Optimize error handlers of ASCII and Latin1 encoders when the replacement
string is pure ASCII: use _PyBytesWriter_WriteBytes(), don't check individual
character.
Cleanup unicode_encode_ucs1():
* Rename repunicode to rep
* Clear rep object on error
* Factorize code between bytes and unicode path
diff --git a/Objects/stringlib/codecs.h b/Objects/stringlib/codecs.h
index 7e8d928..2beb604 100644
--- a/Objects/stringlib/codecs.h
+++ b/Objects/stringlib/codecs.h
@@ -311,7 +311,7 @@
#if STRINGLIB_SIZEOF_CHAR > 1
else if (Py_UNICODE_IS_SURROGATE(ch)) {
Py_ssize_t startpos, endpos, newpos;
- Py_ssize_t repsize, k;
+ Py_ssize_t k;
if (error_handler == _Py_ERROR_UNKNOWN)
error_handler = get_error_handler(errors);
@@ -392,20 +392,12 @@
p = _PyBytesWriter_WriteBytes(&writer, p,
PyBytes_AS_STRING(rep),
PyBytes_GET_SIZE(rep));
- if (p == NULL)
- goto error;
}
else {
/* rep is unicode */
if (PyUnicode_READY(rep) < 0)
goto error;
- repsize = PyUnicode_GET_LENGTH(rep);
-
- p = _PyBytesWriter_Prepare(&writer, p, repsize);
- if (p == NULL)
- goto error;
-
if (!PyUnicode_IS_ASCII(rep)) {
raise_encode_exception(&exc, "utf-8",
unicode,
@@ -415,9 +407,13 @@
}
assert(PyUnicode_KIND(rep) == PyUnicode_1BYTE_KIND);
- memcpy(p, PyUnicode_DATA(rep), repsize);
- p += repsize;
+ p = _PyBytesWriter_WriteBytes(&writer, p,
+ PyUnicode_DATA(rep),
+ PyUnicode_GET_LENGTH(rep));
}
+
+ if (p == NULL)
+ goto error;
Py_CLEAR(rep);
i = newpos;