cpython/Lib/StringIO.py

325 lines
10 KiB
Python
Raw Normal View History

r"""File-like objects that read from or write to a string buffer.
This implements (nearly) all stdio methods.
f = StringIO() # ready for writing
f = StringIO(buf) # ready for reading
f.close() # explicitly release resources held
flag = f.isatty() # always false
pos = f.tell() # get current position
f.seek(pos) # set current position
f.seek(pos, mode) # mode 0: absolute; 1: relative; 2: relative to EOF
buf = f.read() # read until EOF
buf = f.read(n) # read up to n bytes
buf = f.readline() # read until end of line ('\n') or EOF
list = f.readlines()# list of f.readline() results until EOF
f.truncate([size]) # truncate file at to at most size (default: current pos)
f.write(buf) # write at current position
f.writelines(list) # for line in list: f.write(line)
f.getvalue() # return whole file's contents as a string
Notes:
- Using a real file is often faster (but less convenient).
- There's also a much faster implementation in C, called cStringIO, but
it's not subclassable.
- fileno() is left unimplemented so that code which uses it triggers
an exception early.
- Seeking far beyond EOF and then writing will insert real null
bytes that occupy space in the buffer.
- There's a simple test set (see end of this file).
"""
try:
from errno import EINVAL
except ImportError:
EINVAL = 22
__all__ = ["StringIO"]
def _complain_ifclosed(closed):
if closed:
raise ValueError, "I/O operation on closed file"
class StringIO:
2002-05-23 12:15:30 -03:00
"""class StringIO([buffer])
When a StringIO object is created, it can be initialized to an existing
string by passing the string to the constructor. If no string is given,
2002-05-23 12:15:30 -03:00
the StringIO will start empty.
The StringIO object can accept either Unicode or 8-bit strings, but
mixing the two may take some care. If both are used, 8-bit strings that
cannot be interpreted as 7-bit ASCII (that use the 8th bit) will cause
2002-05-23 12:15:30 -03:00
a UnicodeError to be raised when getvalue() is called.
"""
def __init__(self, buf = ''):
# Force self.buf to be a string or unicode
if not isinstance(buf, basestring):
buf = str(buf)
self.buf = buf
self.len = len(buf)
self.buflist = []
self.pos = 0
self.closed = False
def __iter__(self):
return self
def next(self):
2004-03-14 03:54:37 -04:00
"""A file object is its own iterator, for example iter(f) returns f
(unless f is closed). When a file is used as an iterator, typically
in a for loop (for example, for line in f: print line), the next()
method is called repeatedly. This method returns the next input line,
or raises StopIteration when EOF is hit.
"""
_complain_ifclosed(self.closed)
r = self.readline()
if not r:
raise StopIteration
return r
def close(self):
2002-05-23 12:15:30 -03:00
"""Free the memory buffer.
"""
if not self.closed:
self.closed = True
del self.buf, self.pos
def isatty(self):
2004-03-14 03:54:37 -04:00
"""Returns False because StringIO objects are not connected to a
tty-like device.
"""
_complain_ifclosed(self.closed)
return False
def seek(self, pos, mode = 0):
2004-03-14 03:54:37 -04:00
"""Set the file's current position.
The mode argument is optional and defaults to 0 (absolute file
positioning); other values are 1 (seek relative to the current
position) and 2 (seek relative to the file's end).
There is no return value.
"""
_complain_ifclosed(self.closed)
if self.buflist:
self.buf += ''.join(self.buflist)
self.buflist = []
if mode == 1:
pos += self.pos
elif mode == 2:
pos += self.len
self.pos = max(0, pos)
def tell(self):
2004-03-14 03:54:37 -04:00
"""Return the file's current position."""
_complain_ifclosed(self.closed)
return self.pos
Restructure comparison dramatically. There is no longer a default *ordering* between objects; there is only a default equality test (defined by an object being equal to itself only). Read the comment in object.c. The current implementation never uses a three-way comparison to compute a rich comparison, but it does use a rich comparison to compute a three-way comparison. I'm not quite done ripping out all the calls to PyObject_Compare/Cmp, or replacing tp_compare implementations with tp_richcompare implementations; but much of that has happened (to make most unit tests pass). The following tests still fail, because I need help deciding or understanding: test_codeop -- depends on comparing code objects test_datetime -- need Tim Peters' opinion test_marshal -- depends on comparing code objects test_mutants -- need help understanding it The problem with test_codeop and test_marshal is this: these tests compare two different code objects and expect them to be equal. Is that still a feature we'd like to support? I've temporarily removed the comparison and hash code from code objects, so they use the default (equality by pointer only) comparison. For the other two tests, run them to see for yourself. (There may be more failing test with "-u all".) A general problem with getting lots of these tests to pass is the reality that for object types that have a natural total ordering, implementing __cmp__ is much more convenient than implementing __eq__, __ne__, __lt__, and so on. Should we go back to allowing __cmp__ to provide a total ordering? Should we provide some other way to implement rich comparison with a single method override? Alex proposed a __key__() method; I've considered a __richcmp__() method. Or perhaps __cmp__() just shouldn't be killed off...
2006-08-23 21:41:19 -03:00
def read(self, n=None):
2004-03-14 03:54:37 -04:00
"""Read at most size bytes from the file
(less if the read hits EOF before obtaining size bytes).
If the size argument is negative or omitted, read all data until EOF
is reached. The bytes are returned as a string object. An empty
string is returned when EOF is encountered immediately.
"""
_complain_ifclosed(self.closed)
if self.buflist:
self.buf += ''.join(self.buflist)
self.buflist = []
Restructure comparison dramatically. There is no longer a default *ordering* between objects; there is only a default equality test (defined by an object being equal to itself only). Read the comment in object.c. The current implementation never uses a three-way comparison to compute a rich comparison, but it does use a rich comparison to compute a three-way comparison. I'm not quite done ripping out all the calls to PyObject_Compare/Cmp, or replacing tp_compare implementations with tp_richcompare implementations; but much of that has happened (to make most unit tests pass). The following tests still fail, because I need help deciding or understanding: test_codeop -- depends on comparing code objects test_datetime -- need Tim Peters' opinion test_marshal -- depends on comparing code objects test_mutants -- need help understanding it The problem with test_codeop and test_marshal is this: these tests compare two different code objects and expect them to be equal. Is that still a feature we'd like to support? I've temporarily removed the comparison and hash code from code objects, so they use the default (equality by pointer only) comparison. For the other two tests, run them to see for yourself. (There may be more failing test with "-u all".) A general problem with getting lots of these tests to pass is the reality that for object types that have a natural total ordering, implementing __cmp__ is much more convenient than implementing __eq__, __ne__, __lt__, and so on. Should we go back to allowing __cmp__ to provide a total ordering? Should we provide some other way to implement rich comparison with a single method override? Alex proposed a __key__() method; I've considered a __richcmp__() method. Or perhaps __cmp__() just shouldn't be killed off...
2006-08-23 21:41:19 -03:00
if n is None:
n = -1
if n < 0:
newpos = self.len
else:
newpos = min(self.pos+n, self.len)
r = self.buf[self.pos:newpos]
self.pos = newpos
return r
def readline(self, length=None):
Merged revisions 53005-53303 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r53012 | walter.doerwald | 2006-12-12 22:55:31 +0100 (Tue, 12 Dec 2006) | 2 lines Fix typo. ........ r53023 | brett.cannon | 2006-12-13 23:31:37 +0100 (Wed, 13 Dec 2006) | 2 lines Remove an unneeded import of 'warnings'. ........ r53025 | brett.cannon | 2006-12-14 00:02:38 +0100 (Thu, 14 Dec 2006) | 2 lines Remove unneeded imports of 'warnings'. ........ r53026 | brett.cannon | 2006-12-14 00:09:53 +0100 (Thu, 14 Dec 2006) | 4 lines Add test.test_support.guard_warnings_filter . This function returns a context manager that protects warnings.filter from being modified once the context is exited. ........ r53029 | george.yoshida | 2006-12-14 03:22:44 +0100 (Thu, 14 Dec 2006) | 2 lines Note that guard_warnings_filter was added in 2.6 ........ r53031 | vinay.sajip | 2006-12-14 09:53:55 +0100 (Thu, 14 Dec 2006) | 1 line Added news on recent changes to logging ........ r53032 | andrew.kuchling | 2006-12-14 19:57:53 +0100 (Thu, 14 Dec 2006) | 1 line [Patch #1599256 from David Watson] check that os.fsync is available before using it ........ r53042 | kurt.kaiser | 2006-12-15 06:13:11 +0100 (Fri, 15 Dec 2006) | 6 lines 1. Avoid hang when encountering a duplicate in a completion list. Bug 1571112. 2. Duplicate some old entries from Python's NEWS to IDLE's NEWS.txt M AutoCompleteWindow.py M NEWS.txt ........ r53048 | andrew.kuchling | 2006-12-18 18:12:31 +0100 (Mon, 18 Dec 2006) | 1 line [Bug #1618083] Add missing word; make a few grammar fixes ........ r53050 | andrew.kuchling | 2006-12-18 18:16:05 +0100 (Mon, 18 Dec 2006) | 1 line Bump version ........ r53051 | andrew.kuchling | 2006-12-18 18:22:07 +0100 (Mon, 18 Dec 2006) | 1 line [Bug #1616726] Fix description of generator.close(); if you raise some random exception, the exception is raised and doesn't trigger a RuntimeError ........ r53052 | andrew.kuchling | 2006-12-18 18:38:14 +0100 (Mon, 18 Dec 2006) | 1 line Describe new methods in Queue module ........ r53053 | andrew.kuchling | 2006-12-18 20:22:24 +0100 (Mon, 18 Dec 2006) | 1 line [Patch #1615868 by Lars Gustaebel] Use Py_off_t to fix BZ2File.seek() for offsets > 2Gb ........ r53057 | andrew.kuchling | 2006-12-18 22:29:07 +0100 (Mon, 18 Dec 2006) | 1 line Fix markup ........ r53063 | thomas.wouters | 2006-12-19 09:17:50 +0100 (Tue, 19 Dec 2006) | 5 lines Make sre's SubPattern objects accept slice objects like it already accepts simple slices. ........ r53065 | andrew.kuchling | 2006-12-19 15:13:05 +0100 (Tue, 19 Dec 2006) | 6 lines [Patch #1618455 by Ben Maurer] Improve speed of HMAC by using str.translate() instead of a more general XOR that has to construct a list. Slightly modified from Maurer's patch: the _strxor() function is no longer necessary at all. ........ r53066 | andrew.kuchling | 2006-12-19 15:28:23 +0100 (Tue, 19 Dec 2006) | 9 lines [Bug #1613651] Document socket.recv_into, socket.recvfrom_into Also, the text for recvfrom told you to read recv() for an explanation of the 'flags' argument, but recv() just pointed you at the man page. Copied the man-page text to recvfrom(), recvfrom_into, recv_into to avoid the pointless redirection. I don't have LaTeX on this machine; hope my markup is OK. ........ r53067 | andrew.kuchling | 2006-12-19 15:29:04 +0100 (Tue, 19 Dec 2006) | 1 line Comment typo ........ r53068 | andrew.kuchling | 2006-12-19 16:11:41 +0100 (Tue, 19 Dec 2006) | 1 line [Patch #1617413 from Dug Song] Fix HTTP Basic authentication via HTTPS ........ r53071 | andrew.kuchling | 2006-12-19 16:18:12 +0100 (Tue, 19 Dec 2006) | 1 line [Patch #1600491 from Jim Jewett] Describe how to build help files on Windows ........ r53073 | andrew.kuchling | 2006-12-19 16:43:10 +0100 (Tue, 19 Dec 2006) | 6 lines [Patch #1587139 by kxroberto] Protect lock acquisition/release with try...finally to ensure the lock is always released. This could use the 'with' statement, but the patch uses 'finally'. 2.5 backport candidate. ........ r53074 | vinay.sajip | 2006-12-19 19:29:11 +0100 (Tue, 19 Dec 2006) | 1 line Updated documentation for findCaller() to indicate that a 3-tuple is now returned, rather than a 2-tuple. ........ r53090 | georg.brandl | 2006-12-19 23:06:46 +0100 (Tue, 19 Dec 2006) | 3 lines Patch #1484695: The tarfile module now raises a HeaderError exception if a buffer given to frombuf() is invalid. ........ r53099 | raymond.hettinger | 2006-12-20 07:42:06 +0100 (Wed, 20 Dec 2006) | 5 lines Bug #1590891: random.randrange don't return correct value for big number Needs to be backported. ........ r53106 | georg.brandl | 2006-12-20 12:55:16 +0100 (Wed, 20 Dec 2006) | 3 lines Testcase for patch #1484695. ........ r53110 | andrew.kuchling | 2006-12-20 20:48:20 +0100 (Wed, 20 Dec 2006) | 17 lines [Apply length-checking.diff from bug #1599254] Add length checking to single-file mailbox formats: before doing a flush() on a mailbox, seek to the end and verify its length is unchanged, raising ExternalClashError if the file's length has changed. This fix avoids potential data loss if some other process appends to the mailbox file after the table of contents has been generated; instead of overwriting the modified file, you'll get the exception. I also noticed that the self._lookup() call in self.flush() wasn't necessary (everything that sets self._pending to True also calls self.lookup()), and replaced it by an assertion. 2.5 backport candidate. ........ r53112 | andrew.kuchling | 2006-12-20 20:57:10 +0100 (Wed, 20 Dec 2006) | 1 line [Bug #1619674] Make sum() use the term iterable, not sequence ........ r53113 | andrew.kuchling | 2006-12-20 20:58:11 +0100 (Wed, 20 Dec 2006) | 1 line Two grammar fixes ........ r53115 | andrew.kuchling | 2006-12-20 21:11:12 +0100 (Wed, 20 Dec 2006) | 5 lines Some other built-in functions are described with 'sequence' arguments that should really be 'iterable'; this commit changes them. Did I miss any? Did I introduce any errors? ........ r53117 | andrew.kuchling | 2006-12-20 21:20:42 +0100 (Wed, 20 Dec 2006) | 1 line [Bug #1619680] in_dll() arguments are documented in the wrong order ........ r53120 | neal.norwitz | 2006-12-21 05:38:00 +0100 (Thu, 21 Dec 2006) | 1 line Lars asked for permission on on python-dev for work on tarfile.py ........ r53125 | andrew.kuchling | 2006-12-21 14:40:29 +0100 (Thu, 21 Dec 2006) | 1 line Mention the os.SEEK_* constants ........ r53129 | walter.doerwald | 2006-12-21 19:06:30 +0100 (Thu, 21 Dec 2006) | 2 lines Fix typo. ........ r53131 | thomas.heller | 2006-12-21 19:30:56 +0100 (Thu, 21 Dec 2006) | 3 lines Fix wrong markup of an argument in a method signature. Will backport. ........ r53137 | andrew.kuchling | 2006-12-22 01:50:56 +0100 (Fri, 22 Dec 2006) | 1 line Typo fix ........ r53139 | andrew.kuchling | 2006-12-22 14:25:02 +0100 (Fri, 22 Dec 2006) | 1 line [Bug #737202; fix from Titus Brown] Make CGIHTTPServer work for scripts in sub-directories ........ r53141 | andrew.kuchling | 2006-12-22 16:04:45 +0100 (Fri, 22 Dec 2006) | 6 lines [Bug #802128] Make the mode argument of dumbdbm actually work the way it's described, and add a test for it. 2.5 bugfix candidate, maybe; arguably this patch changes the API of dumbdbm and shouldn't be added in a point-release. ........ r53142 | andrew.kuchling | 2006-12-22 16:16:58 +0100 (Fri, 22 Dec 2006) | 6 lines [Bug #802128 continued] Modify mode depending on the process umask. Is there really no other way to read the umask than to set it? Hope this works on Windows... ........ r53145 | andrew.kuchling | 2006-12-22 17:43:26 +0100 (Fri, 22 Dec 2006) | 1 line [Bug #776202] Apply Walter Doerwald's patch to use text mode for encoded files ........ r53146 | andrew.kuchling | 2006-12-22 19:41:42 +0100 (Fri, 22 Dec 2006) | 9 lines [Patch #783050 from Patrick Lynch] The emulation of forkpty() is incorrect; the master should close the slave fd. Added a test to test_pty.py that reads from the master_fd after doing a pty.fork(); without the fix it hangs forever instead of raising an exception. (<crossing fingers for the buildbots>) 2.5 backport candidate. ........ r53147 | andrew.kuchling | 2006-12-22 20:06:16 +0100 (Fri, 22 Dec 2006) | 1 line [Patch #827559 from Chris Gonnerman] Make SimpleHTTPServer redirect when a directory URL is missing the trailing slash; this lets relative links work. ........ r53149 | andrew.kuchling | 2006-12-22 20:21:27 +0100 (Fri, 22 Dec 2006) | 1 line Darn; this test works when you run test_pty.py directly, but fails when regrtest runs it (the os.read() raises os.error). I can't figure out the cause, so am commenting out the test. ........ r53150 | andrew.kuchling | 2006-12-22 22:48:19 +0100 (Fri, 22 Dec 2006) | 1 line Frak; this test also fails ........ r53153 | lars.gustaebel | 2006-12-23 17:40:13 +0100 (Sat, 23 Dec 2006) | 5 lines Patch #1230446: tarfile.py: fix ExFileObject so that read() and tell() work correctly together with readline(). Will backport to 2.5. ........ r53155 | lars.gustaebel | 2006-12-23 18:57:23 +0100 (Sat, 23 Dec 2006) | 5 lines Patch #1262036: Prevent TarFiles from being added to themselves under certain conditions. Will backport to 2.5. ........ r53159 | andrew.kuchling | 2006-12-27 04:25:31 +0100 (Wed, 27 Dec 2006) | 4 lines [Part of patch #1182394] Move the HMAC blocksize to be a class-level constant; this allows changing it in a subclass. To accommodate this, copy() now uses __class__. Also add some text to a comment. ........ r53160 | andrew.kuchling | 2006-12-27 04:31:24 +0100 (Wed, 27 Dec 2006) | 1 line [Rest of patch #1182394] Add ._current() method so that we can use the written-in-C .hexdigest() method ........ r53161 | lars.gustaebel | 2006-12-27 11:30:46 +0100 (Wed, 27 Dec 2006) | 4 lines Patch #1504073: Fix tarfile.open() for mode "r" with a fileobj argument. Will backport to 2.5. ........ r53165 | neal.norwitz | 2006-12-28 05:39:20 +0100 (Thu, 28 Dec 2006) | 1 line Remove a stray (old) macro name left around (I guess) ........ r53188 | neal.norwitz | 2006-12-29 04:01:53 +0100 (Fri, 29 Dec 2006) | 1 line SF bug #1623890, fix argument name in docstring ........ r53200 | raymond.hettinger | 2006-12-30 05:01:17 +0100 (Sat, 30 Dec 2006) | 1 line For sets with cyclical reprs, emit an ellipsis instead of infinitely recursing. ........ r53232 | brett.cannon | 2007-01-04 01:23:49 +0100 (Thu, 04 Jan 2007) | 3 lines Add EnvironmentVarGuard to test.test_support. Provides a context manager to temporarily set or unset environment variables. ........ r53235 | neal.norwitz | 2007-01-04 07:25:31 +0100 (Thu, 04 Jan 2007) | 1 line SF #1627373, fix typo in CarbonEvt. ........ r53244 | raymond.hettinger | 2007-01-04 18:53:34 +0100 (Thu, 04 Jan 2007) | 1 line Fix stability of heapq's nlargest() and nsmallest(). ........ r53249 | martin.v.loewis | 2007-01-04 22:06:12 +0100 (Thu, 04 Jan 2007) | 3 lines Bug #1566280: Explicitly invoke threading._shutdown from Py_Main, to avoid relying on atexit. Will backport to 2.5. ........ r53252 | gregory.p.smith | 2007-01-05 02:59:42 +0100 (Fri, 05 Jan 2007) | 3 lines Support linking of the bsddb module against BerkeleyDB 4.5.x (will backport to 2.5) ........ r53253 | gregory.p.smith | 2007-01-05 03:06:17 +0100 (Fri, 05 Jan 2007) | 2 lines bump module version to match supported berkeleydb version ........ r53255 | neal.norwitz | 2007-01-05 06:25:22 +0100 (Fri, 05 Jan 2007) | 6 lines Prevent crash on shutdown which can occur if we are finalizing and the module dict has been cleared already and some object raises a warning (like in a __del__). Will backport. ........ r53258 | gregory.p.smith | 2007-01-05 08:21:35 +0100 (Fri, 05 Jan 2007) | 2 lines typo fix ........ r53260 | neal.norwitz | 2007-01-05 09:06:43 +0100 (Fri, 05 Jan 2007) | 1 line Add Collin Winter for access to update PEP 3107 ........ r53262 | andrew.kuchling | 2007-01-05 15:22:17 +0100 (Fri, 05 Jan 2007) | 1 line [Bug #1622533] Make docstrings raw strings because they contain control characters (\0, \1) ........ r53264 | andrew.kuchling | 2007-01-05 16:51:24 +0100 (Fri, 05 Jan 2007) | 1 line [Patch #1520904] Fix bsddb tests to write to the temp directory instead of the Lib/bsddb/test directory ........ r53279 | brett.cannon | 2007-01-05 22:45:09 +0100 (Fri, 05 Jan 2007) | 3 lines Silence a warning from gcc 4.0.1 by specifying a function's parameter list is 'void' instead of just a set of empty parentheses. ........ r53285 | raymond.hettinger | 2007-01-06 02:14:41 +0100 (Sat, 06 Jan 2007) | 2 lines SF# 1409443: Expand comment to cover the interaction between f->f_lasti and the PREDICT macros. ........ r53286 | anthony.baxter | 2007-01-06 05:45:54 +0100 (Sat, 06 Jan 2007) | 1 line update to (c) years to include 2007 ........ r53291 | neal.norwitz | 2007-01-06 22:24:35 +0100 (Sat, 06 Jan 2007) | 1 line Add Josiah to SF for maintaining asyncore/asynchat ........ r53293 | peter.astrand | 2007-01-07 09:53:46 +0100 (Sun, 07 Jan 2007) | 1 line Re-implemented fix for #1531862 once again, in a way that works with Python 2.2. Fixes bug #1603424. ........ r53295 | peter.astrand | 2007-01-07 15:34:16 +0100 (Sun, 07 Jan 2007) | 1 line Avoid O(N**2) bottleneck in _communicate_(). Fixes #1598181. ........ r53300 | raymond.hettinger | 2007-01-08 19:09:20 +0100 (Mon, 08 Jan 2007) | 1 line Fix zero-length corner case for iterating over a mutating deque. ........ r53301 | vinay.sajip | 2007-01-08 19:50:32 +0100 (Mon, 08 Jan 2007) | 4 lines Bare except clause removed from SMTPHandler.emit(). Now, only ImportError is trapped. Bare except clause removed from SocketHandler.createSocket(). Now, only socket.error is trapped. (SF #411881) ........ r53302 | vinay.sajip | 2007-01-08 19:51:46 +0100 (Mon, 08 Jan 2007) | 2 lines Bare except clause removed from LogRecord.__init__. Now, only ValueError, TypeError and AttributeError are trapped. (SF #411881) ........ r53303 | vinay.sajip | 2007-01-08 19:52:36 +0100 (Mon, 08 Jan 2007) | 1 line Added entries about removal of some bare except clauses from logging. ........
2007-01-09 19:18:33 -04:00
r"""Read one entire line from the file.
2004-03-14 03:54:37 -04:00
A trailing newline character is kept in the string (but may be absent
when a file ends with an incomplete line). If the size argument is
present and non-negative, it is a maximum byte count (including the
trailing newline) and an incomplete line may be returned.
An empty string is returned only when EOF is encountered immediately.
Note: Unlike stdio's fgets(), the returned string contains null
characters ('\0') if they occurred in the input.
"""
_complain_ifclosed(self.closed)
if self.buflist:
self.buf += ''.join(self.buflist)
self.buflist = []
i = self.buf.find('\n', self.pos)
if i < 0:
newpos = self.len
else:
newpos = i+1
if length is not None:
if self.pos + length < newpos:
newpos = self.pos + length
r = self.buf[self.pos:newpos]
self.pos = newpos
return r
def readlines(self, sizehint = 0):
2004-03-14 03:54:37 -04:00
"""Read until EOF using readline() and return a list containing the
lines thus read.
If the optional sizehint argument is present, instead of reading up
to EOF, whole lines totalling approximately sizehint bytes (or more
to accommodate a final whole line).
"""
total = 0
lines = []
line = self.readline()
while line:
lines.append(line)
total += len(line)
if 0 < sizehint <= total:
break
line = self.readline()
return lines
def truncate(self, size=None):
2004-03-14 03:54:37 -04:00
"""Truncate the file's size.
If the optional size argument is present, the file is truncated to
(at most) that size. The size defaults to the current position.
The current file position is not changed unless the position
is beyond the new file size.
If the specified size exceeds the file's current size, the
file remains unchanged.
"""
2004-01-18 16:29:55 -04:00
_complain_ifclosed(self.closed)
if size is None:
size = self.pos
elif size < 0:
raise IOError(EINVAL, "Negative size not allowed")
elif size < self.pos:
self.pos = size
self.buf = self.getvalue()[:size]
self.len = size
def write(self, s):
2004-03-14 03:54:37 -04:00
"""Write a string to the file.
There is no return value.
"""
_complain_ifclosed(self.closed)
if not s: return
# Force s to be a string or unicode
if not isinstance(s, basestring):
s = str(s)
spos = self.pos
slen = self.len
if spos == slen:
self.buflist.append(s)
self.len = self.pos = spos + len(s)
return
if spos > slen:
self.buflist.append('\0'*(spos - slen))
slen = spos
newpos = spos + len(s)
if spos < slen:
if self.buflist:
self.buf += ''.join(self.buflist)
self.buflist = [self.buf[:spos], s, self.buf[newpos:]]
self.buf = ''
if newpos > slen:
slen = newpos
else:
self.buflist.append(s)
slen = newpos
self.len = slen
self.pos = newpos
def writelines(self, iterable):
2004-03-14 03:54:37 -04:00
"""Write a sequence of strings to the file. The sequence can be any
iterable object producing strings, typically a list of strings. There
is no return value.
(The name is intended to match readlines(); writelines() does not add
line separators.)
"""
write = self.write
for line in iterable:
write(line)
def flush(self):
2004-03-14 03:54:37 -04:00
"""Flush the internal buffer
"""
_complain_ifclosed(self.closed)
def getvalue(self):
"""
Retrieve the entire contents of the "file" at any time before
the StringIO object's close() method is called.
The StringIO object can accept either Unicode or 8-bit strings,
but mixing the two may take some care. If both are used, 8-bit
strings that cannot be interpreted as 7-bit ASCII (that use the
8th bit) will cause a UnicodeError to be raised when getvalue()
2002-05-23 12:15:30 -03:00
is called.
"""
if self.buflist:
self.buf += ''.join(self.buflist)
self.buflist = []
return self.buf
# A little test suite
def test():
import sys
if sys.argv[1:]:
file = sys.argv[1]
else:
file = '/etc/passwd'
lines = open(file, 'r').readlines()
text = open(file, 'r').read()
f = StringIO()
for line in lines[:-2]:
f.write(line)
f.writelines(lines[-2:])
if f.getvalue() != text:
raise RuntimeError, 'write failed'
length = f.tell()
print('File length =', length)
f.seek(len(lines[0]))
f.write(lines[1])
f.seek(0)
print('First line =', repr(f.readline()))
print('Position =', f.tell())
line = f.readline()
print('Second line =', repr(line))
f.seek(-len(line), 1)
line2 = f.read(len(line))
if line != line2:
raise RuntimeError, 'bad result after seek back'
f.seek(len(line2), 1)
list = f.readlines()
line = list[-1]
f.seek(f.tell() - len(line))
line2 = f.read()
if line != line2:
raise RuntimeError, 'bad result after seek back from EOF'
print('Read', len(list), 'more lines')
print('File length =', f.tell())
if f.tell() != length:
raise RuntimeError, 'bad length'
f.truncate(length/2)
f.seek(0, 2)
print('Truncated length =', f.tell())
if f.tell() != length/2:
raise RuntimeError, 'truncate did not adjust length'
f.close()
if __name__ == '__main__':
test()