bool LexicsCutter::Compare_Word(std::string& str, unsigned int pos, LC_WordVector word)
{
std::string lchar_prev;
std::string lchar;
// read first letter of the word into lchar_prev
ReadUTF8(str, lchar, pos);
// okay, here we go, comparing word
// first letter is already okay, we do begin from second and go on
LC_WordVector::iterator i = word.begin();
i++;
while (i != word.end())
{
// get letter from word, return false if the string is shorter
if (!ReadUTF8(str, lchar, pos)) return(false);
// check, if the letter is in the set
LC_LetterSet ls = *i;
if (ls.count(lchar) == 0)
{
// letter is not in set, but we must check, if it is not space or repeat
if ( (!(IgnoreMiddleSpaces && (lchar == " "))) &&
(!(IgnoreLetterRepeat && (lchar == lchar_prev))) )
{
// no checks viable
return(false);
}
}
else
{
// next word letter
i++;
}
// set previous string letter to compare if needed (this check can really conserve time)
if (IgnoreLetterRepeat) lchar_prev = lchar;
}
return(true);
}
bool LexicsCutter::_CompareWord(const std::string& str, unsigned int pos, LC_WordVector word) const
{
std::string chPrev;
std::string ch;
// Read first letter of the word into lchar_prev
ReadUTF8(str, ch, pos);
// Compare word
// First letter is already okay, we do begin from second and go on
LC_WordVector::iterator i = word.begin();
++i;
while (i != word.end())
{
// Get letter from word, return false if the string is shorter
if (!ReadUTF8(str, ch, pos))
return false;
// Check, if the letter is in the set
LC_LetterSet ls = *i;
if (ls.count(ch) == 0)
{
// Letter is not in set, but we must check, if it is not space or repeat
if ((!(_ignoreMiddleSpaces && (ch == " "))) &&
(!(_ignoreLetterRepeat && (ch == chPrev))))
// No checks viable
return false;
}
else
// Next word letter
++i;
// Set previous string letter to compare if needed (this check can really conserve time)
if (_ignoreLetterRepeat)
chPrev = ch;
}
return true;
}