Example usage for org.apache.hadoop.mapreduce RecordReader nextKeyValue

Introduction

In this page you can find the example usage for org.apache.hadoop.mapreduce RecordReader nextKeyValue.

Prototype

public abstract boolean nextKeyValue() throws IOException, InterruptedException;

Source Link

Document

Read the next key, value pair.

Usage

From source file:org.zuinnote.hadoop.office.format.mapreduce.OfficeFormatHadoopExcelNormalTest.java

License:Apache License

@Test
public void readExcelInputFormatExcel2013SingleSheet() throws IOException, InterruptedException {
    Configuration conf = new Configuration(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2013test.xlsx";
    String fileNameSpreadSheet = classLoader.getResource(fileName).getFile();
    Path file = new Path(fileNameSpreadSheet);

    // set locale to the one of the test data
    conf.set("hadoopoffice.read.locale.bcp47", "de");
    Job job = Job.getInstance(conf);//from   w w  w  . j  a v a  2 s  .co  m
    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("[excel2013test.xlsx]Sheet1!A1", spreadSheetKey.toString(),
            "Input Split for Excel file has keyname == \"[excel2013test.xlsx]Sheet1!A1\"");
    assertEquals(4, spreadSheetValue.get().length, "Input Split for Excel file contains row 1 with 4 columns");
    assertEquals("test1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 1 == \"test1\"");
    assertEquals("Sheet1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getSheetName(),
            "Input Split for Excel file contains row 1 with cell 1 sheetname == \"Sheet1\"");
    assertEquals("A1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getAddress(),
            "Input Split for Excel file contains row 1 with cell 1 address == \"A1\"");
    assertEquals("test2", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 2 == \"test2\"");
    assertEquals("test3", ((SpreadSheetCellDAO) spreadSheetValue.get()[2]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 3 == \"test3\"");
    assertEquals("test4", ((SpreadSheetCellDAO) spreadSheetValue.get()[3]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 4 == \"test4\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 2");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(1, spreadSheetValue.get().length, "Input Split for Excel file contains row 2 with 1 column");
    assertEquals("4", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 2 with cell 1 == \"4\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 3");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(5, spreadSheetValue.get().length, "Input Split for Excel file contains row 3 with 5 columns");
    assertEquals("31/12/99", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 3 with cell 1 == \"31/12/99\"");
    assertEquals("5", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 3 with cell 2 == \"5\"");
    assertNull(spreadSheetValue.get()[2], "Input Split for Excel file contains row 3 with cell 3 == null");
    assertNull(spreadSheetValue.get()[3], "Input Split for Excel file contains row 3 with cell 4 == null");
    assertEquals("null", ((SpreadSheetCellDAO) spreadSheetValue.get()[4]).getFormattedValue(),
            "Input Split for Excel file contains row 3 with cell 5 == \"null\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 4");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(1, spreadSheetValue.get().length, "Input Split for Excel file contains row 4 with 1 column");
    assertEquals("1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 4 with cell 1 == \"1\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 5");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(3, spreadSheetValue.get().length, "Input Split for Excel file contains row 5 with 3 columns");
    assertEquals("2", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 5 with cell 1 == \"2\"");
    assertEquals("6", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 5 with cell 2== \"6\"");
    assertEquals("10", ((SpreadSheetCellDAO) spreadSheetValue.get()[2]).getFormattedValue(),
            "Input Split for Excel file contains row 5 with cell 3== \"10\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 6");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(3, spreadSheetValue.get().length, "Input Split for Excel file contains row 6 with 3 columns");
    assertEquals("3", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 6 with cell 1 == \"3\"");
    assertEquals("4", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 6 with cell 2== \"4\"");
    assertEquals("15", ((SpreadSheetCellDAO) spreadSheetValue.get()[2]).getFormattedValue(),
            "Input Split for Excel file contains row 6 with cell 3== \"15\"");
}

---

From source file:org.zuinnote.hadoop.office.format.mapreduce.OfficeFormatHadoopExcelNormalTest.java

License:Apache License

@Test
public void readExcelCellInputFormatExcel2013SingleSheet() throws IOException, InterruptedException {
    Configuration conf = new Configuration(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2013test.xlsx";
    String fileNameSpreadSheet = classLoader.getResource(fileName).getFile();
    Path file = new Path(fileNameSpreadSheet);

    // set locale to the one of the test data
    conf.set("hadoopoffice.read.locale.bcp47", "de");
    Job job = Job.getInstance(conf);//from   w ww .java 2s  . co m
    FileInputFormat.setInputPaths(job, file);
    TaskAttemptContext context = new TaskAttemptContextImpl(conf, new TaskAttemptID());
    ExcelCellFileInputFormat format = new ExcelCellFileInputFormat();
    List<InputSplit> splits = format.getSplits(job);
    assertEquals(1, splits.size(), "Only one split generated for Excel file");
    RecordReader<Text, SpreadSheetCellDAO> reader = format.createRecordReader(splits.get(0), context);
    assertNotNull(reader, "Format returned  null RecordReader");
    reader.initialize(splits.get(0), context);
    Text spreadSheetKey = new Text();
    SpreadSheetCellDAO spreadSheetValue = new SpreadSheetCellDAO();
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains cell");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals("[excel2013test.xlsx]Sheet1!A1", spreadSheetKey.toString(),
            "Input Split for Excel file has keyname == \"[excel2013test.xlsx]Sheet1!A1\"");
    assertEquals("test1", ((SpreadSheetCellDAO) spreadSheetValue).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 1 == \"test1\"");
    assertEquals("Sheet1", ((SpreadSheetCellDAO) spreadSheetValue).getSheetName(),
            "Input Split for Excel file contains row 1 with cell 1 sheetname == \"Sheet1\"");
    assertEquals("A1", ((SpreadSheetCellDAO) spreadSheetValue).getAddress(),
            "Input Split for Excel file contains row 1 with cell 1 address == \"A1\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains cell");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals("test2", ((SpreadSheetCellDAO) spreadSheetValue).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 2 == \"test2\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains cell");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals("test3", ((SpreadSheetCellDAO) spreadSheetValue).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 3 == \"test3\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains cell");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals("test4", ((SpreadSheetCellDAO) spreadSheetValue).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 4 == \"test4\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains cell");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals("4", ((SpreadSheetCellDAO) spreadSheetValue).getFormattedValue(),
            "Input Split for Excel file contains row 2 with cell 1 == \"4\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains cell");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals("31/12/99", ((SpreadSheetCellDAO) spreadSheetValue).getFormattedValue(),
            "Input Split for Excel file contains row 3 with cell 1 == \"31/12/99\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains cell");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals("5", ((SpreadSheetCellDAO) spreadSheetValue).getFormattedValue(),
            "Input Split for Excel file contains row 3 with cell 2 == \"5\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains cell");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals("null", ((SpreadSheetCellDAO) spreadSheetValue).getFormattedValue(),
            "Input Split for Excel file contains row 3 with cell 5 == \"null\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains cell");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals("1", ((SpreadSheetCellDAO) spreadSheetValue).getFormattedValue(),
            "Input Split for Excel file contains row 4 with cell 1 == \"1\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains cell");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals("2", ((SpreadSheetCellDAO) spreadSheetValue).getFormattedValue(),
            "Input Split for Excel file contains row 5 with cell 1 == \"2\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains cell");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals("6", ((SpreadSheetCellDAO) spreadSheetValue).getFormattedValue(),
            "Input Split for Excel file contains row 5 with cell 2== \"6\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains cell");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals("10", ((SpreadSheetCellDAO) spreadSheetValue).getFormattedValue(),
            "Input Split for Excel file contains row 5 with cell 3== \"10\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains cell");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals("3", ((SpreadSheetCellDAO) spreadSheetValue).getFormattedValue(),
            "Input Split for Excel file contains row 6 with cell 1 == \"3\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains cell");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals("4", ((SpreadSheetCellDAO) spreadSheetValue).getFormattedValue(),
            "Input Split for Excel file contains row 6 with cell 2== \"4\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains cell");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals("15", ((SpreadSheetCellDAO) spreadSheetValue).getFormattedValue(),
            "Input Split for Excel file contains row 6 with cell 3== \"15\"");
    assertFalse(reader.nextKeyValue(), "No more cells");
}

---

From source file:org.zuinnote.hadoop.office.format.mapreduce.OfficeFormatHadoopExcelNormalTest.java

License:Apache License

@Test
public void readExcelInputFormatExcel2013MultiSheetAll() throws IOException, InterruptedException {
    Configuration conf = new Configuration(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2013testmultisheet.xlsx";
    String fileNameSpreadSheet = classLoader.getResource(fileName).getFile();
    Path file = new Path(fileNameSpreadSheet);

    // set locale to the one of the test data
    conf.set("hadoopoffice.read.locale.bcp47", "de");
    Job job = Job.getInstance(conf);//w  w  w .ja  v  a  2 s.  c  o  m
    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 (first sheet)");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals("[excel2013testmultisheet.xlsx]Sheet1!A1", spreadSheetKey.toString(),
            "Input Split for Excel file has keyname == \"[excel2013testmultisheet.xlsx]Sheet1!A1\"");
    assertEquals(4, spreadSheetValue.get().length, "Input Split for Excel file contains row 1 with 4 columns");
    assertEquals("test1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 1 == \"test1\"");
    assertEquals("Sheet1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getSheetName(),
            "Input Split for Excel file contains row 1 with cell 1 sheetname == \"Sheet1\"");
    assertEquals("A1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getAddress(),
            "Input Split for Excel file contains row 1 with cell 1 address == \"A1\"");
    assertEquals("test2", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 2 == \"test2\"");
    assertEquals("test3", ((SpreadSheetCellDAO) spreadSheetValue.get()[2]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 3 == \"test3\"");
    assertEquals("test4", ((SpreadSheetCellDAO) spreadSheetValue.get()[3]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 4 == \"test4\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 2 (first sheet)");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(1, spreadSheetValue.get().length, "Input Split for Excel file contains row 2 with 1 column");
    assertEquals("4", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 2 with cell 1 == \"4\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 3 (first sheet)");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(5, spreadSheetValue.get().length, "Input Split for Excel file contains row 3 with 5 columns");
    assertEquals("31/12/99", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 3 with cell 1 == \"31/12/99\"");
    assertEquals("5", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 3 with cell 2 == \"5\"");
    assertNull(spreadSheetValue.get()[2], "Input Split for Excel file contains row 3 with cell 3 == null");
    assertNull(spreadSheetValue.get()[3], "Input Split for Excel file contains row 3 with cell 4 == null");
    assertEquals("null", ((SpreadSheetCellDAO) spreadSheetValue.get()[4]).getFormattedValue(),
            "Input Split for Excel file contains row 3 with cell 5 == \"null\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 4 (first sheet)");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(1, spreadSheetValue.get().length, "Input Split for Excel file contains row 4 with 1 column");
    assertEquals("1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 4 with cell 1 == \"1\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 5 (first sheet)");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(3, spreadSheetValue.get().length, "Input Split for Excel file contains row 5 with 3 columns");
    assertEquals("2", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 5 with cell 1 == \"2\"");
    assertEquals("6", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 5 with cell 2== \"6\"");
    assertEquals("10", ((SpreadSheetCellDAO) spreadSheetValue.get()[2]).getFormattedValue(),
            "Input Split for Excel file contains row 5 with cell 3== \"10\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 6 (first sheet)");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(3, spreadSheetValue.get().length, "Input Split for Excel file contains row 6 with 3 columns");
    assertEquals("3", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 6 with cell 1 == \"3\"");
    assertEquals("4", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 6 with cell 2== \"4\"");
    assertEquals("15", ((SpreadSheetCellDAO) spreadSheetValue.get()[2]).getFormattedValue(),
            "Input Split for Excel file contains row 6 with cell 3== \"15\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 7 (second sheet)");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals("8", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 7 with cell 1 == \"8\"");
    assertEquals("99", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 7 with cell 2 == \"99\"");
    assertEquals(2, spreadSheetValue.get().length, "Input Split for Excel file contains row 7 with 2 columns");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 8 (second sheet)");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(1, spreadSheetValue.get().length, "Input Split for Excel file contains row 8 with 1 column");
    assertEquals("test", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 8 with cell 1 == \"test\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 9 (second sheet)");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(3, spreadSheetValue.get().length, "Input Split for Excel file contains row 9 with 3 columns");
    assertNull(spreadSheetValue.get()[0], "Input Split for Excel file contains row 9 with cell 1 == null");
    assertNull(spreadSheetValue.get()[1], "Input Split for Excel file contains row 9 with cell 2 == null");
    assertEquals("seven", ((SpreadSheetCellDAO) spreadSheetValue.get()[2]).getFormattedValue(),
            "Input Split for Excel file contains row 9 with cell 3 == \"seven\"");
}

---

From source file:org.zuinnote.hadoop.office.format.mapreduce.OfficeFormatHadoopExcelNormalTest.java

License:Apache License

@Test
public void readExcelInputFormatExcel2013MultiSheetSelectedSheet() throws IOException, InterruptedException {
    Configuration conf = new Configuration(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2013testmultisheet.xlsx";
    String fileNameSpreadSheet = classLoader.getResource(fileName).getFile();
    Path file = new Path(fileNameSpreadSheet);

    // set locale to the one of the test data
    conf.set("hadoopoffice.read.locale.bcp47", "de");
    // select the sheet
    conf.set("hadoopoffice.read.sheets", "testsheet");
    Job job = Job.getInstance(conf);/*from  w  w w. ja  v a2 s. c  o m*/
    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 7 (second sheet)");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals("8", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 7 with cell 1 == \"8\"");
    assertEquals("99", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 7 with cell 2 == \"99\"");
    assertEquals(2, spreadSheetValue.get().length, "Input Split for Excel file contains row 7 with 2 columns");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 8 (second sheet)");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(1, spreadSheetValue.get().length, "Input Split for Excel file contains row 8 with 1 column");
    assertEquals("test", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 8 with cell 1 == \"test\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 9 (second sheet)");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(3, spreadSheetValue.get().length, "Input Split for Excel file contains row 9 with 3 columns");
    assertNull(spreadSheetValue.get()[0], "Input Split for Excel file contains row 9 with cell 1 == null");
    assertNull(spreadSheetValue.get()[1], "Input Split for Excel file contains row 9 with cell 2 == null");
    assertEquals("seven", ((SpreadSheetCellDAO) spreadSheetValue.get()[2]).getFormattedValue(),
            "Input Split for Excel file contains row 9 with cell 3 == \"seven\"");
}

---

From source file:org.zuinnote.hadoop.office.format.mapreduce.OfficeFormatHadoopExcelNormalTest.java

License:Apache License

@Test
public void readExcelInputFormatExcel2013Comment() throws IOException, InterruptedException {
    Configuration conf = new Configuration(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2013comment.xlsx";
    String fileNameSpreadSheet = classLoader.getResource(fileName).getFile();

    // set locale to the one of the test data
    conf.set("hadoopoffice.read.locale.bcp47", "de");
    Path file = new Path(fileNameSpreadSheet);
    Job job = Job.getInstance(conf);/*from   w w w.ja  v  a2s  .com*/
    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("[excel2013comment.xlsx]CommentSheet!A1", spreadSheetKey.toString(),
            "Input Split for Excel file has keyname == \"[excel2013comment.xlsx]CommentSheet!A1\"");
    assertEquals(3, spreadSheetValue.get().length, "Input Split for Excel file contains row 1 with 3 columns");
    assertEquals("test1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 1 == \"test1\"");
    assertEquals("First comment", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getComment(),
            "Input Split for Excel file contains row 1 with cell 1 comment == \"First comment\"");
    assertEquals("CommentSheet", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getSheetName(),
            "Input Split for Excel file contains row 1 with cell 1 sheetname == \"CommentSheet\"");
    assertEquals("A1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getAddress(),
            "Input Split for Excel file contains row 1 with cell 1 address == \"A1\"");
    assertEquals("test3", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 2 == \"test3\"");
    assertEquals("test3", ((SpreadSheetCellDAO) spreadSheetValue.get()[2]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 3 == \"test3\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 2");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(1, spreadSheetValue.get().length, "Input Split for Excel file contains row 2 with 1 column");
    assertEquals("4", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 2 with cell 1 == \"4\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 3");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(2, spreadSheetValue.get().length, "Input Split for Excel file contains row 3 with 2 columns");
    assertNull(spreadSheetValue.get()[0], "Input Split for Excel file contains row 3 with cell 1 == null");
    assertEquals("5", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 2 with cell 2 == \"5\"");
    assertEquals("Second comment", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getComment(),
            "Input Split for Excel file contains row 2 with cell 2 comment == \"Second comment\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 4");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(3, spreadSheetValue.get().length, "Input Split for Excel file contains row 4 with 3 column");
    assertNull(spreadSheetValue.get()[0], "Input Split for Excel file contains row 4 with cell 1 == null");
    assertNull(spreadSheetValue.get()[1], "Input Split for Excel file contains row 4 with cell 2 == null");
    assertEquals("6", ((SpreadSheetCellDAO) spreadSheetValue.get()[2]).getFormattedValue(),
            "Input Split for Excel file contains row 4 with cell 3 == \"6\"");
    assertEquals("Third comment", ((SpreadSheetCellDAO) spreadSheetValue.get()[2]).getComment(),
            "Input Split for Excel file contains row 4 with cell 3 comment == \"Third comment\"");
}

---

From source file:org.zuinnote.hadoop.office.format.mapreduce.OfficeFormatHadoopExcelNormalTest.java

License:Apache License

@Test
public void readExcelInputFormatGzipCompressedExcel2013MultiSheetAll()
        throws IOException, InterruptedException {
    Configuration conf = new Configuration(defaultConf);
    CompressionCodec gzip = new GzipCodec();
    ReflectionUtils.setConf(gzip, conf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2013testmultisheet.xlsx.gz";
    String fileNameSpreadSheet = classLoader.getResource(fileName).getFile();
    Path file = new Path(fileNameSpreadSheet);

    // set locale to the one of the test data
    conf.set("hadoopoffice.read.locale.bcp47", "de");
    Job job = Job.getInstance(conf);/*from w ww  .  j  a v a2  s  . c  om*/
    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 (first sheet)");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals("[excel2013testmultisheet.xlsx.gz]Sheet1!A1", spreadSheetKey.toString(),
            "Input Split for Excel file has keyname == \"[excel2013testmultisheet.xlsx.gz]Sheet1!A1\"");
    assertEquals(4, spreadSheetValue.get().length, "Input Split for Excel file contains row 1 with 4 columns");
    assertEquals("test1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 1 == \"test1\"");
    assertEquals("Sheet1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getSheetName(),
            "Input Split for Excel file contains row 1 with cell 1 sheetname == \"Sheet1\"");
    assertEquals("A1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getAddress(),
            "Input Split for Excel file contains row 1 with cell 1 address == \"A1\"");
    assertEquals("test2", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 2 == \"test2\"");
    assertEquals("test3", ((SpreadSheetCellDAO) spreadSheetValue.get()[2]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 3 == \"test3\"");
    assertEquals("test4", ((SpreadSheetCellDAO) spreadSheetValue.get()[3]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 4 == \"test4\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 2 (first sheet)");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(1, spreadSheetValue.get().length, "Input Split for Excel file contains row 2 with 1 column");
    assertEquals("4", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 2 with cell 1 == \"4\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 3 (first sheet)");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(5, spreadSheetValue.get().length, "Input Split for Excel file contains row 3 with 5 columns");
    assertEquals("31/12/99", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 3 with cell 1 == \"31/12/99\"");
    assertEquals("5", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 3 with cell 2 == \"5\"");
    assertNull(spreadSheetValue.get()[2], "Input Split for Excel file contains row 3 with cell 3 == null");
    assertNull(spreadSheetValue.get()[3], "Input Split for Excel file contains row 3 with cell 4 == null");
    assertEquals("null", ((SpreadSheetCellDAO) spreadSheetValue.get()[4]).getFormattedValue(),
            "Input Split for Excel file contains row 3 with cell 5 == \"null\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 4 (first sheet)");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(1, spreadSheetValue.get().length, "Input Split for Excel file contains row 4 with 1 column");
    assertEquals("1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 4 with cell 1 == \"1\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 5 (first sheet)");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(3, spreadSheetValue.get().length, "Input Split for Excel file contains row 5 with 3 columns");
    assertEquals("2", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 5 with cell 1 == \"2\"");
    assertEquals("6", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 5 with cell 2== \"6\"");
    assertEquals("10", ((SpreadSheetCellDAO) spreadSheetValue.get()[2]).getFormattedValue(),
            "Input Split for Excel file contains row 5 with cell 3== \"10\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 6 (first sheet)");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(3, spreadSheetValue.get().length, "Input Split for Excel file contains row 6 with 3 columns");
    assertEquals("3", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 6 with cell 1 == \"3\"");
    assertEquals("4", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 6 with cell 2== \"4\"");
    assertEquals("15", ((SpreadSheetCellDAO) spreadSheetValue.get()[2]).getFormattedValue(),
            "Input Split for Excel file contains row 6 with cell 3== \"15\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 7 (second sheet)");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals("8", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 7 with cell 1 == \"8\"");
    assertEquals("99", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 7 with cell 2 == \"99\"");
    assertEquals(2, spreadSheetValue.get().length, "Input Split for Excel file contains row 7 with 2 columns");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 8 (second sheet)");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(1, spreadSheetValue.get().length, "Input Split for Excel file contains row 8 with 1 column");
    assertEquals("test", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 8 with cell 1 == \"test\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 9 (second sheet)");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(3, spreadSheetValue.get().length, "Input Split for Excel file contains row 9 with 3 columns");
    assertNull(spreadSheetValue.get()[0], "Input Split for Excel file contains row 9 with cell 1 == null");
    assertNull(spreadSheetValue.get()[1], "Input Split for Excel file contains row 9 with cell 2 == null");
    assertEquals("seven", ((SpreadSheetCellDAO) spreadSheetValue.get()[2]).getFormattedValue(),
            "Input Split for Excel file contains row 9 with cell 3 == \"seven\"");
}

---

From source file:org.zuinnote.hadoop.office.format.mapreduce.OfficeFormatHadoopExcelNormalTest.java

License:Apache License

@Test
public void readExcelInputFormatExcel2013LinkedWorkbook() throws IOException, InterruptedException {
    Configuration conf = new Configuration(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2013linkedworkbooks.xlsx";
    String fileNameSpreadSheet = classLoader.getResource(fileName).getFile();
    Path file = new Path(fileNameSpreadSheet);

    // set locale to the one of the test data
    conf.set("hadoopoffice.read.locale.bcp47", "de");
    // enable option to read linked workbooks
    conf.setBoolean("hadoopoffice.read.linkedworkbooks", true);
    conf.setBoolean("hadoopoffice.read.ignoremissinglinkedworkbooks", false);
    Job job = Job.getInstance(conf);//from   ww  w .j a  v  a2s  . com
    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("[excel2013linkedworkbooks.xlsx]Sheet1!A1", spreadSheetKey.toString(),
            "Input Split for Excel file has keyname == \"[excel2013linkedworkbooks.xlsx]Sheet1!A1\"");
    assertEquals(3, spreadSheetValue.get().length, "Input Split for Excel file contains row 1 with 3 columns");
    assertEquals("test1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 1 == \"test1\"");
    assertEquals("Sheet1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getSheetName(),
            "Input Split for Excel file contains row 1 with cell 1 sheetname == \"Sheet1\"");
    assertEquals("A1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getAddress(),
            "Input Split for Excel file contains row 1 with cell 1 address == \"A1\"");
    assertEquals("test2", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 2 == \"test2\"");
    assertEquals("test3", ((SpreadSheetCellDAO) spreadSheetValue.get()[2]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 3 == \"test3\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 2");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(2, spreadSheetValue.get().length, "Input Split for Excel file contains row 1 with 2 columns");
    assertEquals("3", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 1 == \"3\" (this tests also if the cached value of 6 is ignored)");
    assertEquals("5", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 2 == \"5\"");

}

---

From source file:org.zuinnote.hadoop.office.format.mapreduce.OfficeFormatHadoopExcelNormalTest.java

License:Apache License

@Test
public void readExcelInputFormatExcel2013LinkedWorkbookAlternativeLocation()
        throws IOException, InterruptedException {
    Configuration conf = new Configuration(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2013linkedworkbooks.xlsx";
    String fileNameSpreadSheet = classLoader.getResource(fileName).getFile();
    Path file = new Path(fileNameSpreadSheet);
    // alternativeLocation
    String resourcePath = new File(classLoader.getResource(fileName).getFile()).getParent();
    String alternativeLocation = resourcePath + File.separator + "alternatelocationlinkedwb";
    // set locale to the one of the test data
    conf.set("hadoopoffice.read.locale.bcp47", "de");
    // enable option to read linked workbooks
    conf.setBoolean("hadoopoffice.read.linkedworkbooks", true);
    conf.setBoolean("hadoopoffice.read.ignoremissinglinkedworkbooks", false);
    conf.set("hadoopoffice.read.linkedworkbooks.location", alternativeLocation);
    Job job = Job.getInstance(conf);/*from  w ww .  ja  va  2s .c o  m*/
    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("[excel2013linkedworkbooks.xlsx]Sheet1!A1", spreadSheetKey.toString(),
            "Input Split for Excel file has keyname == \"[excel2013linkedworkbooks.xlsx]Sheet1!A1\"");
    assertEquals(3, spreadSheetValue.get().length, "Input Split for Excel file contains row 1 with 3 columns");
    assertEquals("test1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 1 == \"test1\"");
    assertEquals("Sheet1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getSheetName(),
            "Input Split for Excel file contains row 1 with cell 1 sheetname == \"Sheet1\"");
    assertEquals("A1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getAddress(),
            "Input Split for Excel file contains row 1 with cell 1 address == \"A1\"");
    assertEquals("test2", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 2 == \"test2\"");
    assertEquals("test3", ((SpreadSheetCellDAO) spreadSheetValue.get()[2]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 3 == \"test3\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 2");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(2, spreadSheetValue.get().length, "Input Split for Excel file contains row 1 with 2 columns");
    assertEquals("3", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 1 == \"3\" (this tests also if the cached value of 6 is ignored)");
    assertEquals("5", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 2 == \"5\"");

}

---

From source file:org.zuinnote.hadoop.office.format.mapreduce.OfficeFormatHadoopExcelNormalTest.java

License:Apache License

@Test
public void readExcelInputFormatExcel2003LinkedWorkbook() throws IOException, InterruptedException {
    Configuration conf = new Configuration(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2003linkedworkbooks.xls";
    String fileNameSpreadSheet = classLoader.getResource(fileName).getFile();
    Path file = new Path(fileNameSpreadSheet);

    // set locale to the one of the test data
    conf.set("hadoopoffice.read.locale.bcp47", "de");
    // enable option to read linked workbooks
    conf.setBoolean("hadoopoffice.read.linkedworkbooks", true);
    conf.setBoolean("hadoopoffice.read.ignoremissinglinkedworkbooks", false);
    Job job = Job.getInstance(conf);// w  w  w  .java2  s  .  c  o m
    TaskAttemptContext context = new TaskAttemptContextImpl(conf, new TaskAttemptID());
    FileInputFormat.setInputPaths(job, file);
    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("[excel2003linkedworkbooks.xls]Sheet1!A1", spreadSheetKey.toString(),
            "Input Split for Excel file has keyname == \"[excel2003linkedworkbooks.xls]Sheet1!A1\"");
    assertEquals(3, spreadSheetValue.get().length, "Input Split for Excel file contains row 1 with 3 columns");
    assertEquals("test1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 1 == \"test1\"");
    assertEquals("Sheet1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getSheetName(),
            "Input Split for Excel file contains row 1 with cell 1 sheetname == \"Sheet1\"");
    assertEquals("A1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getAddress(),
            "Input Split for Excel file contains row 1 with cell 1 address == \"A1\"");
    assertEquals("test2", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 2 == \"test2\"");
    assertEquals("test3", ((SpreadSheetCellDAO) spreadSheetValue.get()[2]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 3 == \"test3\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 2");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(2, spreadSheetValue.get().length, "Input Split for Excel file contains row 1 with 2 columns");
    assertEquals("3", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 1 == \"3\" (this tests also if the cached value of 6 is ignored)");
    assertEquals("5", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 2 == \"5\"");

}

---

From source file:org.zuinnote.hadoop.office.format.mapreduce.OfficeFormatHadoopExcelNormalTest.java

License:Apache License

@Test
public void readExcelInputFormatExcel2003LinkedWorkbookAlternativeLocation()
        throws IOException, InterruptedException {
    Configuration conf = new Configuration(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2003linkedworkbooks.xls";
    String fileNameSpreadSheet = classLoader.getResource(fileName).getFile();
    Path file = new Path(fileNameSpreadSheet);
    // alternativeLocation
    String resourcePath = new File(classLoader.getResource(fileName).getFile()).getParent();
    String alternativeLocation = resourcePath + File.separator + "alternatelocationlinkedwb";
    // set locale to the one of the test data
    conf.set("hadoopoffice.read.locale.bcp47", "de");
    // enable option to read linked workbooks
    conf.setBoolean("hadoopoffice.read.linkedworkbooks", true);
    conf.setBoolean("hadoopoffice.read.ignoremissinglinkedworkbooks", false);

    conf.set("hadoopoffice.read.linkedworkbooks.location", alternativeLocation);
    Job job = Job.getInstance(conf);/*from  ww w  .  jav a2  s  .  c o m*/
    TaskAttemptContext context = new TaskAttemptContextImpl(conf, new TaskAttemptID());
    FileInputFormat.setInputPaths(job, file);
    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("[excel2003linkedworkbooks.xls]Sheet1!A1", spreadSheetKey.toString(),
            "Input Split for Excel file has keyname == \"[excel2003linkedworkbooks.xls]Sheet1!A1\"");
    assertEquals(3, spreadSheetValue.get().length, "Input Split for Excel file contains row 1 with 3 columns");
    assertEquals("test1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 1 == \"test1\"");
    assertEquals("Sheet1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getSheetName(),
            "Input Split for Excel file contains row 1 with cell 1 sheetname == \"Sheet1\"");
    assertEquals("A1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getAddress(),
            "Input Split for Excel file contains row 1 with cell 1 address == \"A1\"");
    assertEquals("test2", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 2 == \"test2\"");
    assertEquals("test3", ((SpreadSheetCellDAO) spreadSheetValue.get()[2]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 3 == \"test3\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 2");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(2, spreadSheetValue.get().length, "Input Split for Excel file contains row 1 with 2 columns");
    assertEquals("3", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 1 == \"3\" (this tests also if the cached value of 6 is ignored)");
    assertEquals("5", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 1 with cell 2 == \"5\"");

}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• »