void PreRanker::Filter(bool viewportSearch)
{
using TSet = set<impl::PreResult1, LessFeatureID>;
TSet theSet;
sort(m_results.begin(), m_results.end(), ComparePreResult1());
m_results.erase(unique(m_results.begin(), m_results.end(), EqualFeatureID()), m_results.end());
sort(m_results.begin(), m_results.end(), &impl::PreResult1::LessDistance);
if (m_limit != 0 && m_results.size() > m_limit)
{
// Priority is some kind of distance from the viewport or
// position, therefore if we have a bunch of results with the same
// priority, we have no idea here which results are relevant. To
// prevent bias from previous search routines (like sorting by
// feature id) this code randomly selects tail of the
// sorted-by-priority list of pre-results.
double const last = m_results[m_limit - 1].GetDistance();
auto b = m_results.begin() + m_limit - 1;
for (; b != m_results.begin() && b->GetDistance() == last; --b)
;
if (b->GetDistance() != last)
++b;
auto e = m_results.begin() + m_limit;
for (; e != m_results.end() && e->GetDistance() == last; ++e)
;
// The main reason of shuffling here is to select a random subset
// from the low-priority results. We're using a linear
// congruential method with default seed because it is fast,
// simple and doesn't need an external entropy source.
//
// TODO (@y, @m, @vng): consider to take some kind of hash from
// features and then select a subset with smallest values of this
// hash. In this case this subset of results will be persistent
// to small changes in the original set.
minstd_rand engine;
shuffle(b, e, engine);
}
theSet.insert(m_results.begin(), m_results.begin() + min(m_results.size(), m_limit));
if (!viewportSearch)
{
size_t n = min(m_results.size(), m_limit);
nth_element(m_results.begin(), m_results.begin() + n, m_results.end(),
&impl::PreResult1::LessRank);
theSet.insert(m_results.begin(), m_results.begin() + n);
}
m_results.reserve(theSet.size());
m_results.clear();
copy(theSet.begin(), theSet.end(), back_inserter(m_results));
}
/// delete p if it was already in set; return version in set.
T* insert(T* p) {
std::pair<typename TSet::iterator, bool> iNew = set_.insert(p);
if (iNew.second)
return p;
else {
delete p;
return *iNew.first;
}
}
bool FBullCowGame::IsIsogram(FString Guess) const {
if (Guess.length() < 2) return true;
TSet<char> set;
for (char Letter : Guess) {
Letter = tolower(Letter);
if (set.find(Letter) != set.end()) return false;
else set.insert(Letter);
}
}
void CCueDocument::GetMediaFiles(vector<std::string>& mediaFiles)
{
typedef set<std::string> TSet;
TSet uniqueFiles;
for (Tracks::const_iterator it = m_tracks.begin(); it != m_tracks.end(); ++it)
uniqueFiles.insert(it->strFile);
for (TSet::const_iterator it = uniqueFiles.begin(); it != uniqueFiles.end(); it++)
mediaFiles.push_back(*it);
}
TVector<TColumn> ReadCD(const TString& fileName, const TCdParserDefaults& defaults) {
CB_ENSURE(NFs::Exists(TString(fileName)), "column description file is not found");
int columnsCount = defaults.UseDefaultType ? defaults.ColumnCount : 0;
TVector<TColumn> columns(columnsCount, TColumn{defaults.DefaultColumnType, TString()});
TSet<int> parsedColumns;
TString line;
TIFStream reader(fileName.c_str());
while (reader.ReadLine(line)) {
TVector<TString> tokens;
try {
Split(line, "\t", tokens);
} catch (const yexception& e) {
MATRIXNET_DEBUG_LOG << "Got exception " << e.what() << " while parsing feature descriptions line " << line << Endl;
break;
}
if (tokens.empty()) {
continue;
}
CB_ENSURE(tokens.ysize() == 2 || tokens.ysize() == 3, "Each line should have two or three columns. " << line);
int index = FromString<int>(tokens[0]);
CB_ENSURE(index >= 0, "Invalid column index " << index);
if (defaults.UseDefaultType) {
CB_ENSURE(index < columnsCount, "Invalid column index " << index);
}
CB_ENSURE(!parsedColumns.has(index), "column specified twice in cd file: " << index);
parsedColumns.insert(index);
columns.resize(Max(columns.ysize(), index + 1));
TStringBuf type = tokens[1];
if (type == "QueryId") {
type = "GroupId";
}
if (type == "Target") {
type = "Label";
}
CB_ENSURE(TryFromString<EColumn>(type, columns[index].Type), "unsupported column type " << type);
if (tokens.ysize() == 3) {
columns[index].Id = tokens[2];
}
}
if (!defaults.UseDefaultType) {
CheckAllFeaturesPresent(columns, parsedColumns);
}
return columns;
}
