Monday, 12 July 2021

Lucene: StringField, TextField and StoredField

StringField: String field is indexed but not analyzed. Entire string value is stored as single token. It is useful to store ids, phone numbers, country fields etc.,

 

TextField: Text field is indexed and tokenized, without term vectors. If you want full-text searching use this field.

 

StoredField: It is a stored field that is not indexed at all (and so, is not searchable).

 

Example

Document doc = new Document();
doc.add(new StringField("id", id, Field.Store.YES));
doc.add(new TextField("title", title, Field.Store.YES));
doc.add(new TextField("description", description, Field.Store.NO));
doc.add(new TextField("blog", blog, Field.Store.YES));
doc.add(new StoredField("version", VERSION));

 

Find the below working application.

 

DocumentUtil.java

 

package com.sample.app.util;

import java.util.Arrays;
import java.util.List;

import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.StoredField;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;

public class DocumentUtil {

	private static final String VERSION = "1.23";

	public static Document getDocument(String id, String title, String description, String blog) {
		Document doc = new Document();
		doc.add(new StringField("id", id, Field.Store.YES));
		doc.add(new TextField("title", title, Field.Store.YES));
		doc.add(new TextField("description", description, Field.Store.NO));
		doc.add(new TextField("blog", blog, Field.Store.YES));
		doc.add(new StoredField("version", VERSION));
		return doc;

	}

	public static List<Document> getDocuments() {
		Document doc1 = getDocument("1", "JavaWorld",
				"The original independent resource for Java developers, architects, and managers.", " javaworld.com");
		Document doc2 = getDocument("2", "Oracle Blogs | The Java Source",
				" Java powers more than 4.5 billion devices including 800 million computers and 1.5 billion cell phones. If you love Java, this is the blog you must follow.",
				"blogs.oracle.com/java");
		Document doc3 = getDocument("3", "A Java geek",
				"Nicolas Fränkel's blog. IT architect focusing on Java, Java EE, and their surrounding ecosystems. He is a trainer, book writer, speaker & blogger.",
				"blog.frankel.ch");
		Document doc4 = getDocument("4", "Self Learning Java", "Learn Java fundamentals and other java libraries",
				"self-learning-java-tutorial.blogspot.com");

		return Arrays.asList(doc1, doc2, doc3, doc4);

	}
}

App.java

package com.sample.app;

import java.io.File;
import java.io.IOException;
import java.util.List;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.MultiBits;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.MMapDirectory;
import org.apache.lucene.store.NoLockFactory;
import org.apache.lucene.util.Bits;

import com.sample.app.util.DocumentUtil;

public class App {

	private static void printAllDocuments(Directory directory) throws IOException {

		try (IndexReader indexReader = DirectoryReader.open(directory)) {
			System.out.println("All Documents in Lucene Index");
			Bits liveDocs = MultiBits.getLiveDocs(indexReader);
			for (int i = 0; i < indexReader.maxDoc(); i++) {
				if (liveDocs != null && !liveDocs.get(i))
					continue;

				Document doc = indexReader.document(i);
				System.out.println(doc.get("id") + ", " + doc.get("title") + ", " + doc.get("version"));
			}

			System.out.println();
		}

	}

	public static void main(String args[]) throws IOException {

		Analyzer analyzer = new StandardAnalyzer();
		IndexWriterConfig indexWriterConfig1 = new IndexWriterConfig(analyzer);

		Directory directory = new MMapDirectory(new File("/Users/Shared/lucene").toPath(), NoLockFactory.INSTANCE);

		try (IndexWriter indexWriter = new IndexWriter(directory, indexWriterConfig1)) {

			List<Document> documents = DocumentUtil.getDocuments();

			indexWriter.addDocuments(documents);
			indexWriter.commit();

			printAllDocuments(directory);

		}

	}
}


Output

All Documents in Lucene Index
1, JavaWorld, 1.23
2, Oracle Blogs | The Java Source, 1.23
3, A Java geek, 1.23
4, Self Learning Java, 1.23





 

 

  

Previous                                                    Next                                                    Home

No comments:

Post a Comment