all repos — nand2tetris @ 8c016de00acf4ccf622c4e2b1af6d218011fed0c

my nand2tetris progress

projects/06/src/n2tasm2.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
 148
 149
 150
 151
 152
 153
 154
 155
 156
 157
 158
 159
 160
 161
 162
 163
 164
 165
 166
 167
 168
 169
 170
 171
 172
 173
 174
 175
 176
 177
 178
 179
 180
 181
 182
 183
 184
 185
 186
 187
 188
 189
 190
 191
 192
 193
 194
 195
 196
 197
 198
 199
 200
 201
 202
 203
 204
 205
 206
 207
 208
 209
 210
 211
 212
 213
 214
 215
 216
 217
 218
 219
 220
 221
 222
 223
 224
 225
 226
 227
 228
 229
 230
 231
 232
 233
 234
 235
 236
 237
 238
 239
 240
 241
 242
 243
 244
 245
 246
 247
 248
 249
 250
 251
 252
 253
 254
 255
 256
 257
 258
 259
 260
 261
 262
 263
 264
 265
 266
 267
 268
 269
 270
 271
 272
 273
 274
 275
 276
 277
 278
 279
 280
 281
 282
 283
 284
 285
 286
 287
 288
 289
 290
 291
 292
 293
 294
 295
 296
 297
 298
 299
 300
 301
 302
 303
 304
 305
 306
 307
 308
 309
 310
 311
 312
 313
 314
 315
 316
 317
 318
 319
 320
 321
 322
 323
 324
 325
 326
 327
 328
 329
 330
 331
 332
 333
 334
 335
 336
 337
 338
 339
 340
 341
 342
 343
 344
 345
 346
 347
 348
 349
 350
 351
 352
 353
 354
 355
 356
 357
 358
 359
 360
 361
 362
 363
 364
 365
 366
 367
 368
 369
 370
 371
 372
 373
 374
 375
 376
 377
 378
 379
 380
 381
 382
 383
 384
 385
 386
 387
 388
 389
 390
 391
 392
 393
 394
 395
 396
 397
 398
 399
 400
 401
 402
 403
 404
 405
 406
 407
 408
 409
 410
 411
 412
 413
 414
 415
 416
 417
 418
 419
 420
 421
 422
 423
 424
 425
 426
 427
 428
#include <stdbool.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#ifdef _DEBUG
#define DBGLOG   printf
#else
#define DBGLOG(...)
#endif

#define err(...) (fprintf(stderr, __VA_ARGS__), \
                  fprintf(stderr, "%lu | %s\n", file_line_no, file_line), false)
#define die(...)   do { fprintf(stderr, __VA_ARGS__); exit(-1); } while (0)

#define is_symbol_char(c) (('0' <= c && c <= '9') || ('A' <= c && c <= 'Z') \
                        || ('a' <= c && c <= 'z') || c == '_' || c == '.'   \
                                                  || c == '$' || c == ':')
#define is_whitespace(c) ((c == ' ' || c == '\t' || c == '\n' || c == '\r'))
#define is_number(c) (('0' <= c && c <= '9'))

#define MAX_LINE_LEN          256 // TODO: in/excludes NULL terminator?
#define MAX_SYMBOL_LEN        MAX_LINE_LEN - 2 + 1 // + 1 for NULL terminator

size_t instruction_offset = 0;

uint16_t rom[32768];
size_t rom_index = 0;

char  *file_line;     // reference to currently-read line (for convenience)
size_t file_line_no;  // line number, regardless of line content

// label and variable symbols are treated the same internally
#define MAX_SYMBOLS     32768
char *reserved_strs[] = {"R0", "R1", "R2", "R3", "R4", "R5", "R6", "R7",
                         "R8", "R9", "R10", "R11", "R12", "R13", "R14", "R15",
                         "SP", "LCL", "ARG", "THIS", "THAT", "SCREEN", "KBD"};
uint16_t reserved_vals[] = {0, 1, 2, 3, 4, 5, 6, 7,
                            8, 9, 10, 11, 12, 13, 14, 15,
                            0, 1, 2, 3, 4, 0x4000, 0x6000};
char     symbol_strs[MAX_SYMBOLS + sizeof(reserved_vals)][MAX_SYMBOL_LEN];
uint16_t symbol_vals[MAX_SYMBOLS + sizeof(reserved_vals)];
uint16_t symbol_index;
uint16_t next_var_address = 16;


static void write_rom_binary(FILE *fp)
{
	size_t i, k;
        char bin_str[17];
	for (i = 0; i < rom_index; ++i) {
		for (k = 0; k < 16; ++k, rom[i] <<= 1)
			bin_str[k] = (((rom[i] >> 15) & 0x01) != 0) ? '1' : '0';
		bin_str[16] = '\0';
		fprintf(fp, "%s\n", bin_str);
	}
}

static size_t skip_whitespace(const char *line, size_t n)
{
	size_t i;
	for (i = 0; is_whitespace(line[i]) && i < n; ++i);
	return i;
}

//static void debug_dump_all_symbols()
//{
//	size_t i;
//	DBGLOG("-------- DEBUG SYMBOL DUMP --------\n");
//	for (i = 0; i < symbol_index; ++i)
//		DBGLOG("symbol (%s, %hu)\n", symbol_strs[i], symbol_vals[i]);
//	DBGLOG("-------- END SYMBOL DUMP --------\n");
//}

static char *lookup_symbol(const char *str, uint16_t *val)
{
	size_t i;

	for (i = 0; i < sizeof(symbol_strs) / sizeof(symbol_strs[0]); ++i) {
		if (strncmp(symbol_strs[i], str, MAX_SYMBOL_LEN) == 0) {
			*val = symbol_vals[i];
			return symbol_strs[i];
		}
	}

	return NULL;
}

static bool add_symbol(const char *str, uint16_t val)
{
	uint16_t tmp;

	if (symbol_index > 32767)
		return err("error: failed to add symbol '%s': %hu > 32767\n",
		           str, val);

	if (lookup_symbol(str, &tmp) != NULL)
		return err("error: failed to add symbol '%s': symbol already "
		           "exists\n", str);

	strncpy(symbol_strs[symbol_index], str, MAX_SYMBOL_LEN);
	symbol_vals[symbol_index] = val;
	++symbol_index;

	return true;
}

// pre-fill symbol lists with 'reserved' symbols and values
static bool init_reserved_symbols()
{
	size_t i;

	for (i = 0; i < sizeof(reserved_strs) / sizeof(reserved_strs[0]); ++i)
		if (!add_symbol(reserved_strs[i], reserved_vals[i]))
			return err("error: failed to init reserved symbols\n");

	return true;
}

// assumes line[0] == '('
bool parse_line_for_label(const char *line) {
	size_t i;
	char c, label_str[MAX_SYMBOL_LEN + 1];

	for (i = 1; i < MAX_SYMBOL_LEN; ++i) {
		c = line[i];
		if (c == '\0' || c == ')')
			break;
		if (!is_symbol_char(c))
			return err("error: invalid char '%c' in label\n", c);
		label_str[i - 1] = line[i];
	}

	if (c != ')')
		return err("error: no matching ')' found for label\n");

	label_str[i - 1] = '\0';
	return add_symbol(label_str, (uint16_t)instruction_offset);
}

/* returns dest bits 0b00000ddd
 */
bool parse_c_type_dest(const char *line, uint16_t *dest)
{
	size_t i;
	uint8_t a_dest = 0, d_dest = 0, m_dest = 0;

	for (i = 0; line[i] != '='; ++i) {
		switch (line[i]) {
		case 'A': ++a_dest; break;
		case 'D': ++d_dest; break;
		case 'M': ++m_dest; break;
		default: return  err("syntax error: invalid destination "
			               "register '%c'\n", line[i]);
		}

		if (i >= 3)
			return err("error: too many destinations\n");
	}

	if (a_dest > 1)
		return err("syntax error: multiple 'A's in destination\n");
	if (d_dest > 1)
		return err("syntax error: multiple 'D's in destination\n");
	if (m_dest > 1)
		return err("syntax error: multiple 'M's in destination\n");

	*dest = (uint16_t)((a_dest << 2) | (d_dest << 1) | (m_dest));
	return true;
}

/* returns comp bits 0b0acccccc
 */
bool parse_c_type_comp(const char *line, uint16_t *comp)
{
	size_t i;
	char comp_str[5];
	char *comp_tb[] = {"0", "1", "-1", "D", "A", "M", "!D", "!A",
	                   "!M", "-D", "-A", "-M", "D+1", "A+1", "M+1", "D-1",
	                   "A-1", "M-1", "D+A", "D+M", "D-A", "D-M", "A-D",
	                   "M-D", "D&A", "D&M", "D|A", "D|M"};
	char comp_vals[] = {0x2a, 0x3f, 0x3a, 0x0c, 0x30, 0x70, 0x0d, 0x31,
	                     0x71, 0x0f, 0x33, 0x73, 0x1f, 0x37, 0x77, 0x0e,
	                     0x32, 0x72, 0x02, 0x42, 0x13, 0x53, 0x07,
	                     0x47, 0x00, 0x40, 0x15, 0x55};

	for (i = 0; i < 5 && !is_whitespace(line[i]) && line[i] != ';'
	                  && line[i] != '/' && line[i] != '\0'; ++i)
		comp_str[i] = line[i];

	comp_str[i] = '\0';
	if (i > 4)
		return err("syntax error: invalid comp field '%s'\n", comp_str);

	for (i = 0; i < (sizeof(comp_tb) / sizeof(comp_tb[0])); ++i) {
		if (strncmp(comp_tb[i], comp_str, 3) == 0) {
			*comp = (uint16_t)comp_vals[i];
			return true;
		}
	}

	return err("syntax error: invalid comp field '%s'\n", comp_str);
}

/* returns jump bits 0b00000jjj
 */
bool parse_c_type_jump(const char *line, uint16_t *jump)
{
	size_t i;
	char jump_str[5];
	char *jump_tb[] = {"", "JGT", "JEQ", "JGE", "JLT", "JNE", "JLE", "JMP"};

	for (i = 0; i < 5 && !is_whitespace(line[i]) && line[i] != '/'
	                  && line[i] != '\0'; ++i)
		jump_str[i] = line[i];

	jump_str[i] = '\0';
	if (i > 4)
		return err("syntax error: invalid jump field '%s'\n", jump_str);

	for (i = 0; i < (sizeof(jump_tb) / sizeof(jump_tb[0])); ++i) {
		if (strncmp(jump_tb[i], jump_str, 3) == 0) {
			*jump = (uint16_t)i;
			return true;
		}
	}

	return err("syntax error2: invalid jump field '%s'\n", jump_str);
}

/* instruction format: 0b111accccccdddjjj
 */
bool parse_c_type(const char *line, uint16_t *instruction)
{
	size_t i;
	char c;
	const char *dest_start = NULL, *comp_start = NULL, *jump_start = NULL;
	uint16_t dest = 0, comp = 0, jump = 0;

	c = line[0];
	for (i = 0; !is_whitespace(c) && c != '\0'; ++i) {
		c = line[i];
		if (c == '=') {
			dest_start = &line[0];
			comp_start = &line[i+1];
		} else if (c == ';')
			jump_start = &line[i+1];
	}

	// only comp field is mandatory; dest/jump are optional, may not exist
	if (comp_start == NULL)
		comp_start = &line[0];

	if (!parse_c_type_comp(comp_start, &comp))
		return false;

	if (dest_start != NULL)
		if (!parse_c_type_dest(dest_start, &dest))
			return false;

	if (jump_start != NULL)
		if (!parse_c_type_jump(jump_start, &jump))
			return false;

	*instruction = 0xe000 | (comp << 6) | (dest << 3) | jump;
	return true;
}

bool parse_a_type(const char *line, uint16_t *instruction)
{
	char a_str[MAX_SYMBOL_LEN + 1], *sym_ptr;
	size_t i, a_str_len;
	uint16_t a_field = 0;

	for (i = 1; i < MAX_SYMBOL_LEN && is_symbol_char(line[i]); ++i) {
		a_str[i - 1] = line[i];
	}

	if (!(is_whitespace(line[i]) || line[i] == '\0' || line[i] == '/'))
		return err("syntax error: invalid char '%c' in instruction\n",
		           line[i]);

	a_str_len = i - 1;
	a_str[a_str_len] = '\0';

	if (a_str_len == 0)
		return err("syntax error: instruction empty after @\n");

	if (is_number(a_str[0])) {  // @<string> probably number
		if (a_str_len > 5)
			return err("syntax error: instruction field '%s' too "
			      "large\n", a_str);
		for (i = 0; i < 5 && is_number(a_str[i]); ++i) {
			if (!is_number(a_str[i]))
				return err("syntax error: '%s' not a valid "
				           "number\n", a_str);
			a_field = (a_field * 10) + (a_str[i] - 0x30);
		}
		if (a_field > 0x7fff)
			return err("syntax error: %u > 32767, too large\n",
			           a_field);
	} else {  // @<string> probably symbol
		sym_ptr = lookup_symbol(a_str, &a_field);
		if (sym_ptr == NULL) {
			a_field = next_var_address++;
			if (!add_symbol(a_str, a_field))
				return err("error: failed to add var '%s'\n",
				           a_str);
		}
	}

	*instruction = a_field;
	return true;
}

// does not care about line length; exits at first newline or after relevant
// portion parsed (allows for syntactically-incorrect lines, I know)
bool parse_instruction(const char *line, uint16_t *instruction)
{
	if (line[0] == '@')
		return parse_a_type(line, instruction);
	else if (line[0] >= '!' && line[0] < '~')
		return parse_c_type(line, instruction);

	return err("syntax error: invalid char '%c' found\n", line[0]);
}

// if first_pass == true: read labels and associate them with values
// else: (second pass) parse instructions
// Still unsure how I feel about doing handling both passes in one function.
// It's hacky, but also space saving and elegant in a way.
bool pass(FILE *in_file, bool first_pass)
{
	bool ret = true, second_pass = !first_pass; 
	char *line, in_line[MAX_LINE_LEN];
	uint16_t instruction;
	size_t i, line_len;

	if (first_pass)
		if (!init_reserved_symbols())
			return false;

	file_line_no = 0;
	instruction_offset = 0;
	while (fgets(in_line, MAX_LINE_LEN, in_file) != NULL) {  // parse loop
		++file_line_no;
		//DBGLOG("line %lu: %s", file_line_no, in_line);
		file_line = in_line;
		line = &in_line[skip_whitespace(in_line, MAX_LINE_LEN)];

		line_len = 0;
		for (i = 0; line[i] != '\0'; ++i) {
			if (line[i] == '\n' || line[i] == '\r') {
				line[i] = '\0'; // remove newlines
				break;
			}
			++line_len;  // get line length
		}

		if (line_len == 0)  // "empty" line
			continue;
		if (line_len > 1)
			if (line[0] == '/' && line[1] == '/')  // comment found
				continue;
		if (line[0] == '(') {
			if (first_pass) {
				if (!parse_line_for_label(line))
					ret = false;
			} else
				continue;
		} else {
			if (second_pass) {
				if (parse_instruction(line, &instruction))
					rom[rom_index++] = instruction;
				else
					ret = false;
			}
			++instruction_offset;
			continue;  // first pass: if not label, ignore line
		}
	}

	return ret;
}


char *usage_msg = "Usage: n2tasm2 [input/file.asm] [assembled/output]\n"
                  "       n2tasm2 [input/file.asm] # will output to STDOUT\n";

int main(int argc, char *argv[])
{
	FILE *in_file, *out_file;
	char *in_file_path;
	if (argc == 2) {
		out_file = stdout;
	} else if (argc == 3) {
		out_file = fopen(argv[2], "wb");
		if (out_file == NULL)
			die("failed to open %s for writing\n", argv[2]);
	} else {
		die(usage_msg);
	}

	in_file_path = argv[1];
	in_file = fopen(in_file_path, "r");
	if (in_file == NULL)
		die("failed to open assembly file for reading\n");

	if(!pass(in_file, true)) // first pass
		die("failed to parse labels/variables in file\n");

	//debug_dump_all_symbols();
	if (fseek(in_file, 0, SEEK_SET))
		die("failed to re-read file from beginning\n");

	if(!pass(in_file, false)) // second pass
		die("failed to parse assembly in file\n");

	write_rom_binary(out_file);
	if (fclose(in_file))
		die("failed to close assembly file\n");
	if (fclose(out_file))
		die("failed to close output file\n");

	return 0;
}