summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorR. David Murray <rdmurray@bitdance.com>2010-07-17 01:35:16 (GMT)
committerR. David Murray <rdmurray@bitdance.com>2010-07-17 01:35:16 (GMT)
commit05b7631c17670a5b221f88161aad23c741b5be79 (patch)
tree46001b8b0f390a946dbb7b3e523e26f2e42764cf
parent84305c51534482d4defd1f0df898759fbaf5c208 (diff)
downloadcpython-05b7631c17670a5b221f88161aad23c741b5be79.zip
cpython-05b7631c17670a5b221f88161aad23c741b5be79.tar.gz
cpython-05b7631c17670a5b221f88161aad23c741b5be79.tar.bz2
Merged revisions 82922 via svnmerge from
svn+ssh://pythondev@svn.python.org/python/branches/py3k ........ r82922 | r.david.murray | 2010-07-16 21:19:57 -0400 (Fri, 16 Jul 2010) | 4 lines #1555570: correctly handle a \r\n that is split by the read buffer. Patch and test by Tony Nelson. ........
-rw-r--r--Lib/email/feedparser.py4
-rw-r--r--Lib/email/test/test_email.py33
-rw-r--r--Misc/NEWS2
3 files changed, 39 insertions, 0 deletions
diff --git a/Lib/email/feedparser.py b/Lib/email/feedparser.py
index 163fada..5ff266f 100644
--- a/Lib/email/feedparser.py
+++ b/Lib/email/feedparser.py
@@ -104,6 +104,10 @@ class BufferedSubFile(object):
# data after the final RE. In the case of a NL/CR terminated string,
# this is the empty string.
self._partial = parts.pop()
+ #GAN 29Mar09 bugs 1555570, 1721862 Confusion at 8K boundary ending with \r:
+ # is there a \n to follow later?
+ if not self._partial and parts and parts[-1].endswith('\r'):
+ self._partial = parts.pop(-2)+parts.pop()
# parts is a list of strings, alternating between the line contents
# and the eol character(s). Gather up a list of lines after
# re-attaching the newlines.
diff --git a/Lib/email/test/test_email.py b/Lib/email/test/test_email.py
index 4ce9848..067937a 100644
--- a/Lib/email/test/test_email.py
+++ b/Lib/email/test/test_email.py
@@ -2465,6 +2465,39 @@ Do you like this message?
-Me
""")
+ def test_pushCR_LF(self):
+ '''FeedParser BufferedSubFile.push() assumed it received complete
+ line endings. A CR ending one push() followed by a LF starting
+ the next push() added an empty line.
+ '''
+ imt = [
+ ("a\r \n", 2),
+ ("b", 0),
+ ("c\n", 1),
+ ("", 0),
+ ("d\r\n", 1),
+ ("e\r", 0),
+ ("\nf", 1),
+ ("\r\n", 1),
+ ]
+ from email.feedparser import BufferedSubFile, NeedMoreData
+ bsf = BufferedSubFile()
+ om = []
+ nt = 0
+ for il, n in imt:
+ bsf.push(il)
+ nt += n
+ n1 = 0
+ while True:
+ ol = bsf.readline()
+ if ol == NeedMoreData:
+ break
+ om.append(ol)
+ n1 += 1
+ self.assertTrue(n == n1)
+ self.assertTrue(len(om) == nt)
+ self.assertTrue(''.join([il for il, n in imt]) == ''.join(om))
+
class TestParsers(TestEmailBase):
diff --git a/Misc/NEWS b/Misc/NEWS
index bc48622..17fb072 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -833,6 +833,8 @@ Core and Builtins
Library
-------
+- Issue #1555570: email no longer inserts extra blank lines when a \r\n
+ combo crosses an 8192 byte boundary.
- Issue #6906: Tk should not set Unicode environment variables on Windows.