d/freebsd-skq
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

minor perf enhancement for UTF-8

Browse Source 
Reduce some duplicate code.

Reference:
https://www.illumos.org/issues/628

Obtained from:	Illumos
MFC after:	1 week
This commit is contained in:
Pedro F. Giffuni 2014-07-04 22:39:39 +00:00
parent a913717b0d
commit 0716c0ff7a
1 changed files with 10 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
lib/libc/locale/utf8.c
View File

@ -1,4 +1,5 @@
/*-
* Copyright 2011 Nexenta Systems, Inc. All rights reserved.
* Copyright (c) 2002-2004 Tim J. Robbins
* All rights reserved.
*
@ -112,13 +113,6 @@ _UTF8_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, size_t n,
/* Incomplete multibyte sequence */
return ((size_t)-2);
if (us->want == 0 && ((ch = (unsigned char)*s) & ~0x7f) == 0) {
/* Fast path for plain ASCII characters. */
if (pwc != NULL)
*pwc = ch;
return (ch != '\0' ? 1 : 0);
}
if (us->want == 0) {
/*
* Determine the number of octets that make up this character
@ -134,10 +128,12 @@ _UTF8_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, size_t n,
*/
ch = (unsigned char)*s;
if ((ch & 0x80) == 0) {
mask = 0x7f;
want = 1;
lbound = 0;
} else if ((ch & 0xe0) == 0xc0) {
/* Fast path for plain ASCII characters. */
if (pwc != NULL)
*pwc = ch;
return (ch != '\0' ? 1 : 0);
}
if ((ch & 0xe0) == 0xc0) {
mask = 0x1f;
want = 2;
lbound = 0x80;
@ -316,12 +312,6 @@ _UTF8_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps)
/* Reset to initial shift state (no-op) */
return (1);
if ((wc & ~0x7f) == 0) {
/* Fast path for plain ASCII characters. */
*s = (char)wc;
return (1);
}
/*
* Determine the number of octets needed to represent this character.
* We always output the shortest sequence possible. Also specify the
@ -329,8 +319,9 @@ _UTF8_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps)
* about the sequence length.
*/
if ((wc & ~0x7f) == 0) {
lead = 0;
len = 1;
/* Fast path for plain ASCII characters. */
*s = (char)wc;
return (1);
} else if ((wc & ~0x7ff) == 0) {
lead = 0xc0;
len = 2;