summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorVictor Stinner <victor.stinner@haypocalc.com>2011-05-30 20:56:00 (GMT)
committerVictor Stinner <victor.stinner@haypocalc.com>2011-05-30 20:56:00 (GMT)
commite15dce3d18d333b91a567fb8d611ca74781e4f13 (patch)
tree332611b0ce447ea367d486b60a122aa897bec6c7
parentebbb3b797297506b91c2b9256bcd0fe92e8b47b8 (diff)
downloadcpython-e15dce3d18d333b91a567fb8d611ca74781e4f13.zip
cpython-e15dce3d18d333b91a567fb8d611ca74781e4f13.tar.gz
cpython-e15dce3d18d333b91a567fb8d611ca74781e4f13.tar.bz2
Close #12171: IncrementalEncoder.reset() of CJK codecs (multibytecodec) calls
encreset() instead of decreset().
-rw-r--r--Doc/library/codecs.rst3
-rw-r--r--Lib/test/test_multibytecodec.py9
-rw-r--r--Misc/NEWS5
-rw-r--r--Modules/cjkcodecs/multibytecodec.c14
4 files changed, 23 insertions, 8 deletions
diff --git a/Doc/library/codecs.rst b/Doc/library/codecs.rst
index 4d5058e..90bd0dd 100644
--- a/Doc/library/codecs.rst
+++ b/Doc/library/codecs.rst
@@ -458,7 +458,8 @@ define in order to be compatible with the Python codec registry.
.. method:: reset()
- Reset the encoder to the initial state.
+ Reset the encoder to the initial state. The output is discarded: call
+ ``.encode('', final=True)`` to reset the encoder and to get the output.
.. method:: IncrementalEncoder.getstate()
diff --git a/Lib/test/test_multibytecodec.py b/Lib/test/test_multibytecodec.py
index 86c68dc..4448072 100644
--- a/Lib/test/test_multibytecodec.py
+++ b/Lib/test/test_multibytecodec.py
@@ -260,7 +260,8 @@ class TestStateful(unittest.TestCase):
text = '\u4E16\u4E16'
encoding = 'iso-2022-jp'
expected = b'\x1b$B@$@$'
- expected_reset = b'\x1b$B@$@$\x1b(B'
+ reset = b'\x1b(B'
+ expected_reset = expected + reset
def test_encode(self):
self.assertEqual(self.text.encode(self.encoding), self.expected_reset)
@@ -271,6 +272,8 @@ class TestStateful(unittest.TestCase):
encoder.encode(char)
for char in self.text)
self.assertEqual(output, self.expected)
+ self.assertEqual(encoder.encode('', final=True), self.reset)
+ self.assertEqual(encoder.encode('', final=True), b'')
def test_incrementalencoder_final(self):
encoder = codecs.getincrementalencoder(self.encoding)()
@@ -279,12 +282,14 @@ class TestStateful(unittest.TestCase):
encoder.encode(char, index == last_index)
for index, char in enumerate(self.text))
self.assertEqual(output, self.expected_reset)
+ self.assertEqual(encoder.encode('', final=True), b'')
class TestHZStateful(TestStateful):
text = '\u804a\u804a'
encoding = 'hz'
expected = b'~{ADAD'
- expected_reset = b'~{ADAD~}'
+ reset = b'~}'
+ expected_reset = expected + reset
def test_main():
support.run_unittest(__name__)
diff --git a/Misc/NEWS b/Misc/NEWS
index 785761c..e5e5aa9 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -177,9 +177,12 @@ Core and Builtins
Library
-------
+- Issue #12171: IncrementalEncoder.reset() of CJK codecs (multibytecodec) calls
+ encreset() instead of decreset().
+
- Issue #12218: Removed wsgiref.egg-info.
-- Issue #12196: Add pipe2() to the os module.
+- Issue #12196: Add pipe2() to the os module.
- Issue #985064: Make plistlib more resilient to faulty input plists.
Patch by Mher Movsisyan.
diff --git a/Modules/cjkcodecs/multibytecodec.c b/Modules/cjkcodecs/multibytecodec.c
index bb8176f..1b37845 100644
--- a/Modules/cjkcodecs/multibytecodec.c
+++ b/Modules/cjkcodecs/multibytecodec.c
@@ -901,11 +901,17 @@ mbiencoder_encode(MultibyteIncrementalEncoderObject *self,
static PyObject *
mbiencoder_reset(MultibyteIncrementalEncoderObject *self)
{
- if (self->codec->decreset != NULL &&
- self->codec->decreset(&self->state, self->codec->config) != 0)
- return NULL;
+ /* Longest output: 4 bytes (b'\x0F\x1F(B') with ISO 2022 */
+ unsigned char buffer[4], *outbuf;
+ Py_ssize_t r;
+ if (self->codec->encreset != NULL) {
+ outbuf = buffer;
+ r = self->codec->encreset(&self->state, self->codec->config,
+ &outbuf, sizeof(buffer));
+ if (r != 0)
+ return NULL;
+ }
self->pendingsize = 0;
-
Py_RETURN_NONE;
}