Merge pull request RustPython#5370 from youknowone/update-io

Update io, _pyio, test_io from CPython 3.12

Author: youknowone

Lib/_pyio.py

@@ -44,8 +44,9 @@ def text_encoding(encoding, stacklevel=2):
     """
     A helper function to choose the text encoding.
 
-    When encoding is not None, just return it.
-    Otherwise, return the default text encoding (i.e. "locale").
+    When encoding is not None, this function returns it.
+    Otherwise, this function returns the default text encoding
+    (i.e. "locale" or "utf-8" depends on UTF-8 mode).
 
     This function emits an EncodingWarning if *encoding* is None and
     sys.flags.warn_default_encoding is true.
@@ -55,7 +56,10 @@ def text_encoding(encoding, stacklevel=2):
     However, please consider using encoding="utf-8" for new APIs.
     """
     if encoding is None:
-        encoding = "locale"
+        if sys.flags.utf8_mode:
+            encoding = "utf-8"
+        else:
+            encoding = "locale"
         if sys.flags.warn_default_encoding:
             import warnings
             warnings.warn("'encoding' argument not specified.",
@@ -101,7 +105,6 @@ def open(file, mode="r", buffering=-1, encoding=None, errors=None,
     'b'       binary mode
     't'       text mode (default)
     '+'       open a disk file for updating (reading and writing)
-    'U'       universal newline mode (deprecated)
     ========= ===============================================================
 
     The default mode is 'rt' (open for reading text). For binary random
@@ -117,10 +120,6 @@ def open(file, mode="r", buffering=-1, encoding=None, errors=None,
     returned as strings, the bytes having been first decoded using a
     platform-dependent encoding or using the specified encoding if given.
 
-    'U' mode is deprecated and will raise an exception in future versions
-    of Python.  It has no effect in Python 3.  Use newline to control
-    universal newlines mode.
-
     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
@@ -206,7 +205,7 @@ def open(file, mode="r", buffering=-1, encoding=None, errors=None,
     if errors is not None and not isinstance(errors, str):
         raise TypeError("invalid errors: %r" % errors)
     modes = set(mode)
-    if modes - set("axrwb+tU") or len(mode) > len(modes):
+    if modes - set("axrwb+t") or len(mode) > len(modes):
         raise ValueError("invalid mode: %r" % mode)
     creating = "x" in modes
     reading = "r" in modes
@@ -215,13 +214,6 @@ def open(file, mode="r", buffering=-1, encoding=None, errors=None,
     updating = "+" in modes
     text = "t" in modes
     binary = "b" in modes
-    if "U" in modes:
-        if creating or writing or appending or updating:
-            raise ValueError("mode U cannot be combined with 'x', 'w', 'a', or '+'")
-        import warnings
-        warnings.warn("'U' mode is deprecated",
-                      DeprecationWarning, 2)
-        reading = True
     if text and binary:
         raise ValueError("can't have text and binary mode at once")
     if creating + reading + writing + appending > 1:
@@ -311,22 +303,6 @@ def _open_code_with_warning(path):
     open_code = _open_code_with_warning
 
 
-def __getattr__(name):
-    if name == "OpenWrapper":
-        # bpo-43680: Until Python 3.9, _pyio.open was not a static method and
-        # builtins.open was set to OpenWrapper to not become a bound method
-        # when set to a class variable. _io.open is a built-in function whereas
-        # _pyio.open is a Python function. In Python 3.10, _pyio.open() is now
-        # a static method, and builtins.open() is now io.open().
-        import warnings
-        warnings.warn('OpenWrapper is deprecated, use open instead',
-                      DeprecationWarning, stacklevel=2)
-        global OpenWrapper
-        OpenWrapper = open
-        return OpenWrapper
-    raise AttributeError(name)
-
-
 # In normal operation, both `UnsupportedOperation`s should be bound to the
 # same object.
 try:
@@ -338,8 +314,7 @@ class UnsupportedOperation(OSError, ValueError):
 
 class IOBase(metaclass=abc.ABCMeta):
 
-    """The abstract base class for all I/O classes, acting on streams of
-    bytes. There is no public constructor.
+    """The abstract base class for all I/O classes.
 
     This class provides dummy implementations for many methods that
     derived classes can override selectively; the default implementations
@@ -1154,6 +1129,7 @@ def peek(self, size=0):
         do at most one raw read to satisfy it.  We never return more
         than self.buffer_size.
         """
+        self._checkClosed("peek of closed file")
         with self._read_lock:
             return self._peek_unlocked(size)
 
@@ -1172,6 +1148,7 @@ def read1(self, size=-1):
         """Reads up to size bytes, with at most one read() system call."""
         # Returns up to size bytes.  If at least one byte is buffered, we
         # only return buffered bytes.  Otherwise, we do one raw read.
+        self._checkClosed("read of closed file")
         if size < 0:
             size = self.buffer_size
         if size == 0:
@@ -1189,6 +1166,8 @@ def read1(self, size=-1):
     def _readinto(self, buf, read1):
         """Read data into *buf* with at most one system call."""
 
+        self._checkClosed("readinto of closed file")
+
         # Need to create a memoryview object of type 'b', otherwise
         # we may not be able to assign bytes to it, and slicing it
         # would create a new object.
@@ -1233,11 +1212,13 @@ def _readinto(self, buf, read1):
         return written
 
     def tell(self):
-        return _BufferedIOMixin.tell(self) - len(self._read_buf) + self._read_pos
+        # GH-95782: Keep return value non-negative
+        return max(_BufferedIOMixin.tell(self) - len(self._read_buf) + self._read_pos, 0)
 
     def seek(self, pos, whence=0):
         if whence not in valid_seek_flags:
             raise ValueError("invalid whence value")
+        self._checkClosed("seek of closed file")
         with self._read_lock:
             if whence == 1:
                 pos -= len(self._read_buf) - self._read_pos
@@ -1845,7 +1826,7 @@ class TextIOBase(IOBase):
     """Base class for text I/O.
 
     This class provides a character and line based interface to stream
-    I/O. There is no public constructor.
+    I/O.
     """
 
     def read(self, size=-1):
@@ -1997,7 +1978,7 @@ class TextIOWrapper(TextIOBase):
     r"""Character and line based layer over a BufferedIOBase object, buffer.
 
     encoding gives the name of the encoding that the stream will be
-    decoded or encoded with. It defaults to locale.getpreferredencoding(False).
+    decoded or encoded with. It defaults to locale.getencoding().
 
     errors determines the strictness of encoding and decoding (see the
     codecs.register) and defaults to "strict".
@@ -2031,19 +2012,7 @@ def __init__(self, buffer, encoding=None, errors=None, newline=None,
         encoding = text_encoding(encoding)
 
         if encoding == "locale":
-            try:
-                encoding = os.device_encoding(buffer.fileno()) or "locale"
-            except (AttributeError, UnsupportedOperation):
-                pass
-
-        if encoding == "locale":
-            try:
-                import locale
-            except ImportError:
-                # Importing locale may fail if Python is being built
-                encoding = "utf-8"
-            else:
-                encoding = locale.getpreferredencoding(False)
+            encoding = self._get_locale_encoding()
 
         if not isinstance(encoding, str):
             raise ValueError("invalid encoding: %r" % encoding)
@@ -2176,6 +2145,8 @@ def reconfigure(self, *,
         else:
             if not isinstance(encoding, str):
                 raise TypeError("invalid encoding: %r" % encoding)
+            if encoding == "locale":
+                encoding = self._get_locale_encoding()
 
         if newline is Ellipsis:
             newline = self._readnl
@@ -2243,8 +2214,9 @@ def write(self, s):
         self.buffer.write(b)
         if self._line_buffering and (haslf or "\r" in s):
             self.flush()
-        self._set_decoded_chars('')
-        self._snapshot = None
+        if self._snapshot is not None:
+            self._set_decoded_chars('')
+            self._snapshot = None
         if self._decoder:
             self._decoder.reset()
         return length
@@ -2280,6 +2252,15 @@ def _get_decoded_chars(self, n=None):
         self._decoded_chars_used += len(chars)
         return chars
 
+    def _get_locale_encoding(self):
+        try:
+            import locale
+        except ImportError:
+            # Importing locale may fail if Python is being built
+            return "utf-8"
+        else:
+            return locale.getencoding()
+
     def _rewind_decoded_chars(self, n):
         """Rewind the _decoded_chars buffer."""
         if self._decoded_chars_used < n:
@@ -2549,8 +2530,9 @@ def read(self, size=None):
             # Read everything.
             result = (self._get_decoded_chars() +
                       decoder.decode(self.buffer.read(), final=True))
-            self._set_decoded_chars('')
-            self._snapshot = None
+            if self._snapshot is not None:
+                self._set_decoded_chars('')
+                self._snapshot = None
             return result
         else:
             # Keep reading chunks until we have size characters to return.

Lib/io.py

@@ -45,40 +45,22 @@
            "FileIO", "BytesIO", "StringIO", "BufferedIOBase",
            "BufferedReader", "BufferedWriter", "BufferedRWPair",
            "BufferedRandom", "TextIOBase", "TextIOWrapper",
-           "UnsupportedOperation", "SEEK_SET", "SEEK_CUR", "SEEK_END"]
+           "UnsupportedOperation", "SEEK_SET", "SEEK_CUR", "SEEK_END",
+           "DEFAULT_BUFFER_SIZE", "text_encoding",
+           "IncrementalNewlineDecoder"
+           ]
 
 
 import _io
 import abc
 
 from _io import (DEFAULT_BUFFER_SIZE, BlockingIOError, UnsupportedOperation,
-                 open, open_code, BytesIO, StringIO, BufferedReader,
+                 open, open_code, FileIO, BytesIO, StringIO, BufferedReader,
                  BufferedWriter, BufferedRWPair, BufferedRandom,
                  # XXX RUSTPYTHON TODO: IncrementalNewlineDecoder
-                 # IncrementalNewlineDecoder, text_encoding, TextIOWrapper)
+                 # IncrementalNewlineDecoder,
                  text_encoding, TextIOWrapper)
 
-try:
-    from _io import FileIO
-except ImportError:
-    pass
-
-def __getattr__(name):
-    if name == "OpenWrapper":
-        # bpo-43680: Until Python 3.9, _pyio.open was not a static method and
-        # builtins.open was set to OpenWrapper to not become a bound method
-        # when set to a class variable. _io.open is a built-in function whereas
-        # _pyio.open is a Python function. In Python 3.10, _pyio.open() is now
-        # a static method, and builtins.open() is now io.open().
-        import warnings
-        warnings.warn('OpenWrapper is deprecated, use open instead',
-                      DeprecationWarning, stacklevel=2)
-        global OpenWrapper
-        OpenWrapper = open
-        return OpenWrapper
-    raise AttributeError(name)
-
-
 # Pretend this exception was created here.
 UnsupportedOperation.__module__ = "io"
 
@@ -102,10 +84,7 @@ class BufferedIOBase(_io._BufferedIOBase, IOBase):
 class TextIOBase(_io._TextIOBase, IOBase):
     __doc__ = _io._TextIOBase.__doc__
 
-try:
-    RawIOBase.register(FileIO)
-except NameError:
-    pass
+RawIOBase.register(FileIO)
 
 for klass in (BytesIO, BufferedReader, BufferedWriter, BufferedRandom,
               BufferedRWPair):

Lib/test/support/__init__.py

@@ -427,7 +427,7 @@ def check_sanitizer(*, address=False, memory=False, ub=False):
     )
 
 
-def skip_if_sanitizer(reason=None, *, address=False, memory=False, ub=False):
+def skip_if_sanitizer(reason=None, *, address=False, memory=False, ub=False, thread=False):
     """Decorator raising SkipTest if running with a sanitizer active."""
     if not reason:
         reason = 'not working with sanitizers active'