void EnchantSpellingAlternativesPrivate::setEnchantSpellingAlternatives(
Token* token,
MorphoSyntacticData* tokenData,
FsaStringsPool& sp)
{
// try to find simple Uncapitalization
MORPHOLOGINIT;
// FIXME Conditions below could be process unit parameters
const LimaString& tokenStr=token->stringForm();
if (token->status().getAlphaCapital() == T_CAPITAL
|| token->status().getAlphaCapital() == T_CAPITAL_1ST
|| token->status().getAlphaCapital() == T_CAPITAL_SMALL
|| token->status().isAlphaConcatAbbrev()
|| token->status().isAlphaHyphen()
|| token->status().isAlphaPossessive()
|| tokenStr.toUpper() == tokenStr)
{
return;
}
std::vector<std::string> suggestions = m_enchantDictionary->suggest(tokenStr.toUtf8().constData());
for (std::vector<std::string>::const_iterator it = suggestions.begin(); it != suggestions.end();it++)
{
LimaString correction = LimaString::fromUtf8((*it).c_str());
// FIXME Conditions below could be process unit parameters
if ( correction.size() > 1 && correction != tokenStr )
{
DictionaryEntry* entry = new DictionaryEntry(m_dictionary->getEntry(correction));
MorphoSyntacticDataHandler lingInfosHandler(*tokenData, SPELLING_ALTERNATIVE);
if (!entry->isEmpty())
{
LINFO << "EnchantSpellingAlternativesPrivate::setEnchantSpellingAlternatives correcting" << tokenStr << "into" << correction;
// add orthographic alternative to Token;
StringsPoolIndex idx=sp[correction];
token->addOrthographicAlternatives(idx);
if (entry->hasLingInfos())
{
entry->parseLingInfos(&lingInfosHandler);
}
}
else
{
delete entry;
}
}
}
}
LList * AySpellChecker::suggest(const char * word)
{
if(!word || !spell_checker)
return NULL;
std::vector<std::string> suggestions;
spell_checker->suggest(word, suggestions);
LList * words = NULL;
std::vector<std::string>::iterator aEnd = suggestions.end();
for (std::vector<std::string>::iterator aI = suggestions.begin(); aI != aEnd; ++aI)
words = l_list_append(words, strdup(aI->c_str()));
return words;
}