Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

opt: full text index compact #1040

Merged
merged 2 commits into from
Aug 5, 2023
Merged

opt: full text index compact #1040

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a8c3207
opt: full text index compact
xiaoyifang Aug 5, 2023
43b070a
fix: code smells
xiaoyifang Aug 5, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
19 changes: 19 additions & 0 deletions src/common/utils.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,4 +68,23 @@ std::string basename( std::string const & str )
return std::string( str, x + 1 );
}

void removeDirectory( QString const & directory )
{
QDir dir( directory );
Q_FOREACH ( QFileInfo info,
dir.entryInfoList( QDir::NoDotAndDotDot | QDir::AllDirs | QDir::Files, QDir::DirsFirst ) ) {
if ( info.isDir() )
removeDirectory( info.absoluteFilePath() );
else
QFile::remove( info.absoluteFilePath() );
}

dir.rmdir( directory );
}

void removeDirectory( string const & directory )
{
removeDirectory( QString::fromStdString( directory ) );
}

} // namespace Utils::Fs
2 changes: 2 additions & 0 deletions src/common/utils.hh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -332,7 +332,9 @@ char separator();

/// Returns the name part of the given filename.
string basename( string const & );
void removeDirectory( QString const & directory );

void removeDirectory( string const & directory );
} // namespace Fs

} // namespace Utils
Expand Down
53 changes: 5 additions & 48 deletions src/ftshelpers.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,10 +14,6 @@
#include <vector>
#include <string>


#include <QRegularExpression>


using std::vector;
using std::string;

Expand Down Expand Up @@ -49,49 +45,6 @@ bool ftsIndexIsOldOrBad( BtreeIndexing::BtreeDictionary * dict )
}
}


void tokenizeCJK( QStringList & indexWords, QRegularExpression wordRegExp, QStringList list )
{
QStringList wordList, hieroglyphList;
for ( auto word : list ) {
// Check for CJK symbols in word
bool parsed = false;
QString hieroglyph;
for ( int x = 0; x < word.size(); x++ )
if ( Utils::isCJKChar( word.at( x ).unicode() ) ) {
parsed = true;
hieroglyph.append( word[ x ] );

if ( QChar( word.at( x ) ).isHighSurrogate() && QChar( word[ x + 1 ] ).isLowSurrogate() )
hieroglyph.append( word[ ++x ] );

hieroglyphList.append( hieroglyph );
hieroglyph.clear();
}

// If word don't contains CJK symbols put it in list as is
if ( !parsed )
wordList.append( word );
}

indexWords = wordList.filter( wordRegExp );
indexWords.removeDuplicates();

hieroglyphList.removeDuplicates();
indexWords += hieroglyphList;
}

bool containCJK( QString const & str )
{
bool hasCJK = false;
for ( auto x : str )
if ( Utils::isCJKChar( x.unicode() ) ) {
hasCJK = true;
break;
}
return hasCJK;
}

void makeFTSIndex( BtreeIndexing::BtreeDictionary * dict, QAtomicInt & isCancelled )
{
QMutexLocker _( &dict->getFtsMutex() );
Expand All @@ -105,7 +58,7 @@ void makeFTSIndex( BtreeIndexing::BtreeDictionary * dict, QAtomicInt & isCancell
throw exUserAbort();

// Open the database for update, creating a new database if necessary.
Xapian::WritableDatabase db( dict->ftsIndexName(), Xapian::DB_CREATE_OR_OPEN );
Xapian::WritableDatabase db( dict->ftsIndexName() + "_temp", Xapian::DB_CREATE_OR_OPEN );

Xapian::TermGenerator indexer;
// Xapian::Stem stemmer("english");
Expand Down Expand Up @@ -206,6 +159,10 @@ void makeFTSIndex( BtreeIndexing::BtreeDictionary * dict, QAtomicInt & isCancell
offsets.clear();

db.commit();

db.compact( dict->ftsIndexName() );

Utils::Fs::removeDirectory( dict->ftsIndexName() + "_temp" );
}
catch ( Xapian::Error & e ) {
qWarning() << "create xapian index:" << QString::fromStdString( e.get_description() );
Expand Down