Updated the lexer to pick out some more language specific grammar.

includes/lexer.h

@@ -23,8 +23,9 @@ typedef enum {
     TK_Hex,
     TK_Opcode,
     TK_Register,
-    TK_Label,
+    TK_Directive,
-    TK_Directive
+    TK_Symbol,
+    TK_Comma
 } TokenType;
 
 typedef struct {

src/lexer.c

@@ -13,6 +13,7 @@ List* GenerateTokensFromFile(const char* file_path) {
     char* line = NULL;
     size_t len = 0;
     ssize_t bytes_read;
+    List* tokens = CreateList();
 
     file = fopen(file_path, "r");
 
@@ -21,8 +22,6 @@ List* GenerateTokensFromFile(const char* file_path) {
         return NULL;
     }
 
-    //char* context;// = malloc(sizeof(char *));
-
     while((bytes_read = getline(&line, &len, file)) != -1) {
         Token* token = GetNextToken(line);
 
@@ -30,30 +29,7 @@ List* GenerateTokensFromFile(const char* file_path) {
 
             if (!token) break;
             
-            if(token->type == TK_Number)  {
+            AddListItem(token, sizeof(Token), tokens);
-                printf("Found number: '%s'\n", token->value);
-            }
-            else if (token->type == TK_Hex) {
-                printf("Hex number: '%s'\n", token->value);
-            }
-            else if (token->type == TK_Opcode) {
-                printf("Found op: '%s'\n", token->value);
-            }
-            else if (token->type == TK_Register) {
-                printf("Found Reg: '%s'\n", token->value);
-            }
-            else if(token->type == TK_Label) {
-                printf("Label: '%s'\n", token->value);
-            }
-            else if (token->type == TK_Directive) {
-                printf("Directive '%s'\n", token->value);
-            }
-            else {
-                printf("Found text: '%s'\n", token->value);
-            }
-
-            free(token->value);
-            free(token);
 
             token = GetNextToken(NULL);
         }
@@ -65,7 +41,7 @@ List* GenerateTokensFromFile(const char* file_path) {
 
     if (line) free(line);
 
-    return NULL;
+    return tokens;
 }
 
 Token* GetNextToken(char *string) {
@@ -81,32 +57,27 @@ Token* GetNextToken(char *string) {
             if (base == 16) return CreateToken(TK_Hex, string_token);
         }
 
-        //if (strcmp(string_token, ":") == 0) return CreateToken(TK_Colon, string_token);
-        //if (strcmp(string_token, ",") == 0) return CreateToken(TK_Comma, string_token);
-        if (IsOpcode(string_token)) return CreateToken(TK_Opcode, string_token);
-        if (IsRegister(string_token)) return CreateToken(TK_Register, string_token);
-
-        // char* next = SplitOnBasicGrammar(NULL);
-
-        // if (next && strcmp(next, ":") == 0) {
-        //     free(next);
-        //     return CreateToken(TK_Label, string_token);
-        // }
-
-        // if (next) free(next);
-
-        if (strcmp(".db", string_token) == 0) {
         char* next = PeekNextToken();
+
         if (next) {
-                printf("String variable name: '%s'\n", next);
+            if (strcmp(":", next) == 0) {
+                free(next);
+                free(GetToken(NULL));
+                return CreateToken(TK_Symbol, string_token);
+            }
+
             free(next);
         }
-        }
 
+        if (IsOpcode(string_token)) return CreateToken(TK_Opcode, string_token);
+        if (IsRegister(string_token)) return CreateToken(TK_Register, string_token);
+        if (strcmp(",", string_token) == 0) return CreateToken(TK_Comma, string_token);
 
         return CreateToken(TK_String, string_token);
     }
 
+    free(string_token);
+
     return NULL;
 }
 

src/main.c

@@ -21,5 +21,15 @@ int main(int argc, char* args[]) {
         return -1;
     }
     
-    GenerateTokensFromFile(args[1]);
+    List* tokens = GenerateTokensFromFile(args[1]);
+
+    for (int i = 0; i < tokens->size; i++) {
+        Token* t = (Token*) tokens->content[i];
+
+        printf("Token Type: '%d' Value: '%s'\n", t->type, t->value);
+
+        free(t->value);
+    }
+
+    DestroyList(tokens);
 }