Package org.apache.nutch.util

Examples of org.apache.nutch.util.NutchJob

238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
      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.addInputPath(new Path(crawlDb, CrawlDb.CURRENT_NAME));
    job.setInputFormat(SequenceFileInputFormat.class);

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

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

    JobClient.runJob(job);

    // reading the result
    FileSystem fileSystem = FileSystem.get(config);
View Full Code Here
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
      LOG.info("CrawlDb db: " + crawlDb);
    }
   
    Path outFolder = new Path(output);

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

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

    job.setOutputPath(outFolder);
    job.setOutputFormat(TextOutputFormat.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(CrawlDatum.class);

    JobClient.runJob(job);
    if (LOG.isInfoEnabled()) { LOG.info("CrawlDb dump: done"); }
  }
View Full Code Here
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
406
407
408
409
410
411
    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);
    job.addInputPath(new Path(crawlDb, CrawlDb.CURRENT_NAME));
    job.setInputFormat(SequenceFileInputFormat.class);
    job.setMapperClass(CrawlDbTopNMapper.class);
    job.setReducerClass(IdentityReducer.class);

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

    // XXX hmmm, no setFloat() in the API ... :(
    job.setLong("CrawlDbReader.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("CrawlDbReader.topN", topN);

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

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

    // XXX *sigh* this apparently doesn't work ... :-((
    job.setNumReduceTasks(1); // create a single file.
   
    JobClient.runJob(job);
    FileSystem fs = FileSystem.get(config);
    fs.delete(tempDir);
    if (LOG.isInfoEnabled()) { LOG.info("CrawlDb topN: done"); }
View Full Code Here
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
    if (LOG.isInfoEnabled()) {
      LOG.info("Indexer: starting");
      LOG.info("Indexer: linkdb: " + linkDb);
    }

    JobConf job = new NutchJob(getConf());
    job.setJobName("index " + indexDir);

    for (int i = 0; i < segments.length; i++) {
      if (LOG.isInfoEnabled()) {
        LOG.info("Indexer: adding segment: " + segments[i]);
      }
      job.addInputPath(new Path(segments[i], CrawlDatum.FETCH_DIR_NAME));
      job.addInputPath(new Path(segments[i], ParseData.DIR_NAME));
      job.addInputPath(new Path(segments[i], ParseText.DIR_NAME));
    }

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

    job.setMapperClass(Indexer.class);
    job.setReducerClass(Indexer.class);

    job.setOutputPath(indexDir);
    job.setOutputFormat(OutputFormat.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(ObjectWritable.class);

    JobClient.runJob(job);
    if (LOG.isInfoEnabled()) { LOG.info("Indexer: done"); }
  }
View Full Code Here
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
    throws IOException {
    Path newCrawlDb =
      new Path(crawlDb,
               Integer.toString(new Random().nextInt(Integer.MAX_VALUE)));

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


    Path current = new Path(crawlDb, CURRENT_NAME);
    if (FileSystem.get(job).exists(current)) {
      job.addInputPath(current);
    }
    job.setInputFormat(SequenceFileInputFormat.class);

    job.setMapperClass(CrawlDbFilter.class);
    job.setReducerClass(CrawlDbReducer.class);

    job.setOutputPath(newCrawlDb);
    job.setOutputFormat(MapFileOutputFormat.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(CrawlDatum.class);

    return job;
  }
View Full Code Here
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
      return;
    }

    Configuration conf = NutchConfiguration.create();
    conf.addDefaultResource("crawl-tool.xml");
    JobConf job = new NutchJob(conf);

    Path rootUrlDir = null;
    Path dir = new Path("crawl-" + getDate());
    int threads = job.getInt("fetcher.threads.fetch", 10);
    int depth = 5;
    int topN = Integer.MAX_VALUE;

    for (int i = 0; i < args.length; i++) {
      if ("-dir".equals(args[i])) {
        dir = new Path(args[i+1]);
        i++;
      } else if ("-threads".equals(args[i])) {
        threads = Integer.parseInt(args[i+1]);
        i++;
      } else if ("-depth".equals(args[i])) {
        depth = Integer.parseInt(args[i+1]);
        i++;
      } else if ("-topN".equals(args[i])) {
        topN = Integer.parseInt(args[i+1]);
        i++;
      } else if (args[i] != null) {
        rootUrlDir = new Path(args[i]);
      }
    }

    FileSystem fs = FileSystem.get(job);
    if (fs.exists(dir)) {
      throw new RuntimeException(dir + " already exists.");
    }

    if (LOG.isInfoEnabled()) {
      LOG.info("crawl started in: " + dir);
      LOG.info("rootUrlDir = " + rootUrlDir);
      LOG.info("threads = " + threads);
      LOG.info("depth = " + depth);
      if (topN != Integer.MAX_VALUE)
        LOG.info("topN = " + topN);
    }
   
    Path crawlDb = new Path(dir + "/crawldb");
    Path linkDb = new Path(dir + "/linkdb");
    Path segments = new Path(dir + "/segments");
    Path indexes = new Path(dir + "/indexes");
    Path index = new Path(dir + "/index");

    Path tmpDir = job.getLocalPath("crawl"+Path.SEPARATOR+getDate());
    Injector injector = new Injector(conf);
    Generator generator = new Generator(conf);
    Fetcher fetcher = new Fetcher(conf);
    ParseSegment parseSegment = new ParseSegment(conf);
    CrawlDb crawlDbTool = new CrawlDb(conf);
View Full Code Here
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
    // 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);
    sortJob.setInputPath(urlDir);
    sortJob.setMapperClass(InjectMapper.class);

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

    // merge with existing crawl db
    if (LOG.isInfoEnabled()) {
      LOG.info("Injector: Merging injected urls into crawl db.");
View Full Code Here
72
73
74
75
76
77
78
79
80
        fetcher = new Fetcher();
        Configuration conf = new Configuration();
        // conf.addDefaultResource("crawl-tool.xml");
        conf.addDefaultResource("nutch-default.xml");
        conf.addDefaultResource("nutch-site.xml");
        JobConf job = new NutchJob(conf);
        threads = job.getInt("fetcher.threads.fetch", 10);
        fetcher.setConf(conf);
    }
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
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(PartitionUrlByHost.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
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.