Package org.apache.nutch.parse

Examples of org.apache.nutch.parse.ParseStatus$EmptyParseImpl

45
46
47
48
49
50
51
52
    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
60
61
62
63
64
65
66
67
68
69
    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
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
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
121
122
123
124
125
126
    String contentType = content.getContentType();

    String[] params = (String[]) TYPE_PARAMS_MAP.get(contentType);
    if (params == null)
      return new ParseStatus(ParseStatus.FAILED,
                      "No external command defined for contentType: " + contentType).getEmptyParseResult(content.getUrl(), getConf());

    String command = params[0];
    int timeout = Integer.parseInt(params[1]);
    String encoding = params[2];

    if (LOG.isTraceEnabled()) {
      LOG.trace("Use "+command+ " with timeout="+timeout+"secs");
    }

    String text = null;
    String title = null;

    try {

      byte[] raw = content.getContent();

      String contentLength = content.getMetadata().get(Response.CONTENT_LENGTH);
      if (contentLength != null
            && raw.length != Integer.parseInt(contentLength)) {
          return new ParseStatus(ParseStatus.FAILED, ParseStatus.FAILED_TRUNCATED,
                "Content truncated at " + raw.length
            +" bytes. Parser can't handle incomplete "
            + contentType + " file.").getEmptyParseResult(content.getUrl(), getConf());
      }

      ByteArrayOutputStream os = new ByteArrayOutputStream(BUFFER_SIZE);
      ByteArrayOutputStream es = new ByteArrayOutputStream(BUFFER_SIZE/4);

      CommandRunner cr = new CommandRunner();

      cr.setCommand(command+ " " +contentType);
      cr.setInputStream(new ByteArrayInputStream(raw));
      cr.setStdOutputStream(os);
      cr.setStdErrorStream(es);

      cr.setTimeout(timeout);

      cr.evaluate();

      if (cr.getExitValue() != 0)
        return new ParseStatus(ParseStatus.FAILED,
                        "External command " + command
                        + " failed with error: " + es.toString()).getEmptyParseResult(content.getUrl(), getConf());

      text = os.toString(encoding);

    } catch (Exception e) { // run time exception
      return new ParseStatus(e).getEmptyParseResult(content.getUrl(), getConf());
    }

    if (text == null)
      text = "";
View Full Code Here
81
82
83
84
85
86
87
88
89
90
    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
100
101
102
103
104
105
106
107
108
    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
78
79
80
81
82
83
84
85
86
87
88
    if (outlinks.size() > 0) {
      Outlink[] old = parse.getData().getOutlinks();
      String title = parse.getData().getTitle();
      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());
View Full Code Here
146
147
148
149
150
151
152
153
154
155
156
  }
 
  public ParseResult getParse(Content c) {
    String type = c.getContentType();
    if (type != null && !type.trim().equals("") && !type.toLowerCase().startsWith("application/x-javascript"))
      return new ParseStatus(ParseStatus.FAILED_INVALID_FORMAT,
              "Content not JavaScript: '" + type + "'").getEmptyParseResult(c.getUrl(), getConf());
    String script = new String(c.getContent());
    Outlink[] outlinks = getJSLinks(script, "", c.getUrl());
    if (outlinks == null) outlinks = new Outlink[0];
    // Title? use the first line of the script...
View Full Code Here
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
    try {
      byte[] raw = content.getContent();
      String contentLength = content.getMetadata().get(Metadata.CONTENT_LENGTH);
      if ((contentLength != null) &&
          (raw.length != Integer.parseInt(contentLength))) {
        return new ParseStatus(ParseStatus.FAILED,
                               ParseStatus.FAILED_TRUNCATED,
                               "Content truncated at " + raw.length +" bytes. " +
                               "Parser can't handle incomplete file.")
                               .getEmptyParse(this.conf);
      }
      extractor.extract(new ByteArrayInputStream(raw));
      text = extractor.getText();
      properties = extractor.getProperties();
      outlinks = OutlinkExtractor.getOutlinks(text, content.getUrl(), getConf());
     
    } catch (Exception e) {
      return new ParseStatus(ParseStatus.FAILED,
                             "Can't be handled as Microsoft document. " + e)
                             .getEmptyParse(this.conf);
    }
   
    // collect meta data
View Full Code Here
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
      if (mp3.hasID3v2Tag()) {
        parse = getID3v2Parse(mp3, content.getMetadata());
      } else if (mp3.hasID3v1Tag()) {
        parse = getID3v1Parse(mp3, content.getMetadata());
      } else {
        return new ParseStatus(ParseStatus.FAILED,
                               ParseStatus.FAILED_MISSING_CONTENT,
                               "No textual content available").getEmptyParse(conf);
      }
    } catch (IOException e) {
      return new ParseStatus(ParseStatus.FAILED,
                             ParseStatus.FAILED_EXCEPTION,
                             "Couldn't create temporary file:" + e).getEmptyParse(conf);
    } catch (TagException e) {
      return new ParseStatus(ParseStatus.FAILED,
                             ParseStatus.FAILED_EXCEPTION,
                             "ID3 Tags could not be parsed:" + e).getEmptyParse(conf);
    } finally{
      tmp.delete();
    }
View Full Code Here
TOP

Related Classes of org.apache.nutch.parse.ParseStatus$EmptyParseImpl

  • com.atlantbh.nutch.filter.xpath.XPathHtmlParserFilter
  • org.apache.nutch.indexer.more.TestMoreIndexingFilter
  • org.apache.nutch.indexer.TestIndexingFilters
  • org.apache.nutch.metadata.Metadata
  • org.apache.nutch.parse.ext.ExtParser
  • org.apache.nutch.parse.ext.WaxExtParser
  • org.apache.nutch.parse.feed.FeedParser
  • org.apache.nutch.parse.js.JSParseFilter
  • org.apache.nutch.parse.mp3.MP3Parser
  • org.apache.nutch.parse.ms.MSBaseParser
    • 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.