Package org.apache.nutch.parse

Examples of org.apache.nutch.parse.ParseStatus

58
59
60
61
62
63
64
65
66
67
68
      Outlink[] old = parse.getData().getOutlinks();
      Properties metadata = parse.getData().getMetadata();
      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()]);
      parse = new ParseImpl(text, new ParseData(status, title, newlinks, metadata));
    }
    return parse;
View Full Code Here
119
120
121
122
123
124
125
126
127
128
129
  }
 
  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();
    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
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
139
140
141
142
143
144
145
146
147
148
149
150
    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();

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

    if (LOG.isLoggable(Level.FINE))
      LOG.fine("Use "+command+ " with timeout="+timeout+"secs");

    String text = null;
    String title = null;

    try {

      byte[] raw = content.getContent();

      String contentLength =
        (String)content.getMetadata().get("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();
      }

      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();

      text = os.toString();

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

    if (text == null)
      text = "";
View Full Code Here
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
        // check that contentType is one we can handle
        String contentType = content.getContentType();
        if (contentType != null
                && (!contentType.startsWith("text/xml") && !contentType
                        .startsWith("application/rss+xml")))
            return new ParseStatus(ParseStatus.FAILED_INVALID_FORMAT,
                    "Content-Type not text/xml or application/rss+xml: "
                            + contentType).getEmptyParse();

        List theRSSChannels = null;

        try {
            byte[] raw = content.getContent();

            // create a new FeedParser...
            FeedParser parser = FeedParserFactory.newFeedParser();

            // create a listener for handling our callbacks
            FeedParserListener listener = new FeedParserListenerImpl();

            // start parsing our feed and have the onItem methods called
            parser.parse(listener, new ByteArrayInputStream(raw), /* resource */
            null);

            theRSSChannels = ((FeedParserListenerImpl) listener).getChannels();

        } catch (Exception e) { // run time exception
            e.printStackTrace();
            LOG.fine("nutch:parse-rss:RSSParser Exception: " + e.getMessage());
            return new ParseStatus(ParseStatus.FAILED,
                    "Can't be handled as rss document. " + e).getEmptyParse();
        }

        StringBuffer contentTitle = new StringBuffer(), indexText = new StringBuffer();
        List theOutlinks = new Vector();
View Full Code Here
57
58
59
60
61
62
63
64
65
66
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
  public Parse getParse(Content content) {

    // check that contentType is one we can handle
    String contentType = content.getContentType();
    if (contentType != null && !contentType.startsWith("application/msword"))
      return new ParseStatus(ParseStatus.FAILED, ParseStatus.FAILED_INVALID_FORMAT,
        "Content-Type not application/msword: " + contentType).getEmptyParse();

    String text = null;
    String title = null;
    Properties properties = null;

    try {

      byte[] raw = content.getContent();

      String contentLength = content.get("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 msword file.").getEmptyParse();
      }

      WordExtractor extractor = new WordExtractor();

      // collect text
      text = extractor.extractText(new ByteArrayInputStream(raw));

      // collect meta info
      properties = extractor.extractProperties(new ByteArrayInputStream(raw));

      extractor = null;

    } catch (ParseException e) {
      return new ParseStatus(e).getEmptyParse();
    } catch (FastSavedException e) {
      return new ParseStatus(e).getEmptyParse();
    } catch (PasswordProtectedException e) {
      return new ParseStatus(e).getEmptyParse();
    } catch (Exception e) { // run time exception
      return new ParseStatus(ParseStatus.FAILED,
              "Can't be handled as msword document. " + e).getEmptyParse();
    } finally {
      // nothing so far
    }
View Full Code Here
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
139
140
141
142
143
144
145
146
147
148
149
150
151
152
  public Parse getParse(Content content) {

    // check that contentType is one we can handle
    String contentType = content.getContentType();
    if (contentType != null && !contentType.startsWith("application/pdf"))
      return new ParseStatus(ParseStatus.FAILED, ParseStatus.FAILED_INVALID_FORMAT,
        "Content-Type not application/pdf: " + contentType).getEmptyParse();

    // in memory representation of pdf file
    PDDocument pdf = null;

    String text = null;
    String title = null;

    try {

      byte[] raw = content.getContent();

      String contentLength = content.get("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();
      }

      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.
      // pdf.getPageCount();
      // info.getAuthor()
      // info.getSubject()
      // info.getKeywords()
      // info.getCreator()
      // info.getProducer()
      // info.getTrapped()
      // formatDate(info.getCreationDate())
      // formatDate(info.getModificationDate())

    } catch (CryptographyException e) {
      return new ParseStatus(ParseStatus.FAILED,
              "Error decrypting document. " + e).getEmptyParse();
    } catch (InvalidPasswordException e) {
      return new ParseStatus(ParseStatus.FAILED,
              "Can't decrypt document - invalid password. " + e).getEmptyParse();
    } catch (Exception e) { // run time exception
      return new ParseStatus(ParseStatus.FAILED,
              "Can't be handled as pdf document. " + e).getEmptyParse();
    } finally {
      try {
        if (pdf != null)
          pdf.close();
View Full Code Here
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
      if (mp3.hasID3v2Tag()) {
        parse = getID3v2Parse(mp3, content.getMetadata(), content);
      } else if (mp3.hasID3v1Tag()) {
        parse = getID3v1Parse(mp3, content.getMetadata(), content);
      } else {
        return new ParseStatus().getEmptyParseResult(content.getUrl(),
            getConf());
      }
    } catch (IOException e) {
      return new ParseStatus().getEmptyParseResult(content.getUrl(),
          getConf());
    } catch (TagException e) {
      return new ParseStatus().getEmptyParseResult(content.getUrl(),
          getConf());
    } finally {
      tmp.delete();
    }
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.")
                               .getEmptyParseResult(content.getUrl(), 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)
                             .getEmptyParseResult(content.getUrl(), this.conf);
    }
   
    // collect meta data
View Full Code Here
57
58
59
60
61
62
63
64
65
    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
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
      }

      // set the content signature
      if (parseResult == null) {
        byte[] signature = SignatureFactory.getSignature(getConf()).calculate(
          content, new ParseStatus().getEmptyParse(getConf()));
        datum.setSignature(signature);
      }

      try {
        output.collect(key, new NutchWritable(datum));
        output.collect(key, new NutchWritable(content));

        if (parseResult != null) {
          for (Entry <Text, Parse> entry : parseResult) {
            Text url = entry.getKey();
            Parse parse = entry.getValue();
            ParseStatus parseStatus = parse.getData().getStatus();

            if (!parseStatus.isSuccess()) {
              LOG.warn("Error parsing: " + key + ": " + parseStatus);
              parse = parseStatus.getEmptyParse(getConf());
            }

            // Calculate page signature.
            byte[] signature = SignatureFactory.getSignature(getConf()).calculate(
              content, parse);
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.