Skip to content

gh-118761: Improve import time of tomllib #128907

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jan 17, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 9 additions & 0 deletions Lib/test/test_tomllib/test_misc.py
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@
import copy
import datetime
from decimal import Decimal as D
import importlib
from pathlib import Path
import sys
import tempfile
Expand Down Expand Up @@ -113,3 +114,11 @@ def test_inline_table_recursion_limit(self):
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")
31 changes: 19 additions & 12 deletions Lib/tomllib/_parser.py
Original file line number Diff line number Diff line change
Expand Up @@ -4,11 +4,7 @@

from __future__ import annotations

from collections.abc import Iterable
import string
from types import MappingProxyType
from typing import Any, BinaryIO, NamedTuple
import warnings

from ._re import (
RE_DATETIME,
Expand All @@ -18,7 +14,13 @@
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))

Expand All @@ -34,9 +36,11 @@

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(
{
Expand Down Expand Up @@ -80,6 +84,8 @@ def __init__(
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.",
Expand Down Expand Up @@ -115,7 +121,7 @@ def __init__(
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:
Expand All @@ -139,7 +145,7 @@ def loads(s: str, /, *, parse_float: ParseFloat = float) -> dict[str, Any]: # n
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)

Expand Down Expand Up @@ -290,9 +296,10 @@ def append_nest_to_list(self, key: Key) -> None:
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:
Expand Down
7 changes: 5 additions & 2 deletions Lib/tomllib/_re.py
Original file line number Diff line number Diff line change
Expand Up @@ -7,9 +7,12 @@
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
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
Improve import time of :mod:`tomllib` by removing ``typing``, ``string``,
and ``tomllib._types`` imports. Patch by Taneli Hukkinen.
Loading