Package org.apache.nutch.storage

Examples of org.apache.nutch.storage.WebPage

73
74
75
76
77
78
79
80
81
82
83
84
85
  }
 
  private void assertContentType(Configuration conf, String source, String expected) throws IndexingException {
    MoreIndexingFilter filter = new MoreIndexingFilter();
    filter.setConf(conf);
    WebPage page = new WebPage();
    String url = "http://www.example.com/";
    page.setContent(ByteBuffer.wrap("text".getBytes()));
    page.setTitle(new Utf8("title"));
    page.putToHeaders(EncodingDetector.CONTENT_TYPE_UTF8, new Utf8(source));
    NutchDocument doc = filter.filter(new NutchDocument(), url, page);
    assertEquals("mime type not detected", expected, doc.getFieldValue("type"));
  }
View Full Code Here
155
156
157
158
159
160
161
162
163
164
165
      file.setMaxContentLength(maxContentLength);

    // set log level
    // LOG.setLevel(Level.parse((new String(logLevel)).toUpperCase()));

    Content content = file.getProtocolOutput(urlString, new WebPage())
        .getContent();

    System.out.println("Content-Type: " + content.getContentType());
    System.out.println("Content-Length: "
        + content.getMetadata().get(Response.CONTENT_LENGTH));
View Full Code Here
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
  byte[] bytes = new byte[(int) file.length()];
  DataInputStream in = new DataInputStream(new FileInputStream(file));
  in.readFully(bytes);
  in.close();
  Parse parse;
  WebPage page = new WebPage();
  page.setBaseUrl(new Utf8("file:"+urlString));
  page.setContent(ByteBuffer.wrap(bytes));
  // set the content type?
  MimeUtil mimeutil = new MimeUtil(conf);
  String mtype = mimeutil.getMimeType(file);
  page.setContentType(new Utf8(mtype));
   
  parse = new ParseUtil(conf).parse("file:"+urlString, page);
  return parse.getText();
    }
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
    }
    in.close();
    byte[] bytes = out.toByteArray();
    Configuration conf = NutchConfiguration.create();

    WebPage page = new WebPage();
    page.setBaseUrl(new Utf8(url));
    page.setContent(ByteBuffer.wrap(bytes));
    MimeUtil mimeutil = new MimeUtil(conf);
    String mtype = mimeutil.getMimeType(file);
    page.setContentType(new Utf8(mtype));

    new ParseUtil(conf).parse(url, page);

    ByteBuffer bb = page.getFromMetadata(new Utf8("License-Url"));
    assertEquals(license, new String(bb.array()));
    bb = page.getFromMetadata(new Utf8("License-Location"));
    assertEquals(location, new String(bb.array()));
    bb = page.getFromMetadata(new Utf8("Work-Type"));
    if (bb == null)
      assertEquals(type, null);
    else
      assertEquals(type, new String(bb.array()));
  }
View Full Code Here
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
      byte[] bytes = new byte[(int) file.length()];
      DataInputStream in = new DataInputStream(new FileInputStream(file));
      in.readFully(bytes);
      in.close();

      WebPage page = new WebPage();
      page.setBaseUrl(new Utf8(urlString));
      page.setContent(ByteBuffer.wrap(bytes));
      String mtype = mimeutil.getMimeType(file);
      page.setContentType(new Utf8(mtype));

      parse = new ParseUtil(conf).parse(urlString, page);

      String text = parse.getText().replaceAll("[ \t\r\n]+", " ").trim();
View Full Code Here
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
      byte[] bytes = new byte[(int) file.length()];
      DataInputStream in = new DataInputStream(new FileInputStream(file));
      in.readFully(bytes);
      in.close();

      WebPage page = new WebPage();
      page.setBaseUrl(new Utf8(urlString));
      page.setContent(ByteBuffer.wrap(bytes));
      String mtype = mimeutil.getMimeType(file);
      page.setContentType(new Utf8(mtype));

      parse = new ParseUtil(conf).parse(urlString, page);

      int index = parse.getText().indexOf(expectedText);
      assertTrue(index > 0);
View Full Code Here
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
      byte[] bytes = new byte[(int) file.length()];
      DataInputStream in = new DataInputStream(new FileInputStream(file));
      in.readFully(bytes);
      in.close();

      WebPage page = new WebPage();
      page.setBaseUrl(new Utf8(urlString));
      page.setContent(ByteBuffer.wrap(bytes));
      String mtype = mimeutil.getMimeType(file);
      page.setContentType(new Utf8(mtype));

      parse = new ParseUtil(conf).parse(urlString, page);

      // check that there are 2 outlinks:
View Full Code Here
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
    DataInputStream in = new DataInputStream(new FileInputStream(file));
    in.readFully(bytes);
    Configuration conf = NutchConfiguration.create();
    // TikaParser parser = new TikaParser();
    // parser.setConf(conf);
    WebPage page = new WebPage();
    page.setBaseUrl(new Utf8(url));
    page.setContent(ByteBuffer.wrap(bytes));
    MimeUtil mimeutil = new MimeUtil(conf);
    String mtype = mimeutil.getMimeType(file);
    page.setContentType(new Utf8(mtype));
    // Parse parse = parser.getParse(url, page);

    Parse parse = new ParseUtil(conf).parse(url, page);

    System.out.println("content type: " + mtype);
View Full Code Here
378
379
380
381
382
383
384
385
386
387
388
    //    if (verbose) {
    //      LOGGER.setLevel(Level.FINE);
    //    }

    ProtocolOutput out = http.getProtocolOutput(url, new WebPage());
    Content content = out.getContent();

    System.out.println("Status: " + out.getStatus());
    if (content != null) {
      System.out.println("Content Type: " + content.getContentType());
View Full Code Here
50
51
52
53
54
55
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
    //Metadata metadata = new Metadata();
    EncodingDetector detector;
    // Content content;
    String encoding;

    WebPage page = new WebPage();
    page.setBaseUrl(new Utf8("http://www.example.com/"));
    page.setContentType(new Utf8("text/plain"));
    page.setContent(ByteBuffer.wrap(contentInOctets));

    detector = new EncodingDetector(conf);
    detector.autoDetectClues(page, true);
    encoding = detector.guessEncoding(page, "windows-1252");
    // no information is available, so it should return default encoding
    assertEquals("windows-1252", encoding.toLowerCase());

    page = new WebPage();
    page.setBaseUrl(new Utf8("http://www.example.com/"));
    page.setContentType(new Utf8("text/plain"));
    page.setContent(ByteBuffer.wrap(contentInOctets));
    page.putToHeaders(EncodingDetector.CONTENT_TYPE_UTF8, new Utf8("text/plain; charset=UTF-16"));
   
    detector = new EncodingDetector(conf);
    detector.autoDetectClues(page, true);
    encoding = detector.guessEncoding(page, "windows-1252");
    assertEquals("utf-16", encoding.toLowerCase());

    page = new WebPage();
    page.setBaseUrl(new Utf8("http://www.example.com/"));
    page.setContentType(new Utf8("text/plain"));
    page.setContent(ByteBuffer.wrap(contentInOctets));
   
    detector = new EncodingDetector(conf);
    detector.autoDetectClues(page, true);
    detector.addClue("windows-1254", "sniffed");
    encoding = detector.guessEncoding(page, "windows-1252");
    assertEquals("windows-1254", encoding.toLowerCase());

    // enable autodetection
    conf.setInt(EncodingDetector.MIN_CONFIDENCE_KEY, 50);
    page = new WebPage();
    page.setBaseUrl(new Utf8("http://www.example.com/"));
    page.setContentType(new Utf8("text/plain"));
    page.setContent(ByteBuffer.wrap(contentInOctets));
    page.putToMetadata(new Utf8(Response.CONTENT_TYPE), ByteBuffer.wrap("text/plain; charset=UTF-16".getBytes()));
   
    detector = new EncodingDetector(conf);
    detector.autoDetectClues(page, true);
    detector.addClue("utf-32", "sniffed");
    encoding = detector.guessEncoding(page, "windows-1252");
View Full Code Here
TOP

Related Classes of org.apache.nutch.storage.WebPage

  • org.apache.gora.persistency.impl.StateManagerImpl
  • org.apache.nutch.analysis.lang.TestHTMLLanguageParser
  • org.apache.nutch.api.DbReader$DbIterator
  • org.apache.nutch.crawl.DbUpdateReducer
  • org.apache.nutch.crawl.InjectorJob$UrlMapper
  • org.apache.nutch.crawl.TestGenerator
  • org.apache.nutch.crawl.TestInjector
  • org.apache.nutch.crawl.TestURLPartitioner
  • org.apache.nutch.crawl.WebTableReader
  • org.apache.nutch.fetcher.FetcherReducer$FetcherThread
    • 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.