From f88cfda90aaadc7b0dc812ddace4aadc1ee7b754 Mon Sep 17 00:00:00 2001
From: Garritt McCune <glmccune@gmail.com>
Date: Mon, 31 Jan 2022 19:15:27 +0000
Subject: [PATCH] Added a dedicated function to the tokenizer for getting
 string literals.

---
 src/lexer.c     | 12 ++++++------
 src/tokenizer.c | 40 +++++++++++++++++++++++++---------------
 2 files changed, 31 insertions(+), 21 deletions(-)

diff --git a/src/lexer.c b/src/lexer.c
index fc5a1e6..530d74f 100644
--- a/src/lexer.c
+++ b/src/lexer.c
@@ -81,14 +81,14 @@ Token* GetNextToken(char *string) {
         if (IsOpcode(string_token)) return CreateToken(TK_Opcode, string_token);
         if (IsRegister(string_token)) return CreateToken(TK_Register, string_token);
 
-        char* next = SplitOnBasicGrammar(NULL);
+        // char* next = SplitOnBasicGrammar(NULL);
 
-        if (next && strcmp(next, ":") == 0) {
-            free(next);
-            return CreateToken(TK_Label, string_token);
-        }
+        // if (next && strcmp(next, ":") == 0) {
+        //     free(next);
+        //     return CreateToken(TK_Label, string_token);
+        // }
 
-        if (next) free(next);
+        // if (next) free(next);
 
         return CreateToken(TK_String, string_token);
     }
diff --git a/src/tokenizer.c b/src/tokenizer.c
index 85fa6d7..ebf02c8 100644
--- a/src/tokenizer.c
+++ b/src/tokenizer.c
@@ -1,4 +1,8 @@
 #include "../includes/tokenizer.h"
+#include <stdio.h>
+#include <string.h>
+
+void GetStringLiteral(char*, unsigned long, char**, unsigned long*);
 
 char* SplitOnBasicGrammar(char* line) {
     static char* string;
@@ -9,20 +13,12 @@ char* SplitOnBasicGrammar(char* line) {
         position = 0;
     }
 
-    char* token = calloc(1, strlen(string) + 1);
-    int parsing_string = 0;
+    unsigned long length = strlen(string);
+    char* token = calloc(1, length + 1);
+    //int parsing_string = 0;
 
-    for (int i = 0; position < strlen(string); i++, position++) {
+    for (int i = 0; position < length; i++, position++) {
         
-        if (parsing_string) {
-            if (string[position] == '\n') break;
-            if (string[position] == '"') break;
-
-            token[i] = string[position];
-
-            continue;
-        }
-
         if (string[position] == ';') break;
 
         if (string[position] == ':') {
@@ -35,9 +31,9 @@ char* SplitOnBasicGrammar(char* line) {
         }
 
         if (string[position] == '"') {
-            parsing_string = 1;
-            i--;
-            continue;
+            position++;
+            GetStringLiteral(string, length, &token, &position);
+            break;
         }
 
         if (string[position] == ' ') {
@@ -63,6 +59,20 @@ char* SplitOnBasicGrammar(char* line) {
     return token;
 }
 
+void GetStringLiteral(char* text, unsigned long length, char** token, unsigned long* position) {
+    if (!text) return;
+    if (!token) return;
+
+    for(int i = 0; *position < length; (*position)++, i++) {
+        if (text[*position] == '"') {
+            (*position)++;
+            break;
+        }
+        
+        (*token)[i] = text[*position];
+    }
+}
+
 // TokenType GetOperatorType(char c) {
 //     switch (c){
 //         case '+':