Package edu.buffalo.cse.ir.wikiindexer.parsers

Examples of edu.buffalo.cse.ir.wikiindexer.parsers.Parser

325
326
327
328
329
330
331
   
   
    private ParserRunner(Properties props, Collection<WikipediaDocument> collection) {
      this.idxProps = props;
      this.coll = collection;
       parser = new Parser(props);
    }
View Full Code Here
94
95
96
97
98
99
100
101
102
103
104
105
106
 
  private static void runIndexer(Properties properties) throws InterruptedException {
    long start;
    System.out.println("Starting .......");
    ArrayList<WikipediaDocument> list = new ArrayList<WikipediaDocument>();
    Parser parser = new Parser(properties);
    start = System.currentTimeMillis();
    parser.parse(FileUtil.getDumpFileName(properties), list);
   
    System.out.println("Finished parsing: " + (System.currentTimeMillis() - start));
    Map<INDEXFIELD, Tokenizer> tknizerMap;
    ExecutorService svc = Executors.newSingleThreadExecutor();
    CompletionService<IndexableDocument> pool = new ExecutorCompletionService<IndexableDocument>(svc);
View Full Code Here
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
  /**
   * Test method for {@link edu.buffalo.cse.ir.wikiindexer.parsers.Parser#parse(java.lang.String, java.util.Collection)}.
   */
  @Test
  public final void testParse() {
    Parser testClass = new Parser(idxProps);
    ArrayList<WikipediaDocument> list = new ArrayList<WikipediaDocument>();
   
    //null file
    testClass.parse(null, list);
    assertTrue(list.isEmpty());
   
    //empty filename
    testClass.parse("", list);
    assertTrue(list.isEmpty());
   
    //invalid filename
    testClass.parse("abc.xml", list);
    assertTrue(list.isEmpty());
   
    //five documents
    testClass.parse(FileUtil.getRootFilesFolder(idxProps) + "five_entries.xml", list);
    assertEquals(5, list.size());
   
    /* TODO: Add structural test here */
    int cnt = 0;
    for (WikipediaDocument doc : list) {
View Full Code Here
TOP

Related Classes of edu.buffalo.cse.ir.wikiindexer.parsers.Parser

  • edu.buffalo.cse.ir.wikiindexer.parsers.test.ParserTest
  • edu.buffalo.cse.ir.wikiindexer.Runner$ParserRunner
  • edu.buffalo.cse.ir.wikiindexer.SingleRunner
  • edu.buffalo.cse.ir.wikiindexer.wikipedia.WikipediaDocument
  • edu.buffalo.cse.ir.wikiindexer.wikipedia.WikipediaParser
  • org.xml.sax.helpers.DefaultHandler
  • javax.xml.parsers.SAXParserFactory
  • javax.xml.parsers.SAXParser
    • 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.