Branch merge
diff --git a/Lib/_pyio.py b/Lib/_pyio.py
index fa00eb4..5474a4e 100644
--- a/Lib/_pyio.py
+++ b/Lib/_pyio.py
@@ -556,7 +556,11 @@
if not data:
break
res += data
- return bytes(res)
+ if res:
+ return bytes(res)
+ else:
+ # b'' or None
+ return data
def readinto(self, b):
"""Read up to len(b) bytes into b.
diff --git a/Lib/socketserver.py b/Lib/socketserver.py
index 3d32c3e..e7faf88 100644
--- a/Lib/socketserver.py
+++ b/Lib/socketserver.py
@@ -529,7 +529,6 @@
self.active_children = []
self.active_children.append(pid)
self.close_request(request)
- return
else:
# Child process.
# This must never return, hence os._exit()!
diff --git a/Lib/test/cjkencodings/hz-utf8.txt b/Lib/test/cjkencodings/hz-utf8.txt
new file mode 100644
index 0000000..7c11735
--- /dev/null
+++ b/Lib/test/cjkencodings/hz-utf8.txt
@@ -0,0 +1,2 @@
+This sentence is in ASCII.
+The next sentence is in GB.己所不欲,勿施於人。Bye.
diff --git a/Lib/test/cjkencodings/hz.txt b/Lib/test/cjkencodings/hz.txt
new file mode 100644
index 0000000..f882d46
--- /dev/null
+++ b/Lib/test/cjkencodings/hz.txt
@@ -0,0 +1,2 @@
+This sentence is in ASCII.
+The next sentence is in GB.~{<:Ky2;S{#,NpJ)l6HK!#~}Bye.
diff --git a/Lib/test/test_codecencodings_cn.py b/Lib/test/test_codecencodings_cn.py
index 77bac13..9622b63 100644
--- a/Lib/test/test_codecencodings_cn.py
+++ b/Lib/test/test_codecencodings_cn.py
@@ -50,6 +50,35 @@
)
has_iso10646 = True
+class Test_HZ(test_multibytecodec_support.TestBase, unittest.TestCase):
+ encoding = 'hz'
+ tstring = test_multibytecodec_support.load_teststring('hz')
+ codectests = (
+ # test '~\n' (3 lines)
+ (b'This sentence is in ASCII.\n'
+ b'The next sentence is in GB.~{<:Ky2;S{#,~}~\n'
+ b'~{NpJ)l6HK!#~}Bye.\n',
+ 'strict',
+ 'This sentence is in ASCII.\n'
+ 'The next sentence is in GB.'
+ '\u5df1\u6240\u4e0d\u6b32\uff0c\u52ff\u65bd\u65bc\u4eba\u3002'
+ 'Bye.\n'),
+ # test '~\n' (4 lines)
+ (b'This sentence is in ASCII.\n'
+ b'The next sentence is in GB.~\n'
+ b'~{<:Ky2;S{#,NpJ)l6HK!#~}~\n'
+ b'Bye.\n',
+ 'strict',
+ 'This sentence is in ASCII.\n'
+ 'The next sentence is in GB.'
+ '\u5df1\u6240\u4e0d\u6b32\uff0c\u52ff\u65bd\u65bc\u4eba\u3002'
+ 'Bye.\n'),
+ # invalid bytes
+ (b'ab~cd', 'replace', 'ab\uFFFDd'),
+ (b'ab\xffcd', 'replace', 'ab\uFFFDcd'),
+ (b'ab~{\x81\x81\x41\x44~}cd', 'replace', 'ab\uFFFD\uFFFD\u804Acd'),
+ )
+
def test_main():
support.run_unittest(__name__)
diff --git a/Lib/test/test_io.py b/Lib/test/test_io.py
index 1ec6f93..5333bb6 100644
--- a/Lib/test/test_io.py
+++ b/Lib/test/test_io.py
@@ -790,14 +790,17 @@
# Inject some None's in there to simulate EWOULDBLOCK
rawio = self.MockRawIO((b"abc", b"d", None, b"efg", None, None, None))
bufio = self.tp(rawio)
-
self.assertEqual(b"abcd", bufio.read(6))
self.assertEqual(b"e", bufio.read(1))
self.assertEqual(b"fg", bufio.read())
self.assertEqual(b"", bufio.peek(1))
- self.assertTrue(None is bufio.read())
+ self.assertIsNone(bufio.read())
self.assertEqual(b"", bufio.read())
+ rawio = self.MockRawIO((b"a", None, None))
+ self.assertEqual(b"a", rawio.readall())
+ self.assertIsNone(rawio.readall())
+
def test_read_past_eof(self):
rawio = self.MockRawIO((b"abc", b"d", b"efg"))
bufio = self.tp(rawio)
@@ -2467,6 +2470,8 @@
self.assertRaises(ValueError, f.read)
if hasattr(f, "read1"):
self.assertRaises(ValueError, f.read1, 1024)
+ if hasattr(f, "readall"):
+ self.assertRaises(ValueError, f.readall)
if hasattr(f, "readinto"):
self.assertRaises(ValueError, f.readinto, bytearray(1024))
self.assertRaises(ValueError, f.readline)
diff --git a/Lib/test/test_multibytecodec.py b/Lib/test/test_multibytecodec.py
index f3c8c61..069d090 100644
--- a/Lib/test/test_multibytecodec.py
+++ b/Lib/test/test_multibytecodec.py
@@ -257,6 +257,36 @@
# Any ISO 2022 codec will cause the segfault
myunichr(x).encode('iso_2022_jp', 'ignore')
+class TestStateful(unittest.TestCase):
+ text = '\u4E16\u4E16'
+ encoding = 'iso-2022-jp'
+ expected = b'\x1b$B@$@$'
+ expected_reset = b'\x1b$B@$@$\x1b(B'
+
+ def test_encode(self):
+ self.assertEqual(self.text.encode(self.encoding), self.expected_reset)
+
+ def test_incrementalencoder(self):
+ encoder = codecs.getincrementalencoder(self.encoding)()
+ output = b''.join(
+ encoder.encode(char)
+ for char in self.text)
+ self.assertEqual(output, self.expected)
+
+ def test_incrementalencoder_final(self):
+ encoder = codecs.getincrementalencoder(self.encoding)()
+ last_index = len(self.text) - 1
+ output = b''.join(
+ encoder.encode(char, index == last_index)
+ for index, char in enumerate(self.text))
+ self.assertEqual(output, self.expected_reset)
+
+class TestHZStateful(TestStateful):
+ text = '\u804a\u804a'
+ encoding = 'hz'
+ expected = b'~{ADAD'
+ expected_reset = b'~{ADAD~}'
+
def test_main():
support.run_unittest(__name__)
diff --git a/Makefile.pre.in b/Makefile.pre.in
index c2fc69a..270dfb4 100644
--- a/Makefile.pre.in
+++ b/Makefile.pre.in
@@ -840,8 +840,8 @@
MACHDEPS= $(PLATDIR) $(EXTRAPLATDIR)
XMLLIBSUBDIRS= xml xml/dom xml/etree xml/parsers xml/sax
LIBSUBDIRS= tkinter tkinter/test tkinter/test/test_tkinter \
- tkinter/test/test_ttk site-packages test test/data \
- test/decimaltestdata \
+ tkinter/test/test_ttk site-packages test test/data \
+ test/cjkencodings test/decimaltestdata \
test/tracedmodules \
encodings \
email email/mime email/test email/test/data \
diff --git a/Misc/NEWS b/Misc/NEWS
index 37bbbc1..015018c 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -75,6 +75,17 @@
Library
-------
+- Issue #12175: RawIOBase.readall() now returns None if read() returns None.
+
+- Issue #12175: FileIO.readall() now raises a ValueError instead of an IOError
+ if the file is closed.
+
+- Issue #12100: Don't reset incremental encoders of CJK codecs at each call to
+ their encode() method anymore, but continue to call the reset() method if the
+ final argument is True.
+
+- Issue #5715: In socketserver, close the server socket in the child process.
+
- Issue #12124: zipimport doesn't keep a reference to zlib.decompress() anymore
to be able to unload the module.
diff --git a/Modules/_io/fileio.c b/Modules/_io/fileio.c
index 473919b..0fce1a3 100644
--- a/Modules/_io/fileio.c
+++ b/Modules/_io/fileio.c
@@ -536,6 +536,8 @@
Py_ssize_t total = 0;
int n;
+ if (self->fd < 0)
+ return err_closed();
if (!_PyVerify_fd(self->fd))
return PyErr_SetFromErrno(PyExc_IOError);
diff --git a/Modules/_io/iobase.c b/Modules/_io/iobase.c
index 84b560a..316321a 100644
--- a/Modules/_io/iobase.c
+++ b/Modules/_io/iobase.c
@@ -814,6 +814,14 @@
Py_DECREF(chunks);
return NULL;
}
+ if (data == Py_None) {
+ if (PyList_GET_SIZE(chunks) == 0) {
+ Py_DECREF(chunks);
+ return data;
+ }
+ Py_DECREF(data);
+ break;
+ }
if (!PyBytes_Check(data)) {
Py_DECREF(chunks);
Py_DECREF(data);
diff --git a/Modules/cjkcodecs/multibytecodec.c b/Modules/cjkcodecs/multibytecodec.c
index af7ea5b..7b04f020 100644
--- a/Modules/cjkcodecs/multibytecodec.c
+++ b/Modules/cjkcodecs/multibytecodec.c
@@ -479,7 +479,7 @@
MultibyteEncodeBuffer buf;
Py_ssize_t finalsize, r = 0;
- if (datalen == 0)
+ if (datalen == 0 && !(flags & MBENC_RESET))
return PyBytes_FromStringAndSize(NULL, 0);
buf.excobj = NULL;
@@ -514,7 +514,7 @@
break;
}
- if (codec->encreset != NULL)
+ if (codec->encreset != NULL && (flags & MBENC_RESET))
for (;;) {
Py_ssize_t outleft;
@@ -784,8 +784,8 @@
inbuf_end = inbuf + datalen;
r = multibytecodec_encode(ctx->codec, &ctx->state,
- (const Py_UNICODE **)&inbuf,
- datalen, ctx->errors, final ? MBENC_FLUSH : 0);
+ (const Py_UNICODE **)&inbuf, datalen,
+ ctx->errors, final ? MBENC_FLUSH | MBENC_RESET : 0);
if (r == NULL) {
/* recover the original pending buffer */
if (origpending > 0)
diff --git a/Objects/typeobject.c b/Objects/typeobject.c
index 310a56c..5c20e0d 100644
--- a/Objects/typeobject.c
+++ b/Objects/typeobject.c
@@ -2515,9 +2515,9 @@
PyDoc_STR("__prepare__() -> dict\n"
"used to create the namespace for the class statement")},
{"__instancecheck__", type___instancecheck__, METH_O,
- PyDoc_STR("__instancecheck__() -> check if an object is an instance")},
+ PyDoc_STR("__instancecheck__() -> bool\ncheck if an object is an instance")},
{"__subclasscheck__", type___subclasscheck__, METH_O,
- PyDoc_STR("__subclasscheck__() -> check if a class is a subclass")},
+ PyDoc_STR("__subclasscheck__() -> bool\ncheck if a class is a subclass")},
{0}
};
@@ -3354,7 +3354,7 @@
{"__format__", object_format, METH_VARARGS,
PyDoc_STR("default object formatter")},
{"__sizeof__", object_sizeof, METH_NOARGS,
- PyDoc_STR("__sizeof__() -> size of object in memory, in bytes")},
+ PyDoc_STR("__sizeof__() -> int\nsize of object in memory, in bytes")},
{0}
};
diff --git a/Tools/msi/msi.py b/Tools/msi/msi.py
index b668c7a..78ff51b 100644
--- a/Tools/msi/msi.py
+++ b/Tools/msi/msi.py
@@ -1021,6 +1021,8 @@
lib.add_file("zipdir.zip")
if dir=='tests' and parent.physical=='distutils':
lib.add_file("Setup.sample")
+ if dir=='cjkencodings':
+ lib.glob("*.txt")
if dir=='decimaltestdata':
lib.glob("*.decTest")
if dir=='output':