public string GetBestMatchWord(string OriginalWord)
{
EnsureIndexed();
var existing = indexReader.DocFreq(new Term("word", OriginalWord));
if (existing > 0)
{
return(OriginalWord);
}
var suggestions = _luceneChecker.SuggestSimilar(OriginalWord, 10, null, "word", true);
var jaro = new JaroWinklerDistance();
var leven = new LevenshteinDistance();
var ngram = new NGramDistance();
var metrics = suggestions.Select(s => new
{
word = s,
freq = indexReader.DocFreq(new Term("word", s)),
jaro = jaro.GetDistance(OriginalWord, s),
leven = leven.GetDistance(OriginalWord, s),
ngram = ngram.GetDistance(OriginalWord, s)
})
.OrderByDescending(metric =>
(
(metric.freq / 100f) +
metric.jaro +
metric.leven +
metric.ngram
)
/ 4f
)
.ToList();
return(metrics.Select(m => m.word).FirstOrDefault());
}
public AlternateWordList GetAlternateWordList(string OriginalWord, int NumberToReturn)
{
var wordList = new AlternateWordList();
wordList.OriginalWord = OriginalWord;
EnsureIndexed();
var existing = indexReader.DocFreq(new Term("word", OriginalWord));
wordList.OriginalWordFrequency = existing;
var suggestions = _luceneChecker.SuggestSimilar(OriginalWord, NumberToReturn, null, "word", true);
var jaro = new JaroWinklerDistance();
var leven = new LevenshteinDistance();
var ngram = new NGramDistance();
var metrics = suggestions.Select(s => new
{
word = s,
freq = indexReader.DocFreq(new Term("word", s)),
jaro = jaro.GetDistance(OriginalWord, s),
leven = leven.GetDistance(OriginalWord, s),
ngram = ngram.GetDistance(OriginalWord, s)
})
.OrderByDescending(metric =>
(
(metric.freq / 100f) +
metric.jaro +
metric.leven +
metric.ngram
)
/ 4f
)
.ToList();
var list = new List <AlternateWord>();
var sortOrder = 1;
foreach (var item in metrics)
{
var altWord = new AlternateWord();
altWord.Word = item.word;
altWord.Frequency = item.freq;
altWord.JaroWinkler = item.jaro;
altWord.Levenshtein = item.leven;
altWord.NGram = item.ngram;
altWord.BestMatchScore = ((item.freq / 100f) + item.jaro + item.leven + item.ngram) / 4f;
altWord.BestMatchSortOrder = sortOrder;
list.Add(altWord);
sortOrder++;
}
wordList.Words = list;
return(wordList);
}
protected void Page_Load(object sender, EventArgs e)
{
string s1 = "Holmes";
string s2 = "Holmes2136";
Response.Write(JaroWinklerDistance.GetDistance(s1, s2));
Response.Write("<BR>");
Response.Write(new LevenshteinDistance().GetDistance(s1, s2));
Response.Write("<BR>");
}
public List <string> GetTopSuggestions(string value, int numberOfItems)
{
EnsureIndexed();
var suggestionCollection = new List <string>();
var existing = _indexReader.DocFreq(new Term(SpellCheckerConstants.SpellCheckerKey, value));
if (existing > 0)// the fist one will be correct of exist
{
suggestionCollection.Add(value);
}
var suggestions = _checker.SuggestSimilar(value, numberOfItems, null, SpellCheckerConstants.SpellCheckerKey, true);
var jaro = new JaroWinklerDistance();
var leven = new LevenshteinDistance();
var ngram = new NGramDistance();
var metrics = suggestions.Select(s => new
{
word = s,
freq = _indexReader.DocFreq(new Term(SpellCheckerConstants.SpellCheckerKey, s)),
jaro = jaro.GetDistance(value, s),
leven = leven.GetDistance(value, s),
ngram = ngram.GetDistance(value, s)
})
.OrderByDescending(metric => metric.jaro)
.ThenByDescending(m => m.ngram)
.ThenByDescending(metric =>
(
metric.freq / 100f +
metric.leven
)
/ 2f
)
.ToList();
var wordsOnly = metrics.Select(m => m.word).ToList();
suggestionCollection.AddRange(wordsOnly);
return(suggestionCollection);
}
