List of usage examples for org.apache.hadoop.mapred JobConf getBoolean
public boolean getBoolean(String name, boolean defaultValue)
name
property as a boolean
. From source file:com.intel.hadoop.graphbuilder.preprocess.mapreduce.CreateGraphReducer.java
License:Open Source License
@Override public void configure(JobConf job) { super.configure(job); this.valClass = job.getMapOutputValueClass(); this.noBidir = job.getBoolean("noBidir", false); try {/*from w ww. j a v a 2 s. c o m*/ if (job.get("EdgeFunc") != null) { this.EdgeFunc = (Functional) Class.forName(job.get("EdgeFunc")).newInstance(); this.EdgeFunc.configure(job); } if (job.get("VertexFunc") != null) { this.VertexFunc = (Functional) Class.forName(job.get("VertexFunc")).newInstance(); this.VertexFunc.configure(job); } } catch (InstantiationException e) { e.printStackTrace(); } catch (IllegalAccessException e) { e.printStackTrace(); } catch (ClassNotFoundException e) { e.printStackTrace(); } catch (Exception e) { e.printStackTrace(); } }
From source file:com.intel.hadoop.graphbuilder.preprocess.mapreduce.EdgeTransformMapper.java
License:Open Source License
@Override public void configure(JobConf job) { super.configure(job); this.reduceEndPoint = job.getBoolean("reduceEndPoint", EdgeTransformMR.SOURCE); try {/*from ww w .j a va 2 s. c om*/ this.graphparser = (GraphParser) Class.forName(job.get("GraphParser")).newInstance(); this.vidparser = (FieldParser) Class.forName(job.get("VidParser")).newInstance(); this.edataparser = (FieldParser) Class.forName(job.get("EdataParser")).newInstance(); this.valClass = job.getMapOutputValueClass(); val = (PairListType) valClass.newInstance(); } catch (InstantiationException e) { e.printStackTrace(); } catch (IllegalAccessException e) { e.printStackTrace(); } catch (ClassNotFoundException e) { e.printStackTrace(); } }
From source file:com.intel.hadoop.graphbuilder.preprocess.mapreduce.EdgeTransformReducer.java
License:Open Source License
@Override public void configure(JobConf job) { super.configure(job); this.reduceEndPoint = job.getBoolean("reduceEndPoint", EdgeTransformMR.SOURCE); try {/*from w w w . j a v a 2 s . c om*/ this.reduceFunc = (Functional) Class.forName(job.get("ReduceFunc")).newInstance(); this.applyFunc = (Functional) Class.forName(job.get("ApplyFunc")).newInstance(); this.reduceFunc.configure(job); this.applyFunc.configure(job); } catch (InstantiationException e) { e.printStackTrace(); } catch (IllegalAccessException e) { e.printStackTrace(); } catch (ClassNotFoundException e) { e.printStackTrace(); } catch (Exception e) { e.printStackTrace(); } }
From source file:com.ricemap.spateDB.mapred.GridOutputFormat.java
License:Apache License
@Override public RecordWriter<IntWritable, S> getRecordWriter(FileSystem ignored, JobConf job, String name, Progressable progress) throws IOException { // Get grid info CellInfo[] cellsInfo = SpatialSite.getCells(job); boolean pack = job.getBoolean(SpatialSite.PACK_CELLS, false); boolean expand = job.getBoolean(SpatialSite.EXPAND_CELLS, false); GridRecordWriter<S> writer = new GridRecordWriter<S>(job, name, cellsInfo, pack, expand); return writer; }
From source file:com.ricemap.spateDB.mapred.GridOutputFormat2.java
License:Apache License
@Override public RecordWriter<NullWritable, S> getRecordWriter(FileSystem ignored, JobConf job, String name, Progressable progress) throws IOException { // Get grid info CellInfo[] cellsInfo = SpatialSite.getCells(job); boolean pack = job.getBoolean(SpatialSite.PACK_CELLS, false); boolean expand = job.getBoolean(SpatialSite.EXPAND_CELLS, false); GridRecordWriter2<S> writer = new GridRecordWriter2<S>(job, name, cellsInfo, pack, expand); return writer; }
From source file:com.ricemap.spateDB.mapred.RTreeGridOutputFormat.java
License:Apache License
@Override public RecordWriter<IntWritable, S> getRecordWriter(FileSystem ignored, JobConf job, String name, Progressable progress) throws IOException { // Get grid info CellInfo[] cellsInfo = SpatialSite.getCells(job); boolean pack = job.getBoolean(SpatialSite.PACK_CELLS, false); boolean expand = job.getBoolean(SpatialSite.EXPAND_CELLS, false); RTreeGridRecordWriter<S> writer = new RTreeGridRecordWriter<S>(job, name, cellsInfo, pack, expand); writer.setStockObject((S) SpatialSite.createStockShape(job)); return writer; }
From source file:com.taobao.data.hive.hook.automapjoin.AutoMapJoinPreJobHook.java
License:Apache License
@Override public void run(SessionState session, QueryPlan queryPlan, JobConf job, Integer taskId) { if (!job.getBoolean(HiveConf.ConfVars.HIVECONVERTJOIN.varname, false) || null == job.get(AUTO_JOIN_STATICS_DIR) || null == queryPlan) { return;/* w w w .j ava 2 s . co m*/ } List<Task<? extends Serializable>> rootTasks = queryPlan.getRootTasks(); String taskIdStr = "Stage-" + taskId.toString(); dfsTaskTag(rootTasks, taskIdStr); // dfs, fill the member variable 'taskTag' StringBuilder sb = new StringBuilder(); sb.append(queryPlan.getQueryId()); sb.append('\u0001'); sb.append(taskIdStr); sb.append('\u0001'); switch (taskTag) { case Task.NO_TAG: return; case Task.BACKUP_COMMON_JOIN: sb.append("Backup Common Join"); break; case Task.COMMON_JOIN: sb.append("Common Join"); break; case Task.CONVERTED_LOCAL_MAPJOIN: sb.append("Converted Local Map Join"); break; case Task.CONVERTED_MAPJOIN: sb.append("Converted Map Join"); break; case Task.LOCAL_MAPJOIN: sb.append("Local Map Join"); break; } String sessionId = session.getSessionId(); File dir = new File(job.get(AUTO_JOIN_STATICS_DIR)); if (!dir.exists()) { dir.mkdir(); } File file = new File(dir, sessionId + ".stat"); synchronized (lock) { FileOutputStream fout = null; PrintStream pout = null; try { if (!file.exists()) { file.createNewFile(); } fout = new FileOutputStream(file, true); pout = new PrintStream(fout); pout.println(sb.toString()); } catch (FileNotFoundException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } finally { if (null != pout) { pout.close(); } } } // reset dfs results taskTag = Task.NO_TAG; found = false; }
From source file:com.TCG.Nutch_DNS.Generator.java
License:Apache License
public Path[] generate(Path dbDir, Path segments, int numLists, long topN, long curTime) throws IOException { JobConf job = new NutchJob(getConf()); boolean filter = job.getBoolean(GENERATOR_FILTER, true); boolean normalise = job.getBoolean(GENERATOR_NORMALISE, true); return generate(dbDir, segments, numLists, topN, curTime, filter, normalise, false, 1); }
From source file:com.TCG.Nutch_DNS.HostDb.java
License:Apache License
public void update(Path crawlDb, Path[] segments, boolean normalize, boolean filter, boolean additionsAllowed, boolean force) throws IOException { FileSystem fs = FileSystem.get(getConf()); Path lock = new Path(crawlDb, LOCK_NAME); LockUtil.createLockFile(fs, lock, force); SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss"); long start = System.currentTimeMillis(); JobConf job = HostDb.createJob(getConf(), crawlDb); job.setBoolean(CRAWLDB_ADDITIONS_ALLOWED, additionsAllowed); job.setBoolean(HostDbFilter.URL_FILTERING, filter); job.setBoolean(HostDbFilter.URL_NORMALIZING, normalize); boolean url404Purging = job.getBoolean(CRAWLDB_PURGE_404, false); if (LOG.isInfoEnabled()) { LOG.info("CrawlDb update: starting at " + sdf.format(start)); LOG.info("CrawlDb update: db: " + crawlDb); LOG.info("CrawlDb update: segments: " + Arrays.asList(segments)); LOG.info("CrawlDb update: additions allowed: " + additionsAllowed); LOG.info("CrawlDb update: URL normalizing: " + normalize); LOG.info("CrawlDb update: URL filtering: " + filter); LOG.info("CrawlDb update: 404 purging: " + url404Purging); }/*from w ww .j av a2s . c o m*/ for (int i = 0; i < segments.length; i++) { Path fetch = new Path(segments[i], CrawlDatum.FETCH_DIR_NAME); Path parse = new Path(segments[i], CrawlDatum.PARSE_DIR_NAME); if (fs.exists(fetch) && fs.exists(parse)) { FileInputFormat.addInputPath(job, fetch); FileInputFormat.addInputPath(job, parse); } else { LOG.info(" - skipping invalid segment " + segments[i]); } } if (LOG.isInfoEnabled()) { LOG.info("CrawlDb update: Merging segment data into db."); } try { JobClient.runJob(job); } catch (IOException e) { LockUtil.removeLockFile(fs, lock); Path outPath = FileOutputFormat.getOutputPath(job); if (fs.exists(outPath)) fs.delete(outPath, true); throw e; } HostDb.install(job, crawlDb); long end = System.currentTimeMillis(); LOG.info("CrawlDb update: finished at " + sdf.format(end) + ", elapsed: " + TimingUtil.elapsedTime(start, end)); }
From source file:com.TCG.Nutch_DNS.HostDb.java
License:Apache License
public static void install(JobConf job, Path crawlDb) throws IOException { boolean preserveBackup = job.getBoolean("db.preserve.backup", true); Path newCrawlDb = FileOutputFormat.getOutputPath(job); FileSystem fs = new JobClient(job).getFs(); Path old = new Path(crawlDb, "old"); Path current = new Path(crawlDb, CURRENT_NAME); if (fs.exists(current)) { if (fs.exists(old)) fs.delete(old, true);// www . ja v a 2s . c o m fs.rename(current, old); } fs.mkdirs(crawlDb); fs.rename(newCrawlDb, current); if (!preserveBackup && fs.exists(old)) fs.delete(old, true); Path lock = new Path(crawlDb, LOCK_NAME); LockUtil.removeLockFile(fs, lock); }