Package org.apache.nutch.parse

Examples of org.apache.nutch.parse.ParseStatus

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.")
            .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
42
43
44
45
46
47
48
49
    String class2 = "org.apache.nutch.indexer.basic.BasicIndexingFilter";
    conf.set(IndexingFilters.INDEXINGFILTER_ORDER, class1 + " " + class2);

    IndexingFilters filters = new IndexingFilters(conf);
    filters.filter(new Document(), 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
98
99
100
101
102
103
104
105
106
107
108
        } catch (Exception e) { // run time exception
            if (LOG.isWarnEnabled()) {
              e.printStackTrace(LogUtil.getWarnStream(LOG));
              LOG.warn("nutch:parse-rss:RSSParser Exception: " + e.getMessage());
            }
            return new ParseStatus(ParseStatus.FAILED,
                    "Can't be handled as rss document. " + e).getEmptyParse(getConf());
        }

        StringBuffer contentTitle = new StringBuffer(), indexText = new StringBuffer();
        List theOutlinks = new Vector();
View Full Code Here
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
127
    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
59
60
61
62
63
64
65
66
67
68
69
    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
75
76
77
78
79
80
81
82
83
84
85
    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
142
143
144
145
146
147
148
149
150
151
152
  }
 
  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());
    if (outlinks == null) outlinks = new Outlink[0];
    // Title? use the first line of the script...
View Full Code Here
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
127
128
129
130
131
132
133
134
135
136
137
138
      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 pdf file.").getEmptyParse(getConf());
      }

      PDFParser parser = new PDFParser(new ByteArrayInputStream(raw));
      parser.parse();

      pdf = parser.getPDDocument();

      if (pdf.isEncrypted()) {
        DocumentEncryption decryptor = new DocumentEncryption(pdf);
        //Just try using the default password and move on
        decryptor.decryptDocument("");
      }

      // collect text
      PDFTextStripper stripper = new PDFTextStripper();
      text = stripper.getText(pdf);

      // collect title
      PDDocumentInformation info = pdf.getDocumentInformation();
      title = info.getTitle();
      // more useful info, currently not used. please keep them for future use.
      metadata.add(Metadata.PAGE_COUNT, String.valueOf(pdf.getPageCount()));
      metadata.add(Metadata.AUTHOR, info.getAuthor());
      metadata.add(Metadata.SUBJECT, info.getSubject());
      metadata.add(Metadata.KEYWORDS, info.getKeywords());
      metadata.add(Metadata.CREATOR, info.getCreator());
      metadata.add(Metadata.PUBLISHER, info.getProducer());
     
      //TODO: Figure out why we get a java.io.IOException: Error converting date:1-Jan-3 18:15PM
      //error here
     
      //metadata.put(DATE, dcDateFormatter.format(info.getCreationDate().getTime()));
      //metadata.put(LAST_MODIFIED, dcDateFormatter.format(info.getModificationDate().getTime()));

    } catch (CryptographyException e) {
      return new ParseStatus(ParseStatus.FAILED,
              "Error decrypting document. " + e).getEmptyParse(getConf());
    } catch (InvalidPasswordException e) {
      return new ParseStatus(ParseStatus.FAILED,
              "Can't decrypt document - invalid password. " + e).getEmptyParse(getConf());
    } catch (Exception e) { // run time exception
        if (LOG.isWarnEnabled()) {
          LOG.warn("General exception in PDF parser: "+e.getMessage());
          e.printStackTrace(LogUtil.getWarnStream(LOG));       
        }
      return new ParseStatus(ParseStatus.FAILED,
              "Can't be handled as pdf document. " + e).getEmptyParse(getConf());
    } finally {
      try {
        if (pdf != null)
          pdf.close();
View Full Code Here
82
83
84
85
86
87
88
89
90
    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());
    assertEquals("mime type not detected", expected, doc.getFieldValue("type"));
  }
View Full Code Here
99
100
101
102
103
104
105
106
107
108
109
        } catch (Exception e) { // run time exception
            if (LOG.isWarnEnabled()) {
              e.printStackTrace(LogUtil.getWarnStream(LOG));
              LOG.warn("nutch:parse-rss:RSSParser Exception: " + e.getMessage());
            }
            return new ParseStatus(ParseStatus.FAILED,
                    "Can't be handled as rss document. " + e).getEmptyParseResult(content.getUrl(), getConf());
        }

        StringBuffer contentTitle = new StringBuffer(), indexText = new StringBuffer();
        List theOutlinks = new Vector();
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.