Examples with TrecForwardIndex edu.umd.cloud9.collection.trec.TrecForwardIndex used on opensource projects

Example 1 with TrecForwardIndex

use of edu.umd.cloud9.collection.trec.TrecForwardIndex in project Cloud9 by lintool.

the class IT method testForwardIndex.

private void testForwardIndex() throws Exception {
    Configuration conf = IntegrationUtils.getBespinConfiguration();
    FileSystem fs = FileSystem.get(conf);
    assertTrue(fs.exists(collectionPath));
    String index = tmpPrefix + "-findex.dat";
    String[] args = new String[] { "hadoop jar", IntegrationUtils.getJar("target", "cloud9"), edu.umd.cloud9.collection.trec.TrecForwardIndexBuilder.class.getCanonicalName(), "-collection=" + collectionPath, "-index=" + index, "-docnoMapping=" + mappingFile };
    IntegrationUtils.exec(Joiner.on(" ").join(args));
    TrecForwardIndex findex = new TrecForwardIndex();
    findex.loadIndex(new Path(index), new Path(mappingFile), fs);
    assertTrue(findex.getDocument(1).getContent().contains("Newspapers in the Former Yugoslav Republic"));
    assertTrue(findex.getDocument("FBIS3-1").getContent().contains("Newspapers in the Former Yugoslav Republic"));
    assertEquals(1, findex.getFirstDocno());
    assertEquals(472525, findex.getLastDocno());
}