public static bool IsRealWord(string inWord, CSpellApi cSpellApi, bool debugFlag)
{
// init
RootDictionary checkDic = cSpellApi.GetCheckDic();
RootDictionary unitDic = cSpellApi.GetUnitDic();
WordWcMap wordWcMap = cSpellApi.GetWordWcMap();
Word2Vec word2VecOm = cSpellApi.GetWord2VecOm();
int inWordLen = inWord.Length;
// TBD, change method name
int rwSplitWordMinLength = cSpellApi.GetDetectorRwSplitWordMinLength();
int rwSplitWordMinWc = cSpellApi.GetDetectorRwSplitWordMinWc();
// realword must be:
// 1. known in the dictionary
// 2. not exception, such as url, email, digit, ...
// => if excpetion, even is a non-word, no correction
// 3. must have word2Vector value (inWord is auto converted to LC)
// 4. frequency must be above a threshhold (inWord is auto to LC)
// TBD, need to be configureable 200
bool realWordFlag = (checkDic.IsValidWord(inWord)) && (!IsRealWordExceptions(inWord, unitDic) && (inWordLen >= rwSplitWordMinLength) && (word2VecOm.HasWordVec(inWord) == true) && (WordCountScore.GetWc(inWord, wordWcMap) >= rwSplitWordMinWc));
if (debugFlag == true)
{
bool wordInDicFlag = checkDic.IsValidWord(inWord);
bool wordExceptionFlag = IsRealWordExceptions(inWord, unitDic);
bool lengthFlag = (inWordLen >= rwSplitWordMinLength);
bool word2VecFlag = word2VecOm.HasWordVec(inWord);
bool wcFlag = (WordCountScore.GetWc(inWord, wordWcMap) >= rwSplitWordMinWc);
DebugPrint.PrintRwSplitDetect(inWord, realWordFlag, wordInDicFlag, wordExceptionFlag, lengthFlag, word2VecFlag, wcFlag, debugFlag);
}
return(realWordFlag);
}
public static bool IsNonWord(string inWord, CSpellApi cSpellApi, bool debugFlag)
{
// init
RootDictionary checkDic = cSpellApi.GetCheckDic();
RootDictionary unitDic = cSpellApi.GetUnitDic();
// non-word must be:
// 1. not known in the dictionary
// 2. not exception, such as url, email, digit, ...
// => if excpetion, even is a nor-word, still not a misspelt
bool nonWordFlag = (!checkDic.IsValidWord(inWord)) && (!IsNonWordExceptions(inWord, unitDic));
if (debugFlag == true)
{
bool wordDicFlag = checkDic.IsValidWord(inWord);
bool wordExceptionFlag = IsNonWordExceptions(inWord, unitDic);
DebugPrint.PrintNwDetect(inWord, nonWordFlag, wordDicFlag, wordExceptionFlag, debugFlag);
}
return(nonWordFlag);
}
// check dic and exception
private static bool IsRealWordMerge(string inWord, CSpellApi cSpellApi, bool debugFlag)
{
// init
RootDictionary checkDic = cSpellApi.GetSplitWordDic(); // merge Dic
RootDictionary unitDic = cSpellApi.GetUnitDic();
// real word merge must:
// 1. known in the dictionary
// 2. not exception, such as url, email, digit, ...
// => if excpetion, even is a non-word, still not a misspelt
bool realWordMergeFlag = (checkDic.IsValidWord(inWord)) && (!IsRealWordExceptions(inWord, unitDic));
if (debugFlag == true)
{
bool wordInDicFlag = checkDic.IsValidWord(inWord);
bool wordExceptionFlag = IsRealWordExceptions(inWord, unitDic);
DebugPrint.PrintRwMergeDetect(inWord, realWordMergeFlag, wordInDicFlag, wordExceptionFlag, debugFlag);
}
return(realWordMergeFlag);
}
