()\n"); // eventually, if error, die("error: TODO explain...\n", -1); *instruction = 0x0000; // STUB, A-type MSB == 0 anyway return true; // STUB, A-type MSB == 0 anyway } bool parse_c_type(const char *line, uint16_t *instruction) { DEBUG("parse_c_type()\n"); *instruction = 0x8000; // STUB, C-type MSB == 1 anyway return true; // STUB, C-type MSB == 1 anyway } // */ // does not care about line line length; exits at first newline or after // relevant portion parsed (allows for syntactically-incorrect lines, I know) bool parse_instruction_w_type(const char *line, uint16_t *instruction) { bool ret; char c; size_t i = 0; while ((c = line[i]) != '\n') { if (c == ' ' || c == '\t') ; // skip whitespace else if (c == '@') { ret = parse_a_type(line, instruction); break; } else if (c >= '!' && c < '~') { ret = parse_c_type(line, instruction); break; } else { die("error: TODO explain...\n", -1); } ++i; } return ret; } // */ bool parse_next_instruction(const char *line, uint16_t *instruction) { *instruction = 1337; // STUB, should be 0x539, 0b0000010100111001 return parse_instruction_w_type(line, instruction); return true; } /* return false for comment or invalid assembly instruction */ bool parse_line(const char *line, size_t line_len, uint16_t *instruction) { char c; bool slash_found = false; size_t i; if (line_len == 0 || line_len == 1) return false; // filter out comment lines //for (i = 0; (c = line[i]) != NULL; ++i) { for (i = 0; i < line_len; ++i) { c = line[i]; if (c == ' ' || c == '\t') { continue; } else if (c == '/') { if (slash_found) { // second slash means this is a comment return false; } slash_found= true; continue; } else if (slash_found) { // this char not slash, but previous was: invalid syntax // TODO: add line, column numbers alert("\tsyntax error: found '/', comments " "need '//'\n"); return false; } else { // non-whitespace/slash char discovered break; } } // comment not found, so attempting to parse instruction return parse_next_instruction(line, instruction); } const char *test_lines[8] = {"// this is a comment\n", "@12345\n", "\n", "M+1\n", "@98\n", "// this is another comment\n", "/ this is a broken comment\n", "D=M;JNE\n"}; size_t num_test_lines = (sizeof(test_lines) / sizeof(test_lines[0])); int main() { // TODO: read file by lines, parse instructions bool result = false; uint16_t instruction; size_t test_line_len; // New organization allows code to eventually work with lines fetched // from a 'fgets()' loop or something // for testing for (size_t i = 0; i < num_test_lines; ++i) { test_line_len = strlen(test_lines[i]); result = parse_line(test_lines[i], test_line_len, &instruction); if (result) { printf("instruction: 0x%x | ", instruction); bindump_word16(instruction); // output instruction as binary putchar('\n'); } } return 0; } |