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

Introduction

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

Prototype

public abstract void initialize(InputSplit split, TaskAttemptContext context)
        throws IOException, InterruptedException;

Source Link

Document

Called once at initialization.

Usage

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

License:Apache License

@Test
public void readExcelInputFormatExcel2003Empty() throws IOException, InterruptedException {
    Configuration conf = new Configuration(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2003empty.xls";
    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);//ww w.ja va 2  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");
    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");
}

---

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

License:Apache License

@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);//w ww  .  j a v  a  2  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");
    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");
}

---

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

License:Apache License

@Test
public void readExcelInputFormatExcel2003SingleSheet() throws IOException, InterruptedException {
    Configuration conf = new Configuration(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2003test.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");
    Job job = Job.getInstance(conf);/*from   w w w . j  av  a2 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("[excel2003test.xls]Sheet1!A1", spreadSheetKey.toString(),
            "Input Split for Excel file has keyname == \"[excel2003test.xls]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 readExcelInputFormatExcel2013SingleSheetEncryptedPositive()
        throws IOException, InterruptedException {
    Configuration conf = new Configuration(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2013encrypt.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");
    // for decryption simply set the password
    conf.set("hadoopoffice.read.security.crypt.password", "test");
    Job job = Job.getInstance(conf);//from   www .  j  a  v  a 2s .  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("[excel2013encrypt.xlsx]Sheet1!A1", spreadSheetKey.toString(),
            "Input Split for Excel file has keyname == \"[excel2013encrypt.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\"");
}

---

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

License:Apache License

@Test
public void readExcelInputFormatExcel2013SingleSheetEncryptedNegative()
        throws IOException, InterruptedException {
    Configuration conf = new Configuration(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2013encrypt.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");
    // for decryption simply set the password
    conf.set("hadoopoffice.read.security.crypt.password", "test2");
    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);

    InterruptedException ex = assertThrows(InterruptedException.class,
            () -> reader.initialize(splits.get(0), context), "Exception is thrown in case of wrong password");
}

---

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

License:Apache License

@Test
public void readExcelInputFormatExcel2003SingleSheetEncryptedPositive()
        throws IOException, InterruptedException {
    Configuration conf = new Configuration(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2003encrypt.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");
    // for decryption simply set the password
    conf.set("hadoopoffice.read.security.crypt.password", "test");
    Job job = Job.getInstance(conf);/*  w  w  w .j  av  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");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals("[excel2003encrypt.xls]Sheet1!A1", spreadSheetKey.toString(),
            "Input Split for Excel file has keyname == \"[excel2003encrypt.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\"");
}

---

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

License:Apache License

@Test
public void readExcelInputFormatExcel2003SingleSheetEncryptedNegative()
        throws IOException, InterruptedException {
    Configuration conf = new Configuration(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2003encrypt.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");
    // for decryption simply set the password
    conf.set("hadoopoffice.read.security.crypt.password", "test2");
    Job job = Job.getInstance(conf);/*from w w  w .  j  ava  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);
    InterruptedException ex = assertThrows(InterruptedException.class,
            () -> reader.initialize(splits.get(0), context), "Exception is thrown in case of wrong password");
}

---

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

License:Apache License

@Test
public void readExcelInputFormatExcel2013EmptyRows() throws IOException, InterruptedException {
    Configuration conf = new Configuration(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2013testemptyrows.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  ww.  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");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals("[excel2013testemptyrows.xlsx]Sheet1!A1", spreadSheetKey.toString(),
            "Input Split for Excel file has keyname == \"[excel2013testemptyrows.xlsx]Sheet1!A1\"");
    assertEquals(0, spreadSheetValue.get().length, "Input Split for Excel file contains row 1 with 0 columns");

    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 2 with 2 columns");
    assertEquals("4", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 2 with cell 1 == \"4\"");
    assertEquals("1", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 2 with cell 1 == \"1\"");
    assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 3");
    spreadSheetKey = reader.getCurrentKey();
    spreadSheetValue = reader.getCurrentValue();
    assertEquals(0, spreadSheetValue.get().length, "Input Split for Excel file contains row 3 with 0 columns");

    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("10", ((SpreadSheetCellDAO) spreadSheetValue.get()[2]).getFormattedValue(),
            "Input Split for Excel file contains row 6 with cell 3== \"10\"");
}

---

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);//  w w  w. j  av  a2  s.  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("[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   ww w  . j  a  v  a 2 s.c om
    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");
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• »