Lucene 构建索引

1. 索引过程

  1.1 提取文本和创建文档

      首先从文件中提取文本格式信息，并用这些文本信息创建Lucene文档和域。

  1.2 分析文档

      创建Lucene文档和域后，就可以调用IndexWriter对象的addDocument方法将数据传递给Lucene进行索引操作了。在索引操作时，Lucene首先分析文本，将文本数据分割成语汇单元串，然后对它们执行一些可选操作。如：LowerCaseFilter类实现搜索不对大小写敏感、StopFilter类从输入中去掉一些使用频繁却没有意义的词、PorterStemFilter类处理英文文本去掉它们的词干。这些将原始数据转换为词汇单元，随便用一系列Filter来修正该语汇单元的操作。

  1.3 向索引添加文档

      对输入数据分析完毕后，就可以将分析结果写入索引文件中。Lucene将输入数据以一种倒排索引的数据结构进行存储。Lucene使用倒排数据结构的原因是：把文档中提取出的语汇单元作为查询关键字，而不是将文档作为中心实体。换句话说，倒排索引不是回答“这个文档中包含哪些单词？”，而是经过优化后用来快速回答“哪些文档包含单词X？”这个问题。

      Lucene的索引文件目录有唯一一个段结构-索引段：

          Lucene索引都包含一个或多个段，每个段都是一个独立的索引，它包含事个文档索引的一个子集。每当Writer刷新缓冲区增加文档，以及挂起目录删除操作时，索引文件都会建立一个新段。在搜索索引时，每个段都是单独访问的，但搜索结果是合并返回的。

          每个段都包含多个文件，文件格式为_X.<ext>，这里X代表段名称，<ext>代表扩展名，用来标识该文件对应索引的某个部分。如果使用混合文件格式（Lucene默认处理方式，可通过IndexWriter.setUseCompoundFile方法进行修改），则上述索引文件都会被压缩成一个单一的文件：_X.cfs。这种方式在搜索期间减少打开的文件数量。

          还有一个特殊文件，叫段文件，用段_<N>标识，该文件指向所有激活的段。Lucene会首先打开该文件，然后打开它指向的其他文件。值<N>被称为“the geneeration”，它是一个整数，Lucene每次向索引提交更改时都会将这个数加1。

          IndexWriter会周期性地选择一些段，然后将它们合并到一个新段中，然后删除老的段。被合并段的选取策略由一个独立的MergePolicy类主导。一旦选好这些段，具体合并操作由MergeScheduler类实现。

2. 基本索引操作

package lucene.indexing;

import java.io.File;
import java.io.IOException;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.core.WhitespaceAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.Field.Store;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
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.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

public class IndexingTest {

	private String[] ids = { "1", "2" };
	private String[] unindexed = { "netherlands", "italy" };
	private String[] unstored = { "amsterdam has lots of bridges", "venice has lots of canals" };
	private String[] text = { "amsterdam", "venice" };

	private Directory directory;

	public IndexingTest() throws IOException {
		directory = FSDirectory.open(new File("F:/project/Lucene/index"));
	}

	private IndexWriter getWriter() throws IOException {
		Analyzer analyzer = new WhitespaceAnalyzer(Version.LUCENE_40);
		IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_40, analyzer);
		return new IndexWriter(directory, config);
	}

	private void getHitCount(String searchString, String fieldName) throws IOException {
		IndexReader reader = DirectoryReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(reader);
		Term term = new Term(searchString, fieldName);
		Query query = new TermQuery(term);
		TopDocs hits = searcher.search(query, null, 10000);
		System.out.print("在" + searchString + "中查询" + fieldName + ":");
		for (ScoreDoc scoreDoc : hits.scoreDocs) {
			Document doc = searcher.doc(scoreDoc.doc);
			System.out.print(doc.get("id"));
			System.out.print(",");
			System.out.print(doc.get("country"));
			System.out.print(",");
			System.out.print(doc.get("contents"));
			System.out.print(",");
			System.out.print(doc.get("city"));
			System.out.println(".");
		}
		System.out.println();
	}

	public void testIndexWriter() throws IOException {
		IndexWriter writer = getWriter();
		writer.numDocs();
		System.out.println("writer.numDocs=" + writer.numDocs());
		writer.close();
	}

	public void testIndexReader() throws IOException {
		IndexReader reader = DirectoryReader.open(directory);
		System.out.println("reader.maxDoc=" + reader.maxDoc());
		System.out.println("reader.numDocs=" + reader.numDocs());
		reader.close();
	}

	public void testUpdate() throws IOException {
		getHitCount("city", "amsterdam");
		getHitCount("city", "den haag");
		getHitCount("contents", "amsterdam");
		getHitCount("contents", "den");

		IndexWriter writer = getWriter();
		Document doc = new Document();
		doc.add(new StringField("id", "1", Store.YES));
		doc.add(new StringField("country", "nnetherlands", Store.YES));
		doc.add(new TextField("contents", "den haag has a lot of museums", Store.YES));
		doc.add(new StringField("city", "den haag", Store.YES));
		writer.updateDocument(new Term("id", "1"), doc);
		writer.close();

		getHitCount("city", "amsterdam");
		getHitCount("city", "den haag");
		getHitCount("contents", "amsterdam");
		getHitCount("contents", "den");
	}
	
	public void testDelete() throws IOException{
		getHitCount("city", "amsterdam");
		getHitCount("city", "venice");
		getHitCount("contents", "amsterdam");
		getHitCount("contents", "venice");
		IndexWriter writer=getWriter();
		writer.deleteDocuments(new Term("id","1"));
		writer.commit();
		writer.close();
		
		getHitCount("city", "amsterdam");
		getHitCount("city", "venice");
		getHitCount("contents", "amsterdam");
		getHitCount("contents", "venice");
	}

	public void set() throws IOException {
		// directory = new RAMDirectory();

		IndexWriter writer = getWriter();
		for (int i = 0; i < ids.length; i++) {
			Document doc = new Document();
			doc.add(new StringField("id", ids[i], Store.YES));
			doc.add(new StringField("country", unindexed[i], Store.YES));
			doc.add(new TextField("contents", unstored[i], Store.NO));
			doc.add(new StringField("city", text[i], Store.YES));
			writer.addDocument(doc);
		}
		writer.close();
	}

	public static void main(String[] args) throws IOException {
		IndexingTest test = new IndexingTest();
		test.set();
		test.testIndexWriter();
		test.testIndexReader();
		test.testUpdate();
		//test.testDelete();
	}
}