Merge pull request #1960 from dbarbuzzi/bugfix/1952-utils-latinify

Update utils.latinify to support Python 3

evennia/utils/tests/test_utils.py

@@ -223,3 +223,20 @@ class TestImportFunctions(TestCase):
         test_path = self._t_dir_file("invalid_filename.py")
         loaded_mod = utils.mod_import_from_path(test_path)
         self.assertIsNone(loaded_mod)
+
+
+class LatinifyTest(TestCase):
+    def setUp(self):
+        super().setUp()
+
+        self.example_str = 'It naïvely says, “plugh.”'
+        self.expected_output = 'It naively says, "plugh."'
+
+    def test_plain_string(self):
+        result = utils.latinify(self.example_str)
+        self.assertEqual(result, self.expected_output)
+
+    def test_byte_string(self):
+        byte_str = utils.to_bytes(self.example_str)
+        result = utils.latinify(byte_str)
+        self.assertEqual(result, self.expected_output)

evennia/utils/utils.py

@@ -761,7 +761,10 @@ _UNICODE_MAP = {
     "EN DASH": "-",
     "HORIZONTAL BAR": "-",
     "HORIZONTAL ELLIPSIS": "...",
+    "LEFT SINGLE QUOTATION MARK": "'",
     "RIGHT SINGLE QUOTATION MARK": "'",
+    "LEFT DOUBLE QUOTATION MARK": '"',
+    "RIGHT DOUBLE QUOTATION MARK": '"',
 }
 
 
@@ -788,10 +791,13 @@ def latinify(string, default="?", pure_ascii=False):
 
     from unicodedata import name
 
+    if isinstance(string, bytes):
+        string = string.decode("utf8")
+
     converted = []
     for unich in iter(string):
         try:
-            ch = unich.decode("ascii")
+            ch = unich.encode("utf8").decode("ascii")
         except UnicodeDecodeError:
             # deduce a latin letter equivalent from the Unicode data
             # point name; e.g., since `name(u'á') == 'LATIN SMALL