From d58fec0b819471139006cc5839b3641d76c5059d Mon Sep 17 00:00:00 2001 From: Jean-Francois Dockes Date: Mon, 11 May 2020 07:33:54 +0200 Subject: [PATCH] korean: for now dont filter tags, until it is better understood what should be done --- src/common/textsplitko.cpp | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/src/common/textsplitko.cpp b/src/common/textsplitko.cpp index ae7f2622..eba7d4d9 100644 --- a/src/common/textsplitko.cpp +++ b/src/common/textsplitko.cpp @@ -231,8 +231,10 @@ bool TextSplit::ko_to_words(Utf8Iter *itp, unsigned int *cp) } lastNoun.clear(); } - if (isNoun || tags[i] == "Verb" || - tags[i] == "Adjective" || tags[i] == "Adverb") { + // 11/05/2020 For now index everything until more precise + // verification of what should be pruned + if (true || (isNoun || tags[i] == "Verb" || + tags[i] == "Adjective" || tags[i] == "Adverb")) { string::size_type abspos = orgbytepos + bytepos - pagefix; if (!takeword(word, m_wordpos++, abspos, abspos + word.size())) { return false;