cpython/Lib/StringIO.py

324 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
self.softspace = 0
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
def read(self, n = -1):
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 = []
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):
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()