Package org.apache.nutch.parse

Examples of org.apache.nutch.parse.ParseStatus

58
59
60
61
62
63
64
65
66
67
68
    if (outlinks.size() > 0) {
      Outlink[] old = parse.getData().getOutlinks();
      String title = parse.getData().getTitle();
      List 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
125
126
127
128
129
130
131
132
133
134
135
  }
 
  public Parse 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 + "'").getEmptyParse(getConf());
    String script = new String(c.getContent());
    Outlink[] outlinks = getJSLinks(script, c.getUrl(), c.getUrl());
    if (outlinks == null) outlinks = new Outlink[0];
    // Title? use the first line of the script...
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
      final ByteArrayInputStream bainput = new ByteArrayInputStream(
          contentInBytes);
      final InputStream input = bainput;

      if (contentLen != null && contentInBytes.length != len) {
        return new ParseStatus(ParseStatus.FAILED,
            ParseStatus.FAILED_TRUNCATED, "Content truncated at "
                + contentInBytes.length
                + " bytes. Parser can't handle incomplete pdf file.")
            .getEmptyParse(getConf());
      }

      ZipTextExtractor extractor = new ZipTextExtractor(getConf());

      // extract text
      resultText = extractor.extractText(new ByteArrayInputStream(
          contentInBytes), content.getUrl(), outLinksList);

    } catch (Exception e) {
      return new ParseStatus(ParseStatus.FAILED,
          "Can't be handled as Zip document. " + e).getEmptyParse(getConf());
    }

    if (resultText == null) {
      resultText = "";
View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
    rtfParser.setDelegate(delegate);

    try {
      rtfParser.parse();
    } catch (ParseException e) {
        return new ParseStatus(ParseStatus.FAILED,
                               ParseStatus.FAILED_EXCEPTION,
                               e.toString()).getEmptyParse(conf);
    }

    Metadata metadata = new Metadata();
View Full Code Here
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
      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
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).getEmptyParse(getConf());

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

    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.").getEmptyParse(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()).getEmptyParse(getConf());

      text = os.toString();

    } catch (Exception e) { // run time exception
      return new ParseStatus(e).getEmptyParse(getConf());
    }

    if (text == null)
      text = "";
View Full Code Here
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
    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 micrsosoft document. " + e)
                             .getEmptyParse(this.conf);
    }
   
    // collect meta data
View Full Code Here
41
42
43
44
45
46
47
48
    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
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
      final ByteArrayInputStream bainput = new ByteArrayInputStream(
          contentInBytes);
      final InputStream input = bainput;

      if (contentLen != null && contentInBytes.length != len) {
        return new ParseStatus(ParseStatus.FAILED,
            ParseStatus.FAILED_TRUNCATED, "Content truncated at "
                + contentInBytes.length
                + " bytes. Parser can't handle incomplete pdf file.")
            .getEmptyParseResult(content.getUrl(), getConf());
      }

      ZipTextExtractor extractor = new ZipTextExtractor(getConf());

      // extract text
      resultText = extractor.extractText(new ByteArrayInputStream(
          contentInBytes), content.getUrl(), outLinksList);

    } catch (Exception e) {
      return new ParseStatus(ParseStatus.FAILED,
          "Can't be handled as Zip document. " + e).getEmptyParseResult(content.getUrl(), getConf());
    }

    if (resultText == null) {
      resultText = "";
View Full Code Here
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
150
      feed = feedInput.build(input);
    } catch (Exception e) {
      // return empty parse
      LOG.warn("Parse failed: url: " + content.getUrl() + ", exception: "
          + StringUtils.stringifyException(e));
      return new ParseStatus(e)
          .getEmptyParseResult(content.getUrl(), getConf());
    }

    List entries = feed.getEntries();
    String feedLink = feed.getLink();
    try {
      feedLink = normalizers.normalize(feedLink, URLNormalizers.SCOPE_OUTLINK);
      if (feedLink != null)
        feedLink = filters.filter(feedLink);
    } catch (Exception e) {
      feedLink = null;
    }

    for (Iterator i = entries.iterator(); i.hasNext();) {
      SyndEntry entry = (SyndEntry) i.next();
      addToMap(parseResult, feed, feedLink, entry, content);
    }

    String feedDesc = stripTags(feed.getDescriptionEx());
    String feedTitle = stripTags(feed.getTitleEx());

    parseResult.put(content.getUrl(), new ParseText(feedDesc), new ParseData(
        new ParseStatus(ParseStatus.SUCCESS), feedTitle, new Outlink[0],
        content.getMetadata()));

    return parseResult;
  }
View Full Code Here
TOP

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

  • 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.