List of usage examples for org.apache.hadoop.io ArrayFile.Reader ArrayFile.Reader
public Reader(FileSystem fs, String file, Configuration conf) throws IOException
From source file:org.apache.nutch.parse.ParseData.java
License:Apache License
public static void main(String argv[]) throws Exception { String usage = "ParseData (-local | -dfs <namenode:port>) recno segment"; if (argv.length < 3) { System.out.println("usage:" + usage); return;//from w w w.ja va 2 s . co m } Options opts = new Options(); Configuration conf = NutchConfiguration.create(); GenericOptionsParser parser = new GenericOptionsParser(conf, opts, argv); String[] remainingArgs = parser.getRemainingArgs(); FileSystem fs = FileSystem.get(conf); try { int recno = Integer.parseInt(remainingArgs[0]); String segment = remainingArgs[1]; Path file = new Path(segment, DIR_NAME); System.out.println("Reading from file: " + file); ArrayFile.Reader parses = new ArrayFile.Reader(fs, file.toString(), conf); ParseData parseDatum = new ParseData(); parses.get(recno, parseDatum); System.out.println("Retrieved " + recno + " from file " + file); System.out.println(parseDatum); parses.close(); } finally { fs.close(); } }
From source file:org.apache.nutch.parse.ParseText.java
License:Apache License
public static void main(String argv[]) throws Exception { String usage = "ParseText (-local | -dfs <namenode:port>) recno segment"; if (argv.length < 3) { System.out.println("usage:" + usage); return;/*from w w w . ja va 2 s . c o m*/ } Options opts = new Options(); Configuration conf = NutchConfiguration.create(); GenericOptionsParser parser = new GenericOptionsParser(conf, opts, argv); String[] remainingArgs = parser.getRemainingArgs(); FileSystem fs = FileSystem.get(conf); try { int recno = Integer.parseInt(remainingArgs[0]); String segment = remainingArgs[1]; String filename = new Path(segment, ParseText.DIR_NAME).toString(); ParseText parseText = new ParseText(); ArrayFile.Reader parseTexts = new ArrayFile.Reader(fs, filename, conf); parseTexts.get(recno, parseText); System.out.println("Retrieved " + recno + " from file " + filename); System.out.println(parseText); parseTexts.close(); } finally { fs.close(); } }