/** For debugging. */
public static void main(String[] args) throws Exception {
final String usage = "NutchBean query";
if (args.length == 0) {
System.err.println(usage);
System.exit(-1);
}
final Configuration conf = NutchConfiguration.create();
final NutchBean bean = new NutchBean(conf);
try {
final Query query = Query.parse(args[0], conf);
final Hits hits = bean.search(query, 10);
System.out.println("Total hits: " + hits.getTotal());
final int length = (int) Math.min(hits.getTotal(), 10);
final Hit[] show = hits.getHits(0, length);
final HitDetails[] details = bean.getDetails(show);
final Summary[] summaries = bean.getSummary(details, query);
for (int i = 0; i < hits.getLength(); i++) {
System.out.println(" " + i + " " + details[i] + "\n" + summaries[i]);
}
} catch (Throwable t) {
LOG.error("Exception occured while executing search: " + t, t);
System.exit(1);
}
System.exit(0);
}
private static void addFolder(FileSystem fs, Path p, JsonArray succeeded, JsonArray failed) {
try {
if (fs == null) return;
for (FileStatus file : fs.listStatus(p)) {
Path pfs = file.getPath();
if (file.isDir()) {
addFolder(fs, pfs, succeeded, failed);
} else {
Key k = Key.make(pfs.toString());
long size = file.getLen();
Value val = null;
if (pfs.getName().endsWith(Extensions.JSON)) {
JsonParser parser = new JsonParser();
JsonObject json = parser.parse(new InputStreamReader(fs.open(pfs))).getAsJsonObject();
JsonElement v = json.get(Constants.VERSION);
if (v == null) throw new RuntimeException("Missing version");
JsonElement type = json.get(Constants.TYPE);
if (type == null) throw new RuntimeException("Missing type");
Class c = Class.forName(type.getAsString());
OldModel model = (OldModel) c.newInstance();
model.fromJson(json);
} else if (pfs.getName().endsWith(Extensions.HEX)) { // Hex file?
FSDataInputStream s = fs.open(pfs);
int sz = (int) Math.min(1L << 20, size); // Read up to the 1st meg
byte[] mem = MemoryManager.malloc1(sz);
s.readFully(mem);
// Convert to a ValueArray (hope it fits in 1Meg!)
ValueArray ary = new ValueArray(k, 0).read(new AutoBuffer(mem));
val = new Value(k, ary, Value.HDFS);
} else if (size >= 2 * ValueArray.CHUNK_SZ) {
val =
new Value(
k,
new ValueArray(k, size),
Value.HDFS); // ValueArray byte wrapper over a large file
} else {
val = new Value(k, (int) size, Value.HDFS); // Plain Value
val.setdsk();
}
DKV.put(k, val);
Log.info("PersistHdfs: DKV.put(" + k + ")");
JsonObject o = new JsonObject();
o.addProperty(Constants.KEY, k.toString());
o.addProperty(Constants.FILE, pfs.toString());
o.addProperty(Constants.VALUE_SIZE, file.getLen());
succeeded.add(o);
}
}
} catch (Exception e) {
Log.err(e);
JsonObject o = new JsonObject();
o.addProperty(Constants.FILE, p.toString());
o.addProperty(Constants.ERROR, e.getMessage());
failed.add(o);
}
}
/**
* Calculate how many maps to run. Number of maps is bounded by a minimum of the cumulative size
* of the copy / (distcp.bytes.per.map, default BYTES_PER_MAP or -m on the command line) and at
* most (distcp.max.map.tasks, default MAX_MAPS_PER_NODE * nodes in the cluster).
*
* @param totalBytes Count of total bytes for job
* @param job The job to configure
* @return Count of maps to run.
*/
private static void setMapCount(long totalBytes, JobConf job) throws IOException {
int numMaps = (int) (totalBytes / job.getLong(BYTES_PER_MAP_LABEL, BYTES_PER_MAP));
numMaps =
Math.min(
numMaps,
job.getInt(
MAX_MAPS_LABEL,
MAX_MAPS_PER_NODE * new JobClient(job).getClusterStatus().getTaskTrackers()));
job.setNumMapTasks(Math.max(numMaps, 1));
}
/**
* Generate the list of files and make them into FileSplits. This needs to be copied to insert a
* filter on acceptable data
*/
@Override
public List<InputSplit> getSplits(JobContext job) throws IOException {
long minSize = Math.max(getFormatMinSplitSize(), getMinSplitSize(job));
long maxSize = getMaxSplitSize(job);
long desiredMappers =
job.getConfiguration().getLong("org.systemsbiology.jxtandem.DesiredXMLInputMappers", 0);
// generate splits
List<InputSplit> splits = new ArrayList<InputSplit>();
List<FileStatus> fileStatuses = listStatus(job);
boolean forceNumberMappers = fileStatuses.size() == 1;
for (FileStatus file : fileStatuses) {
Path path = file.getPath();
if (!isPathAcceptable(path)) // filter acceptable data
continue;
FileSystem fs = path.getFileSystem(job.getConfiguration());
long length = file.getLen();
BlockLocation[] blkLocations = fs.getFileBlockLocations(file, 0, length);
if ((length != 0) && isSplitable(job, path)) {
long blockSize = file.getBlockSize();
// use desired mappers to force more splits
if (forceNumberMappers && desiredMappers > 0)
maxSize = Math.min(maxSize, (length / desiredMappers));
long splitSize = computeSplitSize(blockSize, minSize, maxSize);
long bytesRemaining = length;
while (withinSlop(splitSize, bytesRemaining)) {
int blkIndex = getBlockIndex(blkLocations, length - bytesRemaining);
splits.add(
new FileSplit(
path, length - bytesRemaining, splitSize, blkLocations[blkIndex].getHosts()));
bytesRemaining -= splitSize;
}
if (bytesRemaining != 0) {
splits.add(
new FileSplit(
path,
length - bytesRemaining,
bytesRemaining,
blkLocations[blkLocations.length - 1].getHosts()));
}
} else if (length != 0) {
splits.add(new FileSplit(path, 0, length, blkLocations[0].getHosts()));
} else {
// Create empty hosts array for zero length files
splits.add(new FileSplit(path, 0, length, new String[0]));
}
}
System.out.println("Total # of splits: " + splits.size());
// LOG.debug("Total # of splits: " + splits.size());
return splits;
}
/**
* A tracker wants to know if there's a Task to run. Returns a task we'd like the TaskTracker to
* execute right now.
*
* <p>Eventually this function should compute load on the various TaskTrackers, and incorporate
* knowledge of DFS file placement. But for right now, it just grabs a single item out of the
* pending task list and hands it back.
*/
public synchronized Task pollForNewTask(String taskTracker) {
//
// Compute average map and reduce task numbers across pool
//
int avgMaps = 0;
int avgReduces = 0;
int numTaskTrackers;
TaskTrackerStatus tts;
synchronized (taskTrackers) {
numTaskTrackers = taskTrackers.size();
tts = (TaskTrackerStatus) taskTrackers.get(taskTracker);
}
if (numTaskTrackers > 0) {
avgMaps = totalMaps / numTaskTrackers;
avgReduces = totalReduces / numTaskTrackers;
}
int totalCapacity = numTaskTrackers * maxCurrentTasks;
//
// Get map + reduce counts for the current tracker.
//
if (tts == null) {
LOG.warning("Unknown task tracker polling; ignoring: " + taskTracker);
return null;
}
int numMaps = tts.countMapTasks();
int numReduces = tts.countReduceTasks();
//
// In the below steps, we allocate first a map task (if appropriate),
// and then a reduce task if appropriate. We go through all jobs
// in order of job arrival; jobs only get serviced if their
// predecessors are serviced, too.
//
//
// We hand a task to the current taskTracker if the given machine
// has a workload that's equal to or less than the averageMaps
// +/- TASK_ALLOC_EPSILON. (That epsilon is in place in case
// there is an odd machine that is failing for some reason but
// has not yet been removed from the pool, making capacity seem
// larger than it really is.)
//
synchronized (jobsByArrival) {
if ((numMaps < maxCurrentTasks) && (numMaps <= (avgMaps + TASK_ALLOC_EPSILON))) {
int totalNeededMaps = 0;
for (Iterator it = jobsByArrival.iterator(); it.hasNext(); ) {
JobInProgress job = (JobInProgress) it.next();
if (job.getStatus().getRunState() != JobStatus.RUNNING) {
continue;
}
Task t = job.obtainNewMapTask(taskTracker, tts);
if (t != null) {
return t;
}
//
// Beyond the highest-priority task, reserve a little
// room for failures and speculative executions; don't
// schedule tasks to the hilt.
//
totalNeededMaps += job.desiredMaps();
double padding = 0;
if (totalCapacity > MIN_SLOTS_FOR_PADDING) {
padding = Math.min(maxCurrentTasks, totalNeededMaps * PAD_FRACTION);
}
if (totalNeededMaps + padding >= totalCapacity) {
break;
}
}
}
//
// Same thing, but for reduce tasks
//
if ((numReduces < maxCurrentTasks) && (numReduces <= (avgReduces + TASK_ALLOC_EPSILON))) {
int totalNeededReduces = 0;
for (Iterator it = jobsByArrival.iterator(); it.hasNext(); ) {
JobInProgress job = (JobInProgress) it.next();
if (job.getStatus().getRunState() != JobStatus.RUNNING) {
continue;
}
Task t = job.obtainNewReduceTask(taskTracker, tts);
if (t != null) {
return t;
}
//
// Beyond the highest-priority task, reserve a little
// room for failures and speculative executions; don't
// schedule tasks to the hilt.
//
totalNeededReduces += job.desiredReduces();
double padding = 0;
if (totalCapacity > MIN_SLOTS_FOR_PADDING) {
padding = Math.min(maxCurrentTasks, totalNeededReduces * PAD_FRACTION);
}
if (totalNeededReduces + padding >= totalCapacity) {
break;
}
}
}
}
return null;
}