M projects/06/Makefile → projects/06/Makefile

@@ -1,17 +1,19 @@ 
-
+# nand2tetris chapter 6 assembler makefile
+# for debugging this makefile: `make -d`
 CFLAGS = -std=c99 -Wall -Wextra
 
-all: bin/assembler1 bin/assembler2
+all: bin/n2tasm1 bin/n2tasm2
 
-# TODO: clean up, make more Makefile-idiomatic
+bin/n2tasm%: src/n2tasm%.c
+	$(CC) $(DEBUG) $(CFLAGS) -o $@ $<
 
-bin/assembler1: assembler1/assembler1.c
-	$(CC) $(CFLAGS) -o $@ $<
+debug: DEBUG = -D_DEBUG
+debug: all
 
-bin/assembler2: assembler2/assembler2.c
-	$(CC) $(CFLAGS) -o $@ $<
+#test:
+# TODO: write tests, decide suitable way to run
 
 clean:
 	rm -vf bin/*
 
-.PHONY: clean
+.PHONY: clean debug

M projects/06/README.md → projects/06/README.md

@@ -1,9 +1,15 @@ 
-
 # Assembler(s)
 
 Approach: write 2-3 assemblers, then compare all three, their approaches, pros/cons, and write retrospective.
 
 1. Write an assembler purely from scratch w/o any "spoilers" or implementation tips from the book or online (besides what I already know).
+- DONE
 2. Write an assembler based off of an elegant assmbler I've already seen online (ex. 100rabbits assembler)
+- Inspiration taken from the following code:
+    - https://github.com/dmatlack/chip8
+    - https://git.sr.ht/~rabbits/gyo
+    - https://git.sr.ht/~rabbits/uxn11
+- DONE
 3. Write the assembler based on the book's recommended implementation/organization.
+- I may/may not do this, time permitting.
 

M projects/06/assembler1/assembler1.c → projects/06/src/n2tasm1.c

@@ -4,9 +4,13 @@ #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 
-#define DBGLOG(...)             printf(__VA_ARGS__)
-//#define DBGLOG(...)
-#define error(...)              fprintf(stderr, __VA_ARGS__); \
+#ifdef _DEBUG
+#define DBGLOG                  printf
+#else
+#define DBGLOG(...)
+#endif
+
+#define err(...)              fprintf(stderr, __VA_ARGS__); \
                                 fprintf(stderr, "%lu | %s\n", \
                                         g_asm_line_number, g_asm_line); \
 				g_error_encountered = true;
@@ -52,7 +56,7 @@ size_t g_symbol_list_len = 0;
 size_t g_current_variable_address = 16; // address for next variable symbol
 
 
-void print_binary_word16(uint16_t w)
+void write_binary_word16(FILE *fp, uint16_t w)
 {
         unsigned char i, msb;
         char binary_string[17];
@@ -67,7 +71,7 @@ else
                         binary_string[i] = '0';
                 w <<= 1;
         }
-        printf("%s", binary_string);
+        fprintf(fp, "%s\n", binary_string);
 }
 
 static uint32_t myatoi(const char *str)
@@ -91,6 +95,7 @@ DBGLOG("-------- DEBUG SYMBOL DUMP --------\n");
 	for (i = 0; i < g_symbol_list_len; ++i) {
 		symbol = g_symbol_list[i];
 		DBGLOG("symbol (%s, %hu)\n", symbol->symbolstr, symbol->value);
+		(void)symbol; // "use" to shut up compiler warning
 	}
 	DBGLOG("-------- END SYMBOL DUMP --------\n");
 
@@ -121,14 +126,14 @@ //DBGLOG("creating symbol {'%s', %hu} ...\n", str, value);
 
 	len = strlen(str);
 	if (len == 0) {
-		error("error creating empty label\n");
+		err("error creating empty label\n");
 		return NULL;
 	}
 
 	symbol = malloc(sizeof(struct symbol_t));
 	symbolstr = malloc(len + 1);
 	if (symbol == NULL || symbolstr == NULL) {
-		error("error creating label: malloc() returned NULL\n");
+		err("error creating label: malloc() returned NULL\n");
 		exit(-1);
 	}
 
@@ -165,14 +170,14 @@ {
 	struct symbol_t *symbol_already_present;
 
 	if (g_symbol_list_len > (MAX_SYMBOLS + RESERVED_LABEL_NUM)) {
-		error("internal: symbol list full, over %d symbols\n",
+		err("internal: symbol list full, over %d symbols\n",
 		       (MAX_SYMBOLS + RESERVED_LABEL_NUM));
 		return false;
 	}
 
 	symbol_already_present = lookup_symbol(symbol->symbolstr);
 	if (symbol_already_present != NULL) { // if present
-		error("error: failed to add symbol %s: already found in list\n",
+		err("error: failed to add symbol %s: already found in list\n",
 		      symbol->symbolstr);
 		return false;
 	}
@@ -212,19 +217,19 @@ 
 	*symbol_len = 0;
 	for (i = 0; (c = line[i]) != '\0'; ++i) {
 		if (i == 0 && ('0' <= c && c <= '9')) {
-			error("syntax error: label starts with a number\n");
+			err("syntax error: label starts with a number\n");
 			return false;
 		}
 		// parse characters until closing ')'
 		if (i > MAX_SYMBOL_STR_LEN) {
-			error("syntax error: label is too long (> %d chars)\n",
+			err("syntax error: label is too long (> %d chars)\n",
 			       MAX_SYMBOL_STR_LEN);
 			return false;
 		} else if (valid_symbol_char(c)) {
 			symbol_str[i] = c;
 		} else {
 			if (i == 1) {
-				error("syntax error: empty label '()'\n");
+				err("syntax error: empty label '()'\n");
 				return false;
 			}
 
@@ -259,7 +264,7 @@ return false;
 	}
 
 	if (line[label_len + 1] != ')') {
-		error("syntax error: no matching ')' found for label, found "
+		err("syntax error: no matching ')' found for label, found "
 		      "value '%c' in label\n", line[label_len + 1]);
 		return false;
 	}
@@ -291,7 +296,7 @@ } else if (('!' <= c && c <= '\'') || ('*' <= c && c <= '~')) {
 			++g_instruction_number;  // likely instruction found
 			return false;
 		} else {
-			error("syntax error: invalid character '%c' found in "
+			err("syntax error: invalid character '%c' found in "
 			      "line\n", c);
 		}
 	}
@@ -310,14 +315,14 @@ 
 	//DBGLOG("line: %s\n", line);
 
 	if (line[0] != '@') {
-		error("syntax error: A-type instruction doesn't start with @\n");
+		err("syntax error: A-type instruction doesn't start with @\n");
 		return false;
 	}
 
 	c = line[1];
 
 	if (c == '\0') {
-		error("syntax error: A-type instruction empty after @\n");
+		err("syntax error: A-type instruction empty after @\n");
 		return false;
 	}
 
@@ -343,7 +348,7 @@ } else {
 		for (i = 1; (c = line[i]) != '\0' && a < 6; ++i) {
 			if ('0' <= c && c <= '9') {
 				if (a > 4) {
-					error("error: @<number> too long\n");
+					err("error: @<number> too long\n");
 					return false;
 				}
 				a_field_str[a] = c; // get number
@@ -351,15 +356,15 @@ a++;
 			} else if ((c == ' ' || c == '\t' || c == '/') && i > 1) {
 				break;
 			} else {       // any other character encountered
-				error("syntax error: invalid char '%c' found "
+				err("syntax error: invalid char '%c' found "
 				      "after @\n", c);
 				return false;
 			}
 		}
 
 		if (a == 0) {
-			error("syntax error: A-type instruction empty "
-			      "after '@'\n");
+			err("syntax error: A-type instruction empty after "
+			      "'@'\n");
 			return false;
 		}
 
@@ -369,7 +374,7 @@ a_field = myatoi(a_field_str);
 	}
 
 	if (a_field > 32767) {
-		error("error: %u > 32767, too large\n", a_field);
+		err("error: %u > 32767, too large\n", a_field);
 		return false;
 	}
 
@@ -389,36 +394,36 @@ 
 	for (len = 0; dest_line[len] != '='; ++len) {  // read until '='
 		if (dest_line[len] == 'A') {
 			if (*dest & 0x04) { // if A register already set
-				error("syntax error: A register set twice\n");
+				err("syntax error: A register set twice\n");
 				return false;
 			}
 			*dest |= 0x04;
 		} else if (dest_line[len] == 'D') {
 			if (*dest & 0x02) { // if D register already set
-				error("syntax error: D register set twice\n");
+				err("syntax error: D register set twice\n");
 				return false;
 			}
 			*dest |= 0x02;
 		} else if (dest_line[len] == 'M') {
 			if (*dest & 0x01) { // if M register already set
-				error("syntax error: M register set twice\n");
+				err("syntax error: M register set twice\n");
 				return false;
 			}
 			*dest |= 0x01;
 		} else {
-			error("syntax error: invalid destination register %c\n",
+			err("syntax error: invalid destination register %c\n",
 			      dest_line[len]);
 			return false;
 		}
 
 		if (len >= 3) {
-			error("syntax error: dest field incorrect length %lu\n",
+			err("syntax error: dest field incorrect length %lu\n",
 			      len);
 			return false;
 		}
 	}
 	if (len == 0) {
-		error("syntax error: dest field empty\n");
+		err("syntax error: dest field empty\n");
 		return false;
 	}
 
@@ -446,7 +451,7 @@ case 'D': *comp = 0x0c; break; // 0 001100
 		case 'A': *comp = 0x30; break; // 0 110000
 		case 'M': *comp = 0x70; break; // 1 110000
 		default:
-			error("syntax error: comp field incorrect value\n");
+			err("syntax error: comp field incorrect value\n");
 			return false;
 		}
 	} else if (len == 2) {  // -1 !D !A !M -D -A -M 
@@ -457,7 +462,7 @@ case 'D': *comp = 0x0f; break; // 0 001111
 			case 'A': *comp = 0x33; break; // 0 110011
 			case 'M': *comp = 0x73; break; // 1 110011
 			default:
-				error("syntax error: comp field incorrect value\n");
+				err("syntax error: comp field incorrect value\n");
 				return false;
 			}
 		} else if (comp_line[0] == '!') {
@@ -466,11 +471,11 @@ case 'D': *comp = 0x0d; break; // 0 001101
 			case 'A': *comp = 0x31; break; // 0 110001
 			case 'M': *comp = 0x71; break; // 1 110001
 			default:
-				error("syntax error: comp field incorrect value\n");
+				err("syntax error: comp field incorrect value\n");
 				return false;
 			}
 		} else {
-			error("syntax error: comp field incorrect value\n");
+			err("syntax error: comp field incorrect value\n");
 			return false;
 		}
 	} else if (len == 3) {
@@ -481,7 +486,7 @@ *comp = 0x1f; // 0 011111
 				} else if (comp_line[1] == '-') {
 					*comp = 0x0e; // 0 001110
 				} else {
-					error("syntax error: comp field "
+					err("syntax error: comp field "
 					      "incorrect value\n");
 					return false;
 				}
@@ -491,7 +496,7 @@ *comp = 0x40;              // _1_ 000000
 				} else if (comp_line[2] == 'A') {
 					*comp = 0x00;              // _0_ 000000
 				} else {
-					error("syntax error: comp field "
+					err("syntax error: comp field "
 					      "incorrect value\n");
 					return false;
 				}
@@ -502,7 +507,7 @@ case '-': *comp |= 0x13; break; // 010011
 				case '&': *comp |= 0x00; break; // 000000
 				case '|': *comp |= 0x15; break; // 010101
 				default:
-					error("syntax error: comp field "
+					err("syntax error: comp field "
 					      "incorrect value\n");
 					return false;
 				}
@@ -514,7 +519,7 @@ *comp = 0x40;              // _1_ 000000
 			} else if (comp_line[0] == 'A') {
 				*comp = 0x00;              // _0_ 000000
 			} else {
-				error("syntax error: comp field incorrect value\n");
+				err("syntax error: comp field incorrect value\n");
 				return false;
 			}
 
@@ -525,12 +530,12 @@ *comp |= 0x32;  // 1 110010
 			} else if (comp_line[1] == '-' && comp_line[2] == 'D') {
 				*comp |= 0x07;  // 1 000111
 			} else {
-				error("syntax error: comp field incorrect value\n");
+				err("syntax error: comp field incorrect value\n");
 				return false;
 			}
 		}
 	} else {
-		error("syntax error: comp field incorrect length %lu\n", len);
+		err("syntax error: comp field incorrect length %lu\n", len);
 		return false;
 	}
 
@@ -552,7 +557,7 @@ jump_line[len] == 'Q' || jump_line[len] == 'L' ||
 	              jump_line[len] == 'N' || jump_line[len] == 'M' ||
 	              jump_line[len] == 'P'; ++len) {}
 	if (len != 3) {
-		error("syntax error: jump field incorrect length %lu\n", len);
+		err("syntax error: jump field incorrect length %lu\n", len);
 		return false;
 	}
 
@@ -564,14 +569,14 @@ *jump = 0x1;
 			} else if (jump_line[2] == 'E') {  // if "JGE"
 				*jump = 0x3;
 			} else {
-				error(err_3rd_char); return false;
+				err(err_3rd_char); return false;
 			}
 			break;
 		case 'E':                                  // if "JE_"
 			if (jump_line[2] == 'Q') {         // if "JEQ"
 				*jump = 0x2;
 			} else {
-				error(err_3rd_char); return false;
+				err(err_3rd_char); return false;
 			}
 			break;
 		case 'L':                                  // if "JL_"
@@ -580,29 +585,29 @@ *jump = 0x4;
 			} else if (jump_line[2] == 'E') {  // if "JLE"
 				*jump = 0x6;
 			} else {
-				error(err_3rd_char); return false;
+				err(err_3rd_char); return false;
 			}
 			break;
 		case 'N':                                  // if "JN_"
 			if (jump_line[2] == 'E') {         // if "JNE"
 				*jump = 0x5;
 			} else {
-				error(err_3rd_char); return false;
+				err(err_3rd_char); return false;
 			}
 			break;
 		case 'M':                                  // if "JM_"
 			if (jump_line[2] == 'P') {         // if "JMP"
 				*jump = 0x7;
 			} else {
-				error(err_3rd_char); return false;
+				err(err_3rd_char); return false;
 			}
 			break;
 		default:
-			error("syntax error: 2nd letter in jump field incorrect\n");
+			err("syntax error: 2nd letter in jump field incorrect\n");
 			return false;
 		}
 	} else {
-		error("syntax error: jump field doesn't start with 'J'\n");
+		err("syntax error: jump field doesn't start with 'J'\n");
 		return false;
 	}
 
@@ -637,7 +642,7 @@ dest_start = &line[0];   // start of line
 				// this 'i+1' might be dangerous!
 				comp_start = &line[i+1]; // after "[dest]="
 			} else {
-				error("syntax error: dest incorrect length %lu\n", i);
+				err("syntax error: dest incorrect length %lu\n", i);
 				return false;
 			}
 		} else if (c == ';') {              // indicates jump field
@@ -645,7 +650,7 @@ if (1 <= i && i <= 7) {
 				// this 'i+1' might be dangerous!
 				jump_start = &line[i+1]; // after "[comp];"
 			} else {
-				error("syntax error: jump incorrect length %lu\n", i);
+				err("syntax error: jump incorrect length %lu\n", i);
 				return false;
 			}
 		}
@@ -702,7 +707,7 @@ ret = parse_c_type(&line[i], instruction);
 			++g_instruction_number;
 			break;
 		} else {
-			error("syntax error: line '%s' incorrectly formatted\n",
+			err("syntax error: line '%s' incorrectly formatted\n",
 			      line);
 		}
 
@@ -733,7 +738,7 @@ slash_found = true;
 			continue;
 		} else if (slash_found) {
 			// this char not slash, but previous was: invalid syntax
-			error("syntax error: found '/', comments need '//'\n");
+			err("syntax error: found '/', comments need '//'\n");
 			return false;
 		} else if (c == '(') {        // found label, ignore and return
 			return false;
@@ -747,7 +752,8 @@ return parse_next_instruction(line, instruction);
 }
 
 
-char *usage_msg = "Usage: assembler1 [path/to/file.asm]\n";
+char *usage_msg = "Usage: n2tasm1 [input/file.asm] [assembled/output]\n"
+                  "       n2tasm1 [input/file.asm] # will output to STDOUT\n";
 
 int main(int argc, char *argv[])
 {
@@ -756,12 +762,27 @@ uint16_t instruction;
 	char in_line[MAX_LINE_LEN];
 	size_t i, file_line, in_line_len;
 	char *in_file_path;
-	FILE *fp;
+	FILE *fp, *fp_out;
 
+	if (argc == 2) {
+		fp_out = stdout;
+	} else if (argc == 3) {
+		fp_out = fopen(argv[2], "wb");
+		if (fp_out == NULL) {
+			fprintf(stderr, "failed to open %s for writing\n",
+			        argv[2]);
+			exit(-1);
+		}
+	} else {
+		fprintf(stderr, usage_msg);
+		exit(-1);
+	}
+	/*
 	if (argc != 2) {                            // requires 1 argument
 		fprintf(stderr, usage_msg);
 		exit(-1);
 	}
+	*/
 
 	in_file_path = argv[1];
 	fp = fopen(in_file_path, "r");
@@ -814,7 +835,7 @@ }
 
 	file_line = 1;
 	while (fgets(in_line, MAX_LINE_LEN, fp) != NULL) {  // parse loop
-		fprintf(stderr, "line %lu: %s", file_line, in_line);
+		DBGLOG("line %lu: %s", file_line, in_line);
 		for (i = 0; in_line[i] != '\0'; ++i) {      // remove newlines
 			if (in_line[i] == '\n' || in_line[i] == '\r') {
 				in_line[i] = '\0';
@@ -830,10 +851,8 @@ g_asm_line = in_line;
 		g_asm_line_number = file_line;
 		result = parse_line(in_line, &instruction);
 
-		if (result) {
-			print_binary_word16(instruction);
-			putchar('\n');
-		}
+		if (result)
+			write_binary_word16(fp_out, instruction);
 
 		++file_line;
 	}

M projects/06/assembler2/assembler2.c → projects/06/src/n2tasm2.c

@@ -4,7 +4,11 @@ #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 
-#define DBGLOG printf
+#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)
@@ -13,7 +17,7 @@ 
 #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'))
+#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?
@@ -182,7 +186,7 @@ 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] != '/'; ++i)
+	                  && line[i] != '/' && line[i] != '\0'; ++i)
 		comp_str[i] = line[i];
 
 	comp_str[i] = '\0';
@@ -207,7 +211,8 @@ 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] != '/'; ++i)
+	for (i = 0; i < 5 && !is_whitespace(line[i]) && line[i] != '/'
+	                  && line[i] != '\0'; ++i)
 		jump_str[i] = line[i];
 
 	jump_str[i] = '\0';
@@ -221,7 +226,7 @@ return true;
 		}
 	}
 
-	return err("syntax error: invalid jump field '%s'\n", jump_str);
+	return err("syntax error2: invalid jump field '%s'\n", jump_str);
 }
 
 /* instruction format: 0b111accccccdddjjj
@@ -340,6 +345,7 @@ 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)];
 
@@ -379,7 +385,8 @@ return ret;
 }
 
 
-char *usage_msg = "Usage: assembler1 [path/to/file.asm]\n";
+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[])
 {
@@ -390,7 +397,7 @@ out_file = stdout;
 	} else if (argc == 3) {
 		out_file = fopen(argv[2], "wb");
 		if (out_file == NULL)
-			die("failed to open output file for writing\n");
+			die("failed to open %s for writing\n", argv[2]);
 	} else {
 		die(usage_msg);
 	}
@@ -418,3 +425,4 @@ die("failed to close output file\n");
 
 	return 0;
 }
+