在lucene中获得两个文档之间的余弦相似度

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.SimilarityCalculator;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

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

public class LuceneCosineSimilarity {

    public static void main(String[] args) throws IOException {
        // 1. 创建分析器和TokenStream
        Analyzer analyzer = new Analyzer() {
            @Override
            protected TokenStreamComponents createComponents(String fieldName) {
                TokenStreamComponents components = new TokenStreamComponents(fieldName);
                components.setTokenStream(new KeywordTokenizer());
                return components;
            }
        };

        // 2. 构建文档
        String doc1Text = "This is the first document.";
        String doc2Text = "This is the second document.";

        Document doc1 = new Document();
        Document doc2 = new Document();

        doc1.add(new Field("title", doc1Text, Field.Store.YES, Field.Index.TOKENIZED));
        doc2.add(new Field("title", doc2Text, Field.Store.YES, Field.Index.TOKENIZED));

        // 3. 创建索引
        Directory index = new FSDirectory(Paths.get("index"));
        IndexWriterConfig config = new IndexWriterConfig(analyzer);
        IndexWriter writer = new IndexWriter(index, config);

        // 4. 添加文档
        writer.addDocument(doc1);
        writer.addDocument(doc2);

        // 5. 计算相似度
        int id1 = 0;
        int id2 = 1;
        SimilarityCalculator similarityCalculator = new SimilarityCalculator(index);
        double similarity = similarityCalculator.calculateSimilarity(id1, id2);

        System.out.println("Cosine Similarity: " + similarity);

        // 6. 关闭索引和Writer
        writer.close();
        index.close();
    }
}