Package org.apache.nutch.util

Examples of org.apache.nutch.util.MimeUtil

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
    public void testIt() throws ProtocolException, ParseException, IOException {
  String urlString;
  Parse parse;
  Configuration conf = NutchConfiguration.create();
  MimeUtil mimeutil = new MimeUtil(conf);

  System.out.println("Expected : " + expectedText);

  for (int i = 0; i < sampleFiles.length; i++) {
      urlString = "file:" + sampleDir + fileSeparator + sampleFiles[i];

      if (sampleFiles[i].startsWith("ootest") == false)
    continue;

      File file = new File(sampleDir + fileSeparator + sampleFiles[i]);
      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
264
265
266
267
268
269
270
  public void addIndexBackendOptions(Configuration conf) {
  }

  public void setConf(Configuration conf) {
    this.conf = conf;
    MIME = new MimeUtil(conf);
  }
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
    public void testIt() throws ProtocolException, ParseException, IOException {
  String urlString;
  Parse parse;
  Configuration conf = NutchConfiguration.create();
  MimeUtil mimeutil = new MimeUtil(conf);

  for (int i = 0; i < sampleFiles.length; i++) {
      urlString = "file:" + sampleDir + fileSeparator + sampleFiles[i];

      File file = new File(sampleDir + fileSeparator + sampleFiles[i]);
      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);
View Full Code Here
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
    String urlString;
    Protocol protocol;
    Parse parse;

    Configuration conf = NutchConfiguration.create();
    MimeUtil mimeutil = new MimeUtil(conf);
    for (int i = 0; i < sampleFiles.length; i++) {
      urlString = "file:" + sampleDir + fileSeparator + sampleFiles[i];

      File file = new File(sampleDir + fileSeparator + sampleFiles[i]);
      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
239
240
241
242
243
244
245
246
247
248
249
250
    // 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);
View Full Code Here
119
120
121
122
123
124
125
126
127
128
    this.userAgent = getAgentString(conf.get("http.agent.name"), conf.get("http.agent.version"), conf
        .get("http.agent.description"), conf.get("http.agent.url"), conf.get("http.agent.email"));
    this.acceptLanguage = conf.get("http.accept.language", acceptLanguage);
    this.accept = conf.get("http.accept", accept);
    this.ip_header = conf.getBoolean("http.store.ip.address", false);
    this.mimeTypes = new MimeUtil(conf);
    this.useHttp11 = conf.getBoolean("http.useHttp11", false);
    this.robots.setConf(conf);
    logConf();
  }
View Full Code Here
59
60
61
62
63
64
65
 
 
  /** Creates a new instance of ZipTextExtractor */
  public ZipTextExtractor(Configuration conf) {
    this.conf = conf;
    this.MIME = new MimeUtil(conf);
  }
View Full Code Here
269
270
271
272
273
274
275
  public void addIndexBackendOptions(Configuration conf) {
  }

  public void setConf(Configuration conf) {
    this.conf = conf;
    MIME = new MimeUtil(conf);
  }
View Full Code Here
75
76
77
78
79
80
81
82
83
84
85
86
    in.close();

    WebPage page = new WebPage();
    page.setBaseUrl(new Utf8(urlString));
    page.setContent(ByteBuffer.wrap(bytes));
    MimeUtil mimeutil = new MimeUtil(conf);
    String mtype = mimeutil.getMimeType(file);
    page.setContentType(new Utf8(mtype));
    parse = new ParseUtil(conf).parse(urlString, page);
    //begin assertion for tests
    ByteBuffer bbuf = page.getFromMetadata(new Utf8("Rel-Tag"));
    byte[] byteArray = new byte[bbuf.remaining()];
View Full Code Here
113
114
115
116
117
118
119
120
121
122
    this.maxContent = conf.getInt("http.content.limit", 64 * 1024);
    this.userAgent = getAgentString(conf.get("http.agent.name"), conf.get("http.agent.version"), conf
        .get("http.agent.description"), conf.get("http.agent.url"), conf.get("http.agent.email"));
    this.acceptLanguage = conf.get("http.accept.language", acceptLanguage);
    this.accept = conf.get("http.accept", accept);
    this.mimeTypes = new MimeUtil(conf);
    this.useHttp11 = conf.getBoolean("http.useHttp11", false);
    this.robots.setConf(conf);
    logConf();
  }
View Full Code Here
TOP

Related Classes of org.apache.nutch.util.MimeUtil

  • org.apache.nutch.indexer.more.MoreIndexingFilter
  • org.apache.nutch.microformats.reltag.TestRelTagParser
  • org.apache.nutch.parse.js.TestJSParseFilter
  • org.apache.nutch.parse.tika.TestMSWordParser
  • org.apache.nutch.parse.tika.TestOOParser
  • org.apache.nutch.parse.tika.TestPdfParser
  • org.apache.nutch.parse.tika.TestRSSParser
  • org.apache.nutch.parse.tika.TestRTFParser
  • org.apache.nutch.parse.tika.TikaParser
  • org.apache.nutch.parse.zip.ZipTextExtractor
    • 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.