package cn.itcast.lucene.utils;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStreamReader;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.Field.Index;
import org.apache.lucene.document.Field.Store;
public class FileAndDocumentUtils {
public static Document file2Document(File file) {
Document doc = new Document();
// Store.YES 是否存储 Index.ANALYZED 是否分词
doc.add(new Field("name", file.getName(), Store.YES, Index.ANALYZED));
doc.add(new Field("content", readFile(file), Store.YES, Index.ANALYZED));
doc.add(new Field("size", file.length() + "", Store.YES, Index.NOT_ANALYZED));
doc.add(new Field("path", file.getAbsolutePath(), Store.YES, Index.NOT_ANALYZED));
return doc;
}
// 读取文件内容
private static String readFile(File file) {
// TODO Auto-generated method stub
StringBuffer content = new StringBuffer();
try {
BufferedReader bfr = new BufferedReader(new InputStreamReader(new FileInputStream(file)));
for (String line = null; (line = bfr.readLine()) != null;) {
content.append(line).append("\n");
}
} catch (Exception e) {
throw new RuntimeException(e);
}
return content.toString();
}
public static File document2File(Document doc) {
return null;
}
/**
*
* @param doc
*/
public static void printDocumentInfo(Document doc) {
// TODO Auto-generated method stub
System.out.println("name = " + doc.get("name"));
System.out.println("content = " + doc.get("content"));
System.out.println("size = " + doc.get("size"));
System.out.println("path = " + doc.get("path"));
}
}