当前位置: 首页>>代码示例>>Java>>正文


Java PathFilter类代码示例

本文整理汇总了Java中org.apache.hadoop.fs.PathFilter的典型用法代码示例。如果您正苦于以下问题:Java PathFilter类的具体用法?Java PathFilter怎么用?Java PathFilter使用的例子?那么, 这里精选的类代码示例或许可以为您提供帮助。


PathFilter类属于org.apache.hadoop.fs包,在下文中一共展示了PathFilter类的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Java代码示例。

示例1: hasNext

import org.apache.hadoop.fs.PathFilter; //导入依赖的package包/类
@Override
public RemoteIterator<LocatedFileStatus>listLocatedStatus(final Path f,
    final PathFilter filter) throws FileNotFoundException, IOException {
  final InodeTree.ResolveResult<FileSystem> res = fsState
      .resolve(getUriPath(f), true);
  final RemoteIterator<LocatedFileStatus> statusIter = res.targetFileSystem
      .listLocatedStatus(res.remainingPath);

  if (res.isInternalDir()) {
    return statusIter;
  }

  return new RemoteIterator<LocatedFileStatus>() {
    @Override
    public boolean hasNext() throws IOException {
      return statusIter.hasNext();
    }

    @Override
    public LocatedFileStatus next() throws IOException {
      final LocatedFileStatus status = statusIter.next();
      return (LocatedFileStatus)fixFileStatus(status,
          getChrootedPath(res, status, f));
    }
  };
}
 
开发者ID:nucypher,项目名称:hadoop-oss,代码行数:27,代码来源:ViewFileSystem.java

示例2: traverseImpl

import org.apache.hadoop.fs.PathFilter; //导入依赖的package包/类
private static ArrayList<FileStatus> traverseImpl(Storage storage, Path path, PathFilter filter)
    throws IOException {
  if (!storage.exists(path.toString())) {
    return new ArrayList<>();
  }
  ArrayList<FileStatus> result = new ArrayList<>();
  FileStatus[] statuses = storage.listStatus(path.toString());
  for (FileStatus status : statuses) {
    if (status.isDirectory()) {
      result.addAll(traverseImpl(storage, status.getPath(), filter));
    } else {
      if (filter.accept(status.getPath())) {
        result.add(status);
      }
    }
  }
  return result;
}
 
开发者ID:jiangxiluning,项目名称:kafka-connect-hdfs,代码行数:19,代码来源:FileUtils.java

示例3: isDirReadable

import org.apache.hadoop.fs.PathFilter; //导入依赖的package包/类
boolean isDirReadable(DrillFileSystem fs, FileStatus dir) {
  Path p = new Path(dir.getPath(), ParquetFileWriter.PARQUET_METADATA_FILE);
  try {
    if (fs.exists(p)) {
      return true;
    } else {

      if (metaDataFileExists(fs, dir)) {
        return true;
      }
      PathFilter filter = new DrillPathFilter();

      FileStatus[] files = fs.listStatus(dir.getPath(), filter);
      if (files.length == 0) {
        return false;
      }
      return super.isFileReadable(fs, files[0]);
    }
  } catch (IOException e) {
    logger.info("Failure while attempting to check for Parquet metadata file.", e);
    return false;
  }
}
 
开发者ID:skhalifa,项目名称:QDrill,代码行数:24,代码来源:ParquetFormatPlugin.java

示例4: addInputPathRecursively

import org.apache.hadoop.fs.PathFilter; //导入依赖的package包/类
/**
 * Add files in the input path recursively into the results.
 * @param result
 *          The List to store all files.
 * @param fs
 *          The FileSystem.
 * @param path
 *          The input path.
 * @param inputFilter
 *          The input filter that can be used to filter files/dirs. 
 * @throws IOException
 */
protected void addInputPathRecursively(List<FileStatus> result,
    FileSystem fs, Path path, PathFilter inputFilter) 
    throws IOException {
  RemoteIterator<LocatedFileStatus> iter = fs.listLocatedStatus(path);
  while (iter.hasNext()) {
    LocatedFileStatus stat = iter.next();
    if (inputFilter.accept(stat.getPath())) {
      if (stat.isDirectory()) {
        addInputPathRecursively(result, fs, stat.getPath(), inputFilter);
      } else {
        result.add(stat);
      }
    }
  }
}
 
开发者ID:naver,项目名称:hadoop,代码行数:28,代码来源:FileInputFormat.java

示例5: LocatedFileStatusFetcher

import org.apache.hadoop.fs.PathFilter; //导入依赖的package包/类
/**
 * @param conf configuration for the job
 * @param dirs the initial list of paths
 * @param recursive whether to traverse the patchs recursively
 * @param inputFilter inputFilter to apply to the resulting paths
 * @param newApi whether using the mapred or mapreduce API
 * @throws InterruptedException
 * @throws IOException
 */
public LocatedFileStatusFetcher(Configuration conf, Path[] dirs,
    boolean recursive, PathFilter inputFilter, boolean newApi) throws InterruptedException,
    IOException {
  int numThreads = conf.getInt(FileInputFormat.LIST_STATUS_NUM_THREADS,
      FileInputFormat.DEFAULT_LIST_STATUS_NUM_THREADS);
  rawExec = Executors.newFixedThreadPool(
      numThreads,
      new ThreadFactoryBuilder().setDaemon(true)
          .setNameFormat("GetFileInfo #%d").build());
  exec = MoreExecutors.listeningDecorator(rawExec);
  resultQueue = new LinkedBlockingQueue<List<FileStatus>>();
  this.conf = conf;
  this.inputDirs = dirs;
  this.recursive = recursive;
  this.inputFilter = inputFilter;
  this.newApi = newApi;
}
 
开发者ID:naver,项目名称:hadoop,代码行数:27,代码来源:LocatedFileStatusFetcher.java

示例6: scanDirectory

import org.apache.hadoop.fs.PathFilter; //导入依赖的package包/类
@VisibleForTesting
protected static List<FileStatus> scanDirectory(Path path, FileContext fc,
    PathFilter pathFilter) throws IOException {
  path = fc.makeQualified(path);
  List<FileStatus> jhStatusList = new ArrayList<FileStatus>();
  try {
    RemoteIterator<FileStatus> fileStatusIter = fc.listStatus(path);
    while (fileStatusIter.hasNext()) {
      FileStatus fileStatus = fileStatusIter.next();
      Path filePath = fileStatus.getPath();
      if (fileStatus.isFile() && pathFilter.accept(filePath)) {
        jhStatusList.add(fileStatus);
      }
    }
  } catch (FileNotFoundException fe) {
    LOG.error("Error while scanning directory " + path, fe);
  }
  return jhStatusList;
}
 
开发者ID:naver,项目名称:hadoop,代码行数:20,代码来源:HistoryFileManager.java

示例7: publishPlainDataStatistics

import org.apache.hadoop.fs.PathFilter; //导入依赖的package包/类
static DataStatistics publishPlainDataStatistics(Configuration conf, 
                                                 Path inputDir) 
throws IOException {
  FileSystem fs = inputDir.getFileSystem(conf);

  // obtain input data file statuses
  long dataSize = 0;
  long fileCount = 0;
  RemoteIterator<LocatedFileStatus> iter = fs.listFiles(inputDir, true);
  PathFilter filter = new Utils.OutputFileUtils.OutputFilesFilter();
  while (iter.hasNext()) {
    LocatedFileStatus lStatus = iter.next();
    if (filter.accept(lStatus.getPath())) {
      dataSize += lStatus.getLen();
      ++fileCount;
    }
  }

  // publish the plain data statistics
  LOG.info("Total size of input data : " 
           + StringUtils.humanReadableInt(dataSize));
  LOG.info("Total number of input data files : " + fileCount);
  
  return new DataStatistics(dataSize, fileCount, false);
}
 
开发者ID:naver,项目名称:hadoop,代码行数:26,代码来源:GenerateData.java

示例8: splitLog

import org.apache.hadoop.fs.PathFilter; //导入依赖的package包/类
/**
 * This method is the base split method that splits WAL files matching a filter. Callers should
 * pass the appropriate filter for meta and non-meta WALs.
 * @param serverNames logs belonging to these servers will be split; this will rename the log
 *                    directory out from under a soft-failed server
 * @param filter
 * @throws IOException
 */
public void splitLog(final Set<ServerName> serverNames, PathFilter filter) throws IOException {
  long splitTime = 0, splitLogSize = 0;
  List<Path> logDirs = getLogDirs(serverNames);

  splitLogManager.handleDeadWorkers(serverNames);
  splitTime = EnvironmentEdgeManager.currentTime();
  splitLogSize = splitLogManager.splitLogDistributed(serverNames, logDirs, filter);
  splitTime = EnvironmentEdgeManager.currentTime() - splitTime;

  if (this.metricsMasterFilesystem != null) {
    if (filter == META_FILTER) {
      this.metricsMasterFilesystem.addMetaWALSplit(splitTime, splitLogSize);
    } else {
      this.metricsMasterFilesystem.addSplit(splitTime, splitLogSize);
    }
  }
}
 
开发者ID:fengchen8086,项目名称:ditb,代码行数:26,代码来源:MasterFileSystem.java

示例9: getFileList

import org.apache.hadoop.fs.PathFilter; //导入依赖的package包/类
/**
 * Get a list of paths that need to be split given a set of server-specific directories and
 * optionally  a filter.
 *
 * See {@link DefaultWALProvider#getServerNameFromWALDirectoryName} for more info on directory
 * layout.
 *
 * Should be package-private, but is needed by
 * {@link org.apache.hadoop.hbase.wal.WALSplitter#split(Path, Path, Path, FileSystem,
 *     Configuration, WALFactory)} for tests.
 */
@VisibleForTesting
public static FileStatus[] getFileList(final Configuration conf, final List<Path> logDirs,
    final PathFilter filter)
    throws IOException {
  List<FileStatus> fileStatus = new ArrayList<FileStatus>();
  for (Path logDir : logDirs) {
    final FileSystem fs = logDir.getFileSystem(conf);
    if (!fs.exists(logDir)) {
      LOG.warn(logDir + " doesn't exist. Nothing to do!");
      continue;
    }
    FileStatus[] logfiles = FSUtils.listStatus(fs, logDir, filter);
    if (logfiles == null || logfiles.length == 0) {
      LOG.info(logDir + " is empty dir, no logs to split");
    } else {
      Collections.addAll(fileStatus, logfiles);
    }
  }
  FileStatus[] a = new FileStatus[fileStatus.size()];
  return fileStatus.toArray(a);
}
 
开发者ID:fengchen8086,项目名称:ditb,代码行数:33,代码来源:SplitLogManager.java

示例10: visitRegionStoreFiles

import org.apache.hadoop.fs.PathFilter; //导入依赖的package包/类
/**
 * Iterate over the region store files
 *
 * @param fs {@link FileSystem}
 * @param regionDir {@link Path} to the region directory
 * @param visitor callback object to get the store files
 * @throws IOException if an error occurred while scanning the directory
 */
public static void visitRegionStoreFiles(final FileSystem fs, final Path regionDir,
    final StoreFileVisitor visitor) throws IOException {
  FileStatus[] families = FSUtils.listStatus(fs, regionDir, new FSUtils.FamilyDirFilter(fs));
  if (families == null) {
    if (LOG.isTraceEnabled()) {
      LOG.trace("No families under region directory:" + regionDir);
    }
    return;
  }

  PathFilter fileFilter = new FSUtils.FileFilter(fs);
  for (FileStatus family: families) {
    Path familyDir = family.getPath();
    String familyName = familyDir.getName();

    // get all the storeFiles in the family
    FileStatus[] storeFiles = FSUtils.listStatus(fs, familyDir, fileFilter);
    if (storeFiles == null) {
      if (LOG.isTraceEnabled()) {
        LOG.trace("No hfiles found for family: " + familyDir + ", skipping.");
      }
      continue;
    }

    for (FileStatus hfile: storeFiles) {
      Path hfilePath = hfile.getPath();
      visitor.storeFile(regionDir.getName(), familyName, hfilePath.getName());
    }
  }
}
 
开发者ID:fengchen8086,项目名称:ditb,代码行数:39,代码来源:FSVisitor.java

示例11: getStoreFiles

import org.apache.hadoop.fs.PathFilter; //导入依赖的package包/类
/**
 * Returns all files belonging to the given region directory. Could return an
 * empty list.
 *
 * @param fs  The file system reference.
 * @param regionDir  The region directory to scan.
 * @return The list of files found.
 * @throws IOException When scanning the files fails.
 */
static List<Path> getStoreFiles(FileSystem fs, Path regionDir)
throws IOException {
  List<Path> res = new ArrayList<Path>();
  PathFilter dirFilter = new FSUtils.DirFilter(fs);
  FileStatus[] familyDirs = fs.listStatus(regionDir, dirFilter);
  for(FileStatus dir : familyDirs) {
    FileStatus[] files = fs.listStatus(dir.getPath());
    for (FileStatus file : files) {
      if (!file.isDir()) {
        res.add(file.getPath());
      }
    }
  }
  return res;
}
 
开发者ID:fengchen8086,项目名称:ditb,代码行数:25,代码来源:IndexFile.java

示例12: MantaRemoteIterator

import org.apache.hadoop.fs.PathFilter; //导入依赖的package包/类
/**
 * Creates a new instance wrapping a {@link MantaDirectoryListingIterator}.
 *
 * @param filter filter object that will filter out results
 * @param stream backing stream
 * @param path base path that is being iterated
 * @param fs reference to the underlying filesystem
 * @param autocloseWhenFinished flag indicate whether or not to close all
 *                              resources when we have finished iterating
 */
public MantaRemoteIterator(final PathFilter filter,
                           final Stream<MantaObject> stream,
                           final Path path,
                           final FileSystem fs,
                           final boolean autocloseWhenFinished) {
    this.filter = filter;

    if (filter == null) {
        this.inner = stream.iterator();
    } else {
        this.inner = stream.filter(obj -> filter.accept(new Path(obj.getPath()))).iterator();
    }

    this.closeableStream = stream;
    this.path = path;
    this.fs = fs;
    this.autocloseWhenFinished = autocloseWhenFinished;
    this.nextRef.set(nextAcceptable());
}
 
开发者ID:joyent,项目名称:hadoop-manta,代码行数:30,代码来源:MantaRemoteIterator.java

示例13: getReaders

import org.apache.hadoop.fs.PathFilter; //导入依赖的package包/类
/** Open the output generated by this format. */
public static MapFile.Reader[] getReaders(Path dir,
    Configuration conf) throws IOException {
  FileSystem fs = dir.getFileSystem(conf);
  PathFilter filter = new PathFilter() {
    @Override
    public boolean accept(Path path) {
      String name = path.getName();
      if (name.startsWith("_") || name.startsWith("."))
        return false;
      return true;
    }
  };
  Path[] names = FileUtil.stat2Paths(fs.listStatus(dir, filter));

  // sort names, so that hash partitioning works
  Arrays.sort(names);
  
  MapFile.Reader[] parts = new MapFile.Reader[names.length];
  for (int i = 0; i < names.length; i++) {
    parts[i] = new MapFile.Reader(fs, names[i].toString(), conf);
  }
  return parts;
}
 
开发者ID:aliyun-beta,项目名称:aliyun-oss-hadoop-fs,代码行数:25,代码来源:MapFileOutputFormat.java

示例14: listLocatedStatus

import org.apache.hadoop.fs.PathFilter; //导入依赖的package包/类
@Override
protected RemoteIterator<LocatedFileStatus> listLocatedStatus(
        final Path path, final PathFilter filter) throws IOException {
    LOG.debug("List located status for path: {}", path);

    String mantaPath = mantaPath(path);

    if (!client.existsAndIsAccessible(mantaPath)) {
        throw new FileNotFoundException(mantaPath);
    }

    /* We emulate a normal filesystem by showing the home directory under root in
     * in order to provide compatibility with consumers that expect this behavior. */
    if (mantaPath.equals(SEPARATOR)) {
        LocatedFileStatus singleEntry = new LocatedFileStatus(new MantaFileStatus(true, path), null);
        return new SingleEntryRemoteIterator<>(singleEntry);
    }

    if (!client.existsAndIsAccessible(mantaPath)) {
        throw new FileNotFoundException(mantaPath);
    }

    Stream<MantaObject> stream = client.listObjects(mantaPath);
    return new MantaRemoteIterator(filter, stream, path, this, true);
}
 
开发者ID:joyent,项目名称:hadoop-manta,代码行数:26,代码来源:MantaFileSystem.java

示例15: mergeFilters

import org.apache.hadoop.fs.PathFilter; //导入依赖的package包/类
/**
 * Will merge given array of filters into one.
 * If given array of filters is empty, will return {@link #DUMMY_FILTER}.
 *
 * @param filters array of filters
 * @return one filter that combines all given filters
 */
public static PathFilter mergeFilters(final PathFilter... filters) {
  if (filters.length == 0) {
    return DUMMY_FILTER;
  }

  return new PathFilter() {
    @Override
    public boolean accept(Path path) {
      for (PathFilter filter : filters) {
        if (!filter.accept(path)) {
          return false;
        }
      }
      return true;
    }
  };
}
 
开发者ID:axbaretto,项目名称:drill,代码行数:25,代码来源:FileSystemUtil.java


注:本文中的org.apache.hadoop.fs.PathFilter类示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。