diff options
author | Serhiy Storchaka <storchaka@gmail.com> | 2014-08-13 09:36:06 +0300 |
---|---|---|
committer | Serhiy Storchaka <storchaka@gmail.com> | 2014-08-13 09:36:06 +0300 |
commit | 5be034cf6165724587beb18dca9e5b7682442a74 (patch) | |
tree | 6b6cef1d5851e7f5770aa78f9290dba4f546bb01 /Python/codecs.c | |
parent | b1ec624fe7b26b6a23658840b50b15b372de670e (diff) | |
parent | 8128e231900edc5b5f035f83186cb7507271ab84 (diff) | |
download | cpython-5be034cf6165724587beb18dca9e5b7682442a74.tar.gz |
Issue #20729: Restored the use of lazy iterkeys()/itervalues()/iteritems()
in the mailbox module. This is partial rollback of changeset f340cb045bf9.
Diffstat (limited to 'Python/codecs.c')
-rw-r--r-- | Python/codecs.c | 27 |
1 files changed, 23 insertions, 4 deletions
diff --git a/Python/codecs.c b/Python/codecs.c index e06d6e0922..4c2ae381b3 100644 --- a/Python/codecs.c +++ b/Python/codecs.c @@ -901,6 +901,7 @@ PyObject *PyCodec_BackslashReplaceErrors(PyObject *exc) } } +#define ENC_UNKNOWN -1 #define ENC_UTF8 0 #define ENC_UTF16BE 1 #define ENC_UTF16LE 2 @@ -916,7 +917,11 @@ get_standard_encoding(const char *encoding, int *bytelength) encoding += 3; if (*encoding == '-' || *encoding == '_' ) encoding++; - if (encoding[0] == '1' && encoding[1] == '6') { + if (encoding[0] == '8' && encoding[1] == '\0') { + *bytelength = 3; + return ENC_UTF8; + } + else if (encoding[0] == '1' && encoding[1] == '6') { encoding += 2; *bytelength = 2; if (*encoding == '\0') { @@ -955,9 +960,11 @@ get_standard_encoding(const char *encoding, int *bytelength) } } } - /* utf-8 */ - *bytelength = 3; - return ENC_UTF8; + else if (strcmp(encoding, "CP_UTF8") == 0) { + *bytelength = 3; + return ENC_UTF8; + } + return ENC_UNKNOWN; } /* This handler is declared static until someone demonstrates @@ -994,6 +1001,12 @@ PyCodec_SurrogatePassErrors(PyObject *exc) } code = get_standard_encoding(encoding, &bytelength); Py_DECREF(encode); + if (code == ENC_UNKNOWN) { + /* Not supported, fail with original exception */ + PyErr_SetObject(PyExceptionInstance_Class(exc), exc); + Py_DECREF(object); + return NULL; + } res = PyBytes_FromStringAndSize(NULL, bytelength*(end-start)); if (!res) { @@ -1068,6 +1081,12 @@ PyCodec_SurrogatePassErrors(PyObject *exc) } code = get_standard_encoding(encoding, &bytelength); Py_DECREF(encode); + if (code == ENC_UNKNOWN) { + /* Not supported, fail with original exception */ + PyErr_SetObject(PyExceptionInstance_Class(exc), exc); + Py_DECREF(object); + return NULL; + } /* Try decoding a single surrogate character. If there are more, let the codec call us again. */ |