我正在尝试在Lucene中创建一个Java独立应用程序,以满足从XML文件中查找文本的目的。以下是我收到的xml文件的示例:
<firstName>Tom</firstName><lastName>Jobs</lastName><role>admin</role><designation>manager</designation>
下面是索引器的代码: SimpleFileIndexer.java
public class SimpleFileIndexer {
public static void main(String[] args) throws Exception {
File indexDir = new File("<path of the index directory>");
File dataDir = new File("<path of the data directory>");
String suffix = "txt";
SimpleFileIndexer indexer = new SimpleFileIndexer();
int numIndex = indexer.index(indexDir, dataDir, suffix);
System.out.println("Numer of total files indexed: " + numIndex);
}
@SuppressWarnings("deprecation")
private int index(File indexDir, File dataDir, String suffix) throws Exception {
IndexWriter indexWriter = new IndexWriter(FSDirectory.open(indexDir), new SimpleAnalyzer(), true,
IndexWriter.MaxFieldLength.LIMITED);
indexWriter.setUseCompoundFile(false);
indexDirectory(indexWriter, dataDir, suffix);
int numIndexed = indexWriter.maxDoc();
indexWriter.optimize();
indexWriter.close();
return numIndexed;
}
private void indexDirectory(IndexWriter indexWriter, File dataDir, String suffix) throws IOException {
File[] files = dataDir.listFiles();
for (int i = 0; i < files.length; i++) {
File f = files[i];
if (f.isDirectory()) {
indexDirectory(indexWriter, f, suffix);
} else {
indexFileWithIndexWriter(indexWriter, f, suffix);
}
}
}
private void indexFileWithIndexWriter(IndexWriter indexWriter, File f, String suffix) throws IOException {
if (f.isHidden() || f.isDirectory() || !f.canRead() || !f.exists()) {
return;
}
if (suffix != null && f.getName().endsWith(suffix)) {
System.out.println("Indexing file:... " + f.getCanonicalPath());
Document doc = new Document();
doc.add(new Field("contents", new FileReader(f)));
doc.add(new Field("filename", f.getCanonicalPath(), Field.Store.YES, Field.Index.ANALYZED));
indexWriter.addDocument(doc);
}
}
}
以下是搜索器的代码: SimpleSearcher.java
public class SimpleSearcher {
public static final String FIELD_CONTENTS = "contents";
public static void main(String[] args) throws Exception {
SimpleSearcher searcher = new SimpleSearcher();
searcher.searchAdvancedIndex();
}
@SuppressWarnings("deprecation")
private void searchAdvancedIndex() throws IOException {
File indexDir = new File("<path of the indexed file directory>");
Directory directory = FSDirectory.open(indexDir);
IndexSearcher searcher = new IndexSearcher(directory);
Query query1 = new TermQuery(new Term(FIELD_CONTENTS, "<firstName>Tom</firstName>"));
Query query2 = new TermQuery(new Term(FIELD_CONTENTS, "<lastName>Jobs</lastName>"));
BooleanQuery booleanQuery = new BooleanQuery();
booleanQuery.add(query1, BooleanClause.Occur.MUST);
booleanQuery.add(query2, BooleanClause.Occur.MUST);
displayQuery(booleanQuery);
TopDocs topDocs = searcher.search(booleanQuery, 100);
ScoreDoc[] hits = topDocs.scoreDocs;
for (int i = 0; i < hits.length; i++) {
int docId = hits[i].doc;
Document d = searcher.doc(docId);
System.out.println(d.get("filename"));
}
System.out.println("Found " + hits.length);
searcher.close();
}
public static void displayQuery(Query query) {
System.out.println("Query: " + query.toString());
}
}
我试图找出文件中是否存在文本<firstName>Tom</firstName>
和<lastName>Jobs</lastName>
。当我运行SimpleIndexer.java文件时,索引创建成功,但是当我运行SimpleSearcher.java文件时,我没有得到文本。
任何帮助都会非常有帮助和赞赏。