OfficeFormatHadoopExcelTest.java 文件源码

@Test
   public void readExcelInputFormatExcel2013Empty() throws IOException, InterruptedException {
    Configuration conf = new Configuration(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName="excel2013empty.xlsx";
    String fileNameSpreadSheet=classLoader.getResource(fileName).getFile(); 
    Path file = new Path(fileNameSpreadSheet);
// set locale to the one of the test data
conf.set("hadoopoffice.locale.bcp47","de");
Job job = Job.getInstance(conf);
    FileInputFormat.setInputPaths(job, file);
TaskAttemptContext context = new TaskAttemptContextImpl(conf, new TaskAttemptID());
    ExcelFileInputFormat format = new ExcelFileInputFormat();
    List<InputSplit> splits = format.getSplits(job);
    assertEquals( 1, splits.size(),"Only one split generated for Excel file");
    RecordReader<Text, ArrayWritable> reader = format.createRecordReader(splits.get(0), context);
assertNotNull( reader,"Format returned  null RecordReader");
reader.initialize(splits.get(0),context);
Text spreadSheetKey = new Text();   
ArrayWritable spreadSheetValue = new ArrayWritable(SpreadSheetCellDAO.class);
assertTrue( reader.nextKeyValue(),"Input Split for Excel file contains row 1");
spreadSheetKey=reader.getCurrentKey();
spreadSheetValue=reader.getCurrentValue();
assertEquals( 0,spreadSheetValue.get().length,"Input Split for Excel file contain row 1 and is empty"); 
assertFalse( reader.nextKeyValue(),"Input Split for Excel file contains no further row");           
   }