mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-27 04:05:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

gh-91924: Optimize unicode_check_encoding_errors() (#93200)

Browse source 
Avoid _PyCodec_Lookup() and PyCodec_LookupError() for most common
built-in encodings and error handlers to avoid creating a temporary
Unicode string object, whereas these encodings and error handlers are
known to be valid.
This commit is contained in:
Victor Stinner 2022-05-27 00:39:49 +02:00 • committed by GitHub
parent efc5d37671
commit 5f8c3fb997
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 16 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

18
Objects/unicodeobject.c
View file

@ -454,7 +454,14 @@ unicode_check_encoding_errors(const char *encoding, const char *errors)
return 0;
}
if (encoding != NULL) {
if (encoding != NULL
// Fast path for the most common built-in encodings. Even if the codec
// is cached, _PyCodec_Lookup() decodes the bytes string from UTF-8 to
// create a temporary Unicode string (the key in the cache).
&& strcmp(encoding, "utf-8") != 0
&& strcmp(encoding, "utf8") != 0
&& strcmp(encoding, "ascii") != 0)
{
PyObject *handler = _PyCodec_Lookup(encoding);
if (handler == NULL) {
return -1;
@ -462,7 +469,14 @@ unicode_check_encoding_errors(const char *encoding, const char *errors)
Py_DECREF(handler);
}
if (errors != NULL) {
if (errors != NULL
// Fast path for the most common built-in error handlers.
&& strcmp(errors, "strict") != 0
&& strcmp(errors, "ignore") != 0
&& strcmp(errors, "replace") != 0
&& strcmp(errors, "surrogateescape") != 0
&& strcmp(errors, "surrogatepass") != 0)
{
PyObject *handler = PyCodec_LookupError(errors);
if (handler == NULL) {
return -1;