Examples of ParseData

Examples of org.apache.nutch.parse.ParseData

471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
    }
    Path parseDir = new Path(segment, ParseData.DIR_NAME);
    if (fs.exists(fetchDir) && fs.isDirectory(fetchDir)) {
      cnt = 0L;
      long errors = 0L;
      ParseData value = new ParseData();
      MapFile.Reader[] mreaders = MapFileOutputFormat.getReaders(fs, parseDir, getConf());
      for (int i = 0; i < mreaders.length; i++) {
        while (mreaders[i].next(key, value)) {
          cnt++;
          if (!value.getStatus().isSuccess()) errors++;
        }
        mreaders[i].close();
      }
      stats.parsed = cnt;
      stats.parseErrors = errors;
View Full Code Here

Examples of org.apache.nutch.parse.ParseData

174
175
176
177
178
179
180
181
182
183
184
185
186
      title = "";

    // collect outlink
    Outlink[] outlinks = OutlinkExtractor.getOutlinks(text, getConf());

    ParseData parseData = new ParseData(ParseStatus.STATUS_SUCCESS, title,
                                        outlinks, content.getMetadata(),
                                        metadata);
    parseData.setConf(this.conf);
    return new ParseImpl(text, parseData);
    // any filter?
    //return HtmlParseFilters.filter(content, parse, root);
  }
View Full Code Here

Examples of org.apache.nutch.parse.ParseData

43
44
45
46
47
48
49
50
   
  public Parse getParse(Content content)
  {
//    return new ParseImpl(content.getUrl(),  TODO MC BUG - don't index url as content
    return new ParseImpl("",
      new ParseData(ParseStatus.STATUS_SUCCESS,
      "", new Outlink[0], content.getMetadata()));
  }
View Full Code Here

Examples of org.apache.nutch.parse.ParseData

335
336
337
338
339
340
341
342
343
344
345
  public void reduce(WritableComparable key, Iterator values, OutputCollector output, Reporter reporter) throws IOException {
    CrawlDatum lastG = null;
    CrawlDatum lastF = null;
    CrawlDatum lastSig = null;
    Content lastC = null;
    ParseData lastPD = null;
    ParseText lastPT = null;
    String lastGname = null;
    String lastFname = null;
    String lastSigname = null;
    String lastCname = null;
View Full Code Here

Examples of org.apache.nutch.parse.ParseData

130
131
132
133
134
135
136
137
138
139
140
    add(urlStr, doc, "encoding", parse.getData().getMeta(ENCODING_KEY),
      false, true, true, false, false);

    // Get metadatas.
    MapWritable mw = datum.getMetaData();
    ParseData pd = parse.getData();

    // Add as stored, indexed, and untokenized but not lowercased.
    add(urlStr, doc, ARCCOLLECTION_KEY,
      getMetadataValue(ARCCOLLECTION_KEY, pd, mw),
      false, true, true, false);
View Full Code Here

Examples of org.apache.nutch.parse.ParseData

174
175
176
177
178
179
180
181
182
183
184
    }

    // collect outlink
    Outlink[] outlinks = OutlinkExtractor.getOutlinks(text, getConf());

    ParseData parseData = new ParseData(ParseStatus.STATUS_SUCCESS, title,
      outlinks, content.getMetadata());
    parseData.setConf(this.conf);
   
    return new ParseImpl(text, parseData);
  }
View Full Code Here

Examples of org.apache.nutch.parse.ParseData

100
101
102
103
104
105
106
107
108
109
110
    }

    if (text == null) { text = ""; }
    if (title == null) { title = ""; }

    ParseData parseData = new ParseData(ParseStatus.STATUS_SUCCESS, title,
                                        outlinks, content.getMetadata(),
                                        metadata);
    parseData.setConf(this.conf);
    return new ParseImpl(text, parseData);
  }
View Full Code Here

Examples of org.apache.nutch.parse.ParseData

44
45
46
47
48
49
50
51
52
    String class1 = "NonExistingFilter";
    String class2 = "org.apache.nutch.indexer.basic.BasicIndexingFilter";
    conf.set(IndexingFilters.INDEXINGFILTER_ORDER, class1 + " " + class2);

    IndexingFilters filters = new IndexingFilters(conf);
    filters.filter(new NutchDocument(), new ParseImpl("text", new ParseData(
      new ParseStatus(), "title", new Outlink[0], new Metadata())), new Text(
      "http://www.example.com/"), new CrawlDatum(), new Inlinks());
  }
View Full Code Here

Examples of org.apache.nutch.parse.ParseData

59
60
61
62
63
64
65
66
67
68
69
    Configuration conf = NutchConfiguration.create();
    conf.addResource("nutch-default.xml");
    conf.addResource("crawl-tests.xml");

    IndexingFilters filters = new IndexingFilters(conf);
    NutchDocument doc = filters.filter(null, new ParseImpl("text", new ParseData(
      new ParseStatus(), "title", new Outlink[0], new Metadata())), new Text(
      "http://www.example.com/"), new CrawlDatum(), new Inlinks());
    
    Assert.assertNull(doc);
  }
View Full Code Here

Examples of org.apache.nutch.parse.ParseData

81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
    String class1 = "org.apache.nutch.indexer.basic.BasicIndexingFilter";
    conf.set(IndexingFilters.INDEXINGFILTER_ORDER, class1);

    IndexingFilters filters1 = new IndexingFilters(conf);
    NutchDocument fdoc1 = filters1.filter(new NutchDocument(),new ParseImpl("text",new ParseData(
      new ParseStatus(),"title",new Outlink[0],new Metadata())),new Text("http://www.example.com/"),
      new CrawlDatum(),new Inlinks());

    // add another index filter
    String class2 = "org.apache.nutch.indexer.metadata.MetadataIndexer";
    // set content metadata
    Metadata md = new Metadata();
    md.add("example","data");
    // set content metadata property defined in MetadataIndexer
    conf.set("index.content.md","example");
    // add MetadataIndxer filter
    conf.set(IndexingFilters.INDEXINGFILTER_ORDER, class1 + " " + class2);
    IndexingFilters filters2 = new IndexingFilters(conf);
    NutchDocument fdoc2 = filters2.filter(new NutchDocument(),new ParseImpl("text",new ParseData(
      new ParseStatus(),"title",new Outlink[0],md)),new Text("http://www.example.com/"),
      new CrawlDatum(),new Inlinks());
    Assert.assertEquals(fdoc1.getFieldNames().size(),fdoc2.getFieldNames().size());
  }
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.