Added unit tests for String data type and updated CI

.github/workflows/clang-build.yml

@@ -16,7 +16,7 @@ jobs:
 
       - name: Run unit tests
         run: |
-          ./test_vector && ./test_map && ./test_bigint
+          ./test_vector && ./test_map && ./test_bigint && ./test_string
 
       - name: Run benchmarks
         run: |

.github/workflows/gcc-build.yml

@@ -13,7 +13,7 @@ jobs:
 
       - name: Run unit tests
         run: |
-          ./test_vector && ./test_map && ./test_bigint
+          ./test_vector && ./test_map && ./test_bigint && ./test_string
 
       - name: Run benchmarks
         run: |

Makefile

@@ -17,6 +17,7 @@ TARGET = usage
 TEST_V_TARGET = test_vector
 TEST_M_TARGET = test_map
 TEST_B_TARGET = test_bigint
+TEST_S_TARGET = test_string
 BENCH_TARGET = benchmark_datum
 
 LIB_OBJS = $(OBJ_DIR)/vector.o $(OBJ_DIR)/map.o $(OBJ_DIR)/bigint.o $(OBJ_DIR)/string.o
@@ -24,7 +25,7 @@ PROG_OBJS = $(OBJ_DIR)/usage.o
 
 .PHONY: all clean
 
-all: $(TARGET) $(TEST_V_TARGET) $(TEST_M_TARGET) $(TEST_B_TARGET) $(BENCH_TARGET)
+all: $(TARGET) $(TEST_V_TARGET) $(TEST_M_TARGET) $(TEST_B_TARGET) $(TEST_S_TARGET) $(BENCH_TARGET)
 bench: $(BENCH_TARGET)
 
 $(TARGET): $(PROG_OBJS) $(LIB_OBJS)
@@ -39,6 +40,9 @@ $(TEST_M_TARGET): $(OBJ_DIR)/test_map.o $(OBJ_DIR)/map.o
 $(TEST_B_TARGET): $(OBJ_DIR)/test_bigint.o $(OBJ_DIR)/bigint.o $(OBJ_DIR)/vector.o
 	$(CC) $(CFLAGS) -o $@ $^
 
+$(TEST_S_TARGET): $(OBJ_DIR)/test_string.o $(OBJ_DIR)/string.o $(OBJ_DIR)/vector.o
+	$(CC) $(CFLAGS) -o $@ $^
+
 $(OBJ_DIR)/%.o: $(SRC_DIR)/%.c | $(OBJ_DIR)
 	$(CC) $(CFLAGS) -c -o $@ $<
 
@@ -65,4 +69,4 @@ $(BENCH_OBJ_DIR):
 	mkdir -p $(BENCH_OBJ_DIR)
 
 clean:
-	rm -rf $(OBJ_DIR) $(BENCH_OBJ_DIR) $(TARGET) $(TEST_V_TARGET) $(TEST_M_TARGET) $(TEST_B_TARGET) $(BENCH_TARGET)
+	rm -rf $(OBJ_DIR) $(BENCH_OBJ_DIR) $(TARGET) $(TEST_V_TARGET) $(TEST_M_TARGET) $(TEST_B_TARGET) $(TEST_S_TARGET) $(BENCH_TARGET)

src/string.c

@@ -451,13 +451,20 @@ string_result_t string_set_at(string_t *str, size_t position, const char *utf8_c
 
     int new_len;
 
-    if (str == NULL || position >= str->char_count || utf8_is_char_valid(utf8_char, &new_len) == 0) {
+    if (str == NULL || utf8_is_char_valid(utf8_char, &new_len) == 0) {
         result.status = STRING_ERR_INVALID;
         SET_MSG(result, "Invalid index or character");
 
         return result;
     }
 
+    if (position >= str->char_count) {
+        result.status = STRING_ERR_OVERFLOW;
+        SET_MSG(result, "Index out of bounds");
+
+        return result;
+    }
+
     char *pos = str->data;
     for (size_t idx = 0; idx < position; idx++) {
         pos += utf8_char_len((unsigned char)*pos);

tests/test_string.c

@@ -0,0 +1,153 @@
+/*
+ * Unit tests for String data type
+*/
+
+#define TEST(NAME) do { \
+    printf("Running test_%s...", #NAME); \
+    test_##NAME(); \
+    printf(" PASSED\n"); \
+} while(0)
+
+#include <stdio.h>
+#include <assert.h>
+#include <string.h>
+
+#include "../src/string.h"
+
+// Test string creation
+void test_string_new(void) {
+    string_result_t res = string_new("hello");
+
+    assert(res.status == STRING_OK);
+    assert(res.value.string != NULL);
+    assert(strcmp(res.value.string->data, "hello") == 0);
+    assert(string_len(res.value.string) == 5);
+    assert(res.value.string->byte_size == 5);
+
+    string_destroy(res.value.string);
+}
+
+// Test empty string
+void test_string_new_empty(void) {
+    string_result_t res = string_new("");
+
+    assert(res.status == STRING_OK);
+    assert(string_len(res.value.string) == 0);
+    assert(res.value.string->byte_size == 0);
+    assert(res.value.string->data[0] == '\0');
+
+    string_destroy(res.value.string);
+}
+
+// Test string concatenation
+void test_string_concat(void) {
+    string_t *str1 = string_new("Foo").value.string;
+    string_t *str2 = string_new(" Bar").value.string;
+
+    string_result_t res = string_concat(str1, str2);
+    assert(res.status == STRING_OK);
+    assert(strcmp(res.value.string->data, "Foo Bar") == 0);
+    assert(string_len(res.value.string) == 7);
+
+    string_destroy(str1);
+    string_destroy(str2);
+    string_destroy(res.value.string);
+}
+
+// Test case-insensitive and sensitive comparison
+void test_string_eq(void) {
+    string_t *str1 = string_new("Foo").value.string;
+    string_t *str2 = string_new("foo").value.string;
+
+    // Case sensitive comparison should be false
+    assert(string_eq(str1, str2, true).value.is_equ == false);
+    // Case insensitive comparison should be true
+    assert(string_eq(str1, str2, false).value.is_equ == true);
+
+    string_destroy(str1);
+    string_destroy(str2);
+}
+
+// Test string reverse using UTF-8 symbols
+void test_string_reverse_utf8(void) {
+    string_t *str = string_new("A🌍Z").value.string;
+
+    string_result_t res = string_reverse(str);
+    
+    assert(res.status == STRING_OK);
+    assert(string_len(res.value.string) == 3);
+    assert(strcmp(res.value.string->data, "Z🌍A") == 0);
+    assert(string_len(res.value.string) == 3);
+
+    string_destroy(str);
+    string_destroy(res.value.string);
+}
+
+// Test mutation of UTF-8 symbol
+void test_string_set_at(void) {
+    string_t *str = string_new("ABC").value.string;
+
+    // Replace 'B' with emoji
+    string_result_t res = string_set_at(str, 1, "😆");
+    assert(res.status == STRING_OK);
+    assert(strcmp(str->data, "A😆C") == 0);
+    assert(string_len(str) == 3);
+    assert(str->byte_size == 6); // that is: A (1B) + emoji (4B) + C (1B)
+
+    string_destroy(str);
+}
+
+// Test mutation with overflow
+void test_string_set_at_overflow(void) {
+    string_t *str = string_new("ABC").value.string;
+
+    string_result_t res = string_set_at(str, 10, "a");
+    assert(res.status == STRING_ERR_OVERFLOW);
+
+    string_destroy(str);
+}
+
+// Test whitespace trimming
+void test_string_trim(void) {
+    string_t *str = string_new("   \t   Foo Bar \n    ").value.string;
+
+    string_result_t res = string_trim(str);
+    assert(res.status == STRING_OK);
+    assert(strcmp(res.value.string->data, "Foo Bar") == 0);
+
+    string_destroy(str);
+    string_destroy(res.value.string);
+}
+
+// Test string splitting into an array
+void test_string_split(void) {
+    string_t *str = string_new("Red,Green,Blue").value.string;
+
+    string_result_t res = string_split(str, ",");
+    assert(res.status == STRING_OK);
+    assert(res.value.split.count == 3);
+
+    assert(strcmp(res.value.split.strings[0]->data, "Red") == 0);
+    assert(strcmp(res.value.split.strings[1]->data, "Green") == 0);
+    assert(strcmp(res.value.split.strings[2]->data, "Blue") == 0);
+
+    string_split_destroy(res.value.split.strings, res.value.split.count);
+    string_destroy(str);
+}
+
+int main(void) {
+    printf("=== Running Vector unit tests ===\n\n");
+
+    TEST(string_new);
+    TEST(string_new_empty);
+    TEST(string_concat);
+    TEST(string_eq);
+    TEST(string_reverse_utf8);
+    TEST(string_set_at);
+    TEST(string_set_at_overflow);
+    TEST(string_trim);
+    TEST(string_split);
+
+    printf("\n=== All tests passed! ===\n");
+    return 0;
+}