Package org.apache.nutch.parse

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

320
321
322
323
324
325
326
327
328
329
330
        Content content = new Content(urlStr, urlStr, bytes.get(), contentType,
          new Metadata(), getConf());
       
        // set the url version into the metadata
        content.getMetadata().set(URL_VERSION, version);
        ParseStatus pstatus = null;
        pstatus = output(output, segmentName, url, datum, content, status,
          CrawlDatum.STATUS_FETCH_SUCCESS);
        reporter.progress();
      }
      catch (Throwable t) { // unexpected exception
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
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
139
140
141
142
143
144
145
146
147
148
149
150
151
  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
56
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
  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
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
    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
44
45
46
47
48
49
50
51
    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
59
60
61
62
63
64
65
66
67
68
    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());
    
    assertNull(doc);
  }
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
    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());
    assertEquals(fdoc1.getFieldNames().size(),fdoc2.getFieldNames().size());
  }
View Full Code Here
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
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
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
    URL base;
    try {
      base = new URL(content.getBaseUrl());
    } catch (MalformedURLException e) {
      return new ParseStatus(e).getEmptyParseResult(content.getUrl(),
          getConf());
    }

    // get the right parser using the mime type as a clue
    Parser parser = tikaConfig.getParser(MediaType.parse(mimeType));
    byte[] raw = content.getContent();

    if (parser == null) {
      String message = "Can't retrieve Tika parser for mime-type "
          + mimeType;
      LOG.error(message);
      return new ParseStatus(ParseStatus.FAILED, message)
          .getEmptyParseResult(content.getUrl(), getConf());
    }

    LOG.debug("Using Tika parser " + parser.getClass().getName()
        + " for mime-type " + mimeType);

    Metadata tikamd = new Metadata();

    HTMLDocumentImpl doc = new HTMLDocumentImpl();
    doc.setErrorChecking(false);
    DocumentFragment root = doc.createDocumentFragment();
    DOMBuilder domhandler = new DOMBuilder(doc, root);
    ParseContext context = new ParseContext();
    try {
      parser.parse(new ByteArrayInputStream(raw), domhandler, tikamd,context);
    } catch (Exception e) {
      LOG.error("Error parsing "+content.getUrl(),e);
      return new ParseStatus(ParseStatus.FAILED, e.getMessage())
          .getEmptyParseResult(content.getUrl(), getConf());
    }

    HTMLMetaTags metaTags = new HTMLMetaTags();
    String text = "";
    String title = "";
    Outlink[] outlinks = new Outlink[0];
    org.apache.nutch.metadata.Metadata nutchMetadata = new org.apache.nutch.metadata.Metadata();

    // we have converted the sax events generated by Tika into a DOM object
    // so we can now use the usual HTML resources from Nutch
    // get meta directives
    HTMLMetaProcessor.getMetaTags(metaTags, root, base);
    if (LOG.isTraceEnabled()) {
      LOG.trace("Meta tags for " + base + ": " + metaTags.toString());
    }

    // check meta directives
    if (!metaTags.getNoIndex()) { // okay to index
      StringBuffer sb = new StringBuffer();
      if (LOG.isTraceEnabled()) {
        LOG.trace("Getting text...");
      }
      utils.getText(sb, root); // extract text
      text = sb.toString();
      sb.setLength(0);
      if (LOG.isTraceEnabled()) {
        LOG.trace("Getting title...");
      }
      utils.getTitle(sb, root); // extract title
      title = sb.toString().trim();
    }

    if (!metaTags.getNoFollow()) { // okay to follow links
      ArrayList<Outlink> l = new ArrayList<Outlink>(); // extract outlinks
      URL baseTag = utils.getBase(root);
      if (LOG.isTraceEnabled()) {
        LOG.trace("Getting links...");
      }
      utils.getOutlinks(baseTag != null ? baseTag : base, l, root);
      outlinks = l.toArray(new Outlink[l.size()]);
      if (LOG.isTraceEnabled()) {
        LOG.trace("found " + outlinks.length + " outlinks in "
            + content.getUrl());
      }
    }

    // populate Nutch metadata with Tika metadata
    String[] TikaMDNames = tikamd.names();
    for (String tikaMDName : TikaMDNames) {
      if (tikaMDName.equalsIgnoreCase(Metadata.TITLE))
        continue;
      // TODO what if multivalued?
      nutchMetadata.add(tikaMDName, tikamd.get(tikaMDName));
    }

    // no outlinks? try OutlinkExtractor e.g works for mime types where no
    // explicit markup for anchors

    if (outlinks.length == 0) {
      outlinks = OutlinkExtractor.getOutlinks(text, getConf());
    }

    ParseStatus status = new ParseStatus(ParseStatus.SUCCESS);
    if (metaTags.getRefresh()) {
      status.setMinorCode(ParseStatus.SUCCESS_REDIRECT);
      status.setArgs(new String[] { metaTags.getRefreshHref().toString(),
          Integer.toString(metaTags.getRefreshTime()) });
    }
    ParseData parseData = new ParseData(status, title, outlinks, content
        .getMetadata(), nutchMetadata);
    ParseResult parseResult = ParseResult.createParseResult(content
View Full Code Here
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
      final int len = Integer.parseInt(contentLen);
      if (LOG.isDebugEnabled()) { LOG.debug("ziplen: " + len); }
      final byte[] contentInBytes = content.getContent();

      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
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.