Package org.apache.nutch.parse

Examples of org.apache.nutch.parse.ParseData

56
57
58
59
60
61
62
63
64
65
66
    conf.setBoolean("moreIndexingFilter.indexMimeTypeParts", false);
    MoreIndexingFilter filter = new MoreIndexingFilter();
    filter.setConf(conf);
    Assert.assertNotNull(filter);
    NutchDocument doc = new NutchDocument();
    ParseImpl parse = new ParseImpl("foo bar", new ParseData());
   
    try{
        filter.filter(doc, parse, new Text("http://nutch.apache.org/index.html"), new CrawlDatum(), new Inlinks());
    }
    catch(Exception e){
View Full Code Here
80
81
82
83
84
85
86
87
88
89
90
    Metadata metadata = new Metadata();
    metadata.add(Response.CONTENT_DISPOSITION, "filename=filename.ext");
    MoreIndexingFilter filter = new MoreIndexingFilter();
    filter.setConf(conf);

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

    Assert.assertEquals("content-disposition not detected", "filename.ext", doc.getFieldValue("title"));
  }
View Full Code Here
99
100
101
102
103
104
105
106
107
108
  private void assertContentType(Configuration conf, String source, String expected) throws IndexingException {
    Metadata metadata = new Metadata();
    metadata.add(Response.CONTENT_TYPE, source);
    MoreIndexingFilter filter = new MoreIndexingFilter();
    filter.setConf(conf);
    NutchDocument doc = filter.filter(new NutchDocument(), new ParseImpl("text", new ParseData(
        new ParseStatus(), "title", new Outlink[0], metadata)), new Text(
        "http://www.example.com/"), new CrawlDatum(), new Inlinks());
    Assert.assertEquals("mime type not detected", expected, doc.getFieldValue("type"));
  }
View Full Code Here
81
82
83
84
85
86
87
88
89
90
91
      List<Outlink> list = Arrays.asList(old);
      outlinks.addAll(list);
      ParseStatus status = parse.getData().getStatus();
      String text = parse.getText();
      Outlink[] newlinks = (Outlink[])outlinks.toArray(new Outlink[outlinks.size()]);
      ParseData parseData = new ParseData(status, title, newlinks,
                                          parse.getData().getContentMeta(),
                                          parse.getData().getParseMeta());

      // replace original parse obj with new one
      parseResult.put(content.getUrl(), new ParseText(text), parseData);
View Full Code Here
161
162
163
164
165
166
167
168
169
      title = script.substring(0, idx);
    } else {
      idx = Math.min(MAX_TITLE_LEN, script.length());
      title = script.substring(0, idx);
    }
    ParseData pd = new ParseData(ParseStatus.STATUS_SUCCESS, title, outlinks,
                                 c.getMetadata());
    return ParseResult.createParseResult(c.getUrl(), new ParseImpl(script, pd));
  }
View Full Code Here
99
100
101
102
103
104
105
106
107
108
109
    }

    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
96
97
98
99
100
101
102
103
104
105
106
107
            Metadata metadata = new Metadata();
            metadata.set(Response.CONTENT_LENGTH, Long.toString(entry.getSize()));
            metadata.set(Response.CONTENT_TYPE, contentType);
            Content content = new Content(newurl, base, b, contentType, metadata, this.conf);
            Parse parse = new ParseUtil(this.conf).parse(content);
            ParseData theParseData = parse.getData();
            Outlink[] theOutlinks = theParseData.getOutlinks();
           
            for(int count = 0; count < theOutlinks.length; count++) {
              outLinksList.add(new Outlink(theOutlinks[count].getToUrl(), theOutlinks[count].getAnchor(), this.conf));
            }
           
View Full Code Here
99
100
101
102
103
104
105
106
107
108
109
    metadataCollector.notifyProperty("TPE1-Text", tag.getArtist());
    metadataCollector.notifyProperty("COMM-Text", tag.getComment());
    metadataCollector.notifyProperty("TCON-Text", "(" + tag.getGenre() + ")");
    metadataCollector.notifyProperty("TIT2-Text", tag.getTitle());
    metadataCollector.notifyProperty("TYER-Text", tag.getYear());
    ParseData parseData = new ParseData(ParseStatus.STATUS_SUCCESS,
                                        metadataCollector.getTitle(),
                                        metadataCollector.getOutlinks(),
                                        contentMeta,
                                        metadataCollector.getData());
    return new ParseImpl(metadataCollector.getText(), parseData);
View Full Code Here
127
128
129
130
131
132
133
134
135
136
137
            metadataCollector.notifyProperty(name + "-" + bodyName, bodyValue);
          }
        }
      }
    }
    ParseData parseData = new ParseData(ParseStatus.STATUS_SUCCESS,
                                        metadataCollector.getTitle(),
                                        metadataCollector.getOutlinks(),
                                        contentMeta,
                                        metadataCollector.getData());
    return new ParseImpl(metadataCollector.getText(), parseData);
View Full Code Here
95
96
97
98
99
100
101
102
103
104
105
106
107
    if (resultTitle == null) {
      resultTitle = "";
    }

    outlinks = (Outlink[]) outLinksList.toArray(new Outlink[0]);
    final ParseData parseData = new ParseData(ParseStatus.STATUS_SUCCESS,
                                              resultTitle, outlinks,
                                              content.getMetadata());
    parseData.setConf(this.conf);

    if (LOG.isTraceEnabled()) { LOG.trace("Zip file parsed sucessfully !!"); }
    return new ParseImpl(resultText, parseData);
  }
View Full Code Here
TOP

Related Classes of org.apache.nutch.parse.ParseData

  • com.atlantbh.nutch.filter.index.omit.OmitIndexingFilterTest
  • com.atlantbh.nutch.filter.xpath.XPathHtmlParserFilterTest
  • com.atlantbh.nutch.filter.xpath.XPathIndexingFilterTest
  • com.atlantbh.nutch.index.alternativedataflow.AlternativeDataFlowIndexingFilterTest
  • com.atlantbh.nutch.index.alternativedataflow.flow.CsvDataFlowTest
  • org.apache.commons.cli.Options
  • org.apache.hadoop.conf.Configuration
  • org.apache.hadoop.fs.FileSystem
  • org.apache.hadoop.util.GenericOptionsParser
  • org.apache.nutch.fetcher.TestFetcher
    • 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.