static int toTxt(LPCTSTR lpszFileName,LPCTSTR lpszFileName2){
CStdioFile srtFile(lpszFileName,CFile::modeCreate|CFile::modeReadWrite|CFile::typeText),
txtFile(lpszFileName2,CFile::modeCreate|CFile::modeReadWrite|CFile::typeText);
CString srtLine;
while(srtFile.ReadString(srtLine)){
if(srtLine.Find (_T("-->")) != -1){
while(srtFile.ReadString(srtLine)){
if(srtLine != _T("\n")){
txtFile.WriteString (srtLine);
}else{
txtFile.WriteString(_T("----\n"));
srtFile.ReadString (srtLine);
break;
}
}
}else{
;
}
}
srtFile.Close();
txtFile.Close();
}
/**
* Loads the characters contained in each font
* from a UTF-8 file to use as the index.
* @param filename Filename of the index file.
*/
void Font::loadIndex(const std::string &filename)
{
_index = L"";
std::ifstream txtFile (filename.c_str(), std::ios::in | std::ios::binary);
if (!txtFile)
{
throw Exception("Failed to load index");
}
char value;
std::string buffer;
while (txtFile.read(&value, 1))
{
buffer += value;
}
if (!txtFile.eof())
{
throw Exception("Invalid data from file");
}
_index = Language::utf8ToWstr(buffer);
txtFile.close();
}
bool FileCSV::Load(const wxString& fileName, unsigned int itemsInLine)
{
// Make sure file exists
if (fileName.IsEmpty() || !wxFileName::FileExists(fileName))
{
mmErrorDialogs::InvalidFile(pParentWindow_);
return false;
}
// Open file
wxTextFile txtFile(fileName);
if (!txtFile.Open(encoding_))
{
mmErrorDialogs::MessageError(pParentWindow_, _("Unable to open file."), _("Universal CSV Import"));
return false;
}
// Parse rows
wxString line;
int row = 0;
for (line = txtFile.GetFirstLine(); !txtFile.Eof(); line = txtFile.GetNextLine())
{
csv2tab_separated_values(line, delimiter_);
wxStringTokenizer tkz(line, "\t", wxTOKEN_RET_EMPTY_ALL);
itemsTable_.push_back(std::vector<ValueAndType>());
// Tokens in row
while (tkz.HasMoreTokens())
{
if (itemsTable_[row].size() >= itemsInLine)
break;
wxString token = tkz.GetNextToken();
itemsTable_[row].push_back(token);
}
++row;
}
txtFile.Close();
return true;
}
bool FileCSV::Save(const wxString& fileName)
{
// Make sure file exists
if (fileName.IsEmpty())
{
mmErrorDialogs::InvalidFile(pParentWindow_);
return false;
}
// Open file
wxTextFile txtFile(fileName);
if (!txtFile.Create())
{
mmErrorDialogs::MessageError(pParentWindow_, _("Unable to create file."), _("Universal CSV Import"));
return false;
}
// Store lines
for (auto rowIt : itemsTable_)
{
wxString line;
for (auto itemIt : rowIt)
{
if (!line.IsEmpty())
line += delimiter_;
line += inQuotes(itemIt.value, delimiter_);
}
txtFile.AddLine(line);
}
// Save the file.
if (!txtFile.Write(wxTextFileType_None, encoding_))
{
mmErrorDialogs::MessageError(pParentWindow_, _("Could not save file."), _("Export error"));
return false;
}
txtFile.Close();
return true;
}
IniFile::IniFile(const char* strFileName): m_txtFileName(strFileName), m_isChanged(false), m_isDecrypt(false)
{
TextFileInputStream txtFile(strFileName);
parseText(txtFile);
}
//////////////////////////////////////////////////////////////////////////
// 读取数据到内存中，并且初始话pDatabase指针指向数据库
// 数据库的格式为：
// pDatabase中数据存储格式为：
// 每行：本行的单词数 依次每个单词
//////////////////////////////////////////////////////////////////////////
bool DataShared::loadData()
{
ifstream zhFile(m_zhFile.c_str());
if (zhFile.fail()){
#ifdef _ERROR
cerr <<"Can not open" <<m_zhFile <<endl;
#endif
return false;
}
string lineStr;
while(!(zhFile.eof())){
getline(zhFile,lineStr);
if(lineStr.size() == 0){
continue;
}
int64_t temp = atoi(lineStr.substr(lineStr.find('\t')+1,lineStr.size()).c_str());
m_ZhSet.insert(temp);
}
#ifdef _DEBUG
cout <<"Han zi:\n";
for(set<int64_t>::iterator iter = m_ZhSet.begin();iter != m_ZhSet.end();iter++){
cout << *iter <<"\t";
}
#endif
ifstream txtFile(m_inputFile.c_str());
if(txtFile.fail()){
#ifdef _ERROR
cerr <<"Can not open" <<m_inputFile <<endl;
#endif
return false;
}
getline(txtFile,lineStr); //读取第一行信息
vector<string> vstr = getInfo(lineStr.c_str(),"\t");
m_nCountRows = atoi(vstr[0].c_str());//总行数
m_nCountDifItem = atoi(vstr[1].c_str());//总不同单词数
m_nCountItem = atoi(vstr[2].c_str());//总单词数
int64_t min = (int)(m_minSup * m_nCountRows);
m_pDatabase = new int64_t *[m_nCountRows];
m_pWordProject = new set<int64_t> *[m_nCountDifItem];
for(int i = 0;i < m_nCountDifItem;i++){
m_pWordProject[i] = new set<int64_t>();
}
int64_t lineCount = 0;
while(!(txtFile.eof())){
getline(txtFile,lineStr);
if(lineStr.size() == 0){
continue;
}
vector<string> vstr = getInfo(lineStr.c_str(),"\t");
m_pDatabase[lineCount] = new int64_t[vstr.size() + 1];
m_pDatabase[lineCount][0] = vstr.size();
for(int i = 0;i < vstr.size();i++){
int64_t id = atoi(vstr[i].c_str());
m_pDatabase[lineCount][i + 1] = id;
m_pWordProject[id]->insert(lineCount);
}
lineCount++;
}
//Compute Freequent1Seq
for(int64_t i = 0;i < m_nCountDifItem;i++){
if(m_pWordProject[i]->size() >= min){
if(m_ZhSet.end() != m_ZhSet.find(i)){
m_freq1Item.push_back(i);
}
}
}
#ifdef _DEBUG
cout <<endl;
cout <<"Database:\n";
for(int i = 0;i < m_nCountRows;i++){
for(int j = 0;j < m_pDatabase[i][0];j++){
cout << m_pDatabase[i][j+1] <<"\t";
}
cout <<endl;
}
cout <<"Freq iterms:\n";
vector<int64_t>::iterator iter = m_freq1Item.begin();
while(iter != m_freq1Item.end()){
cout << *iter++ <<" ";
}
cout <<endl;
#endif
return true;
}
