airborne12 commented on code in PR #67918:
URL: https://github.com/apache/doris/pull/67918#discussion_r4065265333
##########
be/src/storage/index/inverted/token_filter/pinyin_filter.cpp:
##########
@@ -214,29 +236,97 @@ bool PinyinFilter::readTerm(Token* token) {
return false;
}
-bool PinyinFilter::processCurrentToken() {
- processed_candidate_ = true;
+bool PinyinFilter::prepareCurrentSource(std::vector<UChar32>&
source_codepoints) {
+ size_t source_start = 0;
+ size_t source_end = current_token_text_.size();
+ if (config_->trimWhitespace) {
+ source_start = current_token_text_.find_first_not_of(" \t\n\r");
+ if (source_start == std::string::npos) {
+ return false;
+ }
+ source_end = current_token_text_.find_last_not_of(" \t\n\r") + 1;
+ }
+ current_source_ = current_token_text_.substr(source_start, source_end -
source_start);
- if (!has_current_token_) {
+ if (current_source_.empty()) {
return false;
}
- current_source_ = current_token_text_;
+ if (config_->ignorePinyinOffset) {
+ convertToCodepoints(current_source_, source_codepoints);
+ current_start_offset_ += static_cast<int32_t>(source_start);
Review Comment:
Fixed in 31450230. When `ignore_pinyin_offset` is enabled, Pinyin now
preserves the upstream token source span instead of adding trim counts from
transformed bytes. The new ICU-normalizer test uses U+3000 around a CJK rune
and verifies the emitted Pinyin keeps source span `[0,9)`.
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
