From eb4b738963dc915f0281107b05c04bcf6b1c90d7 Mon Sep 17 00:00:00 2001 From: Georg Brandl Date: Wed, 8 Aug 2007 13:03:45 +0000 Subject: [PATCH] Revert the fix for #1548891, it broke backwards compatibility with arbitrary read buffers. Fixes #1730114. (backport from rev. 56830) --- Doc/lib/libstringio.tex | 4 ++++ Lib/test/test_StringIO.py | 22 ---------------------- Misc/NEWS | 3 +++ Modules/cStringIO.c | 7 +++++-- 4 files changed, 12 insertions(+), 24 deletions(-) diff --git a/Doc/lib/libstringio.tex b/Doc/lib/libstringio.tex index 24312518f37..73ff0e4c3c2 100644 --- a/Doc/lib/libstringio.tex +++ b/Doc/lib/libstringio.tex @@ -78,6 +78,10 @@ Unlike the memory files implemented by the \refmodule{StringIO} module, those provided by this module are not able to accept Unicode strings that cannot be encoded as plain \ASCII{} strings. +Calling \function{StringIO()} with a Unicode string parameter populates +the object with the buffer representation of the Unicode string, instead of +encoding the string. + Another difference from the \refmodule{StringIO} module is that calling \function{StringIO()} with a string parameter creates a read-only object. Unlike an object created without a string parameter, it does not have diff --git a/Lib/test/test_StringIO.py b/Lib/test/test_StringIO.py index aa36b098443..cc3367fed8d 100644 --- a/Lib/test/test_StringIO.py +++ b/Lib/test/test_StringIO.py @@ -120,28 +120,6 @@ class TestStringIO(TestGenericStringIO): class TestcStringIO(TestGenericStringIO): MODULE = cStringIO - def test_unicode(self): - - if not test_support.have_unicode: return - - # The cStringIO module converts Unicode strings to character - # strings when writing them to cStringIO objects. - # Check that this works. - - f = self.MODULE.StringIO() - f.write(unicode(self._line[:5])) - s = f.getvalue() - self.assertEqual(s, 'abcde') - self.assertEqual(type(s), types.StringType) - - f = self.MODULE.StringIO(unicode(self._line[:5])) - s = f.getvalue() - self.assertEqual(s, 'abcde') - self.assertEqual(type(s), types.StringType) - - self.assertRaises(UnicodeEncodeError, self.MODULE.StringIO, - unicode('\xf4', 'latin-1')) - import sys if sys.platform.startswith('java'): # Jython doesn't have a buffer object, so we just do a useless diff --git a/Misc/NEWS b/Misc/NEWS index 3d5221cd43a..0e2985c9cb7 100644 --- a/Misc/NEWS +++ b/Misc/NEWS @@ -26,6 +26,9 @@ Core and builtins Library ------- +- Reverted the fix for bug #1548891 because it broke compatibility with + arbitrary read buffers. Added a note in the documentation. + - GB18030 codec now can encode additional two-byte characters that are missing in GBK. diff --git a/Modules/cStringIO.c b/Modules/cStringIO.c index 06bc6cbae36..2d8a6abd76b 100644 --- a/Modules/cStringIO.c +++ b/Modules/cStringIO.c @@ -665,8 +665,11 @@ newIobject(PyObject *s) { char *buf; Py_ssize_t size; - if (PyObject_AsCharBuffer(s, (const char **)&buf, &size) != 0) - return NULL; + if (PyObject_AsReadBuffer(s, (const char **)&buf, &size)) { + PyErr_Format(PyExc_TypeError, "expected read buffer, %.200s found", + s->ob_type->tp_name); + return NULL; + } self = PyObject_New(Iobject, &Itype); if (!self) return NULL;