Update tomllib from 3.14.3 (#7048)

Lib/test/support/__init__.py

@@ -1739,6 +1739,26 @@ def skip_if_pgo_task(test):
     return test if ok else unittest.skip(msg)(test)
 
 
+# XXX: RUSTPYTHON; Taken from 3.14.3
+def skip_if_unlimited_stack_size(test):
+    """Skip decorator for tests not run when an unlimited stack size is configured.
+
+    Tests using support.infinite_recursion([...]) may otherwise run into
+    an infinite loop, running until the memory on the system is filled and
+    crashing due to OOM.
+
+    See https://github.com/python/cpython/issues/143460.
+    """
+    if is_emscripten or is_wasi or os.name == "nt":
+        return test
+
+    import resource
+    curlim, maxlim = resource.getrlimit(resource.RLIMIT_STACK)
+    unlimited_stack_size_cond = curlim == maxlim and curlim in (-1, 0xFFFF_FFFF_FFFF_FFFF)
+    reason = "Not run due to unlimited stack size"
+    return unittest.skipIf(unlimited_stack_size_cond, reason)(test)
+
+
 def detect_api_mismatch(ref_api, other_api, *, ignore=()):
     """Returns the set of items in ref_api not in other_api, except for a
     defined list of items to be ignored in this check.

Lib/test/test_tomllib/test_error.py

@@ -39,8 +39,19 @@ class TestError(unittest.TestCase):
             tomllib.loads("v = '\n'")
         self.assertTrue(" '\\n' " in str(exc_info.exception))
 
+    def test_type_error(self):
+        with self.assertRaises(TypeError) as exc_info:
+            tomllib.loads(b"v = 1")  # type: ignore[arg-type]
+        self.assertEqual(str(exc_info.exception), "Expected str object, not 'bytes'")
+
+        with self.assertRaises(TypeError) as exc_info:
+            tomllib.loads(False)  # type: ignore[arg-type]
+        self.assertEqual(str(exc_info.exception), "Expected str object, not 'bool'")
+
     def test_module_name(self):
-        self.assertEqual(tomllib.TOMLDecodeError().__module__, tomllib.__name__)
+        self.assertEqual(
+            tomllib.TOMLDecodeError("", "", 0).__module__, tomllib.__name__
+        )
 
     def test_invalid_parse_float(self):
         def dict_returner(s: str) -> dict:
@@ -55,3 +66,33 @@ class TestError(unittest.TestCase):
             self.assertEqual(
                 str(exc_info.exception), "parse_float must not return dicts or lists"
             )
+
+    def test_deprecated_tomldecodeerror(self):
+        for args in [
+            (),
+            ("err msg",),
+            (None,),
+            (None, "doc"),
+            ("err msg", None),
+            (None, "doc", None),
+            ("err msg", "doc", None),
+            ("one", "two", "three", "four"),
+            ("one", "two", 3, "four", "five"),
+        ]:
+            with self.assertWarns(DeprecationWarning):
+                e = tomllib.TOMLDecodeError(*args)  # type: ignore[arg-type]
+            self.assertEqual(e.args, args)
+
+    def test_tomldecodeerror(self):
+        msg = "error parsing"
+        doc = "v=1\n[table]\nv='val'"
+        pos = 13
+        formatted_msg = "error parsing (at line 3, column 2)"
+        e = tomllib.TOMLDecodeError(msg, doc, pos)
+        self.assertEqual(e.args, (formatted_msg,))
+        self.assertEqual(str(e), formatted_msg)
+        self.assertEqual(e.msg, msg)
+        self.assertEqual(e.doc, doc)
+        self.assertEqual(e.pos, pos)
+        self.assertEqual(e.lineno, 3)
+        self.assertEqual(e.colno, 2)

Lib/test/test_tomllib/test_misc.py

@@ -5,6 +5,7 @@
 import copy
 import datetime
 from decimal import Decimal as D
+import importlib
 from pathlib import Path
 import sys
 import tempfile
@@ -92,6 +93,7 @@ class TestMiscellaneous(unittest.TestCase):
         }
         self.assertEqual(obj_copy, expected_obj)
 
+    @support.skip_if_unlimited_stack_size
     def test_inline_array_recursion_limit(self):
         with support.infinite_recursion(max_depth=100):
             available = support.get_recursion_available()
@@ -103,6 +105,7 @@ class TestMiscellaneous(unittest.TestCase):
                 recursive_array_toml = "arr = " + nest_count * "[" + nest_count * "]"
                 tomllib.loads(recursive_array_toml)
 
+    @support.skip_if_unlimited_stack_size
     def test_inline_table_recursion_limit(self):
         with support.infinite_recursion(max_depth=100):
             available = support.get_recursion_available()
@@ -113,3 +116,11 @@ class TestMiscellaneous(unittest.TestCase):
                               nest_count=nest_count):
                 recursive_table_toml = nest_count * "key = {" + nest_count * "}"
                 tomllib.loads(recursive_table_toml)
+
+    def test_types_import(self):
+        """Test that `_types` module runs.
+
+        The module is for type annotations only, so it is otherwise
+        never imported by tests.
+        """
+        importlib.import_module(f"{tomllib.__name__}._types")

Lib/tomllib/_parser.py

@@ -4,10 +4,7 @@
 
 from __future__ import annotations
 
-from collections.abc import Iterable
-import string
 from types import MappingProxyType
-from typing import Any, BinaryIO, NamedTuple
 
 from ._re import (
     RE_DATETIME,
@@ -17,7 +14,13 @@ from ._re import (
     match_to_localtime,
     match_to_number,
 )
-from ._types import Key, ParseFloat, Pos
+
+TYPE_CHECKING = False
+if TYPE_CHECKING:
+    from collections.abc import Iterable
+    from typing import IO, Any
+
+    from ._types import Key, ParseFloat, Pos
 
 ASCII_CTRL = frozenset(chr(i) for i in range(32)) | frozenset(chr(127))
 
@@ -33,9 +36,11 @@ ILLEGAL_COMMENT_CHARS = ILLEGAL_BASIC_STR_CHARS
 
 TOML_WS = frozenset(" \t")
 TOML_WS_AND_NEWLINE = TOML_WS | frozenset("\n")
-BARE_KEY_CHARS = frozenset(string.ascii_letters + string.digits + "-_")
+BARE_KEY_CHARS = frozenset(
+    "abcdefghijklmnopqrstuvwxyz" "ABCDEFGHIJKLMNOPQRSTUVWXYZ" "0123456789" "-_"
+)
 KEY_INITIAL_CHARS = BARE_KEY_CHARS | frozenset("\"'")
-HEXDIGIT_CHARS = frozenset(string.hexdigits)
+HEXDIGIT_CHARS = frozenset("abcdef" "ABCDEF" "0123456789")
 
 BASIC_STR_ESCAPE_REPLACEMENTS = MappingProxyType(
     {
@@ -50,11 +55,73 @@ BASIC_STR_ESCAPE_REPLACEMENTS = MappingProxyType(
 )
 
 
+class DEPRECATED_DEFAULT:
+    """Sentinel to be used as default arg during deprecation
+    period of TOMLDecodeError's free-form arguments."""
+
+
 class TOMLDecodeError(ValueError):
-    """An error raised if a document is not valid TOML."""
+    """An error raised if a document is not valid TOML.
+
+    Adds the following attributes to ValueError:
+    msg: The unformatted error message
+    doc: The TOML document being parsed
+    pos: The index of doc where parsing failed
+    lineno: The line corresponding to pos
+    colno: The column corresponding to pos
+    """
+
+    def __init__(
+        self,
+        msg: str = DEPRECATED_DEFAULT,  # type: ignore[assignment]
+        doc: str = DEPRECATED_DEFAULT,  # type: ignore[assignment]
+        pos: Pos = DEPRECATED_DEFAULT,  # type: ignore[assignment]
+        *args: Any,
+    ):
+        if (
+            args
+            or not isinstance(msg, str)
+            or not isinstance(doc, str)
+            or not isinstance(pos, int)
+        ):
+            import warnings
+
+            warnings.warn(
+                "Free-form arguments for TOMLDecodeError are deprecated. "
+                "Please set 'msg' (str), 'doc' (str) and 'pos' (int) arguments only.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+            if pos is not DEPRECATED_DEFAULT:  # type: ignore[comparison-overlap]
+                args = pos, *args
+            if doc is not DEPRECATED_DEFAULT:  # type: ignore[comparison-overlap]
+                args = doc, *args
+            if msg is not DEPRECATED_DEFAULT:  # type: ignore[comparison-overlap]
+                args = msg, *args
+            ValueError.__init__(self, *args)
+            return
+
+        lineno = doc.count("\n", 0, pos) + 1
+        if lineno == 1:
+            colno = pos + 1
+        else:
+            colno = pos - doc.rindex("\n", 0, pos)
+
+        if pos >= len(doc):
+            coord_repr = "end of document"
+        else:
+            coord_repr = f"line {lineno}, column {colno}"
+        errmsg = f"{msg} (at {coord_repr})"
+        ValueError.__init__(self, errmsg)
+
+        self.msg = msg
+        self.doc = doc
+        self.pos = pos
+        self.lineno = lineno
+        self.colno = colno
 
 
-def load(fp: BinaryIO, /, *, parse_float: ParseFloat = float) -> dict[str, Any]:
+def load(fp: IO[bytes], /, *, parse_float: ParseFloat = float) -> dict[str, Any]:
     """Parse TOML from a binary file object."""
     b = fp.read()
     try:
@@ -71,9 +138,14 @@ def loads(s: str, /, *, parse_float: ParseFloat = float) -> dict[str, Any]:  # n
 
     # The spec allows converting "\r\n" to "\n", even in string
     # literals. Let's do so to simplify parsing.
-    src = s.replace("\r\n", "\n")
+    try:
+        src = s.replace("\r\n", "\n")
+    except (AttributeError, TypeError):
+        raise TypeError(
+            f"Expected str object, not '{type(s).__qualname__}'"
+        ) from None
     pos = 0
-    out = Output(NestedDict(), Flags())
+    out = Output()
     header: Key = ()
     parse_float = make_safe_parse_float(parse_float)
 
@@ -113,7 +185,7 @@ def loads(s: str, /, *, parse_float: ParseFloat = float) -> dict[str, Any]:  # n
                 pos, header = create_dict_rule(src, pos, out)
             pos = skip_chars(src, pos, TOML_WS)
         elif char != "#":
-            raise suffixed_err(src, pos, "Invalid statement")
+            raise TOMLDecodeError("Invalid statement", src, pos)
 
         # 3. Skip comment
         pos = skip_comment(src, pos)
@@ -124,8 +196,8 @@ def loads(s: str, /, *, parse_float: ParseFloat = float) -> dict[str, Any]:  # n
         except IndexError:
             break
         if char != "\n":
-            raise suffixed_err(
-                src, pos, "Expected newline or end of document after a statement"
+            raise TOMLDecodeError(
+                "Expected newline or end of document after a statement", src, pos
             )
         pos += 1
 
@@ -224,9 +296,10 @@ class NestedDict:
             cont[last_key] = [{}]
 
 
-class Output(NamedTuple):
-    data: NestedDict
-    flags: Flags
+class Output:
+    def __init__(self) -> None:
+        self.data = NestedDict()
+        self.flags = Flags()
 
 
 def skip_chars(src: str, pos: Pos, chars: Iterable[str]) -> Pos:
@@ -251,12 +324,12 @@ def skip_until(
     except ValueError:
         new_pos = len(src)
         if error_on_eof:
-            raise suffixed_err(src, new_pos, f"Expected {expect!r}") from None
+            raise TOMLDecodeError(f"Expected {expect!r}", src, new_pos) from None
 
     if not error_on.isdisjoint(src[pos:new_pos]):
         while src[pos] not in error_on:
             pos += 1
-        raise suffixed_err(src, pos, f"Found invalid character {src[pos]!r}")
+        raise TOMLDecodeError(f"Found invalid character {src[pos]!r}", src, pos)
     return new_pos
 
 
@@ -287,15 +360,17 @@ def create_dict_rule(src: str, pos: Pos, out: Output) -> tuple[Pos, Key]:
     pos, key = parse_key(src, pos)
 
     if out.flags.is_(key, Flags.EXPLICIT_NEST) or out.flags.is_(key, Flags.FROZEN):
-        raise suffixed_err(src, pos, f"Cannot declare {key} twice")
+        raise TOMLDecodeError(f"Cannot declare {key} twice", src, pos)
     out.flags.set(key, Flags.EXPLICIT_NEST, recursive=False)
     try:
         out.data.get_or_create_nest(key)
     except KeyError:
-        raise suffixed_err(src, pos, "Cannot overwrite a value") from None
+        raise TOMLDecodeError("Cannot overwrite a value", src, pos) from None
 
     if not src.startswith("]", pos):
-        raise suffixed_err(src, pos, "Expected ']' at the end of a table declaration")
+        raise TOMLDecodeError(
+            "Expected ']' at the end of a table declaration", src, pos
+        )
     return pos + 1, key
 
 
@@ -305,7 +380,7 @@ def create_list_rule(src: str, pos: Pos, out: Output) -> tuple[Pos, Key]:
     pos, key = parse_key(src, pos)
 
     if out.flags.is_(key, Flags.FROZEN):
-        raise suffixed_err(src, pos, f"Cannot mutate immutable namespace {key}")
+        raise TOMLDecodeError(f"Cannot mutate immutable namespace {key}", src, pos)
     # Free the namespace now that it points to another empty list item...
     out.flags.unset_all(key)
     # ...but this key precisely is still prohibited from table declaration
@@ -313,10 +388,12 @@ def create_list_rule(src: str, pos: Pos, out: Output) -> tuple[Pos, Key]:
     try:
         out.data.append_nest_to_list(key)
     except KeyError:
-        raise suffixed_err(src, pos, "Cannot overwrite a value") from None
+        raise TOMLDecodeError("Cannot overwrite a value", src, pos) from None
 
     if not src.startswith("]]", pos):
-        raise suffixed_err(src, pos, "Expected ']]' at the end of an array declaration")
+        raise TOMLDecodeError(
+            "Expected ']]' at the end of an array declaration", src, pos
+        )
     return pos + 2, key
 
 
@@ -331,22 +408,22 @@ def key_value_rule(
     for cont_key in relative_path_cont_keys:
         # Check that dotted key syntax does not redefine an existing table
         if out.flags.is_(cont_key, Flags.EXPLICIT_NEST):
-            raise suffixed_err(src, pos, f"Cannot redefine namespace {cont_key}")
+            raise TOMLDecodeError(f"Cannot redefine namespace {cont_key}", src, pos)
         # Containers in the relative path can't be opened with the table syntax or
         # dotted key/value syntax in following table sections.
         out.flags.add_pending(cont_key, Flags.EXPLICIT_NEST)
 
     if out.flags.is_(abs_key_parent, Flags.FROZEN):
-        raise suffixed_err(
-            src, pos, f"Cannot mutate immutable namespace {abs_key_parent}"
+        raise TOMLDecodeError(
+            f"Cannot mutate immutable namespace {abs_key_parent}", src, pos
         )
 
     try:
         nest = out.data.get_or_create_nest(abs_key_parent)
     except KeyError:
-        raise suffixed_err(src, pos, "Cannot overwrite a value") from None
+        raise TOMLDecodeError("Cannot overwrite a value", src, pos) from None
     if key_stem in nest:
-        raise suffixed_err(src, pos, "Cannot overwrite a value")
+        raise TOMLDecodeError("Cannot overwrite a value", src, pos)
     # Mark inline table and array namespaces recursively immutable
     if isinstance(value, (dict, list)):
         out.flags.set(header + key, Flags.FROZEN, recursive=True)
@@ -363,7 +440,7 @@ def parse_key_value_pair(
     except IndexError:
         char = None
     if char != "=":
-        raise suffixed_err(src, pos, "Expected '=' after a key in a key/value pair")
+        raise TOMLDecodeError("Expected '=' after a key in a key/value pair", src, pos)
     pos += 1
     pos = skip_chars(src, pos, TOML_WS)
     pos, value = parse_value(src, pos, parse_float)
@@ -401,7 +478,7 @@ def parse_key_part(src: str, pos: Pos) -> tuple[Pos, str]:
         return parse_literal_str(src, pos)
     if char == '"':
         return parse_one_line_basic_str(src, pos)
-    raise suffixed_err(src, pos, "Invalid initial character for a key part")
+    raise TOMLDecodeError("Invalid initial character for a key part", src, pos)
 
 
 def parse_one_line_basic_str(src: str, pos: Pos) -> tuple[Pos, str]:
@@ -425,7 +502,7 @@ def parse_array(src: str, pos: Pos, parse_float: ParseFloat) -> tuple[Pos, list[
         if c == "]":
             return pos + 1, array
         if c != ",":
-            raise suffixed_err(src, pos, "Unclosed array")
+            raise TOMLDecodeError("Unclosed array", src, pos)
         pos += 1
 
         pos = skip_comments_and_array_ws(src, pos)
@@ -445,20 +522,20 @@ def parse_inline_table(src: str, pos: Pos, parse_float: ParseFloat) -> tuple[Pos
         pos, key, value = parse_key_value_pair(src, pos, parse_float)
         key_parent, key_stem = key[:-1], key[-1]
         if flags.is_(key, Flags.FROZEN):
-            raise suffixed_err(src, pos, f"Cannot mutate immutable namespace {key}")
+            raise TOMLDecodeError(f"Cannot mutate immutable namespace {key}", src, pos)
         try:
             nest = nested_dict.get_or_create_nest(key_parent, access_lists=False)
         except KeyError:
-            raise suffixed_err(src, pos, "Cannot overwrite a value") from None
+            raise TOMLDecodeError("Cannot overwrite a value", src, pos) from None
         if key_stem in nest:
-            raise suffixed_err(src, pos, f"Duplicate inline table key {key_stem!r}")
+            raise TOMLDecodeError(f"Duplicate inline table key {key_stem!r}", src, pos)
         nest[key_stem] = value
         pos = skip_chars(src, pos, TOML_WS)
         c = src[pos : pos + 1]
         if c == "}":
             return pos + 1, nested_dict.dict
         if c != ",":
-            raise suffixed_err(src, pos, "Unclosed inline table")
+            raise TOMLDecodeError("Unclosed inline table", src, pos)
         if isinstance(value, (dict, list)):
             flags.set(key, Flags.FROZEN, recursive=True)
         pos += 1
@@ -480,7 +557,7 @@ def parse_basic_str_escape(
             except IndexError:
                 return pos, ""
             if char != "\n":
-                raise suffixed_err(src, pos, "Unescaped '\\' in a string")
+                raise TOMLDecodeError("Unescaped '\\' in a string", src, pos)
             pos += 1
         pos = skip_chars(src, pos, TOML_WS_AND_NEWLINE)
         return pos, ""
@@ -491,7 +568,7 @@ def parse_basic_str_escape(
     try:
         return pos, BASIC_STR_ESCAPE_REPLACEMENTS[escape_id]
     except KeyError:
-        raise suffixed_err(src, pos, "Unescaped '\\' in a string") from None
+        raise TOMLDecodeError("Unescaped '\\' in a string", src, pos) from None
 
 
 def parse_basic_str_escape_multiline(src: str, pos: Pos) -> tuple[Pos, str]:
@@ -501,11 +578,13 @@ def parse_basic_str_escape_multiline(src: str, pos: Pos) -> tuple[Pos, str]:
 def parse_hex_char(src: str, pos: Pos, hex_len: int) -> tuple[Pos, str]:
     hex_str = src[pos : pos + hex_len]
     if len(hex_str) != hex_len or not HEXDIGIT_CHARS.issuperset(hex_str):
-        raise suffixed_err(src, pos, "Invalid hex value")
+        raise TOMLDecodeError("Invalid hex value", src, pos)
     pos += hex_len
     hex_int = int(hex_str, 16)
     if not is_unicode_scalar_value(hex_int):
-        raise suffixed_err(src, pos, "Escaped character is not a Unicode scalar value")
+        raise TOMLDecodeError(
+            "Escaped character is not a Unicode scalar value", src, pos
+        )
     return pos, chr(hex_int)
 
 
@@ -562,7 +641,7 @@ def parse_basic_str(src: str, pos: Pos, *, multiline: bool) -> tuple[Pos, str]:
         try:
             char = src[pos]
         except IndexError:
-            raise suffixed_err(src, pos, "Unterminated string") from None
+            raise TOMLDecodeError("Unterminated string", src, pos) from None
         if char == '"':
             if not multiline:
                 return pos + 1, result + src[start_pos:pos]
@@ -577,7 +656,7 @@ def parse_basic_str(src: str, pos: Pos, *, multiline: bool) -> tuple[Pos, str]:
             start_pos = pos
             continue
         if char in error_on:
-            raise suffixed_err(src, pos, f"Illegal character {char!r}")
+            raise TOMLDecodeError(f"Illegal character {char!r}", src, pos)
         pos += 1
 
 
@@ -625,7 +704,7 @@ def parse_value(  # noqa: C901
         try:
             datetime_obj = match_to_datetime(datetime_match)
         except ValueError as e:
-            raise suffixed_err(src, pos, "Invalid date or datetime") from e
+            raise TOMLDecodeError("Invalid date or datetime", src, pos) from e
         return datetime_match.end(), datetime_obj
     localtime_match = RE_LOCALTIME.match(src, pos)
     if localtime_match:
@@ -646,24 +725,7 @@ def parse_value(  # noqa: C901
     if first_four in {"-inf", "+inf", "-nan", "+nan"}:
         return pos + 4, parse_float(first_four)
 
-    raise suffixed_err(src, pos, "Invalid value")
-
-
-def suffixed_err(src: str, pos: Pos, msg: str) -> TOMLDecodeError:
-    """Return a `TOMLDecodeError` where error message is suffixed with
-    coordinates in source."""
-
-    def coord_repr(src: str, pos: Pos) -> str:
-        if pos >= len(src):
-            return "end of document"
-        line = src.count("\n", 0, pos) + 1
-        if line == 1:
-            column = pos + 1
-        else:
-            column = pos - src.rindex("\n", 0, pos)
-        return f"line {line}, column {column}"
-
-    return TOMLDecodeError(f"{msg} (at {coord_repr(src, pos)})")
+    raise TOMLDecodeError("Invalid value", src, pos)
 
 
 def is_unicode_scalar_value(codepoint: int) -> bool:

Lib/tomllib/_re.py

@@ -7,9 +7,12 @@ from __future__ import annotations
 from datetime import date, datetime, time, timedelta, timezone, tzinfo
 from functools import lru_cache
 import re
-from typing import Any
 
-from ._types import ParseFloat
+TYPE_CHECKING = False
+if TYPE_CHECKING:
+    from typing import Any
+
+    from ._types import ParseFloat
 
 # E.g.
 # - 00:32:00.999999
@@ -84,6 +87,9 @@ def match_to_datetime(match: re.Match[str]) -> datetime | date:
     return datetime(year, month, day, hour, minute, sec, micros, tzinfo=tz)
 
 
+# No need to limit cache size. This is only ever called on input
+# that matched RE_DATETIME, so there is an implicit bound of
+# 24 (hours) * 60 (minutes) * 2 (offset direction) = 2880.
 @lru_cache(maxsize=None)
 def cached_tz(hour_str: str, minute_str: str, sign_str: str) -> timezone:
     sign = 1 if sign_str == "+" else -1