Lucene入門 4章 インデックス検索プログラム - Lucene 3.6 バージョン

BaseSearcher.java

package searcher;

import java.io.File;
import java.io.IOException;
import java.lang.reflect.Constructor;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.TotalHitCountCollector;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

public abstract class BaseSearcher {

	protected static final String DEFAULT_ANALYZER =
			"org.apache.lucene.analysis.ja.JapaneseAnalyzer";
	protected static final String GOSEN_ANALYZER = 
			"org.apache.lucene.analysis.gosen.GosenAnalyzer";
	protected static final String CJK_ANALYZER = 
			"org.apache.lucene.analysis.cjk.CJKAnalyzer";
	
	protected static final String PROP_ANALYZER = "analyzer";
	
	protected Analyzer analyzer;
	protected String indexDir;
	
	private String analyzerClass;
	
	protected BaseSearcher(String indexDir, String analyzerClass) {
		this.indexDir = indexDir;
		this.analyzerClass = analyzerClass;
	}
	
	/** Analyzerを取得する */
	protected Analyzer getAnalyzer() {
		try {
			if (analyzer == null) {
				// Analyzerクラスを生成
				Class clazz = getClass().getClassLoader().loadClass(analyzerClass);
				Constructor<Analyzer> constructor = clazz.getConstructor(Version.class);
				Object[] args = new Object[]{ Version.LUCENE_36 };
				analyzer = constructor.newInstance(args);
				System.out.println("* Analyzer : " + analyzerClass);
			}
			return analyzer;
		} catch (Exception e) {
			throw new SearcherException(e);
		}
	}
	
	/** インデックス格納先Directoryを取得する */
	protected Directory getDirectory() {
		try {
			Directory d = FSDirectory.open(new File(indexDir));
			return d;
		} catch (IOException e) {
			throw new SearcherException(e);
		}
	}
	
	/** 指定されたQueryでインデックスを検索する */
	protected void searchIndex(Query query) {
		System.out.println("Query = \"" + query + "\"");
		IndexReader reader = null;
		IndexSearcher searcher = null;
		try {
			// IndexReader作成
			reader = IndexReader.open(getDirectory());
			// IndexReaderを与えてIndexSearcherを作成
			searcher = new IndexSearcher(reader);
			// Queryで検索されるトータルドキュメント数を取得する
			TotalHitCountCollector total = new TotalHitCountCollector();
			searcher.search(query, total);
			int totalHits = total.getTotalHits();
			// ランキング上位(最大)10件のドキュメント取得する
			TopDocs docs = searcher.search(query, 10);
			ScoreDoc[] hits = docs.scoreDocs;
			System.out.println(Integer.toString(totalHits) + " 件中 " + Integer.toString(hits.length) + " 件取得しました。");
			// ヒットしたドキュメントを表示する
			for (ScoreDoc hit : hits) {
				// ScoreDocオブジェクトはドキュメントIDしか持っていないので、searcherを経由してドキュメント本体を取得
				Document doc = searcher.doc(hit.doc);
				printDocument(doc);
				System.out.println(Integer.toString(hit.doc) + ", スコア = " + Float.toString(hit.score));
			}
		} catch (IOException e) {
			throw new SearcherException(e);
		} finally {
			try {
				if (searcher != null) {
					searcher.close();
				}
				if (reader != null) {
					reader.close();
				}
			} catch (IOException e) {}
		}
	}
	
	protected abstract void printDocument(Document doc);
	
	public static class SearcherException extends RuntimeException {
		public SearcherException(Exception e) {
			super(e);
		}
	}
}

BookSearcher.java

package searcher;

import indexer.BookIndexer;

import org.apache.lucene.document.Document;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.Query;
import org.apache.lucene.util.NumericUtils;
import org.apache.lucene.util.Version;

public class BookSearcher extends BaseSearcher {

	public static void main(String[] args) {
		BookSearcher bs = new BookSearcher("book-index/kuromoji", DEFAULT_ANALYZER);
		QueryParser qp = new QueryParser(Version.LUCENE_36, BookIndexer.F_TITLE, bs.getAnalyzer());
		try {
			Query query = qp.parse("Java プログラミング");
			bs.searchIndex(query);
		} catch (ParseException e) {
			throw new SearcherException(e);
		}
	}
	
	protected BookSearcher(String indexDir, String analyzerClass) {
		super(indexDir, analyzerClass);
	}
	
	@Override
	protected void printDocument(Document doc) {
		System.out.println("=============================================================================");
		System.out.println(BookIndexer.F_PUBLISHER + " = " + doc.get(BookIndexer.F_PUBLISHER));
		System.out.println(BookIndexer.F_CATEGORY + " = " + doc.get(BookIndexer.F_CATEGORY));
		System.out.println(BookIndexer.F_TITLE + " = " + doc.get(BookIndexer.F_TITLE));
		System.out.println(BookIndexer.F_AUTHOR + " = " + doc.get(BookIndexer.F_AUTHOR));
		System.out.println(NumericUtils.prefixCodedToLong(doc.get(BookIndexer.F_PAGES)) + " ページ");
		System.out.println(BookIndexer.F_ISBN + " = " + doc.get(BookIndexer.F_ISBN));
		System.out.println(BookIndexer.F_DATE + " = " + doc.get(BookIndexer.F_DATE));
		System.out.println(NumericUtils.prefixCodedToLong(doc.get(BookIndexer.F_PRICE)) + " 円");
		System.out.println(BookIndexer.F_SUMMARY + " = " + doc.get(BookIndexer.F_SUMMARY));
	}

}

gistfile1.txt

http://mocobeta-backup.tumblr.com/post/26212093829/lucene-3-6

PostSearcher.java

package searcher;

import indexer.PostIndexer;

import org.apache.lucene.document.Document;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.Query;
import org.apache.lucene.util.Version;

public class PostSearcher extends BaseSearcher {

	public static void main(String[] args) {
		PostSearcher ps = new PostSearcher("post-index/kuromoji", DEFAULT_ANALYZER);
		QueryParser qp = new QueryParser(Version.LUCENE_36, PostIndexer.F_NAME, ps.getAnalyzer());
		try {
			Query q = qp.parse("日立製作所");
			ps.searchIndex(q);
		} catch (ParseException e) {
			throw new SearcherException(e);
		}
	}
	
	protected PostSearcher(String indexDir, String analyzerClass) {
		super(indexDir, analyzerClass);
	}
	
	@Override
	protected void printDocument(Document doc) {
		System.out.println("=============================================================================");
		System.out.println(PostIndexer.F_CODE + " = " + doc.get(PostIndexer.F_CODE));
		System.out.println(PostIndexer.F_KANA + " = " + doc.get(PostIndexer.F_KANA));
		System.out.println(PostIndexer.F_NAME + " = " + doc.get(PostIndexer.F_NAME));
		System.out.println(PostIndexer.F_ADDR + " = " + doc.get(PostIndexer.F_ADDR));
		System.out.println(PostIndexer.F_CONTENT + " = " + doc.get(PostIndexer.F_CONTENT));
		System.out.println(PostIndexer.F_INDZIP + " = " + doc.get(PostIndexer.F_INDZIP));
		System.out.println(PostIndexer.F_ZIP + " = " + doc.get(PostIndexer.F_ZIP));
		System.out.println(PostIndexer.F_POST + " = " + doc.get(PostIndexer.F_POST));
	}

}