Java Dictionary.getWordsIterator方法代码示例

import org.apache.lucene.search.spell.Dictionary; //导入方法依赖的package包/类
/**
  * Indexes the data from the given reader.
* @param reader Source index reader, from which autocomplete words are obtained for the defined field
* @param field the field of the source index reader to index for autocompletion
* @param mergeFactor mergeFactor to use when indexing
* @param ramMB the max amount or memory in MB to use
* @param optimize whether or not the autocomplete index should be optimized
  * @throws AlreadyClosedException if the Autocompleter is already closed
  * @throws IOException
  */
 public final void indexDictionary(IndexReader reader, String field, int mergeFactor, int ramMB, boolean optimize) throws IOException {
   synchronized (modifyCurrentIndexLock) {
     ensureOpen();
     final Directory dir = this.autoCompleteIndex;
     final Dictionary dict = new LuceneDictionary(reader, field);
     final IndexWriter writer = new IndexWriter(dir, new IndexWriterConfig(Version.LUCENE_CURRENT, new WhitespaceAnalyzer(Version.LUCENE_CURRENT)).setRAMBufferSizeMB(ramMB));
     IndexSearcher indexSearcher = obtainSearcher();
     final List<IndexReader> readers = new ArrayList<IndexReader>();

     if (searcher.maxDoc() > 0) {
       ReaderUtil.gatherSubReaders(readers, searcher.getIndexReader());
     }

     //clear the index
     writer.deleteAll();

     try {
       Iterator<String> iter = dict.getWordsIterator();

     while (iter.hasNext()) {
         String word = iter.next();

         // ok index the word
         Document doc = createDocument(word, reader.docFreq(new Term(field, word)));
         writer.addDocument(doc);
       }
     } finally {
       releaseSearcher(indexSearcher);
     }
     // close writer
     if (optimize)
       writer.optimize();
     writer.close();
     // also re-open the autocomplete index to see our own changes when the next suggestion
     // is fetched:
     swapSearcher(dir);
   }
 }
 

import org.apache.lucene.search.spell.Dictionary; //导入方法依赖的package包/类
public void testEmpty() throws Exception {
  Directory dir = newDirectory();
  IndexWriter writer = new IndexWriter(dir, newIndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(random())));
  writer.commit();
  writer.close();
  IndexReader ir = DirectoryReader.open(dir);
  Dictionary dictionary = new HighFrequencyDictionary(ir, "bogus", 0.1f);
  BytesRefIterator tf = dictionary.getWordsIterator();
  assertNull(tf.getComparator());
  assertNull(tf.next());
  dir.close();
}
 

import org.apache.lucene.search.spell.Dictionary; //导入方法依赖的package包/类
/** Build lookup from a dictionary. Some implementations may require sorted
 * or unsorted keys from the dictionary's iterator - use
 * {@link SortedInputIterator} or
 * {@link UnsortedInputIterator} in such case.
 */
public void build(Dictionary dict) throws IOException {
  BytesRefIterator it = dict.getWordsIterator();
  InputIterator tfit;
  if (it instanceof InputIterator) {
    tfit = (InputIterator)it;
  } else {
    tfit = new InputIterator.InputIteratorWrapper(it);
  }
  build(tfit);
}