Examples of org.apache.lucene.index.memory.MemoryIndex.addField()

Class org.apache.lucene.index.memory.MemoryIndex

Examples of org.apache.lucene.index.memory.MemoryIndex.addField()

org.apache.lucene.index.memory.MemoryIndex.addField()
Convenience method; Tokenizes the given field text and adds the resulting terms to the index; Equivalent to adding an indexed non-keyword Lucene {@link org.apache.lucene.document.Field} that is{@link org.apache.lucene.document.Field.Index#ANALYZED tokenized}, {@link org.apache.lucene.document.Field.Store#NO not stored}, {@link org.apache.lucene.document.Field.TermVector#WITH_POSITIONS termVectorStored with positions} (or{@link org.apache.lucene.document.Field.TermVector#WITH_POSITIONS termVectorStored with positions and offsets}), @param fieldName a name to be associated with the text @param text the text to tokenize and index. @param analyzer the analyzer to use for tokenization

            memoryIndex.addField("title", lines.get(0), a);
            StringBuilder sb = new StringBuilder();
            for (String line : lines) {
                sb.append(line);
            }
            memoryIndex.addField("content", sb.toString(), a);


            IndexSearcher searcher = memoryIndex.createSearcher();
            ExistsCollector collector = new ExistsCollector();


            searcher.search(new TermQuery(new Term("content", "אני")), collector);

View Full Code Here

        assert !cachedTokenStream;
        tokenStream = new CachingTokenFilter(new OffsetLimitTokenFilter(tokenStream, maxDocCharsToAnalyze));
        cachedTokenStream = true;
      }
      final MemoryIndex indexer = new MemoryIndex(true);
      indexer.addField(DelegatingAtomicReader.FIELD_NAME, tokenStream);
      tokenStream.reset();
      final IndexSearcher searcher = indexer.createSearcher();
      // MEM index has only atomic ctx
      internalReader = new DelegatingAtomicReader(((AtomicReaderContext)searcher.getTopReaderContext()).reader());
    }

View Full Code Here


  private IndexReader getReaderForField(String field) {
    IndexReader reader = (IndexReader) readers.get(field);
    if (reader == null) {
      MemoryIndex indexer = new MemoryIndex();
      indexer.addField(field, cachedTokenFilter);
      IndexSearcher searcher = indexer.createSearcher();
      reader = searcher.getIndexReader();
      readers.put(field, reader);
    }
    return reader;

View Full Code Here

      cachedTokenStream = true;
    }
    IndexReader reader = (IndexReader) readers.get(field);
    if (reader == null) {
      MemoryIndex indexer = new MemoryIndex();
      indexer.addField(field, tokenStream);
      tokenStream.reset();
      IndexSearcher searcher = indexer.createSearcher();
      reader = searcher.getIndexReader();
      readers.put(field, reader);
    }

View Full Code Here

      cachedTokenStream = true;
    }
    IndexReader reader = readers.get(field);
    if (reader == null) {
      MemoryIndex indexer = new MemoryIndex();
      indexer.addField(field, new OffsetLimitTokenFilter(tokenStream, maxDocCharsToAnalyze));
      tokenStream.reset();
      IndexSearcher searcher = indexer.createSearcher();
      reader = searcher.getIndexReader();
      readers.put(field, reader);
    }

View Full Code Here

        mltQuery.setMinWordLen(0);
        mltQuery.setMinDocFreq(0);


        // one document has all values
        MemoryIndex index = new MemoryIndex();
        index.addField("name.first", "apache lucene", new WhitespaceAnalyzer());
        index.addField("name.last", "1 2 3 4", new WhitespaceAnalyzer());


        // two clauses, one for items and one for like_text if set
        BooleanQuery luceneQuery = (BooleanQuery) mltQuery.rewrite(index.createSearcher().getIndexReader());
        BooleanClause[] clauses = luceneQuery.getClauses();

View Full Code Here

        mltQuery.setMinDocFreq(0);


        // one document has all values
        MemoryIndex index = new MemoryIndex();
        index.addField("name.first", "apache lucene", new WhitespaceAnalyzer());
        index.addField("name.last", "1 2 3 4", new WhitespaceAnalyzer());


        // two clauses, one for items and one for like_text if set
        BooleanQuery luceneQuery = (BooleanQuery) mltQuery.rewrite(index.createSearcher().getIndexReader());
        BooleanClause[] clauses = luceneQuery.getClauses();

View Full Code Here

    }


    private static Fields generateFields(String[] fieldNames, String text) throws IOException {
        MemoryIndex index = new MemoryIndex();
        for (String fieldName : fieldNames) {
            index.addField(fieldName, text, new WhitespaceAnalyzer());
        }
        return MultiFields.getFields(index.createSearcher().getIndexReader());
    }


    private static String termsToString(Terms terms) throws IOException {

View Full Code Here

        MemoryIndex index = new MemoryIndex(withOffsets);
        for (GetField getField : getFields) {
            String field = getField.getName();
            Analyzer analyzer = getAnalyzerAtField(field, perFieldAnalyzer);
            for (Object text : getField.getValues()) {
                index.addField(field, text.toString(), analyzer);
            }
        }
        /* and read vectors from it */
        return MultiFields.getFields(index.createSearcher().getIndexReader());
    }

View Full Code Here

            try {
                // TODO: instead of passing null here, we can have a CTL<Map<String,TokenStream>> and pass previous,
                // like the indexer does
                TokenStream tokenStream = field.tokenStream(parsedDocument.analyzer(), null);
                if (tokenStream != null) {
                    memoryIndex.addField(field.name(), tokenStream, field.boost());
                }
            } catch (IOException e) {
                throw new ElasticsearchException("Failed to create token stream", e);
            }
        }

View Full Code Here

0 1 2

TOP

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.