Package org.apache.nutch.util

Examples of org.apache.nutch.util.NutchJob

144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
   * @throws IOException If an error occurs while running the collector.
   */
  private void runCollector(Path basicFields, Path links, Path output)
    throws IOException {

    JobConf collector = new NutchJob(getConf());
    collector.setJobName("AnchorFields Collector");
    FileInputFormat.addInputPath(collector, links);
    FileInputFormat.addInputPath(collector, basicFields);
    FileOutputFormat.setOutputPath(collector, output);
    collector.setInputFormat(SequenceFileInputFormat.class);
    collector.setMapOutputKeyClass(Text.class);
    collector.setMapOutputValueClass(ObjectWritable.class);
    collector.setMapperClass(Collector.class);
    collector.setReducerClass(Collector.class);
    collector.setOutputKeyClass(Text.class);
    collector.setOutputValueClass(FieldWritable.class);
    collector.setOutputFormat(SequenceFileOutputFormat.class);

    LOG.info("Starting collector job");
    try {
      JobClient.runJob(collector);
    }
View Full Code Here
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
      LOG.info("ReprUrlFixer: crawlDb " + crawlDb);
      Path crawlDbCurrent = new Path(crawlDb, CrawlDb.CURRENT_NAME);
      Path newCrawlDb = new Path(crawlDb,
        Integer.toString(new Random().nextInt(Integer.MAX_VALUE)));

      JobConf updater = new NutchJob(conf);
      updater.setJobName("ReprUtilFixer: " + crawlDb.toString());
      FileInputFormat.addInputPath(updater, crawlDbCurrent);
      FileOutputFormat.setOutputPath(updater, newCrawlDb);
      updater.setInputFormat(SequenceFileInputFormat.class);
      updater.setReducerClass(ReprUrlFixer.class);
      updater.setOutputKeyClass(Text.class);
      updater.setOutputValueClass(CrawlDatum.class);
      updater.setOutputFormat(MapFileOutputFormat.class);

      try {
        JobClient.runJob(updater);
        LOG.info("ReprUrlFixer: installing new crawldb " + crawlDb);
        CrawlDb.install(updater, crawlDb);
      }
      catch (IOException e) {
        LOG.error(StringUtils.stringifyException(e));
        throw e;
      }
    }

    // run the segments through the repr fixer, logic will be run on both the
    // crawl_parse and the crawl_fetch directories for every segment specified
    if (segments != null) {

      for (int i = 0; i < segments.length; i++) {

        Path segment = segments[i];
        LOG.info("ReprUrlFixer: fetching segment " + segment);
        Path segFetch = new Path(segment, CrawlDatum.FETCH_DIR_NAME);
        Path newSegFetch = new Path(segment, CrawlDatum.FETCH_DIR_NAME + "-"
          + Integer.toString(new Random().nextInt(Integer.MAX_VALUE)));

        JobConf fetch = new NutchJob(conf);
        fetch.setJobName("ReprUrlFixer: " + segment.toString());
        FileInputFormat.addInputPath(fetch, segFetch);
        FileOutputFormat.setOutputPath(fetch, newSegFetch);
        fetch.setInputFormat(SequenceFileInputFormat.class);
        fetch.setReducerClass(ReprUrlFixer.class);
        fetch.setOutputKeyClass(Text.class);
        fetch.setOutputValueClass(CrawlDatum.class);
        fetch.setOutputFormat(MapFileOutputFormat.class);

        try {
          JobClient.runJob(fetch);
          LOG.info("ReprUrlFixer: installing new segment fetch directory " + newSegFetch);
          FSUtils.replace(fs, segFetch, newSegFetch, true);
          LOG.info("ReprUrlFixer: finished installing segment fetch directory");
        }
        catch (IOException e) {
          LOG.error(StringUtils.stringifyException(e));
          throw e;
        }

        LOG.info("ReprUrlFixer: parsing segment " + segment);
        Path segParse = new Path(segment, CrawlDatum.PARSE_DIR_NAME);
        Path newSegParse = new Path(segment, CrawlDatum.PARSE_DIR_NAME + "-"
          + Integer.toString(new Random().nextInt(Integer.MAX_VALUE)));

        JobConf parse = new NutchJob(conf);
        parse.setJobName("ReprUrlFixer: " + segment.toString());
        FileInputFormat.addInputPath(parse, segParse);
        FileOutputFormat.setOutputPath(parse, newSegParse);
        parse.setInputFormat(SequenceFileInputFormat.class);
        parse.setReducerClass(ReprUrlFixer.class);
        parse.setOutputKeyClass(Text.class);
        parse.setOutputValueClass(CrawlDatum.class);
        parse.setOutputFormat(MapFileOutputFormat.class);

        try {
          JobClient.runJob(parse);
          LOG.info("ReprUrlFixer: installing new segment parse directry " + newSegParse);
          FSUtils.replace(fs, segParse, newSegParse, true);
View Full Code Here
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
  }

  public static JobConf createMergeJob(Configuration conf, Path output, boolean normalize, boolean filter) {
    Path newCrawlDb = new Path("crawldb-merge-" + Integer.toString(new Random().nextInt(Integer.MAX_VALUE)));

    JobConf job = new NutchJob(conf);
    job.setJobName("crawldb merge " + output);

    job.setInputFormat(SequenceFileInputFormat.class);

    job.setMapperClass(CrawlDbFilter.class);
    job.setBoolean(CrawlDbFilter.URL_FILTERING, filter);
    job.setBoolean(CrawlDbFilter.URL_NORMALIZING, normalize);
    job.setReducerClass(Merger.class);

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

    return job;
  }
View Full Code Here
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
      System.err.println("\toldDb\tname of the crawldb that uses UTF8 class.");
      System.err.println("\tnewDb\tname of the output crawldb that will use Text class.");
      System.err.println("\twithMetadata\tconvert also all metadata keys that use UTF8 to Text.");
      return -1;
    }
    JobConf job = new NutchJob(getConf());
    FileSystem fs = FileSystem.get(getConf());
    Path oldDb = new Path(args[0], CrawlDb.CURRENT_NAME);
    Path newDb =
      new Path(oldDb,
               Integer.toString(new Random().nextInt(Integer.MAX_VALUE)));
    if (!fs.exists(oldDb)) {
      LOG.fatal("Old db doesn't exist in '" + args[0] + "'");
      return -1;
    }
    boolean withMetadata = false;
    if (args.length > 2 && args[2].equalsIgnoreCase("-withMetadata"))
      withMetadata = true;
   
    SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
    long start = System.currentTimeMillis();
    LOG.info("CrawlDbConverter: starting at " + sdf.format(start));

    job.setBoolean(CONVERT_META_KEY, withMetadata);
    FileInputFormat.addInputPath(job, oldDb);
    job.setInputFormat(SequenceFileInputFormat.class);
    job.setMapperClass(CrawlDbConverter.class);
    job.setOutputFormat(MapFileOutputFormat.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(CrawlDatum.class);
    FileOutputFormat.setOutputPath(job, newDb);
    try {
      JobClient.runJob(job);
      CrawlDb.install(job, new Path(args[1]));
    } catch (Exception e) {
View Full Code Here
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
109
110
111
112
113
114
115
116
117
118
119
120
        " [-solr solrURL]");
      return;
    }

    Configuration conf = NutchConfiguration.createCrawlConfiguration();
    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;
    long topN = Long.MAX_VALUE;
    String indexerName = "lucene";
    String solrUrl = null;
   
    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 ("-solr".equals(args[i])) {
        indexerName = "solr";
        solrUrl = StringUtils.lowerCase(args[i + 1]);
        i++;
      } else if (args[i] != null) {
        rootUrlDir = new Path(args[i]);
      }
    }

    boolean isSolrIndex = StringUtils.equalsIgnoreCase(indexerName, "solr");
    FileSystem fs = FileSystem.get(job);

    if (LOG.isInfoEnabled()) {
      LOG.info("crawl started in: " + dir);
      LOG.info("rootUrlDir = " + rootUrlDir);
      LOG.info("threads = " + threads);
      LOG.info("depth = " + depth);     
      LOG.info("indexer=" + indexerName);
      if (isSolrIndex) {
        LOG.info("solrUrl=" + solrUrl);
      }
      if (topN != Long.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
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
   * @throws IOException If an error occurs while converting.
   */
  private void runConverter(Path[] inputs, Path output)
    throws IOException {

    JobConf converter = new NutchJob(getConf());
    converter.setJobName("CustomFields Converter");
    for (int i = 0; i < inputs.length; i++) {
      FileInputFormat.addInputPath(converter, inputs[i]);
    }
    FileOutputFormat.setOutputPath(converter, output);
    converter.setInputFormat(TextInputFormat.class);
    converter.setMapperClass(Converter.class);
    converter.setReducerClass(Converter.class);
    converter.setMapOutputKeyClass(Text.class);
    converter.setMapOutputValueClass(FieldWritable.class);
    converter.setOutputKeyClass(Text.class);
    converter.setOutputValueClass(FieldWritable.class);
    converter.setOutputFormat(SequenceFileOutputFormat.class);

    LOG.info("Starting converter job");
    try {
      JobClient.runJob(converter);
    }
View Full Code Here
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
   * @throws IOException If an error occurs while converting.
   */
  private void runCollector(Path basicFields, Path converted, Path output)
    throws IOException {

    JobConf collector = new NutchJob(getConf());
    collector.setJobName("CustomFields Collector");
    FileInputFormat.addInputPath(collector, converted);
    FileInputFormat.addInputPath(collector, basicFields);
    FileOutputFormat.setOutputPath(collector, output);
    collector.setInputFormat(SequenceFileInputFormat.class);
    collector.setMapOutputKeyClass(Text.class);
    collector.setMapOutputValueClass(ObjectWritable.class);
    collector.setMapperClass(Collector.class);
    collector.setReducerClass(Collector.class);
    collector.setOutputKeyClass(Text.class);
    collector.setOutputValueClass(FieldWritable.class);
    collector.setOutputFormat(SequenceFileOutputFormat.class);

    LOG.info("Starting collector job");
    try {
      JobClient.runJob(collector);
    }
View Full Code Here
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
    SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
    long start = System.currentTimeMillis();
    LOG.info("FieldIndexer: starting at " + sdf.format(start));

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

    for (int i = 0; i < fields.length; i++) {
      Path fieldsDb = fields[i];
      LOG.info("FieldIndexer: adding fields db: " + fieldsDb);
      FileInputFormat.addInputPath(job, fieldsDb);
    }

    job.setInputFormat(SequenceFileInputFormat.class);
    job.setMapperClass(FieldIndexer.class);
    job.setReducerClass(FieldIndexer.class);
    FileOutputFormat.setOutputPath(job, indexDir);
    job.setOutputFormat(OutputFormat.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(FieldWritable.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(LuceneDocumentWrapper.class);

    JobClient.runJob(job);
    long end = System.currentTimeMillis();
    LOG.info("FieldIndexer: finished at " + sdf.format(end) + ", elapsed: " + TimingUtil.elapsedTime(start, end));
  }
View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
      List<Path> segments) throws IOException {
    SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
    long start = System.currentTimeMillis();
    LOG.info("SolrIndexer: starting at " + sdf.format(start));

    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
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
    SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
    long start = System.currentTimeMillis();
    LOG.info("SolrDeleteDuplicates: starting at " + sdf.format(start));
    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);

    long end = System.currentTimeMillis();
    LOG.info("SolrDeleteDuplicates: finished at " + sdf.format(end) + ", elapsed: " + TimingUtil.elapsedTime(start, end));
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.