/**
* Test Analyzer::encodingFromFile().
* \param analyzer analyzer
* \param fileName file name
*/
void testEncodingFromFile(Analyzer& analyzer, const char* fileName)
{
EncodingID id;
if(! analyzer.encodingFromFile(fileName, id))
{
cerr << "error to get encoding ID from file " << fileName << endl;
exit(1);
}
cout << "encoding: " << Knowledge::getEncodingNameFromID(id) << endl << endl;
}
/**
* Run Analyzer::encodingFromString() for each line in \e fileName, and print those different results with Analyzer::encodingFromFile().
* \param analyzer analyzer
* \param fileName file name
*
* It would test like below:
* 1. print the encoding of the file.
* 2. print those lines which encoding is not the same as the file.
*/
void testEncodingFromFileLine(Analyzer& analyzer, const char* fileName)
{
EncodingID fileID;
if(! analyzer.encodingFromFile(fileName, fileID))
{
cerr << "error to get encoding ID from file " << fileName << endl;
exit(1);
}
cout << "file encoding: " << Knowledge::getEncodingNameFromID(fileID) << endl << endl;
ifstream ifs(fileName);
if(! ifs)
{
cerr << "error in opening file " << fileName << endl;
exit(1);
}
cout << "========== the lines with different encoding:" << endl;
string line;
EncodingID lineID;
int totalLine = 0;
int diffLine = 0;
while(getline(ifs, line))
{
if(line.empty())
continue;
++totalLine;
if(! analyzer.encodingFromString(line.c_str(), lineID))
{
cerr << "error to get encoding ID from string " << line << endl;
exit(1);
}
if(lineID != fileID)
{
cout << Knowledge::getEncodingNameFromID(lineID) << "\t" << line << endl;
++diffLine;
}
}
cout << endl;
cout << "========== statistics result:" << endl;
cout << "diff lines: " << diffLine << endl;
cout << "total lines: " << totalLine << endl;
cout << "line correct rate: ";
if(totalLine)
cout << (double)(totalLine - diffLine) / totalLine * 100 << "%" << endl;
else
cout << "0%" << endl;
}