VM: add support for strings

examples/strings.hal

@@ -0,0 +1,11 @@
+---
+globals: 0
+global_pointers: 0
+---
+:0 { args: 0 ptr_args: 0 locals: 0 local_pointers: 0 } {
+    PushLiteralString "Hello,";
+    PushLiteralString " World!";
+    ConcatStrings;
+    PrintString;
+    Exit;
+}

include/assembler/lexer.h

@@ -36,8 +36,12 @@ typedef enum
 	TOKEN_ModI64,
 	TOKEN_Call,
 	TOKEN_PrintTopStackI64,
+	TOKEN_PushLiteralString,
+	TOKEN_ConcatStrings,
+	TOKEN_PrintString,
 	TOKEN_Exit,
 	TOKEN_NUMBER,
+	TOKEN_STRING,
 	TOKEN_COLON,
 	TOKEN_SEMICOLON,
 	TOKEN_HASHTAG,

include/hal64.h

@@ -30,23 +30,34 @@ typedef enum
 	OP_MOD_I64,
 	OP_CALL,
 	OP_PRINT_TOP_STACK_I64,
+	OP_PUSH_LITERAL_STRING,
+	OP_CONCAT_STRINGS,
+	OP_PRINT_STRING,
 	OP_EXIT,
 } InstructionOp;
 
 typedef struct
 {
 	InstructionOp op;
-	union {
+	union
+	{
 		uint64_t immediate;
 		size_t reg;
-		struct {
+		struct
+		{
 			size_t reg;
 			uint64_t immediate;
 		} ri;
-		struct {
+		struct
+		{
 			size_t reg1;
 			size_t reg2;
 		} rr;
+		struct
+		{
+			char *ptr;
+			size_t size;
+		} string;
 	} data;
 } Instruction;
 
@@ -72,13 +83,31 @@ typedef struct
 
 typedef struct
 {
-	uint64_t *call_stack;
-	uint64_t *operands_stack;
+	uint8_t marked;
+	size_t size;
+	void *data;
+} HeapObject;
+
+typedef struct {
+	uint64_t *data;
+	size_t size;
+	size_t capacity;
+} Array;
+
+typedef struct {
+	HeapObject *data;
+	size_t size;
+	size_t capacity;
+} PointersArray;
+
+typedef struct
+{
+	Array call_stack;
+	Array operands_stack;
+	PointersArray pointers_stack;
+	PointersArray objects;
 	uint64_t *locals;
-	size_t call_stack_size;
-	size_t call_stack_capacity;
-	size_t operands_stack_size;
-	size_t operands_stack_capacity;
+	size_t allocated_heap_size;
 } VM;
 
 Program init_program(void);

src/assembler/assemble.c

@@ -1,6 +1,7 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <limits.h>
+#include <string.h>
 #include "assembler/assembler.h"
 #include "assembler/lexer.h"
 #include "utils/memory.h"
@@ -167,6 +168,18 @@ read_literal_number()
 	return token;
 }
 
+static Token
+read_literal_string()
+{
+	Token token;
+	token = read_token();
+	if (token.type != TOKEN_STRING) {
+		fprintf(stderr, "Expected string, got %s\n", token.value);
+		exit(EXIT_FAILURE);
+	}
+	return token;
+}
+
 static void
 read_ri(Instruction *instruction) {
 	Token token;
@@ -297,6 +310,18 @@ read_instruction(Instruction *instruction)
 	case TOKEN_PrintTopStackI64:
 		instruction->op = OP_PRINT_TOP_STACK_I64;
 		break;
+	case TOKEN_PushLiteralString:
+		instruction->op = OP_PUSH_LITERAL_STRING;
+		token = read_literal_string();
+		instruction->data.string.ptr = strdup(token.value);
+		instruction->data.string.size = strlen(token.value);
+		break;
+	case TOKEN_ConcatStrings:
+		instruction->op = OP_CONCAT_STRINGS;
+		break;
+	case TOKEN_PrintString:
+		instruction->op = OP_PRINT_STRING;
+		break;
 	case TOKEN_Exit:
 		instruction->op = OP_EXIT;
 		break;

src/hal64.c

@@ -91,6 +91,15 @@ instruction_as_string(Instruction instruction, char *string, size_t max_length)
 	case OP_PRINT_TOP_STACK_I64:
 		snprintf(string, max_length, "PRINT_TOP_STACK_I64");
 		break;
+	case OP_PUSH_LITERAL_STRING:
+		snprintf(string, max_length, "PUSH_LITERAL_STRING \"%s\"", instruction.data.string);
+		break;
+	case OP_CONCAT_STRINGS:
+		snprintf(string, max_length, "CONCAT_STRINGS");
+		break;
+	case OP_PRINT_STRING:
+		snprintf(string, max_length, "PRINT_STRING");
+		break;
 	default:
 		snprintf(string, max_length, "UNKNOWN");
 		break;

src/lexer.l

@@ -8,6 +8,7 @@
 %%
 
 [ \t\n]+                { /* ignore whitespace */ }
+\"([^\\"]|\\.)*\"       { return TOKEN_STRING;}
 [0-9]+                  { return TOKEN_NUMBER; }
 "---"                   { return TOKEN_HEADER_SEPARATOR; }
 "globals"               { return TOKEN_GLOBALS; }
@@ -46,6 +47,9 @@
 "ModI64"                { return TOKEN_ModI64; }
 "Call"                  { return TOKEN_Call; }
 "PrintTopStackI64"      { return TOKEN_PrintTopStackI64; }
+"PushLiteralString"     { return TOKEN_PushLiteralString; }
+"ConcatStrings"         { return TOKEN_ConcatStrings; }
+"PrintString"           { return TOKEN_PrintString; }
 "Exit"                  { return TOKEN_Exit; }
 
 %%
@@ -70,6 +74,11 @@ Token read_token(void) {
         token.value[0] = '\0';
         return token;
     }
+    if (token.type == TOKEN_STRING) {
+        strncpy(token.value, yytext + 1, yyleng - 2);
+        token.value[strlen(yytext) - 2] = '\0';
+        return token;
+    }
     strcpy(token.value, yytext);
     return token;
 }