コード例 #1
0
ファイル: Injector.java プロジェクト: soolr/nutch-1.7
  public void inject(Path crawlDb, Path urlDir) throws IOException {
    SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
    long start = System.currentTimeMillis();
    if (LOG.isInfoEnabled()) {
      LOG.info("Injector: starting at " + sdf.format(start));
      LOG.info("Injector: crawlDb: " + crawlDb);
      LOG.info("Injector: urlDir: " + urlDir);
    }

    Path tempDir =
        new Path(
            getConf().get("mapred.temp.dir", ".")
                + "/inject-temp-"
                + Integer.toString(new Random().nextInt(Integer.MAX_VALUE)));

    // map text input file to a <url,CrawlDatum> file
    if (LOG.isInfoEnabled()) {
      LOG.info("Injector: Converting injected urls to crawl db entries.");
    }
    JobConf sortJob = new NutchJob(getConf());
    sortJob.setJobName("inject " + urlDir);
    FileInputFormat.addInputPath(sortJob, urlDir);
    sortJob.setMapperClass(InjectMapper.class);

    FileOutputFormat.setOutputPath(sortJob, tempDir);
    sortJob.setOutputFormat(SequenceFileOutputFormat.class);
    sortJob.setOutputKeyClass(Text.class);
    sortJob.setOutputValueClass(CrawlDatum.class);
    sortJob.setLong("injector.current.time", System.currentTimeMillis());
    RunningJob mapJob = JobClient.runJob(sortJob);

    long urlsInjected = mapJob.getCounters().findCounter("injector", "urls_injected").getValue();
    long urlsFiltered = mapJob.getCounters().findCounter("injector", "urls_filtered").getValue();
    LOG.info("Injector: total number of urls rejected by filters: " + urlsFiltered);
    LOG.info(
        "Injector: total number of urls injected after normalization and filtering: "
            + urlsInjected);

    // merge with existing crawl db
    if (LOG.isInfoEnabled()) {
      LOG.info("Injector: Merging injected urls into crawl db.");
    }
    JobConf mergeJob = CrawlDb.createJob(getConf(), crawlDb);
    FileInputFormat.addInputPath(mergeJob, tempDir);
    mergeJob.setReducerClass(InjectReducer.class);
    JobClient.runJob(mergeJob);
    CrawlDb.install(mergeJob, crawlDb);

    // clean up
    FileSystem fs = FileSystem.get(getConf());
    fs.delete(tempDir, true);

    long end = System.currentTimeMillis();
    LOG.info(
        "Injector: finished at "
            + sdf.format(end)
            + ", elapsed: "
            + TimingUtil.elapsedTime(start, end));
  }
コード例 #2
0
ファイル: DistCp.java プロジェクト: neutronsharc/hdfsbackup
  /**
   * Initialize DFSCopyFileMapper specific job-configuration.
   *
   * @param conf : The dfs/mapred configuration.
   * @param jobConf : The handle to the jobConf object to be initialized.
   * @param args Arguments
   */
  private static void setup(Configuration conf, JobConf jobConf, final Arguments args)
      throws IOException {
    jobConf.set(DST_DIR_LABEL, args.dst.toUri().toString());

    // set boolean values
    final boolean update = args.flags.contains(Options.UPDATE);
    final boolean overwrite = !update && args.flags.contains(Options.OVERWRITE);
    jobConf.setBoolean(Options.UPDATE.propertyname, update);
    jobConf.setBoolean(Options.OVERWRITE.propertyname, overwrite);
    jobConf.setBoolean(
        Options.IGNORE_READ_FAILURES.propertyname,
        args.flags.contains(Options.IGNORE_READ_FAILURES));
    jobConf.setBoolean(
        Options.PRESERVE_STATUS.propertyname, args.flags.contains(Options.PRESERVE_STATUS));

    final String randomId = getRandomId();
    JobClient jClient = new JobClient(jobConf);
    Path jobDirectory = new Path(jClient.getSystemDir(), NAME + "_" + randomId);
    jobConf.set(JOB_DIR_LABEL, jobDirectory.toString());

    FileSystem dstfs = args.dst.getFileSystem(conf);
    boolean dstExists = dstfs.exists(args.dst);
    boolean dstIsDir = false;
    if (dstExists) {
      dstIsDir = dstfs.getFileStatus(args.dst).isDir();
    }

    // default logPath
    Path logPath = args.log;
    if (logPath == null) {
      String filename = "_distcp_logs_" + randomId;
      if (!dstExists || !dstIsDir) {
        Path parent = args.dst.getParent();
        if (!dstfs.exists(parent)) {
          dstfs.mkdirs(parent);
        }
        logPath = new Path(parent, filename);
      } else {
        logPath = new Path(args.dst, filename);
      }
    }
    FileOutputFormat.setOutputPath(jobConf, logPath);

    // create src list, dst list
    FileSystem jobfs = jobDirectory.getFileSystem(jobConf);

    Path srcfilelist = new Path(jobDirectory, "_distcp_src_files");
    jobConf.set(SRC_LIST_LABEL, srcfilelist.toString());
    SequenceFile.Writer src_writer =
        SequenceFile.createWriter(
            jobfs,
            jobConf,
            srcfilelist,
            LongWritable.class,
            FilePair.class,
            SequenceFile.CompressionType.NONE);

    Path dstfilelist = new Path(jobDirectory, "_distcp_dst_files");
    SequenceFile.Writer dst_writer =
        SequenceFile.createWriter(
            jobfs, jobConf, dstfilelist, Text.class, Text.class, SequenceFile.CompressionType.NONE);

    Path dstdirlist = new Path(jobDirectory, "_distcp_dst_dirs");
    jobConf.set(DST_DIR_LIST_LABEL, dstdirlist.toString());
    SequenceFile.Writer dir_writer =
        SequenceFile.createWriter(
            jobfs,
            jobConf,
            dstdirlist,
            Text.class,
            FilePair.class,
            SequenceFile.CompressionType.NONE);

    // handle the case where the destination directory doesn't exist
    // and we've only a single src directory OR we're updating/overwriting
    // the contents of the destination directory.
    final boolean special = (args.srcs.size() == 1 && !dstExists) || update || overwrite;
    int srcCount = 0, cnsyncf = 0, dirsyn = 0;
    long fileCount = 0L, byteCount = 0L, cbsyncs = 0L;
    try {
      for (Iterator<Path> srcItr = args.srcs.iterator(); srcItr.hasNext(); ) {
        final Path src = srcItr.next();
        FileSystem srcfs = src.getFileSystem(conf);
        FileStatus srcfilestat = srcfs.getFileStatus(src);
        Path root = special && srcfilestat.isDir() ? src : src.getParent();
        if (srcfilestat.isDir()) {
          ++srcCount;
        }

        Stack<FileStatus> pathstack = new Stack<FileStatus>();
        for (pathstack.push(srcfilestat); !pathstack.empty(); ) {
          FileStatus cur = pathstack.pop();
          FileStatus[] children = srcfs.listStatus(cur.getPath());
          for (int i = 0; i < children.length; i++) {
            boolean skipfile = false;
            final FileStatus child = children[i];
            final String dst = makeRelative(root, child.getPath());
            ++srcCount;

            if (child.isDir()) {
              pathstack.push(child);
            } else {
              // skip file if the src and the dst files are the same.
              skipfile = update && sameFile(srcfs, child, dstfs, new Path(args.dst, dst));
              // skip file if it exceed file limit or size limit
              skipfile |=
                  fileCount == args.filelimit || byteCount + child.getLen() > args.sizelimit;

              if (!skipfile) {
                ++fileCount;
                byteCount += child.getLen();

                if (LOG.isTraceEnabled()) {
                  LOG.trace("adding file " + child.getPath());
                }

                ++cnsyncf;
                cbsyncs += child.getLen();
                if (cnsyncf > SYNC_FILE_MAX || cbsyncs > BYTES_PER_MAP) {
                  src_writer.sync();
                  dst_writer.sync();
                  cnsyncf = 0;
                  cbsyncs = 0L;
                }
              }
            }

            if (!skipfile) {
              src_writer.append(
                  new LongWritable(child.isDir() ? 0 : child.getLen()), new FilePair(child, dst));
            }

            dst_writer.append(new Text(dst), new Text(child.getPath().toString()));
          }

          if (cur.isDir()) {
            String dst = makeRelative(root, cur.getPath());
            dir_writer.append(new Text(dst), new FilePair(cur, dst));
            if (++dirsyn > SYNC_FILE_MAX) {
              dirsyn = 0;
              dir_writer.sync();
            }
          }
        }
      }
    } finally {
      checkAndClose(src_writer);
      checkAndClose(dst_writer);
      checkAndClose(dir_writer);
    }

    FileStatus dststatus = null;
    try {
      dststatus = dstfs.getFileStatus(args.dst);
    } catch (FileNotFoundException fnfe) {
      LOG.info(args.dst + " does not exist.");
    }

    // create dest path dir if copying > 1 file
    if (dststatus == null) {
      if (srcCount > 1 && !dstfs.mkdirs(args.dst)) {
        throw new IOException("Failed to create" + args.dst);
      }
    }

    final Path sorted = new Path(jobDirectory, "_distcp_sorted");
    checkDuplication(jobfs, dstfilelist, sorted, conf);

    if (dststatus != null && args.flags.contains(Options.DELETE)) {
      deleteNonexisting(dstfs, dststatus, sorted, jobfs, jobDirectory, jobConf, conf);
    }

    Path tmpDir =
        new Path(
            (dstExists && !dstIsDir) || (!dstExists && srcCount == 1)
                ? args.dst.getParent()
                : args.dst,
            "_distcp_tmp_" + randomId);
    jobConf.set(TMP_DIR_LABEL, tmpDir.toUri().toString());
    LOG.info("srcCount=" + srcCount);
    jobConf.setInt(SRC_COUNT_LABEL, srcCount);
    jobConf.setLong(TOTAL_SIZE_LABEL, byteCount);
    setMapCount(byteCount, jobConf);
  }