[Python-checkins] cpython (3.6): Issue #28561: Clean up UTF-8 encoder: remove dead code, update comments, etc.

Sun Oct 30 12:26:14 EDT 2016

https://hg.python.org/cpython/rev/542065b03c10
changeset: 104820:542065b03c10
branch: 3.6
parent: 104818:e7b768717074
user: Serhiy Storchaka <storchaka at gmail.com>
date: Sun Oct 30 18:25:27 2016 +0200
summary:
 Issue #28561: Clean up UTF-8 encoder: remove dead code, update comments, etc.
Patch by Xiang Zhang.
files:
 Objects/stringlib/codecs.h | 14 ++++----------
 1 files changed, 4 insertions(+), 10 deletions(-)

diff --git a/Objects/stringlib/codecs.h b/Objects/stringlib/codecs.h
--- a/Objects/stringlib/codecs.h
+++ b/Objects/stringlib/codecs.h
@@ -262,9 +262,7 @@
 Py_ssize_t size,
 const char *errors)
 {
-#define MAX_SHORT_UNICHARS 300 /* largest size we'll do on the stack */
-
- Py_ssize_t i; /* index into s of next input byte */
+ Py_ssize_t i; /* index into data of next input character */
 char *p; /* next free byte in output buffer */
 #if STRINGLIB_SIZEOF_CHAR > 1
 PyObject *error_handler_obj = NULL;
@@ -389,7 +387,7 @@
 goto error;
 
 /* subtract preallocated bytes */
- writer.min_size -= max_char_size;
+ writer.min_size -= max_char_size * (newpos - startpos);
 
 if (PyBytes_Check(rep)) {
 p = _PyBytesWriter_WriteBytes(&writer, p,
@@ -402,14 +400,12 @@
 goto error;
 
 if (!PyUnicode_IS_ASCII(rep)) {
- raise_encode_exception(&exc, "utf-8",
- unicode,
- i-1, i,
+ raise_encode_exception(&exc, "utf-8", unicode,
+ startpos, endpos,
 "surrogates not allowed");
 goto error;
 }
 
- assert(PyUnicode_KIND(rep) == PyUnicode_1BYTE_KIND);
 p = _PyBytesWriter_WriteBytes(&writer, p,
 PyUnicode_DATA(rep),
 PyUnicode_GET_LENGTH(rep));
@@ -463,8 +459,6 @@
 _PyBytesWriter_Dealloc(&writer);
 return NULL;
 #endif
-
-#undef MAX_SHORT_UNICHARS
 }
 
 /* The pattern for constructing UCS2-repeated masks. */
-- 
Repository URL: https://hg.python.org/cpython
