guyuqi commented on a change in pull request #7121:
URL: https://github.com/apache/arrow/pull/7121#discussion_r429709020
##########
File path: cpp/src/arrow/util/utf8.h
##########
@@ -171,6 +172,99 @@ inline bool ValidateUTF8(const util::string_view& str) {
return ValidateUTF8(data, length);
}
+inline bool ValidateAsciiSw(const uint8_t* data, int64_t len) {
+ uint8_t orall = 0;
+
+ if (len >= 16) {
+ uint64_t or1 = 0, or2 = 0;
+ const uint8_t* data2 = data + 8;
+
+ do {
+ or1 |= *(const uint64_t*)data;
+ or2 |= *(const uint64_t*)data2;
+ data += 16;
+ data2 += 16;
+ len -= 16;
+ } while (len >= 16);
+
+ orall = !((or1 | or2) & 0x8080808080808080ULL) - 1;
+ }
+
+ while (len--) orall |= *data++;
Review comment:
Thanks, @wesm !
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
