/// <summary> Suggest similar words (restricted or not to a field of a user index)</summary>
/// <param name="word">String the word you want a spell check done on
/// </param>
/// <param name="num_sug">int the number of suggest words
/// </param>
/// <param name="ir">the indexReader of the user index (can be null see field param)
/// </param>
/// <param name="field">String 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="morePopular">boolean return only the suggest words that are more frequent than the searched word
/// (only if restricted mode = (indexReader!=null and field!=null)
/// </param>
/// <throws> IOException </throws>
/// <returns> String[] the sorted list of the suggest words with this 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 System.String[] SuggestSimilar(System.String word, int num_sug, IndexReader ir, System.String field, bool morePopular)
{
float min = this.minScore;
TRStringDistance sd = new TRStringDistance(word);
int lengthWord = word.Length;
int goalFreq = (morePopular && ir != null) ? ir.DocFreq(new Term(field, word)) : 0;
if (!morePopular && goalFreq > 0)
{
return(new System.String[] { word }); // return the word if it exist in the index and i don't want a more popular word
}
BooleanQuery query = new BooleanQuery();
System.String[] grams;
System.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]);
}
}
IndexSearcher searcher = new IndexSearcher(this.spellindex);
Hits hits = searcher.Search(query);
SuggestWordQueue sugqueue = new SuggestWordQueue(num_sug);
int stop = Math.Min(hits.Length(), 10 * num_sug); // go thru more than 'maxr' matches in case the distance filter triggers
SuggestWord sugword = new SuggestWord();
for (int i = 0; i < stop; i++)
{
sugword.string_Renamed = hits.Doc(i).Get(F_WORD); // get orig word)
if (sugword.string_Renamed.Equals(word))
{
continue; // don't suggest a word for itself, that would be silly
}
//edit distance/normalize with the min word length
sugword.score = 1.0f - ((float)sd.GetDistance(sugword.string_Renamed) / System.Math.Min(sugword.string_Renamed.Length, lengthWord));
if (sugword.score < min)
{
continue;
}
if (ir != null)
{
// use the user index
sugword.freq = ir.DocFreq(new Term(field, sugword.string_Renamed)); // freq in the index
if ((morePopular && goalFreq > sugword.freq) || sugword.freq < 1)
{
// don't suggest a word that is not present in the field
continue;
}
}
sugqueue.Insert(sugword);
if (sugqueue.Size() == num_sug)
{
//if queue full , maintain the min score
min = ((SuggestWord)sugqueue.Top()).score;
}
sugword = new SuggestWord();
}
// convert to array string
System.String[] list = new System.String[sugqueue.Size()];
for (int i = sugqueue.Size() - 1; i >= 0; i--)
{
list[i] = ((SuggestWord)sugqueue.Pop()).string_Renamed;
}
searcher.Close();
return(list);
}
/// <summary> Suggest similar words (restricted or not to a field of a user index)</summary>
/// <param name="word">String the word you want a spell check done on
/// </param>
/// <param name="num_sug">int the number of suggest words
/// </param>
/// <param name="ir">the indexReader of the user index (can be null see field param)
/// </param>
/// <param name="field">String 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="morePopular">boolean return only the suggest words that are more frequent than the searched word
/// (only if restricted mode = (indexReader!=null and field!=null)
/// </param>
/// <throws> IOException </throws>
/// <returns> String[] the sorted list of the suggest words with this 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 System.String[] SuggestSimilar(System.String word, int num_sug, IndexReader ir, System.String field, bool morePopular)
{
float min = this.minScore;
TRStringDistance sd = new TRStringDistance(word);
int lengthWord = word.Length;
int goalFreq = (morePopular && ir != null) ? ir.DocFreq(new Term(field, word)) : 0;
if (!morePopular && goalFreq > 0)
{
return new System.String[]{word}; // return the word if it exist in the index and i don't want a more popular word
}
BooleanQuery query = new BooleanQuery();
System.String[] grams;
System.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]);
}
}
IndexSearcher searcher = new IndexSearcher(this.spellindex);
Hits hits = searcher.Search(query);
SuggestWordQueue sugqueue = new SuggestWordQueue(num_sug);
int stop = Math.Min(hits.Length(), 10 * num_sug); // go thru more than 'maxr' matches in case the distance filter triggers
SuggestWord sugword = new SuggestWord();
for (int i = 0; i < stop; i++)
{
sugword.string_Renamed = hits.Doc(i).Get(F_WORD); // get orig word)
if (sugword.string_Renamed.Equals(word))
{
continue; // don't suggest a word for itself, that would be silly
}
//edit distance/normalize with the min word length
sugword.score = 1.0f - ((float) sd.GetDistance(sugword.string_Renamed) / System.Math.Min(sugword.string_Renamed.Length, lengthWord));
if (sugword.score < min)
{
continue;
}
if (ir != null)
{
// use the user index
sugword.freq = ir.DocFreq(new Term(field, sugword.string_Renamed)); // freq in the index
if ((morePopular && goalFreq > sugword.freq) || sugword.freq < 1)
{
// don't suggest a word that is not present in the field
continue;
}
}
sugqueue.Insert(sugword);
if (sugqueue.Size() == num_sug)
{
//if queue full , maintain the min score
min = ((SuggestWord) sugqueue.Top()).score;
}
sugword = new SuggestWord();
}
// convert to array string
System.String[] list = new System.String[sugqueue.Size()];
for (int i = sugqueue.Size() - 1; i >= 0; i--)
{
list[i] = ((SuggestWord) sugqueue.Pop()).string_Renamed;
}
searcher.Close();
return list;
}