diff --git a/tests/test_encoding.py b/tests/test_encoding.py
index acda49e7..b6baf444 100644
--- a/tests/test_encoding.py
+++ b/tests/test_encoding.py
@@ -11,6 +11,7 @@
 from .test_helpers import ENCODING_FACTORIES, MAX_EXAMPLES
 
 
+@pytest.mark.skip(reason="Takes a really long time to finish, but was added to reproduce a crash.")
 @pytest.mark.parametrize("make_enc", ENCODING_FACTORIES)
 def test_extremely_big_encoding(make_enc: Callable[[], tiktoken.Encoding]):
     enc = make_enc()
diff --git a/tiktoken_ext/openai_public.py b/tiktoken_ext/openai_public.py
index 330ecabb..82f99564 100644
--- a/tiktoken_ext/openai_public.py
+++ b/tiktoken_ext/openai_public.py
@@ -20,7 +20,7 @@ def gpt2():
         # The pattern in the original GPT-2 release is:
         # r"""'s|'t|'re|'ve|'m|'ll|'d| ?[\p{L}]+| ?[\p{N}]+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+"""
         # This is equivalent, but executes faster:
-        "pat_str": r"""'(?:[sdmt]|ll|ve|re)| ?\p{L}+| ?\p{N}+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+""",
+        "pat_str": r"""'(?:[sdmt]|ll|ve|re)| ?\p{L}++| ?\p{N}++| ?[^\s\p{L}\p{N}]++|\s+(?!\S)|\s++""",
         "mergeable_ranks": mergeable_ranks,
         "special_tokens": {ENDOFTEXT: 50256},
     }
@@ -34,7 +34,7 @@ def r50k_base():
     return {
         "name": "r50k_base",
         "explicit_n_vocab": 50257,
-        "pat_str": r"""'(?:[sdmt]|ll|ve|re)| ?\p{L}+| ?\p{N}+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+""",
+        "pat_str": r"""'(?:[sdmt]|ll|ve|re)| ?\p{L}++| ?\p{N}++| ?[^\s\p{L}\p{N}]++|\s+(?!\S)|\s++""",
         "mergeable_ranks": mergeable_ranks,
         "special_tokens": {ENDOFTEXT: 50256},
     }
@@ -48,7 +48,7 @@ def p50k_base():
     return {
         "name": "p50k_base",
         "explicit_n_vocab": 50281,
-        "pat_str": r"""'(?:[sdmt]|ll|ve|re)| ?\p{L}+| ?\p{N}+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+""",
+        "pat_str": r"""'(?:[sdmt]|ll|ve|re)| ?\p{L}++| ?\p{N}++| ?[^\s\p{L}\p{N}]++|\s+(?!\S)|\s++""",
         "mergeable_ranks": mergeable_ranks,
         "special_tokens": {ENDOFTEXT: 50256},
     }
@@ -62,7 +62,7 @@ def p50k_edit():
     special_tokens = {ENDOFTEXT: 50256, FIM_PREFIX: 50281, FIM_MIDDLE: 50282, FIM_SUFFIX: 50283}
     return {
         "name": "p50k_edit",
-        "pat_str": r"""'(?:[sdmt]|ll|ve|re)| ?\p{L}+| ?\p{N}+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+""",
+        "pat_str": r"""'(?:[sdmt]|ll|ve|re)| ?\p{L}++| ?\p{N}++| ?[^\s\p{L}\p{N}]++|\s+(?!\S)|\s++""",
         "mergeable_ranks": mergeable_ranks,
         "special_tokens": special_tokens,
     }
@@ -82,7 +82,7 @@ def cl100k_base():
     }
     return {
         "name": "cl100k_base",
-        "pat_str": r"""'(?i:[sdmt]|ll|ve|re)|[^\r\n\p{L}\p{N}]?+\p{L}+|\p{N}{1,3}| ?[^\s\p{L}\p{N}]++[\r\n]*|\s*[\r\n]|\s+(?!\S)|\s+""",
+        "pat_str": r"""'(?i:[sdmt]|ll|ve|re)|[^\r\n\p{L}\p{N}]?+\p{L}++|\p{N}{1,3}+| ?[^\s\p{L}\p{N}]++[\r\n]*+|\s*[\r\n]|\s+(?!\S)|\s++""",
         "mergeable_ranks": mergeable_ranks,
         "special_tokens": special_tokens,
     }