（二）编程实现一个类“MyFSDataInputStream”，该类继承“org.apache.hadoop.fs.FSDataInputStream”，要求如下：实现按行读取HDFS中指定文件的方法“readLine()”，如果读到文件末尾，则返回空，否则返回文件一行的文本。
# 进入工作目录
cd /home/hadoop/java_code# 1. 删除旧文件
rm -f MyFSDataInputStream.java MyFSDataInputStream.class# 2. 创建修正后的Java文件并编译运行
cat > MyFSDataInputStream.java << 'EOF'
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;
import java.io.*;public class MyFSDataInputStream extends FSDataInputStream {private BufferedReader reader;public MyFSDataInputStream(FSDataInputStream in) {super(in.getWrappedStream());try {this.reader = new BufferedReader(new InputStreamReader(in, "UTF-8"));} catch (UnsupportedEncodingException e) {throw new RuntimeException("UTF-8编码不受支持", e);}}// 修改方法名为 readNextLine()public String readNextLine() throws IOException {return reader.readLine();}@Overridepublic void close() throws IOException {if (reader != null) {reader.close();}super.close();}public static void main(String[] args) {try {Configuration conf = new Configuration();conf.set("fs.defaultFS", "hdfs://master:8020");FileSystem fs = FileSystem.get(conf);Path filePath = new Path("/user/hadoop/test/file1.txt");if (!fs.exists(filePath)) {System.err.println("错误：HDFS文件不存在 - " + filePath);return;}FSDataInputStream fsIn = fs.open(filePath);MyFSDataInputStream myInputStream = new MyFSDataInputStream(fsIn);System.out.println("===== 开始读取文件内容 =====");String line;int lineNumber = 1;// 使用新方法名while ((line = myInputStream.readNextLine()) != null) {System.out.printf("第 %d 行: %s%n", lineNumber++, line);}System.out.println("===== 文件读取完成 =====");System.out.printf("总共 %d 行%n", lineNumber - 1);myInputStream.close();fs.close();} catch (IOException e) {System.err.println("操作失败: " + e.getMessage());e.printStackTrace();}}
}
EOF# 3. 编译（如果失败会显示错误，成功则无输出）
javac -cp $(hadoop classpath) MyFSDataInputStream.java#4.运行
java -cp $(hadoop classpath):. MyFSDataInputStream
（三）查看Java帮助手册或其它资料，用“java.net.URL”和“org.apache.hadoop.fs.FsURLStreamHandlerFactory”编程完成输出HDFS中指定文件的文本到终端中。
# 1. 进入工作目录
cd /home/hadoop/java_code# 2. 删除旧文件（如有）
rm -f HdfsUrlReader.java HdfsUrlReader.class# 3. 一键写入新源码
cat > HdfsUrlReader.java << 'EOF'import org.apache.hadoop.fs.FsUrlStreamHandlerFactory;
import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.net.URL;public class HdfsUrlReader {public static void main(String[] args) throws Exception {/* 注册 hdfs:// 协议处理器 */URL.setURLStreamHandlerFactory(new FsUrlStreamHandlerFactory());/* 目标文件 URL */String hdfsUrl = "hdfs://master:8020/user/hadoop/file1.txt";URL url = new URL(hdfsUrl);/* 打开流并逐行读取 */try (BufferedReader reader = new BufferedReader(new InputStreamReader(url.openStream(), "UTF-8"))) {System.out.println("===== 通过 URL 读取 HDFS 文件 =====");String line;int lineNo = 1;while ((line = reader.readLine()) != null) {System.out.printf("第 %d 行: %s%n", lineNo++, line);}System.out.println("===== 读取完成 =====");}}
}
EOF# 4. 编译
javac -cp $(hadoop classpath) HdfsUrlReader.java# 5. 运行
java -cp $(hadoop classpath):. com.mwh.HdfsUrlReader
