[Python-checkins] r69841 - in python/branches/io-c/Lib: _pyio.py io.py test/test_io.py test/test_memoryio.py

Sat Feb 21 21:05:43 CET 2009

Author: benjamin.peterson
Date: Sat Feb 21 21:05:40 2009
New Revision: 69841
Log:
split the Python implementation of io into another module and rewrite the tests to test both implementations
Added:
 python/branches/io-c/Lib/_pyio.py (contents, props changed)
Modified:
 python/branches/io-c/Lib/io.py
 python/branches/io-c/Lib/test/test_io.py
 python/branches/io-c/Lib/test/test_memoryio.py
Added: python/branches/io-c/Lib/_pyio.py
==============================================================================

--- (empty file)
+++ python/branches/io-c/Lib/_pyio.py	Sat Feb 21 21:05:40 2009
@@ -0,0 +1,1773 @@
+"""
+Python implementation of the io module.
+"""
+
+import os
+import abc
+import codecs
+#import _fileio
+# Import _thread instead of threading to reduce startup cost
+try:
+ from _thread import allocate_lock as Lock
+except ImportError:
+ from _dummy_thread import allocate_lock as Lock
+
+from io import __all__
+
+# open() uses st_blksize whenever we can
+DEFAULT_BUFFER_SIZE = 8 * 1024 # bytes
+
+
+class BlockingIOError(IOError):
+
+ """Exception raised when I/O would block on a non-blocking I/O stream."""
+
+ def __init__(self, errno, strerror, characters_written=0):
+ IOError.__init__(self, errno, strerror)
+ self.characters_written = characters_written
+
+
+def open(file, mode="r", buffering=None, encoding=None, errors=None,
+ newline=None, closefd=True):
+
+ r"""Open file and return a stream. Raise IOError upon failure.
+
+ file is either a text or byte string giving the name (and the path
+ if the file isn't in the current working directory) of the file to
+ be opened or an integer file descriptor of the file to be
+ 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), 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
+ '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)
+ 'U' universal newline mode (for backwards compatibility; unneeded
+ for new code)
+ ========= ===============================================================
+
+ 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
+ 'r+b' opens the file without truncation.
+
+ Python distinguishes between files opened in binary and text modes,
+ 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
+ '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. By
+ default full buffering is on. Pass 0 to switch buffering off (only
+ allowed in binary mode), 1 to set line buffering, and an integer > 1
+ for full buffering.
+
+ encoding is the name of the encoding used to decode or encode the
+ file. This should only be used in text mode. The default encoding is
+ platform dependent, but any encoding supported by Python can be
+ passed. See the codecs module for the list of supported encodings.
+
+ errors is an optional string that specifies how encoding errors are to
+ be handled---this argument should not be used in binary mode. Pass
+ 'strict' to raise a ValueError exception if there is an encoding error
+ (the default of None has the same effect), or pass 'ignore' to ignore
+ errors. (Note that ignoring encoding errors can lead to data loss.)
+ See the documentation for codecs.register for a list of the permitted
+ encoding error strings.
+
+ newline controls how universal newlines works (it only 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
+ these are translated into '\n' before being returned to the
+ caller. If it is '', universal newline mode is enabled, but line
+ endings are returned to the caller untranslated. If it has any of
+ the other legal values, input lines are only terminated by the given
+ string, and the line ending is returned to the caller untranslated.
+
+ * On output, if newline is None, any '\n' characters written are
+ translated to the system default line separator, os.linesep. If
+ newline is '', no translation takes place. If newline is any of the
+ other legal values, any '\n' characters written are translated to
+ the given string.
+
+ 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.
+
+ open() returns a file object whose type depends on the mode, and
+ through which the standard file operations such as reading and writing
+ are performed. When open() is used to open a file in a text mode ('w',
+ 'r', 'wt', 'rt', etc.), it returns a TextIOWrapper. When used to open
+ a file in a binary mode, the returned class varies: in read binary
+ mode, it returns a BufferedReader; in write binary and append binary
+ modes, it returns a BufferedWriter, and in read/write mode, it returns
+ a BufferedRandom.
+
+ It is also possible to use a string or bytearray as a file for both
+ reading and writing. For strings StringIO can be used like a file
+ opened in a text mode, and for bytes a BytesIO can be used like a file
+ opened in a binary mode.
+ """
+ if not isinstance(file, (str, bytes, int)):
+ raise TypeError("invalid file: %r" % file)
+ if not isinstance(mode, str):
+ raise TypeError("invalid mode: %r" % mode)
+ if buffering is not None and not isinstance(buffering, int):
+ raise TypeError("invalid buffering: %r" % buffering)
+ if encoding is not None and not isinstance(encoding, str):
+ raise TypeError("invalid encoding: %r" % encoding)
+ if errors is not None and not isinstance(errors, str):
+ raise TypeError("invalid errors: %r" % errors)
+ modes = set(mode)
+ if modes - set("arwb+tU") or len(mode) > len(modes):
+ raise ValueError("invalid mode: %r" % mode)
+ reading = "r" in modes
+ writing = "w" in modes
+ appending = "a" in modes
+ updating = "+" in modes
+ text = "t" in modes
+ binary = "b" in modes
+ if "U" in modes:
+ if writing or appending:
+ raise ValueError("can't use U and writing mode at once")
+ reading = True
+ if text and binary:
+ raise ValueError("can't have text and binary mode at once")
+ if reading + writing + appending > 1:
+ raise ValueError("can't have read/write/append mode at once")
+ if not (reading or writing or appending):
+ raise ValueError("must have exactly one of read/write/append mode")
+ if binary and encoding is not None:
+ raise ValueError("binary mode doesn't take an encoding argument")
+ if binary and errors is not None:
+ raise ValueError("binary mode doesn't take an errors argument")
+ if binary and newline is not None:
+ raise ValueError("binary mode doesn't take a newline argument")
+ raw = FileIO(file,
+ (reading and "r" or "") +
+ (writing and "w" or "") +
+ (appending and "a" or "") +
+ (updating and "+" or ""),
+ closefd)
+ if buffering is None:
+ buffering = -1
+ line_buffering = False
+ if buffering == 1 or buffering < 0 and raw.isatty():
+ buffering = -1
+ line_buffering = True
+ if buffering < 0:
+ buffering = DEFAULT_BUFFER_SIZE
+ try:
+ bs = os.fstat(raw.fileno()).st_blksize
+ except (os.error, AttributeError):
+ pass
+ else:
+ if bs > 1:
+ buffering = bs
+ if buffering < 0:
+ raise ValueError("invalid buffering size")
+ if buffering == 0:
+ if binary:
+ return raw
+ raise ValueError("can't have unbuffered text I/O")
+ if updating:
+ buffer = BufferedRandom(raw, buffering)
+ elif writing or appending:
+ buffer = BufferedWriter(raw, buffering)
+ elif reading:
+ buffer = BufferedReader(raw, buffering)
+ else:
+ raise ValueError("unknown mode: %r" % mode)
+ if binary:
+ return buffer
+ text = TextIOWrapper(buffer, encoding, errors, newline, line_buffering)
+ text.mode = mode
+ return text
+
+
+class DocDescriptor:
+ """Helper for builtins.open.__doc__
+ """
+ def __get__(self, obj, typ):
+ return (
+ "open(file, mode='r', buffering=None, encoding=None, "
+ "errors=None, newline=None, closefd=True)\n\n" +
+ open.__doc__)
+
+class OpenWrapper:
+ """Wrapper for builtins.open
+
+ Trick so that open won't become a bound method when stored
+ as a class variable (as dbm.dumb does).
+
+ See initstdio() in Python/pythonrun.c.
+ """
+ __doc__ = DocDescriptor()
+
+ def __new__(cls, *args, **kwargs):
+ return open(*args, **kwargs)
+
+
+class UnsupportedOperation(ValueError, IOError):
+ pass
+
+
+class IOBase(metaclass=abc.ABCMeta):
+
+ """The abstract base class for all I/O classes, acting on streams of
+ bytes. There is no public constructor.
+
+ This class provides dummy implementations for many methods that
+ derived classes can override selectively; the default implementations
+ represent a file that cannot be read, written or seeked.
+
+ Even though IOBase does not declare read, readinto, or write because
+ their signatures will vary, implementations and clients should
+ consider those methods part of the interface. Also, implementations
+ may raise a IOError when operations they do not support are called.
+
+ The basic type used for binary data read from or written to a file is
+ bytes. bytearrays are accepted too, and in some cases (such as
+ readinto) needed. Text I/O classes work with str data.
+
+ Note that calling any method (even inquiries) on a closed stream is
+ undefined. Implementations may raise IOError in this case.
+
+ IOBase (and its subclasses) support the iterator protocol, meaning
+ that an IOBase object can be iterated over yielding the lines in a
+ stream.
+
+ IOBase also supports the :keyword:`with` statement. In this example,
+ fp is closed after the suite of the with statment is complete:
+
+ with open('spam.txt', 'r') as fp:
+ fp.write('Spam and eggs!')
+ """
+
+ ### Internal ###
+
+ def _unsupported(self, name: str) -> IOError:
+ """Internal: raise an exception for unsupported operations."""
+ raise UnsupportedOperation("%s.%s() not supported" %
+ (self.__class__.__name__, name))
+
+ ### Positioning ###
+
+ def seek(self, pos: int, whence: int = 0) -> int:
+ """Change stream position.
+
+ Change the stream position to byte offset offset. offset is
+ interpreted relative to the position indicated by whence. Values
+ for whence are:
+
+ * 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
+
+ Return the new absolute position.
+ """
+ self._unsupported("seek")
+
+ def tell(self) -> int:
+ """Return current stream position."""
+ return self.seek(0, 1)
+
+ def truncate(self, pos: int = None) -> int:
+ """Truncate file to size bytes.
+
+ Size defaults to the current IO position as reported by tell(). Return
+ the new size.
+ """
+ self._unsupported("truncate")
+
+ ### Flush and close ###
+
+ def flush(self) -> None:
+ """Flush write buffers, if applicable.
+
+ This is not implemented for read-only and non-blocking streams.
+ """
+ # XXX Should this return the number of bytes written???
+
+ __closed = False
+
+ def close(self) -> None:
+ """Flush and close the IO object.
+
+ This method has no effect if the file is already closed.
+ """
+ if not self.__closed:
+ try:
+ self.flush()
+ except IOError:
+ pass # If flush() fails, just give up
+ self.__closed = True
+
+ def __del__(self) -> None:
+ """Destructor. Calls close()."""
+ # The try/except block is in case this is called at program
+ # exit time, when it's possible that globals have already been
+ # deleted, and then the close() call might fail. Since
+ # there's nothing we can do about such failures and they annoy
+ # the end users, we suppress the traceback.
+ try:
+ self.close()
+ except:
+ pass
+
+ ### Inquiries ###
+
+ def seekable(self) -> bool:
+ """Return whether object supports random access.
+
+ If False, seek(), tell() and truncate() will raise IOError.
+ This method may need to do a test seek().
+ """
+ return False
+
+ def _checkSeekable(self, msg=None):
+ """Internal: raise an IOError if file is not seekable
+ """
+ if not self.seekable():
+ raise IOError("File or stream is not seekable."
+ if msg is None else msg)
+
+
+ def readable(self) -> bool:
+ """Return whether object was opened for reading.
+
+ If False, read() will raise IOError.
+ """
+ return False
+
+ def _checkReadable(self, msg=None):
+ """Internal: raise an IOError if file is not readable
+ """
+ if not self.readable():
+ raise IOError("File or stream is not readable."
+ if msg is None else msg)
+
+ def writable(self) -> bool:
+ """Return whether object was opened for writing.
+
+ If False, write() and truncate() will raise IOError.
+ """
+ return False
+
+ def _checkWritable(self, msg=None):
+ """Internal: raise an IOError if file is not writable
+ """
+ if not self.writable():
+ raise IOError("File or stream is not writable."
+ if msg is None else msg)
+
+ @property
+ def closed(self):
+ """closed: bool. True iff the file has been closed.
+
+ For backwards compatibility, this is a property, not a predicate.
+ """
+ return self.__closed
+
+ def _checkClosed(self, msg=None):
+ """Internal: raise an ValueError if file is closed
+ """
+ if self.closed:
+ raise ValueError("I/O operation on closed file."
+ if msg is None else msg)
+
+ ### Context manager ###
+
+ def __enter__(self) -> "IOBase": # That's a forward reference
+ """Context management protocol. Returns self."""
+ self._checkClosed()
+ return self
+
+ def __exit__(self, *args) -> None:
+ """Context management protocol. Calls close()"""
+ self.close()
+
+ ### Lower-level APIs ###
+
+ # XXX Should these be present even if unimplemented?
+
+ def fileno(self) -> int:
+ """Returns underlying file descriptor if one exists.
+
+ An IOError is raised if the IO object does not use a file descriptor.
+ """
+ self._unsupported("fileno")
+
+ def isatty(self) -> bool:
+ """Return whether this is an 'interactive' stream.
+
+ Return False if it can't be determined.
+ """
+ self._checkClosed()
+ return False
+
+ ### Readline[s] and writelines ###
+
+ def readline(self, limit: int = -1) -> bytes:
+ r"""Read and return a line from the stream.
+
+ If limit is specified, at most limit bytes will be read.
+
+ The line terminator is always b'\n' for binary files; for text
+ files, the newlines argument to open can be used to select the line
+ terminator(s) recognized.
+ """
+ # For backwards compatibility, a (slowish) readline().
+ if hasattr(self, "peek"):
+ def nreadahead():
+ readahead = self.peek(1)
+ if not readahead:
+ return 1
+ n = (readahead.find(b"\n") + 1) or len(readahead)
+ if limit >= 0:
+ n = min(n, limit)
+ return n
+ else:
+ def nreadahead():
+ return 1
+ if limit is None:
+ limit = -1
+ res = bytearray()
+ while limit < 0 or len(res) < limit:
+ b = self.read(nreadahead())
+ if not b:
+ break
+ res += b
+ if res.endswith(b"\n"):
+ break
+ return bytes(res)
+
+ def __iter__(self):
+ self._checkClosed()
+ return self
+
+ def __next__(self):
+ line = self.readline()
+ if not line:
+ raise StopIteration
+ return line
+
+ def readlines(self, hint=None):
+ """Return a list of lines from the stream.
+
+ hint can be specified to control the number of lines read: no more
+ lines will be read if the total size (in bytes/characters) of all
+ lines so far exceeds hint.
+ """
+ if hint is None or hint <= 0:
+ return list(self)
+ n = 0
+ lines = []
+ for line in self:
+ lines.append(line)
+ n += len(line)
+ if n >= hint:
+ break
+ return lines
+
+ def writelines(self, lines):
+ self._checkClosed()
+ for line in lines:
+ self.write(line)
+
+
+class RawIOBase(IOBase):
+
+ """Base class for raw binary I/O."""
+
+ # The read() method is implemented by calling readinto(); derived
+ # classes that want to support read() only need to implement
+ # readinto() as a primitive operation. In general, readinto() can be
+ # more efficient than read().
+
+ # (It would be tempting to also provide an implementation of
+ # readinto() in terms of read(), in case the latter is a more suitable
+ # primitive operation, but that would lead to nasty recursion in case
+ # a subclass doesn't implement either.)
+
+ def read(self, n: int = -1) -> bytes:
+ """Read and return up to n bytes.
+
+ Returns an empty bytes object on EOF, or None if the object is
+ set not to block and has no data to read.
+ """
+ if n is None:
+ n = -1
+ if n < 0:
+ return self.readall()
+ b = bytearray(n.__index__())
+ n = self.readinto(b)
+ del b[n:]
+ return bytes(b)
+
+ def readall(self):
+ """Read until EOF, using multiple read() call."""
+ res = bytearray()
+ while True:
+ data = self.read(DEFAULT_BUFFER_SIZE)
+ if not data:
+ break
+ res += data
+ return bytes(res)
+
+ def readinto(self, b: bytearray) -> int:
+ """Read up to len(b) bytes into b.
+
+ Returns number of bytes read (0 for EOF), or None if the object
+ is set not to block as has no data to read.
+ """
+ self._unsupported("readinto")
+
+ def write(self, b: bytes) -> int:
+ """Write the given buffer to the IO stream.
+
+ Returns the number of bytes written, which may be less than len(b).
+ """
+ self._unsupported("write")
+
+
+from _io import FileIO
+
+
+class BufferedIOBase(IOBase):
+
+ """Base class for buffered IO objects.
+
+ The main difference with RawIOBase is that the read() method
+ supports omitting the size argument, and does not have a default
+ implementation that defers to readinto().
+
+ In addition, read(), readinto() and write() may raise
+ BlockingIOError if the underlying raw stream is in non-blocking
+ mode and not ready; unlike their raw counterparts, they will never
+ return None.
+
+ A typical implementation should not inherit from a RawIOBase
+ implementation, but wrap one.
+ """
+
+ def read(self, n: int = None) -> bytes:
+ """Read and return up to n bytes.
+
+ If the argument is omitted, None, or negative, reads and
+ returns all data until EOF.
+
+ If the argument is positive, and the underlying raw stream is
+ not 'interactive', multiple raw reads may be issued to satisfy
+ the byte count (unless EOF is reached first). But for
+ interactive raw streams (XXX and for pipes?), at most one raw
+ read will be issued, and a short result does not imply that
+ EOF is imminent.
+
+ Returns an empty bytes array on EOF.
+
+ Raises BlockingIOError if the underlying raw stream has no
+ data at the moment.
+ """
+ self._unsupported("read")
+
+ def readinto(self, b: bytearray) -> int:
+ """Read up to len(b) bytes into b.
+
+ Like read(), this may issue multiple reads to the underlying raw
+ stream, unless the latter is 'interactive'.
+
+ Returns the number of bytes read (0 for EOF).
+
+ Raises BlockingIOError if the underlying raw stream has no
+ data at the moment.
+ """
+ # XXX This ought to work with anything that supports the buffer API
+ data = self.read(len(b))
+ n = len(data)
+ try:
+ b[:n] = data
+ except TypeError as err:
+ import array
+ if not isinstance(b, array.array):
+ raise err
+ b[:n] = array.array('b', data)
+ return n
+
+ def write(self, b: bytes) -> int:
+ """Write the given buffer to the IO stream.
+
+ Return the number of bytes written, which is never less than
+ len(b).
+
+ Raises BlockingIOError if the buffer is full and the
+ underlying raw stream cannot accept more data at the moment.
+ """
+ self._unsupported("write")
+
+
+class _BufferedIOMixin(BufferedIOBase):
+
+ """A mixin implementation of BufferedIOBase with an underlying raw stream.
+
+ This passes most requests on to the underlying raw stream. It
+ does *not* provide implementations of read(), readinto() or
+ write().
+ """
+
+ def __init__(self, raw):
+ self.raw = raw
+
+ ### Positioning ###
+
+ def seek(self, pos, whence=0):
+ return self.raw.seek(pos, whence)
+
+ def tell(self):
+ return self.raw.tell()
+
+ def truncate(self, pos=None):
+ # Flush the stream. We're mixing buffered I/O with lower-level I/O,
+ # and a flush may be necessary to synch both views of the current
+ # file state.
+ self.flush()
+
+ if pos is None:
+ pos = self.tell()
+ # XXX: Should seek() be used, instead of passing the position
+ # XXX directly to truncate?
+ return self.raw.truncate(pos)
+
+ ### Flush and close ###
+
+ def flush(self):
+ self.raw.flush()
+
+ def close(self):
+ if not self.closed:
+ try:
+ self.flush()
+ except IOError:
+ pass # If flush() fails, just give up
+ self.raw.close()
+
+ ### Inquiries ###
+
+ def seekable(self):
+ return self.raw.seekable()
+
+ def readable(self):
+ return self.raw.readable()
+
+ def writable(self):
+ return self.raw.writable()
+
+ @property
+ def closed(self):
+ return self.raw.closed
+
+ @property
+ def name(self):
+ return self.raw.name
+
+ @property
+ def mode(self):
+ return self.raw.mode
+
+ ### Lower-level APIs ###
+
+ def fileno(self):
+ return self.raw.fileno()
+
+ def isatty(self):
+ return self.raw.isatty()
+
+
+class BytesIO(BufferedIOBase):
+
+ """Buffered I/O implementation using an in-memory bytes buffer."""
+
+ def __init__(self, initial_bytes=None):
+ buf = bytearray()
+ if initial_bytes is not None:
+ buf += initial_bytes
+ self._buffer = buf
+ self._pos = 0
+
+ def getvalue(self):
+ """Return the bytes value (contents) of the buffer
+ """
+ if self.closed:
+ raise ValueError("getvalue on closed file")
+ return bytes(self._buffer)
+
+ def read(self, n=None):
+ if self.closed:
+ raise ValueError("read from closed file")
+ if n is None:
+ n = -1
+ if n < 0:
+ n = len(self._buffer)
+ if len(self._buffer) <= self._pos:
+ return b""
+ newpos = min(len(self._buffer), self._pos + n)
+ b = self._buffer[self._pos : newpos]
+ self._pos = newpos
+ return bytes(b)
+
+ def read1(self, n):
+ """This is the same as read.
+ """
+ return self.read(n)
+
+ def write(self, b):
+ if self.closed:
+ raise ValueError("write to closed file")
+ if isinstance(b, str):
+ raise TypeError("can't write str to binary stream")
+ n = len(b)
+ if n == 0:
+ return 0
+ pos = self._pos
+ if pos > len(self._buffer):
+ # Inserts null bytes between the current end of the file
+ # and the new write position.
+ padding = b'\x00' * (pos - len(self._buffer))
+ self._buffer += padding
+ self._buffer[pos:pos + n] = b
+ self._pos += n
+ return n
+
+ def seek(self, pos, whence=0):
+ if self.closed:
+ raise ValueError("seek on closed file")
+ try:
+ pos = pos.__index__()
+ except AttributeError as err:
+ raise TypeError("an integer is required") from err
+ if whence == 0:
+ if pos < 0:
+ raise ValueError("negative seek position %r" % (pos,))
+ self._pos = pos
+ elif whence == 1:
+ self._pos = max(0, self._pos + pos)
+ elif whence == 2:
+ self._pos = max(0, len(self._buffer) + pos)
+ else:
+ raise ValueError("invalid whence value")
+ return self._pos
+
+ def tell(self):
+ if self.closed:
+ raise ValueError("tell on closed file")
+ return self._pos
+
+ def truncate(self, pos=None):
+ if self.closed:
+ raise ValueError("truncate on closed file")
+ if pos is None:
+ pos = self._pos
+ elif pos < 0:
+ raise ValueError("negative truncate position %r" % (pos,))
+ del self._buffer[pos:]
+ return self.seek(pos)
+
+ def readable(self):
+ return True
+
+ def writable(self):
+ return True
+
+ def seekable(self):
+ return True
+
+
+class BufferedReader(_BufferedIOMixin):
+
+ """BufferedReader(raw[, buffer_size])
+
+ A buffer for a readable, sequential BaseRawIO object.
+
+ The constructor creates a BufferedReader for the given readable raw
+ stream and buffer_size. If buffer_size is omitted, DEFAULT_BUFFER_SIZE
+ is used.
+ """
+
+ def __init__(self, raw, buffer_size=DEFAULT_BUFFER_SIZE):
+ """Create a new buffered reader using the given readable raw IO object.
+ """
+ raw._checkReadable()
+ _BufferedIOMixin.__init__(self, raw)
+ self.buffer_size = buffer_size
+ self._reset_read_buf()
+ self._read_lock = Lock()
+
+ def _reset_read_buf(self):
+ self._read_buf = b""
+ self._read_pos = 0
+
+ def read(self, n=None):
+ """Read n bytes.
+
+ Returns exactly n bytes of data unless the underlying raw IO
+ stream reaches EOF or if the call would block in non-blocking
+ mode. If n is negative, read until EOF or until read() would
+ block.
+ """
+ with self._read_lock:
+ return self._read_unlocked(n)
+
+ def _read_unlocked(self, n=None):
+ nodata_val = b""
+ empty_values = (b"", None)
+ buf = self._read_buf
+ pos = self._read_pos
+
+ # Special case for when the number of bytes to read is unspecified.
+ if n is None or n == -1:
+ self._reset_read_buf()
+ chunks = [buf[pos:]] # Strip the consumed bytes.
+ current_size = 0
+ while True:
+ # Read until EOF or until read() would block.
+ chunk = self.raw.read()
+ if chunk in empty_values:
+ nodata_val = chunk
+ break
+ current_size += len(chunk)
+ chunks.append(chunk)
+ return b"".join(chunks) or nodata_val
+
+ # The number of bytes to read is specified, return at most n bytes.
+ avail = len(buf) - pos # Length of the available buffered data.
+ if n <= avail:
+ # Fast path: the data to read is fully buffered.
+ self._read_pos += n
+ return buf[pos:pos+n]
+ # Slow path: read from the stream until enough bytes are read,
+ # or until an EOF occurs or until read() would block.
+ chunks = [buf[pos:]]
+ wanted = max(self.buffer_size, n)
+ while avail < n:
+ chunk = self.raw.read(wanted)
+ if chunk in empty_values:
+ nodata_val = chunk
+ break
+ avail += len(chunk)
+ chunks.append(chunk)
+ # n is more then avail only when an EOF occurred or when
+ # read() would have blocked.
+ n = min(n, avail)
+ out = b"".join(chunks)
+ self._read_buf = out[n:] # Save the extra data in the buffer.
+ self._read_pos = 0
+ return out[:n] if out else nodata_val
+
+ def peek(self, n=0):
+ """Returns buffered bytes without advancing the position.
+
+ The argument indicates a desired minimal number of bytes; we
+ do at most one raw read to satisfy it. We never return more
+ than self.buffer_size.
+ """
+ with self._read_lock:
+ return self._peek_unlocked(n)
+
+ def _peek_unlocked(self, n=0):
+ want = min(n, self.buffer_size)
+ have = len(self._read_buf) - self._read_pos
+ if have < want:
+ to_read = self.buffer_size - have
+ current = self.raw.read(to_read)
+ if current:
+ self._read_buf = self._read_buf[self._read_pos:] + current
+ self._read_pos = 0
+ return self._read_buf[self._read_pos:]
+
+ def read1(self, n):
+ """Reads up to n bytes, with at most one read() system call."""
+ # Returns up to n bytes. If at least one byte is buffered, we
+ # only return buffered bytes. Otherwise, we do one raw read.
+ if n <= 0:
+ return b""
+ with self._read_lock:
+ self._peek_unlocked(1)
+ return self._read_unlocked(
+ min(n, len(self._read_buf) - self._read_pos))
+
+ def tell(self):
+ return self.raw.tell() - len(self._read_buf) + self._read_pos
+
+ def seek(self, pos, whence=0):
+ with self._read_lock:
+ if whence == 1:
+ pos -= len(self._read_buf) - self._read_pos
+ pos = self.raw.seek(pos, whence)
+ self._reset_read_buf()
+ return pos
+
+class BufferedWriter(_BufferedIOMixin):
+
+ """A buffer for a writeable sequential RawIO object.
+
+ The constructor creates a BufferedWriter for the given writeable raw
+ stream. If the buffer_size is not given, it defaults to
+ DEAFULT_BUFFER_SIZE. If max_buffer_size is omitted, it defaults to
+ twice the buffer size.
+ """
+
+ def __init__(self, raw,
+ buffer_size=DEFAULT_BUFFER_SIZE, max_buffer_size=None):
+ raw._checkWritable()
+ _BufferedIOMixin.__init__(self, raw)
+ self.buffer_size = buffer_size
+ self.max_buffer_size = (2*buffer_size
+ if max_buffer_size is None
+ else max_buffer_size)
+ self._write_buf = bytearray()
+ self._write_lock = Lock()
+
+ def write(self, b):
+ if self.closed:
+ raise ValueError("write to closed file")
+ if isinstance(b, str):
+ raise TypeError("can't write str to binary stream")
+ with self._write_lock:
+ # XXX we can implement some more tricks to try and avoid
+ # partial writes
+ if len(self._write_buf) > self.buffer_size:
+ # We're full, so let's pre-flush the buffer
+ try:
+ self._flush_unlocked()
+ except BlockingIOError as e:
+ # We can't accept anything else.
+ # XXX Why not just let the exception pass through?
+ raise BlockingIOError(e.errno, e.strerror, 0)
+ before = len(self._write_buf)
+ self._write_buf.extend(b)
+ written = len(self._write_buf) - before
+ if len(self._write_buf) > self.buffer_size:
+ try:
+ self._flush_unlocked()
+ except BlockingIOError as e:
+ if len(self._write_buf) > self.max_buffer_size:
+ # We've hit max_buffer_size. We have to accept a
+ # partial write and cut back our buffer.
+ overage = len(self._write_buf) - self.max_buffer_size
+ self._write_buf = self._write_buf[:self.max_buffer_size]
+ raise BlockingIOError(e.errno, e.strerror, overage)
+ return written
+
+ def truncate(self, pos=None):
+ with self._write_lock:
+ self._flush_unlocked()
+ if pos is None:
+ pos = self.raw.tell()
+ return self.raw.truncate(pos)
+
+ def flush(self):
+ with self._write_lock:
+ self._flush_unlocked()
+
+ def _flush_unlocked(self):
+ if self.closed:
+ raise ValueError("flush of closed file")
+ written = 0
+ try:
+ while self._write_buf:
+ n = self.raw.write(self._write_buf)
+ del self._write_buf[:n]
+ written += n
+ except BlockingIOError as e:
+ n = e.characters_written
+ del self._write_buf[:n]
+ written += n
+ raise BlockingIOError(e.errno, e.strerror, written)
+
+ def tell(self):
+ return self.raw.tell() + len(self._write_buf)
+
+ def seek(self, pos, whence=0):
+ with self._write_lock:
+ self._flush_unlocked()
+ return self.raw.seek(pos, whence)
+
+
+class BufferedRWPair(BufferedIOBase):
+
+ """A buffered reader and writer object together.
+
+ A buffered reader object and buffered writer object put together to
+ form a sequential IO object that can read and write. This is typically
+ used with a socket or two-way pipe.
+
+ reader and writer are RawIOBase objects that are readable and
+ writeable respectively. If the buffer_size is omitted it defaults to
+ DEFAULT_BUFFER_SIZE. The max_buffer_size (for the buffered writer)
+ defaults to twice the buffer size.
+ """
+
+ # XXX The usefulness of this (compared to having two separate IO
+ # objects) is questionable.
+
+ def __init__(self, reader, writer,
+ buffer_size=DEFAULT_BUFFER_SIZE, max_buffer_size=None):
+ """Constructor.
+
+ The arguments are two RawIO instances.
+ """
+ reader._checkReadable()
+ writer._checkWritable()
+ self.reader = BufferedReader(reader, buffer_size)
+ self.writer = BufferedWriter(writer, buffer_size, max_buffer_size)
+
+ def read(self, n=None):
+ if n is None:
+ n = -1
+ return self.reader.read(n)
+
+ def readinto(self, b):
+ return self.reader.readinto(b)
+
+ def write(self, b):
+ return self.writer.write(b)
+
+ def peek(self, n=0):
+ return self.reader.peek(n)
+
+ def read1(self, n):
+ return self.reader.read1(n)
+
+ def readable(self):
+ return self.reader.readable()
+
+ def writable(self):
+ return self.writer.writable()
+
+ def flush(self):
+ return self.writer.flush()
+
+ def close(self):
+ self.writer.close()
+ self.reader.close()
+
+ def isatty(self):
+ return self.reader.isatty() or self.writer.isatty()
+
+ @property
+ def closed(self):
+ return self.writer.closed()
+
+
+class BufferedRandom(BufferedWriter, BufferedReader):
+
+ """A buffered interface to random access streams.
+
+ The constructor creates a reader and writer for a seekable stream,
+ raw, given in the first argument. If the buffer_size is omitted it
+ defaults to DEFAULT_BUFFER_SIZE. The max_buffer_size (for the buffered
+ writer) defaults to twice the buffer size.
+ """
+
+ def __init__(self, raw,
+ buffer_size=DEFAULT_BUFFER_SIZE, max_buffer_size=None):
+ raw._checkSeekable()
+ BufferedReader.__init__(self, raw, buffer_size)
+ BufferedWriter.__init__(self, raw, buffer_size, max_buffer_size)
+
+ def seek(self, pos, whence=0):
+ self.flush()
+ # First do the raw seek, then empty the read buffer, so that
+ # if the raw seek fails, we don't lose buffered data forever.
+ pos = self.raw.seek(pos, whence)
+ with self._read_lock:
+ self._reset_read_buf()
+ return pos
+
+ def tell(self):
+ if self._write_buf:
+ return self.raw.tell() + len(self._write_buf)
+ else:
+ return BufferedReader.tell(self)
+
+ def truncate(self, pos=None):
+ if pos is None:
+ pos = self.tell()
+ # Use seek to flush the read buffer.
+ self.seek(pos)
+ return BufferedWriter.truncate(self)
+
+ def read(self, n=None):
+ if n is None:
+ n = -1
+ self.flush()
+ return BufferedReader.read(self, n)
+
+ def readinto(self, b):
+ self.flush()
+ return BufferedReader.readinto(self, b)
+
+ def peek(self, n=0):
+ self.flush()
+ return BufferedReader.peek(self, n)
+
+ def read1(self, n):
+ self.flush()
+ return BufferedReader.read1(self, n)
+
+ def write(self, b):
+ if self._read_buf:
+ # Undo readahead
+ with self._read_lock:
+ self.raw.seek(self._read_pos - len(self._read_buf), 1)
+ self._reset_read_buf()
+ return BufferedWriter.write(self, b)
+
+
+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 readinto method because Python's character strings
+ are immutable. There is no public constructor.
+ """
+
+ def read(self, n: int = -1) -> str:
+ """Read at most n characters from stream.
+
+ Read from underlying buffer until we have n characters or we hit EOF.
+ If n is negative or omitted, read until EOF.
+ """
+ self._unsupported("read")
+
+ def write(self, s: str) -> int:
+ """Write string s to stream."""
+ self._unsupported("write")
+
+ def truncate(self, pos: int = None) -> int:
+ """Truncate size to pos."""
+ self._unsupported("truncate")
+
+ def readline(self) -> str:
+ """Read until newline or EOF.
+
+ Returns an empty string if EOF is hit immediately.
+ """
+ self._unsupported("readline")
+
+ @property
+ def encoding(self):
+ """Subclasses should override."""
+ return None
+
+ @property
+ def newlines(self):
+ """Line endings translated so far.
+
+ Only line endings translated during reading are considered.
+
+ Subclasses should override.
+ """
+ return None
+
+
+class IncrementalNewlineDecoder(codecs.IncrementalDecoder):
+ r"""Codec used when reading a file in universal newlines mode. It wraps
+ another incremental decoder, translating \r\n and \r into \n. It also
+ records the types of newlines encountered. When used with
+ translate=False, it ensures that the newline sequence is returned in
+ one piece.
+ """
+ def __init__(self, decoder, translate, errors='strict'):
+ codecs.IncrementalDecoder.__init__(self, errors=errors)
+ self.translate = translate
+ self.decoder = decoder
+ self.seennl = 0
+ self.pendingcr = False
+
+ def decode(self, input, final=False):
+ # decode input (with the eventual \r from a previous pass)
+ output = self.decoder.decode(input, final=final)
+ if self.pendingcr and (output or final):
+ output = "\r" + output
+ self.pendingcr = False
+
+ # retain last \r even when not translating data:
+ # then readline() is sure to get \r\n in one pass
+ if output.endswith("\r") and not final:
+ output = output[:-1]
+ self.pendingcr = True
+
+ # Record which newlines are read
+ crlf = output.count('\r\n')
+ cr = output.count('\r') - crlf
+ lf = output.count('\n') - crlf
+ self.seennl |= (lf and self._LF) | (cr and self._CR) \
+ | (crlf and self._CRLF)
+
+ if self.translate:
+ if crlf:
+ output = output.replace("\r\n", "\n")
+ if cr:
+ output = output.replace("\r", "\n")
+
+ return output
+
+ def getstate(self):
+ buf, flag = self.decoder.getstate()
+ flag <<= 1
+ if self.pendingcr:
+ flag |= 1
+ return buf, flag
+
+ def setstate(self, state):
+ buf, flag = state
+ self.pendingcr = bool(flag & 1)
+ self.decoder.setstate((buf, flag >> 1))
+
+ def reset(self):
+ self.seennl = 0
+ self.pendingcr = False
+ self.decoder.reset()
+
+ _LF = 1
+ _CR = 2
+ _CRLF = 4
+
+ @property
+ def newlines(self):
+ return (None,
+ "\n",
+ "\r",
+ ("\r", "\n"),
+ "\r\n",
+ ("\n", "\r\n"),
+ ("\r", "\r\n"),
+ ("\r", "\n", "\r\n")
+ )[self.seennl]
+
+
+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.
+
+ errors determines the strictness of encoding and decoding (see the
+ codecs.register) and defaults to "strict".
+
+ newline can be None, '', '\n', '\r', or '\r\n'. It controls the
+ handling of line endings. If it is None, universal newlines is
+ enabled. With this enabled, on input, the lines endings '\n', '\r',
+ or '\r\n' are translated to '\n' before being returned to the
+ caller. Conversely, on output, '\n' is translated to the system
+ default line seperator, os.linesep. If newline is any other of its
+ legal values, that newline becomes the newline when the file is read
+ and it is returned untranslated. On output, '\n' is converted to the
+ newline.
+
+ If line_buffering is True, a call to flush is implied when a call to
+ write contains a newline character.
+ """
+
+ _CHUNK_SIZE = 128
+
+ def __init__(self, buffer, encoding=None, errors=None, newline=None,
+ line_buffering=False):
+ if newline not in (None, "", "\n", "\r", "\r\n"):
+ raise ValueError("illegal newline value: %r" % (newline,))
+ if encoding is None:
+ try:
+ encoding = os.device_encoding(buffer.fileno())
+ except (AttributeError, UnsupportedOperation):
+ pass
+ if encoding is None:
+ try:
+ import locale
+ except ImportError:
+ # Importing locale may fail if Python is being built
+ encoding = "ascii"
+ else:
+ encoding = locale.getpreferredencoding()
+
+ if not isinstance(encoding, str):
+ raise ValueError("invalid encoding: %r" % encoding)
+
+ if errors is None:
+ errors = "strict"
+ else:
+ if not isinstance(errors, str):
+ raise ValueError("invalid errors: %r" % errors)
+
+ self.buffer = buffer
+ self._line_buffering = line_buffering
+ self._encoding = encoding
+ self._errors = errors
+ self._readuniversal = not newline
+ self._readtranslate = newline is None
+ self._readnl = newline
+ self._writetranslate = newline != ''
+ self._writenl = newline or os.linesep
+ self._encoder = None
+ self._decoder = None
+ self._decoded_chars = '' # buffer for text returned from decoder
+ self._decoded_chars_used = 0 # offset into _decoded_chars for read()
+ self._snapshot = None # info for reconstructing decoder state
+ self._seekable = self._telling = self.buffer.seekable()
+
+ # self._snapshot is either None, or a tuple (dec_flags, next_input)
+ # where dec_flags is the second (integer) item of the decoder state
+ # and next_input is the chunk of input bytes that comes next after the
+ # snapshot point. We use this to reconstruct decoder states in tell().
+
+ # Naming convention:
+ # - "bytes_..." for integer variables that count input bytes
+ # - "chars_..." for integer variables that count decoded characters
+
+ @property
+ def encoding(self):
+ return self._encoding
+
+ @property
+ def errors(self):
+ return self._errors
+
+ @property
+ def line_buffering(self):
+ return self._line_buffering
+
+ def seekable(self):
+ return self._seekable
+
+ def readable(self):
+ return self.buffer.readable()
+
+ def writable(self):
+ return self.buffer.writable()
+
+ def flush(self):
+ self.buffer.flush()
+ self._telling = self._seekable
+
+ def close(self):
+ try:
+ self.flush()
+ except:
+ pass # If flush() fails, just give up
+ self.buffer.close()
+
+ @property
+ def closed(self):
+ return self.buffer.closed
+
+ @property
+ def name(self):
+ return self.buffer.name
+
+ def fileno(self):
+ return self.buffer.fileno()
+
+ def isatty(self):
+ return self.buffer.isatty()
+
+ def write(self, s: str):
+ if self.closed:
+ raise ValueError("write to closed file")
+ if not isinstance(s, str):
+ raise TypeError("can't write %s to text stream" %
+ s.__class__.__name__)
+ length = len(s)
+ haslf = (self._writetranslate or self._line_buffering) and "\n" in s
+ if haslf and self._writetranslate and self._writenl != "\n":
+ s = s.replace("\n", self._writenl)
+ encoder = self._encoder or self._get_encoder()
+ # XXX What if we were just reading?
+ b = encoder.encode(s)
+ self.buffer.write(b)
+ if self._line_buffering and (haslf or "\r" in s):
+ self.flush()
+ self._snapshot = None
+ if self._decoder:
+ self._decoder.reset()
+ return length
+
+ def _get_encoder(self):
+ make_encoder = codecs.getincrementalencoder(self._encoding)
+ self._encoder = make_encoder(self._errors)
+ return self._encoder
+
+ def _get_decoder(self):
+ make_decoder = codecs.getincrementaldecoder(self._encoding)
+ decoder = make_decoder(self._errors)
+ if self._readuniversal:
+ decoder = IncrementalNewlineDecoder(decoder, self._readtranslate)
+ self._decoder = decoder
+ return decoder
+
+ # The following three methods implement an ADT for _decoded_chars.
+ # Text returned from the decoder is buffered here until the client
+ # requests it by calling our read() or readline() method.
+ def _set_decoded_chars(self, chars):
+ """Set the _decoded_chars buffer."""
+ self._decoded_chars = chars
+ self._decoded_chars_used = 0
+
+ def _get_decoded_chars(self, n=None):
+ """Advance into the _decoded_chars buffer."""
+ offset = self._decoded_chars_used
+ if n is None:
+ chars = self._decoded_chars[offset:]
+ else:
+ chars = self._decoded_chars[offset:offset + n]
+ self._decoded_chars_used += len(chars)
+ return chars
+
+ def _rewind_decoded_chars(self, n):
+ """Rewind the _decoded_chars buffer."""
+ if self._decoded_chars_used < n:
+ raise AssertionError("rewind decoded_chars out of bounds")
+ self._decoded_chars_used -= n
+
+ def _read_chunk(self):
+ """
+ Read and decode the next chunk of data from the BufferedReader.
+ """
+
+ # The return value is True unless EOF was reached. The decoded
+ # string is placed in self._decoded_chars (replacing its previous
+ # value). The entire input chunk is sent to the decoder, though
+ # some of it may remain buffered in the decoder, yet to be
+ # converted.
+
+ if self._decoder is None:
+ raise ValueError("no decoder")
+
+ if self._telling:
+ # To prepare for tell(), we need to snapshot a point in the
+ # file where the decoder's input buffer is empty.
+
+ dec_buffer, dec_flags = self._decoder.getstate()
+ # Given this, we know there was a valid snapshot point
+ # len(dec_buffer) bytes ago with decoder state (b'', dec_flags).
+
+ # Read a chunk, decode it, and put the result in self._decoded_chars.
+ input_chunk = self.buffer.read1(self._CHUNK_SIZE)
+ eof = not input_chunk
+ self._set_decoded_chars(self._decoder.decode(input_chunk, eof))
+
+ if self._telling:
+ # At the snapshot point, len(dec_buffer) bytes before the read,
+ # the next input to be decoded is dec_buffer + input_chunk.
+ self._snapshot = (dec_flags, dec_buffer + input_chunk)
+
+ return not eof
+
+ def _pack_cookie(self, position, dec_flags=0,
+ bytes_to_feed=0, need_eof=0, chars_to_skip=0):
+ # The meaning of a tell() cookie is: seek to position, set the
+ # decoder flags to dec_flags, read bytes_to_feed bytes, feed them
+ # into the decoder with need_eof as the EOF flag, then skip
+ # chars_to_skip characters of the decoded result. For most simple
+ # decoders, tell() will often just give a byte offset in the file.
+ return (position | (dec_flags<<64) | (bytes_to_feed<<128) |
+ (chars_to_skip<<192) | bool(need_eof)<<256)
+
+ def _unpack_cookie(self, bigint):
+ rest, position = divmod(bigint, 1<<64)
+ rest, dec_flags = divmod(rest, 1<<64)
+ rest, bytes_to_feed = divmod(rest, 1<<64)
+ need_eof, chars_to_skip = divmod(rest, 1<<64)
+ return position, dec_flags, bytes_to_feed, need_eof, chars_to_skip
+
+ def tell(self):
+ if not self._seekable:
+ raise IOError("underlying stream is not seekable")
+ if not self._telling:
+ raise IOError("telling position disabled by next() call")
+ self.flush()
+ position = self.buffer.tell()
+ decoder = self._decoder
+ if decoder is None or self._snapshot is None:
+ if self._decoded_chars:
+ # This should never happen.
+ raise AssertionError("pending decoded text")
+ return position
+
+ # Skip backward to the snapshot point (see _read_chunk).
+ dec_flags, next_input = self._snapshot
+ position -= len(next_input)
+
+ # How many decoded characters have been used up since the snapshot?
+ chars_to_skip = self._decoded_chars_used
+ if chars_to_skip == 0:
+ # We haven't moved from the snapshot point.
+ return self._pack_cookie(position, dec_flags)
+
+ # Starting from the snapshot position, we will walk the decoder
+ # forward until it gives us enough decoded characters.
+ saved_state = decoder.getstate()
+ try:
+ # Note our initial start point.
+ decoder.setstate((b'', dec_flags))
+ start_pos = position
+ start_flags, bytes_fed, chars_decoded = dec_flags, 0, 0
+ need_eof = 0
+
+ # Feed the decoder one byte at a time. As we go, note the
+ # nearest "safe start point" before the current location
+ # (a point where the decoder has nothing buffered, so seek()
+ # can safely start from there and advance to this location).
+ next_byte = bytearray(1)
+ for next_byte[0] in next_input:
+ bytes_fed += 1
+ chars_decoded += len(decoder.decode(next_byte))
+ dec_buffer, dec_flags = decoder.getstate()
+ if not dec_buffer and chars_decoded <= chars_to_skip:
+ # Decoder buffer is empty, so this is a safe start point.
+ start_pos += bytes_fed
+ chars_to_skip -= chars_decoded
+ start_flags, bytes_fed, chars_decoded = dec_flags, 0, 0
+ if chars_decoded >= chars_to_skip:
+ break
+ else:
+ # We didn't get enough decoded data; signal EOF to get more.
+ chars_decoded += len(decoder.decode(b'', final=True))
+ need_eof = 1
+ if chars_decoded < chars_to_skip:
+ raise IOError("can't reconstruct logical file position")
+
+ # The returned cookie corresponds to the last safe start point.
+ return self._pack_cookie(
+ start_pos, start_flags, bytes_fed, need_eof, chars_to_skip)
+ finally:
+ decoder.setstate(saved_state)
+
+ def truncate(self, pos=None):
+ self.flush()
+ if pos is None:
+ pos = self.tell()
+ self.seek(pos)
+ return self.buffer.truncate()
+
+ def seek(self, cookie, whence=0):
+ if self.closed:
+ raise ValueError("tell on closed file")
+ if not self._seekable:
+ raise IOError("underlying stream is not seekable")
+ if whence == 1: # seek relative to current position
+ if cookie != 0:
+ raise IOError("can't do nonzero cur-relative seeks")
+ # Seeking to the current position should attempt to
+ # sync the underlying buffer with the current position.
+ whence = 0
+ cookie = self.tell()
+ if whence == 2: # seek relative to end of file
+ if cookie != 0:
+ raise IOError("can't do nonzero end-relative seeks")
+ self.flush()
+ position = self.buffer.seek(0, 2)
+ self._set_decoded_chars('')
+ self._snapshot = None
+ if self._decoder:
+ self._decoder.reset()
+ return position
+ if whence != 0:
+ raise ValueError("invalid whence (%r, should be 0, 1 or 2)" %
+ (whence,))
+ if cookie < 0:
+ raise ValueError("negative seek position %r" % (cookie,))
+ self.flush()
+
+ # The strategy of seek() is to go back to the safe start point
+ # and replay the effect of read(chars_to_skip) from there.
+ start_pos, dec_flags, bytes_to_feed, need_eof, chars_to_skip = \
+ self._unpack_cookie(cookie)
+
+ # Seek back to the safe start point.
+ self.buffer.seek(start_pos)
+ self._set_decoded_chars('')
+ self._snapshot = None
+
+ # Restore the decoder to its state from the safe start point.
+ if self._decoder or dec_flags or chars_to_skip:
+ self._decoder = self._decoder or self._get_decoder()
+ self._decoder.setstate((b'', dec_flags))
+ self._snapshot = (dec_flags, b'')
+
+ if chars_to_skip:
+ # Just like _read_chunk, feed the decoder and save a snapshot.
+ input_chunk = self.buffer.read(bytes_to_feed)
+ self._set_decoded_chars(
+ self._decoder.decode(input_chunk, need_eof))
+ self._snapshot = (dec_flags, input_chunk)
+
+ # Skip chars_to_skip of the decoded characters.
+ if len(self._decoded_chars) < chars_to_skip:
+ raise IOError("can't restore logical file position")
+ self._decoded_chars_used = chars_to_skip
+
+ return cookie
+
+ def read(self, n=None):
+ if n is None:
+ n = -1
+ decoder = self._decoder or self._get_decoder()
+ if n < 0:
+ # Read everything.
+ result = (self._get_decoded_chars() +
+ decoder.decode(self.buffer.read(), final=True))
+ self._set_decoded_chars('')
+ self._snapshot = None
+ return result
+ else:
+ # Keep reading chunks until we have n characters to return.
+ eof = False
+ result = self._get_decoded_chars(n)
+ while len(result) < n and not eof:
+ eof = not self._read_chunk()
+ result += self._get_decoded_chars(n - len(result))
+ return result
+
+ def __next__(self):
+ self._telling = False
+ line = self.readline()
+ if not line:
+ self._snapshot = None
+ self._telling = self._seekable
+ raise StopIteration
+ return line
+
+ def readline(self, limit=None):
+ if self.closed:
+ raise ValueError("read from closed file")
+ if limit is None:
+ limit = -1
+
+ # Grab all the decoded text (we will rewind any extra bits later).
+ line = self._get_decoded_chars()
+
+ start = 0
+ decoder = self._decoder or self._get_decoder()
+
+ pos = endpos = None
+ while True:
+ if self._readtranslate:
+ # Newlines are already translated, only search for \n
+ pos = line.find('\n', start)
+ if pos >= 0:
+ endpos = pos + 1
+ break
+ else:
+ start = len(line)
+
+ elif self._readuniversal:
+ # Universal newline search. Find any of \r, \r\n, \n
+ # The decoder ensures that \r\n are not split in two pieces
+
+ # In C we'd look for these in parallel of course.
+ nlpos = line.find("\n", start)
+ crpos = line.find("\r", start)
+ if crpos == -1:
+ if nlpos == -1:
+ # Nothing found
+ start = len(line)
+ else:
+ # Found \n
+ endpos = nlpos + 1
+ break
+ elif nlpos == -1:
+ # Found lone \r
+ endpos = crpos + 1
+ break
+ elif nlpos < crpos:
+ # Found \n
+ endpos = nlpos + 1
+ break
+ elif nlpos == crpos + 1:
+ # Found \r\n
+ endpos = crpos + 2
+ break
+ else:
+ # Found \r
+ endpos = crpos + 1
+ break
+ else:
+ # non-universal
+ pos = line.find(self._readnl)
+ if pos >= 0:
+ endpos = pos + len(self._readnl)
+ break
+
+ if limit >= 0 and len(line) >= limit:
+ endpos = limit # reached length limit
+ break
+
+ # No line ending seen yet - get more data
+ more_line = ''
+ while self._read_chunk():
+ if self._decoded_chars:
+ break
+ if self._decoded_chars:
+ line += self._get_decoded_chars()
+ else:
+ # end of file
+ self._set_decoded_chars('')
+ self._snapshot = None
+ return line
+
+ if limit >= 0 and endpos > limit:
+ endpos = limit # don't exceed limit
+
+ # Rewind _decoded_chars to just after the line ending we found.
+ self._rewind_decoded_chars(len(line) - endpos)
+ return line[:endpos]
+
+ @property
+ def newlines(self):
+ return self._decoder.newlines if self._decoder else None
+
+
+class StringIO(TextIOWrapper):
+ """Text I/O implementation using an in-memory buffer.
+
+ The initial_value argument sets the value of object. The newline
+ argument is like the one of TextIOWrapper's constructor.
+ """
+
+ # XXX This is really slow, but fully functional
+
+ def __init__(self, initial_value="", newline="\n"):
+ super(StringIO, self).__init__(BytesIO(),
+ encoding="utf-8",
+ errors="strict",
+ newline=newline)
+ if initial_value:
+ if not isinstance(initial_value, str):
+ initial_value = str(initial_value)
+ self.write(initial_value)
+ self.seek(0)
+
+ def getvalue(self):
+ self.flush()
+ return self.buffer.getvalue().decode(self._encoding, self._errors)
Modified: python/branches/io-c/Lib/io.py
==============================================================================
--- python/branches/io-c/Lib/io.py	(original)
+++ python/branches/io-c/Lib/io.py	Sat Feb 21 21:05:40 2009
@@ -34,9 +34,6 @@
 """
 # New I/O library conforming to PEP 3116.
 
-# This is a prototype; hopefully eventually some of this will be
-# reimplemented in C.
-
 # XXX edge cases when switching between reading/writing
 # XXX need to support 1 meaning line-buffered
 # XXX whenever an argument is None, use the default value
@@ -55,1824 +52,23 @@
 "BufferedReader", "BufferedWriter", "BufferedRWPair",
 "BufferedRandom", "TextIOBase", "TextIOWrapper"]
 
-import os
-import abc
-import codecs
-#import _fileio
-# Import _thread instead of threading to reduce startup cost
-try:
- from _thread import allocate_lock as Lock
-except ImportError:
- from _dummy_thread import allocate_lock as Lock
-
-
-# open() uses st_blksize whenever we can
-DEFAULT_BUFFER_SIZE = 8 * 1024 # bytes
-
-
-class unused_BlockingIOError(IOError):
-
- """Exception raised when I/O would block on a non-blocking I/O stream."""
-
- def __init__(self, errno, strerror, characters_written=0):
- IOError.__init__(self, errno, strerror)
- self.characters_written = characters_written
-
-
-def unused_open(file, mode="r", buffering=None, encoding=None, errors=None,
- newline=None, closefd=True):
-
- r"""Open file and return a stream. Raise IOError upon failure.
-
- file is either a text or byte string giving the name (and the path
- if the file isn't in the current working directory) of the file to
- be opened or an integer file descriptor of the file to be
- 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), 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
- '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)
- 'U' universal newline mode (for backwards compatibility; unneeded
- for new code)
- ========= ===============================================================
-
- 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
- 'r+b' opens the file without truncation.
-
- Python distinguishes between files opened in binary and text modes,
- 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
- '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. By
- default full buffering is on. Pass 0 to switch buffering off (only
- allowed in binary mode), 1 to set line buffering, and an integer > 1
- for full buffering.
-
- encoding is the name of the encoding used to decode or encode the
- file. This should only be used in text mode. The default encoding is
- platform dependent, but any encoding supported by Python can be
- passed. See the codecs module for the list of supported encodings.
-
- errors is an optional string that specifies how encoding errors are to
- be handled---this argument should not be used in binary mode. Pass
- 'strict' to raise a ValueError exception if there is an encoding error
- (the default of None has the same effect), or pass 'ignore' to ignore
- errors. (Note that ignoring encoding errors can lead to data loss.)
- See the documentation for codecs.register for a list of the permitted
- encoding error strings.
-
- newline controls how universal newlines works (it only 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
- these are translated into '\n' before being returned to the
- caller. If it is '', universal newline mode is enabled, but line
- endings are returned to the caller untranslated. If it has any of
- the other legal values, input lines are only terminated by the given
- string, and the line ending is returned to the caller untranslated.
-
- * On output, if newline is None, any '\n' characters written are
- translated to the system default line separator, os.linesep. If
- newline is '', no translation takes place. If newline is any of the
- other legal values, any '\n' characters written are translated to
- the given string.
 
- 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.
-
- open() returns a file object whose type depends on the mode, and
- through which the standard file operations such as reading and writing
- are performed. When open() is used to open a file in a text mode ('w',
- 'r', 'wt', 'rt', etc.), it returns a TextIOWrapper. When used to open
- a file in a binary mode, the returned class varies: in read binary
- mode, it returns a BufferedReader; in write binary and append binary
- modes, it returns a BufferedWriter, and in read/write mode, it returns
- a BufferedRandom.
-
- It is also possible to use a string or bytearray as a file for both
- reading and writing. For strings StringIO can be used like a file
- opened in a text mode, and for bytes a BytesIO can be used like a file
- opened in a binary mode.
- """
- if not isinstance(file, (str, bytes, int)):
- raise TypeError("invalid file: %r" % file)
- if not isinstance(mode, str):
- raise TypeError("invalid mode: %r" % mode)
- if buffering is not None and not isinstance(buffering, int):
- raise TypeError("invalid buffering: %r" % buffering)
- if encoding is not None and not isinstance(encoding, str):
- raise TypeError("invalid encoding: %r" % encoding)
- if errors is not None and not isinstance(errors, str):
- raise TypeError("invalid errors: %r" % errors)
- modes = set(mode)
- if modes - set("arwb+tU") or len(mode) > len(modes):
- raise ValueError("invalid mode: %r" % mode)
- reading = "r" in modes
- writing = "w" in modes
- appending = "a" in modes
- updating = "+" in modes
- text = "t" in modes
- binary = "b" in modes
- if "U" in modes:
- if writing or appending:
- raise ValueError("can't use U and writing mode at once")
- reading = True
- if text and binary:
- raise ValueError("can't have text and binary mode at once")
- if reading + writing + appending > 1:
- raise ValueError("can't have read/write/append mode at once")
- if not (reading or writing or appending):
- raise ValueError("must have exactly one of read/write/append mode")
- if binary and encoding is not None:
- raise ValueError("binary mode doesn't take an encoding argument")
- if binary and errors is not None:
- raise ValueError("binary mode doesn't take an errors argument")
- if binary and newline is not None:
- raise ValueError("binary mode doesn't take a newline argument")
- raw = FileIO(file,
- (reading and "r" or "") +
- (writing and "w" or "") +
- (appending and "a" or "") +
- (updating and "+" or ""),
- closefd)
- if buffering is None:
- buffering = -1
- line_buffering = False
- if buffering == 1 or buffering < 0 and raw.isatty():
- buffering = -1
- line_buffering = True
- if buffering < 0:
- buffering = DEFAULT_BUFFER_SIZE
- try:
- bs = os.fstat(raw.fileno()).st_blksize
- except (os.error, AttributeError):
- pass
- else:
- if bs > 1:
- buffering = bs
- if buffering < 0:
- raise ValueError("invalid buffering size")
- if buffering == 0:
- if binary:
- return raw
- raise ValueError("can't have unbuffered text I/O")
- if updating:
- buffer = BufferedRandom(raw, buffering)
- elif writing or appending:
- buffer = BufferedWriter(raw, buffering)
- elif reading:
- buffer = BufferedReader(raw, buffering)
- else:
- raise ValueError("unknown mode: %r" % mode)
- if binary:
- return buffer
- text = TextIOWrapper(buffer, encoding, errors, newline, line_buffering)
- text.mode = mode
- return text
 import _io
+
 BlockingIOError = _io.BlockingIOError
 UnsupportedOperation = _io.UnsupportedOperation
 open = _io.open
-
-class unused_DocDescriptor:
- """Helper for builtins.open.__doc__
- """
- def __get__(self, obj, typ):
- return (
- "open(file, mode='r', buffering=None, encoding=None, "
- "errors=None, newline=None, closefd=True)\n\n" +
- open.__doc__)
-
-class unused_OpenWrapper:
- """Wrapper for builtins.open
-
- Trick so that open won't become a bound method when stored
- as a class variable (as dbm.dumb does).
-
- See initstdio() in Python/pythonrun.c.
- """
- __doc__ = unused_DocDescriptor()
-
- def __new__(cls, *args, **kwargs):
- return open(*args, **kwargs)
 OpenWrapper = _io.open
-
-
-class unused_UnsupportedOperation(ValueError, IOError):
- pass
-
-
-class unused_IOBase(metaclass=abc.ABCMeta):
-
- """The abstract base class for all I/O classes, acting on streams of
- bytes. There is no public constructor.
-
- This class provides dummy implementations for many methods that
- derived classes can override selectively; the default implementations
- represent a file that cannot be read, written or seeked.
-
- Even though IOBase does not declare read, readinto, or write because
- their signatures will vary, implementations and clients should
- consider those methods part of the interface. Also, implementations
- may raise a IOError when operations they do not support are called.
-
- The basic type used for binary data read from or written to a file is
- bytes. bytearrays are accepted too, and in some cases (such as
- readinto) needed. Text I/O classes work with str data.
-
- Note that calling any method (even inquiries) on a closed stream is
- undefined. Implementations may raise IOError in this case.
-
- IOBase (and its subclasses) support the iterator protocol, meaning
- that an IOBase object can be iterated over yielding the lines in a
- stream.
-
- IOBase also supports the :keyword:`with` statement. In this example,
- fp is closed after the suite of the with statment is complete:
-
- with open('spam.txt', 'r') as fp:
- fp.write('Spam and eggs!')
- """
-
- ### Internal ###
-
- def _unsupported(self, name: str) -> IOError:
- """Internal: raise an exception for unsupported operations."""
- raise UnsupportedOperation("%s.%s() not supported" %
- (self.__class__.__name__, name))
-
- ### Positioning ###
-
- def seek(self, pos: int, whence: int = 0) -> int:
- """Change stream position.
-
- Change the stream position to byte offset offset. offset is
- interpreted relative to the position indicated by whence. Values
- for whence are:
-
- * 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
-
- Return the new absolute position.
- """
- self._unsupported("seek")
-
- def tell(self) -> int:
- """Return current stream position."""
- return self.seek(0, 1)
-
- def truncate(self, pos: int = None) -> int:
- """Truncate file to size bytes.
-
- Size defaults to the current IO position as reported by tell(). Return
- the new size.
- """
- self._unsupported("truncate")
-
- ### Flush and close ###
-
- def flush(self) -> None:
- """Flush write buffers, if applicable.
-
- This is not implemented for read-only and non-blocking streams.
- """
- # XXX Should this return the number of bytes written???
-
- __closed = False
-
- def close(self) -> None:
- """Flush and close the IO object.
-
- This method has no effect if the file is already closed.
- """
- if not self.__closed:
- try:
- self.flush()
- except IOError:
- pass # If flush() fails, just give up
- self.__closed = True
-
- def __del__(self) -> None:
- """Destructor. Calls close()."""
- # The try/except block is in case this is called at program
- # exit time, when it's possible that globals have already been
- # deleted, and then the close() call might fail. Since
- # there's nothing we can do about such failures and they annoy
- # the end users, we suppress the traceback.
- try:
- self.close()
- except:
- pass
-
- ### Inquiries ###
-
- def seekable(self) -> bool:
- """Return whether object supports random access.
-
- If False, seek(), tell() and truncate() will raise IOError.
- This method may need to do a test seek().
- """
- return False
-
- def _checkSeekable(self, msg=None):
- """Internal: raise an IOError if file is not seekable
- """
- if not self.seekable():
- raise IOError("File or stream is not seekable."
- if msg is None else msg)
-
-
- def readable(self) -> bool:
- """Return whether object was opened for reading.
-
- If False, read() will raise IOError.
- """
- return False
-
- def _checkReadable(self, msg=None):
- """Internal: raise an IOError if file is not readable
- """
- if not self.readable():
- raise IOError("File or stream is not readable."
- if msg is None else msg)
-
- def writable(self) -> bool:
- """Return whether object was opened for writing.
-
- If False, write() and truncate() will raise IOError.
- """
- return False
-
- def _checkWritable(self, msg=None):
- """Internal: raise an IOError if file is not writable
- """
- if not self.writable():
- raise IOError("File or stream is not writable."
- if msg is None else msg)
-
- @property
- def closed(self):
- """closed: bool. True iff the file has been closed.
-
- For backwards compatibility, this is a property, not a predicate.
- """
- return self.__closed
-
- def _checkClosed(self, msg=None):
- """Internal: raise an ValueError if file is closed
- """
- if self.closed:
- raise ValueError("I/O operation on closed file."
- if msg is None else msg)
-
- ### Context manager ###
-
- def __enter__(self) -> "IOBase": # That's a forward reference
- """Context management protocol. Returns self."""
- self._checkClosed()
- return self
-
- def __exit__(self, *args) -> None:
- """Context management protocol. Calls close()"""
- self.close()
-
- ### Lower-level APIs ###
-
- # XXX Should these be present even if unimplemented?
-
- def fileno(self) -> int:
- """Returns underlying file descriptor if one exists.
-
- An IOError is raised if the IO object does not use a file descriptor.
- """
- self._unsupported("fileno")
-
- def isatty(self) -> bool:
- """Return whether this is an 'interactive' stream.
-
- Return False if it can't be determined.
- """
- self._checkClosed()
- return False
-
- ### Readline[s] and writelines ###
-
- def readline(self, limit: int = -1) -> bytes:
- r"""Read and return a line from the stream.
-
- If limit is specified, at most limit bytes will be read.
-
- The line terminator is always b'\n' for binary files; for text
- files, the newlines argument to open can be used to select the line
- terminator(s) recognized.
- """
- # For backwards compatibility, a (slowish) readline().
- if hasattr(self, "peek"):
- def nreadahead():
- readahead = self.peek(1)
- if not readahead:
- return 1
- n = (readahead.find(b"\n") + 1) or len(readahead)
- if limit >= 0:
- n = min(n, limit)
- return n
- else:
- def nreadahead():
- return 1
- if limit is None:
- limit = -1
- res = bytearray()
- while limit < 0 or len(res) < limit:
- b = self.read(nreadahead())
- if not b:
- break
- res += b
- if res.endswith(b"\n"):
- break
- return bytes(res)
-
- def __iter__(self):
- self._checkClosed()
- return self
-
- def __next__(self):
- line = self.readline()
- if not line:
- raise StopIteration
- return line
-
- def readlines(self, hint=None):
- """Return a list of lines from the stream.
-
- hint can be specified to control the number of lines read: no more
- lines will be read if the total size (in bytes/characters) of all
- lines so far exceeds hint.
- """
- if hint is None or hint <= 0:
- return list(self)
- n = 0
- lines = []
- for line in self:
- lines.append(line)
- n += len(line)
- if n >= hint:
- break
- return lines
-
- def writelines(self, lines):
- self._checkClosed()
- for line in lines:
- self.write(line)
 IOBase = _io.IOBase
-
-
-class unused_RawIOBase(IOBase):
-
- """Base class for raw binary I/O."""
-
- # The read() method is implemented by calling readinto(); derived
- # classes that want to support read() only need to implement
- # readinto() as a primitive operation. In general, readinto() can be
- # more efficient than read().
-
- # (It would be tempting to also provide an implementation of
- # readinto() in terms of read(), in case the latter is a more suitable
- # primitive operation, but that would lead to nasty recursion in case
- # a subclass doesn't implement either.)
-
- def read(self, n: int = -1) -> bytes:
- """Read and return up to n bytes.
-
- Returns an empty bytes object on EOF, or None if the object is
- set not to block and has no data to read.
- """
- if n is None:
- n = -1
- if n < 0:
- return self.readall()
- b = bytearray(n.__index__())
- n = self.readinto(b)
- del b[n:]
- return bytes(b)
-
- def readall(self):
- """Read until EOF, using multiple read() call."""
- res = bytearray()
- while True:
- data = self.read(DEFAULT_BUFFER_SIZE)
- if not data:
- break
- res += data
- return bytes(res)
-
- def readinto(self, b: bytearray) -> int:
- """Read up to len(b) bytes into b.
-
- Returns number of bytes read (0 for EOF), or None if the object
- is set not to block as has no data to read.
- """
- self._unsupported("readinto")
-
- def write(self, b: bytes) -> int:
- """Write the given buffer to the IO stream.
-
- Returns the number of bytes written, which may be less than len(b).
- """
- self._unsupported("write")
 RawIOBase = _io.RawIOBase
-
-
-if 0:
- class unused_FileIO(_fileio._FileIO, RawIOBase):
-
- """Raw I/O implementation for OS files."""
-
- # This multiply inherits from _FileIO and RawIOBase to make
- # isinstance(io.FileIO(), io.RawIOBase) return True without requiring
- # that _fileio._FileIO inherits from io.RawIOBase (which would be hard
- # to do since _fileio.c is written in C).
-
- def __init__(self, name, mode="r", closefd=True):
- _fileio._FileIO.__init__(self, name, mode, closefd)
- self._name = name
-
- def close(self):
- _fileio._FileIO.close(self)
- RawIOBase.close(self)
-
- @property
- def name(self):
- return self._name
-
 FileIO = _io.FileIO
-
-
-class unused_BufferedIOBase(IOBase):
-
- """Base class for buffered IO objects.
-
- The main difference with RawIOBase is that the read() method
- supports omitting the size argument, and does not have a default
- implementation that defers to readinto().
-
- In addition, read(), readinto() and write() may raise
- BlockingIOError if the underlying raw stream is in non-blocking
- mode and not ready; unlike their raw counterparts, they will never
- return None.
-
- A typical implementation should not inherit from a RawIOBase
- implementation, but wrap one.
- """
-
- def read(self, n: int = None) -> bytes:
- """Read and return up to n bytes.
-
- If the argument is omitted, None, or negative, reads and
- returns all data until EOF.
-
- If the argument is positive, and the underlying raw stream is
- not 'interactive', multiple raw reads may be issued to satisfy
- the byte count (unless EOF is reached first). But for
- interactive raw streams (XXX and for pipes?), at most one raw
- read will be issued, and a short result does not imply that
- EOF is imminent.
-
- Returns an empty bytes array on EOF.
-
- Raises BlockingIOError if the underlying raw stream has no
- data at the moment.
- """
- self._unsupported("read")
-
- def readinto(self, b: bytearray) -> int:
- """Read up to len(b) bytes into b.
-
- Like read(), this may issue multiple reads to the underlying raw
- stream, unless the latter is 'interactive'.
-
- Returns the number of bytes read (0 for EOF).
-
- Raises BlockingIOError if the underlying raw stream has no
- data at the moment.
- """
- # XXX This ought to work with anything that supports the buffer API
- data = self.read(len(b))
- n = len(data)
- try:
- b[:n] = data
- except TypeError as err:
- import array
- if not isinstance(b, array.array):
- raise err
- b[:n] = array.array('b', data)
- return n
-
- def write(self, b: bytes) -> int:
- """Write the given buffer to the IO stream.
-
- Return the number of bytes written, which is never less than
- len(b).
-
- Raises BlockingIOError if the buffer is full and the
- underlying raw stream cannot accept more data at the moment.
- """
- self._unsupported("write")
 BufferedIOBase = _io.BufferedIOBase
-
-
-class unused_BufferedIOMixin(BufferedIOBase):
-
- """A mixin implementation of BufferedIOBase with an underlying raw stream.
-
- This passes most requests on to the underlying raw stream. It
- does *not* provide implementations of read(), readinto() or
- write().
- """
-
- def __init__(self, raw):
- self.raw = raw
-
- ### Positioning ###
-
- def seek(self, pos, whence=0):
- return self.raw.seek(pos, whence)
-
- def tell(self):
- return self.raw.tell()
-
- def truncate(self, pos=None):
- # Flush the stream. We're mixing buffered I/O with lower-level I/O,
- # and a flush may be necessary to synch both views of the current
- # file state.
- self.flush()
-
- if pos is None:
- pos = self.tell()
- # XXX: Should seek() be used, instead of passing the position
- # XXX directly to truncate?
- return self.raw.truncate(pos)
-
- ### Flush and close ###
-
- def flush(self):
- self.raw.flush()
-
- def close(self):
- if not self.closed:
- try:
- self.flush()
- except IOError:
- pass # If flush() fails, just give up
- self.raw.close()
-
- ### Inquiries ###
-
- def seekable(self):
- return self.raw.seekable()
-
- def readable(self):
- return self.raw.readable()
-
- def writable(self):
- return self.raw.writable()
-
- @property
- def closed(self):
- return self.raw.closed
-
- @property
- def name(self):
- return self.raw.name
-
- @property
- def mode(self):
- return self.raw.mode
-
- ### Lower-level APIs ###
-
- def fileno(self):
- return self.raw.fileno()
-
- def isatty(self):
- return self.raw.isatty()
-
-
-class unused_BytesIO(BufferedIOBase):
-
- """Buffered I/O implementation using an in-memory bytes buffer."""
-
- def __init__(self, initial_bytes=None):
- buf = bytearray()
- if initial_bytes is not None:
- buf += initial_bytes
- self._buffer = buf
- self._pos = 0
-
- def getvalue(self):
- """Return the bytes value (contents) of the buffer
- """
- if self.closed:
- raise ValueError("getvalue on closed file")
- return bytes(self._buffer)
-
- def read(self, n=None):
- if self.closed:
- raise ValueError("read from closed file")
- if n is None:
- n = -1
- if n < 0:
- n = len(self._buffer)
- if len(self._buffer) <= self._pos:
- return b""
- newpos = min(len(self._buffer), self._pos + n)
- b = self._buffer[self._pos : newpos]
- self._pos = newpos
- return bytes(b)
-
- def read1(self, n):
- """This is the same as read.
- """
- return self.read(n)
-
- def write(self, b):
- if self.closed:
- raise ValueError("write to closed file")
- if isinstance(b, str):
- raise TypeError("can't write str to binary stream")
- n = len(b)
- if n == 0:
- return 0
- pos = self._pos
- if pos > len(self._buffer):
- # Inserts null bytes between the current end of the file
- # and the new write position.
- padding = b'\x00' * (pos - len(self._buffer))
- self._buffer += padding
- self._buffer[pos:pos + n] = b
- self._pos += n
- return n
-
- def seek(self, pos, whence=0):
- if self.closed:
- raise ValueError("seek on closed file")
- try:
- pos = pos.__index__()
- except AttributeError as err:
- raise TypeError("an integer is required") from err
- if whence == 0:
- if pos < 0:
- raise ValueError("negative seek position %r" % (pos,))
- self._pos = pos
- elif whence == 1:
- self._pos = max(0, self._pos + pos)
- elif whence == 2:
- self._pos = max(0, len(self._buffer) + pos)
- else:
- raise ValueError("invalid whence value")
- return self._pos
-
- def tell(self):
- if self.closed:
- raise ValueError("tell on closed file")
- return self._pos
-
- def truncate(self, pos=None):
- if self.closed:
- raise ValueError("truncate on closed file")
- if pos is None:
- pos = self._pos
- elif pos < 0:
- raise ValueError("negative truncate position %r" % (pos,))
- del self._buffer[pos:]
- return self.seek(pos)
-
- def readable(self):
- return True
-
- def writable(self):
- return True
-
- def seekable(self):
- return True
-
-# Use the faster implementation of BytesIO if available
-if 0:
- try:
- import _bytesio
-
- class BytesIO(_bytesio._BytesIO, BufferedIOBase):
- __doc__ = _bytesio._BytesIO.__doc__
-
- except ImportError:
- BytesIO = _BytesIO
 BytesIO = _io.BytesIO
-
-
-class unused_BufferedReader(unused_BufferedIOMixin):
-
- """BufferedReader(raw[, buffer_size])
-
- A buffer for a readable, sequential BaseRawIO object.
-
- The constructor creates a BufferedReader for the given readable raw
- stream and buffer_size. If buffer_size is omitted, DEFAULT_BUFFER_SIZE
- is used.
- """
-
- def __init__(self, raw, buffer_size=DEFAULT_BUFFER_SIZE):
- """Create a new buffered reader using the given readable raw IO object.
- """
- raw._checkReadable()
- _BufferedIOMixin.__init__(self, raw)
- self.buffer_size = buffer_size
- self._reset_read_buf()
- self._read_lock = Lock()
-
- def _reset_read_buf(self):
- self._read_buf = b""
- self._read_pos = 0
-
- def read(self, n=None):
- """Read n bytes.
-
- Returns exactly n bytes of data unless the underlying raw IO
- stream reaches EOF or if the call would block in non-blocking
- mode. If n is negative, read until EOF or until read() would
- block.
- """
- with self._read_lock:
- return self._read_unlocked(n)
-
- def _read_unlocked(self, n=None):
- nodata_val = b""
- empty_values = (b"", None)
- buf = self._read_buf
- pos = self._read_pos
-
- # Special case for when the number of bytes to read is unspecified.
- if n is None or n == -1:
- self._reset_read_buf()
- chunks = [buf[pos:]] # Strip the consumed bytes.
- current_size = 0
- while True:
- # Read until EOF or until read() would block.
- chunk = self.raw.read()
- if chunk in empty_values:
- nodata_val = chunk
- break
- current_size += len(chunk)
- chunks.append(chunk)
- return b"".join(chunks) or nodata_val
-
- # The number of bytes to read is specified, return at most n bytes.
- avail = len(buf) - pos # Length of the available buffered data.
- if n <= avail:
- # Fast path: the data to read is fully buffered.
- self._read_pos += n
- return buf[pos:pos+n]
- # Slow path: read from the stream until enough bytes are read,
- # or until an EOF occurs or until read() would block.
- chunks = [buf[pos:]]
- wanted = max(self.buffer_size, n)
- while avail < n:
- chunk = self.raw.read(wanted)
- if chunk in empty_values:
- nodata_val = chunk
- break
- avail += len(chunk)
- chunks.append(chunk)
- # n is more then avail only when an EOF occurred or when
- # read() would have blocked.
- n = min(n, avail)
- out = b"".join(chunks)
- self._read_buf = out[n:] # Save the extra data in the buffer.
- self._read_pos = 0
- return out[:n] if out else nodata_val
-
- def peek(self, n=0):
- """Returns buffered bytes without advancing the position.
-
- The argument indicates a desired minimal number of bytes; we
- do at most one raw read to satisfy it. We never return more
- than self.buffer_size.
- """
- with self._read_lock:
- return self._peek_unlocked(n)
-
- def _peek_unlocked(self, n=0):
- want = min(n, self.buffer_size)
- have = len(self._read_buf) - self._read_pos
- if have < want:
- to_read = self.buffer_size - have
- current = self.raw.read(to_read)
- if current:
- self._read_buf = self._read_buf[self._read_pos:] + current
- self._read_pos = 0
- return self._read_buf[self._read_pos:]
-
- def read1(self, n):
- """Reads up to n bytes, with at most one read() system call."""
- # Returns up to n bytes. If at least one byte is buffered, we
- # only return buffered bytes. Otherwise, we do one raw read.
- if n <= 0:
- return b""
- with self._read_lock:
- self._peek_unlocked(1)
- return self._read_unlocked(
- min(n, len(self._read_buf) - self._read_pos))
-
- def tell(self):
- return self.raw.tell() - len(self._read_buf) + self._read_pos
-
- def seek(self, pos, whence=0):
- with self._read_lock:
- if whence == 1:
- pos -= len(self._read_buf) - self._read_pos
- pos = self.raw.seek(pos, whence)
- self._reset_read_buf()
- return pos
+StringIO = _io.StringIO
 BufferedReader = _io.BufferedReader
-
-
-class unused_BufferedWriter(unused_BufferedIOMixin):
-
- """A buffer for a writeable sequential RawIO object.
-
- The constructor creates a BufferedWriter for the given writeable raw
- stream. If the buffer_size is not given, it defaults to
- DEAFULT_BUFFER_SIZE. If max_buffer_size is omitted, it defaults to
- twice the buffer size.
- """
-
- def __init__(self, raw,
- buffer_size=DEFAULT_BUFFER_SIZE, max_buffer_size=None):
- raw._checkWritable()
- _BufferedIOMixin.__init__(self, raw)
- self.buffer_size = buffer_size
- self.max_buffer_size = (2*buffer_size
- if max_buffer_size is None
- else max_buffer_size)
- self._write_buf = bytearray()
- self._write_lock = Lock()
-
- def write(self, b):
- if self.closed:
- raise ValueError("write to closed file")
- if isinstance(b, str):
- raise TypeError("can't write str to binary stream")
- with self._write_lock:
- # XXX we can implement some more tricks to try and avoid
- # partial writes
- if len(self._write_buf) > self.buffer_size:
- # We're full, so let's pre-flush the buffer
- try:
- self._flush_unlocked()
- except BlockingIOError as e:
- # We can't accept anything else.
- # XXX Why not just let the exception pass through?
- raise BlockingIOError(e.errno, e.strerror, 0)
- before = len(self._write_buf)
- self._write_buf.extend(b)
- written = len(self._write_buf) - before
- if len(self._write_buf) > self.buffer_size:
- try:
- self._flush_unlocked()
- except BlockingIOError as e:
- if len(self._write_buf) > self.max_buffer_size:
- # We've hit max_buffer_size. We have to accept a
- # partial write and cut back our buffer.
- overage = len(self._write_buf) - self.max_buffer_size
- self._write_buf = self._write_buf[:self.max_buffer_size]
- raise BlockingIOError(e.errno, e.strerror, overage)
- return written
-
- def truncate(self, pos=None):
- with self._write_lock:
- self._flush_unlocked()
- if pos is None:
- pos = self.raw.tell()
- return self.raw.truncate(pos)
-
- def flush(self):
- with self._write_lock:
- self._flush_unlocked()
-
- def _flush_unlocked(self):
- if self.closed:
- raise ValueError("flush of closed file")
- written = 0
- try:
- while self._write_buf:
- n = self.raw.write(self._write_buf)
- del self._write_buf[:n]
- written += n
- except BlockingIOError as e:
- n = e.characters_written
- del self._write_buf[:n]
- written += n
- raise BlockingIOError(e.errno, e.strerror, written)
-
- def tell(self):
- return self.raw.tell() + len(self._write_buf)
-
- def seek(self, pos, whence=0):
- with self._write_lock:
- self._flush_unlocked()
- return self.raw.seek(pos, whence)
 BufferedWriter = _io.BufferedWriter
-
-
-class unused_BufferedRWPair(BufferedIOBase):
-
- """A buffered reader and writer object together.
-
- A buffered reader object and buffered writer object put together to
- form a sequential IO object that can read and write. This is typically
- used with a socket or two-way pipe.
-
- reader and writer are RawIOBase objects that are readable and
- writeable respectively. If the buffer_size is omitted it defaults to
- DEFAULT_BUFFER_SIZE. The max_buffer_size (for the buffered writer)
- defaults to twice the buffer size.
- """
-
- # XXX The usefulness of this (compared to having two separate IO
- # objects) is questionable.
-
- def __init__(self, reader, writer,
- buffer_size=DEFAULT_BUFFER_SIZE, max_buffer_size=None):
- """Constructor.
-
- The arguments are two RawIO instances.
- """
- reader._checkReadable()
- writer._checkWritable()
- self.reader = BufferedReader(reader, buffer_size)
- self.writer = BufferedWriter(writer, buffer_size, max_buffer_size)
-
- def read(self, n=None):
- if n is None:
- n = -1
- return self.reader.read(n)
-
- def readinto(self, b):
- return self.reader.readinto(b)
-
- def write(self, b):
- return self.writer.write(b)
-
- def peek(self, n=0):
- return self.reader.peek(n)
-
- def read1(self, n):
- return self.reader.read1(n)
-
- def readable(self):
- return self.reader.readable()
-
- def writable(self):
- return self.writer.writable()
-
- def flush(self):
- return self.writer.flush()
-
- def close(self):
- self.writer.close()
- self.reader.close()
-
- def isatty(self):
- return self.reader.isatty() or self.writer.isatty()
-
- @property
- def closed(self):
- return self.writer.closed()
 BufferedRWPair = _io.BufferedRWPair
-
-class unused_BufferedRandom(unused_BufferedWriter, unused_BufferedReader):
-
- """A buffered interface to random access streams.
-
- The constructor creates a reader and writer for a seekable stream,
- raw, given in the first argument. If the buffer_size is omitted it
- defaults to DEFAULT_BUFFER_SIZE. The max_buffer_size (for the buffered
- writer) defaults to twice the buffer size.
- """
-
- def __init__(self, raw,
- buffer_size=DEFAULT_BUFFER_SIZE, max_buffer_size=None):
- raw._checkSeekable()
- BufferedReader.__init__(self, raw, buffer_size)
- BufferedWriter.__init__(self, raw, buffer_size, max_buffer_size)
-
- def seek(self, pos, whence=0):
- self.flush()
- # First do the raw seek, then empty the read buffer, so that
- # if the raw seek fails, we don't lose buffered data forever.
- pos = self.raw.seek(pos, whence)
- with self._read_lock:
- self._reset_read_buf()
- return pos
-
- def tell(self):
- if self._write_buf:
- return self.raw.tell() + len(self._write_buf)
- else:
- return BufferedReader.tell(self)
-
- def truncate(self, pos=None):
- if pos is None:
- pos = self.tell()
- # Use seek to flush the read buffer.
- self.seek(pos)
- return BufferedWriter.truncate(self)
-
- def read(self, n=None):
- if n is None:
- n = -1
- self.flush()
- return BufferedReader.read(self, n)
-
- def readinto(self, b):
- self.flush()
- return BufferedReader.readinto(self, b)
-
- def peek(self, n=0):
- self.flush()
- return BufferedReader.peek(self, n)
-
- def read1(self, n):
- self.flush()
- return BufferedReader.read1(self, n)
-
- def write(self, b):
- if self._read_buf:
- # Undo readahead
- with self._read_lock:
- self.raw.seek(self._read_pos - len(self._read_buf), 1)
- self._reset_read_buf()
- return BufferedWriter.write(self, b)
 BufferedRandom = _io.BufferedRandom
-
-
-class unused_TextIOBase(IOBase):
-
- """Base class for text I/O.
-
- This class provides a character and line based interface to stream
- I/O. There is no readinto method because Python's character strings
- are immutable. There is no public constructor.
- """
-
- def read(self, n: int = -1) -> str:
- """Read at most n characters from stream.
-
- Read from underlying buffer until we have n characters or we hit EOF.
- If n is negative or omitted, read until EOF.
- """
- self._unsupported("read")
-
- def write(self, s: str) -> int:
- """Write string s to stream."""
- self._unsupported("write")
-
- def truncate(self, pos: int = None) -> int:
- """Truncate size to pos."""
- self._unsupported("truncate")
-
- def readline(self) -> str:
- """Read until newline or EOF.
-
- Returns an empty string if EOF is hit immediately.
- """
- self._unsupported("readline")
-
- @property
- def encoding(self):
- """Subclasses should override."""
- return None
-
- @property
- def newlines(self):
- """Line endings translated so far.
-
- Only line endings translated during reading are considered.
-
- Subclasses should override.
- """
- return None
 TextIOBase = _io.TextIOBase
-
-
 IncrementalNewlineDecoder = _io.IncrementalNewlineDecoder
-class unused_IncrementalNewlineDecoder(codecs.IncrementalDecoder):
- r"""Codec used when reading a file in universal newlines mode. It wraps
- another incremental decoder, translating \r\n and \r into \n. It also
- records the types of newlines encountered. When used with
- translate=False, it ensures that the newline sequence is returned in
- one piece.
- """
- def __init__(self, decoder, translate, errors='strict'):
- codecs.IncrementalDecoder.__init__(self, errors=errors)
- self.translate = translate
- self.decoder = decoder
- self.seennl = 0
- self.pendingcr = False
-
- def decode(self, input, final=False):
- # decode input (with the eventual \r from a previous pass)
- output = self.decoder.decode(input, final=final)
- if self.pendingcr and (output or final):
- output = "\r" + output
- self.pendingcr = False
-
- # retain last \r even when not translating data:
- # then readline() is sure to get \r\n in one pass
- if output.endswith("\r") and not final:
- output = output[:-1]
- self.pendingcr = True
-
- # Record which newlines are read
- crlf = output.count('\r\n')
- cr = output.count('\r') - crlf
- lf = output.count('\n') - crlf
- self.seennl |= (lf and self._LF) | (cr and self._CR) \
- | (crlf and self._CRLF)
-
- if self.translate:
- if crlf:
- output = output.replace("\r\n", "\n")
- if cr:
- output = output.replace("\r", "\n")
-
- return output
-
- def getstate(self):
- buf, flag = self.decoder.getstate()
- flag <<= 1
- if self.pendingcr:
- flag |= 1
- return buf, flag
-
- def setstate(self, state):
- buf, flag = state
- self.pendingcr = bool(flag & 1)
- self.decoder.setstate((buf, flag >> 1))
-
- def reset(self):
- self.seennl = 0
- self.pendingcr = False
- self.decoder.reset()
-
- _LF = 1
- _CR = 2
- _CRLF = 4
-
- @property
- def newlines(self):
- return (None,
- "\n",
- "\r",
- ("\r", "\n"),
- "\r\n",
- ("\n", "\r\n"),
- ("\r", "\r\n"),
- ("\r", "\n", "\r\n")
- )[self.seennl]
-
-
 TextIOWrapper = _io.TextIOWrapper
-class unused_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.
-
- errors determines the strictness of encoding and decoding (see the
- codecs.register) and defaults to "strict".
-
- newline can be None, '', '\n', '\r', or '\r\n'. It controls the
- handling of line endings. If it is None, universal newlines is
- enabled. With this enabled, on input, the lines endings '\n', '\r',
- or '\r\n' are translated to '\n' before being returned to the
- caller. Conversely, on output, '\n' is translated to the system
- default line seperator, os.linesep. If newline is any other of its
- legal values, that newline becomes the newline when the file is read
- and it is returned untranslated. On output, '\n' is converted to the
- newline.
-
- If line_buffering is True, a call to flush is implied when a call to
- write contains a newline character.
- """
-
- _CHUNK_SIZE = 128
-
- def __init__(self, buffer, encoding=None, errors=None, newline=None,
- line_buffering=False):
- if newline not in (None, "", "\n", "\r", "\r\n"):
- raise ValueError("illegal newline value: %r" % (newline,))
- if encoding is None:
- try:
- encoding = os.device_encoding(buffer.fileno())
- except (AttributeError, UnsupportedOperation):
- pass
- if encoding is None:
- try:
- import locale
- except ImportError:
- # Importing locale may fail if Python is being built
- encoding = "ascii"
- else:
- encoding = locale.getpreferredencoding()
-
- if not isinstance(encoding, str):
- raise ValueError("invalid encoding: %r" % encoding)
-
- if errors is None:
- errors = "strict"
- else:
- if not isinstance(errors, str):
- raise ValueError("invalid errors: %r" % errors)
-
- self.buffer = buffer
- self._line_buffering = line_buffering
- self._encoding = encoding
- self._errors = errors
- self._readuniversal = not newline
- self._readtranslate = newline is None
- self._readnl = newline
- self._writetranslate = newline != ''
- self._writenl = newline or os.linesep
- self._encoder = None
- self._decoder = None
- self._decoded_chars = '' # buffer for text returned from decoder
- self._decoded_chars_used = 0 # offset into _decoded_chars for read()
- self._snapshot = None # info for reconstructing decoder state
- self._seekable = self._telling = self.buffer.seekable()
-
- # self._snapshot is either None, or a tuple (dec_flags, next_input)
- # where dec_flags is the second (integer) item of the decoder state
- # and next_input is the chunk of input bytes that comes next after the
- # snapshot point. We use this to reconstruct decoder states in tell().
-
- # Naming convention:
- # - "bytes_..." for integer variables that count input bytes
- # - "chars_..." for integer variables that count decoded characters
-
- @property
- def encoding(self):
- return self._encoding
-
- @property
- def errors(self):
- return self._errors
-
- @property
- def line_buffering(self):
- return self._line_buffering
-
- def seekable(self):
- return self._seekable
-
- def readable(self):
- return self.buffer.readable()
-
- def writable(self):
- return self.buffer.writable()
-
- def flush(self):
- self.buffer.flush()
- self._telling = self._seekable
-
- def close(self):
- try:
- self.flush()
- except:
- pass # If flush() fails, just give up
- self.buffer.close()
-
- @property
- def closed(self):
- return self.buffer.closed
-
- @property
- def name(self):
- return self.buffer.name
-
- def fileno(self):
- return self.buffer.fileno()
-
- def isatty(self):
- return self.buffer.isatty()
-
- def write(self, s: str):
- if self.closed:
- raise ValueError("write to closed file")
- if not isinstance(s, str):
- raise TypeError("can't write %s to text stream" %
- s.__class__.__name__)
- length = len(s)
- haslf = (self._writetranslate or self._line_buffering) and "\n" in s
- if haslf and self._writetranslate and self._writenl != "\n":
- s = s.replace("\n", self._writenl)
- encoder = self._encoder or self._get_encoder()
- # XXX What if we were just reading?
- b = encoder.encode(s)
- self.buffer.write(b)
- if self._line_buffering and (haslf or "\r" in s):
- self.flush()
- self._snapshot = None
- if self._decoder:
- self._decoder.reset()
- return length
-
- def _get_encoder(self):
- make_encoder = codecs.getincrementalencoder(self._encoding)
- self._encoder = make_encoder(self._errors)
- return self._encoder
-
- def _get_decoder(self):
- make_decoder = codecs.getincrementaldecoder(self._encoding)
- decoder = make_decoder(self._errors)
- if self._readuniversal:
- decoder = IncrementalNewlineDecoder(decoder, self._readtranslate)
- self._decoder = decoder
- return decoder
-
- # The following three methods implement an ADT for _decoded_chars.
- # Text returned from the decoder is buffered here until the client
- # requests it by calling our read() or readline() method.
- def _set_decoded_chars(self, chars):
- """Set the _decoded_chars buffer."""
- self._decoded_chars = chars
- self._decoded_chars_used = 0
-
- def _get_decoded_chars(self, n=None):
- """Advance into the _decoded_chars buffer."""
- offset = self._decoded_chars_used
- if n is None:
- chars = self._decoded_chars[offset:]
- else:
- chars = self._decoded_chars[offset:offset + n]
- self._decoded_chars_used += len(chars)
- return chars
-
- def _rewind_decoded_chars(self, n):
- """Rewind the _decoded_chars buffer."""
- if self._decoded_chars_used < n:
- raise AssertionError("rewind decoded_chars out of bounds")
- self._decoded_chars_used -= n
-
- def _read_chunk(self):
- """
- Read and decode the next chunk of data from the BufferedReader.
- """
-
- # The return value is True unless EOF was reached. The decoded
- # string is placed in self._decoded_chars (replacing its previous
- # value). The entire input chunk is sent to the decoder, though
- # some of it may remain buffered in the decoder, yet to be
- # converted.
-
- if self._decoder is None:
- raise ValueError("no decoder")
-
- if self._telling:
- # To prepare for tell(), we need to snapshot a point in the
- # file where the decoder's input buffer is empty.
-
- dec_buffer, dec_flags = self._decoder.getstate()
- # Given this, we know there was a valid snapshot point
- # len(dec_buffer) bytes ago with decoder state (b'', dec_flags).
-
- # Read a chunk, decode it, and put the result in self._decoded_chars.
- input_chunk = self.buffer.read1(self._CHUNK_SIZE)
- eof = not input_chunk
- self._set_decoded_chars(self._decoder.decode(input_chunk, eof))
-
- if self._telling:
- # At the snapshot point, len(dec_buffer) bytes before the read,
- # the next input to be decoded is dec_buffer + input_chunk.
- self._snapshot = (dec_flags, dec_buffer + input_chunk)
-
- return not eof
-
- def _pack_cookie(self, position, dec_flags=0,
- bytes_to_feed=0, need_eof=0, chars_to_skip=0):
- # The meaning of a tell() cookie is: seek to position, set the
- # decoder flags to dec_flags, read bytes_to_feed bytes, feed them
- # into the decoder with need_eof as the EOF flag, then skip
- # chars_to_skip characters of the decoded result. For most simple
- # decoders, tell() will often just give a byte offset in the file.
- return (position | (dec_flags<<64) | (bytes_to_feed<<128) |
- (chars_to_skip<<192) | bool(need_eof)<<256)
-
- def _unpack_cookie(self, bigint):
- rest, position = divmod(bigint, 1<<64)
- rest, dec_flags = divmod(rest, 1<<64)
- rest, bytes_to_feed = divmod(rest, 1<<64)
- need_eof, chars_to_skip = divmod(rest, 1<<64)
- return position, dec_flags, bytes_to_feed, need_eof, chars_to_skip
-
- def tell(self):
- if not self._seekable:
- raise IOError("underlying stream is not seekable")
- if not self._telling:
- raise IOError("telling position disabled by next() call")
- self.flush()
- position = self.buffer.tell()
- decoder = self._decoder
- if decoder is None or self._snapshot is None:
- if self._decoded_chars:
- # This should never happen.
- raise AssertionError("pending decoded text")
- return position
-
- # Skip backward to the snapshot point (see _read_chunk).
- dec_flags, next_input = self._snapshot
- position -= len(next_input)
-
- # How many decoded characters have been used up since the snapshot?
- chars_to_skip = self._decoded_chars_used
- if chars_to_skip == 0:
- # We haven't moved from the snapshot point.
- return self._pack_cookie(position, dec_flags)
-
- # Starting from the snapshot position, we will walk the decoder
- # forward until it gives us enough decoded characters.
- saved_state = decoder.getstate()
- try:
- # Note our initial start point.
- decoder.setstate((b'', dec_flags))
- start_pos = position
- start_flags, bytes_fed, chars_decoded = dec_flags, 0, 0
- need_eof = 0
-
- # Feed the decoder one byte at a time. As we go, note the
- # nearest "safe start point" before the current location
- # (a point where the decoder has nothing buffered, so seek()
- # can safely start from there and advance to this location).
- next_byte = bytearray(1)
- for next_byte[0] in next_input:
- bytes_fed += 1
- chars_decoded += len(decoder.decode(next_byte))
- dec_buffer, dec_flags = decoder.getstate()
- if not dec_buffer and chars_decoded <= chars_to_skip:
- # Decoder buffer is empty, so this is a safe start point.
- start_pos += bytes_fed
- chars_to_skip -= chars_decoded
- start_flags, bytes_fed, chars_decoded = dec_flags, 0, 0
- if chars_decoded >= chars_to_skip:
- break
- else:
- # We didn't get enough decoded data; signal EOF to get more.
- chars_decoded += len(decoder.decode(b'', final=True))
- need_eof = 1
- if chars_decoded < chars_to_skip:
- raise IOError("can't reconstruct logical file position")
-
- # The returned cookie corresponds to the last safe start point.
- return self._pack_cookie(
- start_pos, start_flags, bytes_fed, need_eof, chars_to_skip)
- finally:
- decoder.setstate(saved_state)
-
- def truncate(self, pos=None):
- self.flush()
- if pos is None:
- pos = self.tell()
- self.seek(pos)
- return self.buffer.truncate()
-
- def seek(self, cookie, whence=0):
- if self.closed:
- raise ValueError("tell on closed file")
- if not self._seekable:
- raise IOError("underlying stream is not seekable")
- if whence == 1: # seek relative to current position
- if cookie != 0:
- raise IOError("can't do nonzero cur-relative seeks")
- # Seeking to the current position should attempt to
- # sync the underlying buffer with the current position.
- whence = 0
- cookie = self.tell()
- if whence == 2: # seek relative to end of file
- if cookie != 0:
- raise IOError("can't do nonzero end-relative seeks")
- self.flush()
- position = self.buffer.seek(0, 2)
- self._set_decoded_chars('')
- self._snapshot = None
- if self._decoder:
- self._decoder.reset()
- return position
- if whence != 0:
- raise ValueError("invalid whence (%r, should be 0, 1 or 2)" %
- (whence,))
- if cookie < 0:
- raise ValueError("negative seek position %r" % (cookie,))
- self.flush()
-
- # The strategy of seek() is to go back to the safe start point
- # and replay the effect of read(chars_to_skip) from there.
- start_pos, dec_flags, bytes_to_feed, need_eof, chars_to_skip = \
- self._unpack_cookie(cookie)
-
- # Seek back to the safe start point.
- self.buffer.seek(start_pos)
- self._set_decoded_chars('')
- self._snapshot = None
-
- # Restore the decoder to its state from the safe start point.
- if self._decoder or dec_flags or chars_to_skip:
- self._decoder = self._decoder or self._get_decoder()
- self._decoder.setstate((b'', dec_flags))
- self._snapshot = (dec_flags, b'')
-
- if chars_to_skip:
- # Just like _read_chunk, feed the decoder and save a snapshot.
- input_chunk = self.buffer.read(bytes_to_feed)
- self._set_decoded_chars(
- self._decoder.decode(input_chunk, need_eof))
- self._snapshot = (dec_flags, input_chunk)
-
- # Skip chars_to_skip of the decoded characters.
- if len(self._decoded_chars) < chars_to_skip:
- raise IOError("can't restore logical file position")
- self._decoded_chars_used = chars_to_skip
-
- return cookie
-
- def read(self, n=None):
- if n is None:
- n = -1
- decoder = self._decoder or self._get_decoder()
- if n < 0:
- # Read everything.
- result = (self._get_decoded_chars() +
- decoder.decode(self.buffer.read(), final=True))
- self._set_decoded_chars('')
- self._snapshot = None
- return result
- else:
- # Keep reading chunks until we have n characters to return.
- eof = False
- result = self._get_decoded_chars(n)
- while len(result) < n and not eof:
- eof = not self._read_chunk()
- result += self._get_decoded_chars(n - len(result))
- return result
-
- def __next__(self):
- self._telling = False
- line = self.readline()
- if not line:
- self._snapshot = None
- self._telling = self._seekable
- raise StopIteration
- return line
-
- def readline(self, limit=None):
- if self.closed:
- raise ValueError("read from closed file")
- if limit is None:
- limit = -1
-
- # Grab all the decoded text (we will rewind any extra bits later).
- line = self._get_decoded_chars()
-
- start = 0
- decoder = self._decoder or self._get_decoder()
-
- pos = endpos = None
- while True:
- if self._readtranslate:
- # Newlines are already translated, only search for \n
- pos = line.find('\n', start)
- if pos >= 0:
- endpos = pos + 1
- break
- else:
- start = len(line)
-
- elif self._readuniversal:
- # Universal newline search. Find any of \r, \r\n, \n
- # The decoder ensures that \r\n are not split in two pieces
-
- # In C we'd look for these in parallel of course.
- nlpos = line.find("\n", start)
- crpos = line.find("\r", start)
- if crpos == -1:
- if nlpos == -1:
- # Nothing found
- start = len(line)
- else:
- # Found \n
- endpos = nlpos + 1
- break
- elif nlpos == -1:
- # Found lone \r
- endpos = crpos + 1
- break
- elif nlpos < crpos:
- # Found \n
- endpos = nlpos + 1
- break
- elif nlpos == crpos + 1:
- # Found \r\n
- endpos = crpos + 2
- break
- else:
- # Found \r
- endpos = crpos + 1
- break
- else:
- # non-universal
- pos = line.find(self._readnl)
- if pos >= 0:
- endpos = pos + len(self._readnl)
- break
-
- if limit >= 0 and len(line) >= limit:
- endpos = limit # reached length limit
- break
-
- # No line ending seen yet - get more data
- more_line = ''
- while self._read_chunk():
- if self._decoded_chars:
- break
- if self._decoded_chars:
- line += self._get_decoded_chars()
- else:
- # end of file
- self._set_decoded_chars('')
- self._snapshot = None
- return line
-
- if limit >= 0 and endpos > limit:
- endpos = limit # don't exceed limit
-
- # Rewind _decoded_chars to just after the line ending we found.
- self._rewind_decoded_chars(len(line) - endpos)
- return line[:endpos]
-
- @property
- def newlines(self):
- return self._decoder.newlines if self._decoder else None
-
-StringIO = _io.StringIO
-class unused_StringIO(unused_TextIOWrapper):
- """Text I/O implementation using an in-memory buffer.
-
- The initial_value argument sets the value of object. The newline
- argument is like the one of TextIOWrapper's constructor.
- """
-
- # XXX This is really slow, but fully functional
-
- def __init__(self, initial_value="", newline="\n"):
- super(unused_StringIO, self).__init__(BytesIO(),
- encoding="utf-8",
- errors="strict",
- newline=newline)
- if initial_value:
- if not isinstance(initial_value, str):
- initial_value = str(initial_value)
- self.write(initial_value)
- self.seek(0)
-
- def getvalue(self):
- self.flush()
- return self.buffer.getvalue().decode(self._encoding, self._errors)
-
-
-# make test_memoryio happy!
-_BytesIO = BytesIO
-_StringIO = StringIO
Modified: python/branches/io-c/Lib/test/test_io.py
==============================================================================
--- python/branches/io-c/Lib/test/test_io.py	(original)
+++ python/branches/io-c/Lib/test/test_io.py	Sat Feb 21 21:05:40 2009
@@ -14,7 +14,8 @@
 from test import support
 
 import codecs
-import io # The module under test
+import io # C implementation of io
+import _pyio as pyio # Python implementation of io
 
 
 def _default_chunk_size():
@@ -23,7 +24,7 @@
 return f._CHUNK_SIZE
 
 
-class MockRawIO(io.RawIOBase):
+class MockRawIO:
 
 def __init__(self, read_stack=()):
 self._read_stack = list(read_stack)
@@ -82,13 +83,19 @@
 def truncate(self, pos=None):
 return pos
 
+class CMockRawIO(MockRawIO, io.RawIOBase):
+ pass
+
+class PyMockRawIO(MockRawIO, pyio.RawIOBase):
+ pass
+
 
 class MisbehavedRawIO(MockRawIO):
 def write(self, b):
- return MockRawIO.write(self, b) * 2
+ return super().write(b) * 2
 
 def read(self, n=None):
- return MockRawIO.read(self, n) * 2
+ return super().read(n) * 2
 
 def seek(self, pos, whence):
 return -123
@@ -97,33 +104,52 @@
 return -456
 
 def readinto(self, buf):
- MockRawIO.readinto(self, buf)
+ super().readinto(buf)
 return len(buf) * 5
 
+class CMisbehavedRawIO(MisbehavedRawIO, io.RawIOBase):
+ pass
+
+class PyMisbehavedRawIO(MisbehavedRawIO, pyio.RawIOBase):
+ pass
+
 
 class CloseFailureIO(MockRawIO):
 
 def close(self):
 raise IOError
 
+class CCloseFailureIO(CloseFailureIO, io.RawIOBase):
+ pass
+
+class PyCloseFailureIO(CloseFailureIO, pyio.RawIOBase):
+ pass
 
-class MockFileIO(io.BytesIO):
+
+class MockFileIO:
 
 def __init__(self, data):
 self.read_history = []
- io.BytesIO.__init__(self, data)
+ super().__init__(data)
 
 def read(self, n=None):
- res = io.BytesIO.read(self, n)
+ res = super().read(n)
 self.read_history.append(None if res is None else len(res))
 return res
 
 def readinto(self, b):
- res = io.BytesIO.readinto(self, b)
+ res = super().readinto(b)
 self.read_history.append(res)
 return res
 
-class MockNonBlockWriterIO(io.RawIOBase):
+class CMockFileIO(MockFileIO, io.BytesIO):
+ pass
+
+class PyMockFileIO(MockFileIO, pyio.BytesIO):
+ pass
+
+
+class MockNonBlockWriterIO:
 
 def __init__(self):
 self._write_stack = []
@@ -158,10 +184,16 @@
 else:
 self._blocker_char = None
 self._write_stack.append(b[:n])
- raise io.BlockingIOError(0, "test blocking", n)
+ raise self.BlockingIOError(0, "test blocking", n)
 self._write_stack.append(b)
 return len(b)
 
+class CMockNonBlockWriterIO(MockNonBlockWriterIO, io.RawIOBase):
+ BlockingIOError = io.BlockingIOError
+
+class PyMockNonBlockWriterIO(MockNonBlockWriterIO, pyio.RawIOBase):
+ BlockingIOError = pyio.BlockingIOError
+
 
 class IOTest(unittest.TestCase):
 
@@ -235,13 +267,13 @@
 self.assertEqual(f.read(2), b"x")
 
 def test_raw_file_io(self):
- f = io.open(support.TESTFN, "wb", buffering=0)
+ f = self.open(support.TESTFN, "wb", buffering=0)
 self.assertEqual(f.readable(), False)
 self.assertEqual(f.writable(), True)
 self.assertEqual(f.seekable(), True)
 self.write_ops(f)
 f.close()
- f = io.open(support.TESTFN, "rb", buffering=0)
+ f = self.open(support.TESTFN, "rb", buffering=0)
 self.assertEqual(f.readable(), True)
 self.assertEqual(f.writable(), False)
 self.assertEqual(f.seekable(), True)
@@ -249,13 +281,13 @@
 f.close()
 
 def test_buffered_file_io(self):
- f = io.open(support.TESTFN, "wb")
+ f = self.open(support.TESTFN, "wb")
 self.assertEqual(f.readable(), False)
 self.assertEqual(f.writable(), True)
 self.assertEqual(f.seekable(), True)
 self.write_ops(f)
 f.close()
- f = io.open(support.TESTFN, "rb")
+ f = self.open(support.TESTFN, "rb")
 self.assertEqual(f.readable(), True)
 self.assertEqual(f.writable(), False)
 self.assertEqual(f.seekable(), True)
@@ -266,7 +298,7 @@
 f = io.open(support.TESTFN, "wb")
 f.write(b"abc\ndef\nxyzzy\nfoo\x00bar\nanother line")
 f.close()
- f = io.open(support.TESTFN, "rb")
+ f = self.open(support.TESTFN, "rb")
 self.assertEqual(f.readline(), b"abc\n")
 self.assertEqual(f.readline(10), b"def\n")
 self.assertEqual(f.readline(2), b"xy")
@@ -276,11 +308,11 @@
 f.close()
 
 def test_raw_bytes_io(self):
- f = io.BytesIO()
+ f = self.BytesIO()
 self.write_ops(f)
 data = f.getvalue()
 self.assertEqual(data, b"hello world\n")
- f = io.BytesIO(data)
+ f = self.BytesIO(data)
 self.read_ops(f, True)
 
 def test_large_file_ops(self):
@@ -296,10 +328,10 @@
 print("Use 'regrtest.py -u largefile test_io' to run it.",
 file=sys.stderr)
 return
- f = io.open(support.TESTFN, "w+b", 0)
+ f = self.open(support.TESTFN, "w+b", 0)
 self.large_file_ops(f)
 f.close()
- f = io.open(support.TESTFN, "w+b")
+ f = self.open(support.TESTFN, "w+b")
 self.large_file_ops(f)
 f.close()
 
@@ -320,32 +352,32 @@
 
 # issue 5008
 def test_append_mode_tell(self):
- with io.open(support.TESTFN, "wb") as f:
+ with self.open(support.TESTFN, "wb") as f:
 f.write(b"xxx")
- with io.open(support.TESTFN, "ab", buffering=0) as f:
+ with self.open(support.TESTFN, "ab", buffering=0) as f:
 self.assertEqual(f.tell(), 3)
- with io.open(support.TESTFN, "ab") as f:
+ with self.open(support.TESTFN, "ab") as f:
 self.assertEqual(f.tell(), 3)
- with io.open(support.TESTFN, "a") as f:
+ with self.open(support.TESTFN, "a") as f:
 self.assert_(f.tell() > 0)
 
 def test_destructor(self):
 record = []
- class MyFileIO(io.FileIO):
+ class MyFileIO(self.FileIO):
 def __del__(self):
 record.append(1)
 try:
- f = io.FileIO.__del__
+ f = super().__del__
 except AttributeError:
 pass
 else:
- f(self)
+ f()
 def close(self):
 record.append(2)
- io.FileIO.close(self)
+ super().close()
 def flush(self):
 record.append(3)
- io.FileIO.flush(self)
+ super().flush()
 f = MyFileIO(support.TESTFN, "wb")
 f.write(b"xxx")
 del f
@@ -353,54 +385,54 @@
 
 def test_IOBase_destructor(self):
 record = []
- class MyIO(io.IOBase):
+ class MyIO(self.IOBase):
 def __init__(self):
 pass
 def __del__(self):
 record.append(1)
 try:
- f = io.IOBase.__del__
+ f = super().__del__
 except AttributeError:
 pass
 else:
- f(self)
+ f()
 def close(self):
 record.append(2)
- io.IOBase.close(self)
+ super().close()
 def flush(self):
 record.append(3)
- io.IOBase.flush(self)
+ super().flush()
 f = MyIO()
 del f
 self.assertEqual(record, [1, 2, 3])
 
 def test_close_flushes(self):
- f = io.open(support.TESTFN, "wb")
+ f = self.open(support.TESTFN, "wb")
 f.write(b"xxx")
 f.close()
- f = io.open(support.TESTFN, "rb")
+ f = self.open(support.TESTFN, "rb")
 self.assertEqual(f.read(), b"xxx")
 f.close()
 
 def test_array_writes(self):
 a = array.array('i', range(10))
 n = len(a.tostring())
- f = io.open(support.TESTFN, "wb", 0)
+ f = self.open(support.TESTFN, "wb", 0)
 self.assertEqual(f.write(a), n)
 f.close()
- f = io.open(support.TESTFN, "wb")
+ f = self.open(support.TESTFN, "wb")
 self.assertEqual(f.write(a), n)
 f.close()
 
 def test_closefd(self):
- self.assertRaises(ValueError, io.open, support.TESTFN, 'w',
+ self.assertRaises(ValueError, self.open, support.TESTFN, 'w',
 closefd=False)
 
 def testReadClosed(self):
- with io.open(support.TESTFN, "w") as f:
+ with self.open(support.TESTFN, "w") as f:
 f.write("egg\n")
- with io.open(support.TESTFN, "r") as f:
- file = io.open(f.fileno(), "r", closefd=False)
+ with self.open(support.TESTFN, "r") as f:
+ file = self.open(f.fileno(), "r", closefd=False)
 self.assertEqual(file.read(), "egg\n")
 file.seek(0)
 file.close()
@@ -408,20 +440,20 @@
 
 def test_no_closefd_with_filename(self):
 # can't use closefd in combination with a file name
- self.assertRaises(ValueError, io.open, support.TESTFN, "r", closefd=False)
+ self.assertRaises(ValueError, self.open, support.TESTFN, "r", closefd=False)
 
 def test_closefd_attr(self):
- with io.open(support.TESTFN, "wb") as f:
+ with self.open(support.TESTFN, "wb") as f:
 f.write(b"egg\n")
- with io.open(support.TESTFN, "r") as f:
+ with self.open(support.TESTFN, "r") as f:
 self.assertEqual(f.buffer.raw.closefd, True)
- file = io.open(f.fileno(), "r", closefd=False)
+ file = self.open(f.fileno(), "r", closefd=False)
 self.assertEqual(file.buffer.raw.closefd, False)
 
 def test_garbage_collection(self):
 # FileIO objects are collected, and collecting them flushes
 # all data to disk.
- f = io.FileIO(support.TESTFN, "wb")
+ f = self.FileIO(support.TESTFN, "wb")
 f.write(b"abcxxx")
 f.f = f
 wr = weakref.ref(f)
@@ -431,71 +463,24 @@
 with open(support.TESTFN, "rb") as f:
 self.assertEqual(f.read(), b"abcxxx")
 
-
-class MemorySeekTestMixin:
-
- def testInit(self):
- buf = self.buftype("1234567890")
- bytesIo = self.ioclass(buf)
-
- def testRead(self):
- buf = self.buftype("1234567890")
- bytesIo = self.ioclass(buf)
-
- self.assertEquals(buf[:1], bytesIo.read(1))
- self.assertEquals(buf[1:5], bytesIo.read(4))
- self.assertEquals(buf[5:], bytesIo.read(900))
- self.assertEquals(self.EOF, bytesIo.read())
-
- def testReadNoArgs(self):
- buf = self.buftype("1234567890")
- bytesIo = self.ioclass(buf)
-
- self.assertEquals(buf, bytesIo.read())
- self.assertEquals(self.EOF, bytesIo.read())
-
- def testSeek(self):
- buf = self.buftype("1234567890")
- bytesIo = self.ioclass(buf)
-
- bytesIo.read(5)
- bytesIo.seek(0)
- self.assertEquals(buf, bytesIo.read())
-
- bytesIo.seek(3)
- self.assertEquals(buf[3:], bytesIo.read())
- self.assertRaises(TypeError, bytesIo.seek, 0.0)
-
- def testTell(self):
- buf = self.buftype("1234567890")
- bytesIo = self.ioclass(buf)
-
- self.assertEquals(0, bytesIo.tell())
- bytesIo.seek(5)
- self.assertEquals(5, bytesIo.tell())
- bytesIo.seek(10000)
- self.assertEquals(10000, bytesIo.tell())
-
-
-class BytesIOTest(MemorySeekTestMixin, unittest.TestCase):
- @staticmethod
- def buftype(s):
- return s.encode("utf-8")
- ioclass = io.BytesIO
- EOF = b""
-
-
-class StringIOTest(MemorySeekTestMixin, unittest.TestCase):
- buftype = str
- ioclass = io.StringIO
- EOF = ""
+class CIOTest(IOTest):
+ open = io.open
+ IOBase = io.IOBase
+ BytesIO = io.BytesIO
+ FileIO = io.FileIO
+
+class PyIOTest(IOTest):
+ open = staticmethod(pyio.open)
+ IOBase = pyio.IOBase
+ BytesIO = pyio.BytesIO
+ FileIO = pyio.FileIO
 
 
 class CommonBufferedTests:
 # Tests common to BufferedReader, BufferedWriter and BufferedRandom
 
 def testFileno(self):
- rawio = MockRawIO()
+ rawio = self.MockRawIO()
 bufio = self.tp(rawio)
 
 self.assertEquals(42, bufio.fileno())
@@ -506,7 +491,7 @@
 pass
 
 def testInvalidArgs(self):
- rawio = MockRawIO()
+ rawio = self.MockRawIO()
 bufio = self.tp(rawio)
 # Invalid whence
 self.assertRaises(ValueError, bufio.seek, 0, -1)
@@ -519,18 +504,18 @@
 def __del__(self):
 record.append(1)
 try:
- f = tp.__del__
+ f = super().__del__
 except AttributeError:
 pass
 else:
- f(self)
+ f()
 def close(self):
 record.append(2)
- tp.close(self)
+ super().close()
 def flush(self):
 record.append(3)
- tp.flush(self)
- rawio = MockRawIO()
+ super().flush()
+ rawio = self.MockRawIO()
 bufio = MyBufferedIO(rawio)
 writable = bufio.writable()
 del bufio
@@ -541,7 +526,7 @@
 
 def testContext(self):
 # Test usability as a context manager
- rawio = MockRawIO()
+ rawio = self.MockRawIO()
 bufio = self.tp(rawio)
 def _with():
 with bufio:
@@ -561,11 +546,10 @@
 
 
 class BufferedReaderTest(unittest.TestCase, CommonBufferedTests):
- tp = io.BufferedReader
 read_mode = "rb"
 
 def testConstructor(self):
- rawio = MockRawIO([b"abc"])
+ rawio = self.MockRawIO([b"abc"])
 bufio = self.tp(rawio)
 bufio.__init__(rawio)
 bufio.__init__(rawio, buffer_size=1024)
@@ -582,19 +566,19 @@
 # than 2GB RAM and a 64-bit kernel.
 self.assertRaises((OverflowError, MemoryError, ValueError),
 bufio.__init__, rawio, sys.maxsize)
- rawio = MockRawIO([b"abc"])
+ rawio = self.MockRawIO([b"abc"])
 bufio.__init__(rawio)
 self.assertEquals(b"abc", bufio.read())
 
 def testRead(self):
- rawio = MockRawIO((b"abc", b"d", b"efg"))
+ rawio = self.MockRawIO((b"abc", b"d", b"efg"))
 bufio = self.tp(rawio)
 self.assertEquals(b"abcdef", bufio.read(6))
 # Invalid args
 self.assertRaises(ValueError, bufio.read, -2)
 
 def testRead1(self):
- rawio = MockRawIO((b"abc", b"d", b"efg"))
+ rawio = self.MockRawIO((b"abc", b"d", b"efg"))
 bufio = self.tp(rawio)
 self.assertEquals(b"a", bufio.read(1))
 self.assertEquals(b"b", bufio.read1(1))
@@ -610,7 +594,7 @@
 self.assertRaises(ValueError, bufio.read1, -1)
 
 def testReadinto(self):
- rawio = MockRawIO((b"abc", b"d", b"efg"))
+ rawio = self.MockRawIO((b"abc", b"d", b"efg"))
 bufio = self.tp(rawio)
 b = bytearray(2)
 self.assertEquals(bufio.readinto(b), 2)
@@ -635,7 +619,7 @@
 ]
 
 for bufsize, buf_read_sizes, raw_read_sizes in tests:
- rawio = MockFileIO(data)
+ rawio = self.MockFileIO(data)
 bufio = self.tp(rawio, buffer_size=bufsize)
 pos = 0
 for nbytes in buf_read_sizes:
@@ -646,7 +630,7 @@
 
 def testReadNonBlocking(self):
 # Inject some None's in there to simulate EWOULDBLOCK
- rawio = MockRawIO((b"abc", b"d", None, b"efg", None, None, None))
+ rawio = self.MockRawIO((b"abc", b"d", None, b"efg", None, None, None))
 bufio = self.tp(rawio)
 
 self.assertEquals(b"abcd", bufio.read(6))
@@ -657,13 +641,13 @@
 self.assertEquals(b"", bufio.read())
 
 def testReadToEof(self):
- rawio = MockRawIO((b"abc", b"d", b"efg"))
+ rawio = self.MockRawIO((b"abc", b"d", b"efg"))
 bufio = self.tp(rawio)
 
 self.assertEquals(b"abcdefg", bufio.read(9000))
 
 def testReadNoArgs(self):
- rawio = MockRawIO((b"abc", b"d", b"efg"))
+ rawio = self.MockRawIO((b"abc", b"d", b"efg"))
 bufio = self.tp(rawio)
 
 self.assertEquals(b"abcdefg", bufio.read())
@@ -711,7 +695,7 @@
 support.unlink(support.TESTFN)
 
 def testMisbehavedRawIO(self):
- rawio = MisbehavedRawIO((b"abc", b"d", b"efg"))
+ rawio = self.MisbehavedRawIO((b"abc", b"d", b"efg"))
 bufio = self.tp(rawio)
 self.assertRaises(IOError, bufio.seek, 0)
 self.assertRaises(IOError, bufio.tell)
@@ -719,7 +703,7 @@
 
 def test_garbage_collection(self):
 # BufferedReader objects are collected
- rawio = io.FileIO(support.TESTFN, "w+b")
+ rawio = self.FileIO(support.TESTFN, "w+b")
 f = self.tp(rawio)
 f.f = f
 wr = weakref.ref(f)
@@ -727,13 +711,28 @@
 gc.collect()
 self.assert_(wr() is None, wr)
 
+class CBufferedReaderTest(BufferedReaderTest):
+ tp = io.BufferedReader
+ BlockingIOError = io.BlockingIOError
+ FileIO = io.FileIO
+ MisbehavedRawIO = CMisbehavedRawIO
+ MockRawIO = CMockRawIO
+ MockFileIO = CMockFileIO
+
+class PyBufferedReaderTest(BufferedReaderTest):
+ tp = pyio.BufferedReader
+ BlockingIOError = pyio.BlockingIOError
+ FileIO = pyio.FileIO
+ MisbehavedRawIO = PyMisbehavedRawIO
+ MockRawIO = PyMockRawIO
+ MockFileIO = PyMockFileIO
+
 
 class BufferedWriterTest(unittest.TestCase, CommonBufferedTests):
- tp = io.BufferedWriter
 write_mode = "wb"
 
 def testConstructor(self):
- rawio = MockRawIO()
+ rawio = self.MockRawIO()
 bufio = self.tp(rawio)
 bufio.__init__(rawio)
 bufio.__init__(rawio, buffer_size=1024)
@@ -758,13 +757,13 @@
 
 def testWrite(self):
 # Write to the buffered IO but don't overflow the buffer.
- writer = MockRawIO()
+ writer = self.MockRawIO()
 bufio = self.tp(writer, 8)
 bufio.write(b"abc")
 self.assertFalse(writer._write_stack)
 
 def testWriteOverflow(self):
- writer = MockRawIO()
+ writer = self.MockRawIO()
 bufio = self.tp(writer, 8)
 contents = b"abcdefghijklmnop"
 for n in range(0, len(contents), 3):
@@ -778,7 +777,7 @@
 # Lots of writes, test the flushed output is as expected.
 contents = bytes(range(256)) * 1000
 n = 0
- writer = MockRawIO()
+ writer = self.MockRawIO()
 bufio = self.tp(writer, 13)
 # Generator of write sizes: repeat each N 15 times then proceed to N+1
 def gen_sizes():
@@ -818,7 +817,7 @@
 self.check_writes(lambda bufio: bufio.truncate(bufio.tell()))
 
 def testWriteNonBlocking(self):
- raw = MockNonBlockWriterIO()
+ raw = self.MockNonBlockWriterIO()
 bufio = self.tp(raw, 8, 8)
 
 self.assertEquals(bufio.write(b"abcd"), 4)
@@ -831,7 +830,7 @@
 raw.block_on(b"0")
 try:
 bufio.write(b"opqrwxyz0123456789")
- except io.BlockingIOError as e:
+ except self.BlockingIOError as e:
 written = e.characters_written
 else:
 self.fail("BlockingIOError should have been raised")
@@ -858,14 +857,14 @@
 self.assertEqual(raw.getvalue(), b"XYcdef123456")
 
 def testFlush(self):
- writer = MockRawIO()
+ writer = self.MockRawIO()
 bufio = self.tp(writer, 8)
 bufio.write(b"abc")
 bufio.flush()
 self.assertEquals(b"abc", writer._write_stack[0])
 
 def testDestructor(self):
- writer = MockRawIO()
+ writer = self.MockRawIO()
 bufio = self.tp(writer, 8)
 bufio.write(b"abc")
 del bufio
@@ -931,7 +930,7 @@
 support.unlink(support.TESTFN)
 
 def testMisbehavedRawIO(self):
- rawio = MisbehavedRawIO()
+ rawio = self.MisbehavedRawIO()
 bufio = self.tp(rawio, 5)
 self.assertRaises(IOError, bufio.seek, 0)
 self.assertRaises(IOError, bufio.tell)
@@ -940,7 +939,7 @@
 def test_garbage_collection(self):
 # BufferedWriter objects are collected, and collecting them flushes
 # all data to disk.
- rawio = io.FileIO(support.TESTFN, "w+b")
+ rawio = self.FileIO(support.TESTFN, "w+b")
 f = self.tp(rawio)
 f.write(b"123xxx")
 f.x = f
@@ -951,20 +950,43 @@
 with open(support.TESTFN, "rb") as f:
 self.assertEqual(f.read(), b"123xxx")
 
+class CBufferedWriterTest(BufferedWriterTest):
+ tp = io.BufferedWriter
+ BlockingIOError = io.BlockingIOError
+ FileIO = io.FileIO
+ MockRawIO = CMockRawIO
+ MisbehavedRawIO = CMisbehavedRawIO
+ MockNonBlockWriterIO = CMockNonBlockWriterIO
+
+class PyBufferedWriterTest(BufferedWriterTest):
+ tp = pyio.BufferedWriter
+ BlockingIOError = pyio.BlockingIOError
+ FileIO = pyio.FileIO
+ MockRawIO = PyMockRawIO
+ MisbehavedRawIO = PyMisbehavedRawIO
+ MockNonBlockWriterIO = PyMockNonBlockWriterIO
+
 
 class BufferedRWPairTest(unittest.TestCase):
 
 def testRWPair(self):
- r = MockRawIO(())
- w = MockRawIO()
- pair = io.BufferedRWPair(r, w)
+ r = self.MockRawIO(())
+ w = self.MockRawIO()
+ pair = self.tp(r, w)
 self.assertFalse(pair.closed)
 
 # XXX More Tests
 
+class CBufferedRWPairTest(BufferedRWPairTest):
+ tp = io.BufferedRWPair
+ MockRawIO = CMockRawIO
+
+class PyBufferedRWPairTest(BufferedRWPairTest):
+ tp = pyio.BufferedRWPair
+ MockRawIO = PyMockRawIO
+
 
 class BufferedRandomTest(BufferedReaderTest, BufferedWriterTest):
- tp = io.BufferedRandom
 read_mode = "rb+"
 write_mode = "wb+"
 
@@ -973,7 +995,7 @@
 BufferedWriterTest.testConstructor(self)
 
 def testReadAndWrite(self):
- raw = MockRawIO((b"asdf", b"ghjk"))
+ raw = self.MockRawIO((b"asdf", b"ghjk"))
 rw = self.tp(raw, 8, 12)
 
 self.assertEqual(b"as", rw.read(2))
@@ -1095,6 +1117,24 @@
 BufferedReaderTest.test_garbage_collection(self)
 BufferedWriterTest.test_garbage_collection(self)
 
+class CBufferedRandomTest(BufferedRandomTest):
+ tp = io.BufferedRandom
+ BlockingIOError = io.BlockingIOError
+ FileIO = io.FileIO
+ MockRawIO = CMockRawIO
+ MockFileIO = CMockFileIO
+ MisbehavedRawIO = CMisbehavedRawIO
+ MockNonBlockWriterIO = CMockNonBlockWriterIO
+
+class PyBufferedRandomTest(BufferedRandomTest):
+ tp = pyio.BufferedRandom
+ BlockingIOError = pyio.BlockingIOError
+ FileIO = pyio.FileIO
+ MockRawIO = PyMockRawIO
+ MockFileIO = PyMockFileIO
+ MisbehavedRawIO = PyMisbehavedRawIO
+ MockNonBlockWriterIO = PyMockNonBlockWriterIO
+
 
 # To fully exercise seek/tell, the StatefulIncrementalDecoder has these
 # properties:
@@ -1251,9 +1291,9 @@
 support.unlink(support.TESTFN)
 
 def testConstructor(self):
- r = io.BytesIO(b"\xc3\xa9\n\n")
- b = io.BufferedReader(r, 1000)
- t = io.TextIOWrapper(b)
+ r = self.BytesIO(b"\xc3\xa9\n\n")
+ b = self.BufferedReader(r, 1000)
+ t = self.TextIOWrapper(b)
 t.__init__(b, encoding="latin1", newline="\r\n")
 self.assertEquals(t.encoding, "latin1")
 self.assertEquals(t.line_buffering, False)
@@ -1267,9 +1307,9 @@
 self.assertRaises(ValueError, t.read)
 
 def testLineBuffering(self):
- r = io.BytesIO()
- b = io.BufferedWriter(r, 1000)
- t = io.TextIOWrapper(b, newline="\n", line_buffering=True)
+ r = self.BytesIO()
+ b = self.BufferedWriter(r, 1000)
+ t = self.TextIOWrapper(b, newline="\n", line_buffering=True)
 t.write("X")
 self.assertEquals(r.getvalue(), b"") # No flush happened
 t.write("Y\nZ")
@@ -1279,50 +1319,50 @@
 
 def testEncoding(self):
 # Check the encoding attribute is always set, and valid
- b = io.BytesIO()
- t = io.TextIOWrapper(b, encoding="utf8")
+ b = self.BytesIO()
+ t = self.TextIOWrapper(b, encoding="utf8")
 self.assertEqual(t.encoding, "utf8")
- t = io.TextIOWrapper(b)
+ t = self.TextIOWrapper(b)
 self.assert_(t.encoding is not None)
 codecs.lookup(t.encoding)
 
 def testEncodingErrorsReading(self):
 # (1) default
- b = io.BytesIO(b"abc\n\xff\n")
- t = io.TextIOWrapper(b, encoding="ascii")
+ b = self.BytesIO(b"abc\n\xff\n")
+ t = self.TextIOWrapper(b, encoding="ascii")
 self.assertRaises(UnicodeError, t.read)
 # (2) explicit strict
- b = io.BytesIO(b"abc\n\xff\n")
- t = io.TextIOWrapper(b, encoding="ascii", errors="strict")
+ b = self.BytesIO(b"abc\n\xff\n")
+ t = self.TextIOWrapper(b, encoding="ascii", errors="strict")
 self.assertRaises(UnicodeError, t.read)
 # (3) ignore
- b = io.BytesIO(b"abc\n\xff\n")
- t = io.TextIOWrapper(b, encoding="ascii", errors="ignore")
+ b = self.BytesIO(b"abc\n\xff\n")
+ t = self.TextIOWrapper(b, encoding="ascii", errors="ignore")
 self.assertEquals(t.read(), "abc\n\n")
 # (4) replace
- b = io.BytesIO(b"abc\n\xff\n")
- t = io.TextIOWrapper(b, encoding="ascii", errors="replace")
+ b = self.BytesIO(b"abc\n\xff\n")
+ t = self.TextIOWrapper(b, encoding="ascii", errors="replace")
 self.assertEquals(t.read(), "abc\n\ufffd\n")
 
 def testEncodingErrorsWriting(self):
 # (1) default
- b = io.BytesIO()
- t = io.TextIOWrapper(b, encoding="ascii")
+ b = self.BytesIO()
+ t = self.TextIOWrapper(b, encoding="ascii")
 self.assertRaises(UnicodeError, t.write, "\xff")
 # (2) explicit strict
- b = io.BytesIO()
- t = io.TextIOWrapper(b, encoding="ascii", errors="strict")
+ b = self.BytesIO()
+ t = self.TextIOWrapper(b, encoding="ascii", errors="strict")
 self.assertRaises(UnicodeError, t.write, "\xff")
 # (3) ignore
- b = io.BytesIO()
- t = io.TextIOWrapper(b, encoding="ascii", errors="ignore",
+ b = self.BytesIO()
+ t = self.TextIOWrapper(b, encoding="ascii", errors="ignore",
 newline="\n")
 t.write("abc\xffdef\n")
 t.flush()
 self.assertEquals(b.getvalue(), b"abcdef\n")
 # (4) replace
- b = io.BytesIO()
- t = io.TextIOWrapper(b, encoding="ascii", errors="replace",
+ b = self.BytesIO()
+ t = self.TextIOWrapper(b, encoding="ascii", errors="replace",
 newline="\n")
 t.write("abc\xffdef\n")
 t.flush()
@@ -1352,8 +1392,8 @@
 for do_reads in (False, True):
 for bufsize in range(1, 10):
 for newline, exp_lines in tests:
- bufio = io.BufferedReader(io.BytesIO(data), bufsize)
- textio = io.TextIOWrapper(bufio, newline=newline,
+ bufio = self.BufferedReader(self.BytesIO(data), bufsize)
+ textio = self.TextIOWrapper(bufio, newline=newline,
 encoding=encoding)
 if do_reads:
 got_lines = []
@@ -1380,8 +1420,8 @@
 ("\r\n", ["AAA\nBB\x00B\nCCC\rDDD\rEEE\r\n", "FFF\r\n", "GGG"]),
 ("\r", ["AAA\nBB\x00B\nCCC\r", "DDD\r", "EEE\r", "\nFFF\r", "\nGGG"]),
 ]:
- buf = io.BytesIO(testdata)
- txt = io.TextIOWrapper(buf, encoding="ascii", newline=newline)
+ buf = self.BytesIO(testdata)
+ txt = self.TextIOWrapper(buf, encoding="ascii", newline=newline)
 self.assertEquals(txt.readlines(), expected)
 txt.seek(0)
 self.assertEquals(txt.read(), "".join(expected))
@@ -1395,8 +1435,8 @@
 }
 tests = [(None, testdict[os.linesep])] + sorted(testdict.items())
 for newline, expected in tests:
- buf = io.BytesIO()
- txt = io.TextIOWrapper(buf, encoding="ascii", newline=newline)
+ buf = self.BytesIO()
+ txt = self.TextIOWrapper(buf, encoding="ascii", newline=newline)
 txt.write("AAA\nB")
 txt.write("BB\nCCC\n")
 txt.write("X\rY\r\nZ")
@@ -1406,34 +1446,34 @@
 
 def testDestructor(self):
 l = []
- class MyBytesIO(io.BytesIO):
+ class MyBytesIO(self.BytesIO):
 def close(self):
 l.append(self.getvalue())
- io.BytesIO.close(self)
+ self.BytesIO.close(self)
 b = MyBytesIO()
- t = io.TextIOWrapper(b, encoding="ascii")
+ t = self.TextIOWrapper(b, encoding="ascii")
 t.write("abc")
 del t
 self.assertEquals([b"abc"], l)
 
 def testOverrideDestructor(self):
 record = []
- class MyTextIO(io.TextIOWrapper):
+ class MyTextIO(self.TextIOWrapper):
 def __del__(self):
 record.append(1)
 try:
- f = io.TextIOWrapper.__del__
+ f = super().__del__
 except AttributeError:
 pass
 else:
- f(self)
+ f()
 def close(self):
 record.append(2)
- io.TextIOWrapper.close(self)
+ super().close()
 def flush(self):
 record.append(3)
- io.TextIOWrapper.flush(self)
- b = io.BytesIO()
+ super().flush()
+ b = self.BytesIO()
 t = MyTextIO(b, encoding="ascii")
 del t
 self.assertEqual(record, [1, 2, 3])
@@ -1443,15 +1483,15 @@
 # even if close() fails.
 rawio = CloseFailureIO()
 def f():
- io.TextIOWrapper(rawio).xyzzy
+ self.TextIOWrapper(rawio).xyzzy
 self.assertRaises(AttributeError, f)
 
 def test_garbage_collection(self):
 # TextIOWrapper objects are collected, and collecting them flushes
 # all data to disk.
 rawio = io.FileIO(support.TESTFN, "wb")
- b = io.BufferedWriter(rawio)
- t = io.TextIOWrapper(b, encoding="ascii")
+ b = self.BufferedWriter(rawio)
+ t = self.TextIOWrapper(b, encoding="ascii")
 t.write("456def")
 t.x = t
 wr = weakref.ref(t)
@@ -1466,11 +1506,11 @@
 def testBasicIO(self):
 for chunksize in (1, 2, 3, 4, 5, 15, 16, 17, 31, 32, 33, 63, 64, 65):
 for enc in "ascii", "latin1", "utf8" :# , "utf-16-be", "utf-16-le":
- f = io.open(support.TESTFN, "w+", encoding=enc)
+ f = self.open(support.TESTFN, "w+", encoding=enc)
 f._CHUNK_SIZE = chunksize
 self.assertEquals(f.write("abc"), 3)
 f.close()
- f = io.open(support.TESTFN, "r+", encoding=enc)
+ f = self.open(support.TESTFN, "r+", encoding=enc)
 f._CHUNK_SIZE = chunksize
 self.assertEquals(f.tell(), 0)
 self.assertEquals(f.read(), "abc")
@@ -1513,7 +1553,7 @@
 self.assertEquals(rlines, wlines)
 
 def testTelling(self):
- f = io.open(support.TESTFN, "w+", encoding="utf8")
+ f = self.open(support.TESTFN, "w+", encoding="utf8")
 p0 = f.tell()
 f.write("\xff\n")
 p1 = f.tell()
@@ -1541,10 +1581,10 @@
 u_suffix = "\u8888\n"
 suffix = bytes(u_suffix.encode("utf-8"))
 line = prefix + suffix
- f = io.open(support.TESTFN, "wb")
+ f = self.open(support.TESTFN, "wb")
 f.write(line*2)
 f.close()
- f = io.open(support.TESTFN, "r", encoding="utf-8")
+ f = self.open(support.TESTFN, "r", encoding="utf-8")
 s = f.read(prefix_size)
 self.assertEquals(s, str(prefix, "ascii"))
 self.assertEquals(f.tell(), prefix_size)
@@ -1553,34 +1593,34 @@
 def testSeekingToo(self):
 # Regression test for a specific bug
 data = b'\xe0\xbf\xbf\n'
- f = io.open(support.TESTFN, "wb")
+ f = self.open(support.TESTFN, "wb")
 f.write(data)
 f.close()
- f = io.open(support.TESTFN, "r", encoding="utf-8")
+ f = self.open(support.TESTFN, "r", encoding="utf-8")
 f._CHUNK_SIZE # Just test that it exists
 f._CHUNK_SIZE = 2
 f.readline()
 f.tell()
 
 def testSeekAndTell(self):
- """Test seek/tell using the StatefulIncrementalDecoder."""
+ #Test seek/tell using the StatefulIncrementalDecoder.
 # Make test faster by doing smaller seeks
 CHUNK_SIZE = 128
 
 def testSeekAndTellWithData(data, min_pos=0):
 """Tell/seek to various points within a data stream and ensure
 that the decoded data returned by read() is consistent."""
- f = io.open(support.TESTFN, 'wb')
+ f = self.open(support.TESTFN, 'wb')
 f.write(data)
 f.close()
- f = io.open(support.TESTFN, encoding='test_decoder')
+ f = self.open(support.TESTFN, encoding='test_decoder')
 f._CHUNK_SIZE = CHUNK_SIZE
 decoded = f.read()
 f.close()
 
 for i in range(min_pos, len(decoded) + 1): # seek positions
 for j in [1, 5, len(decoded) - i]: # read lengths
- f = io.open(support.TESTFN, encoding='test_decoder')
+ f = self.open(support.TESTFN, encoding='test_decoder')
 self.assertEquals(f.read(i), decoded[:i])
 cookie = f.tell()
 self.assertEquals(f.read(j), decoded[i:i + j])
@@ -1618,8 +1658,8 @@
 "utf-32-le",
 "utf-32-be")
 for encoding in tests:
- buf = io.BytesIO()
- f = io.TextIOWrapper(buf, encoding=encoding)
+ buf = self.BytesIO()
+ f = self.TextIOWrapper(buf, encoding=encoding)
 # Check if the BOM is written only once (see issue1753).
 f.write(data)
 f.write(data)
@@ -1635,7 +1675,7 @@
 nchars = len(line)
 nbytes = len(line.encode(enc))
 for chunk_size in (32, 64, 128, 256):
- f = io.open(support.TESTFN, "w+", encoding=enc)
+ f = self.open(support.TESTFN, "w+", encoding=enc)
 f._CHUNK_SIZE = chunk_size
 t0 = timer()
 for i in range(nlines):
@@ -1665,7 +1705,7 @@
 print("Using readline()+tell(): %6.3f seconds" % (t4-t3))
 
 def testReadOneByOne(self):
- txt = io.TextIOWrapper(io.BytesIO(b"AA\r\nBB"))
+ txt = self.TextIOWrapper(self.BytesIO(b"AA\r\nBB"))
 reads = ""
 while True:
 c = txt.read(1)
@@ -1677,7 +1717,7 @@
 # read in amounts equal to TextIOWrapper._CHUNK_SIZE which is 128.
 def testReadByChunk(self):
 # make sure "\r\n" straddles 128 char boundary.
- txt = io.TextIOWrapper(io.BytesIO(b"A" * 127 + b"\r\nB"))
+ txt = self.TextIOWrapper(self.BytesIO(b"A" * 127 + b"\r\nB"))
 reads = ""
 while True:
 c = txt.read(128)
@@ -1687,7 +1727,7 @@
 self.assertEquals(reads, "A"*127+"\nB")
 
 def test_issue1395_1(self):
- txt = io.TextIOWrapper(io.BytesIO(self.testdata), encoding="ascii")
+ txt = self.TextIOWrapper(self.BytesIO(self.testdata), encoding="ascii")
 
 # read one char at a time
 reads = ""
@@ -1699,7 +1739,7 @@
 self.assertEquals(reads, self.normalized)
 
 def test_issue1395_2(self):
- txt = io.TextIOWrapper(io.BytesIO(self.testdata), encoding="ascii")
+ txt = self.TextIOWrapper(self.BytesIO(self.testdata), encoding="ascii")
 txt._CHUNK_SIZE = 4
 
 reads = ""
@@ -1711,7 +1751,7 @@
 self.assertEquals(reads, self.normalized)
 
 def test_issue1395_3(self):
- txt = io.TextIOWrapper(io.BytesIO(self.testdata), encoding="ascii")
+ txt = self.TextIOWrapper(self.BytesIO(self.testdata), encoding="ascii")
 txt._CHUNK_SIZE = 4
 
 reads = txt.read(4)
@@ -1722,7 +1762,7 @@
 self.assertEquals(reads, self.normalized)
 
 def test_issue1395_4(self):
- txt = io.TextIOWrapper(io.BytesIO(self.testdata), encoding="ascii")
+ txt = self.TextIOWrapper(self.BytesIO(self.testdata), encoding="ascii")
 txt._CHUNK_SIZE = 4
 
 reads = txt.read(4)
@@ -1730,7 +1770,7 @@
 self.assertEquals(reads, self.normalized)
 
 def test_issue1395_5(self):
- txt = io.TextIOWrapper(io.BytesIO(self.testdata), encoding="ascii")
+ txt = self.TextIOWrapper(self.BytesIO(self.testdata), encoding="ascii")
 txt._CHUNK_SIZE = 4
 
 reads = txt.read(4)
@@ -1740,11 +1780,25 @@
 self.assertEquals(txt.read(4), "BBB\n")
 
 def test_issue2282(self):
- buffer = io.BytesIO(self.testdata)
- txt = io.TextIOWrapper(buffer, encoding="ascii")
+ buffer = self.BytesIO(self.testdata)
+ txt = self.TextIOWrapper(buffer, encoding="ascii")
 
 self.assertEqual(buffer.seekable(), txt.seekable())
 
+class CTextIOWrapperTest(TextIOWrapperTest):
+ open = io.open
+ BufferedReader = io.BufferedReader
+ BufferedWriter = io.BufferedWriter
+ TextIOWrapper = io.TextIOWrapper
+ BytesIO = io.BytesIO
+
+class PyTextIOWrapperTest(TextIOWrapperTest):
+ open = staticmethod(pyio.open)
+ BufferedReader = pyio.BufferedReader
+ BufferedWriter = pyio.BufferedWriter
+ TextIOWrapper = pyio.TextIOWrapper
+ BytesIO = pyio.BytesIO
+
 
 class IncrementalNewlineDecoderTest(unittest.TestCase):
 
@@ -1833,12 +1887,18 @@
 )
 for enc in encodings:
 decoder = enc and codecs.getincrementaldecoder(enc)()
- decoder = io.IncrementalNewlineDecoder(decoder, translate=True)
+ decoder = self.IncrementalNewlineDecoder(decoder, translate=True)
 self.check_newline_decoding(decoder, enc)
 decoder = codecs.getincrementaldecoder("utf-8")()
- decoder = io.IncrementalNewlineDecoder(decoder, translate=True)
+ decoder = self.IncrementalNewlineDecoder(decoder, translate=True)
 self.check_newline_decoding_utf8(decoder)
 
+class CIncrementalNewlineDecoderTest(IncrementalNewlineDecoderTest):
+ IncrementalNewlineDecoder = io.IncrementalNewlineDecoder
+
+class PyIncrementalNewlineDecoderTest(IncrementalNewlineDecoderTest):
+ IncrementalNewlineDecoder = pyio.IncrementalNewlineDecoder
+
 
 # XXX Tests for open()
 
@@ -1848,7 +1908,7 @@
 support.unlink(support.TESTFN)
 
 def testImport__all__(self):
- for name in io.__all__:
+ for name in self.io.__all__:
 obj = getattr(io, name, None)
 self.assert_(obj is not None, name)
 if name == "open":
@@ -1856,14 +1916,14 @@
 elif "error" in name.lower():
 self.assert_(issubclass(obj, Exception), name)
 else:
- self.assert_(issubclass(obj, io.IOBase))
+ self.assert_(issubclass(obj, self.IOBase), name)
 
 def test_attributes(self):
- f = io.open(support.TESTFN, "wb", buffering=0)
+ f = self.open(support.TESTFN, "wb", buffering=0)
 self.assertEquals(f.mode, "wb")
 f.close()
 
- f = io.open(support.TESTFN, "U")
+ f = self.open(support.TESTFN, "U")
 self.assertEquals(f.name, support.TESTFN)
 self.assertEquals(f.buffer.name, support.TESTFN)
 self.assertEquals(f.buffer.raw.name, support.TESTFN)
@@ -1872,12 +1932,12 @@
 self.assertEquals(f.buffer.raw.mode, "rb")
 f.close()
 
- f = io.open(support.TESTFN, "w+")
+ f = self.open(support.TESTFN, "w+")
 self.assertEquals(f.mode, "w+")
 self.assertEquals(f.buffer.mode, "rb+") # Does it really matter?
 self.assertEquals(f.buffer.raw.mode, "rb+")
 
- g = io.open(f.fileno(), "wb", closefd=False)
+ g = self.open(f.fileno(), "wb", closefd=False)
 self.assertEquals(g.mode, "wb")
 self.assertEquals(g.raw.mode, "wb")
 self.assertEquals(g.name, f.fileno())
@@ -1903,7 +1963,7 @@
 {"mode": "w+", "buffering": 2},
 {"mode": "w+b", "buffering": 0},
 ]:
- f = io.open(support.TESTFN, **kwargs)
+ f = self.open(support.TESTFN, **kwargs)
 f.close()
 self.assertRaises(ValueError, f.flush)
 self.assertRaises(ValueError, f.fileno)
@@ -1928,16 +1988,16 @@
 
 def test_blockingioerror(self):
 # Various BlockingIOError issues
- self.assertRaises(TypeError, io.BlockingIOError)
- self.assertRaises(TypeError, io.BlockingIOError, 1)
- self.assertRaises(TypeError, io.BlockingIOError, 1, 2, 3, 4)
- self.assertRaises(TypeError, io.BlockingIOError, 1, "", None)
- b = io.BlockingIOError(1, "")
+ self.assertRaises(TypeError, self.BlockingIOError)
+ self.assertRaises(TypeError, self.BlockingIOError, 1)
+ self.assertRaises(TypeError, self.BlockingIOError, 1, 2, 3, 4)
+ self.assertRaises(TypeError, self.BlockingIOError, 1, "", None)
+ b = self.BlockingIOError(1, "")
 self.assertEqual(b.characters_written, 0)
 class C(str):
 pass
 c = C("")
- b = io.BlockingIOError(1, c)
+ b = self.BlockingIOError(1, c)
 c.b = b
 b.c = c
 wr = weakref.ref(c)
@@ -1945,13 +2005,28 @@
 gc.collect()
 self.assert_(wr() is None, wr)
 
+class CMiscIOTest(MiscIOTest):
+ io = io
+ open = io.open
+ BlockingIOError = io.BlockingIOError
+ IOBase = io.IOBase
+
+class PyMiscIOTest(MiscIOTest):
+ io = pyio
+ open = staticmethod(pyio.open)
+ BlockingIOError = pyio.BlockingIOError
+ IOBase = pyio.IOBase
+
 def test_main():
- support.run_unittest(IOTest, BytesIOTest, StringIOTest,
- BufferedReaderTest, BufferedWriterTest,
- BufferedRWPairTest, BufferedRandomTest,
+ support.run_unittest(CIOTest, PyIOTest,
+ CBufferedReaderTest, PyBufferedReaderTest,
+ CBufferedWriterTest, PyBufferedWriterTest,
+ CBufferedRWPairTest, PyBufferedRWPairTest,
+ CBufferedRandomTest, PyBufferedRandomTest,
 StatefulIncrementalDecoderTest,
- IncrementalNewlineDecoderTest,
- TextIOWrapperTest, MiscIOTest,
+ CIncrementalNewlineDecoderTest, PyIncrementalNewlineDecoderTest,
+ CTextIOWrapperTest, PyTextIOWrapperTest,
+ CMiscIOTest, PyMiscIOTest,
 )
 
 if __name__ == "__main__":
Modified: python/branches/io-c/Lib/test/test_memoryio.py
==============================================================================
--- python/branches/io-c/Lib/test/test_memoryio.py	(original)
+++ python/branches/io-c/Lib/test/test_memoryio.py	Sat Feb 21 21:05:40 2009
@@ -7,8 +7,53 @@
 from test import support
 
 import io
+import _pyio as pyio
 import sys
 
+class MemorySeekTestMixin:
+
+ def testInit(self):
+ buf = self.buftype("1234567890")
+ bytesIo = self.ioclass(buf)
+
+ def testRead(self):
+ buf = self.buftype("1234567890")
+ bytesIo = self.ioclass(buf)
+
+ self.assertEquals(buf[:1], bytesIo.read(1))
+ self.assertEquals(buf[1:5], bytesIo.read(4))
+ self.assertEquals(buf[5:], bytesIo.read(900))
+ self.assertEquals(self.EOF, bytesIo.read())
+
+ def testReadNoArgs(self):
+ buf = self.buftype("1234567890")
+ bytesIo = self.ioclass(buf)
+
+ self.assertEquals(buf, bytesIo.read())
+ self.assertEquals(self.EOF, bytesIo.read())
+
+ def testSeek(self):
+ buf = self.buftype("1234567890")
+ bytesIo = self.ioclass(buf)
+
+ bytesIo.read(5)
+ bytesIo.seek(0)
+ self.assertEquals(buf, bytesIo.read())
+
+ bytesIo.seek(3)
+ self.assertEquals(buf[3:], bytesIo.read())
+ self.assertRaises(TypeError, bytesIo.seek, 0.0)
+
+ def testTell(self):
+ buf = self.buftype("1234567890")
+ bytesIo = self.ioclass(buf)
+
+ self.assertEquals(0, bytesIo.tell())
+ bytesIo.seek(5)
+ self.assertEquals(5, bytesIo.tell())
+ bytesIo.seek(10000)
+ self.assertEquals(10000, bytesIo.tell())
+
 
 class MemoryTestMixin:
 
@@ -290,11 +335,11 @@
 self.assertEqual(test2(), buf)
 
 
-class PyBytesIOTest(MemoryTestMixin, unittest.TestCase):
+class PyBytesIOTest(MemoryTestMixin, MemorySeekTestMixin, unittest.TestCase):
 @staticmethod
 def buftype(s):
 return s.encode("ascii")
- ioclass = io.unused_BytesIO
+ ioclass = pyio.BytesIO
 EOF = b""
 
 def test_read1(self):
@@ -365,9 +410,9 @@
 self.assertEqual(memio.getvalue(), buf)
 
 
-class PyStringIOTest(MemoryTestMixin, unittest.TestCase):
+class PyStringIOTest(MemoryTestMixin, MemorySeekTestMixin, unittest.TestCase):
 buftype = str
- ioclass = io.unused_StringIO
+ ioclass = pyio.StringIO
 EOF = ""
 
 # TextIO-specific behaviour.
