ViniciusSouzaRoque commented on code in PR #12333:
URL: https://github.com/apache/arrow/pull/12333#discussion_r904856120
##########
cpp/src/gandiva/gdv_string_function_stubs.cc:
##########
@@ -449,6 +450,218 @@ const char* gdv_fn_initcap_utf8(int64_t context, const
char* data, int32_t data_
*out_len = out_idx;
return out;
}
+GANDIVA_EXPORT
+const char* translate_utf8_utf8_utf8(int64_t context, const char* in, int32_t
in_len,
+ const char* from, int32_t from_len, const
char* to,
+ int32_t to_len, int32_t* out_len) {
+ if (in_len <= 0) {
+ *out_len = 0;
+ return "";
+ }
+
+ if (from_len <= 0) {
+ *out_len = in_len;
+ return in;
+ }
+
+ // This variable is to control if there are multi-byte utf8 entries
+ bool has_multi_byte = false;
+
+ // This variable is to store the final result
+ char* result;
+ int result_len;
+
+ // Searching multi-bytes in In
+ for (int i = 0; i < in_len; i++) {
+ unsigned char char_single_byte = in[i];
+ if (char_single_byte > 127) {
+ // found a multi-byte utf-8 char
+ has_multi_byte = true;
+ break;
+ }
+ }
+
+ // Searching multi-bytes in From
+ for (int i = 0; i < from_len; i++) {
+ unsigned char char_single_byte = from[i];
+ if (char_single_byte > 127) {
+ // found a multi-byte utf-8 char
+ has_multi_byte = true;
+ break;
+ }
+ }
+
+ // Searching multi-bytes in To
+ for (int i = 0; i < to_len; i++) {
+ unsigned char char_single_byte = to[i];
+ if (char_single_byte > 127) {
+ // found a multi-byte utf-8 char
+ has_multi_byte = true;
+ break;
+ }
+ }
Review Comment:
@siddhantrao23 Yeah, is good. Done.
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
