Package org.apache.nutch.parse

Examples of org.apache.nutch.parse.ParseStatus

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
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
    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(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
81
82
83
84
85
86
87
88
89
    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
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
210
      }

      // 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
321
322
323
324
325
326
327
328
329
330
331
        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
82
83
84
85
86
87
88
89
90
91
92
    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
150
151
152
153
154
155
156
157
158
159
160
  }
 
  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
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
    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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
    } catch (IOException e) {
      // This can never happen because it's an in memory stream
    } catch(PatternSyntaxException e) {
      System.err.println(e.getMessage());
      log.error("Error parsing urlRegex: " + e.getMessage());
      return new ParseStatus(ParseStatus.FAILED, "Error parsing urlRegex: " + e.getMessage()).getEmptyParseResult(content.getUrl(), configuration);
    } catch (ParserConfigurationException e) {
      System.err.println(e.getMessage());
      log.error("HTML Cleaning error: " + e.getMessage());
      return new ParseStatus(ParseStatus.FAILED, "HTML Cleaning error: " + e.getMessage()).getEmptyParseResult(content.getUrl(), configuration);
    } catch (SAXException e) {
      System.err.println(e.getMessage());
      log.error("XML parsing error: " + e.getMessage());
      return new ParseStatus(ParseStatus.FAILED, "XML parsing error: " + e.getMessage()).getEmptyParseResult(content.getUrl(), configuration);
    } catch (JaxenException e) {
      System.err.println(e.getMessage());
      log.error("XPath error: " + e.getMessage());
      return new ParseStatus(ParseStatus.FAILED, "XPath error: " + e.getMessage()).getEmptyParseResult(content.getUrl(), configuration);
    }
   
    return parseResult;
  }
View Full Code Here
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
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
    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(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
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
      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
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.