Sync with Tomli

Author: hukkin

Doc/library/tomllib.rst

@@ -44,8 +44,7 @@ This module defines the following functions:
    float to be decoded.  By default, this is equivalent to ``float(num_str)``.
    This can be used to use another datatype or parser for TOML floats
    (e.g. :class:`decimal.Decimal`). The callable must not return a
-   :class:`dict`, a :class:`list`, or anything that has the ``append``
-   attribute. These illegal types produce undefined behavior.
+   :class:`dict` or a :class:`list`, else a :exc:`ValueError` is raised.
 
    A :exc:`TOMLDecodeError` will be raised on an invalid TOML document.
 

Lib/test/test_tomllib/test_error.py

@@ -41,3 +41,17 @@ def test_invalid_char_quotes(self):
 
     def test_module_name(self):
         self.assertEqual(tomllib.TOMLDecodeError().__module__, tomllib.__name__)
+
+    def test_invalid_parse_float(self):
+        def dict_returner(s: str) -> dict:
+            return {}
+
+        def list_returner(s: str) -> list:
+            return []
+
+        for invalid_parse_float in (dict_returner, list_returner):
+            with self.assertRaises(ValueError) as exc_info:
+                tomllib.loads("f=0.1", parse_float=invalid_parse_float)
+            self.assertEqual(
+                str(exc_info.exception), "parse_float must not return dicts or lists"
+            )

Lib/tomllib/_parser.py

@@ -75,6 +75,7 @@ def loads(s: str, /, *, parse_float: ParseFloat = float) -> dict[str, Any]:  # n
     pos = 0
     out = Output(NestedDict(), Flags())
     header: Key = ()
+    parse_float = make_safe_parse_float(parse_float)
 
     # Parse one statement at a time
     # (typically means one line in TOML source)
@@ -216,10 +217,9 @@ def append_nest_to_list(self, key: Key) -> None:
         last_key = key[-1]
         if last_key in cont:
             list_ = cont[last_key]
-            try:
-                list_.append({})
-            except AttributeError:
+            if not isinstance(list_, list):
                 raise KeyError("An object other than list found behind this key")
+            list_.append({})
         else:
             cont[last_key] = [{}]
 
@@ -668,3 +668,24 @@ def coord_repr(src: str, pos: Pos) -> str:
 
 def is_unicode_scalar_value(codepoint: int) -> bool:
     return (0 <= codepoint <= 55295) or (57344 <= codepoint <= 1114111)
+
+
+def make_safe_parse_float(parse_float: ParseFloat) -> ParseFloat:
+    """A decorator to make `parse_float` safe.
+
+    `parse_float` must not return dicts or lists, because these types
+    would be mixed with parsed TOML tables and arrays, thus confusing
+    the parser. The returned decorated callable raises `ValueError`
+    instead of returning illegal types.
+    """
+    # The default `float` callable never returns illegal types. Optimize it.
+    if parse_float is float:  # type: ignore[comparison-overlap]
+        return float
+
+    def safe_parse_float(float_str: str) -> Any:
+        float_value = parse_float(float_str)
+        if isinstance(float_value, (dict, list)):
+            raise ValueError("parse_float must not return dicts or lists")
+        return float_value
+
+    return safe_parse_float