Add new input validator API functions (#1576)

Fixes #1549

JerryScript-DCO-1.0-Signed-off-by: László Langó llango.u-szeged@partner.samsung.com

jerry-core/ecma/base/ecma-helpers-string.c

@@ -151,7 +151,7 @@ ecma_new_ecma_string_from_utf8 (const lit_utf8_byte_t *string_p, /**< utf-8 stri
                                 lit_utf8_size_t string_size) /**< string size */
 {
   JERRY_ASSERT (string_p != NULL || string_size == 0);
-  JERRY_ASSERT (lit_is_cesu8_string_valid (string_p, string_size));
+  JERRY_ASSERT (lit_is_valid_cesu8_string (string_p, string_size));
 
   lit_magic_string_id_t magic_string_id = lit_is_utf8_string_magic (string_p, string_size);
 
@@ -269,7 +269,7 @@ ecma_new_ecma_string_from_utf8_converted_to_cesu8 (const lit_utf8_byte_t *string
   {
     converted_string_size += string_size;
 
-    JERRY_ASSERT (lit_is_utf8_string_valid (string_p, string_size));
+    JERRY_ASSERT (lit_is_valid_utf8_string (string_p, string_size));
 
     lit_utf8_byte_t *data_p;
 

jerry-core/ecma/builtin-objects/ecma-builtin-global.c

@@ -899,7 +899,7 @@ ecma_builtin_global_object_decode_uri_helper (ecma_value_t uri, /**< uri argumen
         }
 
         if (!is_valid
-            || !lit_is_utf8_string_valid (octets, bytes_count))
+            || !lit_is_valid_utf8_string (octets, bytes_count))
         {
           ret_value = ecma_raise_uri_error (ECMA_ERR_MSG ("Invalid UTF8 string."));
           break;
@@ -923,7 +923,7 @@ ecma_builtin_global_object_decode_uri_helper (ecma_value_t uri, /**< uri argumen
     {
       JERRY_ASSERT (output_start_p + output_size == output_char_p);
 
-      if (lit_is_cesu8_string_valid (output_start_p, output_size))
+      if (lit_is_valid_cesu8_string (output_start_p, output_size))
       {
         ecma_string_t *output_string_p = ecma_new_ecma_string_from_utf8 (output_start_p, output_size);
         ret_value = ecma_make_string_value (output_string_p);

jerry-core/jerry.c

@@ -982,7 +982,7 @@ jerry_create_object (void)
 } /* jerry_create_object */
 
 /**
- * Create string from a valid UTF8 string
+ * Create string from a valid UTF-8 string
  *
  * Note:
  *      returned value must be freed with jerry_release_value when it is no longer needed.
@@ -996,7 +996,7 @@ jerry_create_string_from_utf8 (const jerry_char_t *str_p) /**< pointer to string
 } /* jerry_create_string_from_utf8 */
 
 /**
- * Create string from a valid UTF8 string
+ * Create string from a valid UTF-8 string
  *
  * Note:
  *      returned value must be freed with jerry_release_value when it is no longer needed.
@@ -1016,7 +1016,7 @@ jerry_create_string_sz_from_utf8 (const jerry_char_t *str_p, /**< pointer to str
 } /* jerry_create_string_sz_from_utf8 */
 
 /**
- * Create string from a valid CESU8 string
+ * Create string from a valid CESU-8 string
  *
  * Note:
  *      returned value must be freed with jerry_release_value, when it is no longer needed.
@@ -1030,7 +1030,7 @@ jerry_create_string (const jerry_char_t *str_p) /**< pointer to string */
 } /* jerry_create_string */
 
 /**
- * Create string from a valid CESU8 string
+ * Create string from a valid CESU-8 string
  *
  * Note:
  *      returned value must be freed with jerry_release_value when it is no longer needed.
@@ -2006,6 +2006,34 @@ jerry_foreach_object_property (const jerry_value_t obj_val, /**< object value */
   return false;
 } /* jerry_foreach_object_property */
 
+/**
+ * Validate UTF-8 string
+ *
+ * @return true - if UTF-8 string is well-formed
+ *         false - otherwise
+ */
+bool
+jerry_is_valid_utf8_string (const jerry_char_t *utf8_buf_p, /**< UTF-8 string */
+                            jerry_size_t buf_size) /**< string size */
+{
+  return lit_is_valid_utf8_string ((lit_utf8_byte_t *) utf8_buf_p,
+                                   (lit_utf8_size_t) buf_size);
+} /* jerry_is_valid_utf8_string */
+
+/**
+ * Validate CESU-8 string
+ *
+ * @return true - if CESU-8 string is well-formed
+ *         false - otherwise
+ */
+bool
+jerry_is_valid_cesu8_string (const jerry_char_t *cesu8_buf_p, /**< CESU-8 string */
+                             jerry_size_t buf_size) /**< string size */
+{
+  return lit_is_valid_cesu8_string ((lit_utf8_byte_t *) cesu8_buf_p,
+                                    (lit_utf8_size_t) buf_size);
+} /* jerry_is_valid_cesu8_string */
+
 /**
  * @}
  */

jerry-core/jerryscript.h

@@ -329,6 +329,12 @@ void jerry_set_object_native_handle (const jerry_value_t obj_val, uintptr_t hand
 bool jerry_foreach_object_property (const jerry_value_t obj_val, jerry_object_property_foreach_t foreach_p,
                                     void *user_data_p);
 
+/**
+ * Input validator functions
+ */
+bool jerry_is_valid_utf8_string (const jerry_char_t *utf8_buf_p, jerry_size_t buf_size);
+bool jerry_is_valid_cesu8_string (const jerry_char_t *cesu8_buf_p, jerry_size_t buf_size);
+
 /**
  * Snapshot functions
  */

jerry-core/lit/lit-strings.c

@@ -28,7 +28,7 @@
  *         false otherwise
  */
 bool
-lit_is_utf8_string_valid (const lit_utf8_byte_t *utf8_buf_p, /**< utf-8 string */
+lit_is_valid_utf8_string (const lit_utf8_byte_t *utf8_buf_p, /**< utf-8 string */
                           lit_utf8_size_t buf_size) /**< string size */
 {
   lit_utf8_size_t idx = 0;
@@ -116,7 +116,7 @@ lit_is_utf8_string_valid (const lit_utf8_byte_t *utf8_buf_p, /**< utf-8 string *
   }
 
   return true;
-} /* lit_is_utf8_string_valid */
+} /* lit_is_valid_utf8_string */
 
 /**
  * Validate cesu-8 string
@@ -125,14 +125,14 @@ lit_is_utf8_string_valid (const lit_utf8_byte_t *utf8_buf_p, /**< utf-8 string *
  *         false otherwise
  */
 bool
-lit_is_cesu8_string_valid (const lit_utf8_byte_t *utf8_buf_p, /**< utf-8 string */
+lit_is_valid_cesu8_string (const lit_utf8_byte_t *cesu8_buf_p, /**< cesu-8 string */
                            lit_utf8_size_t buf_size) /**< string size */
 {
   lit_utf8_size_t idx = 0;
 
   while (idx < buf_size)
   {
-    lit_utf8_byte_t c = utf8_buf_p[idx++];
+    lit_utf8_byte_t c = cesu8_buf_p[idx++];
     if ((c & LIT_UTF8_1_BYTE_MASK) == LIT_UTF8_1_BYTE_MARKER)
     {
       continue;
@@ -166,7 +166,7 @@ lit_is_cesu8_string_valid (const lit_utf8_byte_t *utf8_buf_p, /**< utf-8 string
 
     for (lit_utf8_size_t offset = 0; offset < extra_bytes_count; ++offset)
     {
-      c = utf8_buf_p[idx + offset];
+      c = cesu8_buf_p[idx + offset];
       if ((c & LIT_UTF8_EXTRA_BYTE_MASK) != LIT_UTF8_EXTRA_BYTE_MARKER)
       {
         /* invalid continuation byte */
@@ -186,7 +186,7 @@ lit_is_cesu8_string_valid (const lit_utf8_byte_t *utf8_buf_p, /**< utf-8 string
   }
 
   return true;
-} /* lit_is_cesu8_string_valid */
+} /* lit_is_valid_cesu8_string */
 
 /**
  * Check if the code point is UTF-16 low surrogate

jerry-core/lit/lit-strings.h

@@ -85,8 +85,8 @@
 #define LIT_UTF8_FIRST_BYTE_MAX LIT_UTF8_5_BYTE_MARKER
 
 /* validation */
-bool lit_is_utf8_string_valid (const lit_utf8_byte_t *utf8_buf_p, lit_utf8_size_t buf_size);
-bool lit_is_cesu8_string_valid (const lit_utf8_byte_t *utf8_buf_p, lit_utf8_size_t buf_size);
+bool lit_is_valid_utf8_string (const lit_utf8_byte_t *utf8_buf_p, lit_utf8_size_t buf_size);
+bool lit_is_valid_cesu8_string (const lit_utf8_byte_t *cesu8_buf_p, lit_utf8_size_t buf_size);
 
 /* checks */
 bool lit_is_code_point_utf16_low_surrogate (lit_code_point_t code_point);