From 0de6cf5024b142cc2f1bda27eaed749227d4c6ef Mon Sep 17 00:00:00 2001
From: LaEntropiaa <aadrian887mh@gmail.com>
Date: Mon, 9 Mar 2026 11:58:55 -0600
Subject: [PATCH] Modified the structure of the lexer, now is more easy to add
 types of numbers like fractions, like i could enev consider roots,
 irrationals, complex or imaginary, that would be dope. For now only support
 for integer, we need to get this shit running

---
 include/lexer.h   |  4 ++--
 src/lexer.c       | 27 ++++++++++++++++++++++-----
 test/test_lexer.c | 27 +++++++++++++++++++++------
 3 files changed, 45 insertions(+), 13 deletions(-)

diff --git a/include/lexer.h b/include/lexer.h
index 4f3c211..0f83a53 100644
--- a/include/lexer.h
+++ b/include/lexer.h
@@ -30,6 +30,7 @@ typedef enum {
 
 typedef enum {
     LEXER_OK = 0,
+    LEXER_INT_OVERFLOW,
     LEXER_FAILED_NUMBER_CONVERSION,
     LEXER_NOT_RECOGNIZED_SYMBOL,
     LEXER_EMPTY_INPUT,
@@ -70,7 +71,6 @@ size_t ASTNodeArray_len(ASTNodeArray *arr);
 // Lexer funtions as well as few functionality
 LexerErr tokenize(const char* input, ASTNodeArray *out);
 LexerErr tokenize_number(const char* input, size_t *offset, ASTNode *out);
-LexerErr string_to_number(const char* input, size_t *offset, int64_t *number);
-void reverser_string(char* input);
+LexerErr string_to_integer(const char buf[], int64_t *number);
 
 #endif // !LEXER_H
diff --git a/src/lexer.c b/src/lexer.c
index 4663f3f..4e8bbea 100644
--- a/src/lexer.c
+++ b/src/lexer.c
@@ -112,11 +112,14 @@ size_t ASTNodeArray_len(ASTNodeArray *arr) {
     return arr->len;
 }
 
+
+
 // CURRENTLY, it only supports ints, not clear how floating
 // point is implemented but i'll figure it out
-LexerErr string_to_number(const char *input, size_t *offset, int64_t *number) {
+LexerErr tokenize_number(const char *input, size_t *offset, ASTNode *out) {
     char buf[128] = { '\0' };
     size_t buf_pos = 0;
+    bool is_integer = true; // Will later be used to differentiate fractions
 
     size_t current = *offset;
     while (isdigit(input[current])) {
@@ -128,15 +131,30 @@ LexerErr string_to_number(const char *input, size_t *offset, int64_t *number) {
         current++;
         buf_pos++;
     }
-    
+
+    ASTNode new_node;
+    if (is_integer) {
+        new_node.type = NODE_INTEGER;
+        LexerErr status = string_to_integer(buf, &new_node.data.integer);
+        if (status == LEXER_OK) {
+            *out = new_node;
+        }
+        *offset = current;
+        return status;
+    }
+
+    return LEXER_FAILED_NUMBER_CONVERSION;
+}
+
+LexerErr string_to_integer(const char *buf, int64_t *number) {
     int c = 0;
     int64_t count = 0;
     while (buf[c] != '\0') {
         
         int digit = buf[c] - '0';
 
-        if (count > (INT_MAX - digit) / 10) {
-            return LEXER_FAILED_NUMBER_CONVERSION;
+        if (count > (INT64_MAX - digit) / 10) {
+            return LEXER_INT_OVERFLOW;
         }
         count = count * 10;
         count += digit;
@@ -145,6 +163,5 @@ LexerErr string_to_number(const char *input, size_t *offset, int64_t *number) {
     }
 
     *number = count;
-    *offset = current;
     return LEXER_OK;
 }
diff --git a/test/test_lexer.c b/test/test_lexer.c
index e9d1c81..860ad5c 100644
--- a/test/test_lexer.c
+++ b/test/test_lexer.c
@@ -6,21 +6,36 @@
 #include <setjmp.h>
 #include <cmocka.h>
 
-static void test_string_to_number(void **state) {
+static void test_string_to_number_normal(void **state) {
     (void) state;
 
     char num[16] = "2333t55";
     size_t offset = 0;
-    int64_t result = 0;
-    assert_int_equal(string_to_number(num, &offset, &result), 0);
+    ASTNode result;
 
-    assert_int_equal(offset, 4);
-    assert_double_equal(result, 2333, 1e-6);
+    assert_int_equal(tokenize_number(num, &offset, &result), LEXER_OK);
+
+    assert_int_equal(offset, 4); // equal to t position in string
+    assert_int_equal(result.type, NODE_INTEGER);
+    assert_int_equal(result.data.integer, 2333);
+}
+
+static void test_string_to_number_overflow(void **state) {
+    (void) state;
+
+    // Number is INT64_MAX but with a extra 8 at the end
+    char num[32] = "92233720368547758078yy7";
+    size_t offset = 0;
+    ASTNode result;
+    assert_int_equal(tokenize_number(num, &offset, &result), LEXER_INT_OVERFLOW);
+    // Technically it can trigger a buf overflow error but obvioulsy 
+    // it will trigger int overflow error first
 }
 
 int main(void) {
     const struct CMUnitTest tests[] = {
-        cmocka_unit_test(test_string_to_number),
+        cmocka_unit_test(test_string_to_number_normal),
+        cmocka_unit_test(test_string_to_number_overflow),
     };
 
     return cmocka_run_group_tests(tests, NULL, NULL);