bool cut(Unicode::const_iterator begin, Unicode::const_iterator end, vector<Unicode>& res) const
{
#ifndef NO_CODING_LOG
if (!_getInitFlag())
{
LogError("not inited.");
return false;
}
if (begin > end)
{
LogError("begin > end");
return false;
}
#endif
//use hmm cut first
vector<Unicode> hmmRes;
if (!_hmmSeg.cut(begin, end, hmmRes))
{
LogError("_hmmSeg cut failed.");
return false;
}
vector<Unicode> fullRes;
for (vector<Unicode>::const_iterator hmmResItr = hmmRes.begin(); hmmResItr != hmmRes.end(); hmmResItr++)
{
// if it's too long, cut with _fullSeg, put fullRes in res
if (hmmResItr->size() > _maxWordLen)
{
if (_fullSeg.cut(hmmResItr->begin(), hmmResItr->end(), fullRes))
{
for (vector<Unicode>::const_iterator fullResItr = fullRes.begin(); fullResItr != fullRes.end(); fullResItr++)
{
res.push_back(*fullResItr);
}
}
}
else // just use the hmm result
{
res.push_back(*hmmResItr);
}
}
return true;
}
bool cut(Unicode::const_iterator begin, Unicode::const_iterator end, vector<Unicode>& res) const
{
assert(_getInitFlag());
if (begin >= end)
{
LogError("begin >= end");
return false;
}
//use mix cut first
vector<Unicode> mixRes;
if (!_mixSeg.cut(begin, end, mixRes))
{
LogError("_mixSeg cut failed.");
return false;
}
vector<Unicode> fullRes;
for (vector<Unicode>::const_iterator mixResItr = mixRes.begin(); mixResItr != mixRes.end(); mixResItr++)
{
// if it's too long, cut with _fullSeg, put fullRes in res
if (mixResItr->size() > _maxWordLen)
{
if (_fullSeg.cut(mixResItr->begin(), mixResItr->end(), fullRes))
{
for (vector<Unicode>::const_iterator fullResItr = fullRes.begin(); fullResItr != fullRes.end(); fullResItr++)
{
res.push_back(*fullResItr);
}
//clear tmp res
fullRes.clear();
}
}
else // just use the mix result
{
res.push_back(*mixResItr);
}
}
return true;
}