List of usage examples for org.apache.hadoop.fs Path toString
@Override
public String toString()
From source file:boa.functions.BoaAstIntrinsics.java
License:Apache License
private static void openCommentMap() { final Configuration conf = new Configuration(); try {/*from w w w . ja v a2s. c om*/ final FileSystem fs = FileSystem.get(conf); final Path p = new Path("hdfs://boa-njt/", new Path( context.getConfiguration().get("boa.comments.dir", context.getConfiguration().get("boa.input.dir", "repcache/live")), new Path("comments"))); commentsMap = new MapFile.Reader(fs, p.toString(), conf); } catch (final Exception e) { e.printStackTrace(); } }
From source file:boa.functions.BoaAstIntrinsics.java
License:Apache License
private static void openIssuesMap() { final Configuration conf = new Configuration(); try {/*from w w w . j a v a 2 s. co m*/ final FileSystem fs = FileSystem.get(conf); final Path p = new Path("hdfs://boa-njt/", new Path( context.getConfiguration().get("boa.issues.dir", context.getConfiguration().get("boa.input.dir", "repcache/live")), new Path("issues"))); issuesMap = new MapFile.Reader(fs, p.toString(), conf); } catch (final Exception e) { e.printStackTrace(); } }
From source file:ca.uwaterloo.iss4e.hadoop.io.CartesianInputFormat.java
License:Open Source License
private List<InputSplit> getInputSplits(JobContext jobContext, String inputFormatClass, Path path) throws ClassNotFoundException, IOException { Configuration conf = jobContext.getConfiguration(); FileInputFormat inputFormat = (FileInputFormat) ReflectionUtils.newInstance(Class.forName(inputFormatClass), conf);/*from w ww . j ava2 s .c o m*/ // Set the input path for the left data set path = path.getFileSystem(conf).makeQualified(path); String dirStr = StringUtils.escapeString(path.toString()); String dirs = conf.get(INPUT_DIR); conf.set(INPUT_DIR, dirStr); return inputFormat.getSplits(jobContext); }
From source file:ca.uwaterloo.iss4e.spark.pointperrow.CosineMain.java
License:Open Source License
public void readFiles(JavaSparkContext sc, FileSystem fs, FileStatus[] files) { for (int i = 0; i < files.length; i++) { if (files[i].isDirectory()) { try { readFiles(sc, fs, fs.listStatus(files[i].getPath())); } catch (IOException e) { e.printStackTrace();// w ww. jav a 2s . co m } } else { if (lines == null) { Path p = files[i].getPath(); lines = sc.textFile(p.toString()); } else { JavaRDD<String> r = sc.textFile(files[i].getPath().toString()); lines.union(r); } } } }
From source file:cascading.flow.hadoop.MapReduceFlow.java
License:Open Source License
protected Map<String, Tap> createSources(JobConf jobConf) { Path[] paths = FileInputFormat.getInputPaths(jobConf); if (paths.length == 0) { try {//from ww w . ja v a 2s . c om paths = org.apache.hadoop.mapreduce.lib.input.FileInputFormat.getInputPaths(new Job(jobConf)); } catch (IOException exception) { throw new CascadingException(exception); } } Map<String, Tap> taps = new HashMap<String, Tap>(); for (Path path : paths) taps.put(path.toString(), new Hfs(new NullScheme(), path.toString())); return taps; }
From source file:cascading.flow.hadoop.MapReduceFlow.java
License:Open Source License
protected Map<String, Tap> createSinks(JobConf jobConf) { Map<String, Tap> taps = new HashMap<String, Tap>(); Path path = FileOutputFormat.getOutputPath(jobConf); if (path == null) { try {//w ww.j a va2 s. c om path = org.apache.hadoop.mapreduce.lib.output.FileOutputFormat.getOutputPath(new Job(jobConf)); } catch (IOException exception) { throw new CascadingException(exception); } } taps.put(path.toString(), new Hfs(new NullScheme(), path.toString(), deleteSinkOnInit ? SinkMode.REPLACE : SinkMode.KEEP)); return taps; }
From source file:cascading.flow.hadoop.util.HadoopMRUtil.java
License:Open Source License
public static String readStateFromDistCache(JobConf jobConf, String id, String kind) throws IOException { Path[] files = DistributedCache.getLocalCacheFiles(jobConf); Path stepStatePath = null;/*from w ww .j a v a 2 s .co m*/ for (Path file : files) { if (!file.toString().contains(kind + "-state-" + id)) continue; stepStatePath = file; break; } if (stepStatePath == null) throw new FlowException("unable to find step state from distributed cache"); LOG.info("reading step state from local path: {}", stepStatePath); Hfs temp = new Lfs(new TextLine(new Fields("line")), stepStatePath.toString()); TupleEntryIterator reader = null; try { reader = temp.openForRead(new HadoopFlowProcess(jobConf)); if (!reader.hasNext()) throw new FlowException("step state path is empty: " + temp.getIdentifier()); return reader.next().getString(0); } catch (IOException exception) { throw new FlowException("unable to find state path: " + temp.getIdentifier(), exception); } finally { try { if (reader != null) reader.close(); } catch (IOException exception) { LOG.warn("error closing state path reader", exception); } } }
From source file:cascading.flow.hadoop.util.HadoopUtil.java
License:Open Source License
public static void addInputPath(Configuration conf, Path path) { Path workingDirectory = getWorkingDirectory(conf); path = new Path(workingDirectory, path); String dirStr = StringUtils.escapeString(path.toString()); String dirs = conf.get("mapred.input.dir"); conf.set("mapred.input.dir", dirs == null ? dirStr : dirs + StringUtils.COMMA_STR + dirStr); }
From source file:cascading.flow.hadoop.util.HadoopUtil.java
License:Open Source License
public static void setOutputPath(Configuration conf, Path path) { Path workingDirectory = getWorkingDirectory(conf); path = new Path(workingDirectory, path); conf.set("mapred.output.dir", path.toString()); }
From source file:cascading.flow.hadoop.util.HadoopUtil.java
License:Open Source License
private static Path getWorkingDirectory(Configuration conf) { String name = conf.get("mapred.working.dir"); if (name != null) { return new Path(name); } else {/*from w w w . j a v a 2 s. c om*/ try { Path dir = FileSystem.get(conf).getWorkingDirectory(); conf.set("mapred.working.dir", dir.toString()); return dir; } catch (IOException e) { throw new RuntimeException(e); } } }