使用lucene实现简单的全文检索

叁歲伎倆 2022-06-03 00:00 236阅读 0赞

本文是一个使用lucene为文本创建并管理索引，根据索引检索文本的简单全文搜索例子。

# Manven依赖 #

<dependency>
      <groupId>org.apache.lucene</groupId>
      <artifactId>lucene-core</artifactId>
      <version>6.0.0</version>
    </dependency>
    <dependency>
      <groupId>org.apache.lucene</groupId>
      <artifactId>lucene-queryparser</artifactId>
      <version>6.0.0</version>
    </dependency>
    <dependency>
      <groupId>org.apache.lucene</groupId>
      <artifactId>lucene-analyzers-common</artifactId>
      <version>6.0.0</version>
    </dependency>
    <dependency>
      <groupId>commons-io</groupId>
      <artifactId>commons-io</artifactId>
      <version>2.5</version>
    </dependency>

# 索引管理 #

## 创建索引 ##

public static void createIndex(FileManage file){
    //索引保存路径
        String indexRootPath = getIndexRoot();
        File f = new File(indexRootPath);
        if(!f.exists()){
            f.mkdirs();
        }
    
        String indexPath = indexRootPath+File.separator+File.separator;
        Directory indexDir = null;
        IndexWriter indexWriter = null;
        try{
            indexDir = FSDirectory.open(new File(indexPath).toPath());
            Analyzer analyzer = new StandardAnalyzer();
            IndexWriterConfig config = new IndexWriterConfig(analyzer);
            indexWriter = new IndexWriter(indexDir, config);
    
            File sourceFile = new File(sourceRootPath);
            String content = org.apache.commons.io.FileUtils.readFileToString(sourceFile, "utf-8");
    
            Document doc = new Document();
            doc.add(new TextField("fileName", file.getPath(), Field.Store.YES));
            doc.add(new TextField("content", content, Field.Store.YES));
            indexWriter.addDocument(doc);
            indexWriter.flush();
        }catch(Exception e){
            log.error("create index error|",e);
        }finally{
            if(null != indexWriter){
                try {
                    indexWriter.close();
                } catch (IOException e) {
                    log.error("",e);
                }
            }
        }
    }

## 删除索引 ##

public static void deleteIndex(FileManage file){
        String indexRootPath = getIndexRoot();
        File f = new File(indexRootPath);
        if(!f.exists()){
            f.mkdirs();
        }
    
        String indexPath = indexRootPath+File.separator;
        Directory indexDir = null;
        IndexWriter indexWriter = null;
        try{
            indexDir = FSDirectory.open(new File(indexPath).toPath());
            Analyzer analyzer = new StandardAnalyzer();
            IndexWriterConfig config = new IndexWriterConfig(analyzer);
            indexWriter = new IndexWriter(indexDir, config);
            indexWriter.deleteDocuments(new Term("fileName", file.getFileName()));
            indexWriter.flush();
        }catch(Exception e){
            log.error("create index error|",e);
        }finally{
            if(null != indexWriter){
                try {
                    indexWriter.close();
                } catch (IOException e) {
                    log.error("",e);
                }
            }
        }
    }

## 更新索引 ##

public static void updateIndex(FileManage file){
        String indexRootPath = getIndexRoot();
        String sourceRootPath = getSourceRoot();
        File f = new File(indexRootPath);
        if(!f.exists()){
            f.mkdirs();
        }
    
        String indexPath = indexRootPath+File.separator;
        Directory indexDir = null;
        IndexWriter indexWriter = null;
        try{
            indexDir = FSDirectory.open(new File(indexPath).toPath());
            Analyzer analyzer = new StandardAnalyzer();
            IndexWriterConfig config = new IndexWriterConfig(analyzer);
            indexWriter = new IndexWriter(indexDir, config);
    
            File sourceFile = new File(file.getPath());
            String content = org.apache.commons.io.FileUtils.readFileToString(sourceFile, "utf-8");
    
            Document doc = new Document();
            doc.add(new TextField("fileName", file.getFileName(), Field.Store.YES));
            doc.add(new TextField("content", content, Field.Store.YES));
            indexWriter.updateDocument(new Term("fileName", file.getFileName()),doc);
            indexWriter.flush();
        }catch(Exception e){
            log.error("create index error|",e);
        }finally{
            if(null != indexWriter){
                try {
                    indexWriter.close();
                } catch (IOException e) {
                    log.error("",e);
                }
            }
        }
    }

## 根据索引检索 ##

public static List<SearchResult> search(List<FileManage> sourcefiles, String param){
        if(XaUtil.isEmpty(sourcefiles)){
            return Collections.EMPTY_LIST;
        }
        List<SearchResult> result = new ArrayList<SearchResult>();
        String indexRootPath = getIndexRoot();
        File f = new File(indexRootPath);
        if(!f.exists()){
            f.mkdirs();
        }
        Directory indexDir = null;
        DirectoryReader ireader = null;
        try{
            Analyzer analyzer = new StandardAnalyzer();
            IndexWriterConfig config = new IndexWriterConfig(analyzer);
            String[] fieldStr = new String[]{"fileName", "content"};
            BooleanClause.Occur[] flags = {BooleanClause.Occur.MUST,
                BooleanClause.Occur.MUST};
            String indexPath = indexRootPath+File.separator;
            indexDir = FSDirectory.open(new File(indexPath).toPath());
            for(FileManage file : sourcefiles){
                ireader = DirectoryReader.open(indexDir);
                IndexSearcher isearcher = new IndexSearcher(ireader);
                String[] queryAry = new String[]{file.getUuidName(), param};
                Query query = MultiFieldQueryParser.parse(queryAry,fieldStr,flags,analyzer);
                ScoreDoc[] hits = isearcher.search(query,1000).scoreDocs;
                Document doc =null;
                for(ScoreDoc hit : hits){
                    doc = isearcher.doc(hit.doc);
                    SearchResult sr = new SearchResult();
                    sr.setScore(hit.score);
                    sr.setFileName(doc.get("fileName"));
                    result.add(sr);
                }
            }
        }catch (Exception e){
            log.error("",e);
        }finally {
            if(null != indexDir){
                try {
                    indexDir.close();
                } catch (IOException e) {
                    log.error("",e);
                }
            }
            if(null != ireader){
                try {
                    ireader.close();
                } catch (IOException e) {
                    log.error("",e);
                }
            }
            return result;
        }
    }

（完）