mirror of
https://github.com/jart/cosmopolitan.git
synced 2025-07-06 19:28:29 +00:00
Make improvements
- Introduce ualarm() function - Make rename() report EISEMPTY on Windows - Always raise EINVAL upon open(O_RDONLY|O_TRUNC) - Add macro so ./configure will detect SOCK_CLOEXEC - Fix O_TRUNC without O_CREAT not working on Windows - Let fcntl(F_SETFL) change O_APPEND status on Windows - Make sure pwrite() / pread() report ESPIPE on sockets - Raise ESPIPE on Windows when pwrite() is used on pipe - Properly compute O_APPEND CreateFile() flags on Windows - Don't require O_DIRECTORY to open directories on Windows - Fix more instances of Windows reporting EISDIR and ENOTDIR - Normalize EFTYPE and EMLINK to ELOOP on NetBSD and FreeBSD - Make unlink() / rmdir() work on read-only files on Windows - Validate UTF-8 on Windows paths to fix bug with overlong NUL - Always print signal name to stderr when crashing due to SIG_DFL - Fix Windows bug where denormalized paths >260 chars didn't work - Block signals on BSDs when thread exits before trashing its own stack
This commit is contained in:
parent
ec957491ea
commit
ebf784d4f5
76 changed files with 1019 additions and 568 deletions
|
@ -21,8 +21,6 @@
|
|||
#include "libc/intrin/likely.h"
|
||||
#include "libc/str/str.h"
|
||||
|
||||
typedef char xmm_t __attribute__((__vector_size__(16), __aligned__(16)));
|
||||
|
||||
static const char kUtf8Dispatch[] = {
|
||||
0, 0, 1, 1, 1, 1, 1, 1, // 0300 utf8-2
|
||||
1, 1, 1, 1, 1, 1, 1, 1, // 0310
|
||||
|
@ -37,10 +35,10 @@ static const char kUtf8Dispatch[] = {
|
|||
/**
|
||||
* Returns true if text is utf-8.
|
||||
*
|
||||
* _isutf8 n=0 1 nanoseconds
|
||||
* _isutf8 n=5 661 ps/byte 1,476 mb/s
|
||||
* _isutf8 ascii n=22851 26 ps/byte 35 GB/s
|
||||
* _isutf8 unicode n=3193 543 ps/byte 1,795 mb/s
|
||||
* isutf8 n=0 1 nanoseconds
|
||||
* isutf8 n=5 661 ps/byte 1,476 mb/s
|
||||
* isutf8 ascii n=22851 26 ps/byte 35 GB/s
|
||||
* isutf8 unicode n=3193 543 ps/byte 1,795 mb/s
|
||||
*
|
||||
* This function considers all ASCII characters including NUL to be
|
||||
* valid UTF-8. The conditions for something not being valid are:
|
||||
|
@ -51,7 +49,7 @@ static const char kUtf8Dispatch[] = {
|
|||
*
|
||||
* @param size if -1 implies strlen
|
||||
*/
|
||||
dontasan bool _isutf8(const void *data, size_t size) {
|
||||
dontasan bool isutf8(const void *data, size_t size) {
|
||||
long c;
|
||||
unsigned m;
|
||||
const char *p, *e;
|
||||
|
@ -61,6 +59,7 @@ dontasan bool _isutf8(const void *data, size_t size) {
|
|||
e = p + size;
|
||||
while (p < e) {
|
||||
#if defined(__x86_64__) && !defined(__chibicc__)
|
||||
typedef char xmm_t __attribute__((__vector_size__(16), __aligned__(16)));
|
||||
if (!((intptr_t)p & 15)) {
|
||||
for (;;) {
|
||||
if ((m = __builtin_ia32_pmovmskb128(*(xmm_t *)p >= (xmm_t){0}) ^
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue