public void TestInternalLevenshteinDistance()
{
DirectSpellChecker spellchecker = new DirectSpellChecker();
Directory dir = NewDirectory();
RandomIndexWriter writer = new RandomIndexWriter(Random(), dir,
new MockAnalyzer(Random(), MockTokenizer.KEYWORD, true), Similarity, TimeZone);
String[] termsToAdd = { "metanoia", "metanoian", "metanoiai", "metanoias", "metanoið‘" };
for (int i = 0; i < termsToAdd.Length; i++)
{
Document doc = new Document();
doc.Add(NewTextField("repentance", termsToAdd[i], Field.Store.NO));
writer.AddDocument(doc);
}
IndexReader ir = writer.Reader;
String misspelled = "metanoix";
SuggestWord[] similar = spellchecker.SuggestSimilar(new Term("repentance", misspelled), 4, ir, SuggestMode.SUGGEST_WHEN_NOT_IN_INDEX);
assertTrue(similar.Length == 4);
IStringDistance sd = spellchecker.Distance;
assertTrue(sd is LuceneLevenshteinDistance);
foreach (SuggestWord word in similar)
{
assertTrue(word.Score == sd.GetDistance(word.String, misspelled));
assertTrue(word.Score == sd.GetDistance(misspelled, word.String)); // LUCNENET TODO: Perhaps change this to word.ToString()?
}
ir.Dispose();
writer.Dispose();
dir.Dispose();
}
public void TestGetDistance()
{
float d = sd.GetDistance("al", "al");
assertTrue(d == 1.0f);
d = sd.GetDistance("martha", "marhta");
assertTrue(d > 0.961 && d < 0.962);
d = sd.GetDistance("jones", "johnson");
assertTrue(d > 0.832 && d < 0.833);
d = sd.GetDistance("abcvwxyz", "cabvwxyz");
assertTrue(d > 0.958 && d < 0.959);
d = sd.GetDistance("dwayne", "duane");
assertTrue(d > 0.84 && d < 0.841);
d = sd.GetDistance("dixon", "dicksonx");
assertTrue(d > 0.813 && d < 0.814);
d = sd.GetDistance("fvie", "ten");
assertTrue(d == 0f);
float d1 = sd.GetDistance("zac ephron", "zac efron");
float d2 = sd.GetDistance("zac ephron", "kai ephron");
assertTrue(d1 > d2);
d1 = sd.GetDistance("brittney spears", "britney spears");
d2 = sd.GetDistance("brittney spears", "brittney startzman");
assertTrue(d1 > d2);
}
public void TestGetDistance()
{
float d = sd.GetDistance("al", "al");
assertEquals(d, 1.0f, 0.001);
d = sd.GetDistance("martha", "marhta");
assertEquals(d, 0.6666, 0.001);
d = sd.GetDistance("jones", "johnson");
assertEquals(d, 0.4285, 0.001);
d = sd.GetDistance("abcvwxyz", "cabvwxyz");
assertEquals(d, 0.75, 0.001);
d = sd.GetDistance("dwayne", "duane");
assertEquals(d, 0.666, 0.001);
d = sd.GetDistance("dixon", "dicksonx");
assertEquals(d, 0.5, 0.001);
d = sd.GetDistance("six", "ten");
assertEquals(d, 0, 0.001);
float d1 = sd.GetDistance("zac ephron", "zac efron");
float d2 = sd.GetDistance("zac ephron", "kai ephron");
assertEquals(d1, d2, 0.001);
d1 = sd.GetDistance("brittney spears", "britney spears");
d2 = sd.GetDistance("brittney spears", "brittney startzman");
assertTrue(d1 > d2);
}
/// <summary>
/// Suggest similar words (optionally restricted to a field of an index).
/// <para>
/// As the Lucene similarity that is used to fetch the most relevant n-grammed terms
/// is not the same as the edit distance strategy used to calculate the best
/// matching spell-checked word from the hits that Lucene found, one usually has
/// to retrieve a couple of numSug's in order to get the true best match.
/// </para>
/// <para>
/// I.e. if numSug == 1, don't count on that suggestion being the best one.
/// Thus, you should set this value to <b>at least</b> 5 for a good suggestion.
/// </para>
/// </summary>
/// <param name="word"> the word you want a spell check done on </param>
/// <param name="numSug"> the number of suggested words </param>
/// <param name="ir"> the indexReader of the user index (can be null see field param) </param>
/// <param name="field"> the field of the user index: if field is not null, the suggested
/// words are restricted to the words present in this field. </param>
/// <param name="suggestMode">
/// (NOTE: if indexReader==null and/or field==null, then this is overridden with SuggestMode.SUGGEST_ALWAYS) </param>
/// <param name="accuracy"> The minimum score a suggestion must have in order to qualify for inclusion in the results </param>
/// <exception cref="System.IO.IOException"> if the underlying index throws an <see cref="System.IO.IOException"/> </exception>
/// <exception cref="ObjectDisposedException"> if the <see cref="SpellChecker"/> is already disposed </exception>
/// <returns> string[] the sorted list of the suggest words with these 2 criteria:
/// first criteria: the edit distance, second criteria (only if restricted mode): the popularity
/// of the suggest words in the field of the user index
/// </returns>
public virtual string[] SuggestSimilar(string word, int numSug, IndexReader ir, string field, SuggestMode suggestMode, float accuracy)
{
// obtainSearcher calls ensureOpen
IndexSearcher indexSearcher = ObtainSearcher();
try
{
if (ir == null || field == null)
{
suggestMode = SuggestMode.SUGGEST_ALWAYS;
}
if (suggestMode == SuggestMode.SUGGEST_ALWAYS)
{
ir = null;
field = null;
}
int lengthWord = word.Length;
int freq = (ir != null && field != null) ? ir.DocFreq(new Term(field, word)) : 0;
int goalFreq = suggestMode == SuggestMode.SUGGEST_MORE_POPULAR ? freq : 0;
// if the word exists in the real index and we don't care for word frequency, return the word itself
if (suggestMode == SuggestMode.SUGGEST_WHEN_NOT_IN_INDEX && freq > 0)
{
return(new string[] { word });
}
BooleanQuery query = new BooleanQuery();
string[] grams;
string key;
for (int ng = GetMin(lengthWord); ng <= GetMax(lengthWord); ng++)
{
key = "gram" + ng; // form key
grams = FormGrams(word, ng); // form word into ngrams (allow dups too)
if (grams.Length == 0)
{
continue; // hmm
}
if (bStart > 0) // should we boost prefixes?
{
Add(query, "start" + ng, grams[0], bStart); // matches start of word
}
if (bEnd > 0) // should we boost suffixes
{
Add(query, "end" + ng, grams[grams.Length - 1], bEnd); // matches end of word
}
for (int i = 0; i < grams.Length; i++)
{
Add(query, key, grams[i]);
}
}
int maxHits = 10 * numSug;
// System.out.println("Q: " + query);
ScoreDoc[] hits = indexSearcher.Search(query, null, maxHits).ScoreDocs;
// System.out.println("HITS: " + hits.length());
SuggestWordQueue sugQueue = new SuggestWordQueue(numSug, comparer);
// go thru more than 'maxr' matches in case the distance filter triggers
int stop = Math.Min(hits.Length, maxHits);
SuggestWord sugWord = new SuggestWord();
for (int i = 0; i < stop; i++)
{
sugWord.String = indexSearcher.Doc(hits[i].Doc).Get(F_WORD); // get orig word
// don't suggest a word for itself, that would be silly
if (sugWord.String.Equals(word, StringComparison.Ordinal))
{
continue;
}
// edit distance
sugWord.Score = sd.GetDistance(word, sugWord.String);
if (sugWord.Score < accuracy)
{
continue;
}
if (ir != null && field != null) // use the user index
{
sugWord.Freq = ir.DocFreq(new Term(field, sugWord.String)); // freq in the index
// don't suggest a word that is not present in the field
if ((suggestMode == SuggestMode.SUGGEST_MORE_POPULAR && goalFreq > sugWord.Freq) || sugWord.Freq < 1)
{
continue;
}
}
sugQueue.InsertWithOverflow(sugWord);
if (sugQueue.Count == numSug)
{
// if queue full, maintain the minScore score
accuracy = sugQueue.Top.Score;
}
sugWord = new SuggestWord();
}
// convert to array string
string[] list = new string[sugQueue.Count];
for (int i = sugQueue.Count - 1; i >= 0; i--)
{
list[i] = sugQueue.Pop().String;
}
return(list);
}
finally
{
ReleaseSearcher(indexSearcher);
}
}
