Package org.apache.nutch.util

Examples of org.apache.nutch.util.NutchJob

52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
  private void indexSolr(String solrUrl, Path crawlDb, Path linkDb,
      List<Path> segments) throws IOException {
    LOG.info("SolrIndexer: starting");

    final JobConf job = new NutchJob(getConf());
    job.setJobName("index-solr " + solrUrl);

    IndexerMapReduce.initMRJob(crawlDb, linkDb, segments, job);

    job.set(SolrConstants.SERVER_URL, solrUrl);

    NutchIndexWriterFactory.addClassToConf(job, SolrWriter.class);

    job.setReduceSpeculativeExecution(false);

    final Path tmp = new Path("tmp_" + System.currentTimeMillis() + "-" +
                         new Random().nextInt());

    FileOutputFormat.setOutputPath(job, tmp);
View Full Code Here
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
  public void dedup(String solrUrl) throws IOException {
    LOG.info("SolrDeleteDuplicates: starting...");
    LOG.info("SolrDeleteDuplicates: Solr url: " + solrUrl);
   
    JobConf job = new NutchJob(getConf());

    job.set(SolrConstants.SERVER_URL, solrUrl);
    job.setInputFormat(SolrInputFormat.class);
    job.setOutputFormat(NullOutputFormat.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(SolrRecord.class);
    job.setMapperClass(IdentityMapper.class);
    job.setReducerClass(SolrDeleteDuplicates.class);

    JobClient.runJob(job);
   
    LOG.info("SolrDeleteDuplicates: done.");
  }
View Full Code Here
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
      LOG.info("CrawlDb db: " + crawlDb);
    }

    Path outFolder = new Path(output);

    JobConf job = new NutchJob(config);
    job.setJobName("dump " + crawlDb);

    FileInputFormat.addInputPath(job, new Path(crawlDb, CrawlDb.CURRENT_NAME));
    job.setInputFormat(SequenceFileInputFormat.class);
    FileOutputFormat.setOutputPath(job, outFolder);

    if (format.equals("csv")) {
      job.setOutputFormat(CrawlDatumCsvOutputFormat.class);
    }
    else if (format.equals("crawldb")) {
      job.setOutputFormat(MapFileOutputFormat.class);
    } else {
      job.setOutputFormat(TextOutputFormat.class);
    }

    if (status != null) job.set("status", status);
    if (regex != null) job.set("regex", regex);
    if (retry != null) job.setInt("retry", retry);
   
    job.setMapperClass(CrawlDbDumpMapper.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(CrawlDatum.class);

    JobClient.runJob(job);
    if (LOG.isInfoEnabled()) { LOG.info("CrawlDb dump: done"); }
  }
View Full Code Here
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
    Path tempDir =
      new Path(config.get("mapred.temp.dir", ".") +
               "/readdb-topN-temp-"+
               Integer.toString(new Random().nextInt(Integer.MAX_VALUE)));

    JobConf job = new NutchJob(config);
    job.setJobName("topN prepare " + crawlDb);
    FileInputFormat.addInputPath(job, new Path(crawlDb, CrawlDb.CURRENT_NAME));
    job.setInputFormat(SequenceFileInputFormat.class);
    job.setMapperClass(CrawlDbTopNMapper.class);
    job.setReducerClass(IdentityReducer.class);

    FileOutputFormat.setOutputPath(job, tempDir);
    job.setOutputFormat(SequenceFileOutputFormat.class);
    job.setOutputKeyClass(FloatWritable.class);
    job.setOutputValueClass(Text.class);

    // XXX hmmm, no setFloat() in the API ... :(
    job.setLong("db.reader.topn.min", Math.round(1000000.0 * min));
    JobClient.runJob(job);

    if (LOG.isInfoEnabled()) {
      LOG.info("CrawlDb topN: collecting topN scores.");
    }
    job = new NutchJob(config);
    job.setJobName("topN collect " + crawlDb);
    job.setLong("db.reader.topn", topN);

    FileInputFormat.addInputPath(job, tempDir);
    job.setInputFormat(SequenceFileInputFormat.class);
    job.setMapperClass(IdentityMapper.class);
    job.setReducerClass(CrawlDbTopNReducer.class);

    FileOutputFormat.setOutputPath(job, outFolder);
    job.setOutputFormat(TextOutputFormat.class);
    job.setOutputKeyClass(FloatWritable.class);
    job.setOutputValueClass(Text.class);

    job.setNumReduceTasks(1); // create a single file.

    JobClient.runJob(job);
    FileSystem fs = FileSystem.get(config);
    fs.delete(tempDir, true);
    if (LOG.isInfoEnabled()) { LOG.info("CrawlDb topN: done"); }
View Full Code Here
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
    // map text input file to a <url,CrawlDatum> file
    if (LOG.isInfoEnabled()) {
      LOG.info("Injector: Converting injected urls to crawl db entries.");
    }
    JobConf sortJob = new NutchJob(getConf());
    sortJob.setJobName("inject " + urlDir);
    FileInputFormat.addInputPath(sortJob, urlDir);
    sortJob.setMapperClass(InjectMapper.class);

    FileOutputFormat.setOutputPath(sortJob, tempDir);
    sortJob.setOutputFormat(SequenceFileOutputFormat.class);
    sortJob.setOutputKeyClass(Text.class);
    sortJob.setOutputValueClass(CrawlDatum.class);
    sortJob.setLong("injector.current.time", System.currentTimeMillis());
    RunningJob mapJob = JobClient.runJob(sortJob);

    long urlsInjected = mapJob.getCounters().findCounter("injector", "urls_injected").getValue();
    long urlsFiltered = mapJob.getCounters().findCounter("injector", "urls_filtered").getValue();
    LOG.info("Injector: total number of urls rejected by filters: " + urlsFiltered);
View Full Code Here
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
      LOG.info("CrawlDb statistics start: " + crawlDb);
    }

    Path tmpFolder = new Path(crawlDb, "stat_tmp" + System.currentTimeMillis());

    JobConf job = new NutchJob(config);
    job.setJobName("stats " + crawlDb);
    job.setBoolean("db.reader.stats.sort", sort);

    FileInputFormat.addInputPath(job, new Path(crawlDb, CrawlDb.CURRENT_NAME));
    job.setInputFormat(SequenceFileInputFormat.class);

    job.setMapperClass(CrawlDbStatMapper.class);
    job.setCombinerClass(CrawlDbStatCombiner.class);
    job.setReducerClass(CrawlDbStatReducer.class);

    FileOutputFormat.setOutputPath(job, tmpFolder);
    job.setOutputFormat(SequenceFileOutputFormat.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(LongWritable.class);

    // https://issues.apache.org/jira/browse/NUTCH-1029
    job.setBoolean("mapreduce.fileoutputcommitter.marksuccessfuljobs", false);

    JobClient.runJob(job);

    // reading the result
    FileSystem fileSystem = FileSystem.get(config);
View Full Code Here
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
    Path outDir1 =
      new Path("dedup-urls-"+
               Integer.toString(new Random().nextInt(Integer.MAX_VALUE)));

    JobConf job = new NutchJob(getConf());

    for (int i = 0; i < indexDirs.length; i++) {
      if (LOG.isInfoEnabled()) {
        LOG.info("Dedup: adding indexes in: " + indexDirs[i]);
      }
      FileInputFormat.addInputPath(job, indexDirs[i]);
    }
    job.setJobName("dedup 1: urls by time");

    job.setInputFormat(InputFormat.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IndexDoc.class);

    job.setReducerClass(UrlsReducer.class);
    FileOutputFormat.setOutputPath(job, outDir1);

    job.setOutputKeyClass(MD5Hash.class);
    job.setOutputValueClass(IndexDoc.class);
    job.setOutputFormat(SequenceFileOutputFormat.class);

    JobClient.runJob(job);

    Path outDir2 =
      new Path("dedup-hash-"+
               Integer.toString(new Random().nextInt(Integer.MAX_VALUE)));
    job = new NutchJob(getConf());
    job.setJobName("dedup 2: content by hash");

    FileInputFormat.addInputPath(job, outDir1);
    job.setInputFormat(SequenceFileInputFormat.class);
    job.setMapOutputKeyClass(MD5Hash.class);
    job.setMapOutputValueClass(IndexDoc.class);
    job.setPartitionerClass(HashPartitioner.class);
    job.setSpeculativeExecution(false);
   
    job.setReducerClass(HashReducer.class);
    FileOutputFormat.setOutputPath(job, outDir2);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IndexDoc.class);
    job.setOutputFormat(SequenceFileOutputFormat.class);

    JobClient.runJob(job);

    // remove outDir1 - no longer needed
    fs.delete(outDir1, true);
   
    job = new NutchJob(getConf());
    job.setJobName("dedup 3: delete from index(es)");

    FileInputFormat.addInputPath(job, outDir2);
    job.setInputFormat(SequenceFileInputFormat.class);
    //job.setInputKeyClass(Text.class);
    //job.setInputValueClass(IndexDoc.class);

    job.setInt("io.file.buffer.size", 4096);
    job.setMapperClass(DeleteDuplicates.class);
    job.setReducerClass(DeleteDuplicates.class);

    job.setOutputFormat(DeleteDuplicates.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);

    JobClient.runJob(job);

    fs.delete(outDir2, true);
View Full Code Here
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
    Path outlinkDb = new Path(webGraphDb, WebGraph.OUTLINK_DIR);

    // run the inverter job
    Path tempInverted = new Path(webGraphDb, "inverted-"
      + Integer.toString(new Random().nextInt(Integer.MAX_VALUE)));
    JobConf inverter = new NutchJob(conf);
    inverter.setJobName("LinkDumper: inverter");
    FileInputFormat.addInputPath(inverter, nodeDb);
    if (loopsExists) {
      FileInputFormat.addInputPath(inverter, loopSetDb);
    }
    FileInputFormat.addInputPath(inverter, outlinkDb);
    inverter.setInputFormat(SequenceFileInputFormat.class);
    inverter.setMapperClass(Inverter.class);
    inverter.setReducerClass(Inverter.class);
    inverter.setMapOutputKeyClass(Text.class);
    inverter.setMapOutputValueClass(ObjectWritable.class);
    inverter.setOutputKeyClass(Text.class);
    inverter.setOutputValueClass(LinkNode.class);
    FileOutputFormat.setOutputPath(inverter, tempInverted);
    inverter.setOutputFormat(SequenceFileOutputFormat.class);

    try {
      LOG.info("LinkDumper: running inverter");
      JobClient.runJob(inverter);
      LOG.info("LinkDumper: finished inverter");
    }
    catch (IOException e) {
      LOG.error(StringUtils.stringifyException(e));
      throw e;
    }

    // run the merger job
    JobConf merger = new NutchJob(conf);
    merger.setJobName("LinkDumper: merger");
    FileInputFormat.addInputPath(merger, tempInverted);
    merger.setInputFormat(SequenceFileInputFormat.class);
    merger.setReducerClass(Merger.class);
    merger.setMapOutputKeyClass(Text.class);
    merger.setMapOutputValueClass(LinkNode.class);
    merger.setOutputKeyClass(Text.class);
    merger.setOutputValueClass(LinkNodes.class);
    FileOutputFormat.setOutputPath(merger, linkdump);
    merger.setOutputFormat(MapFileOutputFormat.class);

    try {
      LOG.info("LinkDumper: running merger");
      JobClient.runJob(merger);
      LOG.info("LinkDumper: finished merger");
View Full Code Here
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
          return -1;
        }
      }
    }
   
    JobConf job = new NutchJob(getConf());
    job.setBoolean(FILTER_KEY, filter);
    job.setBoolean(NORMALIZE_KEY, normalize);
    FileInputFormat.addInputPath(job, new Path(args[0]));
    job.setInputFormat(TextInputFormat.class);
    job.setMapperClass(FG.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(Generator.SelectorEntry.class);
    job.setPartitionerClass(URLPartitioner.class);
    job.setReducerClass(FG.class);
    String segName = Generator.generateSegmentName();
    job.setNumReduceTasks(job.getNumMapTasks());
    job.setOutputFormat(SequenceFileOutputFormat.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(CrawlDatum.class);
    job.setOutputKeyComparatorClass(Generator.HashComparator.class);
    FileOutputFormat.setOutputPath(job, new Path(args[1],
        new Path(segName, CrawlDatum.GENERATE_DIR_NAME)));
    try {
      JobClient.runJob(job);
      return 0;
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
  public void indexSolr(String solrUrl, Path crawlDb, Path linkDb,
      List<Path> segments) throws IOException {
    LOG.info("SolrIndexer: starting");

    final JobConf job = new NutchJob(getConf());
    job.setJobName("index-solr " + solrUrl);

    IndexerMapReduce.initMRJob(crawlDb, linkDb, segments, job);

    job.set(SolrConstants.SERVER_URL, solrUrl);

    NutchIndexWriterFactory.addClassToConf(job, SolrWriter.class);

    job.setReduceSpeculativeExecution(false);

    final Path tmp = new Path("tmp_" + System.currentTimeMillis() + "-" +
                         new Random().nextInt());

    FileOutputFormat.setOutputPath(job, tmp);
View Full Code Here
TOP

Related Classes of org.apache.nutch.util.NutchJob

  • com.flaptor.hounder.crawler.Nutch9Fetcher
  • org.apache.nutch.crawl.Crawl
  • org.apache.nutch.crawl.CrawlDb
  • org.apache.nutch.crawl.CrawlDbMerger
  • org.apache.nutch.crawl.CrawlDbReader
  • org.apache.nutch.crawl.DbUpdaterJob
  • org.apache.nutch.crawl.DeduplicationJob
  • org.apache.nutch.crawl.Generator
  • org.apache.nutch.crawl.GeneratorJob
  • org.apache.nutch.crawl.Injector
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.