diff options
| author | Alexander Belopolsky <alexander.belopolsky@gmail.com> | 2011-02-25 19:19:57 (GMT) |
|---|---|---|
| committer | Alexander Belopolsky <alexander.belopolsky@gmail.com> | 2011-02-25 19:19:57 (GMT) |
| commit | 1d52146a25fdf534117602e77c7f3f539ea64294 (patch) | |
| tree | 5adfb510b3345e0321770055f224e54ddb33d090 /Objects/unicodeobject.c | |
| parent | eea22d2d660eae039ab392684ac8a8693f1f2a4d (diff) | |
| download | cpython-1d52146a25fdf534117602e77c7f3f539ea64294.zip cpython-1d52146a25fdf534117602e77c7f3f539ea64294.tar.gz cpython-1d52146a25fdf534117602e77c7f3f539ea64294.tar.bz2 | |
Issue #11303: Added shortcuts for utf8 and latin1 encodings.
Documented the list of optimized encodings as CPython implementation
detail.
Diffstat (limited to 'Objects/unicodeobject.c')
| -rw-r--r-- | Objects/unicodeobject.c | 14 |
1 files changed, 10 insertions, 4 deletions
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c index e7bbd80..48ea0a2 100644 --- a/Objects/unicodeobject.c +++ b/Objects/unicodeobject.c @@ -1462,13 +1462,15 @@ PyObject *PyUnicode_Decode(const char *s, char lower[11]; /* Enough for any encoding shortcut */ if (encoding == NULL) - encoding = PyUnicode_GetDefaultEncoding(); + return PyUnicode_DecodeUTF8(s, size, errors); /* Shortcuts for common default encodings */ if (normalize_encoding(encoding, lower, sizeof(lower))) { - if (strcmp(lower, "utf-8") == 0) + if ((strcmp(lower, "utf-8") == 0) || + (strcmp(lower, "utf8") == 0)) return PyUnicode_DecodeUTF8(s, size, errors); else if ((strcmp(lower, "latin-1") == 0) || + (strcmp(lower, "latin1") == 0) || (strcmp(lower, "iso-8859-1") == 0)) return PyUnicode_DecodeLatin1(s, size, errors); #if defined(MS_WINDOWS) && defined(HAVE_USABLE_WCHAR_T) @@ -1670,15 +1672,19 @@ PyObject *PyUnicode_AsEncodedString(PyObject *unicode, } if (encoding == NULL) - encoding = PyUnicode_GetDefaultEncoding(); + return PyUnicode_EncodeUTF8(PyUnicode_AS_UNICODE(unicode), + PyUnicode_GET_SIZE(unicode), + errors); /* Shortcuts for common default encodings */ if (normalize_encoding(encoding, lower, sizeof(lower))) { - if (strcmp(lower, "utf-8") == 0) + if ((strcmp(lower, "utf-8") == 0) || + (strcmp(lower, "utf8") == 0)) return PyUnicode_EncodeUTF8(PyUnicode_AS_UNICODE(unicode), PyUnicode_GET_SIZE(unicode), errors); else if ((strcmp(lower, "latin-1") == 0) || + (strcmp(lower, "latin1") == 0) || (strcmp(lower, "iso-8859-1") == 0)) return PyUnicode_EncodeLatin1(PyUnicode_AS_UNICODE(unicode), PyUnicode_GET_SIZE(unicode), |