mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-04 08:59:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 11

If the data read from the bytestream in readline() ends in a '\r' read one more

Browse source 
byte, even if the user has passed a size parameter. This extra byte shouldn't
cause a buffer overflow in the tokenizer. The original plan was to return a line
ending in '\r', which might be recognizable as a complete line and skip any '\n'
that was read afterwards. Unfortunately this didn't work, as the tokenizer only
recognizes '\n' as line ends, which in turn lead to joined lines and
SyntaxErrors, so this special treatment of a split '\r\n' has been dropped. (It
can only happen with a temporarily exhausted bytestream now anyway.)
Fixes parts of SF bugs #1163244 and #1175396.
This commit is contained in:
Walter Dörwald 2005-04-21 21:32:03 +00:00
parent 49ab700cc1
commit bc8e642c1b
2 changed files with 10 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

16
Lib/codecs.py
View file

@ -230,7 +230,6 @@ class StreamReader(Codec):
self.errors = errors
self.bytebuffer = ""
self.charbuffer = u""
self.atcr = False
def decode(self, input, errors='strict'):
raise NotImplementedError
@ -306,18 +305,12 @@ class StreamReader(Codec):
# If size is given, we call read() only once
while True:
data = self.read(readsize)
if self.atcr and data.startswith(u"\n"):
data = data[1:]
if data:
self.atcr = data.endswith(u"\r")
# If we're at a "\r" (and are allowed to read more), read one
# extra character (which might be a "\n") to get a proper
# line ending. (If the stream is temporarily exhausted we return
# the wrong line ending, but at least we won't generate a bogus
# second line.)
if self.atcr and size is None:
# If we're at a "\r" read one # extra character # (which might
# be a "\n") to get a proper # line ending. If the stream is
# temporarily exhausted we return the wrong line ending.
if data.endswith(u"\r"):
data += self.read(size=1, chars=1)
self.atcr = data.endswith(u"\r")
line += data
lines = line.splitlines(True)
@ -367,7 +360,6 @@ class StreamReader(Codec):
"""
self.bytebuffer = ""
self.charbuffer = u""
self.atcr = False
def seek(self, offset, whence=0):
""" Set the input stream's current position.