Package org.apache.nutch.parse

Examples of org.apache.nutch.parse.Parse

119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
  public void testNone() throws ProtocolException, ParseException {
    String urlString;
    Protocol protocol;
    Content content;
    Parser parser;
    Parse parse;

    urlString = "file:" + sampleDir + fileSeparator + none;
    protocol = ProtocolFactory.getProtocol(urlString);
    content = protocol.getContent(urlString);
    parser = ParserFactory.getParser(content.getContentType(), urlString);
    try {
      parse = parser.getParse(content);
      Properties metadata = parse.getData().getMetadata();
    } catch (ParseException e) {
      return;
    }
    fail("Expected ParseException");
View Full Code Here
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
    public void testIt() throws ProtocolException, ParseException {
        String urlString;
        Protocol protocol;
        Content content;
        Parser parser;
        Parse parse;

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

            protocol = ProtocolFactory.getProtocol(urlString);
            content = protocol.getProtocolOutput(urlString).getContent();

            parser = ParserFactory.getParser(content.getContentType(),
                    urlString);
            parse = parser.getParse(content);

            //check that there are 3 outlinks:
            //http://test.channel.com
            //http://www-scf.usc.edu/~mattmann/
            //http://www.nutch.org

            ParseData theParseData = parse.getData();

            Outlink[] theOutlinks = theParseData.getOutlinks();

            assertTrue("There aren't 3 outlinks read!", theOutlinks.length == 3);
View Full Code Here
119
120
121
122
123
124
125
126
127
128
129
    doc.add("segment", metadata.get(Nutch.SEGMENT_NAME_KEY));

    // add digest, used by dedup
    doc.add("digest", metadata.get(Nutch.SIGNATURE_KEY));

    final Parse parse = new ParseImpl(parseText, parseData);
    try {
      // extract information from dbDatum and pass it to
      // fetchDatum so that indexing filters can use it
      final Text url = (Text) dbDatum.getMetaData().get(Nutch.WRITABLE_REPR_URL_KEY);
      if (url != null) {
View Full Code Here
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
  public void testId3v2() throws ProtocolException, ParseException {

    String urlString;
    Protocol protocol;
    Content content;
    Parse parse;

    Configuration conf = NutchConfiguration.create();
    urlString = "file:" + sampleDir + fileSeparator + id3v2;
    protocol = new ProtocolFactory(conf).getProtocol(urlString);
    content = protocol.getProtocolOutput(new Text(urlString), new CrawlDatum())
                      .getContent();
    parse = new ParseUtil(conf).parseByExtensionId("parse-mp3", content).get(urlString);
    Metadata metadata = parse.getData().getParseMeta();
    assertEquals("postgresql comment id3v2", metadata.get("COMM-Text"));
    assertEquals("postgresql composer id3v2", metadata.get("TCOM-Text"));
    assertEquals("02", metadata.get("TRCK-Text"));
    assertEquals("http://localhost/", metadata.get("WCOP-URL Link"));
    assertEquals("postgresql artist id3v2", metadata.get("TPE1-Text"));
    assertEquals("(28)", metadata.get("TCON-Text"));
    assertEquals("2004", metadata.get("TYER-Text"));
    assertEquals("postgresql title id3v2", metadata.get("TIT2-Text"));
    assertEquals("postgresql album id3v2", metadata.get("TALB-Text"));
    assertEquals("postgresql encoded by id3v2", metadata.get("TENC-Text"));

    assertEquals("postgresql title id3v2 - "
        + "postgresql album id3v2 - "
        + "postgresql artist id3v2", parse.getData().getTitle());
    assertEquals("http://localhost/", parse.getData().getOutlinks()[0].getToUrl());

  }
View Full Code Here
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
  public void testId3v1() throws ProtocolException, ParseException {

    String urlString;
    Protocol protocol;
    Content content;
    Parse parse;

    Configuration conf = NutchConfiguration.create();
    urlString = "file:" + sampleDir + fileSeparator + id3v1;
    protocol = new ProtocolFactory(conf).getProtocol(urlString);
    content = protocol.getProtocolOutput(new Text(urlString), new CrawlDatum())
                      .getContent();
    parse = new ParseUtil(conf).parseByExtensionId("parse-mp3", content).get(urlString);

    Metadata metadata = parse.getData().getParseMeta();
    assertEquals("postgresql comment id3v1", metadata.get("COMM-Text"));
    assertEquals("postgresql artist id3v1", metadata.get("TPE1-Text"));
    assertEquals("(28)", metadata.get("TCON-Text"));
    assertEquals("2004", metadata.get("TYER-Text"));
    assertEquals("postgresql title id3v1", metadata.get("TIT2-Text"));
    assertEquals("postgresql album id3v1", metadata.get("TALB-Text"));

    assertEquals("postgresql title id3v1 - "
        + "postgresql album id3v1 - "
        + "postgresql artist id3v1", parse.getData().getTitle());

  }
View Full Code Here
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
  public void testNone() throws ProtocolException, ParseException {
    String urlString;
    Protocol protocol;
    Content content;
    Parse parse;

    Configuration conf = NutchConfiguration.create();
    urlString = "file:" + sampleDir + fileSeparator + none;
    protocol = new ProtocolFactory(conf).getProtocol(urlString);
    content = protocol.getProtocolOutput(new Text(urlString), new CrawlDatum())
                      .getContent();
    parse = new ParseUtil(conf).parseByExtensionId("parse-mp3", content).get(urlString);
//    Metadata metadata = parse.getData().getParseMeta();
    if (parse.getData().getStatus().isSuccess()) {
      fail("Expected ParseException");
    }
  }
View Full Code Here
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
   * <li>3. meta http-equiv (content-language) (http://www.w3.org/TR/REC-html40/struct/global.html#h-7.4.4.2)
   * <br>Only the first occurence of language is stored.
   */
  public ParseResult filter(Content content, ParseResult parseResult, HTMLMetaTags metaTags, DocumentFragment doc) {
   
    Parse parse = parseResult.get(content.getUrl());

    // Trying to find the document's language
    LanguageParser parser = new LanguageParser(doc);
    String lang = parser.getLanguage();

    if (lang != null) {
      parse.getData().getParseMeta().set(Metadata.LANGUAGE, lang);
    }
    return parseResult;
  }
View Full Code Here
50
51
52
53
54
55
56
57
58
59
60
61
    try {
      ParseUtil parser = new ParseUtil(NutchConfiguration.create());
      /* loop through the test documents and validate result */
      for (int t = 0; t < docs.length; t++) {
        Content content = getContent(docs[t]);
        Parse parse = parser.parse(content).get(content.getUrl());
        assertEquals(metalanguages[t], (String) parse.getData().getParseMeta().get(Metadata.LANGUAGE));
      }
    } catch (Exception e) {
      e.printStackTrace(System.out);
      fail(e.toString());
    }
View Full Code Here
268
269
270
271
272
273
274
275
276
277
278
    doc.add("segment", metadata.get(Nutch.SEGMENT_NAME_KEY));

    // add digest, used by dedup
    doc.add("digest", metadata.get(Nutch.SIGNATURE_KEY));

    final Parse parse = new ParseImpl(parseText, parseData);
    try {
      // extract information from dbDatum and pass it to
      // fetchDatum so that indexing filters can use it
      final Text url = (Text) dbDatum.getMetaData().get(Nutch.WRITABLE_REPR_URL_KEY);
      if (url != null) {
View Full Code Here
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
  public void testIt() throws ProtocolException, ParseException {
    String urlString;
    Protocol protocol;
    Content content;
    Parse parse;

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

      Configuration conf = NutchConfiguration.create();
      protocol = new ProtocolFactory(conf).getProtocol(urlString);
      content = protocol.getProtocolOutput(new Text(urlString), new CrawlDatum()).getContent();
      parse = new ParseUtil(conf).parseByExtensionId("parse-tika", content).get(content.getUrl());

      assertEquals("121", parse.getData().getMeta("width"));
      assertEquals("48", parse.getData().getMeta("height"));
    }
  }
View Full Code Here
TOP

Related Classes of org.apache.nutch.parse.Parse

  • com.atlantbh.nutch.filter.index.omit.OmitIndexingFilterTest
  • com.atlantbh.nutch.filter.xpath.XPathHtmlParserFilterTest
  • com.atlantbh.nutch.filter.xpath.XPathIndexingFilterTest
  • com.atlantbh.nutch.index.alternativedataflow.AlternativeDataFlowIndexingFilterTest
  • com.atlantbh.nutch.index.alternativedataflow.flow.CsvDataFlowTest
  • org.apache.nutch.analysis.lang.HTMLLanguageParser
  • org.apache.nutch.analysis.lang.LanguageIdentifier
  • org.apache.nutch.analysis.lang.TestHTMLLanguageParser
  • org.apache.nutch.indexer.field.BasicFields$Extractor
  • org.apache.nutch.indexer.IndexerMapReduce
    • 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.