tris/recoll
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Textsplit: lost char at korean->ascii transition

Browse Source
This commit is contained in:
Jean-Francois Dockes 2020-04-10 14:54:13 +01:00
parent ec7379f837
commit eb53b598d6
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/common/textsplit.cpp
View File

@ -680,8 +680,8 @@ bool TextSplit::text_to_words(const string &in)
// nothing right after a CJK section). Because // nothing right after a CJK section). Because
// katakana-western transitions sometimes have no whitespace // katakana-western transitions sometimes have no whitespace
// (and maybe hangul too, but probably not). // (and maybe hangul too, but probably not).
if (prev_csc != CSC_CJK && csc != prev_csc && if (prev_csc != CSC_CJK && prev_csc != CSC_HANGUL &&
(m_wordLen || m_span.length())) { csc != prev_csc && (m_wordLen || m_span.length())) {
LOGDEB2("csc " << valToString(csc_names, csc) << " prev_csc " << LOGDEB2("csc " << valToString(csc_names, csc) << " prev_csc " <<
valToString(csc_names, prev_csc) << " wl " << valToString(csc_names, prev_csc) << " wl " <<
m_wordLen << " spl " << m_span.length() << endl); m_wordLen << " spl " << m_span.length() << endl);