zzzxl1993 commented on code in PR #50141:
URL: https://github.com/apache/doris/pull/50141#discussion_r2063112408
##########
be/src/olap/rowset/segment_v2/inverted_index/analyzer/ik/core/CharacterUtil.cpp:
##########
@@ -20,77 +20,50 @@
namespace doris::segment_v2 {
int32_t CharacterUtil::identifyCharType(int32_t rune) {
- // Numbers
- if (rune >= 0x30 && rune <= 0x39) {
+ if (rune >= '0' && rune <= '9') {
return CHAR_ARABIC;
}
-
- // English
- if ((rune >= 0x61 && rune <= 0x7a) || (rune >= 0x41 && rune <= 0x5a)) {
+ if ((rune >= 'a' && rune <= 'z') || (rune >= 'A' && rune <= 'Z')) {
return CHAR_ENGLISH;
}
- // CJK Unified Chinese Characters
- if ((rune >= 0x4E00 && rune <= 0x9FFF) || (rune >= 0x3400 && rune <=
0x4DBF) ||
- (rune >= 0x20000 && rune <= 0x2A6DF) || (rune >= 0x2A700 && rune <=
0x2B73F) ||
- (rune >= 0x2B740 && rune <= 0x2B81F) || (rune >= 0x2B820 && rune <=
0x2CEAF) ||
- (rune >= 0x2CEB0 && rune <= 0x2EBEF) || (rune >= 0x30000 && rune <=
0x3134F)) {
+ UBlockCode block = ublock_getCode(rune);
+
+ if (block == UBLOCK_CJK_UNIFIED_IDEOGRAPHS || block ==
UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS ||
Review Comment:
Should we extend the Chinese character checks to include more Unicode
blocks? For example, currently we're missing characters like 𠮷 (U+20BB7) from
Extension B that some users might need.
--
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: commits-unsubscr...@doris.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@doris.apache.org
For additional commands, e-mail: commits-h...@doris.apache.org
