List of usage examples for org.apache.lucene.analysis.icu ICUNormalizer2Filter ICUNormalizer2Filter
public ICUNormalizer2Filter(TokenStream input, Normalizer2 normalizer)
From source file:fastcampus.lucene.example.search.SpellCheckerExample.java
License:Apache License
public static void main(String[] args) throws Exception { Directory directory = FSDirectory.open(Paths.get("./index/spell/")); SpellChecker spellChecker = new SpellChecker(directory); //Analyzer analyzer = new StandardAnalyzer(); // ? Analyzer analyzer = new Analyzer() { @Override// w w w.ja v a 2 s. com protected TokenStreamComponents createComponents(String s) { Reader reader = new StringReader(s); Tokenizer tokenizer = new StandardTokenizer(); tokenizer.setReader(reader); String name = "nfc_cf"; Normalizer2 normalizer = Normalizer2.getInstance(null, name, Normalizer2.Mode.DECOMPOSE); TokenFilter filter = new ICUNormalizer2Filter(tokenizer, normalizer); return new TokenStreamComponents(tokenizer, filter); } }; IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer); //?? Writer? ? ? Path path = Paths.get("./data/spell/dic.txt"); spellChecker.setSpellIndex(directory); spellChecker.clearIndex(); spellChecker.indexDictionary(new PlainTextDictionary(path), indexWriterConfig, true); String wordForSuggestions = "?"; //spellChecker.setStringDistance(new LevensteinDistance()); //#Levenstein spellChecker.setStringDistance(new JaroWinklerDistance()); //Jaro-Winkler int suggestionsNumber = 1; String[] suggestions = spellChecker.suggestSimilar(wordForSuggestions, suggestionsNumber); if (suggestions != null && suggestions.length > 0) { for (String word : suggestions) { System.out.println("Did you mean:" + word); } } else { System.out.println("No suggestions found for word:" + wordForSuggestions); } }
From source file:org.apache.solr.analysis.ICUNormalizer2FilterFactory.java
License:Apache License
public TokenStream create(TokenStream input) { return new ICUNormalizer2Filter(input, normalizer); }