Example usage for org.apache.hadoop.fs FileStatus FileStatus

List of usage examples for org.apache.hadoop.fs FileStatus FileStatus

Introduction

In this page you can find the example usage for org.apache.hadoop.fs FileStatus FileStatus.

Prototype

public FileStatus() 

Source Link

Usage

From source file:com.inmobi.conduit.distcp.tools.TestGlobbedCopyListing.java

License:Apache License

private void verifyContents(Path listingPath) throws Exception {
    SequenceFile.Reader reader = new SequenceFile.Reader(cluster.getFileSystem(), listingPath,
            new Configuration());
    Text key = new Text();
    FileStatus value = new FileStatus();
    Map<String, String> actualValues = new HashMap<String, String>();
    while (reader.next(key, value)) {
        actualValues.put(value.getPath().toString(), key.toString());
    }//from   w w  w .j  ava2  s  . c  om

    Assert.assertEquals(expectedValues.size(), actualValues.size());
    for (Map.Entry<String, String> entry : actualValues.entrySet()) {
        Assert.assertEquals(entry.getValue(), expectedValues.get(entry.getKey()));
    }
}

From source file:com.pinterest.hdfsbackup.distcp.DistCp.java

License:Apache License

/** Delete the dst files/dirs which do not exist in src */
static private void deleteNonexisting(FileSystem dstfs, FileStatus dstroot, Path dstsorted, FileSystem jobfs,
        Path jobdir, JobConf jobconf, Configuration conf) throws IOException {
    if (!dstroot.isDir()) {
        throw new IOException("dst must be a directory when option " + Options.DELETE.cmd
                + " is set, but dst (= " + dstroot.getPath() + ") is not a directory.");
    }/*from ww  w . j  a  v  a 2s. co m*/

    //write dst lsr results
    final Path dstlsr = new Path(jobdir, "_distcp_dst_lsr");
    final SequenceFile.Writer writer = SequenceFile.createWriter(jobfs, jobconf, dstlsr, Text.class,
            FileStatus.class, SequenceFile.CompressionType.NONE);
    try {
        //do lsr to get all file statuses in dstroot
        final Stack<FileStatus> lsrstack = new Stack<FileStatus>();
        for (lsrstack.push(dstroot); !lsrstack.isEmpty();) {
            final FileStatus status = lsrstack.pop();
            if (status.isDir()) {
                for (FileStatus child : dstfs.listStatus(status.getPath())) {
                    String relative = makeRelative(dstroot.getPath(), child.getPath());
                    writer.append(new Text(relative), child);
                    lsrstack.push(child);
                }
            }
        }
    } finally {
        checkAndClose(writer);
    }

    //sort lsr results
    final Path sortedlsr = new Path(jobdir, "_distcp_dst_lsr_sorted");
    SequenceFile.Sorter sorter = new SequenceFile.Sorter(jobfs, new Text.Comparator(), Text.class,
            FileStatus.class, jobconf);
    sorter.sort(dstlsr, sortedlsr);

    //compare lsr list and dst list
    SequenceFile.Reader lsrin = null;
    SequenceFile.Reader dstin = null;
    try {
        lsrin = new SequenceFile.Reader(jobfs, sortedlsr, jobconf);
        dstin = new SequenceFile.Reader(jobfs, dstsorted, jobconf);

        //compare sorted lsr list and sorted dst list
        final Text lsrpath = new Text();
        final FileStatus lsrstatus = new FileStatus();
        final Text dstpath = new Text();
        final Text dstfrom = new Text();
        final FsShell shell = new FsShell(conf);
        final String[] shellargs = { "-rmr", null };

        boolean hasnext = dstin.next(dstpath, dstfrom);
        for (; lsrin.next(lsrpath, lsrstatus);) {
            int dst_cmp_lsr = dstpath.compareTo(lsrpath);
            for (; hasnext && dst_cmp_lsr < 0;) {
                hasnext = dstin.next(dstpath, dstfrom);
                dst_cmp_lsr = dstpath.compareTo(lsrpath);
            }

            if (dst_cmp_lsr == 0) {
                //lsrpath exists in dst, skip it
                hasnext = dstin.next(dstpath, dstfrom);
            } else {
                //lsrpath does not exist, delete it
                String s = new Path(dstroot.getPath(), lsrpath.toString()).toString();
                if (shellargs[1] == null || !isAncestorPath(shellargs[1], s)) {
                    shellargs[1] = s;
                    int r = 0;
                    try {
                        r = shell.run(shellargs);
                    } catch (Exception e) {
                        throw new IOException("Exception from shell.", e);
                    }
                    if (r != 0) {
                        throw new IOException(
                                "\"" + shellargs[0] + " " + shellargs[1] + "\" returns non-zero value " + r);
                    }
                }
            }
        }
    } finally {
        checkAndClose(lsrin);
        checkAndClose(dstin);
    }
}

From source file:com.scaleunlimited.cascading.DistCp.java

License:Apache License

/** Delete the dst files/dirs which do not exist in src */
static private void deleteNonexisting(FileSystem dstfs, FileStatus dstroot, Path dstsorted, FileSystem jobfs,
        Path jobdir, JobConf jobconf, Configuration conf) throws IOException {
    if (!dstroot.isDir()) {
        throw new IOException("dst must be a directory when option " + Options.DELETE.cmd
                + " is set, but dst (= " + dstroot.getPath() + ") is not a directory.");
    }//from   w  w  w  .  jav a 2  s .  c o  m

    //write dst lsr results
    final Path dstlsr = new Path(jobdir, "_distcp_dst_lsr");
    final SequenceFile.Writer writer = SequenceFile.createWriter(jobfs, jobconf, dstlsr, Text.class,
            FileStatus.class, SequenceFile.CompressionType.NONE);
    try {
        //do lsr to get all file statuses in dstroot
        final Stack<FileStatus> lsrstack = new Stack<FileStatus>();
        for (lsrstack.push(dstroot); !lsrstack.isEmpty();) {
            final FileStatus status = lsrstack.pop();
            if (status.isDir()) {
                for (FileStatus child : dstfs.listStatus(status.getPath())) {
                    String relative = makeRelative(dstroot.getPath(), child.getPath());
                    writer.append(new Text(relative), child);
                    lsrstack.push(child);
                }
            }
        }
    } finally {
        checkAndClose(writer);
    }

    //sort lsr results
    final Path sortedlsr = new Path(jobdir, "_distcp_dst_lsr_sorted");
    SequenceFile.Sorter sorter = new SequenceFile.Sorter(jobfs, new Text.Comparator(), Text.class,
            FileStatus.class, jobconf);
    sorter.sort(dstlsr, sortedlsr);

    //compare lsr list and dst list  
    SequenceFile.Reader lsrin = null;
    SequenceFile.Reader dstin = null;
    try {
        lsrin = new SequenceFile.Reader(jobfs, sortedlsr, jobconf);
        dstin = new SequenceFile.Reader(jobfs, dstsorted, jobconf);

        //compare sorted lsr list and sorted dst list
        final Text lsrpath = new Text();
        final FileStatus lsrstatus = new FileStatus();
        final Text dstpath = new Text();
        final Text dstfrom = new Text();
        final FsShell shell = new FsShell(conf);
        final String[] shellargs = { "-rmr", null };

        boolean hasnext = dstin.next(dstpath, dstfrom);
        for (; lsrin.next(lsrpath, lsrstatus);) {
            int dst_cmp_lsr = dstpath.compareTo(lsrpath);
            for (; hasnext && dst_cmp_lsr < 0;) {
                hasnext = dstin.next(dstpath, dstfrom);
                dst_cmp_lsr = dstpath.compareTo(lsrpath);
            }

            if (dst_cmp_lsr == 0) {
                //lsrpath exists in dst, skip it
                hasnext = dstin.next(dstpath, dstfrom);
            } else {
                //lsrpath does not exist, delete it
                String s = new Path(dstroot.getPath(), lsrpath.toString()).toString();
                if (shellargs[1] == null || !isAncestorPath(shellargs[1], s)) {
                    shellargs[1] = s;
                    int r = 0;
                    try {
                        r = shell.run(shellargs);
                    } catch (Exception e) {
                        throw new IOException("Exception from shell.", e);
                    }
                    if (r != 0) {
                        throw new IOException(
                                "\"" + shellargs[0] + " " + shellargs[1] + "\" returns non-zero value " + r);
                    }
                }
            }
        }
    } finally {
        checkAndClose(lsrin);
        checkAndClose(dstin);
    }
}

From source file:com.uber.hoodie.common.table.view.IncrementalTimelineSyncFileSystemView.java

License:Apache License

private void removeFileSlicesForPartition(HoodieTimeline timeline, HoodieInstant instant, String partition,
        List<String> paths) {
    if (isPartitionAvailableInStore(partition)) {
        log.info("Removing file slices for partition (" + partition + ") for instant (" + instant + ")");
        FileStatus[] statuses = paths.stream().map(p -> {
            FileStatus status = new FileStatus();
            status.setPath(new Path(p));
            return status;
        }).toArray(FileStatus[]::new);
        List<HoodieFileGroup> fileGroups = buildFileGroups(statuses,
                timeline.filterCompletedAndCompactionInstants(), false);
        applyDeltaFileSlicesToPartitionView(partition, fileGroups, DeltaApplyMode.REMOVE);
    } else {/*  w  ww  .  ja v  a  2 s . co  m*/
        log.warn("Skipping partition (" + partition + ") when syncing instant (" + instant
                + ") as it is not loaded");
    }
}

From source file:fr.ens.biologie.genomique.eoulsan.modules.mgmt.hadoop.DistCp.java

License:LGPL

/** Delete the dst files/dirs which do not exist in src */
static private void deleteNonexisting(final FileSystem dstfs, final FileStatus dstroot, final Path dstsorted,
        final FileSystem jobfs, final Path jobdir, final JobConf jobconf, final Configuration conf)
        throws IOException {
    if (!dstroot.isDir()) {
        throw new IOException("dst must be a directory when option " + Options.DELETE.cmd
                + " is set, but dst (= " + dstroot.getPath() + ") is not a directory.");
    }//from w  w  w  .j  a  v  a 2s  . c om

    // write dst lsr results
    final Path dstlsr = new Path(jobdir, "_distcp_dst_lsr");
    final SequenceFile.Writer writer = SequenceFile.createWriter(jobfs, jobconf, dstlsr, Text.class,
            dstroot.getClass(), SequenceFile.CompressionType.NONE);
    try {
        // do lsr to get all file statuses in dstroot
        final Stack<FileStatus> lsrstack = new Stack<>();
        for (lsrstack.push(dstroot); !lsrstack.isEmpty();) {
            final FileStatus status = lsrstack.pop();
            if (status.isDir()) {
                for (FileStatus child : dstfs.listStatus(status.getPath())) {
                    String relative = makeRelative(dstroot.getPath(), child.getPath());
                    writer.append(new Text(relative), child);
                    lsrstack.push(child);
                }
            }
        }
    } finally {
        checkAndClose(writer);
    }

    // sort lsr results
    final Path sortedlsr = new Path(jobdir, "_distcp_dst_lsr_sorted");
    SequenceFile.Sorter sorter = new SequenceFile.Sorter(jobfs, new Text.Comparator(), Text.class,
            FileStatus.class, jobconf);
    sorter.sort(dstlsr, sortedlsr);

    // compare lsr list and dst list
    SequenceFile.Reader lsrin = null;
    SequenceFile.Reader dstin = null;
    try {
        lsrin = new SequenceFile.Reader(jobfs, sortedlsr, jobconf);
        dstin = new SequenceFile.Reader(jobfs, dstsorted, jobconf);

        // compare sorted lsr list and sorted dst list
        final Text lsrpath = new Text();
        final FileStatus lsrstatus = new FileStatus();
        final Text dstpath = new Text();
        final Text dstfrom = new Text();
        final FsShell shell = new FsShell(conf);
        final String[] shellargs = { "-rmr", null };

        boolean hasnext = dstin.next(dstpath, dstfrom);
        for (; lsrin.next(lsrpath, lsrstatus);) {
            int dst_cmp_lsr = dstpath.compareTo(lsrpath);
            for (; hasnext && dst_cmp_lsr < 0;) {
                hasnext = dstin.next(dstpath, dstfrom);
                dst_cmp_lsr = dstpath.compareTo(lsrpath);
            }

            if (dst_cmp_lsr == 0) {
                // lsrpath exists in dst, skip it
                hasnext = dstin.next(dstpath, dstfrom);
            } else {
                // lsrpath does not exist, delete it
                String s = new Path(dstroot.getPath(), lsrpath.toString()).toString();
                if (shellargs[1] == null || !isAncestorPath(shellargs[1], s)) {
                    shellargs[1] = s;
                    int r = 0;
                    try {
                        r = shell.run(shellargs);
                    } catch (Exception e) {
                        throw new IOException("Exception from shell.", e);
                    }
                    if (r != 0) {
                        throw new IOException(
                                "\"" + shellargs[0] + " " + shellargs[1] + "\" returns non-zero value " + r);
                    }
                }
            }
        }
    } finally {
        checkAndClose(lsrin);
        checkAndClose(dstin);
    }
}

From source file:org.jd.copier.mapred.DistCp.java

License:Apache License

/** Delete the dst files/dirs which do not exist in src */
static private void deleteNonexisting(FileSystem dstfs, FileStatus dstroot, Path dstsorted, FileSystem jobfs,
        Path jobdir, JobConf jobconf, Configuration conf) throws IOException {
    if (!dstroot.isDir()) {
        throw new IOException("dst must be a directory when option " + Options.DELETE.cmd
                + " is set, but dst (= " + dstroot.getPath() + ") is not a directory.");
    }//from  ww  w.  j a v a2s  .com

    //write dst lsr results
    final Path dstlsr = new Path(jobdir, "_distcp_dst_lsr");
    final SequenceFile.Writer writer = SequenceFile.createWriter(jobfs, jobconf, dstlsr, Text.class,
            dstroot.getClass(), SequenceFile.CompressionType.NONE);
    try {
        //do lsr to get all file statuses in dstroot
        final Stack<FileStatus> lsrstack = new Stack<FileStatus>();
        for (lsrstack.push(dstroot); !lsrstack.isEmpty();) {
            final FileStatus status = lsrstack.pop();
            if (status.isDir()) {
                for (FileStatus child : dstfs.listStatus(status.getPath())) {
                    String relative = makeRelative(dstroot.getPath(), child.getPath());
                    writer.append(new Text(relative), child);
                    lsrstack.push(child);
                }
            }
        }
    } finally {
        checkAndClose(writer);
    }

    //sort lsr results
    final Path sortedlsr = new Path(jobdir, "_distcp_dst_lsr_sorted");
    SequenceFile.Sorter sorter = new SequenceFile.Sorter(jobfs, new Text.Comparator(), Text.class,
            FileStatus.class, jobconf);
    sorter.sort(dstlsr, sortedlsr);

    //compare lsr list and dst list  
    SequenceFile.Reader lsrin = null;
    SequenceFile.Reader dstin = null;
    try {
        lsrin = new SequenceFile.Reader(jobfs, sortedlsr, jobconf);
        dstin = new SequenceFile.Reader(jobfs, dstsorted, jobconf);

        //compare sorted lsr list and sorted dst list
        final Text lsrpath = new Text();
        final FileStatus lsrstatus = new FileStatus();
        final Text dstpath = new Text();
        final Text dstfrom = new Text();
        final FsShell shell = new FsShell(conf);
        final String[] shellargs = { "-rmr", null };

        boolean hasnext = dstin.next(dstpath, dstfrom);
        for (; lsrin.next(lsrpath, lsrstatus);) {
            int dst_cmp_lsr = dstpath.compareTo(lsrpath);
            for (; hasnext && dst_cmp_lsr < 0;) {
                hasnext = dstin.next(dstpath, dstfrom);
                dst_cmp_lsr = dstpath.compareTo(lsrpath);
            }

            if (dst_cmp_lsr == 0) {
                //lsrpath exists in dst, skip it
                hasnext = dstin.next(dstpath, dstfrom);
            } else {
                //lsrpath does not exist, delete it
                String s = new Path(dstroot.getPath(), lsrpath.toString()).toString();
                if (shellargs[1] == null || !isAncestorPath(shellargs[1], s)) {
                    shellargs[1] = s;
                    int r = 0;
                    try {
                        r = shell.run(shellargs);
                    } catch (Exception e) {
                        throw new IOException("Exception from shell.", e);
                    }
                    if (r != 0) {
                        throw new IOException(
                                "\"" + shellargs[0] + " " + shellargs[1] + "\" returns non-zero value " + r);
                    }
                }
            }
        }
    } finally {
        checkAndClose(lsrin);
        checkAndClose(dstin);
    }
}