Package it.unimi.dsi.mg4j.document

Examples of it.unimi.dsi.mg4j.document.StringArrayDocumentCollection

22
23
24
25
26
27
28
29
30
31
32
  public void testSkipToBeyondUsedClusters() throws Exception {
    /* We test what happens when we skip to a document belonging to a local index larger
     * than any index in which the term appears. */
   
    final String basename = File.createTempFile( getClass().getSimpleName(), "test" ).getCanonicalPath();
        new IndexBuilder( basename, new StringArrayDocumentCollection( "A B", "B", "A", "A" ) ).run();
    BinIO.storeObject( DocumentalStrategies.uniform( 2, 4 ), basename + "-strategy" );
    new PartitionDocumentally( basename + "-text", basename + "-cluster", DocumentalStrategies.uniform( 2, 4 ), basename + "-strategy", 0, 1024, CompressionFlags.DEFAULT_STANDARD_INDEX, true, false, 0, 0, 0, ProgressLogger.DEFAULT_LOG_INTERVAL ).run();
    FileLinesCollection flc;
    flc = new FileLinesCollection( basename + "-cluster-0.terms", "ASCII" );
    BinIO.storeObject( new ShiftAddXorSignedStringMap( flc.iterator(), new MWHCFunction<CharSequence>( flc , TransformationStrategies.utf16() ) ), basename + "-cluster-0.termmap" ); 
View Full Code Here
29
30
31
32
33
34
35
36
  private BitStreamIndex index;
  private String basename;

  public void setUp() throws ConfigurationException, SecurityException, IOException, URISyntaxException, ClassNotFoundException, InstantiationException, IllegalAccessException, InvocationTargetException, NoSuchMethodException {
    basename = File.createTempFile( getClass().getSimpleName(), "test" ).getCanonicalPath();
    new IndexBuilder( basename, new StringArrayDocumentCollection( "a", "b", "c" ) ).run();
    index = DiskBasedIndex.getInstance( basename + "-text", true, true );
  }
View Full Code Here
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
    titleBasename = File.createTempFile( ScorerTest.class.getSimpleName(), "title", tempDir ).toString();
    bodyFBasename = File.createTempFile( ScorerTest.class.getSimpleName(), "bodyf", tempDir ).toString();
    titleFBasename = File.createTempFile( ScorerTest.class.getSimpleName(), "titlef", tempDir ).toString();
    basenameFComb = File.createTempFile( ScorerTest.class.getSimpleName(), "combf", tempDir ).toString();
    bodyBasenameBis = File.createTempFile( ScorerTest.class.getSimpleName(), "bodyfbis", tempDir ).toString();
    documentCollection0 = new StringArrayDocumentCollection(
        // number of documents N = 3
        // average document size = 9 + 4 + 14 / 3 = 9
        // number of occurrences = 27
        new String[] {
            "This sentence speaks really really really good of gods", // size 9
            "And this, is a list of all the green things in the green world", // size 14
            "get THIS not THAT" } // size 4
        );

    // BM25 testing

    bodyDocumentCollection = new StringArrayDocumentCollection(
        new String[] {
            "A C C",
            "D Z",
            "A X Z",
            "C X X",
            "Q",
        }
    );
   
    // Doc size: 3 2 3 3 1 (avg: 12/5)
    // Frequency: A:2 C:2 D:1 Q:1 X:2 Z:2

    titleDocumentCollection = new StringArrayDocumentCollection(
        new String[] {
            "A",
            "Q",
            "Z",
            "Q X",
            "Z",
        }
    );
   
    // Doc size: 1 1 1 2 1 (avg: 9/8)
    // Frequency: A:1 Q:2 X:1 Z:2
    
    // BM25F testing

    bodyFDocumentCollection = new StringArrayDocumentCollection(
        new String[] {
            "A C C",
            "D Z",
            "A X Z",
            "C X X",
            "Q",
            "1",
            "1",
            "1"
        }
    );
   
    // Doc size: 3 2 3 3 1 (avg: 12/5)
    // Frequency: A:2 C:2 D:1 Q:1 X:2 Z:2

    titleFDocumentCollection = new StringArrayDocumentCollection(
        new String[] {
            "A",
            "Q",
            "Z",
            "Q X",
View Full Code Here
TOP

Related Classes of it.unimi.dsi.mg4j.document.StringArrayDocumentCollection

  • it.unimi.dsi.fastutil.io.FastByteArrayInputStream
  • it.unimi.dsi.mg4j.index.cluster.DocumentalConcatenatedClusterDocumentIteratorTest
  • it.unimi.dsi.mg4j.index.MultiTermIndexIteratorTest
  • it.unimi.dsi.mg4j.search.BitStreamIndexReaderTest
  • it.unimi.dsi.mg4j.search.OrderedAndDocumentIteratorTest
  • it.unimi.dsi.mg4j.search.OrDocumentIteratorTest
  • it.unimi.dsi.mg4j.search.RemappingDocumentIteratorTest
  • it.unimi.dsi.mg4j.search.score.ScorerTest
  • it.unimi.dsi.mg4j.search.TrueFalseDocumentIteratorTest
  • it.unimi.dsi.mg4j.search.WeightTest
    • 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.