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

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.

diff --git a/Lib/codecs.py b/Lib/codecs.py
index 58bba73ac0acc428c265aa287e0dbfefeea99c17..eb52ea23941cfec6246170a90a1ea707776d4fe1 100644 (file)
--- a/Lib/codecs.py
+++ b/Lib/codecs.py
@@ -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.

diff --git a/Misc/NEWS b/Misc/NEWS
index 01a1c733331dddbad70ecc8aeac342ee6b807cac..23f760b774bd437fbc6e9f9a4e81a7bf9ac96487 100644 (file)
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -266,6 +266,12 @@ Library
 - Bug #1149508: ``textwrap`` now handles hyphenated numbers (eg. "2004-03-05")
   correctly.
 
+- Partial fixes for SF bugs #1163244 and #1175396: If a chunk read by
+  ``codecs.StreamReader.readline()`` has a trailing "\r", read one more
+  character even if the user has passed a size parameter to get a proper
+  line ending. Remove the special handling of a "\r\n" that has been split
+  between two lines.
+
 
 Build
 -----