[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
This commit is contained in:
pre-commit-ci[bot] 2024-04-13 00:00:18 +00:00
parent 72ad6dc953
commit f4cd1ba0d6
813 changed files with 66015 additions and 58839 deletions

View file

@ -1,6 +1,7 @@
"""A lil' TOML parser."""
from __future__ import annotations
__all__ = ("loads", "load", "TOMLDecodeError")
__version__ = "1.0.3" # DO NOT EDIT THIS LINE MANUALLY. LET bump2version UTILITY DO IT
__all__ = ('loads', 'load', 'TOMLDecodeError')
__version__ = '1.0.3' # DO NOT EDIT THIS LINE MANUALLY. LET bump2version UTILITY DO IT
from pip._vendor.tomli._parser import TOMLDecodeError, load, loads

View file

@ -1,28 +1,26 @@
from __future__ import annotations
import string
from types import MappingProxyType
from typing import (
TYPE_CHECKING,
Any,
Callable,
Dict,
FrozenSet,
Iterable,
Optional,
TextIO,
Tuple,
)
from typing import Any
from typing import Callable
from typing import Dict
from typing import FrozenSet
from typing import Iterable
from typing import Optional
from typing import TextIO
from typing import Tuple
from typing import TYPE_CHECKING
from pip._vendor.tomli._re import (
RE_BIN,
RE_DATETIME,
RE_HEX,
RE_LOCALTIME,
RE_NUMBER,
RE_OCT,
match_to_datetime,
match_to_localtime,
match_to_number,
)
from pip._vendor.tomli._re import match_to_datetime
from pip._vendor.tomli._re import match_to_localtime
from pip._vendor.tomli._re import match_to_number
from pip._vendor.tomli._re import RE_BIN
from pip._vendor.tomli._re import RE_DATETIME
from pip._vendor.tomli._re import RE_HEX
from pip._vendor.tomli._re import RE_LOCALTIME
from pip._vendor.tomli._re import RE_NUMBER
from pip._vendor.tomli._re import RE_OCT
if TYPE_CHECKING:
from re import Pattern
@ -32,29 +30,29 @@ ASCII_CTRL = frozenset(chr(i) for i in range(32)) | frozenset(chr(127))
# Neither of these sets include quotation mark or backslash. They are
# currently handled as separate cases in the parser functions.
ILLEGAL_BASIC_STR_CHARS = ASCII_CTRL - frozenset("\t")
ILLEGAL_MULTILINE_BASIC_STR_CHARS = ASCII_CTRL - frozenset("\t\n\r")
ILLEGAL_BASIC_STR_CHARS = ASCII_CTRL - frozenset('\t')
ILLEGAL_MULTILINE_BASIC_STR_CHARS = ASCII_CTRL - frozenset('\t\n\r')
ILLEGAL_LITERAL_STR_CHARS = ILLEGAL_BASIC_STR_CHARS
ILLEGAL_MULTILINE_LITERAL_STR_CHARS = ASCII_CTRL - frozenset("\t\n")
ILLEGAL_MULTILINE_LITERAL_STR_CHARS = ASCII_CTRL - frozenset('\t\n')
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 + "-_")
TOML_WS = frozenset(' \t')
TOML_WS_AND_NEWLINE = TOML_WS | frozenset('\n')
BARE_KEY_CHARS = frozenset(string.ascii_letters + string.digits + '-_')
KEY_INITIAL_CHARS = BARE_KEY_CHARS | frozenset("\"'")
BASIC_STR_ESCAPE_REPLACEMENTS = MappingProxyType(
{
"\\b": "\u0008", # backspace
"\\t": "\u0009", # tab
"\\n": "\u000A", # linefeed
"\\f": "\u000C", # form feed
"\\r": "\u000D", # carriage return
'\\"': "\u0022", # quote
"\\\\": "\u005C", # backslash
}
'\\b': '\u0008', # backspace
'\\t': '\u0009', # tab
'\\n': '\u000A', # linefeed
'\\f': '\u000C', # form feed
'\\r': '\u000D', # carriage return
'\\"': '\u0022', # quote
'\\\\': '\u005C', # backslash
},
)
# Type annotations
@ -67,18 +65,18 @@ class TOMLDecodeError(ValueError):
"""An error raised if a document is not valid TOML."""
def load(fp: TextIO, *, parse_float: ParseFloat = float) -> Dict[str, Any]:
def load(fp: TextIO, *, parse_float: ParseFloat = float) -> dict[str, Any]:
"""Parse TOML from a file object."""
s = fp.read()
return loads(s, parse_float=parse_float)
def loads(s: str, *, parse_float: ParseFloat = float) -> Dict[str, Any]: # noqa: C901
def loads(s: str, *, parse_float: ParseFloat = float) -> dict[str, Any]: # noqa: C901
"""Parse TOML from a string."""
# 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")
src = s.replace('\r\n', '\n')
pos = 0
state = State()
@ -100,24 +98,24 @@ def loads(s: str, *, parse_float: ParseFloat = float) -> Dict[str, Any]: # noqa
char = src[pos]
except IndexError:
break
if char == "\n":
if char == '\n':
pos += 1
continue
if char in KEY_INITIAL_CHARS:
pos = key_value_rule(src, pos, state, parse_float)
pos = skip_chars(src, pos, TOML_WS)
elif char == "[":
elif char == '[':
try:
second_char: Optional[str] = src[pos + 1]
second_char: str | None = src[pos + 1]
except IndexError:
second_char = None
if second_char == "[":
if second_char == '[':
pos = create_list_rule(src, pos, state)
else:
pos = create_dict_rule(src, pos, state)
pos = skip_chars(src, pos, TOML_WS)
elif char != "#":
raise suffixed_err(src, pos, "Invalid statement")
elif char != '#':
raise suffixed_err(src, pos, 'Invalid statement')
# 3. Skip comment
pos = skip_comment(src, pos)
@ -127,9 +125,9 @@ def loads(s: str, *, parse_float: ParseFloat = float) -> Dict[str, Any]: # noqa
char = src[pos]
except IndexError:
break
if char != "\n":
if char != '\n':
raise suffixed_err(
src, pos, "Expected newline or end of document after a statement"
src, pos, 'Expected newline or end of document after a statement',
)
pos += 1
@ -156,39 +154,39 @@ class Flags:
EXPLICIT_NEST = 1
def __init__(self) -> None:
self._flags: Dict[str, dict] = {}
self._flags: dict[str, dict] = {}
def unset_all(self, key: Key) -> None:
cont = self._flags
for k in key[:-1]:
if k not in cont:
return
cont = cont[k]["nested"]
cont = cont[k]['nested']
cont.pop(key[-1], None)
def set_for_relative_key(self, head_key: Key, rel_key: Key, flag: int) -> None:
cont = self._flags
for k in head_key:
if k not in cont:
cont[k] = {"flags": set(), "recursive_flags": set(), "nested": {}}
cont = cont[k]["nested"]
cont[k] = {'flags': set(), 'recursive_flags': set(), 'nested': {}}
cont = cont[k]['nested']
for k in rel_key:
if k in cont:
cont[k]["flags"].add(flag)
cont[k]['flags'].add(flag)
else:
cont[k] = {"flags": {flag}, "recursive_flags": set(), "nested": {}}
cont = cont[k]["nested"]
cont[k] = {'flags': {flag}, 'recursive_flags': set(), 'nested': {}}
cont = cont[k]['nested']
def set(self, key: Key, flag: int, *, recursive: bool) -> None: # noqa: A003
cont = self._flags
key_parent, key_stem = key[:-1], key[-1]
for k in key_parent:
if k not in cont:
cont[k] = {"flags": set(), "recursive_flags": set(), "nested": {}}
cont = cont[k]["nested"]
cont[k] = {'flags': set(), 'recursive_flags': set(), 'nested': {}}
cont = cont[k]['nested']
if key_stem not in cont:
cont[key_stem] = {"flags": set(), "recursive_flags": set(), "nested": {}}
cont[key_stem]["recursive_flags" if recursive else "flags"].add(flag)
cont[key_stem] = {'flags': set(), 'recursive_flags': set(), 'nested': {}}
cont[key_stem]['recursive_flags' if recursive else 'flags'].add(flag)
def is_(self, key: Key, flag: int) -> bool:
if not key:
@ -198,20 +196,20 @@ class Flags:
if k not in cont:
return False
inner_cont = cont[k]
if flag in inner_cont["recursive_flags"]:
if flag in inner_cont['recursive_flags']:
return True
cont = inner_cont["nested"]
cont = inner_cont['nested']
key_stem = key[-1]
if key_stem in cont:
cont = cont[key_stem]
return flag in cont["flags"] or flag in cont["recursive_flags"]
return flag in cont['flags'] or flag in cont['recursive_flags']
return False
class NestedDict:
def __init__(self) -> None:
# The parsed content of the TOML document
self.dict: Dict[str, Any] = {}
self.dict: dict[str, Any] = {}
def get_or_create_nest(
self,
@ -227,7 +225,7 @@ class NestedDict:
if access_lists and isinstance(cont, list):
cont = cont[-1]
if not isinstance(cont, dict):
raise KeyError("There is no nest behind this key")
raise KeyError('There is no nest behind this key')
return cont
def append_nest_to_list(self, key: Key) -> None:
@ -236,7 +234,7 @@ class NestedDict:
if last_key in cont:
list_ = cont[last_key]
if not isinstance(list_, list):
raise KeyError("An object other than list found behind this key")
raise KeyError('An object other than list found behind this key')
list_.append({})
else:
cont[last_key] = [{}]
@ -256,7 +254,7 @@ def skip_until(
pos: Pos,
expect: str,
*,
error_on: FrozenSet[str],
error_on: frozenset[str],
error_on_eof: bool,
) -> Pos:
try:
@ -276,12 +274,12 @@ def skip_until(
def skip_comment(src: str, pos: Pos) -> Pos:
try:
char: Optional[str] = src[pos]
char: str | None = src[pos]
except IndexError:
char = None
if char == "#":
if char == '#':
return skip_until(
src, pos + 1, "\n", error_on=ILLEGAL_COMMENT_CHARS, error_on_eof=False
src, pos + 1, '\n', error_on=ILLEGAL_COMMENT_CHARS, error_on_eof=False,
)
return pos
@ -301,15 +299,15 @@ def create_dict_rule(src: str, pos: Pos, state: State) -> Pos:
pos, key = parse_key(src, pos)
if state.flags.is_(key, Flags.EXPLICIT_NEST) or state.flags.is_(key, Flags.FROZEN):
raise suffixed_err(src, pos, f"Can not declare {key} twice")
raise suffixed_err(src, pos, f'Can not declare {key} twice')
state.flags.set(key, Flags.EXPLICIT_NEST, recursive=False)
try:
state.out.get_or_create_nest(key)
except KeyError:
raise suffixed_err(src, pos, "Can not overwrite a value")
raise suffixed_err(src, pos, 'Can not overwrite a value')
state.header_namespace = key
if src[pos : pos + 1] != "]":
if src[pos: pos + 1] != ']':
raise suffixed_err(src, pos, 'Expected "]" at the end of a table declaration')
return pos + 1
@ -320,7 +318,7 @@ def create_list_rule(src: str, pos: Pos, state: State) -> Pos:
pos, key = parse_key(src, pos)
if state.flags.is_(key, Flags.FROZEN):
raise suffixed_err(src, pos, f"Can not mutate immutable namespace {key}")
raise suffixed_err(src, pos, f'Can not mutate immutable namespace {key}')
# Free the namespace now that it points to another empty list item...
state.flags.unset_all(key)
# ...but this key precisely is still prohibited from table declaration
@ -328,11 +326,11 @@ def create_list_rule(src: str, pos: Pos, state: State) -> Pos:
try:
state.out.append_nest_to_list(key)
except KeyError:
raise suffixed_err(src, pos, "Can not overwrite a value")
raise suffixed_err(src, pos, 'Can not overwrite a value')
state.header_namespace = key
end_marker = src[pos : pos + 2]
if end_marker != "]]":
end_marker = src[pos: pos + 2]
if end_marker != ']]':
raise suffixed_err(
src,
pos,
@ -349,16 +347,16 @@ def key_value_rule(src: str, pos: Pos, state: State, parse_float: ParseFloat) ->
if state.flags.is_(abs_key_parent, Flags.FROZEN):
raise suffixed_err(
src, pos, f"Can not mutate immutable namespace {abs_key_parent}"
src, pos, f'Can not mutate immutable namespace {abs_key_parent}',
)
# Containers in the relative path can't be opened with the table syntax after this
state.flags.set_for_relative_key(state.header_namespace, key, Flags.EXPLICIT_NEST)
try:
nest = state.out.get_or_create_nest(abs_key_parent)
except KeyError:
raise suffixed_err(src, pos, "Can not overwrite a value")
raise suffixed_err(src, pos, 'Can not overwrite a value')
if key_stem in nest:
raise suffixed_err(src, pos, "Can not overwrite a value")
raise suffixed_err(src, pos, 'Can not overwrite a value')
# Mark inline table and array namespaces recursively immutable
if isinstance(value, (dict, list)):
abs_key = state.header_namespace + key
@ -368,14 +366,14 @@ def key_value_rule(src: str, pos: Pos, state: State, parse_float: ParseFloat) ->
def parse_key_value_pair(
src: str, pos: Pos, parse_float: ParseFloat
) -> Tuple[Pos, Key, Any]:
src: str, pos: Pos, parse_float: ParseFloat,
) -> tuple[Pos, Key, Any]:
pos, key = parse_key(src, pos)
try:
char: Optional[str] = src[pos]
char: str | None = src[pos]
except IndexError:
char = None
if char != "=":
if char != '=':
raise suffixed_err(src, pos, 'Expected "=" after a key in a key/value pair')
pos += 1
pos = skip_chars(src, pos, TOML_WS)
@ -383,16 +381,16 @@ def parse_key_value_pair(
return pos, key, value
def parse_key(src: str, pos: Pos) -> Tuple[Pos, Key]:
def parse_key(src: str, pos: Pos) -> tuple[Pos, Key]:
pos, key_part = parse_key_part(src, pos)
key = [key_part]
pos = skip_chars(src, pos, TOML_WS)
while True:
try:
char: Optional[str] = src[pos]
char: str | None = src[pos]
except IndexError:
char = None
if char != ".":
if char != '.':
return pos, tuple(key)
pos += 1
pos = skip_chars(src, pos, TOML_WS)
@ -401,9 +399,9 @@ def parse_key(src: str, pos: Pos) -> Tuple[Pos, Key]:
pos = skip_chars(src, pos, TOML_WS)
def parse_key_part(src: str, pos: Pos) -> Tuple[Pos, str]:
def parse_key_part(src: str, pos: Pos) -> tuple[Pos, str]:
try:
char: Optional[str] = src[pos]
char: str | None = src[pos]
except IndexError:
char = None
if char in BARE_KEY_CHARS:
@ -414,64 +412,64 @@ 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 suffixed_err(src, pos, 'Invalid initial character for a key part')
def parse_one_line_basic_str(src: str, pos: Pos) -> Tuple[Pos, str]:
def parse_one_line_basic_str(src: str, pos: Pos) -> tuple[Pos, str]:
pos += 1
return parse_basic_str(src, pos, multiline=False)
def parse_array(src: str, pos: Pos, parse_float: ParseFloat) -> Tuple[Pos, list]:
def parse_array(src: str, pos: Pos, parse_float: ParseFloat) -> tuple[Pos, list]:
pos += 1
array: list = []
pos = skip_comments_and_array_ws(src, pos)
if src[pos : pos + 1] == "]":
if src[pos: pos + 1] == ']':
return pos + 1, array
while True:
pos, val = parse_value(src, pos, parse_float)
array.append(val)
pos = skip_comments_and_array_ws(src, pos)
c = src[pos : pos + 1]
if c == "]":
c = src[pos: pos + 1]
if c == ']':
return pos + 1, array
if c != ",":
raise suffixed_err(src, pos, "Unclosed array")
if c != ',':
raise suffixed_err(src, pos, 'Unclosed array')
pos += 1
pos = skip_comments_and_array_ws(src, pos)
if src[pos : pos + 1] == "]":
if src[pos: pos + 1] == ']':
return pos + 1, array
def parse_inline_table(src: str, pos: Pos, parse_float: ParseFloat) -> Tuple[Pos, dict]:
def parse_inline_table(src: str, pos: Pos, parse_float: ParseFloat) -> tuple[Pos, dict]:
pos += 1
nested_dict = NestedDict()
flags = Flags()
pos = skip_chars(src, pos, TOML_WS)
if src[pos : pos + 1] == "}":
if src[pos: pos + 1] == '}':
return pos + 1, nested_dict.dict
while True:
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"Can not mutate immutable namespace {key}")
raise suffixed_err(src, pos, f'Can not mutate immutable namespace {key}')
try:
nest = nested_dict.get_or_create_nest(key_parent, access_lists=False)
except KeyError:
raise suffixed_err(src, pos, "Can not overwrite a value")
raise suffixed_err(src, pos, 'Can not overwrite a value')
if key_stem in nest:
raise suffixed_err(src, pos, f'Duplicate inline table key "{key_stem}"')
nest[key_stem] = value
pos = skip_chars(src, pos, TOML_WS)
c = src[pos : pos + 1]
if c == "}":
c = src[pos: pos + 1]
if c == '}':
return pos + 1, nested_dict.dict
if c != ",":
raise suffixed_err(src, pos, "Unclosed inline table")
if c != ',':
raise suffixed_err(src, pos, 'Unclosed inline table')
if isinstance(value, (dict, list)):
flags.set(key, Flags.FROZEN, recursive=True)
pos += 1
@ -479,62 +477,62 @@ def parse_inline_table(src: str, pos: Pos, parse_float: ParseFloat) -> Tuple[Pos
def parse_basic_str_escape(
src: str, pos: Pos, *, multiline: bool = False
) -> Tuple[Pos, str]:
escape_id = src[pos : pos + 2]
src: str, pos: Pos, *, multiline: bool = False,
) -> tuple[Pos, str]:
escape_id = src[pos: pos + 2]
pos += 2
if multiline and escape_id in {"\\ ", "\\\t", "\\\n"}:
if multiline and escape_id in {'\\ ', '\\\t', '\\\n'}:
# Skip whitespace until next non-whitespace character or end of
# the doc. Error if non-whitespace is found before newline.
if escape_id != "\\\n":
if escape_id != '\\\n':
pos = skip_chars(src, pos, TOML_WS)
char = src[pos : pos + 1]
char = src[pos: pos + 1]
if not char:
return pos, ""
if char != "\n":
return pos, ''
if char != '\n':
raise suffixed_err(src, pos, 'Unescaped "\\" in a string')
pos += 1
pos = skip_chars(src, pos, TOML_WS_AND_NEWLINE)
return pos, ""
if escape_id == "\\u":
return pos, ''
if escape_id == '\\u':
return parse_hex_char(src, pos, 4)
if escape_id == "\\U":
if escape_id == '\\U':
return parse_hex_char(src, pos, 8)
try:
return pos, BASIC_STR_ESCAPE_REPLACEMENTS[escape_id]
except KeyError:
if len(escape_id) != 2:
raise suffixed_err(src, pos, "Unterminated string")
raise suffixed_err(src, pos, 'Unterminated string')
raise suffixed_err(src, pos, 'Unescaped "\\" in a string')
def parse_basic_str_escape_multiline(src: str, pos: Pos) -> Tuple[Pos, str]:
def parse_basic_str_escape_multiline(src: str, pos: Pos) -> tuple[Pos, str]:
return parse_basic_str_escape(src, pos, multiline=True)
def parse_hex_char(src: str, pos: Pos, hex_len: int) -> Tuple[Pos, str]:
hex_str = src[pos : pos + hex_len]
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 any(c not in string.hexdigits for c in hex_str):
raise suffixed_err(src, pos, "Invalid hex value")
raise suffixed_err(src, pos, 'Invalid hex value')
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 suffixed_err(src, pos, 'Escaped character is not a Unicode scalar value')
return pos, chr(hex_int)
def parse_literal_str(src: str, pos: Pos) -> Tuple[Pos, str]:
def parse_literal_str(src: str, pos: Pos) -> tuple[Pos, str]:
pos += 1 # Skip starting apostrophe
start_pos = pos
pos = skip_until(
src, pos, "'", error_on=ILLEGAL_LITERAL_STR_CHARS, error_on_eof=True
src, pos, "'", error_on=ILLEGAL_LITERAL_STR_CHARS, error_on_eof=True,
)
return pos + 1, src[start_pos:pos] # Skip ending apostrophe
def parse_multiline_str(src: str, pos: Pos, *, literal: bool) -> Tuple[Pos, str]:
def parse_multiline_str(src: str, pos: Pos, *, literal: bool) -> tuple[Pos, str]:
pos += 3
if src[pos : pos + 1] == "\n":
if src[pos: pos + 1] == '\n':
pos += 1
if literal:
@ -554,37 +552,37 @@ def parse_multiline_str(src: str, pos: Pos, *, literal: bool) -> Tuple[Pos, str]
# Add at maximum two extra apostrophes/quotes if the end sequence
# is 4 or 5 chars long instead of just 3.
if src[pos : pos + 1] != delim:
if src[pos: pos + 1] != delim:
return pos, result
pos += 1
if src[pos : pos + 1] != delim:
if src[pos: pos + 1] != delim:
return pos, result + delim
pos += 1
return pos, result + (delim * 2)
def parse_basic_str(src: str, pos: Pos, *, multiline: bool) -> Tuple[Pos, str]:
def parse_basic_str(src: str, pos: Pos, *, multiline: bool) -> tuple[Pos, str]:
if multiline:
error_on = ILLEGAL_MULTILINE_BASIC_STR_CHARS
parse_escapes = parse_basic_str_escape_multiline
else:
error_on = ILLEGAL_BASIC_STR_CHARS
parse_escapes = parse_basic_str_escape
result = ""
result = ''
start_pos = pos
while True:
try:
char = src[pos]
except IndexError:
raise suffixed_err(src, pos, "Unterminated string")
raise suffixed_err(src, pos, 'Unterminated string')
if char == '"':
if not multiline:
return pos + 1, result + src[start_pos:pos]
if src[pos + 1 : pos + 3] == '""':
if src[pos + 1: pos + 3] == '""':
return pos + 3, result + src[start_pos:pos]
pos += 1
continue
if char == "\\":
if char == '\\':
result += src[start_pos:pos]
pos, parsed_escape = parse_escapes(src, pos)
result += parsed_escape
@ -595,39 +593,39 @@ def parse_basic_str(src: str, pos: Pos, *, multiline: bool) -> Tuple[Pos, str]:
pos += 1
def parse_regex(src: str, pos: Pos, regex: "Pattern") -> Tuple[Pos, str]:
def parse_regex(src: str, pos: Pos, regex: Pattern) -> tuple[Pos, str]:
match = regex.match(src, pos)
if not match:
raise suffixed_err(src, pos, "Unexpected sequence")
raise suffixed_err(src, pos, 'Unexpected sequence')
return match.end(), match.group()
def parse_value( # noqa: C901
src: str, pos: Pos, parse_float: ParseFloat
) -> Tuple[Pos, Any]:
src: str, pos: Pos, parse_float: ParseFloat,
) -> tuple[Pos, Any]:
try:
char: Optional[str] = src[pos]
char: str | None = src[pos]
except IndexError:
char = None
# Basic strings
if char == '"':
if src[pos + 1 : pos + 3] == '""':
if src[pos + 1: pos + 3] == '""':
return parse_multiline_str(src, pos, literal=False)
return parse_one_line_basic_str(src, pos)
# Literal strings
if char == "'":
if src[pos + 1 : pos + 3] == "''":
if src[pos + 1: pos + 3] == "''":
return parse_multiline_str(src, pos, literal=True)
return parse_literal_str(src, pos)
# Booleans
if char == "t":
if src[pos + 1 : pos + 4] == "rue":
if char == 't':
if src[pos + 1: pos + 4] == 'rue':
return pos + 4, True
if char == "f":
if src[pos + 1 : pos + 5] == "alse":
if char == 'f':
if src[pos + 1: pos + 5] == 'alse':
return pos + 5, False
# Dates and times
@ -636,22 +634,22 @@ def parse_value( # noqa: C901
try:
datetime_obj = match_to_datetime(datetime_match)
except ValueError:
raise suffixed_err(src, pos, "Invalid date or datetime")
raise suffixed_err(src, pos, 'Invalid date or datetime')
return datetime_match.end(), datetime_obj
localtime_match = RE_LOCALTIME.match(src, pos)
if localtime_match:
return localtime_match.end(), match_to_localtime(localtime_match)
# Non-decimal integers
if char == "0":
second_char = src[pos + 1 : pos + 2]
if second_char == "x":
if char == '0':
second_char = src[pos + 1: pos + 2]
if second_char == 'x':
pos, hex_str = parse_regex(src, pos + 2, RE_HEX)
return pos, int(hex_str, 16)
if second_char == "o":
if second_char == 'o':
pos, oct_str = parse_regex(src, pos + 2, RE_OCT)
return pos, int(oct_str, 8)
if second_char == "b":
if second_char == 'b':
pos, bin_str = parse_regex(src, pos + 2, RE_BIN)
return pos, int(bin_str, 2)
@ -664,22 +662,22 @@ def parse_value( # noqa: C901
return number_match.end(), match_to_number(number_match, parse_float)
# Arrays
if char == "[":
if char == '[':
return parse_array(src, pos, parse_float)
# Inline tables
if char == "{":
if char == '{':
return parse_inline_table(src, pos, parse_float)
# Special floats
first_three = src[pos : pos + 3]
if first_three in {"inf", "nan"}:
first_three = src[pos: pos + 3]
if first_three in {'inf', 'nan'}:
return pos + 3, parse_float(first_three)
first_four = src[pos : pos + 4]
if first_four in {"-inf", "+inf", "-nan", "+nan"}:
first_four = src[pos: pos + 4]
if first_four in {'-inf', '+inf', '-nan', '+nan'}:
return pos + 4, parse_float(first_four)
raise suffixed_err(src, pos, "Invalid value")
raise suffixed_err(src, pos, 'Invalid value')
def suffixed_err(src: str, pos: Pos, msg: str) -> TOMLDecodeError:
@ -688,15 +686,15 @@ def suffixed_err(src: str, pos: Pos, msg: str) -> TOMLDecodeError:
def coord_repr(src: str, pos: Pos) -> str:
if pos >= len(src):
return "end of document"
line = src.count("\n", 0, pos) + 1
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}"
column = pos - src.rindex('\n', 0, pos)
return f'line {line}, column {column}'
return TOMLDecodeError(f"{msg} (at {coord_repr(src, pos)})")
return TOMLDecodeError(f'{msg} (at {coord_repr(src, pos)})')
def is_unicode_scalar_value(codepoint: int) -> bool:

View file

@ -1,6 +1,16 @@
from datetime import date, datetime, time, timedelta, timezone, tzinfo
from __future__ import annotations
import re
from typing import TYPE_CHECKING, Any, Optional, Union
from datetime import date
from datetime import datetime
from datetime import time
from datetime import timedelta
from datetime import timezone
from datetime import tzinfo
from typing import Any
from typing import Optional
from typing import TYPE_CHECKING
from typing import Union
if TYPE_CHECKING:
from re import Match
@ -10,28 +20,28 @@ if TYPE_CHECKING:
# E.g.
# - 00:32:00.999999
# - 00:32:00
_TIME_RE_STR = r"([01][0-9]|2[0-3]):([0-5][0-9]):([0-5][0-9])(\.[0-9]+)?"
_TIME_RE_STR = r'([01][0-9]|2[0-3]):([0-5][0-9]):([0-5][0-9])(\.[0-9]+)?'
RE_HEX = re.compile(r"[0-9A-Fa-f](?:_?[0-9A-Fa-f])*")
RE_BIN = re.compile(r"[01](?:_?[01])*")
RE_OCT = re.compile(r"[0-7](?:_?[0-7])*")
RE_HEX = re.compile(r'[0-9A-Fa-f](?:_?[0-9A-Fa-f])*')
RE_BIN = re.compile(r'[01](?:_?[01])*')
RE_OCT = re.compile(r'[0-7](?:_?[0-7])*')
RE_NUMBER = re.compile(
r"[+-]?(?:0|[1-9](?:_?[0-9])*)" # integer
+ r"(?:\.[0-9](?:_?[0-9])*)?" # optional fractional part
+ r"(?:[eE][+-]?[0-9](?:_?[0-9])*)?" # optional exponent part
r'[+-]?(?:0|[1-9](?:_?[0-9])*)' + # integer
r'(?:\.[0-9](?:_?[0-9])*)?' + # optional fractional part
r'(?:[eE][+-]?[0-9](?:_?[0-9])*)?', # optional exponent part
)
RE_LOCALTIME = re.compile(_TIME_RE_STR)
RE_DATETIME = re.compile(
r"([0-9]{4})-(0[1-9]|1[0-2])-(0[1-9]|1[0-9]|2[0-9]|3[01])" # date, e.g. 1988-10-27
+ r"(?:"
+ r"[T ]"
+ _TIME_RE_STR
+ r"(?:(Z)|([+-])([01][0-9]|2[0-3]):([0-5][0-9]))?" # time offset
+ r")?"
r'([0-9]{4})-(0[1-9]|1[0-2])-(0[1-9]|1[0-9]|2[0-9]|3[01])' + # date, e.g. 1988-10-27
r'(?:' +
r'[T ]' +
_TIME_RE_STR +
r'(?:(Z)|([+-])([01][0-9]|2[0-3]):([0-5][0-9]))?' + # time offset
r')?',
)
def match_to_datetime(match: "Match") -> Union[datetime, date]:
def match_to_datetime(match: Match) -> datetime | date:
"""Convert a `RE_DATETIME` match to `datetime.datetime` or `datetime.date`.
Raises ValueError if the match does not correspond to a valid date
@ -54,14 +64,14 @@ def match_to_datetime(match: "Match") -> Union[datetime, date]:
if hour_str is None:
return date(year, month, day)
hour, minute, sec = int(hour_str), int(minute_str), int(sec_str)
micros = int(micros_str[1:].ljust(6, "0")[:6]) if micros_str else 0
micros = int(micros_str[1:].ljust(6, '0')[:6]) if micros_str else 0
if offset_dir_str:
offset_dir = 1 if offset_dir_str == "+" else -1
tz: Optional[tzinfo] = timezone(
offset_dir = 1 if offset_dir_str == '+' else -1
tz: tzinfo | None = timezone(
timedelta(
hours=offset_dir * int(offset_hour_str),
minutes=offset_dir * int(offset_minute_str),
)
),
)
elif zulu_time:
tz = timezone.utc
@ -70,14 +80,14 @@ def match_to_datetime(match: "Match") -> Union[datetime, date]:
return datetime(year, month, day, hour, minute, sec, micros, tzinfo=tz)
def match_to_localtime(match: "Match") -> time:
def match_to_localtime(match: Match) -> time:
hour_str, minute_str, sec_str, micros_str = match.groups()
micros = int(micros_str[1:].ljust(6, "0")[:6]) if micros_str else 0
micros = int(micros_str[1:].ljust(6, '0')[:6]) if micros_str else 0
return time(int(hour_str), int(minute_str), int(sec_str), micros)
def match_to_number(match: "Match", parse_float: "ParseFloat") -> Any:
def match_to_number(match: Match, parse_float: ParseFloat) -> Any:
match_str = match.group()
if "." in match_str or "e" in match_str or "E" in match_str:
if '.' in match_str or 'e' in match_str or 'E' in match_str:
return parse_float(match_str)
return int(match_str)