sagnikc-dremio commented on a change in pull request #7641:
URL: https://github.com/apache/arrow/pull/7641#discussion_r459373149
##########
File path: cpp/src/gandiva/precompiled/string_ops.cc
##########
@@ -305,21 +342,161 @@ const char* trim_utf8(gdv_int64 context, const char*
data, gdv_int32 data_len,
--end;
}
- // string with no leading/trailing spaces, return original string
- if (start == 0 && end == data_len - 1) {
- *out_len = data_len;
- return data;
+ // string has some leading/trailing spaces and some non-space characters
+ *out_len = end - start + 1;
+ return data + start;
+}
+
+// Trims characters present in the trim text from the left end of the base text
+FORCE_INLINE
+const char* ltrim_utf8_utf8(gdv_int64 context, const char* basetext,
+ gdv_int32 basetext_len, const char* trimtext,
+ gdv_int32 trimtext_len, int32_t* out_len) {
+ if (basetext_len == 0) {
+ *out_len = 0;
+ return "";
+ } else if (trimtext_len == 0) {
+ *out_len = basetext_len;
+ return basetext;
+ }
+
+ gdv_int32 start_ptr, char_len;
+ // scan the base text from left to right and increment the start pointer till
+ // there is a character which is not present in the trim text
+ for (start_ptr = 0; start_ptr < basetext_len; start_ptr += char_len) {
+ char_len = utf8_char_length(basetext[start_ptr]);
+ if (char_len == 0 || start_ptr + char_len > basetext_len) {
+ // invalid byte or incomplete glyph
+ set_error_for_invalid_utf(context, basetext[start_ptr]);
+ *out_len = 0;
+ return "";
+ }
+ for (gdv_int32 char_ptr = 1; char_ptr < char_len; ++char_ptr) {
Review comment:
Removed the check.
----------------------------------------------------------------
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:
us...@infra.apache.org
