CharField: Detect and prohibit surrogate characters

rest_framework/fields.py

@@ -35,6 +35,7 @@ from rest_framework.exceptions import ErrorDetail, ValidationError
 from rest_framework.settings import api_settings
 from rest_framework.utils import html, humanize_datetime, json, representation
 from rest_framework.utils.formatting import lazy_format
+from rest_framework.validators import ProhibitSurrogateCharactersValidator
 
 
 class empty:
@@ -784,6 +785,7 @@ class CharField(Field):
         # ProhibitNullCharactersValidator is None on Django < 2.0
         if ProhibitNullCharactersValidator is not None:
             self.validators.append(ProhibitNullCharactersValidator())
+        self.validators.append(ProhibitSurrogateCharactersValidator())
 
     def run_validation(self, data=empty):
         # Test for the empty string here so that it does not get validated,

rest_framework/validators.py

@@ -174,6 +174,17 @@ class UniqueTogetherValidator:
         )
 
 
+class ProhibitSurrogateCharactersValidator:
+    message = _('Surrogate characters are not allowed: U+{code_point:X}.')
+    code = 'surrogate_characters_not_allowed'
+
+    def __call__(self, value):
+        for surrogate_character in (ch for ch in str(value)
+                                    if 0xD800 <= ord(ch) <= 0xDFFF):
+            message = self.message.format(code_point=ord(surrogate_character))
+            raise ValidationError(message, code=self.code)
+
+
 class BaseUniqueForValidator:
     message = None
     missing_message = _('This field is required.')