projjal commented on a change in pull request #7641:
URL: https://github.com/apache/arrow/pull/7641#discussion_r457847628
##########
File path: cpp/src/gandiva/precompiled/string_ops.cc
##########
@@ -322,6 +387,138 @@ const char* trim_utf8(gdv_int64 context, const char*
data, gdv_int32 data_len,
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 (!is_substr_utf8_utf8(trimtext, trimtext_len, basetext + start_ptr,
char_len)) {
+ break;
+ }
+ }
+
+ // the first character from the left is not present in the trim text,
+ // hence there is nothing to be trimmed, return original string
+ if (start_ptr == 0) {
+ *out_len = basetext_len;
+ return basetext;
+ }
+
+ // all the characters in the base text are present in the trim text,
+ // hence trim the entire string, return empty string
+ if (start_ptr == trimtext_len) {
+ *out_len = 0;
+ return "";
+ }
+
+ // base text has some characters which are not present in the trim text
+ *out_len = basetext_len - start_ptr;
+ return basetext + start_ptr;
+}
+
+// Trims characters present in the trim text from the right end of the base
text
+FORCE_INLINE
+const char* rtrim_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 end_cnt, char_len, end_ptr = 0;
+ // scan the base text from left to right and increment the end pointer to
the current
+ // position when there is a character which is not present in the trim text
+ for (end_cnt = 0; end_cnt < basetext_len; end_cnt += char_len) {
Review comment:
You can go back byte by byte and check in the trim set if the current
byte is the first byte in utf8 char.
```
while (end >= start) {
int char_len = utf8_char_len(end);
if (char_len == 0) {end—; break;} // trailing byte in mutlitbyte char
if (char, char_len) present in (trim, trim_len) break;
end—;```
----------------------------------------------------------------
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
