Python implementation of the io module.
from __future__ import (print_function, unicode_literals)
# Import thread instead of threading to reduce startup cost
from thread import allocate_lock as Lock
from dummy_thread import allocate_lock as Lock
from io import (__all__, SEEK_SET, SEEK_CUR, SEEK_END)
# open() uses st_blksize whenever we can
DEFAULT_BUFFER_SIZE = 8 * 1024 # bytes
# NOTE: Base classes defined here are registered with the "official" ABCs
# defined in io.py. We don't use real inheritance though, because we don't want
# to inherit the C implementations.
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):
super(IOError, self).__init__(errno, strerror)
if not isinstance(characters_written, (int, long)):
raise TypeError("characters_written must be a integer")
self.characters_written = characters_written
def open(file, mode="r", buffering=-1,
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
========= ===============================================================
--------- ---------------------------------------------------------------
'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
'+' open a disk file for updating (reading and writing)
'U' universal newline mode (for backwards compatibility; unneeded
========= ===============================================================
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.
Pass 0 to switch buffering off (only allowed in binary mode), 1 to select
line buffering (only usable in text mode), and an integer > 1 to indicate
the size of a fixed-size chunk buffer. When no buffering argument is
given, the default buffering policy works as follows:
* Binary files are buffered in fixed-size chunks; the size of the buffer
is chosen using a heuristic trying to determine the underlying device's
"block size" and falling back on `io.DEFAULT_BUFFER_SIZE`.
On many systems, the buffer will typically be 4096 or 8192 bytes long.
* "Interactive" text files (files for which isatty() returns True)
use line buffering. Other text files use the policy described above
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
newline controls how universal newlines works (it only applies to text
mode). It can be None, '', '\n', '\r', and '\r\n'. It works as
* 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
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
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
if not isinstance(file, (basestring, int, long)):
raise TypeError("invalid file: %r" % file)
if not isinstance(mode, basestring):
raise TypeError("invalid mode: %r" % mode)
if not isinstance(buffering, (int, long)):
raise TypeError("invalid buffering: %r" % buffering)
if encoding is not None and not isinstance(encoding, basestring):
raise TypeError("invalid encoding: %r" % encoding)
if errors is not None and not isinstance(errors, basestring):
raise TypeError("invalid errors: %r" % errors)
if modes - set("arwb+tU") or len(mode) > len(modes):
raise ValueError("invalid mode: %r" % mode)
raise ValueError("can't use U and writing mode at once")
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")
(reading and "r" or "") +
(writing and "w" or "") +
(appending and "a" or "") +
(updating and "+" or ""),
if buffering == 1 or buffering < 0 and raw.isatty():
buffering = DEFAULT_BUFFER_SIZE
bs = os.fstat(raw.fileno()).st_blksize
except (os.error, AttributeError):
raise ValueError("invalid buffering size")
raise ValueError("can't have unbuffered text I/O")
buffer = BufferedRandom(raw, buffering)
elif writing or appending:
buffer = BufferedWriter(raw, buffering)
buffer = BufferedReader(raw, buffering)
raise ValueError("unknown mode: %r" % mode)
text = TextIOWrapper(buffer, encoding, errors, newline, line_buffering)
"""Helper for builtins.open.__doc__
def __get__(self, obj, typ):
"open(file, mode='r', buffering=-1, encoding=None, "
"errors=None, newline=None, closefd=True)\n\n" +
"""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):
__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 an IOError when operations they do not support are called.
The basic type used for binary data read from or written to a file is
the bytes type. Method arguments may also be bytearray or memoryview of
arrays of bytes. In some cases, such as readinto, a writable object such
as bytearray is required. Text I/O classes work with unicode 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
IOBase also supports the :keyword:`with` statement. In this example,
fp is closed after the suite of the with statement is complete:
with open('spam.txt', 'r') as fp:
fp.write('Spam and eggs!')
def _unsupported(self, name):
"""Internal: raise an exception for unsupported operations."""
raise UnsupportedOperation("%s.%s() not supported" %
(self.__class__.__name__, name))
def seek(self, pos, whence=0):
"""Change stream position.
Change the stream position to byte offset pos. Argument pos is
interpreted relative to the position indicated by whence. Values
* 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")
"""Return current stream position."""
def truncate(self, pos=None):
"""Truncate file to size bytes.
Size defaults to the current IO position as reported by tell(). Return
self._unsupported("truncate")
"""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???
"""Flush and close the IO object.
This method has no effect if the file is already closed.
"""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.
"""Return whether object supports random access.
If False, seek(), tell() and truncate() will raise IOError.
This method may need to do a test seek().
def _checkSeekable(self, msg=None):
"""Internal: raise an IOError if file is not seekable
raise IOError("File or stream is not seekable."
"""Return whether object was opened for reading.
If False, read() will raise IOError.
def _checkReadable(self, msg=None):
"""Internal: raise an IOError if file is not readable
raise IOError("File or stream is not readable."
"""Return whether object was opened for writing.
If False, write() and truncate() will raise IOError.
def _checkWritable(self, msg=None):
"""Internal: raise an IOError if file is not writable
raise IOError("File or stream is not writable."
"""closed: bool. True iff the file has been closed.
For backwards compatibility, this is a property, not a predicate.
def _checkClosed(self, msg=None):
"""Internal: raise a ValueError if file is closed
raise ValueError("I/O operation on closed file."
"""Context management protocol. Returns self."""
def __exit__(self, *args):
"""Context management protocol. Calls close()"""
# XXX Should these be present even if unimplemented?
"""Returns underlying file descriptor if one exists.
An IOError is raised if the IO object does not use a file descriptor.
self._unsupported("fileno")
"""Return whether this is an 'interactive' stream.
Return False if it can't be determined.
### Readline[s] and writelines ###
def readline(self, limit=-1):
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"):
n = (readahead.find(b"\n") + 1) or len(readahead)
elif not isinstance(limit, (int, long)):
raise TypeError("limit must be an integer")
while limit < 0 or len(res) < limit:
b = self.read(nreadahead())