void CopyWordCounts( WordCount& targetWordCount, WordCount& sourceWordCount, int weight )
{
for( wciter iwc=sourceWordCount.begin(); iwc!=sourceWordCount.end(); iwc++ )
{
if( targetWordCount.find( iwc->first ) == targetWordCount.end() )
targetWordCount[ iwc->first ] = 0;
targetWordCount[ iwc->first ] += weight * iwc->second;
}
}
int main(int argc, char* argv[])
{
timeval start,end;
double difference,t1,t2;
char *str1;
string str2;
int cnt=1;
int i=0;
if(argc!=2)
{
cout<<"Please enter an input file :-";
return 0;
}
str1=argv[1];
FileReader reader; //Instantiate class FileReadermas
std::string s=reader.readFile(str1); //Call to function read
WordCount word; //Instantiate class word
gettimeofday(&start, NULL);
t1 = start.tv_sec + start.tv_usec/1000000.0;
word.count(s); //call to function count
t2 = end.tv_sec + end.tv_usec/1000000.0;
difference=t2 - t1;
//cout<<"Map time:"<<difference*1000000<<" microseconds"<<endl;
Node* n;
Tree* t = new Tree();
stringstream str(s);
gettimeofday(&start, NULL);
t1 = start.tv_sec + start.tv_usec/1000000.0;
while(str>>str2)
{
t->insert(pair<string,int>(str2,cnt));
}
t2 = end.tv_sec + end.tv_usec/1000000.0;
difference=t2 - t1;
//cout<<"Red Black Tree time:"<<difference*1000000<<" microseconds"<<endl;
t->inorder(t->getRoot());
//t->height(t->getRoot());
return 0;
}
void DumpPositionTable( PositionText& ptext )
{
for( ptiter ip=ptext.begin(); ip!=ptext.end(); ip++ )
{
cout << "DumpPositionTable for key value ='" << ip->first << "'" << endl;
WordCount* wc = ip->second;
for( wciter iwc=wc->begin(); iwc!=wc->end(); iwc++ )
{
cout << iwc->first << ": " << iwc->second << endl;
}
}
}
int main(int argc, const char *argv[])
{
WordCount count;
string infile;
cout << "Input a filename to read:" << endl;
cin >> infile;
count.readfile(infile);
string outfile;
cout << "Input a filename to write:" << endl;
cin >> outfile;
count.writefile(outfile);
return 0;
}
string GetMaxWord( WordCount& wordCount )
{
string word;
int maxCount = 0;
for( wciter iwc=wordCount.begin(); iwc!=wordCount.end(); iwc++ )
{
// cout << iwc->first << ": " << iwc->second << endl;
if( iwc->second > maxCount )
{
word = iwc->first;
maxCount = iwc->second;
}
}
return word;
}
// impl by chenshuo
void sort_words_by_frequencies(const WordCount& counts)
{
typedef std::vector<std::pair<int, WordCount::const_iterator> > FreqList;
FreqList freq;
freq.reserve(counts.size());
for (WordCount::const_iterator it = counts.begin(); it != counts.end(); ++it)
{
freq.push_back(make_pair(it->second, it));
}
std::sort(freq.begin(), freq.end(), Greater());
for (FreqList::iterator itr = freq.begin(); itr!=freq.end(); ++itr)
{
std::cout << itr->first << '\t' << itr->second->first << '\n';
}
}
void TranslateNumber::Translate(char buffer)
{
extern vector <DataBase> m_NumLib;
WordCount Wc;
ToSTL stl;
stl.GetData(NumPrefix);
Wc.AddWordNumber();
for (int i = 0;i < m_NumLib.size();i++)
{
if (buffer == m_NumLib[i].Ch[0])
{
stl.GetData(m_NumLib[i].Value);
Wc.AddWordNumber();
break;
}
}
}
int show(int ac, const char ** av, std::vector<Summary> * sum)
{
int level = 1;
if ( ac > 1 ) level = std::atoi(av[1]);
cout << "\nFluency Bad Need New Old When Name\n";
cout << "=====================================================\n";
Show data;
WordCount wc;
showr(".", data, level, sum, &wc);
cout << "-----------------------------------------------------\n";
output_les_stat(data.st, data.flue);
cout << '\n';
cout << '\n' << wc.str() << '\n';
return 0;
}
int main(int argc, char* argv[])
{
char *str1;
if(argc!=2)
{
cout<<"Please enter an input file :-";
return 0;
}
str1=argv[1];
FileReader reader; //Instantiate class FileReader
std::string s=reader.readFile(str1);//Call to function read
WordCount word; //Instantiate class word
word.count(s); //call to function count
return 0;
}
int wordc(int ac, const char ** av)
{
if (ac < 2)
{
cout << "Use: -wc {srt or txt file}\n";
cout << "word count statistics\n";
return 1;
}
string fi = av[1];
bool srt = false;
try
{
int sz = fi.size();
if ( sz < 5 ) throw 1;
if ( fi.substr(sz - 4) == ".srt" ) srt = true;
}
catch (int)
{
throw "Input file must be .srt or .txt";
}
cout << "Input : " << fi << '\n';
WordCount wc;
if (srt)
{
Lesson si(fi, true, true);
wc = si.wordcount();
}
else
{
wc = wordcount(gl::file2str(fi));
}
cout << wc.str() << '\n';
return 0;
}
string GetRandWord( WordCount& wordCount, int accumulation )
{
WordCount wordTable;
int totalCount = 0;
// cout << "-----[ RANDOM TABLE ]-----" << endl;
int terminalWeight = 0;
if( accumulation > 5 )
{
int distance = accumulation - 5;
terminalWeight = distance * distance * distance;
}
for( wciter iwc=wordCount.begin(); iwc!=wordCount.end(); iwc++ )
{
totalCount += iwc->second * iwc->second;
if( iwc->first == BEGIN_KEY || iwc->first == END_KEY )
{
totalCount += terminalWeight;
}
wordTable[ iwc->first ] = totalCount;
// cout << totalCount << " " << iwc->first << endl;
}
int roll = rand() % totalCount;
// cout << " --> roll: " << roll << endl;
totalCount = 0;
string word;
// cout << "-----[ SAME TABLE? ]-----" << endl;
for( wciter iwc=wordTable.begin(); iwc!=wordTable.end(); iwc++ )
{
// cout << iwc->second << " " << iwc->first << endl;
if( roll <= iwc->second )
{
word = iwc->first;
break;
}
}
// cout << " --> word: " << word << endl;
return word;
}
void ExtractLex::Process(WordCount &wcIn, const std::string *out)
{
std::map<const std::string*, WordCount> &collOut = wcIn.GetColl();
WordCount &wcOut = collOut[out];
wcOut.AddCount(COUNT_INCR);
}
int main( int argc, char* argv[] )
{
bool isEnd;
string triplet, pair, token, word;
string peripenultimate = WORD_KEY;
string penultimate = WORD_KEY;
string previous = BEGIN_KEY;
WordCount mainWordCount;
while( true )
{
cin >> token;
if( token == END_KEY )
break;
word = Convert( token, isEnd );
cout << "READ WORD FROM INPUT: " << word << endl;
if( mainWordCount.find( word ) == mainWordCount.end() )
{
mainWordCount[ word ] = 0;
}
++mainWordCount[ word ];
AddCount( PreText, word, previous );
AddCount( PostText, previous, word );
if( penultimate != WORD_KEY )
{
pair = previous + " " + word;
AddCount( PrePairText, pair, penultimate );
pair = penultimate + " " + previous;
AddCount( PostPairText, pair, word );
if( penultimate != WORD_KEY )
{
triplet = penultimate + " " + previous + " " + word;
AddCount( PreTripletText, triplet, peripenultimate );
triplet = peripenultimate + " " + penultimate + " " + previous;
AddCount( PostTripletText, triplet, word );
}
}
if( isEnd )
{
AddCount( PostText, word, END_KEY );
if( previous != WORD_KEY )
{
pair = previous + " " + word;
AddCount( PostPairText, pair, END_KEY );
if( penultimate != WORD_KEY )
{
triplet = penultimate + " " + previous + " " + word;
AddCount( PostTripletText, triplet, END_KEY );
}
}
previous = BEGIN_KEY;
peripenultimate = WORD_KEY;
penultimate = WORD_KEY;
}
else
{
peripenultimate = penultimate;
penultimate = previous;
previous = word;
}
}
// cout << endl;
cout << "PreText" << endl;
DumpPositionTable( PreText );
cout << "PostText" << endl;
DumpPositionTable( PostText );
cout << "PrePairText" << endl;
DumpPositionTable( PrePairText );
cout << "PostPairText" << endl;
DumpPositionTable( PostPairText );
cout << "PreTripletText" << endl;
DumpPositionTable( PreTripletText );
cout << "PostTripletText" << endl;
DumpPositionTable( PostTripletText );
while(1)
{
cin >> word;
if( word == END_KEY )
break;
word = Convert( word, isEnd );
// cout << endl << "create utterance for word: " << word << endl;
penultimate = WORD_KEY;
previous = WORD_KEY;
BackTrack( penultimate, previous, word );
int accumulation = 0;
while( word != END_KEY )
{
cout << word;
pair = previous + " " + word;
triplet = penultimate + " " + previous + " " + word;
// cout << endl << "pair='" << pair << "'" << endl;
// cout << "triplet='" << triplet << "'" << endl;
peripenultimate = penultimate;
penultimate = previous;
previous = word;
WordCount wordCount;
if( PostTripletText.find(triplet) != PostTripletText.end() )
{
// cout << " -> call GetRandWord( PostTripletText[" << triplet << "] )" << endl;
// word = GetRandWord( *PostTripletText[triplet], accumulation++ );
CopyWordCounts( wordCount, *PostTripletText[triplet], 9 );
}
else if( PostPairText.find(pair) != PostPairText.end() )
{
// cout << " -> call GetRandWord( PostPairText[" << pair << "] )" << endl;
// word = GetRandWord( *PostPairText[pair], accumulation++ );
CopyWordCounts( wordCount, *PostPairText[pair], 3 );
}
else
{
// cout << " -> call GetRandWord( PostText[" << word << "] )" << endl;
// word = GetRandWord( *PostText[word], accumulation++ );
CopyWordCounts( wordCount, *PostText[word], 1 );
}
word = GetRandWord( wordCount, accumulation++ );
if( word == END_KEY )
cout << "." << endl << endl;
else
cout << " ";
}
}
}
