public void testBOMMarkers() throws Exception {
final String fileWithBom = "stopwithbom.txt";
SolrResourceLoader loader = new SolrResourceLoader("solr/collection1");
// preliminary sanity check
InputStream bomStream = loader.openResource(fileWithBom);
try {
final byte[] bomExpected = new byte[] {-17, -69, -65};
final byte[] firstBytes = new byte[3];
assertEquals(
"Should have been able to read 3 bytes from bomStream", 3, bomStream.read(firstBytes));
assertTrue(
"This test only works if "
+ fileWithBom
+ " contains a BOM -- it appears someone removed it.",
Arrays.equals(bomExpected, firstBytes));
} finally {
try {
bomStream.close();
} catch (Exception e) {
/* IGNORE */
}
}
// now make sure getLines skips the BOM...
List<String> lines = loader.getLines(fileWithBom);
assertEquals(1, lines.size());
assertEquals("BOMsAreEvil", lines.get(0));
}
public void testWrongEncoding() throws Exception {
String wrongEncoding = "stopwordsWrongEncoding.txt";
SolrResourceLoader loader = new SolrResourceLoader("solr/collection1");
// ensure we get our exception
try {
List<String> lines = loader.getLines(wrongEncoding);
fail();
} catch (SolrException expected) {
assertTrue(expected.getCause() instanceof CharacterCodingException);
}
}
