diff options
| author | YDBot <[email protected]> | 2026-07-01 16:23:57 +0000 |
|---|---|---|
| committer | YDBot <[email protected]> | 2026-07-01 16:23:57 +0000 |
| commit | e9b445a7f111ee5ba5c58672d767833df25ba262 (patch) | |
| tree | 1b8bdb84d3fd994ff3ac60e36c30f93fbfce1243 /contrib/tools/python3/Lib | |
| parent | 1cfcce4de55cd075cfba845abf02c1554f141e01 (diff) | |
| parent | c98b5dbfe575ba628d7c3427854e7bd26030eb2c (diff) | |
Merge pull request #44637 from ydb-platform/merge-rightlib-260626-1120
Diffstat (limited to 'contrib/tools/python3/Lib')
70 files changed, 1771 insertions, 964 deletions
diff --git a/contrib/tools/python3/Lib/_collections_abc.py b/contrib/tools/python3/Lib/_collections_abc.py index 6e224d36001..da2d0c29f84 100644 --- a/contrib/tools/python3/Lib/_collections_abc.py +++ b/contrib/tools/python3/Lib/_collections_abc.py @@ -461,8 +461,8 @@ class Buffer(metaclass=ABCMeta): class _CallableGenericAlias(GenericAlias): """ Represent `Callable[argtypes, resulttype]`. - This sets ``__args__`` to a tuple containing the flattened ``argtypes`` - followed by ``resulttype``. + This sets ``__args__`` to a tuple containing the flattened + ``argtypes`` followed by ``resulttype``. Example: ``Callable[[int, str], float]`` sets ``__args__`` to ``(int, str, float)``. @@ -943,8 +943,9 @@ class MutableMapping(Mapping): __marker = object() def pop(self, key, default=__marker): - '''D.pop(k[,d]) -> v, remove specified key and return the corresponding value. - If key is not found, d is returned if given, otherwise KeyError is raised. + '''D.pop(k[,d]) -> v, remove specified key and return the corresponding + value. If key is not found, d is returned if given, otherwise + KeyError is raised. ''' try: value = self[key] @@ -978,9 +979,12 @@ class MutableMapping(Mapping): def update(self, other=(), /, **kwds): ''' D.update([E, ]**F) -> None. Update D from mapping/iterable E and F. - If E present and has a .keys() method, does: for k in E.keys(): D[k] = E[k] - If E present and lacks .keys() method, does: for (k, v) in E: D[k] = v - In either case, this is followed by: for k, v in F.items(): D[k] = v + If E present and has a .keys() method, does: + for k in E.keys(): D[k] = E[k] + If E present and lacks .keys() method, does: + for (k, v) in E: D[k] = v + In either case, this is followed by: + for k, v in F.items(): D[k] = v ''' if isinstance(other, Mapping): for key in other: @@ -1045,8 +1049,8 @@ class Sequence(Reversible, Collection): yield self[i] def index(self, value, start=0, stop=None): - '''S.index(value, [start, [stop]]) -> integer -- return first index of value. - Raises ValueError if the value is not present. + '''S.index(value, [start, [stop]]) -> integer -- return first index of + value. Raises ValueError if the value is not present. Supporting start and stop arguments is optional, but recommended. @@ -1153,15 +1157,16 @@ class MutableSequence(Sequence): self[i], self[n-i-1] = self[n-i-1], self[i] def extend(self, values): - 'S.extend(iterable) -- extend sequence by appending elements from the iterable' + """S.extend(iterable) -- extend sequence by appending elements from the + iterable""" if values is self: values = list(values) for v in values: self.append(v) def pop(self, index=-1): - '''S.pop([index]) -> item -- remove and return item at index (default last). - Raise IndexError if list is empty or index is out of range. + '''S.pop([index]) -> item -- remove and return item at index (default + last). Raise IndexError if list is empty or index is out of range. ''' v = self[index] del self[index] diff --git a/contrib/tools/python3/Lib/_pydecimal.py b/contrib/tools/python3/Lib/_pydecimal.py index 49119ede7ce..f83524a2560 100644 --- a/contrib/tools/python3/Lib/_pydecimal.py +++ b/contrib/tools/python3/Lib/_pydecimal.py @@ -102,8 +102,8 @@ class DecimalException(ArithmeticError): anything, though. handle -- Called when context._raise_error is called and the - trap_enabler is not set. First argument is self, second is the - context. More arguments can be given, those being after + trap_enabler is not set. First argument is self, second is + the context. More arguments can be given, those being after the explanation in _raise_error (For example, context._raise_error(NewError, '(-x)!', self._sign) would call NewError().handle(context, self._sign).) @@ -220,11 +220,12 @@ class InvalidContext(InvalidOperation): """Invalid context. Unknown rounding, for example. This occurs and signals invalid-operation if an invalid context was - detected during an operation. This can occur if contexts are not checked - on creation and either the precision exceeds the capability of the - underlying concrete representation or an unknown or unsupported rounding - was specified. These aspects of the context need only be checked when - the values are required to be used. The result is [0,qNaN]. + detected during an operation. This can occur if contexts are not + checked on creation and either the precision exceeds the capability of + the underlying concrete representation or an unknown or unsupported + rounding was specified. These aspects of the context need only be + checked when the values are required to be used. The result is + [0,qNaN]. """ def handle(self, context, *args): @@ -317,8 +318,9 @@ class FloatOperation(DecimalException, TypeError): Decimal.from_float() or context.create_decimal_from_float() do not set the flag. - Otherwise (the signal is trapped), only equality comparisons and explicit - conversions are silent. All other mixed operations raise FloatOperation. + Otherwise (the signal is trapped), only equality comparisons and + explicit conversions are silent. All other mixed operations raise + FloatOperation. """ # List of public traps and flags @@ -2860,8 +2862,8 @@ class Decimal(object): """Compares self to other using the abstract representations. This is not like the standard compare, which use their numerical - value. Note that a total ordering is defined for all possible abstract - representations. + value. Note that a total ordering is defined for all possible + abstract representations. """ other = _convert_other(other, raiseit=True) @@ -2932,7 +2934,8 @@ class Decimal(object): def compare_total_mag(self, other, context=None): """Compares self to other using abstract repr., ignoring sign. - Like compare_total, but with operand's sign ignored and assumed to be 0. + Like compare_total, but with operand's sign ignored and assumed to + be 0. """ other = _convert_other(other, raiseit=True) @@ -4069,9 +4072,9 @@ class Context(object): def abs(self, a): """Returns the absolute value of the operand. - If the operand is negative, the result is the same as using the minus - operation on the operand. Otherwise, the result is the same as using - the plus operation on the operand. + If the operand is negative, the result is the same as using the + minus operation on the operand. Otherwise, the result is the same + as using the plus operation on the operand. >>> ExtendedContext.abs(Decimal('2.1')) Decimal('2.1') @@ -4127,16 +4130,17 @@ class Context(object): def compare(self, a, b): """Compares values numerically. - If the signs of the operands differ, a value representing each operand - ('-1' if the operand is less than zero, '0' if the operand is zero or - negative zero, or '1' if the operand is greater than zero) is used in - place of that operand for the comparison instead of the actual - operand. + If the signs of the operands differ, a value representing each + operand ('-1' if the operand is less than zero, '0' if the operand + is zero or negative zero, or '1' if the operand is greater than + zero) is used in place of that operand for the comparison instead of + the actual operand. - The comparison is then effected by subtracting the second operand from - the first and then returning a value according to the result of the - subtraction: '-1' if the result is less than zero, '0' if the result is - zero or negative zero, or '1' if the result is greater than zero. + The comparison is then effected by subtracting the second operand + from the first and then returning a value according to the result of + the subtraction: '-1' if the result is less than zero, '0' if the + result is zero or negative zero, or '1' if the result is greater + than zero. >>> ExtendedContext.compare(Decimal('2.1'), Decimal('3')) Decimal('-1') @@ -4199,8 +4203,8 @@ class Context(object): """Compares two operands using their abstract representation. This is not like the standard compare, which use their numerical - value. Note that a total ordering is defined for all possible abstract - representations. + value. Note that a total ordering is defined for all possible + abstract representations. >>> ExtendedContext.compare_total(Decimal('12.73'), Decimal('127.9')) Decimal('-1') @@ -4227,7 +4231,8 @@ class Context(object): def compare_total_mag(self, a, b): """Compares two operands using their abstract representation ignoring sign. - Like compare_total, but with operand's sign ignored and assumed to be 0. + Like compare_total, but with operand's sign ignored and assumed to + be 0. """ a = _convert_other(a, raiseit=True) return a.compare_total_mag(b) @@ -4885,8 +4890,8 @@ class Context(object): If either operand is a special value then the general rules apply. Otherwise, the operands are multiplied together - ('long multiplication'), resulting in a number which may be as long as - the sum of the lengths of the two operands. + ('long multiplication'), resulting in a number which may be as long + as the sum of the lengths of the two operands. >>> ExtendedContext.multiply(Decimal('1.20'), Decimal('3')) Decimal('3.60') @@ -5162,19 +5167,19 @@ class Context(object): """Returns a value equal to 'a' (rounded), having the exponent of 'b'. The coefficient of the result is derived from that of the left-hand - operand. It may be rounded using the current rounding setting (if the - exponent is being increased), multiplied by a positive power of ten (if - the exponent is being decreased), or is unchanged (if the exponent is - already equal to that of the right-hand operand). + operand. It may be rounded using the current rounding setting (if + the exponent is being increased), multiplied by a positive power of + ten (if the exponent is being decreased), or is unchanged (if the + exponent is already equal to that of the right-hand operand). Unlike other operations, if the length of the coefficient after the quantize operation would be greater than precision then an Invalid - operation condition is raised. This guarantees that, unless there is - an error condition, the exponent of the result of a quantize is always - equal to that of the right-hand operand. + operation condition is raised. This guarantees that, unless there + is an error condition, the exponent of the result of a quantize is + always equal to that of the right-hand operand. - Also unlike other operations, quantize will never raise Underflow, even - if the result is subnormal and inexact. + Also unlike other operations, quantize will never raise Underflow, + even if the result is subnormal and inexact. >>> ExtendedContext.quantize(Decimal('2.17'), Decimal('0.001')) Decimal('2.170') @@ -5228,13 +5233,13 @@ class Context(object): """Returns the remainder from integer division. The result is the residue of the dividend after the operation of - calculating integer division as described for divide-integer, rounded - to precision digits if necessary. The sign of the result, if - non-zero, is the same as that of the original dividend. + calculating integer division as described for divide-integer, + rounded to precision digits if necessary. The sign of the result, + if non-zero, is the same as that of the original dividend. - This operation will fail under the same conditions as integer division - (that is, if integer division on the same two operands would fail, the - remainder cannot be calculated). + This operation will fail under the same conditions as integer + division (that is, if integer division on the same two operands + would fail, the remainder cannot be calculated). >>> ExtendedContext.remainder(Decimal('2.1'), Decimal('3')) Decimal('2.1') @@ -5268,9 +5273,9 @@ class Context(object): is chosen). If the result is equal to 0 then its sign will be the sign of a. - This operation will fail under the same conditions as integer division - (that is, if integer division on the same two operands would fail, the - remainder cannot be calculated). + This operation will fail under the same conditions as integer + division (that is, if integer division on the same two operands + would fail, the remainder cannot be calculated). >>> ExtendedContext.remainder_near(Decimal('2.1'), Decimal('3')) Decimal('-0.9') @@ -5328,8 +5333,8 @@ class Context(object): def same_quantum(self, a, b): """Returns True if the two operands have the same exponent. - The result is never affected by either the sign or the coefficient of - either operand. + The result is never affected by either the sign or the coefficient + of either operand. >>> ExtendedContext.same_quantum(Decimal('2.17'), Decimal('0.001')) False @@ -5401,8 +5406,8 @@ class Context(object): def sqrt(self, a): """Square root of a non-negative number to context precision. - If the result must be inexact, it is rounded using the round-half-even - algorithm. + If the result must be inexact, it is rounded using the + round-half-even algorithm. >>> ExtendedContext.sqrt(Decimal('0')) Decimal('0') diff --git a/contrib/tools/python3/Lib/_pyio.py b/contrib/tools/python3/Lib/_pyio.py index 9ed2e5b2aa0..7c1635cb331 100644 --- a/contrib/tools/python3/Lib/_pyio.py +++ b/contrib/tools/python3/Lib/_pyio.py @@ -82,27 +82,28 @@ def open(file, mode="r", buffering=-1, encoding=None, errors=None, wrapped. (If a file descriptor is given, it is closed when the returned I/O object is closed, unless closefd is set to False.) - mode is an optional string that specifies the mode in which the file is - opened. It defaults to 'r' which means open for reading in text mode. Other - common values are 'w' for writing (truncating the file if it already - exists), 'x' for exclusive creation of a new file, and 'a' for appending - (which on some Unix systems, means that all writes append to the end of the - file regardless of the current seek position). In text mode, if encoding is - not specified the encoding used is platform dependent. (For reading and - writing raw bytes use binary mode and leave encoding unspecified.) The - available modes are: + mode is an optional string that specifies the mode in which the file + is opened. It defaults to 'r' which means open for reading in text + mode. Other common values are 'w' for writing (truncating the file if + it already exists), 'x' for exclusive creation of a new file, and + 'a' for appending (which on some Unix systems, means that all writes + append to the end of the file regardless of the current seek position). + In text mode, if encoding is not specified the encoding used is platform + dependent. (For reading and writing raw bytes use binary mode and leave + encoding unspecified.) The available modes are: - ========= =============================================================== + ========= ========================================================== Character Meaning - --------- --------------------------------------------------------------- + --------- ---------------------------------------------------------- 'r' open for reading (default) 'w' open for writing, truncating the file first 'x' create a new file and open it for writing - 'a' open for writing, appending to the end of the file if it exists + 'a' open for writing, appending to the end of the file if it + exists 'b' binary mode 't' text mode (default) '+' open a disk file for updating (reading and writing) - ========= =============================================================== + ========= ========================================================== The default mode is 'rt' (open for reading text). For binary random access, the mode 'w+b' opens and truncates the file to 0 bytes, while @@ -110,22 +111,22 @@ def open(file, mode="r", buffering=-1, encoding=None, errors=None, raises an `FileExistsError` if the file already exists. Python distinguishes between files opened in binary and text modes, - even when the underlying operating system doesn't. Files opened in + even when the underlying operating system doesn't. Files opened in binary mode (appending 'b' to the mode argument) return contents as - bytes objects without any decoding. In text mode (the default, or when + bytes objects without any decoding. In text mode (the default, or when 't' is appended to the mode argument), the contents of the file are returned as strings, the bytes having been first decoded using a platform-dependent encoding or using the specified encoding if given. buffering is an optional integer used to set the buffering policy. - Pass 0 to switch buffering off (only allowed in binary mode), 1 to select - line buffering (only usable in text mode), and an integer > 1 to indicate - the size of a fixed-size chunk buffer. When no buffering argument is - given, the default buffering policy works as follows: + Pass 0 to switch buffering off (only allowed in binary mode), 1 to + select line buffering (only usable in text mode), and an integer > 1 to + indicate the size of a fixed-size chunk buffer. When no buffering + argument is given, the default buffering policy works as follows: * Binary files are buffered in fixed-size chunks; the size of the buffer - is chosen using a heuristic trying to determine the underlying device's - "block size" and falling back on `io.DEFAULT_BUFFER_SIZE`. + is chosen using a heuristic trying to determine the underlying + device's "block size" and falling back on `io.DEFAULT_BUFFER_SIZE`. On many systems, the buffer will typically be 4096 or 8192 bytes long. * "Interactive" text files (files for which isatty() returns True) @@ -146,8 +147,8 @@ def open(file, mode="r", buffering=-1, encoding=None, errors=None, encoding error strings. newline is a string controlling how universal newlines works (it only - applies to text mode). It can be None, '', '\n', '\r', and '\r\n'. It works - as follows: + applies to text mode). It can be None, '', '\n', '\r', and '\r\n'. It + works as follows: * On input, if newline is None, universal newlines mode is enabled. Lines in the input can end in '\n', '\r', or '\r\n', and @@ -163,17 +164,17 @@ def open(file, mode="r", buffering=-1, encoding=None, errors=None, other legal values, any '\n' characters written are translated to the given string. - closedfd is a bool. If closefd is False, the underlying file descriptor will - be kept open when the file is closed. This does not work when a file name is - given and must be True in that case. + closedfd is a bool. If closefd is False, the underlying file descriptor + will be kept open when the file is closed. This does not work when + a file name is given and must be True in that case. The newly created file is non-inheritable. A custom opener can be used by passing a callable as *opener*. The - underlying file descriptor for the file object is then obtained by calling - *opener* with (*file*, *flags*). *opener* must return an open file - descriptor (passing os.open as *opener* results in functionality similar to - passing None). + underlying file descriptor for the file object is then obtained by + calling *opener* with (*file*, *flags*). *opener* must return an open + file descriptor (passing os.open as *opener* results in functionality + similar to passing None). open() returns a file object whose type depends on the mode, and through which the standard file operations such as reading and writing @@ -357,10 +358,12 @@ class IOBase(metaclass=abc.ABCMeta): interpreted relative to the position indicated by whence. Values for whence are ints: - * 0 -- start of stream (the default); offset should be zero or positive + * 0 -- start of stream (the default); offset should be zero or + positive * 1 -- current stream position; offset may be negative * 2 -- end of stream; offset is usually negative - Some operating systems / file systems could provide additional values. + Some operating systems / file systems could provide additional + values. Return an int indicating the new absolute position. """ @@ -373,8 +376,8 @@ class IOBase(metaclass=abc.ABCMeta): def truncate(self, pos=None): """Truncate file to size bytes. - Size defaults to the current IO position as reported by tell(). Return - the new size. + Size defaults to the current IO position as reported by tell(). + Return the new size. """ self._unsupported("truncate") @@ -498,7 +501,8 @@ class IOBase(metaclass=abc.ABCMeta): def fileno(self): """Returns underlying file descriptor (an int) if one exists. - An OSError is raised if the IO object does not use a file descriptor. + An OSError is raised if the IO object does not use a file + descriptor. """ self._unsupported("fileno") @@ -1482,17 +1486,22 @@ class FileIO(RawIOBase): _closefd = True def __init__(self, file, mode='r', closefd=True, opener=None): - """Open a file. The mode can be 'r' (default), 'w', 'x' or 'a' for reading, - writing, exclusive creation or appending. The file will be created if it - doesn't exist when opened for writing or appending; it will be truncated - when opened for writing. A FileExistsError will be raised if it already - exists when opened for creating. Opening a file for creating implies - writing so this mode behaves in a similar way to 'w'. Add a '+' to the mode - to allow simultaneous reading and writing. A custom opener can be used by - passing a callable as *opener*. The underlying file descriptor for the file - object is then obtained by calling opener with (*name*, *flags*). - *opener* must return an open file descriptor (passing os.open as *opener* - results in functionality similar to passing None). + """Open a file. + + The mode can be 'r' (default), 'w', 'x' or 'a' for reading, + writing, exclusive creation or appending. The file will be created + if it doesn't exist when opened for writing or appending; it will be + truncated when opened for writing. A FileExistsError will be raised + if it already exists when opened for creating. Opening a file for + creating implies writing so this mode behaves in a similar way to + 'w'. Add a '+' to the mode to allow simultaneous reading and + writing. + + A custom opener can be used by passing a callable as *opener*. + The underlying file descriptor for the file object is then obtained + by calling opener with (*name*, *flags*). *opener* must return + an open file descriptor (passing os.open as *opener* results in + functionality similar to passing None). """ if self._fd >= 0: # Have to close the existing file first. @@ -1702,8 +1711,8 @@ class FileIO(RawIOBase): """Write bytes b to file, return number written. Only makes one system call, so not all of the data may be written. - The number of bytes actually written is returned. In non-blocking mode, - returns None if the write would block. + The number of bytes actually written is returned. In non-blocking + mode, returns None if the write would block. """ self._checkClosed() self._checkWritable() @@ -1715,11 +1724,12 @@ class FileIO(RawIOBase): def seek(self, pos, whence=SEEK_SET): """Move to new file position. - Argument offset is a byte count. Optional argument whence defaults to - SEEK_SET or 0 (offset from start of file, offset should be >= 0); other values - are SEEK_CUR or 1 (move relative to current position, positive or negative), - and SEEK_END or 2 (move relative to end of file, usually negative, although - many platforms allow seeking beyond the end of a file). + Argument offset is a byte count. Optional argument whence defaults + to SEEK_SET or 0 (offset from start of file, offset should be >= 0); + other values are SEEK_CUR or 1 (move relative to current position, + positive or negative), and SEEK_END or 2 (move relative to end of + file, usually negative, although many platforms allow seeking beyond + the end of a file). Note that not all file objects are seekable. """ @@ -1751,8 +1761,8 @@ class FileIO(RawIOBase): def close(self): """Close the file. - A closed file cannot be used for further I/O operations. close() may be - called more than once without error. + A closed file cannot be used for further I/O operations. + close() may be called more than once without error. """ if not self.closed: try: @@ -1831,8 +1841,8 @@ class TextIOBase(IOBase): def read(self, size=-1): """Read at most size characters from stream, where size is an int. - Read from underlying buffer until we have size characters or we hit EOF. - If size is negative or omitted, read until EOF. + Read from underlying buffer until we have size characters or we hit + EOF. If size is negative or omitted, read until EOF. Returns a string. """ diff --git a/contrib/tools/python3/Lib/argparse.py b/contrib/tools/python3/Lib/argparse.py index a0faa3f41e2..7d845175644 100644 --- a/contrib/tools/python3/Lib/argparse.py +++ b/contrib/tools/python3/Lib/argparse.py @@ -2601,7 +2601,7 @@ class ArgumentParser(_AttributeHolder, _ActionsContainer): choices = iter(choices) if value not in choices: args = {'value': str(value), - 'choices': ', '.join(map(str, action.choices))} + 'choices': ', '.join(repr(str(choice)) for choice in action.choices)} msg = _('invalid choice: %(value)r (choose from %(choices)s)') raise ArgumentError(action, msg % args) diff --git a/contrib/tools/python3/Lib/asyncio/__main__.py b/contrib/tools/python3/Lib/asyncio/__main__.py index 42bfcdbf50f..2effdbc38da 100644 --- a/contrib/tools/python3/Lib/asyncio/__main__.py +++ b/contrib/tools/python3/Lib/asyncio/__main__.py @@ -96,11 +96,15 @@ class REPLThread(threading.Thread): if not sys.flags.isolated and (startup_path := os.getenv("PYTHONSTARTUP")): sys.audit("cpython.run_startup", startup_path) - - import tokenize - with tokenize.open(startup_path) as f: - startup_code = compile(f.read(), startup_path, "exec") + try: + import tokenize + with tokenize.open(startup_path) as f: + startup_code = compile(f.read(), startup_path, "exec") exec(startup_code, console.locals) + except SystemExit: + raise + except BaseException: + console.showtraceback() ps1 = getattr(sys, "ps1", ">>> ") if can_colorize() and CAN_USE_PYREPL: diff --git a/contrib/tools/python3/Lib/asyncio/base_events.py b/contrib/tools/python3/Lib/asyncio/base_events.py index 84cad10636f..ec8e3b6f79f 100644 --- a/contrib/tools/python3/Lib/asyncio/base_events.py +++ b/contrib/tools/python3/Lib/asyncio/base_events.py @@ -489,10 +489,10 @@ class BaseEventLoop(events.AbstractEventLoop): If factory is None the default task factory will be set. If factory is a callable, it should have a signature matching - '(loop, coro, **kwargs)', where 'loop' will be a reference to the active - event loop, 'coro' will be a coroutine object, and **kwargs will be - arbitrary keyword arguments that should be passed on to Task. - The callable must return a Task. + '(loop, coro, **kwargs)', where 'loop' will be a reference to the + active event loop, 'coro' will be a coroutine object, and **kwargs + will be arbitrary keyword arguments that should be passed on to + Task. The callable must return a Task. """ if factory is not None and not callable(factory): raise TypeError('task factory must be a callable or None') @@ -727,8 +727,8 @@ class BaseEventLoop(events.AbstractEventLoop): def stop(self): """Stop running the event loop. - Every callback already scheduled will still run. This simply informs - run_forever to stop looping after a complete iteration. + Every callback already scheduled will still run. This simply + informs run_forever to stop looping after a complete iteration. """ self._stopping = True @@ -966,7 +966,7 @@ class BaseEventLoop(events.AbstractEventLoop): f"and file {file!r} combination") async def _sock_sendfile_fallback(self, sock, file, offset, count): - if offset: + if hasattr(file, 'seek'): file.seek(offset) blocksize = ( min(count, constants.SENDFILE_FALLBACK_READBUFFER_SIZE) @@ -1073,12 +1073,12 @@ class BaseEventLoop(events.AbstractEventLoop): Create a streaming transport connection to a given internet host and port: socket family AF_INET or socket.AF_INET6 depending on host (or - family if specified), socket type SOCK_STREAM. protocol_factory must be - a callable returning a protocol instance. + family if specified), socket type SOCK_STREAM. protocol_factory must + be a callable returning a protocol instance. - This method is a coroutine which will try to establish the connection - in the background. When successful, the coroutine returns a - (transport, protocol) pair. + This method is a coroutine which will try to establish the + connection in the background. When successful, the coroutine + returns a (transport, protocol) pair. """ if server_hostname is not None and not ssl: raise ValueError('server_hostname is only meaningful with ssl') @@ -1281,7 +1281,6 @@ class BaseEventLoop(events.AbstractEventLoop): raise RuntimeError( f"fallback is disabled and native sendfile is not " f"supported for transport {transport!r}") - return await self._sendfile_fallback(transport, file, offset, count) @@ -1290,7 +1289,7 @@ class BaseEventLoop(events.AbstractEventLoop): "sendfile syscall is not supported") async def _sendfile_fallback(self, transp, file, offset, count): - if offset: + if hasattr(file, 'seek'): file.seek(offset) blocksize = min(count, 16384) if count else 16384 buf = bytearray(blocksize) @@ -1546,11 +1545,11 @@ class BaseEventLoop(events.AbstractEventLoop): The host parameter can be a string, in that case the TCP server is bound to host and port. - The host parameter can also be a sequence of strings and in that case - the TCP server is bound to all hosts of the sequence. If a host - appears multiple times (possibly indirectly e.g. when hostnames - resolve to the same IP address), the server is only bound once to that - host. + The host parameter can also be a sequence of strings and in that + case the TCP server is bound to all hosts of the sequence. If + a host appears multiple times (possibly indirectly e.g. when + hostnames resolve to the same IP address), the server is only bound + once to that host. Return a Server object which can be used to stop the service. diff --git a/contrib/tools/python3/Lib/asyncio/events.py b/contrib/tools/python3/Lib/asyncio/events.py index 3b740b9b905..24e49d561e6 100644 --- a/contrib/tools/python3/Lib/asyncio/events.py +++ b/contrib/tools/python3/Lib/asyncio/events.py @@ -341,8 +341,8 @@ class AbstractEventLoop: If host is an empty string or None all interfaces are assumed and a list of multiple sockets will be returned (most likely - one for IPv4 and another one for IPv6). The host parameter can also be - a sequence (e.g. list) of hosts to bind to. + one for IPv4 and another one for IPv6). The host parameter can also + be a sequence (e.g. list) of hosts to bind to. family can be set to either AF_INET or AF_INET6 to force the socket to use IPv4 or IPv6. If not set it will be determined @@ -382,8 +382,9 @@ class AbstractEventLoop: start_serving set to True (default) causes the created server to start accepting connections immediately. When set to False, - the user should await Server.start_serving() or Server.serve_forever() - to make the server to start accepting connections. + the user should await Server.start_serving() or + Server.serve_forever() to make the server to start accepting + connections. """ raise NotImplementedError @@ -446,8 +447,9 @@ class AbstractEventLoop: start_serving set to True (default) causes the created server to start accepting connections immediately. When set to False, - the user should await Server.start_serving() or Server.serve_forever() - to make the server to start accepting connections. + the user should await Server.start_serving() or + Server.serve_forever() to make the server to start accepting + connections. """ raise NotImplementedError @@ -478,8 +480,8 @@ class AbstractEventLoop: protocol_factory must be a callable returning a protocol instance. - socket family AF_INET, socket.AF_INET6 or socket.AF_UNIX depending on - host (or family if specified), socket type SOCK_DGRAM. + socket family AF_INET, socket.AF_INET6 or socket.AF_UNIX depending + on host (or family if specified), socket type SOCK_DGRAM. reuse_address tells the kernel to reuse a local socket in TIME_WAIT state, without waiting for its natural timeout to @@ -519,7 +521,8 @@ class AbstractEventLoop: async def connect_write_pipe(self, protocol_factory, pipe): """Register write pipe in event loop. - protocol_factory should instantiate object with BaseProtocol interface. + protocol_factory should instantiate object with BaseProtocol + interface. Pipe is file-like object already switched to nonblocking. Return pair (transport, protocol), where transport support WriteTransport interface.""" diff --git a/contrib/tools/python3/Lib/asyncio/locks.py b/contrib/tools/python3/Lib/asyncio/locks.py index 3df4c693a91..22af506d497 100644 --- a/contrib/tools/python3/Lib/asyncio/locks.py +++ b/contrib/tools/python3/Lib/asyncio/locks.py @@ -158,10 +158,10 @@ class Lock(_ContextManagerMixin, mixins._LoopBoundMixin): class Event(mixins._LoopBoundMixin): """Asynchronous equivalent to threading.Event. - Class implementing event objects. An event manages a flag that can be set - to true with the set() method and reset to false with the clear() method. - The wait() method blocks until the flag is true. The flag is initially - false. + Class implementing event objects. An event manages a flag that can be + set to true with the set() method and reset to false with the clear() + method. The wait() method blocks until the flag is true. The flag is + initially false. """ def __init__(self): @@ -353,9 +353,9 @@ class Semaphore(_ContextManagerMixin, mixins._LoopBoundMixin): """A Semaphore implementation. A semaphore manages an internal counter which is decremented by each - acquire() call and incremented by each release() call. The counter - can never go below zero; when acquire() finds that it is zero, it blocks, - waiting until some other thread calls release(). + acquire() call and incremented by each release() call. The counter + can never go below zero; when acquire() finds that it is zero, it + blocks, waiting until some other thread calls release(). Semaphores also support the context management protocol. @@ -511,8 +511,8 @@ class Barrier(mixins._LoopBoundMixin): async def wait(self): """Wait for the barrier. - When the specified number of tasks have started waiting, they are all - simultaneously awoken. + When the specified number of tasks have started waiting, they are + all simultaneously awoken. Returns an unique and individual index number from 0 to 'parties-1'. """ async with self._cond: diff --git a/contrib/tools/python3/Lib/asyncio/proactor_events.py b/contrib/tools/python3/Lib/asyncio/proactor_events.py index f404273c3ae..6b94975d004 100644 --- a/contrib/tools/python3/Lib/asyncio/proactor_events.py +++ b/contrib/tools/python3/Lib/asyncio/proactor_events.py @@ -756,8 +756,7 @@ class BaseProactorEventLoop(base_events.BaseEventLoop): offset += blocksize total_sent += blocksize finally: - if total_sent > 0: - file.seek(offset) + file.seek(offset) async def _sendfile_native(self, transp, file, offset, count): resume_reading = transp.is_reading() diff --git a/contrib/tools/python3/Lib/asyncio/queues.py b/contrib/tools/python3/Lib/asyncio/queues.py index 756216fac80..30004f2bc9b 100644 --- a/contrib/tools/python3/Lib/asyncio/queues.py +++ b/contrib/tools/python3/Lib/asyncio/queues.py @@ -33,9 +33,9 @@ class QueueShutDown(Exception): class Queue(mixins._LoopBoundMixin): """A queue, useful for coordinating producer and consumer coroutines. - If maxsize is less than or equal to zero, the queue size is infinite. If it - is an integer greater than 0, then "await put()" will block when the - queue reaches maxsize, until an item is removed by get(). + If maxsize is less than or equal to zero, the queue size is infinite. + If it is an integer greater than 0, then "await put()" will block when + the queue reaches maxsize, until an item is removed by get(). Unlike queue.Queue, you can reliably know this Queue's size with qsize(), since your single-threaded asyncio application won't be @@ -174,8 +174,8 @@ class Queue(mixins._LoopBoundMixin): If queue is empty, wait until an item is available. - Raises QueueShutDown if the queue has been shut down and is empty, or - if the queue has been shut down immediately. + Raises QueueShutDown if the queue has been shut down and is empty, + or if the queue has been shut down immediately. """ while self.empty(): if self._is_shutdown and self.empty(): @@ -203,10 +203,11 @@ class Queue(mixins._LoopBoundMixin): def get_nowait(self): """Remove and return an item from the queue. - Return an item if one is immediately available, else raise QueueEmpty. + Return an item if one is immediately available, else raise + QueueEmpty. - Raises QueueShutDown if the queue has been shut down and is empty, or - if the queue has been shut down immediately. + Raises QueueShutDown if the queue has been shut down and is empty, + or if the queue has been shut down immediately. """ if self.empty(): if self._is_shutdown: @@ -223,12 +224,12 @@ class Queue(mixins._LoopBoundMixin): a subsequent call to task_done() tells the queue that the processing on the task is complete. - If a join() is currently blocking, it will resume when all items have - been processed (meaning that a task_done() call was received for every - item that had been put() into the queue). + If a join() is currently blocking, it will resume when all items + have been processed (meaning that a task_done() call was received + for every item that had been put() into the queue). - Raises ValueError if called more times than there were items placed in - the queue. + Raises ValueError if called more times than there were items placed + in the queue. """ if self._unfinished_tasks <= 0: raise ValueError('task_done() called too many times') @@ -239,10 +240,11 @@ class Queue(mixins._LoopBoundMixin): async def join(self): """Block until all items in the queue have been gotten and processed. - The count of unfinished tasks goes up whenever an item is added to the - queue. The count goes down whenever a consumer calls task_done() to - indicate that the item was retrieved and all work on it is complete. - When the count of unfinished tasks drops to zero, join() unblocks. + The count of unfinished tasks goes up whenever an item is added to + the queue. The count goes down whenever a consumer calls + task_done() to indicate that the item was retrieved and all work on + it is complete. When the count of unfinished tasks drops to zero, + join() unblocks. """ if self._unfinished_tasks > 0: await self._finished.wait() diff --git a/contrib/tools/python3/Lib/asyncio/runners.py b/contrib/tools/python3/Lib/asyncio/runners.py index 102ae78021b..c7bfdad319f 100644 --- a/contrib/tools/python3/Lib/asyncio/runners.py +++ b/contrib/tools/python3/Lib/asyncio/runners.py @@ -34,7 +34,8 @@ class Runner: with asyncio.Runner(debug=True) as runner: runner.run(main()) - The run() method can be called multiple times within the runner's context. + The run() method can be called multiple times within the runner's + context. This can be useful for interactive console (e.g. IPython), unittest runners, console tools, -- everywhere when async code diff --git a/contrib/tools/python3/Lib/asyncio/selector_events.py b/contrib/tools/python3/Lib/asyncio/selector_events.py index ff7e16df3c6..7c2062e3dd5 100644 --- a/contrib/tools/python3/Lib/asyncio/selector_events.py +++ b/contrib/tools/python3/Lib/asyncio/selector_events.py @@ -530,11 +530,12 @@ class BaseSelectorEventLoop(base_events.BaseEventLoop): async def sock_sendall(self, sock, data): """Send data to the socket. - The socket must be connected to a remote socket. This method continues - to send data from data until either all data has been sent or an - error occurs. None is returned on success. On error, an exception is - raised, and there is no way to determine how much data, if any, was - successfully processed by the receiving end of the connection. + The socket must be connected to a remote socket. This method + continues to send data from data until either all data has been + sent or an error occurs. None is returned on success. On error, + an exception is raised, and there is no way to determine how much + data, if any, was successfully processed by the receiving end of + the connection. """ base_events._check_ssl_socket(sock) if self._debug and sock.gettimeout() != 0: @@ -583,11 +584,12 @@ class BaseSelectorEventLoop(base_events.BaseEventLoop): async def sock_sendto(self, sock, data, address): """Send data to the socket. - The socket must be connected to a remote socket. This method continues - to send data from data until either all data has been sent or an - error occurs. None is returned on success. On error, an exception is - raised, and there is no way to determine how much data, if any, was - successfully processed by the receiving end of the connection. + The socket must be connected to a remote socket. This method + continues to send data from data until either all data has been + sent or an error occurs. None is returned on success. On error, + an exception is raised, and there is no way to determine how much + data, if any, was successfully processed by the receiving end of + the connection. """ base_events._check_ssl_socket(sock) if self._debug and sock.gettimeout() != 0: @@ -698,10 +700,11 @@ class BaseSelectorEventLoop(base_events.BaseEventLoop): async def sock_accept(self, sock): """Accept a connection. - The socket must be bound to an address and listening for connections. - The return value is a pair (conn, address) where conn is a new socket - object usable to send and receive data on the connection, and address - is the address bound to the socket on the other end of the connection. + The socket must be bound to an address and listening for + connections. The return value is a pair (conn, address) where + conn is a new socket object usable to send and receive data on the + connection, and address is the address bound to the socket on the + other end of the connection. """ base_events._check_ssl_socket(sock) if self._debug and sock.gettimeout() != 0: diff --git a/contrib/tools/python3/Lib/asyncio/streams.py b/contrib/tools/python3/Lib/asyncio/streams.py index 64aac4cc50d..dd8f6618623 100644 --- a/contrib/tools/python3/Lib/asyncio/streams.py +++ b/contrib/tools/python3/Lib/asyncio/streams.py @@ -541,17 +541,17 @@ class StreamReader: self._waiter = None async def readline(self): - """Read chunk of data from the stream until newline (b'\n') is found. + r"""Read chunk of data from the stream until newline (b'\n') is found. - On success, return chunk that ends with newline. If only partial + On success, return chunk that ends with newline. If only partial line can be read due to EOF, return incomplete line without - terminating newline. When EOF was reached while no bytes read, empty - bytes object is returned. + terminating newline. When EOF was reached while no bytes read, + empty bytes object is returned. - If limit is reached, ValueError will be raised. In that case, if + If limit is reached, ValueError will be raised. In that case, if newline was found, complete line including newline will be removed - from internal buffer. Else, internal buffer will be cleared. Limit is - compared against part of the line without newline. + from internal buffer. Else, internal buffer will be cleared. + Limit is compared against part of the line without newline. If stream was paused, this function will automatically resume it if needed. diff --git a/contrib/tools/python3/Lib/asyncio/tasks.py b/contrib/tools/python3/Lib/asyncio/tasks.py index dadcb5b5f36..e5e7d3e4aa9 100644 --- a/contrib/tools/python3/Lib/asyncio/tasks.py +++ b/contrib/tools/python3/Lib/asyncio/tasks.py @@ -640,10 +640,11 @@ def as_completed(fs, *, timeout=None): Run the supplied awaitables concurrently. The returned object can be iterated to obtain the results of the awaitables as they finish. - The object returned can be iterated as an asynchronous iterator or a plain - iterator. When asynchronous iteration is used, the originally-supplied - awaitables are yielded if they are tasks or futures. This makes it easy to - correlate previously-scheduled tasks with their results: + The object returned can be iterated as an asynchronous iterator or + a plain iterator. When asynchronous iteration is used, the + originally-supplied awaitables are yielded if they are tasks or + futures. This makes it easy to correlate previously-scheduled tasks + with their results: ipv4_connect = create_task(open_connection("127.0.0.1", 80)) ipv6_connect = create_task(open_connection("::1", 80)) @@ -659,26 +660,27 @@ def as_completed(fs, *, timeout=None): else: print("IPv4 connection established.") - During asynchronous iteration, implicitly-created tasks will be yielded for - supplied awaitables that aren't tasks or futures. + During asynchronous iteration, implicitly-created tasks will be + yielded for supplied awaitables that aren't tasks or futures. - When used as a plain iterator, each iteration yields a new coroutine that - returns the result or raises the exception of the next completed awaitable. - This pattern is compatible with Python versions older than 3.13: + When used as a plain iterator, each iteration yields a new coroutine + that returns the result or raises the exception of the next completed + awaitable. This pattern is compatible with Python versions older than + 3.13: ipv4_connect = create_task(open_connection("127.0.0.1", 80)) ipv6_connect = create_task(open_connection("::1", 80)) tasks = [ipv4_connect, ipv6_connect] for next_connect in as_completed(tasks): - # next_connect is not one of the original task objects. It must be - # awaited to obtain the result value or raise the exception of the - # awaitable that finishes next. + # next_connect is not one of the original task objects. It must + # be awaited to obtain the result value or raise the exception + # of the awaitable that finishes next. reader, writer = await next_connect - A TimeoutError is raised if the timeout occurs before all awaitables are - done. This is raised by the async for loop during asynchronous iteration or - by the coroutines yielded during plain iteration. + A TimeoutError is raised if the timeout occurs before all awaitables + are done. This is raised by the async for loop during asynchronous + iteration or by the coroutines yielded during plain iteration. """ if inspect.isawaitable(fs): raise TypeError( @@ -1007,21 +1009,22 @@ def run_coroutine_threadsafe(coro, loop): def create_eager_task_factory(custom_task_constructor): """Create a function suitable for use as a task factory on an event-loop. - Example usage: + Example usage: - loop.set_task_factory( - asyncio.create_eager_task_factory(my_task_constructor)) + loop.set_task_factory( + asyncio.create_eager_task_factory(my_task_constructor)) - Now, tasks created will be started immediately (rather than being first - scheduled to an event loop). The constructor argument can be any callable - that returns a Task-compatible object and has a signature compatible - with `Task.__init__`; it must have the `eager_start` keyword argument. + Now, tasks created will be started immediately (rather than being first + scheduled to an event loop). The constructor argument can be any + callable that returns a Task-compatible object and has a signature + compatible with `Task.__init__`; it must have the `eager_start` + keyword argument. - Most applications will use `Task` for `custom_task_constructor` and in - this case there's no need to call `create_eager_task_factory()` - directly. Instead the global `eager_task_factory` instance can be - used. E.g. `loop.set_task_factory(asyncio.eager_task_factory)`. - """ + Most applications will use `Task` for `custom_task_constructor` and in + this case there's no need to call `create_eager_task_factory()` + directly. Instead the global `eager_task_factory` instance can be + used. E.g. `loop.set_task_factory(asyncio.eager_task_factory)`. + """ def factory(loop, coro, *, name=None, context=None): return custom_task_constructor( diff --git a/contrib/tools/python3/Lib/asyncio/threads.py b/contrib/tools/python3/Lib/asyncio/threads.py index db048a8231d..5001351b097 100644 --- a/contrib/tools/python3/Lib/asyncio/threads.py +++ b/contrib/tools/python3/Lib/asyncio/threads.py @@ -17,7 +17,8 @@ async def to_thread(func, /, *args, **kwargs): allowing context variables from the main thread to be accessed in the separate thread. - Return a coroutine that can be awaited to get the eventual result of *func*. + Return a coroutine that can be awaited to get the eventual result of + *func*. """ loop = events.get_running_loop() ctx = contextvars.copy_context() diff --git a/contrib/tools/python3/Lib/asyncio/timeouts.py b/contrib/tools/python3/Lib/asyncio/timeouts.py index e6f5100691d..7ac664be47c 100644 --- a/contrib/tools/python3/Lib/asyncio/timeouts.py +++ b/contrib/tools/python3/Lib/asyncio/timeouts.py @@ -27,7 +27,8 @@ class _State(enum.Enum): class Timeout: """Asynchronous context manager for cancelling overdue coroutines. - Use `timeout()` or `timeout_at()` rather than instantiating this class directly. + Use `timeout()` or `timeout_at()` rather than instantiating this class + directly. """ def __init__(self, when: Optional[float]) -> None: diff --git a/contrib/tools/python3/Lib/asyncio/unix_events.py b/contrib/tools/python3/Lib/asyncio/unix_events.py index 41ccf1b78fb..9222a8769e9 100644 --- a/contrib/tools/python3/Lib/asyncio/unix_events.py +++ b/contrib/tools/python3/Lib/asyncio/unix_events.py @@ -58,7 +58,8 @@ def waitstatus_to_exitcode(status): class _UnixSelectorEventLoop(selector_events.BaseSelectorEventLoop): """Unix event loop. - Adds signal handling and UNIX Domain Socket support to SelectorEventLoop. + Adds signal handling and UNIX Domain Socket support to + SelectorEventLoop. """ def __init__(self, selector=None): @@ -395,12 +396,12 @@ class _UnixSelectorEventLoop(selector_events.BaseSelectorEventLoop): # order to simplify the common case. self.remove_writer(registered_fd) if fut.cancelled(): - self._sock_sendfile_update_filepos(fileno, offset, total_sent) + self._sock_sendfile_update_filepos(fileno, offset) return if count: blocksize = count - total_sent if blocksize <= 0: - self._sock_sendfile_update_filepos(fileno, offset, total_sent) + self._sock_sendfile_update_filepos(fileno, offset) fut.set_result(total_sent) return @@ -434,20 +435,20 @@ class _UnixSelectorEventLoop(selector_events.BaseSelectorEventLoop): # plain send(). err = exceptions.SendfileNotAvailableError( "os.sendfile call failed") - self._sock_sendfile_update_filepos(fileno, offset, total_sent) + self._sock_sendfile_update_filepos(fileno, offset) fut.set_exception(err) else: - self._sock_sendfile_update_filepos(fileno, offset, total_sent) + self._sock_sendfile_update_filepos(fileno, offset) fut.set_exception(exc) except (SystemExit, KeyboardInterrupt): raise except BaseException as exc: - self._sock_sendfile_update_filepos(fileno, offset, total_sent) + self._sock_sendfile_update_filepos(fileno, offset) fut.set_exception(exc) else: if sent == 0: # EOF - self._sock_sendfile_update_filepos(fileno, offset, total_sent) + self._sock_sendfile_update_filepos(fileno, offset) fut.set_result(total_sent) else: offset += sent @@ -458,9 +459,9 @@ class _UnixSelectorEventLoop(selector_events.BaseSelectorEventLoop): fd, sock, fileno, offset, count, blocksize, total_sent) - def _sock_sendfile_update_filepos(self, fileno, offset, total_sent): - if total_sent > 0: - os.lseek(fileno, offset, os.SEEK_SET) + def _sock_sendfile_update_filepos(self, fileno, offset): + # After this helper runs, the source fd's lseek pointer is at offset." + os.lseek(fileno, offset, os.SEEK_SET) def _sock_add_cancellation_callback(self, fut, sock): def cb(fut): diff --git a/contrib/tools/python3/Lib/asyncio/windows_events.py b/contrib/tools/python3/Lib/asyncio/windows_events.py index bf99bc271c7..a36832f7f9f 100644 --- a/contrib/tools/python3/Lib/asyncio/windows_events.py +++ b/contrib/tools/python3/Lib/asyncio/windows_events.py @@ -610,6 +610,9 @@ class IocpProactor: ov = _overlapped.Overlapped(NULL) offset_low = offset & 0xffff_ffff offset_high = (offset >> 32) & 0xffff_ffff + # TransmitFile ignores OVERLAPPED.Offset for handles not opened with + # FILE_FLAG_OVERLAPPED, so seek the CRT file pointer to match. + file.seek(offset) ov.TransmitFile(sock.fileno(), msvcrt.get_osfhandle(file.fileno()), offset_low, offset_high, diff --git a/contrib/tools/python3/Lib/asyncio/windows_utils.py b/contrib/tools/python3/Lib/asyncio/windows_utils.py index acd49441131..d6393f0b1ff 100644 --- a/contrib/tools/python3/Lib/asyncio/windows_utils.py +++ b/contrib/tools/python3/Lib/asyncio/windows_utils.py @@ -111,8 +111,9 @@ class PipeHandle: def close(self, *, CloseHandle=_winapi.CloseHandle): if self._handle is not None: - CloseHandle(self._handle) + handle = self._handle self._handle = None + CloseHandle(handle) def __del__(self, _warn=warnings.warn): if self._handle is not None: diff --git a/contrib/tools/python3/Lib/base64.py b/contrib/tools/python3/Lib/base64.py index 6636e06382f..888443c472c 100755 --- a/contrib/tools/python3/Lib/base64.py +++ b/contrib/tools/python3/Lib/base64.py @@ -328,17 +328,20 @@ def a85encode(b, *, foldspaces=False, wrapcol=0, pad=False, adobe=False): foldspaces is an optional flag that uses the special short sequence 'y' instead of 4 consecutive spaces (ASCII 0x20) as supported by 'btoa'. This - feature is not supported by the "standard" Adobe encoding. + feature is not supported by the standard encoding used in PDF. - wrapcol controls whether the output should have newline (b'\\n') characters - added to it. If this is non-zero, each output line will be at most this - many characters long, excluding the trailing newline. + If wrapcol is non-zero, insert a newline (b'\\n') character after at most + every wrapcol characters. - pad controls whether the input is padded to a multiple of 4 before - encoding. Note that the btoa implementation always pads. + pad controls whether zero-padding applied to the end of the input + is fully retained in the output encoding, as done by btoa, + producing an exact multiple of 5 bytes of output. + + adobe controls whether the encoded byte sequence is framed with <~ + and ~>, as in a PostScript base-85 string literal. Note that + while ASCII85Decode streams in PDF documents must be terminated + with ~>, they must not use a leading <~. - adobe controls whether the encoded byte sequence is framed with <~ and ~>, - which is used by the Adobe implementation. """ global _a85chars, _a85chars2 # Delay the initialization of tables to not waste memory @@ -367,12 +370,14 @@ def a85encode(b, *, foldspaces=False, wrapcol=0, pad=False, adobe=False): def a85decode(b, *, foldspaces=False, adobe=False, ignorechars=b' \t\n\r\v'): """Decode the Ascii85 encoded bytes-like object or ASCII string b. - foldspaces is a flag that specifies whether the 'y' short sequence should be - accepted as shorthand for 4 consecutive spaces (ASCII 0x20). This feature is - not supported by the "standard" Adobe encoding. + foldspaces is a flag that specifies whether the 'y' short sequence + should be accepted as shorthand for 4 consecutive spaces (ASCII + 0x20). This feature is not supported by the standard Ascii85 + encoding used in PDF and PostScript. - adobe controls whether the input sequence is in Adobe Ascii85 format (i.e. - is framed with <~ and ~>). + adobe controls whether the <~ and ~> markers are present. While + the leading <~ is not required, the input must end with ~>, or a + ValueError is raised. ignorechars should be a byte string containing characters to ignore from the input. This should only contain whitespace characters, and by default @@ -445,8 +450,10 @@ _b85dec = None def b85encode(b, pad=False): """Encode bytes-like object b in base85 format and return a bytes object. - If pad is true, the input is padded with b'\\0' so its length is a multiple of - 4 bytes before encoding. + The input is padded with b'\0' so its length is a multiple of 4 + bytes before encoding. If pad is true, all the resulting + characters are retained in the output, which will always be a + multiple of 5 bytes. """ global _b85chars, _b85chars2 # Delay the initialization of tables to not waste memory diff --git a/contrib/tools/python3/Lib/concurrent/futures/_base.py b/contrib/tools/python3/Lib/concurrent/futures/_base.py index 7d69a5baead..d4819f19e5e 100644 --- a/contrib/tools/python3/Lib/concurrent/futures/_base.py +++ b/contrib/tools/python3/Lib/concurrent/futures/_base.py @@ -200,15 +200,15 @@ def as_completed(fs, timeout=None): """An iterator over the given futures that yields each as it completes. Args: - fs: The sequence of Futures (possibly created by different Executors) to - iterate over. - timeout: The maximum number of seconds to wait. If None, then there - is no limit on the wait time. + fs: The sequence of Futures (possibly created by different + Executors) to iterate over. + timeout: The maximum number of seconds to wait. If None, then + there is no limit on the wait time. Returns: - An iterator that yields the given Futures as they complete (finished or - cancelled). If any given Futures are duplicated, they will be returned - once. + An iterator that yields the given Futures as they complete + (finished or cancelled). If any given Futures are duplicated, + they will be returned once. Raises: TimeoutError: If the entire result iterator could not be generated @@ -264,19 +264,20 @@ def wait(fs, timeout=None, return_when=ALL_COMPLETED): """Wait for the futures in the given sequence to complete. Args: - fs: The sequence of Futures (possibly created by different Executors) to - wait upon. - timeout: The maximum number of seconds to wait. If None, then there - is no limit on the wait time. - return_when: Indicates when this function should return. The options - are: + fs: The sequence of Futures (possibly created by different + Executors) to wait upon. + timeout: The maximum number of seconds to wait. If None, then + there is no limit on the wait time. + return_when: Indicates when this function should return. + The options are: FIRST_COMPLETED - Return when any future finishes or is cancelled. FIRST_EXCEPTION - Return when any future finishes by raising an - exception. If no future raises an exception + exception. If no future raises an exception then it is equivalent to ALL_COMPLETED. - ALL_COMPLETED - Return when all futures finish or are cancelled. + ALL_COMPLETED - Return when all futures finish or are + cancelled. Returns: A named 2-tuple of sets. The first set, named 'done', contains the @@ -410,11 +411,12 @@ class Future(object): Args: fn: A callable that will be called with this future as its only - argument when the future completes or is cancelled. The callable - will always be called by a thread in the same process in which - it was added. If the future has already completed or been - cancelled then the callable will be called immediately. These - callables are called in the order that they were added. + argument when the future completes or is cancelled. The + callable will always be called by a thread in the same + process in which it was added. If the future has already + completed or been cancelled then the callable will be + called immediately. These callables are called in the + order that they were added. """ with self._condition: if self._state not in [CANCELLED, CANCELLED_AND_NOTIFIED, FINISHED]: @@ -429,17 +431,19 @@ class Future(object): """Return the result of the call that the future represents. Args: - timeout: The number of seconds to wait for the result if the future - isn't done. If None, then there is no limit on the wait time. + timeout: The number of seconds to wait for the result if the + future isn't done. If None, then there is no limit on the + wait time. Returns: The result of the call that the future represents. Raises: CancelledError: If the future was cancelled. - TimeoutError: If the future didn't finish executing before the given - timeout. - Exception: If the call raised then that exception will be raised. + TimeoutError: If the future didn't finish executing before the + given timeout. + Exception: If the call raised then that exception will be + raised. """ try: with self._condition: @@ -465,17 +469,17 @@ class Future(object): Args: timeout: The number of seconds to wait for the exception if the - future isn't done. If None, then there is no limit on the wait - time. + future isn't done. If None, then there is no limit on the + wait time. Returns: - The exception raised by the call that the future represents or None - if the call completed without raising. + The exception raised by the call that the future represents or + None if the call completed without raising. Raises: CancelledError: If the future was cancelled. - TimeoutError: If the future didn't finish executing before the given - timeout. + TimeoutError: If the future didn't finish executing before the + given timeout. """ with self._condition: @@ -500,22 +504,23 @@ class Future(object): Should only be used by Executor implementations and unit tests. If the future has been cancelled (cancel() was called and returned - True) then any threads waiting on the future completing (though calls - to as_completed() or wait()) are notified and False is returned. + True) then any threads waiting on the future completing (though + calls to as_completed() or wait()) are notified and False is + returned. If the future was not cancelled then it is put in the running state (future calls to running() will return True) and True is returned. This method should be called by Executor implementations before - executing the work associated with this future. If this method returns - False then the work should not be executed. + executing the work associated with this future. If this method + returns False then the work should not be executed. Returns: False if the Future was cancelled, True otherwise. Raises: - RuntimeError: if this method was already called or if set_result() - or set_exception() was called. + RuntimeError: if this method was already called or if + set_result() or set_exception() was called. """ with self._condition: if self._state == CANCELLED: @@ -572,8 +577,9 @@ class Executor(object): def submit(self, fn, /, *args, **kwargs): """Submits a callable to be executed with the given arguments. - Schedules the callable to be executed as fn(*args, **kwargs) and returns - a Future instance representing the execution of the callable. + Schedules the callable to be executed as fn(*args, **kwargs) and + returns a Future instance representing the execution of the + callable. Returns: A Future representing the given call. @@ -586,20 +592,20 @@ class Executor(object): Args: fn: A callable that will take as many arguments as there are passed iterables. - timeout: The maximum number of seconds to wait. If None, then there - is no limit on the wait time. - chunksize: The size of the chunks the iterable will be broken into - before being passed to a child process. This argument is only - used by ProcessPoolExecutor; it is ignored by + timeout: The maximum number of seconds to wait. If None, then + there is no limit on the wait time. + chunksize: The size of the chunks the iterable will be broken + into before being passed to a child process. This argument + is only used by ProcessPoolExecutor; it is ignored by ThreadPoolExecutor. Returns: - An iterator equivalent to: map(func, *iterables) but the calls may - be evaluated out-of-order. + An iterator equivalent to: map(func, *iterables) but the calls + may be evaluated out-of-order. Raises: - TimeoutError: If the entire result iterator could not be generated - before the given timeout. + TimeoutError: If the entire result iterator could not be + generated before the given timeout. Exception: If fn(*args) raises for any values. """ if timeout is not None: @@ -632,8 +638,8 @@ class Executor(object): Args: wait: If True then shutdown will not return until all running - futures have finished executing and the resources used by the - executor have been reclaimed. + futures have finished executing and the resources used by + the executor have been reclaimed. cancel_futures: If True then shutdown will cancel all pending futures. Futures that are completed or running will not be cancelled. diff --git a/contrib/tools/python3/Lib/concurrent/futures/process.py b/contrib/tools/python3/Lib/concurrent/futures/process.py index 0dee8303ba2..8ff717f5e00 100644 --- a/contrib/tools/python3/Lib/concurrent/futures/process.py +++ b/contrib/tools/python3/Lib/concurrent/futures/process.py @@ -634,19 +634,21 @@ class ProcessPoolExecutor(_base.Executor): Args: max_workers: The maximum number of processes that can be used to - execute the given calls. If None or not given then as many - worker processes will be created as the machine has processors. - mp_context: A multiprocessing context to launch the workers created - using the multiprocessing.get_context('start method') API. This - object should provide SimpleQueue, Queue and Process. + execute the given calls. If None or not given then as many + worker processes will be created as the machine has + processors. + mp_context: A multiprocessing context to launch the workers + created using the multiprocessing.get_context('start method') + API. This object should provide SimpleQueue, Queue and + Process. initializer: A callable used to initialize worker processes. initargs: A tuple of arguments to pass to the initializer. - max_tasks_per_child: The maximum number of tasks a worker process - can complete before it will exit and be replaced with a fresh - worker process. The default of None means worker process will - live as long as the executor. Requires a non-'fork' mp_context - start method. When given, we default to using 'spawn' if no - mp_context is supplied. + max_tasks_per_child: The maximum number of tasks a worker + process can complete before it will exit and be replaced + with a fresh worker process. The default of None means + worker process will live as long as the executor. Requires + a non-'fork' mp_context start method. When given, we + default to using 'spawn' if no mp_context is supplied. """ _check_system_limits() @@ -816,19 +818,20 @@ class ProcessPoolExecutor(_base.Executor): Args: fn: A callable that will take as many arguments as there are passed iterables. - timeout: The maximum number of seconds to wait. If None, then there - is no limit on the wait time. - chunksize: If greater than one, the iterables will be chopped into - chunks of size chunksize and submitted to the process pool. - If set to one, the items in the list will be sent one at a time. + timeout: The maximum number of seconds to wait. If None, then + there is no limit on the wait time. + chunksize: If greater than one, the iterables will be chopped + into chunks of size chunksize and submitted to the process + pool. If set to one, the items in the list will be sent + one at a time. Returns: - An iterator equivalent to: map(func, *iterables) but the calls may - be evaluated out-of-order. + An iterator equivalent to: map(func, *iterables) but the calls + may be evaluated out-of-order. Raises: - TimeoutError: If the entire result iterator could not be generated - before the given timeout. + TimeoutError: If the entire result iterator could not be + generated before the given timeout. Exception: If fn(*args) raises for any values. """ if chunksize < 1: diff --git a/contrib/tools/python3/Lib/configparser.py b/contrib/tools/python3/Lib/configparser.py index 05b86acb919..3968ac45eed 100644 --- a/contrib/tools/python3/Lib/configparser.py +++ b/contrib/tools/python3/Lib/configparser.py @@ -316,12 +316,15 @@ class ParsingError(Error): def append(self, lineno, line): self.errors.append((lineno, line)) - self.message += '\n\t[line %2d]: %s' % (lineno, repr(line)) + self.message += f'\n\t[line {lineno:2d}]: {line!r}' def combine(self, others): + messages = [self.message] for other in others: - for error in other.errors: - self.append(*error) + for lineno, line in other.errors: + self.errors.append((lineno, line)) + messages.append(f'\n\t[line {lineno:2d}]: {line!r}') + self.message = "".join(messages) return self @staticmethod @@ -597,7 +600,9 @@ class RawConfigParser(MutableMapping): \] # ] """ _OPT_TMPL = r""" - (?P<option>.*?) # very permissive! + (?P<option> # very permissive! + (?:(?!{delim})\S)* # non-delimiter non-whitespace + (?:\s+(?:(?!{delim})\S)+)*) # optionally more words \s*(?P<vi>{delim})\s* # any number of space/tab, # followed by any of the # allowed delimiters, @@ -605,7 +610,9 @@ class RawConfigParser(MutableMapping): (?P<value>.*)$ # everything up to eol """ _OPT_NV_TMPL = r""" - (?P<option>.*?) # very permissive! + (?P<option> # very permissive! + (?:(?!{delim})\S)* # non-delimiter non-whitespace + (?:\s+(?:(?!{delim})\S)+)*) # optionally more words \s*(?: # any number of space/tab, (?P<vi>{delim})\s* # optionally followed by # any of the allowed diff --git a/contrib/tools/python3/Lib/curses/textpad.py b/contrib/tools/python3/Lib/curses/textpad.py index aa87061b8d7..3a98fd6043a 100644 --- a/contrib/tools/python3/Lib/curses/textpad.py +++ b/contrib/tools/python3/Lib/curses/textpad.py @@ -23,7 +23,8 @@ class Textbox: Ctrl-A Go to left edge of window. Ctrl-B Cursor left, wrapping to previous line if appropriate. Ctrl-D Delete character under cursor. - Ctrl-E Go to right edge (stripspaces off) or end of line (stripspaces on). + Ctrl-E Go to right edge (stripspaces off) or end of line + (stripspaces on). Ctrl-F Cursor right, wrapping to next line when appropriate. Ctrl-G Terminate, returning the window contents. Ctrl-H Delete character backward. @@ -34,11 +35,12 @@ class Textbox: Ctrl-O Insert a blank line at cursor location. Ctrl-P Cursor up; move up one line. - Move operations do nothing if the cursor is at an edge where the movement - is not possible. The following synonyms are supported where possible: + Move operations do nothing if the cursor is at an edge where the + movement is not possible. The following synonyms are supported where + possible: - KEY_LEFT = Ctrl-B, KEY_RIGHT = Ctrl-F, KEY_UP = Ctrl-P, KEY_DOWN = Ctrl-N - KEY_BACKSPACE = Ctrl-h + KEY_LEFT = Ctrl-B, KEY_RIGHT = Ctrl-F, KEY_UP = Ctrl-P, + KEY_DOWN = Ctrl-N, KEY_BACKSPACE = Ctrl-h """ def __init__(self, win, insert_mode=False): self.win = win diff --git a/contrib/tools/python3/Lib/dataclasses.py b/contrib/tools/python3/Lib/dataclasses.py index 7883ce78e57..8703e076389 100644 --- a/contrib/tools/python3/Lib/dataclasses.py +++ b/contrib/tools/python3/Lib/dataclasses.py @@ -665,10 +665,10 @@ def _init_fn(fields, std_fields, kw_only_fields, frozen, has_post_init, return_type=None) -def _frozen_get_del_attr(cls, fields, func_builder): - locals = {'cls': cls, +def _frozen_set_del_attr(cls, fields, func_builder): + locals = {'__class__': cls, 'FrozenInstanceError': FrozenInstanceError} - condition = 'type(self) is cls' + condition = 'type(self) is __class__' if fields: condition += ' or name in {' + ', '.join(repr(f.name) for f in fields) + '}' @@ -676,14 +676,14 @@ def _frozen_get_del_attr(cls, fields, func_builder): ('self', 'name', 'value'), (f' if {condition}:', ' raise FrozenInstanceError(f"cannot assign to field {name!r}")', - f' super(cls, self).__setattr__(name, value)'), + f' super(__class__, self).__setattr__(name, value)'), locals=locals, overwrite_error=True) func_builder.add_fn('__delattr__', ('self', 'name'), (f' if {condition}:', ' raise FrozenInstanceError(f"cannot delete field {name!r}")', - f' super(cls, self).__delattr__(name)'), + f' super(__class__, self).__delattr__(name)'), locals=locals, overwrite_error=True) @@ -1141,7 +1141,7 @@ def _process_class(cls, init, repr, eq, order, unsafe_hash, frozen, overwrite_error='Consider using functools.total_ordering') if frozen: - _frozen_get_del_attr(cls, field_list, func_builder) + _frozen_set_del_attr(cls, field_list, func_builder) # Decide if/how we're going to create a hash function. hash_action = _hash_action[bool(unsafe_hash), @@ -1219,6 +1219,35 @@ def _get_slots(cls): raise TypeError(f"Slots of '{cls.__name__}' cannot be determined") +def _update_func_cell_for__class__(f, oldcls, newcls): + # Returns True if we update a cell, else False. + if f is None: + # f will be None in the case of a property where not all of + # fget, fset, and fdel are used. Nothing to do in that case. + return False + try: + idx = f.__code__.co_freevars.index("__class__") + except ValueError: + # This function doesn't reference __class__, so nothing to do. + return False + # Fix the cell to point to the new class, if it's already pointing + # at the old class. + closure = f.__closure__[idx] + + try: + contents = closure.cell_contents + except ValueError: + # Cell is empty + return False + + # This check makes it so we avoid updating an incorrect cell if the + # class body contains a function that was defined in a different class. + if contents is oldcls: + closure.cell_contents = newcls + return True + return False + + def _add_slots(cls, is_frozen, weakref_slot): # Need to create a new class, since we can't set __slots__ # after a class has been created. @@ -1260,18 +1289,37 @@ def _add_slots(cls, is_frozen, weakref_slot): # And finally create the class. qualname = getattr(cls, '__qualname__', None) - cls = type(cls)(cls.__name__, cls.__bases__, cls_dict) + newcls = type(cls)(cls.__name__, cls.__bases__, cls_dict) if qualname is not None: - cls.__qualname__ = qualname + newcls.__qualname__ = qualname if is_frozen: # Need this for pickling frozen classes with slots. if '__getstate__' not in cls_dict: - cls.__getstate__ = _dataclass_getstate + newcls.__getstate__ = _dataclass_getstate if '__setstate__' not in cls_dict: - cls.__setstate__ = _dataclass_setstate + newcls.__setstate__ = _dataclass_setstate - return cls + # Fix up any closures which reference __class__. This is used to + # fix zero argument super so that it points to the correct class + # (the newly created one, which we're returning) and not the + # original class. We can break out of this loop as soon as we + # make an update, since all closures for a class will share a + # given cell. + for member in newcls.__dict__.values(): + # If this is a wrapped function, unwrap it. + member = inspect.unwrap(member) + + if isinstance(member, types.FunctionType): + if _update_func_cell_for__class__(member, cls, newcls): + break + elif isinstance(member, property): + if (_update_func_cell_for__class__(member.fget, cls, newcls) + or _update_func_cell_for__class__(member.fset, cls, newcls) + or _update_func_cell_for__class__(member.fdel, cls, newcls)): + break + + return newcls def dataclass(cls=None, /, *, init=True, repr=True, eq=True, order=False, diff --git a/contrib/tools/python3/Lib/email/_header_value_parser.py b/contrib/tools/python3/Lib/email/_header_value_parser.py index 03fedd99539..c02175e24e0 100644 --- a/contrib/tools/python3/Lib/email/_header_value_parser.py +++ b/contrib/tools/python3/Lib/email/_header_value_parser.py @@ -639,11 +639,11 @@ class LocalPart(TokenList): for tok in self[0] + [DOT]: if tok.token_type == 'cfws': continue - if (last_is_tl and tok.token_type == 'dot' and + if (last_is_tl and tok.token_type == 'dot' and last and last[-1].token_type == 'cfws'): res[-1] = TokenList(last[:-1]) is_tl = isinstance(tok, TokenList) - if (is_tl and last.token_type == 'dot' and + if (is_tl and last.token_type == 'dot' and tok and tok[0].token_type == 'cfws'): res.append(TokenList(tok[1:])) else: @@ -1245,8 +1245,7 @@ def get_bare_quoted_string(value): bare_quoted_string = BareQuotedString() value = value[1:] if value and value[0] == '"': - token, value = get_qcontent(value) - bare_quoted_string.append(token) + return bare_quoted_string, value[1:] while value and value[0] != '"': if value[0] in WSP: token, value = get_fws(value) @@ -1464,6 +1463,16 @@ def get_phrase(value): else: try: token, value = get_word(value) + if (token[0].token_type == 'encoded-word' + and phrase + and phrase[-1].token_type == 'atom' + and len(phrase[-1]) > 1 + and phrase[-1][-2].token_type == 'encoded-word' + and phrase[-1][-1].token_type == 'cfws' + and not phrase[-1][-1].comments + ): + # linear ws between ews needs special handing... + phrase[-1][-1] = EWWhiteSpaceTerminal(phrase[-1], 'fws') except errors.HeaderParseError: if value[0] in CFWS_LEADER: token, value = get_cfws(value) @@ -2059,12 +2068,10 @@ def get_address_list(value): address_list.defects.append(errors.InvalidHeaderDefect( "invalid address in address-list")) if value and value[0] != ',': - # Crap after address; treat it as an invalid mailbox. - # The mailbox info will still be available. - mailbox = address_list[-1][0] - mailbox.token_type = 'invalid-mailbox' + # Crap after address: add it to the address list + # as an invalid mailbox token, value = get_invalid_mailbox(value, ',') - mailbox.extend(token) + address_list.append(Address([token])) address_list.defects.append(errors.InvalidHeaderDefect( "invalid address in address-list")) if value: # Must be a , at this point. diff --git a/contrib/tools/python3/Lib/email/_parseaddr.py b/contrib/tools/python3/Lib/email/_parseaddr.py index 565af0cf361..fe63c7ee0c7 100644 --- a/contrib/tools/python3/Lib/email/_parseaddr.py +++ b/contrib/tools/python3/Lib/email/_parseaddr.py @@ -59,7 +59,7 @@ def _parsedate_tz(data): The last (additional) element is the time zone offset in seconds, except if the timezone was specified as -0000. In that case the last element is - None. This indicates a UTC timestamp that explicitly declaims knowledge of + None. This indicates a UTC timestamp that explicitly disclaims knowledge of the source timezone, as opposed to a +0000 timestamp that indicates the source timezone really was UTC. diff --git a/contrib/tools/python3/Lib/email/charset.py b/contrib/tools/python3/Lib/email/charset.py index 043801107b6..db5d40e0288 100644 --- a/contrib/tools/python3/Lib/email/charset.py +++ b/contrib/tools/python3/Lib/email/charset.py @@ -93,8 +93,6 @@ ALIASES = { # Map charsets to their Unicode codec strings. CODEC_MAP = { - 'gb2312': 'eucgb2312_cn', - 'big5': 'big5_tw', # Hack: We don't want *any* conversion for stuff marked us-ascii, as all # sorts of garbage might be sent to us in the guise of 7-bit us-ascii. # Let that stuff pass through without conversion to/from Unicode. diff --git a/contrib/tools/python3/Lib/email/generator.py b/contrib/tools/python3/Lib/email/generator.py index a03eb1fbbc9..444d7b0fae4 100644 --- a/contrib/tools/python3/Lib/email/generator.py +++ b/contrib/tools/python3/Lib/email/generator.py @@ -392,7 +392,7 @@ class Generator: b = boundary counter = 0 while True: - cre = cls._compile_re('^--' + re.escape(b) + '(--)?$', re.MULTILINE) + cre = cls._compile_re('^--' + re.escape(b) + '(--)?\r?$', re.MULTILINE) if not cre.search(text): break b = boundary + '.' + str(counter) diff --git a/contrib/tools/python3/Lib/email/quoprimime.py b/contrib/tools/python3/Lib/email/quoprimime.py index 27fcbb5a26e..a5a6eef0b6d 100644 --- a/contrib/tools/python3/Lib/email/quoprimime.py +++ b/contrib/tools/python3/Lib/email/quoprimime.py @@ -272,7 +272,7 @@ def decode(encoded, eol=NL): decoded += eol # Special case if original string did not end with eol if encoded[-1] not in '\r\n' and decoded.endswith(eol): - decoded = decoded[:-1] + decoded = decoded[:-len(eol)] return decoded diff --git a/contrib/tools/python3/Lib/encodings/aliases.py b/contrib/tools/python3/Lib/encodings/aliases.py index 6a5ca046b5e..03645b8f5fa 100644 --- a/contrib/tools/python3/Lib/encodings/aliases.py +++ b/contrib/tools/python3/Lib/encodings/aliases.py @@ -71,6 +71,10 @@ aliases = { # cp1140 codec '1140' : 'cp1140', + 'cp01140' : 'cp1140', + 'csibm01140' : 'cp1140', + 'ebcdic_us_37_euro' : 'cp1140', + 'ibm01140' : 'cp1140', 'ibm1140' : 'cp1140', # cp1250 codec @@ -159,8 +163,12 @@ aliases = { # cp858 codec '858' : 'cp858', + 'cp00858' : 'cp858', + 'csibm00858' : 'cp858', 'csibm858' : 'cp858', + 'ibm00858' : 'cp858', 'ibm858' : 'cp858', + 'pc_multilingual_850_euro' : 'cp858', # cp860 codec '860' : 'cp860', diff --git a/contrib/tools/python3/Lib/ensurepip/__init__.py b/contrib/tools/python3/Lib/ensurepip/__init__.py index 9f4e64bc78b..d2f310a7c9f 100644 --- a/contrib/tools/python3/Lib/ensurepip/__init__.py +++ b/contrib/tools/python3/Lib/ensurepip/__init__.py @@ -10,7 +10,7 @@ from shutil import copy2 __all__ = ["version", "bootstrap"] -_PIP_VERSION = "26.0.1" +_PIP_VERSION = "26.1.2" # Directory of system wheel packages. Some Linux distribution packaging # policies recommend against bundling dependencies. For example, Fedora diff --git a/contrib/tools/python3/Lib/enum.py b/contrib/tools/python3/Lib/enum.py index 5e7b00654dd..dbf7bd343ab 100644 --- a/contrib/tools/python3/Lib/enum.py +++ b/contrib/tools/python3/Lib/enum.py @@ -697,9 +697,9 @@ class EnumType(type): """ Either returns an existing member, or creates a new enum class. - This method is used both when an enum class is given a value to match - to an enumeration member (i.e. Color(3)) and for the functional API - (i.e. Color = Enum('Color', names='RED GREEN BLUE')). + This method is used both when an enum class is given a value to + match to an enumeration member (i.e. Color(3)) and for the + functional API (i.e. Color = Enum('Color', names='RED GREEN BLUE')). The value lookup branch is chosen if the enum is final. @@ -707,16 +707,17 @@ class EnumType(type): `value` will be the name of the new class. - `names` should be either a string of white-space/comma delimited names - (values will start at `start`), or an iterator/mapping of name, value pairs. + `names` should be either a string of white-space/comma delimited + names (values will start at `start`), or an iterator/mapping of + name, value pairs. `module` should be set to the module this class is being created in; - if it is not set, an attempt to find that module will be made, but if - it fails the class will not be picklable. + if it is not set, an attempt to find that module will be made, but + if it fails the class will not be picklable. - `qualname` should be set to the actual location this class can be found - at in its module; by default it is set to the global scope. If this is - not correct, unpickling will fail in some circumstances. + `qualname` should be set to the actual location this class can be + found at in its module; by default it is set to the global scope. + If this is not correct, unpickling will fail in some circumstances. `type`, if set, will be mixed in as the first base class. """ @@ -810,8 +811,8 @@ class EnumType(type): """ Returns a mapping of member name->value. - This mapping lists all enum members, including aliases. Note that this - is a read-only view of the internal mapping. + This mapping lists all enum members, including aliases. Note that + this is a read-only view of the internal mapping. """ return MappingProxyType(cls._member_map_) diff --git a/contrib/tools/python3/Lib/ftplib.py b/contrib/tools/python3/Lib/ftplib.py index 10c5d1ea08a..463da58de85 100644 --- a/contrib/tools/python3/Lib/ftplib.py +++ b/contrib/tools/python3/Lib/ftplib.py @@ -883,7 +883,16 @@ def ftpcp(source, sourcename, target, targetname = '', type = 'I'): type = 'TYPE ' + type source.voidcmd(type) target.voidcmd(type) - sourcehost, sourceport = parse227(source.sendcmd('PASV')) + # Don't trust the IPv4 address the source server advertises in its PASV + # reply: a malicious source could otherwise point the target's data + # connection at an arbitrary host (SSRF). A caller that needs the old + # behavior can set trust_server_pasv_ipv4_address on the source FTP + # object. See FTP.makepasv(), which applies the same rule. + untrusted_host, sourceport = parse227(source.sendcmd('PASV')) + if source.trust_server_pasv_ipv4_address: + sourcehost = untrusted_host + else: + sourcehost = source.sock.getpeername()[0] target.sendport(sourcehost, sourceport) # RFC 959: the user must "listen" [...] BEFORE sending the # transfer request. diff --git a/contrib/tools/python3/Lib/functools.py b/contrib/tools/python3/Lib/functools.py index 0dee17e5bcd..9338df33a4f 100644 --- a/contrib/tools/python3/Lib/functools.py +++ b/contrib/tools/python3/Lib/functools.py @@ -507,16 +507,16 @@ def lru_cache(maxsize=128, typed=False): If *maxsize* is set to None, the LRU features are disabled and the cache can grow without bound. - If *typed* is True, arguments of different types will be cached separately. - For example, f(decimal.Decimal("3.0")) and f(3.0) will be treated as - distinct calls with distinct results. Some types such as str and int may - be cached separately even when typed is false. + If *typed* is True, arguments of different types will be cached + separately. For example, f(decimal.Decimal("3.0")) and f(3.0) will be + treated as distinct calls with distinct results. Some types such as + str and int may be cached separately even when typed is false. Arguments to the cached function must be hashable. View the cache statistics named tuple (hits, misses, maxsize, currsize) - with f.cache_info(). Clear the cache and statistics with f.cache_clear(). - Access the underlying function with f.__wrapped__. + with f.cache_info(). Clear the cache and statistics with + f.cache_clear(). Access the underlying function with f.__wrapped__. See: https://en.wikipedia.org/wiki/Cache_replacement_policies#Least_recently_used_(LRU) diff --git a/contrib/tools/python3/Lib/glob.py b/contrib/tools/python3/Lib/glob.py index 3fec2aa97e6..64ac0ca94b2 100644 --- a/contrib/tools/python3/Lib/glob.py +++ b/contrib/tools/python3/Lib/glob.py @@ -25,17 +25,17 @@ def glob(pathname, *, root_dir=None, dir_fd=None, recursive=False, The order of the returned list is undefined. Sort it if you need a particular order. - If `root_dir` is not None, it should be a path-like object specifying the - root directory for searching. It has the same effect as changing the - current directory before calling it (without actually - changing it). If pathname is relative, the result will contain - paths relative to `root_dir`. + If `root_dir` is not None, it should be a path-like object specifying + the root directory for searching. It has the same effect as changing + the current directory before calling it (without actually changing it). + If pathname is relative, the result will contain paths relative to + `root_dir`. If `dir_fd` is not None, it should be a file descriptor referring to a directory, and paths will then be relative to that directory. - If `include_hidden` is true, the patterns '*', '?', '**' will match hidden - directories. + If `include_hidden` is true, the patterns '*', '?', '**' will match + hidden directories. If `recursive` is true, the pattern '**' will match any files and zero or more directories and subdirectories. @@ -56,16 +56,16 @@ def iglob(pathname, *, root_dir=None, dir_fd=None, recursive=False, particular order. If `root_dir` is not None, it should be a path-like object specifying - the root directory for searching. It has the same effect as changing - the current directory before calling it (without actually - changing it). If pathname is relative, the result will contain - paths relative to `root_dir`. + the root directory for searching. It has the same effect as changing + the current directory before calling it (without actually changing it). + If pathname is relative, the result will contain paths relative to + `root_dir`. If `dir_fd` is not None, it should be a file descriptor referring to a directory, and paths will then be relative to that directory. - If `include_hidden` is true, the patterns '*', '?', '**' will match hidden - directories. + If `include_hidden` is true, the patterns '*', '?', '**' will match + hidden directories. If `recursive` is true, the pattern '**' will match any files and zero or more directories and subdirectories. @@ -294,15 +294,15 @@ _no_recurse_symlinks = object() def translate(pat, *, recursive=False, include_hidden=False, seps=None): """Translate a pathname with shell wildcards to a regular expression. - If `recursive` is true, the pattern segment '**' will match any number of - path segments. + If `recursive` is true, the pattern segment '**' will match any number + of path segments. If `include_hidden` is true, wildcards can match path segments beginning with a dot ('.'). If a sequence of separator characters is given to `seps`, they will be - used to split the pattern into segments and match path separators. If not - given, os.path.sep and os.path.altsep (where available) are used. + used to split the pattern into segments and match path separators. If + not given, os.path.sep and os.path.altsep (where available) are used. """ if not seps: if os.path.altsep: diff --git a/contrib/tools/python3/Lib/gzip.py b/contrib/tools/python3/Lib/gzip.py index a550c20a7a0..cb13095da43 100644 --- a/contrib/tools/python3/Lib/gzip.py +++ b/contrib/tools/python3/Lib/gzip.py @@ -34,16 +34,16 @@ def open(filename, mode="rb", compresslevel=_COMPRESS_LEVEL_BEST, encoding=None, errors=None, newline=None): """Open a gzip-compressed file in binary or text mode. - The filename argument can be an actual filename (a str or bytes object), or - an existing file object to read from or write to. + The filename argument can be an actual filename (a str or bytes object), + or an existing file object to read from or write to. - The mode argument can be "r", "rb", "w", "wb", "x", "xb", "a" or "ab" for - binary mode, or "rt", "wt", "xt" or "at" for text mode. The default mode is - "rb", and the default compresslevel is 9. + The mode argument can be "r", "rb", "w", "wb", "x", "xb", "a" or "ab" + for binary mode, or "rt", "wt", "xt" or "at" for text mode. The default + mode is "rb", and the default compresslevel is 9. - For binary mode, this function is equivalent to the GzipFile constructor: - GzipFile(filename, mode, compresslevel). In this case, the encoding, errors - and newline arguments must not be provided. + For binary mode, this function is equivalent to the GzipFile + constructor: GzipFile(filename, mode, compresslevel). In this case, + the encoding, errors and newline arguments must not be provided. For text mode, a GzipFile object is created, and wrapped in an io.TextIOWrapper instance with the specified encoding, error handling @@ -148,8 +148,8 @@ class GzipFile(_compression.BaseStream): """The GzipFile class simulates most of the methods of a file object with the exception of the truncate() method. - This class only supports opening files in binary mode. If you need to open a - compressed file in text mode, use the gzip.open() function. + This class only supports opening files in binary mode. If you need to + open a compressed file in text mode, use the gzip.open() function. """ @@ -165,31 +165,33 @@ class GzipFile(_compression.BaseStream): non-trivial value. The new class instance is based on fileobj, which can be a regular - file, an io.BytesIO object, or any other object which simulates a file. - It defaults to None, in which case filename is opened to provide - a file object. + file, an io.BytesIO object, or any other object which simulates + a file. It defaults to None, in which case filename is opened to + provide a file object. When fileobj is not None, the filename argument is only used to be included in the gzip file header, which may include the original filename of the uncompressed file. It defaults to the filename of fileobj, if discernible; otherwise, it defaults to the empty string, - and in this case the original filename is not included in the header. + and in this case the original filename is not included in the + header. - The mode argument can be any of 'r', 'rb', 'a', 'ab', 'w', 'wb', 'x', or - 'xb' depending on whether the file will be read or written. The default - is the mode of fileobj if discernible; otherwise, the default is 'rb'. - A mode of 'r' is equivalent to one of 'rb', and similarly for 'w' and - 'wb', 'a' and 'ab', and 'x' and 'xb'. + The mode argument can be any of 'r', 'rb', 'a', 'ab', 'w', 'wb', + 'x', or 'xb' depending on whether the file will be read or written. + The default is the mode of fileobj if discernible; otherwise, the + default is 'rb'. A mode of 'r' is equivalent to one of 'rb', and + similarly for 'w' and 'wb', 'a' and 'ab', and 'x' and 'xb'. - The compresslevel argument is an integer from 0 to 9 controlling the - level of compression; 1 is fastest and produces the least compression, - and 9 is slowest and produces the most compression. 0 is no compression - at all. The default is 9. + The compresslevel argument is an integer from 0 to 9 controlling + the level of compression; 1 is fastest and produces the least + compression, and 9 is slowest and produces the most compression. + 0 is no compression at all. The default is 9. - The optional mtime argument is the timestamp requested by gzip. The time - is in Unix format, i.e., seconds since 00:00:00 UTC, January 1, 1970. - If mtime is omitted or None, the current time is used. Use mtime = 0 - to generate a compressed stream that does not depend on creation time. + The optional mtime argument is the timestamp requested by gzip. + The time is in Unix format, i.e., seconds since 00:00:00 UTC, + January 1, 1970. If mtime is omitted or None, the current time + is used. Use mtime = 0 to generate a compressed stream that does + not depend on creation time. """ @@ -551,10 +553,10 @@ class _GzipReader(_compression.DecompressReader): # Read a chunk of data from the file if self._decompressor.needs_input: buf = self._fp.read(READ_BUFFER_SIZE) - uncompress = self._decompressor.decompress(buf, size) else: - uncompress = self._decompressor.decompress(b"", size) + buf = b"" + uncompress = self._decompressor.decompress(buf, size) if self._decompressor.unused_data != b"": # Prepend the already read bytes to the fileobj so they can # be seen by _read_eof() and _read_gzip_header() diff --git a/contrib/tools/python3/Lib/http/client.py b/contrib/tools/python3/Lib/http/client.py index dd5f4136e9e..c1ff4cef02f 100644 --- a/contrib/tools/python3/Lib/http/client.py +++ b/contrib/tools/python3/Lib/http/client.py @@ -972,13 +972,22 @@ class HTTPConnection: return ip def _tunnel(self): + if _contains_disallowed_url_pchar_re.search(self._tunnel_host): + raise ValueError('Tunnel host can\'t contain control characters %r' + % (self._tunnel_host,)) connect = b"CONNECT %s:%d %s\r\n" % ( self._wrap_ipv6(self._tunnel_host.encode("idna")), self._tunnel_port, self._http_vsn_str.encode("ascii")) headers = [connect] for header, value in self._tunnel_headers.items(): - headers.append(f"{header}: {value}\r\n".encode("latin-1")) + header_bytes = header.encode("latin-1") + value_bytes = value.encode("latin-1") + if not _is_legal_header_name(header_bytes): + raise ValueError('Invalid header name %r' % (header_bytes,)) + if _is_illegal_header_value(value_bytes): + raise ValueError('Invalid header value %r' % (value_bytes,)) + headers.append(b"%s: %s\r\n" % (header_bytes, value_bytes)) headers.append(b"\r\n") # Making a single send() call instead of one per line encourages # the host OS to use a more optimal packet size instead of diff --git a/contrib/tools/python3/Lib/http/cookies.py b/contrib/tools/python3/Lib/http/cookies.py index 63d119ad46c..2cffa2a9ad6 100644 --- a/contrib/tools/python3/Lib/http/cookies.py +++ b/contrib/tools/python3/Lib/http/cookies.py @@ -389,17 +389,21 @@ class Morsel(dict): return '<%s: %s>' % (self.__class__.__name__, self.OutputString()) def js_output(self, attrs=None): + import urllib.parse # Print javascript output_string = self.OutputString(attrs) if _has_control_character(output_string): raise CookieError("Control characters are not allowed in cookies") + # Base64-encode value to avoid template + # injection in cookie values. + output_encoded = urllib.parse.quote(output_string, safe='', encoding='utf-8') return """ <script type="text/javascript"> <!-- begin hiding - document.cookie = \"%s\"; + document.cookie = decodeURIComponent(\"%s\"); // end hiding --> </script> - """ % (output_string.replace('"', r'\"')) + """ % (output_encoded,) def OutputString(self, attrs=None): # Build up our result diff --git a/contrib/tools/python3/Lib/imaplib.py b/contrib/tools/python3/Lib/imaplib.py index 141e6398944..db16f3c802c 100644 --- a/contrib/tools/python3/Lib/imaplib.py +++ b/contrib/tools/python3/Lib/imaplib.py @@ -616,7 +616,7 @@ class IMAP4: """ typ, dat = self._simple_command('LOGIN', user, self._quote(password)) if typ != 'OK': - raise self.error(dat[-1]) + raise self.error(dat[-1].decode('UTF-8', 'replace')) self.state = 'AUTH' return typ, dat diff --git a/contrib/tools/python3/Lib/inspect.py b/contrib/tools/python3/Lib/inspect.py index 48f89e8171c..a10a5fd7001 100644 --- a/contrib/tools/python3/Lib/inspect.py +++ b/contrib/tools/python3/Lib/inspect.py @@ -1,7 +1,7 @@ """Get useful information from live Python objects. This module encapsulates the interface provided by the internal special -attributes (co_*, im_*, tb_*, etc.) in a friendlier fashion. +attributes (co_*, tb_*, etc.) in a friendlier fashion. It also provides some help for examining source code and class layout. Here are some of the useful functions provided by this module: diff --git a/contrib/tools/python3/Lib/json/__init__.py b/contrib/tools/python3/Lib/json/__init__.py index c7a6dcdf77e..a29e6bb58b4 100644 --- a/contrib/tools/python3/Lib/json/__init__.py +++ b/contrib/tools/python3/Lib/json/__init__.py @@ -143,8 +143,8 @@ def dump(obj, fp, *, skipkeys=False, ensure_ascii=True, check_circular=True, If ``indent`` is a non-negative integer, then JSON array elements and object members will be pretty-printed with that indent level. An indent - level of 0 will only insert newlines. ``None`` is the most compact - representation. + level of 0 will only insert newlines. ``None`` is the default and gives + a representation with no newlines inserted. If specified, ``separators`` should be an ``(item_separator, key_separator)`` tuple. The default is ``(', ', ': ')`` if *indent* is @@ -207,8 +207,8 @@ def dumps(obj, *, skipkeys=False, ensure_ascii=True, check_circular=True, If ``indent`` is a non-negative integer, then JSON array elements and object members will be pretty-printed with that indent level. An indent - level of 0 will only insert newlines. ``None`` is the most compact - representation. + level of 0 will only insert newlines. ``None`` is the default and gives + a representation with no newlines inserted. If specified, ``separators`` should be an ``(item_separator, key_separator)`` tuple. The default is ``(', ', ': ')`` if *indent* is diff --git a/contrib/tools/python3/Lib/json/tool.py b/contrib/tools/python3/Lib/json/tool.py index fdfc3372bcc..e132fc58900 100644 --- a/contrib/tools/python3/Lib/json/tool.py +++ b/contrib/tools/python3/Lib/json/tool.py @@ -63,7 +63,8 @@ def main(): infile = open(options.infile, encoding='utf-8') try: if options.json_lines: - objs = (json.loads(line) for line in infile) + lines = infile.readlines() + objs = (json.loads(line) for line in lines) else: objs = (json.load(infile),) finally: diff --git a/contrib/tools/python3/Lib/locale.py b/contrib/tools/python3/Lib/locale.py index db6d0abb26b..bcb6ac0f49a 100644 --- a/contrib/tools/python3/Lib/locale.py +++ b/contrib/tools/python3/Lib/locale.py @@ -1491,8 +1491,8 @@ locale_alias = { # This maps Windows language identifiers to locale strings. # # This list has been updated from -# http://msdn.microsoft.com/library/default.asp?url=/library/en-us/intl/nls_238z.asp -# to include every locale up to Windows Vista. +# https://learn.microsoft.com/en-us/openspecs/windows_protocols/ms-lcid/70feba9f-294e-491e-b6eb-56532684c37f +# to include every locale up to protocol revision 16.0 (2024-04-23). # # NOTE: this mapping is incomplete. If your language is missing, please # submit a bug report as detailed in the Python devguide at: @@ -1502,10 +1502,15 @@ locale_alias = { # windows_locale = { - 0x0436: "af_ZA", # Afrikaans - 0x041c: "sq_AL", # Albanian - 0x0484: "gsw_FR",# Alsatian - France + 0x0036: "af", # Afrikaans + 0x0436: "af_ZA", # Afrikaans - South Africa + 0x001c: "sq", # Albanian + 0x041c: "sq_AL", # Albanian - Albania + 0x0084: "gsw", # Alsatian + 0x0484: "gsw_FR", # Alsatian - France + 0x005e: "am", # Amharic 0x045e: "am_ET", # Amharic - Ethiopia + 0x0001: "ar", # Arabic 0x0401: "ar_SA", # Arabic - Saudi Arabia 0x0801: "ar_IQ", # Arabic - Iraq 0x0c01: "ar_EG", # Arabic - Egypt @@ -1519,39 +1524,72 @@ windows_locale = { 0x2c01: "ar_JO", # Arabic - Jordan 0x3001: "ar_LB", # Arabic - Lebanon 0x3401: "ar_KW", # Arabic - Kuwait - 0x3801: "ar_AE", # Arabic - United Arab Emirates + 0x3801: "ar_AE", # Arabic - U.A.E. 0x3c01: "ar_BH", # Arabic - Bahrain 0x4001: "ar_QA", # Arabic - Qatar - 0x042b: "hy_AM", # Armenian + 0x002b: "hy", # Armenian + 0x042b: "hy_AM", # Armenian - Armenia + 0x004d: "as", # Assamese 0x044d: "as_IN", # Assamese - India - 0x042c: "az_AZ", # Azeri - Latin - 0x082c: "az_AZ", # Azeri - Cyrillic - 0x046d: "ba_RU", # Bashkir - 0x042d: "eu_ES", # Basque - Russia - 0x0423: "be_BY", # Belarusian - 0x0445: "bn_IN", # Begali - 0x201a: "bs_BA", # Bosnian - Cyrillic - 0x141a: "bs_BA", # Bosnian - Latin + 0x002c: "az", # Azerbaijani (Latin) + 0x742c: "az", # Azerbaijani (Cyrillic) + 0x782c: "az", # Azerbaijani (Latin) + 0x042c: "az_AZ", # Azerbaijani (Latin) - Azerbaijan + 0x0045: "bn", # Bangla + 0x0445: "bn_IN", # Bangla - India + 0x0845: "bn_BD", # Bangla - Bangladesh + 0x006d: "ba", # Bashkir + 0x046d: "ba_RU", # Bashkir - Russia + 0x002d: "eu", # Basque + 0x042d: "eu_ES", # Basque - Spain + 0x0023: "be", # Belarusian + 0x0423: "be_BY", # Belarusian - Belarus + 0x641a: "bs", # Bosnian (Cyrillic) + 0x681a: "bs", # Bosnian (Latin) + 0x141a: "bs_BA", # Bosnian (Latin) - Bosnia and Herzegovina + 0x201a: "bs_BA", # Bosnian (Cyrillic) - Bosnia and Herzegovina + 0x781a: "bs", # Bosnian (Latin) + 0x007e: "br", # Breton 0x047e: "br_FR", # Breton - France - 0x0402: "bg_BG", # Bulgarian -# 0x0455: "my_MM", # Burmese - Not supported - 0x0403: "ca_ES", # Catalan - 0x0004: "zh_CHS",# Chinese - Simplified - 0x0404: "zh_TW", # Chinese - Taiwan - 0x0804: "zh_CN", # Chinese - PRC - 0x0c04: "zh_HK", # Chinese - Hong Kong S.A.R. - 0x1004: "zh_SG", # Chinese - Singapore - 0x1404: "zh_MO", # Chinese - Macao S.A.R. - 0x7c04: "zh_CHT",# Chinese - Traditional + 0x0002: "bg", # Bulgarian + 0x0402: "bg_BG", # Bulgarian - Bulgaria + 0x0055: "my", # Burmese + 0x0455: "my_MM", # Burmese - Myanmar + 0x0003: "ca", # Catalan + 0x0403: "ca_ES", # Catalan - Spain + 0x0803: "ca_ES", # Valencian - Spain + 0x0092: "ku", # Central Kurdish + 0x7c92: "ku", # Central Kurdish + 0x0492: "ku_IQ", # Central Kurdish - Iraq + 0x005c: "chr", # Cherokee + 0x7c5c: "chr", # Cherokee + 0x045c: "chr_US", # Cherokee - United States + 0x0004: "zh", # Chinese (Simplified) + 0x7804: "zh", # Chinese (Simplified) + 0x7c04: "zh", # Chinese (Traditional) + 0x0404: "zh_TW", # Chinese (Traditional) - Taiwan + 0x0804: "zh_CN", # Chinese (Simplified) - People's Republic of China + 0x0c04: "zh_HK", # Chinese (Traditional) - Hong Kong S.A.R. + 0x1004: "zh_SG", # Chinese (Simplified) - Singapore + 0x1404: "zh_MO", # Chinese (Traditional) - Macao S.A.R. + 0x0083: "co", # Corsican 0x0483: "co_FR", # Corsican - France - 0x041a: "hr_HR", # Croatian - 0x101a: "hr_BA", # Croatian - Bosnia - 0x0405: "cs_CZ", # Czech - 0x0406: "da_DK", # Danish - 0x048c: "gbz_AF",# Dari - Afghanistan - 0x0465: "div_MV",# Divehi - Maldives - 0x0413: "nl_NL", # Dutch - The Netherlands + 0x001a: "hr", # Croatian + 0x041a: "hr_HR", # Croatian - Croatia + 0x101a: "hr_BA", # Croatian (Latin) - Bosnia and Herzegovina + 0x0005: "cs", # Czech + 0x0405: "cs_CZ", # Czech - Czech Republic + 0x0006: "da", # Danish + 0x0406: "da_DK", # Danish - Denmark + 0x008c: "prs", # Dari + 0x048c: "prs_AF", # Dari - Afghanistan + 0x0065: "dv", # Divehi + 0x0465: "dv_MV", # Divehi - Maldives + 0x0013: "nl", # Dutch + 0x0413: "nl_NL", # Dutch - Netherlands 0x0813: "nl_BE", # Dutch - Belgium + 0x0c51: "dz_BT", # Dzongkha - Bhutan + 0x0009: "en", # English 0x0409: "en_US", # English - United States 0x0809: "en_GB", # English - United Kingdom 0x0c09: "en_AU", # English - Australia @@ -1559,122 +1597,248 @@ windows_locale = { 0x1409: "en_NZ", # English - New Zealand 0x1809: "en_IE", # English - Ireland 0x1c09: "en_ZA", # English - South Africa - 0x2009: "en_JA", # English - Jamaica - 0x2409: "en_CB", # English - Caribbean + 0x2009: "en_JM", # English - Jamaica 0x2809: "en_BZ", # English - Belize - 0x2c09: "en_TT", # English - Trinidad + 0x2c09: "en_TT", # English - Trinidad and Tobago 0x3009: "en_ZW", # English - Zimbabwe - 0x3409: "en_PH", # English - Philippines + 0x3409: "en_PH", # English - Republic of the Philippines + 0x3c09: "en_HK", # English - Hong Kong 0x4009: "en_IN", # English - India 0x4409: "en_MY", # English - Malaysia - 0x4809: "en_IN", # English - Singapore - 0x0425: "et_EE", # Estonian - 0x0438: "fo_FO", # Faroese - 0x0464: "fil_PH",# Filipino - 0x040b: "fi_FI", # Finnish + 0x4809: "en_SG", # English - Singapore + 0x4c09: "en_AE", # English - United Arab Emirates + 0x0025: "et", # Estonian + 0x0425: "et_EE", # Estonian - Estonia + 0x0038: "fo", # Faroese + 0x0438: "fo_FO", # Faroese - Faroe Islands + 0x0064: "fil", # Filipino + 0x0464: "fil_PH", # Filipino - Philippines + 0x000b: "fi", # Finnish + 0x040b: "fi_FI", # Finnish - Finland + 0x000c: "fr", # French 0x040c: "fr_FR", # French - France 0x080c: "fr_BE", # French - Belgium 0x0c0c: "fr_CA", # French - Canada 0x100c: "fr_CH", # French - Switzerland 0x140c: "fr_LU", # French - Luxembourg - 0x180c: "fr_MC", # French - Monaco + 0x180c: "fr_MC", # French - Principality of Monaco + 0x1c0c: "fr_029", # French - Caribbean + 0x200c: "fr_RE", # French - Reunion + 0x240c: "fr_CD", # French - Congo, DRC + 0x280c: "fr_SN", # French - Senegal + 0x2c0c: "fr_CM", # French - Cameroon + 0x300c: "fr_CI", # French - Côte d'Ivoire + 0x340c: "fr_ML", # French - Mali + 0x380c: "fr_MA", # French - Morocco + 0x3c0c: "fr_HT", # French - Haiti + 0x0062: "fy", # Frisian 0x0462: "fy_NL", # Frisian - Netherlands - 0x0456: "gl_ES", # Galician - 0x0437: "ka_GE", # Georgian + 0x0067: "ff", # Fulah + 0x7c67: "ff", # Fulah (Latin) + 0x0467: "ff_NG", + 0x0867: "ff_SN", # Fulah - Senegal + 0x0056: "gl", # Galician + 0x0456: "gl_ES", # Galician - Spain + 0x0037: "ka", # Georgian + 0x0437: "ka_GE", # Georgian - Georgia + 0x0007: "de", # German 0x0407: "de_DE", # German - Germany 0x0807: "de_CH", # German - Switzerland 0x0c07: "de_AT", # German - Austria 0x1007: "de_LU", # German - Luxembourg 0x1407: "de_LI", # German - Liechtenstein - 0x0408: "el_GR", # Greek + 0x0008: "el", # Greek + 0x0408: "el_GR", # Greek - Greece + 0x006f: "kl", # Greenlandic 0x046f: "kl_GL", # Greenlandic - Greenland - 0x0447: "gu_IN", # Gujarati - 0x0468: "ha_NG", # Hausa - Latin - 0x040d: "he_IL", # Hebrew - 0x0439: "hi_IN", # Hindi - 0x040e: "hu_HU", # Hungarian - 0x040f: "is_IS", # Icelandic - 0x0421: "id_ID", # Indonesian - 0x045d: "iu_CA", # Inuktitut - Syllabics - 0x085d: "iu_CA", # Inuktitut - Latin + 0x0074: "gn", # Guarani + 0x0474: "gn_PY", # Guarani - Paraguay + 0x0047: "gu", # Gujarati + 0x0447: "gu_IN", # Gujarati - India + 0x0068: "ha", # Hausa (Latin) + 0x7c68: "ha", # Hausa (Latin) + 0x0468: "ha_NG", # Hausa (Latin) - Nigeria + 0x0075: "haw", # Hawaiian + 0x0475: "haw_US", # Hawaiian - United States + 0x000d: "he", # Hebrew + 0x040d: "he_IL", # Hebrew - Israel + 0x0039: "hi", # Hindi + 0x0439: "hi_IN", # Hindi - India + 0x000e: "hu", # Hungarian + 0x040e: "hu_HU", # Hungarian - Hungary + 0x000f: "is", # Icelandic + 0x040f: "is_IS", # Icelandic - Iceland + 0x0070: "ig", # Igbo + 0x0470: "ig_NG", # Igbo - Nigeria + 0x0021: "id", # Indonesian + 0x0421: "id_ID", # Indonesian - Indonesia + 0x005d: "iu", # Inuktitut (Latin) + 0x785d: "iu", # Inuktitut (Syllabics) + 0x7c5d: "iu", # Inuktitut (Latin) + 0x045d: "iu_CA", # Inuktitut (Syllabics) - Canada + 0x085d: "iu_CA", # Inuktitut (Latin) - Canada + 0x003c: "ga", # Irish 0x083c: "ga_IE", # Irish - Ireland + 0x0010: "it", # Italian 0x0410: "it_IT", # Italian - Italy 0x0810: "it_CH", # Italian - Switzerland - 0x0411: "ja_JP", # Japanese + 0x0011: "ja", # Japanese + 0x0411: "ja_JP", # Japanese - Japan + 0x004b: "kn", # Kannada 0x044b: "kn_IN", # Kannada - India - 0x043f: "kk_KZ", # Kazakh - 0x0453: "kh_KH", # Khmer - Cambodia - 0x0486: "qut_GT",# K'iche - Guatemala + 0x0471: "kr_NG", # Kanuri (Latin) - Nigeria + 0x0060: "ks", # Kashmiri + 0x0460: "ks", # Kashmiri - Perso_Arabic + 0x0860: "ks_IN", # Kashmiri (Devanagari) - India + 0x003f: "kk", # Kazakh + 0x043f: "kk_KZ", # Kazakh - Kazakhstan + 0x0053: "km", # Khmer + 0x0453: "km_KH", # Khmer - Cambodia + 0x0087: "rw", # Kinyarwanda 0x0487: "rw_RW", # Kinyarwanda - Rwanda - 0x0457: "kok_IN",# Konkani - 0x0412: "ko_KR", # Korean - 0x0440: "ky_KG", # Kyrgyz - 0x0454: "lo_LA", # Lao - Lao PDR - 0x0426: "lv_LV", # Latvian - 0x0427: "lt_LT", # Lithuanian - 0x082e: "dsb_DE",# Lower Sorbian - Germany - 0x046e: "lb_LU", # Luxembourgish - 0x042f: "mk_MK", # FYROM Macedonian + 0x0041: "sw", # Kiswahili + 0x0441: "sw_KE", # Kiswahili - Kenya + 0x0057: "kok", # Konkani + 0x0457: "kok_IN", # Konkani - India + 0x0012: "ko", # Korean + 0x0412: "ko_KR", # Korean - Korea + 0x0040: "ky", # Kyrgyz + 0x0440: "ky_KG", # Kyrgyz - Kyrgyzstan + 0x0054: "lo", # Lao + 0x0454: "lo_LA", # Lao - Lao P.D.R. + 0x0476: "la_VA", # Latin - Vatican City + 0x0026: "lv", # Latvian + 0x0426: "lv_LV", # Latvian - Latvia + 0x0027: "lt", # Lithuanian + 0x0427: "lt_LT", # Lithuanian - Lithuania + 0x7c2e: "dsb", # Lower Sorbian + 0x082e: "dsb_DE", # Lower Sorbian - Germany + 0x006e: "lb", # Luxembourgish + 0x046e: "lb_LU", # Luxembourgish - Luxembourg + 0x002f: "mk", # Macedonian + 0x042f: "mk_MK", # Macedonian - North Macedonia + 0x003e: "ms", # Malay 0x043e: "ms_MY", # Malay - Malaysia 0x083e: "ms_BN", # Malay - Brunei Darussalam + 0x004c: "ml", # Malayalam 0x044c: "ml_IN", # Malayalam - India - 0x043a: "mt_MT", # Maltese - 0x0481: "mi_NZ", # Maori - 0x047a: "arn_CL",# Mapudungun - 0x044e: "mr_IN", # Marathi - 0x047c: "moh_CA",# Mohawk - Canada - 0x0450: "mn_MN", # Mongolian - Cyrillic - 0x0850: "mn_CN", # Mongolian - PRC - 0x0461: "ne_NP", # Nepali - 0x0414: "nb_NO", # Norwegian - Bokmal - 0x0814: "nn_NO", # Norwegian - Nynorsk + 0x003a: "mt", # Maltese + 0x043a: "mt_MT", # Maltese - Malta + 0x0081: "mi", # Maori + 0x0481: "mi_NZ", # Maori - New Zealand + 0x007a: "arn", # Mapudungun + 0x047a: "arn_CL", # Mapudungun - Chile + 0x004e: "mr", # Marathi + 0x044e: "mr_IN", # Marathi - India + 0x007c: "moh", # Mohawk + 0x047c: "moh_CA", # Mohawk - Canada + 0x0050: "mn", # Mongolian (Cyrillic) + 0x7850: "mn", # Mongolian (Cyrillic) + 0x7c50: "mn", # Mongolian (Traditional Mongolian) + 0x0450: "mn_MN", # Mongolian (Cyrillic) - Mongolia + 0x0c50: "mn_MN", # Mongolian (Traditional Mongolian) - Mongolia + 0x0061: "ne", # Nepali + 0x0461: "ne_NP", # Nepali - Nepal + 0x0861: "ne_IN", # Nepali - India + 0x0014: "no", # Norwegian (Bokmal) + 0x0414: "nb_NO", # Norwegian (Bokmal) - Norway + 0x0814: "nn_NO", # Norwegian (Nynorsk) - Norway + 0x7814: "nn", # Norwegian (Nynorsk) + 0x7c14: "nb", # Norwegian (Bokmal) + 0x0082: "oc", # Occitan 0x0482: "oc_FR", # Occitan - France - 0x0448: "or_IN", # Oriya - India + 0x0048: "or", # Odia + 0x0448: "or_IN", # Odia - India + 0x0072: "om", # Oromo + 0x0472: "om_ET", # Oromo - Ethiopia + 0x0063: "ps", # Pashto 0x0463: "ps_AF", # Pashto - Afghanistan - 0x0429: "fa_IR", # Persian - 0x0415: "pl_PL", # Polish + 0x0029: "fa", # Persian + 0x0429: "fa_IR", # Persian - Iran + 0x0015: "pl", # Polish + 0x0415: "pl_PL", # Polish - Poland + 0x0016: "pt", # Portuguese 0x0416: "pt_BR", # Portuguese - Brazil 0x0816: "pt_PT", # Portuguese - Portugal - 0x0446: "pa_IN", # Punjabi - 0x046b: "quz_BO",# Quechua (Bolivia) - 0x086b: "quz_EC",# Quechua (Ecuador) - 0x0c6b: "quz_PE",# Quechua (Peru) + 0x0046: "pa", # Punjabi + 0x7c46: "pa", # Punjabi + 0x0446: "pa_IN", # Punjabi - India + 0x0846: "pa_PK", # Punjabi - Islamic Republic of Pakistan + 0x006b: "quz", # Quechua + 0x046b: "quz_BO", # Quechua - Bolivia + 0x086b: "quz_EC", # Quechua - Ecuador + 0x0c6b: "quz_PE", # Quechua - Peru + 0x0018: "ro", # Romanian 0x0418: "ro_RO", # Romanian - Romania - 0x0417: "rm_CH", # Romansh - 0x0419: "ru_RU", # Russian - 0x243b: "smn_FI",# Sami Finland - 0x103b: "smj_NO",# Sami Norway - 0x143b: "smj_SE",# Sami Sweden - 0x043b: "se_NO", # Sami Northern Norway - 0x083b: "se_SE", # Sami Northern Sweden - 0x0c3b: "se_FI", # Sami Northern Finland - 0x203b: "sms_FI",# Sami Skolt - 0x183b: "sma_NO",# Sami Southern Norway - 0x1c3b: "sma_SE",# Sami Southern Sweden - 0x044f: "sa_IN", # Sanskrit - 0x0c1a: "sr_SP", # Serbian - Cyrillic - 0x1c1a: "sr_BA", # Serbian - Bosnia Cyrillic - 0x081a: "sr_SP", # Serbian - Latin - 0x181a: "sr_BA", # Serbian - Bosnia Latin + 0x0818: "ro_MD", # Romanian - Moldova + 0x0017: "rm", # Romansh + 0x0417: "rm_CH", # Romansh - Switzerland + 0x0019: "ru", # Russian + 0x0419: "ru_RU", # Russian - Russia + 0x0819: "ru_MD", # Russian - Moldova + 0x0085: "sah", # Sakha + 0x0485: "sah_RU", # Sakha - Russia + 0x003b: "se", # Sami (Northern) + 0x043b: "se_NO", # Sami (Northern) - Norway + 0x083b: "se_SE", # Sami (Northern) - Sweden + 0x0c3b: "se_FI", # Sami (Northern) - Finland + 0x7c3b: "smj", # Sami (Lule) + 0x103b: "smj_NO", # Sami (Lule) - Norway + 0x143b: "smj_SE", # Sami (Lule) - Sweden + 0x783b: "sma", # Sami (Southern) + 0x183b: "sma_NO", # Sami (Southern) - Norway + 0x1c3b: "sma_SE", # Sami (Southern) - Sweden + 0x743b: "sms", # Sami (Skolt) + 0x203b: "sms_FI", # Sami (Skolt) - Finland + 0x703b: "smn", # Sami (Inari) + 0x243b: "smn_FI", # Sami (Inari) - Finland + 0x004f: "sa", # Sanskrit + 0x044f: "sa_IN", # Sanskrit - India + 0x0091: "gd", # Scottish Gaelic + 0x0491: "gd_GB", # Scottish Gaelic - United Kingdom + 0x6c1a: "sr", # Serbian (Cyrillic) + 0x701a: "sr", # Serbian (Latin) + 0x7c1a: "sr", # Serbian (Latin) + 0x081a: "sr_CS", # Serbian (Latin) - Serbia and Montenegro (Former) + 0x0c1a: "sr_CS", # Serbian (Cyrillic) - Serbia and Montenegro (Former) + 0x181a: "sr_BA", # Serbian (Latin) - Bosnia and Herzegovina + 0x1c1a: "sr_BA", # Serbian (Cyrillic) - Bosnia and Herzegovina + 0x241a: "sr_RS", # Serbian (Latin) - Serbia + 0x281a: "sr_RS", # Serbian (Cyrillic) - Serbia + 0x2c1a: "sr_ME", # Serbian (Latin) - Montenegro + 0x301a: "sr_ME", # Serbian (Cyrillic) - Montenegro + 0x006c: "nso", # Sesotho sa Leboa + 0x046c: "nso_ZA", # Sesotho sa Leboa - South Africa + 0x0032: "tn", # Setswana + 0x0432: "tn_ZA", # Setswana - South Africa + 0x0832: "tn_BW", # Setswana - Botswana + 0x0059: "sd", # Sindhi + 0x7c59: "sd", # Sindhi + 0x0859: "sd_PK", # Sindhi - Islamic Republic of Pakistan + 0x005b: "si", # Sinhala 0x045b: "si_LK", # Sinhala - Sri Lanka - 0x046c: "ns_ZA", # Northern Sotho - 0x0432: "tn_ZA", # Setswana - Southern Africa - 0x041b: "sk_SK", # Slovak - 0x0424: "sl_SI", # Slovenian + 0x001b: "sk", # Slovak + 0x041b: "sk_SK", # Slovak - Slovakia + 0x0024: "sl", # Slovenian + 0x0424: "sl_SI", # Slovenian - Slovenia + 0x0477: "so_SO", # Somali - Somalia + 0x0030: "st", # Sotho + 0x0430: "st_ZA", # Sotho - South Africa + 0x000a: "es", # Spanish 0x040a: "es_ES", # Spanish - Spain 0x080a: "es_MX", # Spanish - Mexico - 0x0c0a: "es_ES", # Spanish - Spain (Modern) + 0x0c0a: "es_ES", # Spanish - Spain 0x100a: "es_GT", # Spanish - Guatemala 0x140a: "es_CR", # Spanish - Costa Rica 0x180a: "es_PA", # Spanish - Panama 0x1c0a: "es_DO", # Spanish - Dominican Republic - 0x200a: "es_VE", # Spanish - Venezuela + 0x200a: "es_VE", # Spanish - Bolivarian Republic of Venezuela 0x240a: "es_CO", # Spanish - Colombia 0x280a: "es_PE", # Spanish - Peru 0x2c0a: "es_AR", # Spanish - Argentina 0x300a: "es_EC", # Spanish - Ecuador 0x340a: "es_CL", # Spanish - Chile - 0x380a: "es_UR", # Spanish - Uruguay + 0x380a: "es_UY", # Spanish - Uruguay 0x3c0a: "es_PY", # Spanish - Paraguay 0x400a: "es_BO", # Spanish - Bolivia 0x440a: "es_SV", # Spanish - El Salvador @@ -1682,36 +1846,87 @@ windows_locale = { 0x4c0a: "es_NI", # Spanish - Nicaragua 0x500a: "es_PR", # Spanish - Puerto Rico 0x540a: "es_US", # Spanish - United States -# 0x0430: "", # Sutu - Not supported - 0x0441: "sw_KE", # Swahili + 0x5c0a: "es_CU", # Spanish - Cuba + 0x001d: "sv", # Swedish 0x041d: "sv_SE", # Swedish - Sweden 0x081d: "sv_FI", # Swedish - Finland - 0x045a: "syr_SY",# Syriac - 0x0428: "tg_TJ", # Tajik - Cyrillic - 0x085f: "tmz_DZ",# Tamazight - Latin - 0x0449: "ta_IN", # Tamil - 0x0444: "tt_RU", # Tatar - 0x044a: "te_IN", # Telugu - 0x041e: "th_TH", # Thai - 0x0851: "bo_BT", # Tibetan - Bhutan - 0x0451: "bo_CN", # Tibetan - PRC - 0x041f: "tr_TR", # Turkish - 0x0442: "tk_TM", # Turkmen - Cyrillic - 0x0480: "ug_CN", # Uighur - Arabic - 0x0422: "uk_UA", # Ukrainian - 0x042e: "wen_DE",# Upper Sorbian - Germany - 0x0420: "ur_PK", # Urdu + 0x005a: "syr", # Syriac + 0x045a: "syr_SY", # Syriac - Syria + 0x0028: "tg", # Tajik (Cyrillic) + 0x7c28: "tg", # Tajik (Cyrillic) + 0x0428: "tg_TJ", # Tajik (Cyrillic) - Tajikistan + 0x005f: "tzm", # Tamazight (Latin) + 0x785f: "tzm", + 0x7c5f: "tzm", # Tamazight (Latin) + 0x085f: "tzm_DZ", # Tamazight (Latin) - Algeria + 0x045f: "tzm_MA", # Central Atlas Tamazight (Arabic) - Morocco + 0x105f: "tzm_MA", + 0x0049: "ta", # Tamil + 0x0449: "ta_IN", # Tamil - India + 0x0849: "ta_LK", # Tamil - Sri Lanka + 0x0044: "tt", # Tatar + 0x0444: "tt_RU", # Tatar - Russia + 0x004a: "te", # Telugu + 0x044a: "te_IN", # Telugu - India + 0x001e: "th", # Thai + 0x041e: "th_TH", # Thai - Thailand + 0x0051: "bo", # Tibetan + 0x0451: "bo_CN", # Tibetan - People's Republic of China + 0x0073: "ti", # Tigrinya + 0x0473: "ti_ET", # Tigrinya - Ethiopia + 0x0873: "ti_ER", # Tigrinya - Eritrea + 0x0031: "ts", # Tsonga + 0x0431: "ts_ZA", # Tsonga - South Africa + 0x001f: "tr", # Turkish + 0x041f: "tr_TR", # Turkish - Turkey + 0x0042: "tk", # Turkmen + 0x0442: "tk_TM", # Turkmen - Turkmenistan + 0x0022: "uk", # Ukrainian + 0x0422: "uk_UA", # Ukrainian - Ukraine + 0x002e: "hsb", # Upper Sorbian + 0x042e: "hsb_DE", # Upper Sorbian - Germany + 0x0020: "ur", # Urdu + 0x0420: "ur_PK", # Urdu - Islamic Republic of Pakistan 0x0820: "ur_IN", # Urdu - India - 0x0443: "uz_UZ", # Uzbek - Latin - 0x0843: "uz_UZ", # Uzbek - Cyrillic - 0x042a: "vi_VN", # Vietnamese - 0x0452: "cy_GB", # Welsh + 0x0080: "ug", # Uyghur + 0x0480: "ug_CN", # Uyghur - People's Republic of China + 0x0043: "uz", # Uzbek (Latin) + 0x7843: "uz", # Uzbek (Cyrillic) + 0x7c43: "uz", # Uzbek (Latin) + 0x0443: "uz_UZ", # Uzbek (Latin) - Uzbekistan + 0x0033: "ve", # Venda + 0x0433: "ve_ZA", # Venda - South Africa + 0x002a: "vi", # Vietnamese + 0x042a: "vi_VN", # Vietnamese - Vietnam + 0x0052: "cy", # Welsh + 0x0452: "cy_GB", # Welsh - United Kingdom + 0x0088: "wo", # Wolof 0x0488: "wo_SN", # Wolof - Senegal + 0x0034: "xh", # Xhosa 0x0434: "xh_ZA", # Xhosa - South Africa - 0x0485: "sah_RU",# Yakut - Cyrillic - 0x0478: "ii_CN", # Yi - PRC + 0x0078: "ii", # Yi + 0x0478: "ii_CN", # Yi - People's Republic of China + 0x043d: "yi_001", # Yiddish - World + 0x006a: "yo", # Yoruba 0x046a: "yo_NG", # Yoruba - Nigeria - 0x0435: "zu_ZA", # Zulu + 0x0035: "zu", # Zulu + 0x0435: "zu_ZA", # Zulu - South Africa + 0x0086: "qut", + +# 0x0001007f: "x-IV-mathan", # math alphanumeric sorting + 0x00010407: "de_DE", + 0x0001040e: "hu_HU", + 0x00010437: "ka_GE", + 0x00020804: "zh_CN", + 0x00021004: "zh_SG", + 0x00021404: "zh_MO", + 0x00030404: "zh_TW", + 0x00040404: "zh_TW", + 0x00040411: "ja_JP", + 0x00040c04: "zh_HK", + 0x00041404: "zh_MO", + 0x00050804: "zh_CN", + 0x00051004: "zh_SG", } def _print_locale(): diff --git a/contrib/tools/python3/Lib/multiprocessing/connection.py b/contrib/tools/python3/Lib/multiprocessing/connection.py index efb9ea95ab4..2a0151dab80 100644 --- a/contrib/tools/python3/Lib/multiprocessing/connection.py +++ b/contrib/tools/python3/Lib/multiprocessing/connection.py @@ -75,7 +75,11 @@ def arbitrary_address(family): if family == 'AF_INET': return ('localhost', 0) elif family == 'AF_UNIX': - return tempfile.mktemp(prefix='sock-', dir=util.get_temp_dir()) + # NOTE: util.get_temp_dir() is a 0o700 per-process directory. A + # mktemp-style ToC vs ToU concern is not important; bind() surfaces + # the extremely unlikely collision as EADDRINUSE. + return os.path.join(util.get_temp_dir(), + f'sock-{os.urandom(6).hex()}') elif family == 'AF_PIPE': return (r'\\.\pipe\pyc-%d-%d-%s' % (os.getpid(), next(_mmap_counter), os.urandom(8).hex())) diff --git a/contrib/tools/python3/Lib/multiprocessing/popen_fork.py b/contrib/tools/python3/Lib/multiprocessing/popen_fork.py index a57ef6bdad5..05593737dbb 100644 --- a/contrib/tools/python3/Lib/multiprocessing/popen_fork.py +++ b/contrib/tools/python3/Lib/multiprocessing/popen_fork.py @@ -64,7 +64,17 @@ class Popen(object): code = 1 parent_r, child_w = os.pipe() child_r, parent_w = os.pipe() - self.pid = os.fork() + # gh-146313: Tell the resource tracker's at-fork handler to keep + # the inherited pipe fd so this child reuses the parent's tracker + # (gh-80849) rather than closing it and launching its own. + from .resource_tracker import _fork_intent + _fork_intent.preserve_fd = True + try: + self.pid = os.fork() + finally: + # Reset in both parent and child so the flag does not leak + # into a subsequent raw os.fork() or nested Process launch. + _fork_intent.preserve_fd = False if self.pid == 0: try: atexit._clear() diff --git a/contrib/tools/python3/Lib/multiprocessing/resource_tracker.py b/contrib/tools/python3/Lib/multiprocessing/resource_tracker.py index 22e3bbcf21b..028c1f60e59 100644 --- a/contrib/tools/python3/Lib/multiprocessing/resource_tracker.py +++ b/contrib/tools/python3/Lib/multiprocessing/resource_tracker.py @@ -20,6 +20,7 @@ import os import signal import sys import threading +import time import warnings from collections import deque @@ -79,6 +80,10 @@ class ResourceTracker(object): # The reader should understand all formats. self._use_simple_format = True + # Set to True by _stop_locked() if the waitpid polling loop ran to + # its timeout without reaping the tracker. Exposed for tests. + self._waitpid_timed_out = False + def _reentrant_call_error(self): # gh-109629: this happens if an explicit call to the ResourceTracker # gets interrupted by a garbage collection, invoking a finalizer (*) @@ -91,16 +96,51 @@ class ResourceTracker(object): # making sure child processess are cleaned before ResourceTracker # gets destructed. # see https://github.com/python/cpython/issues/88887 - self._stop(use_blocking_lock=False) + # gh-146313: use a timeout to avoid deadlocking if a forked child + # still holds the pipe's write end open. + self._stop(use_blocking_lock=False, wait_timeout=1.0) + + def _after_fork_in_child(self): + # gh-146313: Called in the child right after os.fork(). + # + # The tracker process is a child of the *parent*, not of us, so we + # could never waitpid() it anyway. Clearing _pid means our __del__ + # becomes a no-op (the early return for _pid is None). + # + # Whether we keep the inherited _fd depends on who forked us: + # + # - multiprocessing.Process with the 'fork' start method sets + # _fork_intent.preserve_fd before forking. The child keeps the + # fd and reuses the parent's tracker (gh-80849). This is safe + # because multiprocessing's atexit handler joins all children + # before the parent's __del__ runs, so by then the fd copies + # are gone and the parent can reap the tracker promptly. + # + # - A raw os.fork() leaves the flag unset. We close the fd in the child after forking so + # the parent's __del__ can reap the tracker without waiting + # for the child to exit. If we later need a tracker, ensure_running() + # will launch a fresh one. + self._lock._at_fork_reinit() + self._reentrant_messages.clear() + self._pid = None + self._exitcode = None + if (self._fd is not None and + not getattr(_fork_intent, 'preserve_fd', False)): + fd = self._fd + self._fd = None + try: + os.close(fd) + except OSError: + pass - def _stop(self, use_blocking_lock=True): + def _stop(self, use_blocking_lock=True, wait_timeout=None): if use_blocking_lock: with self._lock: - self._stop_locked() + self._stop_locked(wait_timeout=wait_timeout) else: acquired = self._lock.acquire(blocking=False) try: - self._stop_locked() + self._stop_locked(wait_timeout=wait_timeout) finally: if acquired: self._lock.release() @@ -110,6 +150,10 @@ class ResourceTracker(object): close=os.close, waitpid=os.waitpid, waitstatus_to_exitcode=os.waitstatus_to_exitcode, + monotonic=time.monotonic, + sleep=time.sleep, + WNOHANG=getattr(os, 'WNOHANG', None), + wait_timeout=None, ): # This shouldn't happen (it might when called by a finalizer) # so we check for it anyway. @@ -126,7 +170,30 @@ class ResourceTracker(object): self._fd = None try: - _, status = waitpid(self._pid, 0) + if wait_timeout is None: + _, status = waitpid(self._pid, 0) + else: + # gh-146313: A forked child may still hold the pipe's write + # end open, preventing the tracker from seeing EOF and + # exiting. Poll with WNOHANG to avoid blocking forever. + deadline = monotonic() + wait_timeout + delay = 0.001 + while True: + result_pid, status = waitpid(self._pid, WNOHANG) + if result_pid != 0: + break + remaining = deadline - monotonic() + if remaining <= 0: + # The tracker is still running; it will be + # reparented to PID 1 (or the nearest subreaper) + # when we exit, and reaped there once all pipe + # holders release their fd. + self._pid = None + self._exitcode = None + self._waitpid_timed_out = True + return + delay = min(delay * 2, remaining, 0.1) + sleep(delay) except ChildProcessError: self._pid = None self._exitcode = None @@ -312,12 +379,24 @@ class ResourceTracker(object): self._ensure_running_and_write(msg) +# gh-146313: Per-thread flag set by .popen_fork.Popen._launch() just before +# os.fork(), telling _after_fork_in_child() to keep the inherited pipe fd so +# the child can reuse this tracker (gh-80849). Unset for raw os.fork() calls, +# where the child instead closes the fd so the parent's __del__ can reap the +# tracker. Using threading.local() keeps multiple threads calling +# popen_fork.Popen._launch() at once from clobbering eachothers intent. +_fork_intent = threading.local() + _resource_tracker = ResourceTracker() ensure_running = _resource_tracker.ensure_running register = _resource_tracker.register unregister = _resource_tracker.unregister getfd = _resource_tracker.getfd +# gh-146313: See _after_fork_in_child docstring. +if hasattr(os, 'register_at_fork'): + os.register_at_fork(after_in_child=_resource_tracker._after_fork_in_child) + def _decode_message(line): if line.startswith(b'{'): diff --git a/contrib/tools/python3/Lib/ntpath.py b/contrib/tools/python3/Lib/ntpath.py index 01f060e70be..eb127ec2632 100644 --- a/contrib/tools/python3/Lib/ntpath.py +++ b/contrib/tools/python3/Lib/ntpath.py @@ -152,12 +152,14 @@ def splitdrive(p): It is always true that: result[0] + result[1] == p - If the path contained a drive letter, drive_or_unc will contain everything - up to and including the colon. e.g. splitdrive("c:/dir") returns ("c:", "/dir") + If the path contained a drive letter, drive_or_unc will contain + everything up to and including the colon. e.g. splitdrive("c:/dir") + returns ("c:", "/dir") - If the path contained a UNC path, the drive_or_unc will contain the host name - and share up to but not including the fourth directory separator character. - e.g. splitdrive("//host/computer/dir") returns ("//host/computer", "/dir") + If the path contained a UNC path, the drive_or_unc will contain the + host name and share up to but not including the fourth directory + separator character. e.g. splitdrive("//host/computer/dir") returns + ("//host/computer", "/dir") Paths cannot contain both a drive letter and a UNC path. @@ -222,8 +224,8 @@ except ImportError: def split(p): """Split a pathname. - Return tuple (head, tail) where tail is everything after the final slash. - Either part may be empty.""" + Return tuple (head, tail) where tail is everything after the final + slash. Either part may be empty.""" p = os.fspath(p) seps = _get_bothseps(p) d, r, p = splitroot(p) diff --git a/contrib/tools/python3/Lib/pickle.py b/contrib/tools/python3/Lib/pickle.py index 550f8675f2c..12da440b9f8 100644 --- a/contrib/tools/python3/Lib/pickle.py +++ b/contrib/tools/python3/Lib/pickle.py @@ -847,17 +847,11 @@ class _Pickler: # Write data in-band # XXX The C implementation avoids a copy here buf = m.tobytes() - in_memo = id(buf) in self.memo if m.readonly: - if in_memo: - self._save_bytes_no_memo(buf) - else: - self.save_bytes(buf) + self._save_bytes_no_memo(buf) else: - if in_memo: - self._save_bytearray_no_memo(buf) - else: - self.save_bytearray(buf) + self._save_bytearray_no_memo(buf) + self.memoize(obj) else: # Write data out-of-band self.write(NEXT_BUFFER) diff --git a/contrib/tools/python3/Lib/pydoc_data/module_docs.py b/contrib/tools/python3/Lib/pydoc_data/module_docs.py index 8c4013606ca..9e456490967 100644 --- a/contrib/tools/python3/Lib/pydoc_data/module_docs.py +++ b/contrib/tools/python3/Lib/pydoc_data/module_docs.py @@ -1,4 +1,4 @@ -# Autogenerated by Sphinx on Tue Apr 7 20:18:56 2026 +# Autogenerated by Sphinx on Wed Jun 10 14:23:59 2026 # as part of the release process. module_docs = { diff --git a/contrib/tools/python3/Lib/pydoc_data/topics.py b/contrib/tools/python3/Lib/pydoc_data/topics.py index bbbd6a3effd..31d582a90ab 100644 --- a/contrib/tools/python3/Lib/pydoc_data/topics.py +++ b/contrib/tools/python3/Lib/pydoc_data/topics.py @@ -1,4 +1,4 @@ -# Autogenerated by Sphinx on Tue Apr 7 20:18:56 2026 +# Autogenerated by Sphinx on Wed Jun 10 14:23:59 2026 # as part of the release process. topics = { @@ -2122,9 +2122,9 @@ Added in version 3.10. The match statement is used for pattern matching. Syntax: match_stmt ::= 'match' subject_expr ":" NEWLINE INDENT case_block+ DEDENT - subject_expr ::= `!star_named_expression` "," `!star_named_expressions`? - | `!named_expression` - case_block ::= 'case' patterns [guard] ":" `!block` + subject_expr ::= flexible_expression "," [flexible_expression_list [',']] + | assignment_expression + case_block ::= 'case' patterns [guard] ":" suite Note: @@ -2215,7 +2215,7 @@ section. Guards ------ - guard ::= "if" `!named_expression` + guard ::= "if" assignment_expression A "guard" (which is part of the "case") must succeed for code inside the "case" block to execute. It takes the form: "if" followed by an @@ -4625,11 +4625,6 @@ Note: See also the description of the "try" statement in section The try statement and "raise" statement in section The raise statement. - --[ Footnotes ]- - -[1] This limitation occurs because the code that is executed by these - operations is not available at the time the module is compiled. ''', 'execmodel': r'''Execution model *************** @@ -4976,6 +4971,180 @@ Note: See also the description of the "try" statement in section The try statement and "raise" statement in section The raise statement. + +Runtime Components +================== + + +General Computing Model +----------------------- + +Python’s execution model does not operate in a vacuum. It runs on a +host machine and through that host’s runtime environment, including +its operating system (OS), if there is one. When a program runs, the +conceptual layers of how it runs on the host look something like this: + + **host machine** + **process** (global resources) + **thread** (runs machine code) + +Each process represents a program running on the host. Think of each +process itself as the data part of its program. Think of the process’ +threads as the execution part of the program. This distinction will +be important to understand the conceptual Python runtime. + +The process, as the data part, is the execution context in which the +program runs. It mostly consists of the set of resources assigned to +the program by the host, including memory, signals, file handles, +sockets, and environment variables. + +Processes are isolated and independent from one another. (The same is +true for hosts.) The host manages the process’ access to its assigned +resources, in addition to coordinating between processes. + +Each thread represents the actual execution of the program’s machine +code, running relative to the resources assigned to the program’s +process. It’s strictly up to the host how and when that execution +takes place. + +From the point of view of Python, a program always starts with exactly +one thread. However, the program may grow to run in multiple +simultaneous threads. Not all hosts support multiple threads per +process, but most do. Unlike processes, threads in a process are not +isolated and independent from one another. Specifically, all threads +in a process share all of the process’ resources. + +The fundamental point of threads is that each one does *run* +independently, at the same time as the others. That may be only +conceptually at the same time (“concurrently”) or physically (“in +parallel”). Either way, the threads effectively run at a non- +synchronized rate. + +Note: + + That non-synchronized rate means none of the process’ memory is + guaranteed to stay consistent for the code running in any given + thread. Thus multi-threaded programs must take care to coordinate + access to intentionally shared resources. Likewise, they must take + care to be absolutely diligent about not accessing any *other* + resources in multiple threads; otherwise two threads running at the + same time might accidentally interfere with each other’s use of some + shared data. All this is true for both Python programs and the + Python runtime.The cost of this broad, unstructured requirement is + the tradeoff for the kind of raw concurrency that threads provide. + The alternative to the required discipline generally means dealing + with non-deterministic bugs and data corruption. + + +Python Runtime Model +-------------------- + +The same conceptual layers apply to each Python program, with some +extra data layers specific to Python: + + **host machine** + **process** (global resources) + Python global runtime (*state*) + Python interpreter (*state*) + **thread** (runs Python bytecode and “C-API”) + Python thread *state* + +At the conceptual level: when a Python program starts, it looks +exactly like that diagram, with one of each. The runtime may grow to +include multiple interpreters, and each interpreter may grow to +include multiple thread states. + +Note: + + A Python implementation won’t necessarily implement the runtime + layers distinctly or even concretely. The only exception is places + where distinct layers are directly specified or exposed to users, + like through the "threading" module. + +Note: + + The initial interpreter is typically called the “main” interpreter. + Some Python implementations, like CPython, assign special roles to + the main interpreter.Likewise, the host thread where the runtime was + initialized is known as the “main” thread. It may be different from + the process’ initial thread, though they are often the same. In + some cases “main thread” may be even more specific and refer to the + initial thread state. A Python runtime might assign specific + responsibilities to the main thread, such as handling signals. + +As a whole, the Python runtime consists of the global runtime state, +interpreters, and thread states. The runtime ensures all that state +stays consistent over its lifetime, particularly when used with +multiple host threads. + +The global runtime, at the conceptual level, is just a set of +interpreters. While those interpreters are otherwise isolated and +independent from one another, they may share some data or other +resources. The runtime is responsible for managing these global +resources safely. The actual nature and management of these resources +is implementation-specific. Ultimately, the external utility of the +global runtime is limited to managing interpreters. + +In contrast, an “interpreter” is conceptually what we would normally +think of as the (full-featured) “Python runtime”. When machine code +executing in a host thread interacts with the Python runtime, it calls +into Python in the context of a specific interpreter. + +Note: + + The term “interpreter” here is not the same as the “bytecode + interpreter”, which is what regularly runs in threads, executing + compiled Python code.In an ideal world, “Python runtime” would refer + to what we currently call “interpreter”. However, it’s been called + “interpreter” at least since introduced in 1997 (CPython:a027efa5b). + +Each interpreter completely encapsulates all of the non-process- +global, non-thread-specific state needed for the Python runtime to +work. Notably, the interpreter’s state persists between uses. It +includes fundamental data like "sys.modules". The runtime ensures +multiple threads using the same interpreter will safely share it +between them. + +A Python implementation may support using multiple interpreters at the +same time in the same process. They are independent and isolated from +one another. For example, each interpreter has its own "sys.modules". + +For thread-specific runtime state, each interpreter has a set of +thread states, which it manages, in the same way the global runtime +contains a set of interpreters. It can have thread states for as many +host threads as it needs. It may even have multiple thread states for +the same host thread, though that isn’t as common. + +Each thread state, conceptually, has all the thread-specific runtime +data an interpreter needs to operate in one host thread. The thread +state includes the current raised exception and the thread’s Python +call stack. It may include other thread-specific resources. + +Note: + + The term “Python thread” can sometimes refer to a thread state, but + normally it means a thread created using the "threading" module. + +Each thread state, over its lifetime, is always tied to exactly one +interpreter and exactly one host thread. It will only ever be used in +that thread and with that interpreter. + +Multiple thread states may be tied to the same host thread, whether +for different interpreters or even the same interpreter. However, for +any given host thread, only one of the thread states tied to it can be +used by the thread at a time. + +Thread states are isolated and independent from one another and don’t +share any data, except for possibly sharing an interpreter and objects +or other resources belonging to that interpreter. + +Once a program is running, new Python threads can be created using the +"threading" module (on platforms and Python implementations that +support threads). Additional processes can be created using the "os", +"subprocess", and "multiprocessing" modules. Coroutines (async) can be +run using "asyncio" in each interpreter, typically only in a single +thread (often the main thread). + -[ Footnotes ]- [1] This limitation occurs because the code that is executed by these @@ -5317,7 +5486,8 @@ following: | | is not supported. | +-----------+------------------------------------------------------------+ -For a locale aware separator, use the "'n'" presentation type instead. +For a locale-aware separator, use the "'n'" float presentation type or +integer presentation type instead. Changed in version 3.1: Added the "','" option (see also **PEP 378**). @@ -5368,7 +5538,10 @@ The available integer presentation types are: +-----------+------------------------------------------------------------+ | "'n'" | Number. This is the same as "'d'", except that it uses the | | | current locale setting to insert the appropriate digit | - | | group separators. | + | | group separators. Note that the default locale is not the | + | | system locale. Depending on your use case, you may wish to | + | | set "LC_NUMERIC" with "locale.setlocale()" before using | + | | "'n'". | +-----------+------------------------------------------------------------+ | None | The same as "'d'". | +-----------+------------------------------------------------------------+ @@ -5442,7 +5615,10 @@ The available presentation types for "float" and "Decimal" values are: +-----------+------------------------------------------------------------+ | "'n'" | Number. This is the same as "'g'", except that it uses the | | | current locale setting to insert the appropriate digit | - | | group separators for the integral part of a number. | + | | group separators for the integral part of a number. Note | + | | that the default locale is not the system locale. | + | | Depending on your use case, you may wish to set | + | | "LC_NUMERIC" with "locale.setlocale()" before using "'n'". | +-----------+------------------------------------------------------------+ | "'%'" | Percentage. Multiplies the number by 100 and displays in | | | fixed ("'f'") format, followed by a percent sign. | @@ -6039,8 +6215,9 @@ steps: 1. find a module, loading and initializing it if necessary -2. define a name or names in the local namespace for the scope where - the "import" statement occurs. +2. define a name or names in the current namespace for the scope where + the "import" statement occurs, just as an assignment statement + would (including "global" and "nonlocal" semantics). When the statement contains multiple clauses (separated by commas) the two steps are carried out separately for each clause, just as though @@ -6085,7 +6262,7 @@ The "from" form uses a slightly more complex process: 3. if the attribute is not found, "ImportError" is raised. - 4. otherwise, a reference to that value is stored in the local + 4. otherwise, a reference to that value is stored in the current namespace, using the name in the "as" clause if it is present, otherwise using the attribute name @@ -9342,9 +9519,22 @@ str.isdigit() decimal characters and digits that need special handling, such as the compatibility superscript digits. This covers digits which cannot be used to form numbers in base 10, like the Kharosthi - numbers. Formally, a digit is a character that has the property + numbers. Formally, a digit is a character that has the property value Numeric_Type=Digit or Numeric_Type=Decimal. + For example: + + >>> '0123456789'.isdigit() + True + >>> '٠١٢٣٤٥٦٧٨٩'.isdigit() # Arabic-Indic digits zero to nine + True + >>> '⅕'.isdigit() # Vulgar fraction one fifth + False + >>> '²'.isdecimal(), '²'.isdigit(), '²'.isnumeric() + (False, True, True) + + See also "isdecimal()" and "isnumeric()". + str.isidentifier() Return "True" if the string is a valid identifier according to the @@ -9380,15 +9570,14 @@ str.isnumeric() >>> '0123456789'.isnumeric() True - >>> '٠١٢٣٤٥٦٧٨٩'.isnumeric() # Arabic-indic digit zero to nine + >>> '٠١٢٣٤٥٦٧٨٩'.isnumeric() # Arabic-Indic digits zero to nine True >>> '⅕'.isnumeric() # Vulgar fraction one fifth True >>> '²'.isdecimal(), '²'.isdigit(), '²'.isnumeric() (False, True, True) - See also "isdecimal()" and "isdigit()". Numeric characters are a - superset of decimal numbers. + See also "isdecimal()" and "isdigit()". str.isprintable() @@ -9770,7 +9959,7 @@ str.split(sep=None, maxsplit=-1) >>> " foo ".split(maxsplit=0) ['foo '] - See also "join()". + See also "join()" and "rsplit()". str.splitlines(keepends=False) @@ -9860,6 +10049,8 @@ str.strip(chars=None, /) not a prefix or suffix; rather, all combinations of its values are stripped. + Whitespace characters are defined by "str.isspace()". + For example: >>> ' spacious '.strip() @@ -9884,8 +10075,18 @@ str.strip(chars=None, /) str.swapcase() Return a copy of the string with uppercase characters converted to - lowercase and vice versa. Note that it is not necessarily true that - "s.swapcase().swapcase() == s". + lowercase and vice versa. For example: + + >>> 'Hello World'.swapcase() + 'hELLO wORLD' + + Note that it is not necessarily true that "s.swapcase().swapcase() + == s". For example: + + >>> 'straße'.swapcase().swapcase() + 'strasse' + + See also "str.lower()" and "str.upper()". str.title() @@ -11899,6 +12100,9 @@ class dict(iterable, /, **kwargs) insertion order. This behavior was an implementation detail of CPython from 3.6. + Dictionaries are generic over two types, signifying (respectively) + the types of the dictionary’s keys and values. + These are the operations that dictionaries support (and therefore, custom mapping types should support too): @@ -12598,6 +12802,8 @@ class list(iterable=(), /) Many other operations also produce lists, including the "sorted()" built-in. + Lists are generic over the types of their items. + Lists implement all of the common and mutable sequence operations. Lists also provide the following additional method: @@ -12683,6 +12889,10 @@ class tuple(iterable=(), /) Tuples implement all of the common sequence operations. + Tuples are generic over the types of their contents. For more + information, refer to the typing documentation on annotating + tuples. + For heterogeneous collections of data where access by name is clearer than access by index, "collections.namedtuple()" may be a more appropriate choice than a simple tuple object. diff --git a/contrib/tools/python3/Lib/rlcompleter.py b/contrib/tools/python3/Lib/rlcompleter.py index 23eb0020f42..e75dd0a9e3d 100644 --- a/contrib/tools/python3/Lib/rlcompleter.py +++ b/contrib/tools/python3/Lib/rlcompleter.py @@ -34,6 +34,7 @@ import builtins import inspect import keyword import re +import types import __main__ import warnings @@ -178,14 +179,14 @@ class Completer: if (word[:n] == attr and not (noprefix and word[:n+1] == noprefix)): match = "%s.%s" % (expr, word) - if isinstance(getattr(type(thisobject), word, None), - property): - # bpo-44752: thisobject.word is a method decorated by - # `@property`. What follows applies a postfix if - # thisobject.word is callable, but know we know that - # this is not callable (because it is a property). - # Also, getattr(thisobject, word) will evaluate the - # property method, which is not desirable. + + class_attr = getattr(type(thisobject), word, None) + if isinstance( + class_attr, + (property, types.GetSetDescriptorType, types.MemberDescriptorType) + ) or (hasattr(class_attr, '__get__') and not callable(class_attr)): + # Avoid evaluating descriptors, which could run + # arbitrary code or raise exceptions. matches.append(match) continue if (value := getattr(thisobject, word, None)) is not None: diff --git a/contrib/tools/python3/Lib/runpy.py b/contrib/tools/python3/Lib/runpy.py index ef54d3282ee..1d5ecf0cf15 100644 --- a/contrib/tools/python3/Lib/runpy.py +++ b/contrib/tools/python3/Lib/runpy.py @@ -103,8 +103,10 @@ def _run_module_code(code, init_globals=None, # Helper to get the full name, spec and code for a module def _get_module_details(mod_name, error=ImportError): + # name= is only accepted by ImportError and its subclasses. + kwargs = {"name": mod_name} if issubclass(error, ImportError) else {} if mod_name.startswith("."): - raise error("Relative module names not supported") + raise error("Relative module names not supported", **kwargs) pkg_name, _, _ = mod_name.rpartition(".") if pkg_name: # Try importing the parent to avoid catching initialization errors @@ -137,12 +139,13 @@ def _get_module_details(mod_name, error=ImportError): if mod_name.endswith(".py"): msg += (f". Try using '{mod_name[:-3]}' instead of " f"'{mod_name}' as the module name.") - raise error(msg.format(mod_name, type(ex).__name__, ex)) from ex + raise error(msg.format(mod_name, type(ex).__name__, ex), + **kwargs) from ex if spec is None: - raise error("No module named %s" % mod_name) + raise error("No module named %s" % mod_name, **kwargs) if spec.submodule_search_locations is not None: if mod_name == "__main__" or mod_name.endswith(".__main__"): - raise error("Cannot use package as __main__ module") + raise error("Cannot use package as __main__ module", **kwargs) try: pkg_main_name = mod_name + ".__main__" return _get_module_details(pkg_main_name, error) @@ -150,17 +153,19 @@ def _get_module_details(mod_name, error=ImportError): if mod_name not in sys.modules: raise # No module loaded; being a package is irrelevant raise error(("%s; %r is a package and cannot " + - "be directly executed") %(e, mod_name)) + "be directly executed") %(e, mod_name), + **kwargs) loader = spec.loader if loader is None: raise error("%r is a namespace package and cannot be executed" - % mod_name) + % mod_name, + **kwargs) try: code = loader.get_code(mod_name) except ImportError as e: - raise error(format(e)) from e + raise error(format(e), **kwargs) from e if code is None: - raise error("No code object available for %s" % mod_name) + raise error("No code object available for %s" % mod_name, **kwargs) return mod_name, spec, code class _Error(Exception): @@ -234,6 +239,7 @@ def _get_main_module_details(error=ImportError): # Also moves the standard __main__ out of the way so that the # preexisting __loader__ entry doesn't cause issues main_name = "__main__" + kwargs = {"name": main_name} if issubclass(error, ImportError) else {} saved_main = sys.modules[main_name] del sys.modules[main_name] try: @@ -241,7 +247,8 @@ def _get_main_module_details(error=ImportError): except ImportError as exc: if main_name in str(exc): raise error("can't find %r module in %r" % - (main_name, sys.path[0])) from exc + (main_name, sys.path[0]), + **kwargs) from exc raise finally: sys.modules[main_name] = saved_main diff --git a/contrib/tools/python3/Lib/shutil.py b/contrib/tools/python3/Lib/shutil.py index 7df972012c7..86322f05444 100644 --- a/contrib/tools/python3/Lib/shutil.py +++ b/contrib/tools/python3/Lib/shutil.py @@ -823,10 +823,14 @@ def move(src, dst, copy_function=copy2): If dst already exists but is not a directory, it may be overwritten depending on os.rename() semantics. - If the destination is on our current filesystem, then rename() is used. - Otherwise, src is copied to the destination and then removed. Symlinks are - recreated under the new name if os.rename() fails because of cross - filesystem renames. + os.rename() is preferably used if the source and destination are on the + same filesystem. In case os.rename() fails due to OSError (e.g. the user + has write permission to *dst* file but not to its parent directory), + this method falls back to using *copy_function* silently. + Symlinks are also recreated under the new name if os.rename() fails + because of cross filesystem renames. + + It's recommended to use os.rename() if atomic move is strictly required. The optional `copy_function` argument is a callable that will be used to copy the source or it will be delegated to `copytree`. @@ -878,8 +882,8 @@ def move(src, dst, copy_function=copy2): return real_dst def _destinsrc(src, dst): - src = os.path.abspath(src) - dst = os.path.abspath(dst) + src = os.path.realpath(src) + dst = os.path.realpath(dst) if not src.endswith(os.path.sep): src += os.path.sep if not dst.endswith(os.path.sep): @@ -1246,27 +1250,9 @@ def _unpack_zipfile(filename, extract_dir): if not zipfile.is_zipfile(filename): raise ReadError("%s is not a zip file" % filename) - zip = zipfile.ZipFile(filename) - try: - for info in zip.infolist(): - name = info.filename - - # don't extract absolute paths or ones with .. in them - if name.startswith('/') or '..' in name: - continue - - targetpath = os.path.join(extract_dir, *name.split('/')) - if not targetpath: - continue - - _ensure_directory(targetpath) - if not name.endswith('/'): - # file - with zip.open(name, 'r') as source, \ - open(targetpath, 'wb') as target: - copyfileobj(source, target) - finally: - zip.close() + with zipfile.ZipFile(filename) as zip: + zip._ignore_invalid_names = True + zip.extractall(extract_dir) def _unpack_tarfile(filename, extract_dir, *, filter=None): """Unpack tar/tar.gz/tar.bz2/tar.xz `filename` to `extract_dir` diff --git a/contrib/tools/python3/Lib/smtplib.py b/contrib/tools/python3/Lib/smtplib.py index 9bedcc5ff6c..95ad966c393 100755 --- a/contrib/tools/python3/Lib/smtplib.py +++ b/contrib/tools/python3/Lib/smtplib.py @@ -253,7 +253,6 @@ class SMTP: will be used. """ - self._host = host self.timeout = timeout self.esmtp_features = {} self.command_encoding = 'ascii' @@ -344,6 +343,7 @@ class SMTP: port = int(port) except ValueError: raise OSError("nonnumeric port") + self._host = host if not port: port = self.default_port sys.audit("smtplib.connect", self, host, port) diff --git a/contrib/tools/python3/Lib/socket.py b/contrib/tools/python3/Lib/socket.py index 35d87eff34d..55644bd4c17 100644 --- a/contrib/tools/python3/Lib/socket.py +++ b/contrib/tools/python3/Lib/socket.py @@ -634,18 +634,22 @@ def _fallback_socketpair(family=AF_INET, type=SOCK_STREAM, proto=0): # Authenticating avoids using a connection from something else # able to connect to {host}:{port} instead of us. # We expect only AF_INET and AF_INET6 families. - try: - if ( - ssock.getsockname() != csock.getpeername() - or csock.getsockname() != ssock.getpeername() - ): - raise ConnectionError("Unexpected peer connection") - except: - # getsockname() and getpeername() can fail - # if either socket isn't connected. - ssock.close() - csock.close() - raise + # + # Note that we skip this on WASI because on that platorm the client socket + # may not have finished connecting by the time we've reached this point (gh-146139). + if sys.platform != "wasi": + try: + if ( + ssock.getsockname() != csock.getpeername() + or csock.getsockname() != ssock.getpeername() + ): + raise ConnectionError("Unexpected peer connection") + except: + # getsockname() and getpeername() can fail + # if either socket isn't connected. + ssock.close() + csock.close() + raise return (ssock, csock) diff --git a/contrib/tools/python3/Lib/tarfile.py b/contrib/tools/python3/Lib/tarfile.py index 533c0cc8736..b22b2b38abb 100755 --- a/contrib/tools/python3/Lib/tarfile.py +++ b/contrib/tools/python3/Lib/tarfile.py @@ -489,7 +489,7 @@ class _Stream: if flag & 4: xlen = ord(self.__read(1)) + 256 * ord(self.__read(1)) - self.read(xlen) + self.__read(xlen) if flag & 8: while True: s = self.__read(1) @@ -819,16 +819,22 @@ def _get_filtered_attrs(member, dest_path, for_data=True): if member.islnk() or member.issym(): if os.path.isabs(member.linkname): raise AbsoluteLinkError(member) + # A link member that resolves to the destination directory itself + # would replace it with a (sym)link, redirecting the destination + # for all subsequent members. + if target_path == dest_path: + raise OutsideDestinationError(member, target_path) normalized = os.path.normpath(member.linkname) if normalized != member.linkname: new_attrs['linkname'] = normalized if member.issym(): - target_path = os.path.join(dest_path, - os.path.dirname(name), - member.linkname) + # The symlink is created at `name` with trailing separators + # stripped, so its target is relative to the directory + # containing that path. + link_dir = os.path.dirname(name.rstrip('/' + os.sep)) + target_path = os.path.join(dest_path, link_dir, normalized) else: - target_path = os.path.join(dest_path, - member.linkname) + target_path = os.path.join(dest_path, normalized) target_path = os.path.realpath(target_path, strict=os.path.ALLOW_MISSING) if os.path.commonpath([target_path, dest_path]) != dest_path: @@ -882,11 +888,14 @@ class TarInfo(object): size = 'Size in bytes.', mtime = 'Time of last modification.', chksum = 'Header checksum.', - type = ('File type. type is usually one of these constants: ' - 'REGTYPE, AREGTYPE, LNKTYPE, SYMTYPE, DIRTYPE, FIFOTYPE, ' - 'CONTTYPE, CHRTYPE, BLKTYPE, GNUTYPE_SPARSE.'), + type = ('File type. type is usually one of these constants: ' + 'REGTYPE,\n' + 'AREGTYPE, LNKTYPE, SYMTYPE, DIRTYPE, FIFOTYPE, ' + 'CONTTYPE, CHRTYPE,\n' + 'BLKTYPE, GNUTYPE_SPARSE.'), linkname = ('Name of the target file name, which is only present ' - 'in TarInfo objects of type LNKTYPE and SYMTYPE.'), + 'in TarInfo\n' + 'objects of type LNKTYPE and SYMTYPE.'), uname = 'User name.', gname = 'Group name.', devmajor = 'Device major number.', @@ -894,7 +903,8 @@ class TarInfo(object): offset = 'The tar header starts here.', offset_data = "The file's data starts here.", pax_headers = ('A dictionary containing key-value pairs of an ' - 'associated pax extended header.'), + 'associated pax\n' + 'extended header.'), sparse = 'Sparse member information.', _tarfile = None, _sparse_structs = None, @@ -2198,10 +2208,11 @@ class TarFile(object): return tarinfo def list(self, verbose=True, *, members=None): - """Print a table of contents to sys.stdout. If `verbose' is False, only - the names of the members are printed. If it is True, an `ls -l'-like - output is produced. `members' is optional and must be a subset of the - list returned by getmembers(). + """Print a table of contents to sys.stdout. + + If `verbose' is False, only the names of the members are printed. + If it is True, an `ls -l'-like output is produced. `members' is + optional and must be a subset of the list returned by getmembers(). """ # Convert tarinfo type to stat type. type2mode = {REGTYPE: stat.S_IFREG, SYMTYPE: stat.S_IFLNK, @@ -2292,10 +2303,12 @@ class TarFile(object): self.addfile(tarinfo) def addfile(self, tarinfo, fileobj=None): - """Add the TarInfo object `tarinfo' to the archive. If `tarinfo' represents - a non zero-size regular file, the `fileobj' argument should be a binary file, - and tarinfo.size bytes are read from it and added to the archive. - You can create TarInfo objects directly, or by using gettarinfo(). + """Add the TarInfo object `tarinfo' to the archive. + + If `tarinfo' represents a non zero-size regular file, the `fileobj' + argument should be a binary file, and tarinfo.size bytes are read + from it and added to the archive. You can create TarInfo objects + directly, or by using gettarinfo(). """ self._check("awx") diff --git a/contrib/tools/python3/Lib/timeit.py b/contrib/tools/python3/Lib/timeit.py index 02cfafaf36e..f5f75048be1 100755 --- a/contrib/tools/python3/Lib/timeit.py +++ b/contrib/tools/python3/Lib/timeit.py @@ -322,7 +322,7 @@ def main(args=None, *, _wrap_timer=None): callback = None if verbose: def callback(number, time_taken): - msg = "{num} loop{s} -> {secs:.{prec}g} secs" + msg = "{num} loop{s} -> {secs:.{prec}g} sec" plural = (number != 1) print(msg.format(num=number, s='s' if plural else '', secs=time_taken, prec=precision)) diff --git a/contrib/tools/python3/Lib/tomllib/_parser.py b/contrib/tools/python3/Lib/tomllib/_parser.py index 9c80a6a547d..a1f7ffd6d24 100644 --- a/contrib/tools/python3/Lib/tomllib/_parser.py +++ b/contrib/tools/python3/Lib/tomllib/_parser.py @@ -6,8 +6,9 @@ from __future__ import annotations from collections.abc import Iterable import string +import sys from types import MappingProxyType -from typing import Any, BinaryIO, NamedTuple +from typing import Any, BinaryIO, NamedTuple, Final from ._re import ( RE_DATETIME, @@ -19,6 +20,13 @@ from ._re import ( ) from ._types import Key, ParseFloat, Pos +# Pathologically excessive number of parts in a key runs into quadratic +# behavior (e.g. in Flags.is_). +# Even if keys aren't currently parsed using recursion, they name a +# recursive structure, so it makes sense to limit it using getrecursionlimit() +# and RecursionError. +MAX_KEY_PARTS: Final = sys.getrecursionlimit() + ASCII_CTRL = frozenset(chr(i) for i in range(32)) | frozenset(chr(127)) # Neither of these sets include quotation mark or backslash. They are @@ -385,6 +393,10 @@ def parse_key(src: str, pos: Pos) -> tuple[Pos, Key]: pos = skip_chars(src, pos, TOML_WS) pos, key_part = parse_key_part(src, pos) key += (key_part,) + if len(key) > MAX_KEY_PARTS: + raise RecursionError( + f"TOML key has more than the allowed {MAX_KEY_PARTS} parts" + ) pos = skip_chars(src, pos, TOML_WS) diff --git a/contrib/tools/python3/Lib/traceback.py b/contrib/tools/python3/Lib/traceback.py index b412954bd53..0acb75bbab5 100644 --- a/contrib/tools/python3/Lib/traceback.py +++ b/contrib/tools/python3/Lib/traceback.py @@ -70,10 +70,10 @@ def extract_tb(tb, limit=None): This is useful for alternate formatting of stack traces. If 'limit' is omitted or None, all entries are extracted. A pre-processed stack trace entry is a FrameSummary object - containing attributes filename, lineno, name, and line - representing the information that is usually printed for a stack - trace. The line is a string with leading and trailing - whitespace stripped; if the source is not available it is None. + representing the information that is usually printed for a + stack trace. The line attribute is a string with + leading and trailing whitespace stripped; if the source is not + available the corresponding attribute is None. """ return StackSummary._extract_from_extended_frame_gen( _walk_tb_with_full_positions(tb), limit=limit) @@ -251,9 +251,8 @@ def extract_stack(f=None, limit=None): The return value has the same format as for extract_tb(). The optional 'f' and 'limit' arguments have the same meaning as for - print_stack(). Each item in the list is a quadruple (filename, - line number, function name, text), and the entries are in order - from oldest to newest stack frame. + print_stack(). Each item in the list is a FrameSummary object, + and the entries are in order from oldest to newest stack frame. """ if f is None: f = sys._getframe().f_back @@ -281,7 +280,7 @@ class FrameSummary: active when the frame was captured. - :attr:`name` The name of the function or method that was executing when the frame was captured. - - :attr:`line` The text from the linecache module for the + - :attr:`line` The text from the linecache module for the line of code that was running when the frame was captured. - :attr:`locals` Either None if locals were not supplied, or a dict mapping the name to the repr() of the variable. @@ -951,7 +950,7 @@ def _extract_caret_anchors_from_line_segment(segment): _WIDE_CHAR_SPECIFIERS = "WF" def _display_width(line, offset=None): - """Calculate the extra amount of width space the given source + """Calculate the amount of width space the given source code segment might take if it were to be displayed on a fixed width output device. Supports wide unicode characters and emojis.""" @@ -1037,7 +1036,7 @@ class TracebackException: def __init__(self, exc_type, exc_value, exc_traceback, *, limit=None, lookup_lines=True, capture_locals=False, compact=False, max_group_width=15, max_group_depth=10, save_exc_type=True, _seen=None): - # NB: we need to accept exc_traceback, exc_value, exc_traceback to + # NB: we need to accept exc_type, exc_value, exc_traceback to # permit backwards compat with the existing API, otherwise we # need stub thunk objects just to glue it together. # Handle loops in __cause__ or __context__. diff --git a/contrib/tools/python3/Lib/types.py b/contrib/tools/python3/Lib/types.py index ff474c14144..84622a5b4df 100644 --- a/contrib/tools/python3/Lib/types.py +++ b/contrib/tools/python3/Lib/types.py @@ -176,18 +176,19 @@ def get_original_bases(cls, /): class DynamicClassAttribute: """Route attribute access on a class to __getattr__. - This is a descriptor, used to define attributes that act differently when - accessed through an instance and through a class. Instance access remains - normal, but access to an attribute through a class will be routed to the - class's __getattr__ method; this is done by raising AttributeError. + This is a descriptor, used to define attributes that act differently + when accessed through an instance and through a class. Instance access + remains normal, but access to an attribute through a class will be + routed to the class's __getattr__ method; this is done by raising + AttributeError. - This allows one to have properties active on an instance, and have virtual - attributes on the class with the same name. (Enum used this between Python - versions 3.4 - 3.9 .) + This allows one to have properties active on an instance, and have + virtual attributes on the class with the same name. (Enum used this + between Python versions 3.4 - 3.9 .) - Subclass from this to use a different method of accessing virtual attributes - and still be treated properly by the inspect module. (Enum uses this since - Python 3.10 .) + Subclass from this to use a different method of accessing virtual + attributes and still be treated properly by the inspect module. (Enum + uses this since Python 3.10 .) """ def __init__(self, fget=None, fset=None, fdel=None, doc=None): diff --git a/contrib/tools/python3/Lib/typing.py b/contrib/tools/python3/Lib/typing.py index cbc6d90e13a..381aaf3c7d0 100644 --- a/contrib/tools/python3/Lib/typing.py +++ b/contrib/tools/python3/Lib/typing.py @@ -5,7 +5,7 @@ Among other things, the module includes the following: * Generic, Protocol, and internal machinery to support generic aliases. All subscripted types like X[int], Union[int, str] are generic aliases. * Various "special forms" that have unique meanings in type annotations: - NoReturn, Never, ClassVar, Self, Concatenate, Unpack, and others. + Any, Never, ClassVar, Self, Concatenate, Unpack, and others. * Classes whose instances can be type arguments to generic classes and functions: TypeVar, ParamSpec, TypeVarTuple. * Public helper functions: get_type_hints, overload, cast, final, and others. @@ -598,12 +598,12 @@ class _AnyMeta(type): class Any(metaclass=_AnyMeta): """Special type indicating an unconstrained type. - - Any is compatible with every type. - - Any assumed to have all methods. - - All values assumed to be instances of Any. + - Any is assignable to every type. + - Any assumed to have all methods and attributes. + - All values are assignable to Any. Note that all the above statements are true from the point of view of - static type checkers. At runtime, Any should not be used with instance + static type checkers. At runtime, Any cannot be used with instance checks. """ @@ -722,7 +722,7 @@ def ClassVar(self, parameters): ClassVar accepts only types and cannot be further subscribed. - Note that ClassVar is not a class itself, and should not + Note that ClassVar is not a class itself, and cannot be used with isinstance() or issubclass(). """ item = _type_check(parameters, f'{self} accepts only single type.', allow_special_forms=True) @@ -805,7 +805,7 @@ def _make_union(left, right): @_SpecialForm def Optional(self, parameters): - """Optional[X] is equivalent to Union[X, None].""" + """Optional[X] is equivalent to X | None.""" arg = _type_check(parameters, f"{self} requires a single type.") return Union[arg, type(None)] @@ -848,7 +848,7 @@ def Literal(self, *parameters): def TypeAlias(self, parameters): """Special form for marking type aliases. - Use TypeAlias to indicate that an assignment should + TypeAlias can be used to indicate that an assignment should be recognized as a proper type alias definition by type checkers. @@ -1410,31 +1410,35 @@ class _BaseGenericAlias(_Final, _root=True): class _GenericAlias(_BaseGenericAlias, _root=True): - # The type of parameterized generics. - # - # That is, for example, `type(List[int])` is `_GenericAlias`. - # - # Objects which are instances of this class include: - # * Parameterized container types, e.g. `Tuple[int]`, `List[int]`. - # * Note that native container types, e.g. `tuple`, `list`, use - # `types.GenericAlias` instead. - # * Parameterized classes: - # class C[T]: pass - # # C[int] is a _GenericAlias - # * `Callable` aliases, generic `Callable` aliases, and - # parameterized `Callable` aliases: - # T = TypeVar('T') - # # _CallableGenericAlias inherits from _GenericAlias. - # A = Callable[[], None] # _CallableGenericAlias - # B = Callable[[T], None] # _CallableGenericAlias - # C = B[int] # _CallableGenericAlias - # * Parameterized `Final`, `ClassVar`, `TypeGuard`, and `TypeIs`: - # # All _GenericAlias - # Final[int] - # ClassVar[float] - # TypeGuard[bool] - # TypeIs[range] + """The type of parameterized generics. + That is, for example, `type(List[int])` is `_GenericAlias`. + + Objects which are instances of this class include: + * Parameterized container types, e.g. `Tuple[int]`, `List[int]`. + * Note that native container types, e.g. `tuple`, `list`, use + `types.GenericAlias` instead. + * Parameterized classes: + class C[T]: pass + # C[int] is a _GenericAlias + * `Callable` aliases, generic `Callable` aliases, and + parameterized `Callable` aliases: + T = TypeVar('T') + # _CallableGenericAlias inherits from _GenericAlias. + A = Callable[[], None] # _CallableGenericAlias + B = Callable[[T], None] # _CallableGenericAlias + C = B[int] # _CallableGenericAlias + * Parameterized `Final`, `ClassVar`, `TypeForm`, `TypeGuard`, and `TypeIs`: + # All _GenericAlias + Final[int] + ClassVar[float] + TypeForm[bytearray] + TypeGuard[bool] + TypeIs[range] + + Note that instances of this class are not classes (e.g by `inspect.isclass`), + even though they behave like them. + """ def __init__(self, origin, args, *, inst=True, name=None): super().__init__(origin, inst=inst, name=name) if not isinstance(args, tuple): @@ -1466,20 +1470,21 @@ class _GenericAlias(_BaseGenericAlias, _root=True): @_tp_cache def __getitem__(self, args): - # Parameterizes an already-parameterized object. - # - # For example, we arrive here doing something like: - # T1 = TypeVar('T1') - # T2 = TypeVar('T2') - # T3 = TypeVar('T3') - # class A(Generic[T1]): pass - # B = A[T2] # B is a _GenericAlias - # C = B[T3] # Invokes _GenericAlias.__getitem__ - # - # We also arrive here when parameterizing a generic `Callable` alias: - # T = TypeVar('T') - # C = Callable[[T], None] - # C[int] # Invokes _GenericAlias.__getitem__ + """Parameterizes an already-parameterized object. + + For example, we arrive here doing something like: + T1 = TypeVar('T1') + T2 = TypeVar('T2') + T3 = TypeVar('T3') + class A(Generic[T1]): pass + B = A[T2] # B is a _GenericAlias + C = B[T3] # Invokes _GenericAlias.__getitem__ + + We also arrive here when parameterizing a generic `Callable` alias: + T = TypeVar('T') + C = Callable[[T], None] + C[int] # Invokes _GenericAlias.__getitem__ + """ if self.__origin__ in (Generic, Protocol): # Can't subscript Generic[...] or Protocol[...]. @@ -1496,20 +1501,20 @@ class _GenericAlias(_BaseGenericAlias, _root=True): return r def _determine_new_args(self, args): - # Determines new __args__ for __getitem__. - # - # For example, suppose we had: - # T1 = TypeVar('T1') - # T2 = TypeVar('T2') - # class A(Generic[T1, T2]): pass - # T3 = TypeVar('T3') - # B = A[int, T3] - # C = B[str] - # `B.__args__` is `(int, T3)`, so `C.__args__` should be `(int, str)`. - # Unfortunately, this is harder than it looks, because if `T3` is - # anything more exotic than a plain `TypeVar`, we need to consider - # edge cases. + """Determines new __args__ for __getitem__. + For example, suppose we had: + T1 = TypeVar('T1') + T2 = TypeVar('T2') + class A(Generic[T1, T2]): pass + T3 = TypeVar('T3') + B = A[int, T3] + C = B[str] + `B.__args__` is `(int, T3)`, so `C.__args__` should be `(int, str)`. + Unfortunately, this is harder than it looks, because if `T3` is + anything more exotic than a plain `TypeVar`, we need to consider + edge cases. + """ params = self.__parameters__ # In the example above, this would be {T3: str} for param in params: @@ -1881,7 +1886,7 @@ def Unpack(self, parameters): def foo(**kwargs: Unpack[Movie]): ... Note that there is only some runtime checking of this operator. Not - everything the runtime allows may be accepted by static type checkers. + everything the runtime allows is accepted by static type checkers. For more information, see PEPs 646 and 692. """ @@ -2347,7 +2352,7 @@ def runtime_checkable(cls): Such protocol can be used with isinstance() and issubclass(). Raise TypeError if applied to a non-protocol class. This allows a simple-minded structural check very similar to - one trick ponies in collections.abc such as Iterable. + one-trick ponies in collections.abc such as Iterable. For example:: @@ -2418,8 +2423,8 @@ _allowed_types = (types.FunctionType, types.BuiltinFunctionType, def get_type_hints(obj, globalns=None, localns=None, include_extras=False): """Return type hints for an object. - This is often the same as obj.__annotations__, but it handles - forward references encoded as string literals and recursively replaces all + This is often the same as inspect.get_annotations(obj) or obj.__annotations__, + but it handles forward references encoded as string literals and recursively replaces all 'Annotated[T, ...]' with 'T' (unless 'include_extras=True'). The argument may be a module, class, method, or function. The annotations @@ -2483,8 +2488,12 @@ def get_type_hints(obj, globalns=None, localns=None, include_extras=False): else: nsobj = obj # Find globalns for the unwrapped object. + seen = {id(nsobj)} while hasattr(nsobj, '__wrapped__'): nsobj = nsobj.__wrapped__ + if id(nsobj) in seen: + raise ValueError(f'wrapper loop when unwrapping {obj!r}') + seen.add(id(nsobj)) globalns = getattr(nsobj, '__globals__', {}) if localns is None: localns = globalns @@ -2597,7 +2606,7 @@ def get_args(tp): def is_typeddict(tp): - """Check if an annotation is a TypedDict class. + """Check if an object is a TypedDict class. For example:: @@ -2711,10 +2720,10 @@ _overload_registry = defaultdict(functools.partial(defaultdict, dict)) def overload(func): """Decorator for overloaded functions/methods. - In a stub file, place two or more stub definitions for the same - function in a row, each decorated with @overload. - - For example:: + In a non-stub file, place two or more stub definitions for the same + function in a row, each decorated with @overload, followed + by an implementation. The implementation should *not* + be decorated with @overload:: @overload def utf8(value: None) -> None: ... @@ -2722,10 +2731,11 @@ def overload(func): def utf8(value: bytes) -> bytes: ... @overload def utf8(value: str) -> bytes: ... + def utf8(value): + ... # implementation goes here - In a non-stub file (i.e. a regular .py file), do the same but - follow it with an implementation. The implementation should *not* - be decorated with @overload:: + In a stub file or in an abstract method (for example, in a Protocol definition), + the implementation may be omitted:: @overload def utf8(value: None) -> None: ... @@ -2733,8 +2743,6 @@ def overload(func): def utf8(value: bytes) -> bytes: ... @overload def utf8(value: str) -> bytes: ... - def utf8(value): - ... # implementation goes here The overloads for a function can be retrieved at runtime using the get_overloads() function. @@ -2770,7 +2778,7 @@ def final(f): """Decorator to indicate final methods and final classes. Use this decorator to indicate to type checkers that the decorated - method cannot be overridden, and decorated class cannot be subclassed. + method cannot be overridden, and the decorated class cannot be subclassed. For example:: @@ -2812,7 +2820,7 @@ T_co = TypeVar('T_co', covariant=True) # Any type covariant containers. V_co = TypeVar('V_co', covariant=True) # Any type covariant containers. VT_co = TypeVar('VT_co', covariant=True) # Value type covariant containers. T_contra = TypeVar('T_contra', contravariant=True) # Ditto contravariant. -# Internal type variable used for Type[]. +# Internal type bound to class object types. CT_co = TypeVar('CT_co', covariant=True, bound=type) @@ -2903,7 +2911,7 @@ Type.__doc__ = \ And a function that takes a class argument that's a subclass of User and returns an instance of the corresponding class:: - def new_user[U](user_class: Type[U]) -> U: + def new_user[U](user_class: type[U]) -> U: user = user_class() # (Here we could write the user object to a database) return user @@ -2916,7 +2924,7 @@ Type.__doc__ = \ @runtime_checkable class SupportsInt(Protocol): - """An ABC with one abstract method __int__.""" + """A protocol with one abstract method __int__.""" __slots__ = () @@ -2927,7 +2935,7 @@ class SupportsInt(Protocol): @runtime_checkable class SupportsFloat(Protocol): - """An ABC with one abstract method __float__.""" + """A protocol with one abstract method __float__.""" __slots__ = () @@ -2938,7 +2946,7 @@ class SupportsFloat(Protocol): @runtime_checkable class SupportsComplex(Protocol): - """An ABC with one abstract method __complex__.""" + """A protocol with one abstract method __complex__.""" __slots__ = () @@ -2949,7 +2957,7 @@ class SupportsComplex(Protocol): @runtime_checkable class SupportsBytes(Protocol): - """An ABC with one abstract method __bytes__.""" + """A protocol with one abstract method __bytes__.""" __slots__ = () @@ -2960,7 +2968,7 @@ class SupportsBytes(Protocol): @runtime_checkable class SupportsIndex(Protocol): - """An ABC with one abstract method __index__.""" + """A protocol with one abstract method __index__.""" __slots__ = () @@ -2971,7 +2979,7 @@ class SupportsIndex(Protocol): @runtime_checkable class SupportsAbs[T](Protocol): - """An ABC with one abstract method __abs__ that is covariant in its return type.""" + """A protocol with one abstract method __abs__ that is covariant in its return type.""" __slots__ = () @@ -2982,7 +2990,7 @@ class SupportsAbs[T](Protocol): @runtime_checkable class SupportsRound[T](Protocol): - """An ABC with one abstract method __round__ that is covariant in its return type.""" + """A protocol with one abstract method __round__ that is covariant in its return type.""" __slots__ = () @@ -3061,7 +3069,7 @@ class NamedTupleMeta(type): def NamedTuple(typename, fields=_sentinel, /, **kwargs): - """Typed version of namedtuple. + """Typed version of collections.namedtuple. Usage:: @@ -3073,8 +3081,8 @@ def NamedTuple(typename, fields=_sentinel, /, **kwargs): Employee = collections.namedtuple('Employee', ['name', 'id']) - The resulting class has an extra __annotations__ attribute, giving a - dict that maps field names to types. (The field names are also in + The types for each field name can be retrieved by calling + inspect.get_annotations(Employee). (The field names are also in the _fields attribute, which is part of the namedtuple API.) An alternative equivalent functional syntax is also accepted:: @@ -3159,7 +3167,7 @@ class _TypedDictMeta(type): This method is called when TypedDict is subclassed, or when TypedDict is instantiated. This way - TypedDict supports all three syntax forms described in its docstring. + TypedDict classes can be created through both class-based and functional syntax. Subclasses and instances of TypedDict return actual dictionaries. """ for base in bases: @@ -3272,14 +3280,22 @@ def TypedDict(typename, fields=_sentinel, /, *, total=True): >>> Point2D(x=1, y=2, label='first') == dict(x=1, y=2, label='first') True - The type info can be accessed via the Point2D.__annotations__ dict, and - the Point2D.__required_keys__ and Point2D.__optional_keys__ frozensets. + The type info can be accessed by calling inspect.get_annotations(Point2D), and + via the Point2D.__required_keys__ and Point2D.__optional_keys__ frozensets. TypedDict supports an additional equivalent form:: Point2D = TypedDict('Point2D', {'x': int, 'y': int, 'label': str}) By default, all keys must be present in a TypedDict. It is possible - to override this by specifying totality:: + to override this by using the NotRequired and Required special forms:: + + class Point2D(TypedDict): + x: int # the "x" key must always be present (Required is the default) + y: NotRequired[int] # the "y" key can be omitted + + This means that a Point2D TypedDict can have the "y" key omitted, but the "x" key must be present. + Items are required by default, so the Required special form is not necessary in this example. + In addition, the total argument to the TypedDict function can be used to make all items not required:: class Point2D(TypedDict, total=False): x: int @@ -3288,16 +3304,8 @@ def TypedDict(typename, fields=_sentinel, /, *, total=True): This means that a Point2D TypedDict can have any of the keys omitted. A type checker is only expected to support a literal False or True as the value of the total argument. True is the default, and makes all items defined in the - class body be required. - - The Required and NotRequired special forms can also be used to mark - individual keys as being required or not required:: - - class Point2D(TypedDict): - x: int # the "x" key must always be present (Required is the default) - y: NotRequired[int] # the "y" key can be omitted - - See PEP 655 for more details on Required and NotRequired. + class body be required. The Required special form can be used to mark individual + keys as required in a total=False TypedDict. The ReadOnly special form can be used to mark individual keys as immutable for type checkers:: @@ -3306,6 +3314,7 @@ def TypedDict(typename, fields=_sentinel, /, *, total=True): id: ReadOnly[int] # the "id" key must not be modified username: str # the "username" key can be changed + See PEPs 589, 655, and 705 for more information. """ if fields is _sentinel or fields is None: import warnings @@ -3352,7 +3361,7 @@ def Required(self, parameters): year: int m = Movie( - title='The Matrix', # typechecker error if key is omitted + title='The Matrix', # type checker error if key is omitted year=1999, ) @@ -3374,7 +3383,7 @@ def NotRequired(self, parameters): year: NotRequired[int] m = Movie( - title='The Matrix', # typechecker error if key is omitted + title='The Matrix', # type checker error if key is omitted year=1999, ) """ @@ -3394,7 +3403,7 @@ def ReadOnly(self, parameters): def mutate_movie(m: Movie) -> None: m["year"] = 1992 # allowed - m["title"] = "The Matrix" # typechecker error + m["title"] = "The Matrix" # type checker error There is no runtime checking for this property. """ @@ -3481,8 +3490,8 @@ class IO(Generic[AnyStr]): classes (text vs. binary, read vs. write vs. read/write, append-only, unbuffered). The TextIO and BinaryIO subclasses below capture the distinctions between text vs. binary, which is - pervasive in the interface; however we currently do not offer a - way to track the other distinctions in the type system. + pervasive in the interface. For more precise types, define a custom + Protocol. """ __slots__ = () @@ -3572,7 +3581,7 @@ class IO(Generic[AnyStr]): class BinaryIO(IO[bytes]): - """Typed version of the return of open() in binary mode.""" + """Typed approximation of the return of open() in binary mode.""" __slots__ = () @@ -3586,7 +3595,7 @@ class BinaryIO(IO[bytes]): class TextIO(IO[str]): - """Typed version of the return of open() in text mode.""" + """Typed approximation of the return of open() in text mode.""" __slots__ = () @@ -3653,7 +3662,7 @@ def dataclass_transform( field_specifiers: tuple[type[Any] | Callable[..., Any], ...] = (), **kwargs: Any, ) -> _IdentityCallable: - """Decorator to mark an object as providing dataclass-like behaviour. + """Decorator to mark an object as providing dataclass-like behavior. The decorator can be applied to a function, class, or metaclass. diff --git a/contrib/tools/python3/Lib/unittest/mock.py b/contrib/tools/python3/Lib/unittest/mock.py index b6dd1c27fee..bf32ff6dd3c 100644 --- a/contrib/tools/python3/Lib/unittest/mock.py +++ b/contrib/tools/python3/Lib/unittest/mock.py @@ -3102,6 +3102,10 @@ class ThreadingMixin(Base): return ret_value + def _increment_mock_call(self, /, *args, **kwargs): + with self._mock_calls_events_lock: + super()._increment_mock_call(*args, **kwargs) + def wait_until_called(self, *, timeout=_timeout_unset): """Wait until the mock object is called. diff --git a/contrib/tools/python3/Lib/urllib/robotparser.py b/contrib/tools/python3/Lib/urllib/robotparser.py index 63689816f30..d055fd4e41b 100644 --- a/contrib/tools/python3/Lib/urllib/robotparser.py +++ b/contrib/tools/python3/Lib/urllib/robotparser.py @@ -7,7 +7,7 @@ 2) PSF license for Python 2.2 The robots.txt Exclusion Protocol is implemented as specified in - http://www.robotstxt.org/norobots-rfc.txt + RFC 9309 """ import collections @@ -21,19 +21,6 @@ __all__ = ["RobotFileParser"] RequestRate = collections.namedtuple("RequestRate", "requests seconds") -def normalize(path): - unquoted = urllib.parse.unquote(path, errors='surrogateescape') - return urllib.parse.quote(unquoted, errors='surrogateescape') - -def normalize_path(path): - path, sep, query = path.partition('?') - path = normalize(path) - if sep: - query = re.sub(r'[^=&]+', lambda m: normalize(m[0]), query) - path += '?' + query - return path - - class RobotFileParser: """ This class provides a set of methods to read, parse and answer questions about a single robots.txt file. @@ -42,6 +29,7 @@ class RobotFileParser: def __init__(self, url=''): self.entries = [] + self.groups = {} self.sitemaps = [] self.default_entry = None self.disallow_all = False @@ -86,13 +74,13 @@ class RobotFileParser: self.parse(raw.decode("utf-8", "surrogateescape").splitlines()) def _add_entry(self, entry): - if "*" in entry.useragents: - # the default entry is considered last - if self.default_entry is None: - # the first default entry wins - self.default_entry = entry - else: - self.entries.append(entry) + self.entries.append(entry) + for agent in entry.useragents: + agent = agent.lower() + if agent not in self.groups: + self.groups[agent] = entry + else: + self.groups[agent] = merge_entries(self.groups[agent], entry) def parse(self, lines): """Parse the input lines from a robots.txt file. @@ -100,6 +88,7 @@ class RobotFileParser: We allow that a user-agent: line is not preceded by one or more blank lines. """ + entries = [] # states: # 0: start state # 1: saw user-agent line @@ -109,14 +98,6 @@ class RobotFileParser: self.modified() for line in lines: - if not line: - if state == 1: - entry = Entry() - state = 0 - elif state == 2: - self._add_entry(entry) - entry = Entry() - state = 0 # remove optional comment and strip line i = line.find('#') if i >= 0: @@ -132,16 +113,23 @@ class RobotFileParser: if state == 2: self._add_entry(entry) entry = Entry() - entry.useragents.append(line[1]) + product_token = line[1] + entry.useragents.append(product_token) state = 1 elif line[0] == "disallow": if state != 0: - entry.rulelines.append(RuleLine(line[1], False)) state = 2 + try: + entry.rulelines.append(RuleLine(line[1], False)) + except ValueError: + pass elif line[0] == "allow": if state != 0: - entry.rulelines.append(RuleLine(line[1], True)) state = 2 + try: + entry.rulelines.append(RuleLine(line[1], True)) + except ValueError: + pass elif line[0] == "crawl-delay": if state != 0: # before trying to convert to int we need to make @@ -164,9 +152,18 @@ class RobotFileParser: # so it doesn't matter where you place it in your file." # Therefore we do not change the state of the parser. self.sitemaps.append(line[1]) - if state == 2: + if state != 0: self._add_entry(entry) + def _find_entry(self, useragent): + entry = self.groups.get(useragent.lower()) + if entry is not None: + return entry + for entry in self.groups.values(): + if entry.applies_to(useragent): + return entry + return self.groups.get('*') + def can_fetch(self, useragent, url): """using the parsed robots.txt decide if useragent can fetch url""" if self.disallow_all: @@ -183,37 +180,32 @@ class RobotFileParser: # the first match counts parsed_url = urllib.parse.urlsplit(url) url = urllib.parse.urlunsplit(('', '', *parsed_url[2:])) - url = normalize_path(url) + url = normalize_uri(url) if not url: url = "/" - for entry in self.entries: - if entry.applies_to(useragent): - return entry.allowance(url) - # try the default entry last - if self.default_entry: - return self.default_entry.allowance(url) - # agent not found ==> access granted - return True + if url == '/robots.txt': + # The /robots.txt URI is implicitly allowed. + return True + entry = self._find_entry(useragent) + if entry is None: + return True + return entry.allowance(url) def crawl_delay(self, useragent): if not self.mtime(): return None - for entry in self.entries: - if entry.applies_to(useragent): - return entry.delay - if self.default_entry: - return self.default_entry.delay - return None + entry = self._find_entry(useragent) + if entry is None: + return None + return entry.delay def request_rate(self, useragent): if not self.mtime(): return None - for entry in self.entries: - if entry.applies_to(useragent): - return entry.req_rate - if self.default_entry: - return self.default_entry.req_rate - return None + entry = self._find_entry(useragent) + if entry is None: + return None + return entry.req_rate def site_maps(self): if not self.sitemaps: @@ -224,7 +216,7 @@ class RobotFileParser: entries = self.entries if self.default_entry is not None: entries = entries + [self.default_entry] - return '\n\n'.join(map(str, entries)) + return '\n\n'.join(filter(None, map(str, entries))) class RuleLine: """A rule line is a single "Allow:" (allowance==True) or "Disallow:" @@ -233,14 +225,42 @@ class RuleLine: if path == '' and not allowance: # an empty value means allow all allowance = True - self.path = normalize_path(path) + path = re.sub(r'[*]{2,}', '*', path) + path = re.sub(r'[$][$*]+', '$', path) + path = normalize_pattern(path) + self.fullmatch = path.endswith('$') + path = path.rstrip('$') + if '$' in path: + raise ValueError('$ not at the end of path') + self.matcher = None + if '*' in path: + pattern = re.compile(translate_pattern(path), re.DOTALL) + if self.fullmatch: + self.matcher = pattern.fullmatch + else: + self.matcher = pattern.match + self.path = path self.allowance = allowance def applies_to(self, filename): - return self.path == "*" or filename.startswith(self.path) + # If the filename matches the rule, return the matching length plus 1. + # If it does not match, return 0. + if self.matcher is not None: + m = self.matcher(filename) + if m: + return m.end() + 1 + else: + if self.fullmatch: + if filename == self.path: + return len(self.path) + 1 + else: + if filename.startswith(self.path): + return len(self.path) + 1 + return 0 def __str__(self): - return ("Allow" if self.allowance else "Disallow") + ": " + self.path + return (("Allow" if self.allowance else "Disallow") + ": " + self.path + + ('$' if self.fullmatch else '')) class Entry: @@ -252,6 +272,8 @@ class Entry: self.req_rate = None def __str__(self): + if not self.useragents: + return '' ret = [] for agent in self.useragents: ret.append(f"User-agent: {agent}") @@ -260,27 +282,74 @@ class Entry: if self.req_rate is not None: rate = self.req_rate ret.append(f"Request-rate: {rate.requests}/{rate.seconds}") - ret.extend(map(str, self.rulelines)) + if self.rulelines: + ret.extend(map(str, self.rulelines)) + else: + ret.append("Allow:") return '\n'.join(ret) def applies_to(self, useragent): """check if this entry applies to the specified agent""" + if useragent is None: + return '*' in self.useragents # split the name token and make it lower case useragent = useragent.split("/")[0].lower() for agent in self.useragents: - if agent == '*': - # we have the catch-all agent - return True - agent = agent.lower() - if agent in useragent: - return True + if agent != '*': + agent = agent.lower() + if agent in useragent: + return True return False def allowance(self, filename): """Preconditions: - our agent applies to this entry - - filename is URL encoded""" + - filename is URL encoded + """ + best_match = -1 + allowance = True for line in self.rulelines: - if line.applies_to(filename): - return line.allowance - return True + m = line.applies_to(filename) + if m: + if m > best_match: + best_match = m + allowance = line.allowance + elif m == best_match and not allowance: + allowance = line.allowance + return allowance + + +def normalize(path): + unquoted = urllib.parse.unquote(path, errors='surrogateescape') + return urllib.parse.quote(unquoted, errors='surrogateescape') + +def normalize_uri(path): + path, sep, query = path.partition('?') + path = normalize(path) + if sep: + query = re.sub(r'[^=&]+', lambda m: normalize(m[0]), query) + path += '?' + query + return path + +def normalize_pattern(path): + path, sep, query = path.partition('?') + path = re.sub(r'[^*$]+', lambda m: normalize(m[0]), path) + if sep: + query = re.sub(r'[^=&*$]+', lambda m: normalize(m[0]), query) + path += '?' + query + return path + +def translate_pattern(path): + parts = list(map(re.escape, path.split('*'))) + for i in range(1, len(parts)-1): + parts[i] = f'(?>.*?{parts[i]})' + parts[-1] = f'.*{parts[-1]}' + return ''.join(parts) + +def merge_entries(e1, e2): + entry = Entry() + entry.useragents = list(filter(set(e2.useragents).__contains__, e1.useragents)) + entry.rulelines = e1.rulelines + e2.rulelines + entry.delay = e1.delay if e2.delay is None else e2.delay + entry.req_rate = e1.req_rate if e2.req_rate is None else e2.req_rate + return entry diff --git a/contrib/tools/python3/Lib/venv/scripts/common/activate b/contrib/tools/python3/Lib/venv/scripts/common/activate index 70673a265d4..241a8650bda 100644 --- a/contrib/tools/python3/Lib/venv/scripts/common/activate +++ b/contrib/tools/python3/Lib/venv/scripts/common/activate @@ -17,7 +17,7 @@ deactivate () { # Call hash to forget past locations. Without forgetting # past locations the $PATH changes we made may not be respected. # See "man bash" for more details. hash is usually a builtin of your shell - hash -r 2> /dev/null + hash -r 2> /dev/null || true if [ -n "${_OLD_VIRTUAL_PS1:-}" ] ; then PS1="${_OLD_VIRTUAL_PS1:-}" @@ -73,4 +73,4 @@ fi # Call hash to forget past commands. Without forgetting # past commands the $PATH changes we made may not be respected -hash -r 2> /dev/null +hash -r 2> /dev/null || true diff --git a/contrib/tools/python3/Lib/webbrowser.py b/contrib/tools/python3/Lib/webbrowser.py index ee5824100c7..be033d707a9 100755 --- a/contrib/tools/python3/Lib/webbrowser.py +++ b/contrib/tools/python3/Lib/webbrowser.py @@ -275,7 +275,6 @@ class UnixBrowser(BaseBrowser): def open(self, url, new=0, autoraise=True): sys.audit("webbrowser.open", url) - self._check_url(url) if new == 0: action = self.remote_action elif new == 1: @@ -289,7 +288,9 @@ class UnixBrowser(BaseBrowser): raise Error("Bad 'new' parameter to open(); " f"expected 0, 1, or 2, got {new}") - args = [arg.replace("%s", url).replace("%action", action) + self._check_url(url.replace("%action", action)) + + args = [arg.replace("%action", action).replace("%s", url) for arg in self.remote_args] args = [arg for arg in args if arg] success = self._invoke(args, True, autoraise, url) diff --git a/contrib/tools/python3/Lib/xml/etree/ElementTree.py b/contrib/tools/python3/Lib/xml/etree/ElementTree.py index 9bb09ab5407..ef162a967d8 100644 --- a/contrib/tools/python3/Lib/xml/etree/ElementTree.py +++ b/contrib/tools/python3/Lib/xml/etree/ElementTree.py @@ -8,8 +8,8 @@ 2. Element represents a single node in this tree. Interactions with the whole document (reading and writing to/from files) are - usually done on the ElementTree level. Interactions with a single XML element - and its sub-elements are done on the Element level. + usually done on the ElementTree level. Interactions with a single XML + element and its sub-elements are done on the Element level. Element is a flexible container object designed to store hierarchical data structures in memory. It can be described as a cross between a list and a @@ -273,7 +273,8 @@ class Element: """Find first matching element by tag name or path. *path* is a string having either an element tag or an XPath, - *namespaces* is an optional mapping from namespace prefix to full name. + *namespaces* is an optional mapping from namespace prefix to full + name. Return the first matching element, or None if no element was found. @@ -285,7 +286,8 @@ class Element: *path* is a string having either an element tag or an XPath, *default* is the value to return if the element was not found, - *namespaces* is an optional mapping from namespace prefix to full name. + *namespaces* is an optional mapping from namespace prefix to full + name. Return text content of first matching element, or default value if none was found. Note that if an element is found having no text @@ -298,7 +300,8 @@ class Element: """Find all matching subelements by tag name or path. *path* is a string having either an element tag or an XPath, - *namespaces* is an optional mapping from namespace prefix to full name. + *namespaces* is an optional mapping from namespace prefix to full + name. Returns list containing all matching elements in document order. @@ -309,7 +312,8 @@ class Element: """Find all matching subelements by tag name or path. *path* is a string having either an element tag or an XPath, - *namespaces* is an optional mapping from namespace prefix to full name. + *namespaces* is an optional mapping from namespace prefix to full + name. Return an iterable yielding all matching elements in document order. @@ -549,8 +553,8 @@ class ElementTree: def parse(self, source, parser=None): """Load external XML document into element tree. - *source* is a file name or file object, *parser* is an optional parser - instance that defaults to XMLParser. + *source* is a file name or file object, *parser* is an optional + parser instance that defaults to XMLParser. ParseError is raised if the parser fails to parse the document. @@ -583,7 +587,8 @@ class ElementTree: def iter(self, tag=None): """Create and return tree iterator for the root element. - The iterator loops over all elements in this tree, in document order. + The iterator loops over all elements in this tree, in document + order. *tag* is a string with the tag name to iterate over (default is to return all elements). @@ -598,7 +603,8 @@ class ElementTree: Same as getroot().find(path), which is Element.find() *path* is a string having either an element tag or an XPath, - *namespaces* is an optional mapping from namespace prefix to full name. + *namespaces* is an optional mapping from namespace prefix to full + name. Return the first matching element, or None if no element was found. @@ -620,7 +626,8 @@ class ElementTree: Same as getroot().findtext(path), which is Element.findtext() *path* is a string having either an element tag or an XPath, - *namespaces* is an optional mapping from namespace prefix to full name. + *namespaces* is an optional mapping from namespace prefix to full + name. Return the first matching element, or None if no element was found. @@ -642,7 +649,8 @@ class ElementTree: Same as getroot().findall(path), which is Element.findall(). *path* is a string having either an element tag or an XPath, - *namespaces* is an optional mapping from namespace prefix to full name. + *namespaces* is an optional mapping from namespace prefix to full + name. Return list containing all matching elements in document order. @@ -689,24 +697,26 @@ class ElementTree: """Write element tree to a file as XML. Arguments: - *file_or_filename* -- file name or a file object opened for writing + *file_or_filename* -- file name or a file object opened for + writing *encoding* -- the output encoding (default: US-ASCII) - *xml_declaration* -- bool indicating if an XML declaration should be - added to the output. If None, an XML declaration - is added if encoding IS NOT either of: - US-ASCII, UTF-8, or Unicode + *xml_declaration* -- bool indicating if an XML declaration should + be added to the output. If None, an XML + declaration is added if encoding IS NOT + either of: US-ASCII, UTF-8, or Unicode - *default_namespace* -- sets the default XML namespace (for "xmlns") + *default_namespace* -- sets the default XML namespace (for + "xmlns") *method* -- either "xml" (default), "html, "text", or "c14n" *short_empty_elements* -- controls the formatting of elements - that contain no content. If True (default) - they are emitted as a single self-closed - tag, otherwise they are emitted as a pair - of start/end tags + that contain no content. If True + (default) they are emitted as a single + self-closed tag, otherwise they are + emitted as a pair of start/end tags """ if self._root is None: @@ -903,9 +913,12 @@ def _serialize_xml(write, elem, qnames, namespaces, if elem.tail: write(_escape_cdata(elem.tail)) +_CDATA_CONTENT_ELEMENTS = {"script", "style", "xmp", "iframe", "noembed", + "noframes", "plaintext"} + HTML_EMPTY = {"area", "base", "basefont", "br", "col", "embed", "frame", "hr", "img", "input", "isindex", "link", "meta", "param", "source", - "track", "wbr"} + "track", "wbr", "plaintext"} def _serialize_html(write, elem, qnames, namespaces, **kwargs): tag = elem.tag @@ -946,7 +959,7 @@ def _serialize_html(write, elem, qnames, namespaces, **kwargs): write(">") ltag = tag.lower() if text: - if ltag == "script" or ltag == "style": + if ltag in _CDATA_CONTENT_ELEMENTS: write(text) else: write(_escape_cdata(text)) @@ -1079,9 +1092,9 @@ def tostring(element, encoding=None, method=None, *, is returned. Otherwise a bytestring is returned. *element* is an Element instance, *encoding* is an optional output - encoding defaulting to US-ASCII, *method* is an optional output which can - be one of "xml" (default), "html", "text" or "c14n", *default_namespace* - sets the default XML namespace (for "xmlns"). + encoding defaulting to US-ASCII, *method* is an optional output which + can be one of "xml" (default), "html", "text" or "c14n", + *default_namespace* sets the default XML namespace (for "xmlns"). Returns an (optionally) encoded string containing the XML data. @@ -1221,7 +1234,8 @@ def iterparse(source, events=None, parser=None): "end" events are reported. *source* is a filename or file object containing XML data, *events* is - a list of events to report back, *parser* is an optional parser instance. + a list of events to report back, *parser* is an optional parser + instance. Returns an iterator providing (event, elem) pairs. @@ -1753,10 +1767,11 @@ class XMLParser: def canonicalize(xml_data=None, *, out=None, from_file=None, **options): """Convert XML to its C14N 2.0 serialised form. - If *out* is provided, it must be a file or file-like object that receives - the serialised canonical XML output (text, not bytes) through its ``.write()`` - method. To write to a file, open it in text mode with encoding "utf-8". - If *out* is not provided, this function returns the output as text string. + If *out* is provided, it must be a file or file-like object that + receives the serialised canonical XML output (text, not bytes) through + its ``.write()`` method. To write to a file, open it in text mode with + encoding "utf-8". If *out* is not provided, this function returns the + output as text string. Either *xml_data* (an XML string) or *from_file* (a file path or file-like object) must be provided as input. @@ -1790,19 +1805,22 @@ class C14NWriterTarget: Serialises parse events to XML C14N 2.0. The *write* function is used for writing out the resulting data stream - as text (not bytes). To write to a file, open it in text mode with encoding - "utf-8" and pass its ``.write`` method. + as text (not bytes). To write to a file, open it in text mode with + encoding "utf-8" and pass its ``.write`` method. Configuration options: - *with_comments*: set to true to include comments - - *strip_text*: set to true to strip whitespace before and after text content - - *rewrite_prefixes*: set to true to replace namespace prefixes by "n{number}" + - *strip_text*: set to true to strip whitespace before and after text + content + - *rewrite_prefixes*: set to true to replace namespace prefixes by + "n{number}" - *qname_aware_tags*: a set of qname aware tag names in which prefixes should be replaced in text content - - *qname_aware_attrs*: a set of qname aware attribute names in which prefixes - should be replaced in text content - - *exclude_attrs*: a set of attribute names that should not be serialised + - *qname_aware_attrs*: a set of qname aware attribute names in which + prefixes should be replaced in text content + - *exclude_attrs*: a set of attribute names that should not be + serialised - *exclude_tags*: a set of tag names that should not be serialised """ def __init__(self, write, *, diff --git a/contrib/tools/python3/Lib/xmlrpc/client.py b/contrib/tools/python3/Lib/xmlrpc/client.py index f441376d09c..84e4e4d11a7 100644 --- a/contrib/tools/python3/Lib/xmlrpc/client.py +++ b/contrib/tools/python3/Lib/xmlrpc/client.py @@ -965,7 +965,7 @@ def dumps(params, methodname=None, methodresponse=None, encoding=None, data = ( xmlheader, "<methodCall>\n" - "<methodName>", methodname, "</methodName>\n", + "<methodName>", escape(methodname), "</methodName>\n", data, "</methodCall>\n" ) diff --git a/contrib/tools/python3/Lib/ya.make b/contrib/tools/python3/Lib/ya.make index 65c28a37639..871099f3685 100644 --- a/contrib/tools/python3/Lib/ya.make +++ b/contrib/tools/python3/Lib/ya.make @@ -4,9 +4,9 @@ ENABLE(PYBUILD_NO_PY) PY3_LIBRARY() -VERSION(3.13.13) +VERSION(3.13.14) -ORIGINAL_SOURCE(https://github.com/python/cpython/archive/v3.13.13.tar.gz) +ORIGINAL_SOURCE(https://github.com/python/cpython/archive/v3.13.14.tar.gz) LICENSE(Python-2.0) diff --git a/contrib/tools/python3/Lib/zipfile/__init__.py b/contrib/tools/python3/Lib/zipfile/__init__.py index 3d889e9c4f1..37555d32d99 100644 --- a/contrib/tools/python3/Lib/zipfile/__init__.py +++ b/contrib/tools/python3/Lib/zipfile/__init__.py @@ -531,8 +531,12 @@ class ZipInfo: return header + filename + extra def _encodeFilenameFlags(self): + if self.flag_bits & _MASK_UTF_FILENAME: + encoding = 'ascii' + else: + encoding = 'cp437' try: - return self.filename.encode('ascii'), self.flag_bits + return self.filename.encode(encoding), self.flag_bits & ~_MASK_UTF_FILENAME except UnicodeEncodeError: return self.filename.encode('utf-8'), self.flag_bits | _MASK_UTF_FILENAME @@ -585,11 +589,12 @@ class ZipInfo: def from_file(cls, filename, arcname=None, *, strict_timestamps=True): """Construct an appropriate ZipInfo for a file on the filesystem. - filename should be the path to a file or directory on the filesystem. + filename should be the path to a file or directory on the + filesystem. - arcname is the name which it will have within the archive (by default, - this will be the same as filename, but without a drive letter and with - leading path separators removed). + arcname is the name which it will have within the archive (by + default, this will be the same as filename, but without a drive + letter and with leading path separators removed). """ if isinstance(filename, os.PathLike): filename = os.fspath(filename) @@ -1326,25 +1331,26 @@ class ZipFile: mode: The mode can be either read 'r', write 'w', exclusive create 'x', or append 'a'. compression: ZIP_STORED (no compression), ZIP_DEFLATED (requires zlib), - ZIP_BZIP2 (requires bz2) or ZIP_LZMA (requires lzma). - allowZip64: if True ZipFile will create files with ZIP64 extensions when - needed, otherwise it will raise an exception when this would - be necessary. - compresslevel: None (default for the given compression type) or an integer - specifying the level to pass to the compressor. - When using ZIP_STORED or ZIP_LZMA this keyword has no effect. - When using ZIP_DEFLATED integers 0 through 9 are accepted. - When using ZIP_BZIP2 integers 1 through 9 are accepted. + ZIP_BZIP2 (requires bz2) or ZIP_LZMA (requires lzma). + allowZip64: if True ZipFile will create files with ZIP64 extensions + when needed, otherwise it will raise an exception when this + would be necessary. + compresslevel: None (default for the given compression type) or + an integer specifying the level to pass to the compressor. + When using ZIP_STORED or ZIP_LZMA this keyword has no effect. + When using ZIP_DEFLATED integers 0 through 9 are accepted. + When using ZIP_BZIP2 integers 1 through 9 are accepted. """ fp = None # Set here since __del__ checks it _windows_illegal_name_trans_table = None + _ignore_invalid_names = False def __init__(self, file, mode="r", compression=ZIP_STORED, allowZip64=True, compresslevel=None, *, strict_timestamps=True, metadata_encoding=None): - """Open the ZIP file with mode read 'r', write 'w', exclusive create 'x', - or append 'a'.""" + """Open the ZIP file with mode read 'r', write 'w', exclusive create + 'x', or append 'a'.""" if mode not in ('r', 'w', 'x', 'a'): raise ValueError("ZipFile requires mode 'r', 'w', 'x', or 'a'") @@ -1626,10 +1632,10 @@ class ZipFile: pwd is the password to decrypt files (only used for reading). - When writing, if the file size is not known in advance but may exceed - 2 GiB, pass force_zip64 to use the ZIP64 format, which can handle large - files. If the size is known in advance, it is best to pass a ZipInfo - instance for name, with zinfo.file_size set. + When writing, if the file size is not known in advance but may + exceed 2 GiB, pass force_zip64 to use the ZIP64 format, which can + handle large files. If the size is known in advance, it is best to + pass a ZipInfo instance for name, with zinfo.file_size set. """ if mode not in {"r", "w"}: raise ValueError('open() requires mode "r" or "w"') @@ -1741,7 +1747,7 @@ class ZipFile: zinfo.compress_size = 0 zinfo.CRC = 0 - zinfo.flag_bits = 0x00 + zinfo.flag_bits = _MASK_UTF_FILENAME if zinfo.compress_type == ZIP_LZMA: # Compressed data includes an end-of-stream (EOS) marker zinfo.flag_bits |= _MASK_COMPRESS_OPTION_1 @@ -1824,21 +1830,31 @@ class ZipFile: # build the destination pathname, replacing # forward slashes to platform specific separators. - arcname = member.filename.replace('/', os.path.sep) - - if os.path.altsep: + arcname = member.filename + if os.path.sep != '/': + arcname = arcname.replace('/', os.path.sep) + if os.path.altsep and os.path.altsep != '/': arcname = arcname.replace(os.path.altsep, os.path.sep) # interpret absolute pathname as relative, remove drive letter or # UNC path, redundant separators, "." and ".." components. - arcname = os.path.splitdrive(arcname)[1] + drive, root, arcname = os.path.splitroot(arcname) + if self._ignore_invalid_names and (drive or root): + return None + if self._ignore_invalid_names and os.path.pardir in arcname.split(os.path.sep): + return None invalid_path_parts = ('', os.path.curdir, os.path.pardir) arcname = os.path.sep.join(x for x in arcname.split(os.path.sep) if x not in invalid_path_parts) if os.path.sep == '\\': # filter illegal characters on Windows - arcname = self._sanitize_windows_name(arcname, os.path.sep) + arcname2 = self._sanitize_windows_name(arcname, os.path.sep) + if self._ignore_invalid_names and arcname2 != arcname: + return None + arcname = arcname2 if not arcname and not member.is_dir(): + if self._ignore_invalid_names: + return None raise ValueError("Empty filename.") targetpath = os.path.join(targetpath, arcname) |