pitrou commented on code in PR #13497:
URL: https://github.com/apache/arrow/pull/13497#discussion_r918638883
##########
cpp/src/gandiva/gdv_string_function_stubs.cc:
##########
@@ -264,6 +265,304 @@ const char* gdv_fn_lower_utf8(int64_t context, const
char* data, int32_t data_le
return out;
}
+// converts utf8 to utf16 encoding
+GANDIVA_EXPORT
+const char* gdv_fn_encode(int64_t context, const char* data, int32_t data_len,
+ const char* charset, int32_t charset_len, int32_t*
out_len) {
+ if (data_len == 0) {
+ *out_len = 0;
+ return "";
+ }
+
+ char* out =
+ reinterpret_cast<char*>(gdv_fn_context_arena_malloc(context, 32 *
data_len));
+ if (out == nullptr) {
+ gdv_fn_context_set_error_msg(context, "Could not allocate memory for
output string");
+ *out_len = 0;
+ return "";
+ }
+
+ int32_t char_len;
+ uint32_t char_codepoint;
+ int32_t y = 5;
+ int32_t z = 9;
+
+ std::string charset_str(charset, charset_len);
+
+ if (boost::iequals(charset_str, "UTF-16BE")) {
+ char* tmp = out;
+
+ int ind_w = 0;
+
+ for (int32_t i = 0; i < data_len; i += char_len) {
+ char_len = gdv_fn_utf8_char_length(data[i]);
+
+ if (char_len == 1) {
+ int32_t input = static_cast<int32_t>(data[i]);
+
+ auto num_bytes = snprintf(tmp + ind_w, y, "%.4X", input);
Review Comment:
Well, first, the question is why we would want to output hex-encoded data in
this function? Why would people interested in utf16 data want their data
hex-encoded?
--
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]
