mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-03 16:39:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

Issue #8923: cache str.encode() result

Browse source 
When a string is encoded to UTF-8 in strict mode, the result is cached into the
object. Examples: str.encode(), str.encode('utf-8'), PyUnicode_AsUTF8String()
and PyUnicode_AsEncodedString(unicode, "utf-8", NULL).
This commit is contained in:
Victor Stinner 2011-03-02 01:03:14 +00:00
parent f3fd733f92
commit a5c68c3cb7
2 changed files with 21 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

5
Misc/NEWS
View file

@ -10,6 +10,11 @@ What's New in Python 3.3 Alpha 1?
Core and Builtins Core and Builtins
----------------- -----------------
- Issue #8923: When a string is encoded to UTF-8 in strict mode, the result is
cached into the object. Examples: str.encode(), str.encode('utf-8'),
PyUnicode_AsUTF8String() and PyUnicode_AsEncodedString(unicode, "utf-8",
NULL).
- Issue #10831: PyUnicode_FromFormat() supports %li, %lli and %zi formats. - Issue #10831: PyUnicode_FromFormat() supports %li, %lli and %zi formats.
- Issue #10829: Refactor PyUnicode_FromFormat(), use the same function to parse - Issue #10829: Refactor PyUnicode_FromFormat(), use the same function to parse

25
Objects/unicodeobject.c
View file

@ -1710,17 +1710,21 @@ PyUnicode_AsEncodedString(PyObject *unicode,
} }
if (encoding == NULL) if (encoding == NULL)
return PyUnicode_EncodeUTF8(PyUnicode_AS_UNICODE(unicode), return PyUnicode_AsUTF8String(unicode);
PyUnicode_GET_SIZE(unicode),
errors);
/* Shortcuts for common default encodings */ /* Shortcuts for common default encodings */
if (normalize_encoding(encoding, lower, sizeof(lower))) { if (normalize_encoding(encoding, lower, sizeof(lower))) {
if ((strcmp(lower, "utf-8") == 0) || if ((strcmp(lower, "utf-8") == 0) ||
(strcmp(lower, "utf8") == 0)) (strcmp(lower, "utf8") == 0))
return PyUnicode_EncodeUTF8(PyUnicode_AS_UNICODE(unicode), {
PyUnicode_GET_SIZE(unicode), if (errors == NULL || strcmp(errors, "strict") == 0) {
errors); return PyUnicode_AsUTF8String(unicode);
} else {
return PyUnicode_EncodeUTF8(PyUnicode_AS_UNICODE(unicode),
PyUnicode_GET_SIZE(unicode),
errors);
}
}
else if ((strcmp(lower, "latin-1") == 0) || else if ((strcmp(lower, "latin-1") == 0) ||
(strcmp(lower, "latin1") == 0) || (strcmp(lower, "latin1") == 0) ||
(strcmp(lower, "iso-8859-1") == 0)) (strcmp(lower, "iso-8859-1") == 0))
@ -3077,13 +3081,16 @@ PyUnicode_EncodeUTF8(const Py_UNICODE *s,
PyObject * PyObject *
PyUnicode_AsUTF8String(PyObject *unicode) PyUnicode_AsUTF8String(PyObject *unicode)
{ {
PyObject *utf8;
if (!PyUnicode_Check(unicode)) { if (!PyUnicode_Check(unicode)) {
PyErr_BadArgument(); PyErr_BadArgument();
return NULL; return NULL;
} }
return PyUnicode_EncodeUTF8(PyUnicode_AS_UNICODE(unicode), utf8 = _PyUnicode_AsDefaultEncodedString(unicode);
PyUnicode_GET_SIZE(unicode), if (utf8 == NULL)
NULL); return NULL;
Py_INCREF(utf8);
return utf8;
} }
/* --- UTF-32 Codec ------------------------------------------------------- */ /* --- UTF-32 Codec ------------------------------------------------------- */