Java IndexWriter.updateDocument方法代码示例

import org.apache.lucene.index.IndexWriter; //导入方法依赖的package包/类
static void indexDoc(IndexWriter writer, Path file, long lastModified) throws IOException {
	try (InputStream stream = Files.newInputStream(file)) {
		Document doc = new Document();
		Field pathField = new StringField("path", file.toString(), Field.Store.YES);
		doc.add(pathField);
		doc.add(new LongPoint("modified", lastModified));
		doc.add(new TextField("contents", new BufferedReader(new InputStreamReader(stream, StandardCharsets.UTF_8))));

		if (writer.getConfig().getOpenMode() == OpenMode.CREATE) {
			System.out.println("adding " + file);
			writer.addDocument(doc);
		} else {
			System.out.println("updating " + file);
			writer.updateDocument(new Term("path", file.toString()), doc);
		}
	}
}
 

import org.apache.lucene.index.IndexWriter; //导入方法依赖的package包/类
private static void update(final Term uid, final List<ParseContext.Document> docs, final IndexWriter indexWriter) throws IOException {
    if (docs.size() > 1) {
        indexWriter.updateDocuments(uid, docs);
    } else {
        indexWriter.updateDocument(uid, docs.get(0));
    }
}
 

import org.apache.lucene.index.IndexWriter; //导入方法依赖的package包/类
private void writeEmptyTermVector(TermVectorsResponse outResponse) throws IOException {

        Directory dir = newDirectory();
        IndexWriterConfig conf = new IndexWriterConfig(new StandardAnalyzer());
        conf.setOpenMode(OpenMode.CREATE);
        IndexWriter writer = new IndexWriter(dir, conf);
        FieldType type = new FieldType(TextField.TYPE_STORED);
        type.setStoreTermVectorOffsets(true);
        type.setStoreTermVectorPayloads(false);
        type.setStoreTermVectorPositions(true);
        type.setStoreTermVectors(true);
        type.freeze();
        Document d = new Document();
        d.add(new Field("id", "abc", StringField.TYPE_STORED));

        writer.updateDocument(new Term("id", "abc"), d);
        writer.commit();
        writer.close();
        DirectoryReader dr = DirectoryReader.open(dir);
        IndexSearcher s = new IndexSearcher(dr);
        TopDocs search = s.search(new TermQuery(new Term("id", "abc")), 1);
        ScoreDoc[] scoreDocs = search.scoreDocs;
        int doc = scoreDocs[0].doc;
        Fields fields = dr.getTermVectors(doc);
        EnumSet<Flag> flags = EnumSet.of(Flag.Positions, Flag.Offsets);
        outResponse.setFields(fields, null, flags, fields);
        outResponse.setExists(true);
        dr.close();
        dir.close();

    }
 

import org.apache.lucene.index.IndexWriter; //导入方法依赖的package包/类
private void writeStandardTermVector(TermVectorsResponse outResponse) throws IOException {

        Directory dir = newDirectory();
        IndexWriterConfig conf = new IndexWriterConfig(new StandardAnalyzer());

        conf.setOpenMode(OpenMode.CREATE);
        IndexWriter writer = new IndexWriter(dir, conf);
        FieldType type = new FieldType(TextField.TYPE_STORED);
        type.setStoreTermVectorOffsets(true);
        type.setStoreTermVectorPayloads(false);
        type.setStoreTermVectorPositions(true);
        type.setStoreTermVectors(true);
        type.freeze();
        Document d = new Document();
        d.add(new Field("id", "abc", StringField.TYPE_STORED));
        d.add(new Field("title", "the1 quick brown fox jumps over  the1 lazy dog", type));
        d.add(new Field("desc", "the1 quick brown fox jumps over  the1 lazy dog", type));

        writer.updateDocument(new Term("id", "abc"), d);
        writer.commit();
        writer.close();
        DirectoryReader dr = DirectoryReader.open(dir);
        IndexSearcher s = new IndexSearcher(dr);
        TopDocs search = s.search(new TermQuery(new Term("id", "abc")), 1);
        ScoreDoc[] scoreDocs = search.scoreDocs;
        int doc = scoreDocs[0].doc;
        Fields termVectors = dr.getTermVectors(doc);
        EnumSet<Flag> flags = EnumSet.of(Flag.Positions, Flag.Offsets);
        outResponse.setFields(termVectors, null, flags, termVectors);
        dr.close();
        dir.close();

    }
 

import org.apache.lucene.index.IndexWriter; //导入方法依赖的package包/类
private static void indexDoc(IndexWriter writer, FileBean t) throws Exception {
        Document doc = new Document();
        if (t.getContent() != null) {
            doc.add(new TextField(LuceneConstants.PATH, t.getFilepath(), Field.Store.YES));
            doc.add(new StringField(LuceneConstants.MODIFIED, UtilsTool.getDateStrByLastModified(t.getLastModified()), Field.Store.YES));
            doc.add(new TextField(LuceneConstants.CONTENT, t.getContent(), CommonConstants.IS_OPEN_CONTEXT ? Field.Store.YES : Field.Store.NO));
//            System.out.println("added to document:" + t.getFilepath());
            if (writer.getConfig().getOpenMode() == IndexWriterConfig.OpenMode.CREATE){
                writer.addDocument(doc);
            } else{
                writer.updateDocument(new Term(LuceneConstants.PATH, t.getFilepath()), doc);
            }
        }
    }
 

import org.apache.lucene.index.IndexWriter; //导入方法依赖的package包/类
static void indexDoc(IndexWriter writer, Path file, long lastModified) throws IOException {
    try (InputStream stream = Files.newInputStream(file)) {
        Document doc = new Document();
        Field pathField = new StringField("path", file.toString(), Field.Store.YES);
        doc.add(pathField);
        doc.add(new LongPoint("modified", lastModified));
        doc.add(new TextField("contents", new BufferedReader(new InputStreamReader(stream, StandardCharsets.UTF_8))));
        if (writer.getConfig().getOpenMode() == IndexWriterConfig.OpenMode.CREATE) {
            System.out.println("adding " + file);
            writer.addDocument(doc);
            System.out.println("updating " + file);
            writer.updateDocument(new Term("path", file.toString()), doc);
        }
    }
}
 

import org.apache.lucene.index.IndexWriter; //导入方法依赖的package包/类
/**
 * 更新博客索引
 *
 * @param user
 * @throws Exception
 */
public void updateIndex(UUser user) throws Exception {
  IndexWriter writer = getWriter();
  Document doc = new Document();
  doc.add(new StringField("userid", String.valueOf(user.getId()), Field.Store.YES));
  doc.add(new TextField("username", user.getUsername(), Field.Store.YES));
  doc.add(new TextField("description", user.getDescription(), Field.Store.YES));

  writer.updateDocument(new Term("userid", String.valueOf(user.getId())), doc);
  writer.close();
}
 

import org.apache.lucene.index.IndexWriter; //导入方法依赖的package包/类
public void testClearAllEntityIdentity() throws Exception {
    IndicesRequestCache cache = new IndicesRequestCache(Settings.EMPTY);
    AtomicBoolean indexShard =  new AtomicBoolean(true);

    ShardRequestCache requestCacheStats = new ShardRequestCache();
    Directory dir = newDirectory();
    IndexWriter writer = new IndexWriter(dir, newIndexWriterConfig());

    writer.addDocument(newDoc(0, "foo"));
    DirectoryReader reader = ElasticsearchDirectoryReader.wrap(DirectoryReader.open(writer),
        new ShardId("foo", "bar", 1));
    TermQueryBuilder termQuery = new TermQueryBuilder("id", "0");
    TestEntity entity = new TestEntity(requestCacheStats, indexShard);
    Loader loader = new Loader(reader, 0);

    writer.updateDocument(new Term("id", "0"), newDoc(0, "bar"));
    DirectoryReader secondReader = ElasticsearchDirectoryReader.wrap(DirectoryReader.open(writer),
        new ShardId("foo", "bar", 1));
    TestEntity secondEntity = new TestEntity(requestCacheStats, indexShard);
    Loader secondLoader = new Loader(secondReader, 0);

    writer.updateDocument(new Term("id", "0"), newDoc(0, "baz"));
    DirectoryReader thirdReader = ElasticsearchDirectoryReader.wrap(DirectoryReader.open(writer),
        new ShardId("foo", "bar", 1));
    AtomicBoolean differentIdentity =  new AtomicBoolean(true);
    TestEntity thirddEntity = new TestEntity(requestCacheStats, differentIdentity);
    Loader thirdLoader = new Loader(thirdReader, 0);

    BytesReference value1 = cache.getOrCompute(entity, loader, reader, termQuery.buildAsBytes());
    assertEquals("foo", value1.streamInput().readString());
    BytesReference value2 = cache.getOrCompute(secondEntity, secondLoader, secondReader, termQuery.buildAsBytes());
    assertEquals("bar", value2.streamInput().readString());
    logger.info("Memory size: {}", requestCacheStats.stats().getMemorySize());
    BytesReference value3 = cache.getOrCompute(thirddEntity, thirdLoader, thirdReader, termQuery.buildAsBytes());
    assertEquals("baz", value3.streamInput().readString());
    assertEquals(3, cache.count());
    final long hitCount = requestCacheStats.stats().getHitCount();
    // clear all for the indexShard Idendity even though is't still open
    cache.clear(randomFrom(entity, secondEntity));
    cache.cleanCache();
    assertEquals(1, cache.count());
    // third has not been validated since it's a different identity
    value3 = cache.getOrCompute(thirddEntity, thirdLoader, thirdReader, termQuery.buildAsBytes());
    assertEquals(hitCount + 1, requestCacheStats.stats().getHitCount());
    assertEquals("baz", value3.streamInput().readString());


    IOUtils.close(reader, secondReader, thirdReader, writer, dir, cache);

}
 

import org.apache.lucene.index.IndexWriter; //导入方法依赖的package包/类
/**
 * Given a queue of documents to index, index them by popping the queue limited to 1000 items.
 * This method must be synchronized as we have not added any logic to deal with multiple threads writing to the
 * index.
 */
public synchronized void indexDocuments(List<ContentDTO> contentDTOList) throws IOException {
    Analyzer analyzer = new StandardAnalyzer();
    IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer);

    indexWriterConfig.setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND);

    IndexWriter writer = new IndexWriter(this.indexDirectory, indexWriterConfig);

    try {
        for(ContentDTO contentDTO: contentDTOList) {

            Document doc = new Document();
            // Path is the primary key for documents
            String primaryKey =  Values.EMPTY_STRING + contentDTO.getId();
            Field pathField = new StringField(Values.PATH, primaryKey, Field.Store.YES);
            doc.add(pathField);


            StringBuffer stringBuffer = new StringBuffer();
            stringBuffer.append(contentDTO.getTitle().toLowerCase()).append(" ");
            stringBuffer.append(contentDTO.getDescription().toLowerCase()).append(" ");
            stringBuffer.append(contentDTO.getDescription().toLowerCase()).append(" ");
            stringBuffer.append(contentDTO.getTopic().replace("/", " ").replace("_", " ")).append(" ");
            stringBuffer.append(contentDTO.getUrl().replaceAll("\\W+", " ")).append(" ");


            doc.add(new TextField(Values.CONTENT, stringBuffer.toString(), Field.Store.NO));
            doc.add(new TextField(Values.TITLE, contentDTO.getTitle().toLowerCase(), Field.Store.NO));
            doc.add(new TextField(Values.DESCRIPTION, contentDTO.getDescription().toLowerCase(), Field.Store.NO));
            doc.add(new TextField("topics", contentDTO.getTopic().replace("/", " ").replace("_", " "), Field.Store.NO));
            doc.add(new TextField(Values.URL, contentDTO.getUrl().replaceAll("\\W+", " "), Field.Store.NO));


            writer.updateDocument(new Term(Values.PATH, primaryKey), doc);
        }
    }
    finally {
        writer.close();
    }
}
 

import org.apache.lucene.index.IndexWriter; //导入方法依赖的package包/类
public void update(IndexWriter indexWriter) throws CorruptIndexException, IOException {
	indexWriter.updateDocument(GLOBAL_PROPERTIES_TERM, doc);
}
 

import org.apache.lucene.index.IndexWriter; //导入方法依赖的package包/类
public void updateEvent (Event event) throws IOException {
	Directory index = FSDirectory.open (Paths.get(indexDirectoryPath));
	
	PerFieldAnalyzerWrapper analyzer = new PerFieldAnalyzerWrapper (new StandardAnalyzer (), fieldAnalyzerLookup);
	
	IndexWriterConfig indexWriterConfig = new IndexWriterConfig (analyzer);
	
	indexWriterConfig.setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND);
	
	IndexWriter indexWriter = new IndexWriter (index, indexWriterConfig);
	
	Document d = eventToDocument(event);
	
	indexWriter.updateDocument(new Term ("id", event.getId()), d);
	
	indexWriter.commit();
	
	indexWriter.close();
	
	index.close ();
}
 

import org.apache.lucene.index.IndexWriter; //导入方法依赖的package包/类
public void addOrUpdateNote (Note note, String noteHtmlContents) throws IOException {
	Directory index = FSDirectory.open (Paths.get(indexDirectoryPath));
	
	PerFieldAnalyzerWrapper analyzer = new PerFieldAnalyzerWrapper (new StandardAnalyzer (), fieldAnalyzerLookup);
	
	IndexWriterConfig indexWriterConfig = new IndexWriterConfig (analyzer);
	
	indexWriterConfig.setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND);
	
	IndexWriter indexWriter = new IndexWriter (index, indexWriterConfig);
	
	Document d = noteToDocument(note, noteHtmlContents);	
	
	if (!DirectoryReader.indexExists(index)) 
		indexWriter.addDocument(d);
	else {		
		IndexReader indexReader = DirectoryReader.open (index);
		
		IndexSearcher indexSearcher = new IndexSearcher (indexReader);
		
		TopDocs existingDocuments = indexSearcher.search(new TermQuery (new Term ("id", note.getId())), 1);
		
		if (existingDocuments.totalHits == 0)		
			indexWriter.addDocument(d);
		else indexWriter.updateDocument(new Term ("id", note.getId()), d);
	}

	indexWriter.commit();
	
	indexWriter.close();
	
	index.close ();
}