Make improvements

- wcsstr() is now linearly complex
- strstr16() is now linearly complex
- strstr() is now vectorized on aarch64 (10x)
- strstr() now uses KMP on pathological cases
- memmem() is now vectorized on aarch64 (10x)
- memmem() now uses KMP on pathological cases
- Disable shared_ptr::owner_before until fixed
- Make iswlower(), iswupper() consistent with glibc
- Remove figure space from iswspace() implementation
- Include line and paragraph separator in iswcntrl()
- Use Musl wcwidth(), iswalpha(), iswpunct(), towlower(), towupper()
This commit is contained in:
Justine Tunney 2024-09-01 01:14:40 -07:00
parent e1528a71e2
commit 7c83f4abc8
No known key found for this signature in database
GPG key ID: BE714B4575D6E328
67 changed files with 5602 additions and 5165 deletions

View file

@ -16,9 +16,11 @@
TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
PERFORMANCE OF THIS SOFTWARE.
*/
#include "libc/stdio/stdio.h"
#include "libc/str/str.h"
#include "libc/str/strwidth.h"
#include "libc/str/unicode.h"
#include "libc/testlib/benchmark.h"
#include "libc/testlib/ezbench.h"
#include "libc/testlib/testlib.h"
@ -28,6 +30,7 @@ TEST(wcwidth, test) {
ASSERT_EQ(-1, wcwidth(-7));
ASSERT_EQ(1, wcwidth(0x10FFFD));
ASSERT_EQ(-1, wcwidth(0x10FFFD + 1));
ASSERT_EQ(2, wcwidth(L'😀'));
}
TEST(strwidth, testCjkWidesAndCombiningLowLines_withThompsonPikeEncoding) {
@ -74,6 +77,12 @@ TEST(strwidth, testTextDelimitingControlCodes_dontHaveSubstance) {
EXPECT_EQ(0, strwidth("\1", 0));
}
#define WCWIDTH(x) __expropriate(wcwidth(__veil("r", x)))
BENCH(wcwidth, bench) {
EZBENCH2("wcwidth", donothing, __expropriate(wcwidth(__veil("r", u''))));
BENCHMARK(1000, 1, WCWIDTH(u'a'));
BENCHMARK(1000, 1, WCWIDTH(u'a'));
BENCHMARK(1000, 1, WCWIDTH(u''));
BENCHMARK(1000, 1, WCWIDTH(L'😀'));
BENCHMARK(1000, 1, WCWIDTH(0));
}