Skip to content

Commit

Permalink
Merge 408cc7a into 7551fc5
Browse files Browse the repository at this point in the history
  • Loading branch information
tomatolog committed Jul 4, 2024
2 parents 7551fc5 + 408cc7a commit 2589034
Show file tree
Hide file tree
Showing 12 changed files with 772 additions and 153 deletions.
8 changes: 4 additions & 4 deletions src/dict/template_dict_traits.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -522,7 +522,7 @@ void TemplateDictTraits_c::LoadStopwords ( const char * sFiles, FilenameBuilder_

// tokenize stopwords line by line to prevent exceptions to fold multiple lines
sphSplitApply ( (const char *)dBuffer.Begin(), iLength, "\r\n", [&] ( const char * sLine, int iLineLen )
{
{
BYTE* pToken;
pTokenizerClone->SetBuffer ( (const BYTE *)sLine, iLineLen );
while ( ( pToken = pTokenizerClone->GetToken() ) != nullptr )
Expand Down Expand Up @@ -686,7 +686,7 @@ void TemplateDictTraits_c::AddWordform ( CSphWordforms* pContainer, char* sBuffe
if ( !dTokens.GetLength() )
{
if ( !bCommentedWholeLine )
sphWarning ( "table '%s': all source tokens are stopwords (wordform='%s', file='%s'). IGNORED.", pContainer->m_sIndexName.cstr(), sBuffer, szFile );
sphWarning ( "table '%s': all wordform source tokens are stopwords (wordform='%s', file='%s'). IGNORED.", pContainer->m_sIndexName.cstr(), sBuffer, szFile );
return;
}

Expand Down Expand Up @@ -915,7 +915,7 @@ CSphWordforms* TemplateDictTraits_c::LoadWordformContainer ( const CSphVector<CS

TokenizerRefPtr_c pMyTokenizer = pTokenizer->Clone ( SPH_CLONE_INDEX );
const CSphTokenizerSettings& tSettings = pMyTokenizer->GetSettings();

CSphVector<int> dBlended;

// get a list of blend chars and set add them to the tokenizer as simple chars
Expand Down Expand Up @@ -1276,4 +1276,4 @@ void sphShutdownWordforms()
void SetupLemmatizerBase()
{
g_sLemmatizerBase = GET_FULL_SHARE_DIR();
}
}
Loading

0 comments on commit 2589034

Please sign in to comment.