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

limit max size of korean single-word span

Browse Source
This commit is contained in:
Jean-Francois Dockes 2020-05-31 09:57:58 +02:00
parent 8faababeb3
commit f3858a7e3a
1 changed files with 7 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
src/common/textsplitko.cpp
View File

@ -283,7 +283,13 @@ bool TextSplit::ko_to_words(Utf8Iter *itp, unsigned int *cp)
span = inputdata.substr(it->first, it->second-it->first); span = inputdata.substr(it->first, it->second-it->first);
LOGKO("KO: SPAN: [" << span << "] pos " << m_wordpos << LOGKO("KO: SPAN: [" << span << "] pos " << m_wordpos <<
" bytepos " << bytepos << "\n"); " bytepos " << bytepos << "\n");
if (!takeword(span, m_wordpos, abspos, abspos + span.size())) { // Xapian max term length is 245 bytes. textsplit default
// max word is 40 bytes. Let's take into account the
// longer utf-8 Korean chars (usually 3 bytes).
if (int(span.size()) > 3 * o_maxWordLength) {
LOGINF("kosplitter: dropping span too long: " << span);
} else if (!takeword(
span, m_wordpos, abspos, abspos + span.size())) {
return false; return false;
} }
} }