* Test the LazySimpleSerDe class.
*/
public void testRegexSerDe() throws Throwable {
try {
// Create the SerDe
SerDe serDe = createSerDe(
"host,identity,user,time,request,status,size,referer,agent",
"string,string,string,string,string,string,string,string,string",
"([^ ]*) ([^ ]*) ([^ ]*) (-|\\[[^\\]]*\\]) ([^ \"]*|\"[^\"]*\") "
+ "([0-9]*) ([0-9]*) ([^ \"]*|\"[^\"]*\") ([^ \"]*|\"[^\"]*\")",
"%1$s %2$s %3$s %4$s %5$s %6$s %7$s %8$s %9$s");
// Data
Text t = new Text(
"127.0.0.1 - - [26/May/2009:00:00:00 +0000] "
+ "\"GET /someurl/?track=Blabla(Main) HTTP/1.1\" 200 5864 - "
+ "\"Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) "
+ "AppleWebKit/525.19 (KHTML, like Gecko) Chrome/1.0.154.65 Safari/525.19\"");
// Deserialize
Object row = serDe.deserialize(t);
ObjectInspector rowOI = serDe.getObjectInspector();
System.out.println("Deserialized row: " + row);
// Serialize
Text serialized = (Text) serDe.serialize(row, rowOI);
assertEquals(t, serialized);
// Do some changes (optional)
ObjectInspector standardWritableRowOI = ObjectInspectorUtils
.getStandardObjectInspector(rowOI, ObjectInspectorCopyOption.WRITABLE);
Object standardWritableRow = ObjectInspectorUtils.copyToStandardObject(
row, rowOI, ObjectInspectorCopyOption.WRITABLE);
// Serialize
serialized = (Text) serDe.serialize(standardWritableRow,
standardWritableRowOI);
assertEquals(t, serialized);
} catch (Throwable e) {
e.printStackTrace();