[Python-checkins] cpython (3.3): Issue #8260: The read(), readline() and readlines() methods of
serhiy.storchaka
python-checkins at python.org
Sun Jan 26 18:30:34 CET 2014
http://hg.python.org/cpython/rev/9c96c266896e
changeset: 88728:9c96c266896e
branch: 3.3
parent: 88705:8c5876a6b3ed
user: Serhiy Storchaka <storchaka at gmail.com>
date: Sun Jan 26 19:21:00 2014 +0200
summary:
Issue #8260: The read(), readline() and readlines() methods of
codecs.StreamReader returned incomplete data when were called after
readline() or read(size). Based on patch by Amaury Forgeot d'Arc.
files:
Lib/codecs.py | 13 ++++-----
Lib/test/test_codecs.py | 36 +++++++++++++++++++++++++++-
Misc/NEWS | 4 +++
3 files changed, 44 insertions(+), 9 deletions(-)
diff --git a/Lib/codecs.py b/Lib/codecs.py
--- a/Lib/codecs.py
+++ b/Lib/codecs.py
@@ -463,14 +463,11 @@
# read until we get the required number of characters (if available)
while True:
# can the request be satisfied from the character buffer?
- if chars < 0:
- if size < 0:
- if self.charbuffer:
- break
- elif len(self.charbuffer) >= size:
+ if chars >= 0:
+ if len(self.charbuffer) >= chars:
break
- else:
- if len(self.charbuffer) >= chars:
+ elif size >= 0:
+ if len(self.charbuffer) >= size:
break
# we need more data
if size < 0:
@@ -479,6 +476,8 @@
newdata = self.stream.read(size)
# decode bytes (those remaining from the last call included)
data = self.bytebuffer + newdata
+ if not data:
+ break
try:
newchars, decodedbytes = self.decode(data, self.errors)
except UnicodeDecodeError as exc:
diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py
--- a/Lib/test/test_codecs.py
+++ b/Lib/test/test_codecs.py
@@ -173,6 +173,40 @@
size*"a",
)
+ def test_mixed_readline_and_read(self):
+ lines = ["Humpty Dumpty sat on a wall,\n",
+ "Humpty Dumpty had a great fall.\r\n",
+ "All the king's horses and all the king's men\r",
+ "Couldn't put Humpty together again."]
+ data = ''.join(lines)
+ def getreader():
+ stream = io.BytesIO(data.encode(self.encoding))
+ return codecs.getreader(self.encoding)(stream)
+
+ # Issue #8260: Test readline() followed by read()
+ f = getreader()
+ self.assertEqual(f.readline(), lines[0])
+ self.assertEqual(f.read(), ''.join(lines[1:]))
+ self.assertEqual(f.read(), '')
+
+ # Issue #16636: Test readline() followed by readlines()
+ f = getreader()
+ self.assertEqual(f.readline(), lines[0])
+ self.assertEqual(f.readlines(), lines[1:])
+ self.assertEqual(f.read(), '')
+
+ # Test read() followed by read()
+ f = getreader()
+ self.assertEqual(f.read(size=40, chars=5), data[:5])
+ self.assertEqual(f.read(), data[5:])
+ self.assertEqual(f.read(), '')
+
+ # Issue #12446: Test read() followed by readlines()
+ f = getreader()
+ self.assertEqual(f.read(size=40, chars=5), data[:5])
+ self.assertEqual(f.readlines(), [lines[0][5:]] + lines[1:])
+ self.assertEqual(f.read(), '')
+
def test_bug1175396(self):
s = [
'<%!--===================================================\r\n',
@@ -2307,8 +2341,6 @@
def test_readline(self):
for encoding in bytes_transform_encodings:
- if encoding in ['uu_codec', 'zlib_codec']:
- continue
sin = codecs.encode(b"\x80", encoding)
reader = codecs.getreader(encoding)(io.BytesIO(sin))
sout = reader.readline()
diff --git a/Misc/NEWS b/Misc/NEWS
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -50,6 +50,10 @@
Library
-------
+- Issue #8260: The read(), readline() and readlines() methods of
+ codecs.StreamReader returned incomplete data when were called after
+ readline() or read(size). Based on patch by Amaury Forgeot d'Arc.
+
- Issue #20317: ExitStack.__exit__ could create a self-referential loop if an
exception raised by a cleanup operation already had its context set
correctly (for example, by the @contextmanager decorator). The infinite
--
Repository URL: http://hg.python.org/cpython
More information about the Python-checkins
mailing list