Lucene全文索引与搜索入门篇2 - 可视化理解Lucene

@Test
public void create() throws Exception {
    String content = "hello world index";
    String indexPath = "test/index";
    IndexWriterConfig iwc = new IndexWriterConfig(new StandardAnalyzer());
    try (Directory dir = FSDirectory.open(Paths.get(indexPath));
         IndexWriter writer = new IndexWriter(dir, iwc);
    ) {
        Document doc = new Document();
        doc.add(new StringField("path", indexPath, Field.Store.YES));
        doc.add(new TextField("content", content, Field.Store.YES));
        doc.add(new LongPoint("modified", Clock.systemUTC().millis()));
        writer.addDocument(doc);
    }

@Test
public void update() throws Exception {
    String content = "world index";
    String indexPath = "test/index";
    IndexWriterConfig iwc = new IndexWriterConfig(new StandardAnalyzer());
    try (Directory dir = FSDirectory.open(Paths.get(indexPath));
         IndexWriter writer = new IndexWriter(dir, iwc);
    ) {
        Document doc = new Document();
        doc.add(new StringField("path", indexPath + "_update", Field.Store.YES));
        doc.add(new TextField("content", content, Field.Store.YES));
        doc.add(new LongPoint("modified", Clock.systemUTC().millis()));
        writer.updateDocument(new Term("path", indexPath), doc);
    }
}

@Test
public void delete() throws Exception {
    String fieldName = "content";
    String indexPath = "test/index";
    IndexWriterConfig iwc = new IndexWriterConfig(new StandardAnalyzer());
    try (Directory dir = FSDirectory.open(Paths.get(indexPath));
         IndexWriter writer = new IndexWriter(dir, iwc);
    ) {
        QueryParser parser = new QueryParser(fieldName, new StandardAnalyzer());
        Query query = parser.parse("hello world");
        long deleteCounts = writer.deleteDocuments(query);
        System.out.println("delete doc by query of count=" + deleteCounts);
    }
}

@Test
public void read() throws Exception {
    String indexPath = "test/index";
    Directory dir = FSDirectory.open(Paths.get(indexPath));
    DirectoryReader reader = DirectoryReader.open(dir);
    IndexReader indexReader = new IndexSearcher(reader).getIndexReader();
    //获取索引信息
    System.out.println("索引leaves信息：" + indexReader.getContext().leaves());
    System.out.println("索引中文档数量：" + indexReader.numDocs());
    System.out.println("索引中文档的最大值：" + indexReader.maxDoc());
    System.out.println("索引中被删除文档数量：" + indexReader.numDeletedDocs());
}

@Test
public void search() throws Exception {
    String indexPath = "test/index";
    String fieldName = "content";
    Directory dir = FSDirectory.open(Paths.get(indexPath));
    IndexSearcher searcher = new IndexSearcher(DirectoryReader.open(dir));
    QueryParser parser = new QueryParser(fieldName, new StandardAnalyzer());
    Query query = parser.parse("hello world");
    TopDocs docs = searcher.search(query, 10);
    System.out.println("匹配的搜索条数：" + docs.totalHits.value);
    for (int i = 0; i < docs.scoreDocs.length; i++) {
        ScoreDoc scoreDoc = docs.scoreDocs[i];
        System.out.println("获取Document文档 docId=" + scoreDoc.doc + "，匹配打分=" + scoreDoc.score);
        Document doc = searcher.doc(scoreDoc.doc);
        Iterator<IndexableField> iterator = doc.iterator();
        while (iterator.hasNext()) {
            IndexableField field = iterator.next();
            String fieldValue = doc.get(field.name());
            System.out.println("[fieldName]=" + field.name() + ",[fieldValue]=" + fieldValue);
        }
        System.out.println();
    }
}

@Test
public void booleanSearch() throws Exception {
    String indexPath = "test/index";
    Directory dir = FSDirectory.open(Paths.get(indexPath));
    IndexSearcher searcher = new IndexSearcher(DirectoryReader.open(dir));
    Query queryContent = new QueryParser("content", new StandardAnalyzer()).parse("hello world");
    BoostQuery boost = new BoostQuery(queryContent, 100);
    Query queryPath = new QueryParser("path",  new SimpleAnalyzer()).parse("test\\/index");
    BooleanQuery.Builder builder = new BooleanQuery.Builder();
    builder.add(queryContent, BooleanClause.Occur.MUST);
    builder.add(boost, BooleanClause.Occur.SHOULD);
    builder.add(queryPath, BooleanClause.Occur.MUST);
    BooleanQuery query = builder.build();
    TopDocs docs = searcher.search(query, 10);
    System.out.println("匹配的搜索条数：" + docs.totalHits.value);
    for (int i = 0; i < docs.scoreDocs.length; i++) {
        ScoreDoc scoreDoc = docs.scoreDocs[i];
        System.out.println("获取Document文档 docId=" + scoreDoc.doc + "，匹配打分=" + scoreDoc.score);
        Document doc = searcher.doc(scoreDoc.doc);
        Iterator<IndexableField> iterator = doc.iterator();
        while (iterator.hasNext()) {
            IndexableField field = iterator.next();
            String fieldValue = doc.get(field.name());
            System.out.println("[fieldName]=" + field.name() + ",[fieldValue]=" + fieldValue);
        }
        System.out.println();
    }
}

Occur

Occur是用来决定各个条件的逻辑关系，具体如下：

l Occur.SHOULD 或

l Occur.MUST 且

l Occur.MUST_NOT 且非

l Occur.FILTER 同 MUST，但该字句不参与评分

而这些逻辑组合之间也有要关注的地方(下面几点关注一下即可，跟版本有关，在8.1.0的版本中是直接意思，并没有出现下面的情况。应该是新版已经更新，6版本之前的可以关注下面的信息。)：

1. MUST和MUST：取得连个查询子句的交集。
2. MUST和MUST_NOT：表示查询结果中不能包含MUST_NOT所对应得查询子句的检索结果。
3. SHOULD与MUST_NOT：连用时，功能同MUST和MUST_NOT。
4. SHOULD与MUST连用时，结果为MUST子句的检索结果,但是SHOULD可影响排序。
5. SHOULD与SHOULD：表示“或”关系，最终检索结果为所有检索子句的并集。
6. MUST_NOT和MUST_NOT：无意义，检索无结果。