Example usage for org.apache.hadoop.io ArrayWritable get

Introduction

In this page you can find the example usage for org.apache.hadoop.io ArrayWritable get.

Prototype

public Writable[] get() 

Source Link

Usage

From source file:org.zuinnote.hadoop.office.format.mapred.OfficeFormatHadoopExcelLowFootPrintSAXTest.java

License:Apache License

@Test
public void readExcelInputFormatExcel2003SingleSheetLowFootprint() throws IOException {
    JobConf job = new JobConf(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2003test.xls";
    String fileNameSpreadSheet = classLoader.getResource(fileName).getFile();
    Path file = new Path(fileNameSpreadSheet);
    FileInputFormat.setInputPaths(job, file);
    // set locale to the one of the test data
    job.set("hadoopoffice.read.locale.bcp47", "de");
    // low footprint
    job.set("hadoopoffice.read.lowFootprint", "true");
    ExcelFileInputFormat format = new ExcelFileInputFormat();
    format.configure(job);/*from  w w w .j av  a2  s  .c o m*/
    InputSplit[] inputSplits = format.getSplits(job, 1);
    assertEquals(1, inputSplits.length, "Only one split generated for Excel file");
    RecordReader<Text, ArrayWritable> reader = format.getRecordReader(inputSplits[0], job, reporter);
    assertNotNull(reader, "Format returned  null RecordReader");
    Text spreadSheetKey = new Text();
    ArrayWritable spreadSheetValue = new ArrayWritable(SpreadSheetCellDAO.class);
    assertTrue(reader.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 1");
    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.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 2");
    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.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 3");
    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.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 4");
    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.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 5");
    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.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 6");
    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.mapred.OfficeFormatHadoopExcelLowFootPrintSAXTest.java

License:Apache License

@Test
public void readExcelInputFormatExcel2003MultiSheetAllLowFootPrint() throws IOException {
    JobConf job = new JobConf(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2003testmultisheet.xls";
    String fileNameSpreadSheet = classLoader.getResource(fileName).getFile();
    Path file = new Path(fileNameSpreadSheet);
    FileInputFormat.setInputPaths(job, file);
    // set locale to the one of the test data
    job.set("hadoopoffice.read.locale.bcp47", "de");

    // low footprint
    job.set("hadoopoffice.read.lowFootprint", "true");
    ExcelFileInputFormat format = new ExcelFileInputFormat();
    format.configure(job);/*from w  w w . jav  a2  s .  c o m*/
    InputSplit[] inputSplits = format.getSplits(job, 1);
    assertEquals(1, inputSplits.length, "Only one split generated for Excel file");
    RecordReader<Text, ArrayWritable> reader = format.getRecordReader(inputSplits[0], job, reporter);
    assertNotNull(reader, "Format returned  null RecordReader");
    Text spreadSheetKey = new Text();
    ArrayWritable spreadSheetValue = new ArrayWritable(SpreadSheetCellDAO.class);
    assertTrue(reader.next(spreadSheetKey, spreadSheetValue),
            "Input Split for Excel file contains row 1 (first sheet)");
    assertEquals("[excel2003testmultisheet.xls]Sheet1!A1", spreadSheetKey.toString(),
            "Input Split for Excel file has keyname == \"[excel2093testmultisheet.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.next(spreadSheetKey, spreadSheetValue),
            "Input Split for Excel file contains row 2 (first sheet)");
    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.next(spreadSheetKey, spreadSheetValue),
            "Input Split for Excel file contains row 3 (first sheet)");
    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.next(spreadSheetKey, spreadSheetValue),
            "Input Split for Excel file contains row 4 (first sheet)");
    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.next(spreadSheetKey, spreadSheetValue),
            "Input Split for Excel file contains row 5 (first sheet)");
    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.next(spreadSheetKey, spreadSheetValue),
            "Input Split for Excel file contains row 6 (first sheet)");
    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.next(spreadSheetKey, spreadSheetValue),
            "Input Split for Excel file contains row 7 (second sheet)");
    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.next(spreadSheetKey, spreadSheetValue),
            "Input Split for Excel file contains row 8 (second sheet)");
    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.next(spreadSheetKey, spreadSheetValue),
            "Input Split for Excel file contains row 9 (second sheet)");
    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.mapred.OfficeFormatHadoopExcelLowFootPrintSAXTest.java

License:Apache License

@Test
public void readExcelInputFormatExcel2013SingleSheetLowFootprint() throws IOException {
    JobConf job = new JobConf(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2013test.xlsx";
    String fileNameSpreadSheet = classLoader.getResource(fileName).getFile();
    Path file = new Path(fileNameSpreadSheet);
    FileInputFormat.setInputPaths(job, file);
    // set locale to the one of the test data
    job.set("hadoopoffice.read.locale.bcp47", "de");

    // low footprint
    job.set("hadoopoffice.read.lowFootprint", "true");

    job.set("hadoopoffice.read.lowFootprint.parser", "sax");
    ExcelFileInputFormat format = new ExcelFileInputFormat();
    format.configure(job);//from ww  w.  j ava 2s  .c o  m
    InputSplit[] inputSplits = format.getSplits(job, 1);
    assertEquals(1, inputSplits.length, "Only one split generated for Excel file");
    RecordReader<Text, ArrayWritable> reader = format.getRecordReader(inputSplits[0], job, reporter);
    assertNotNull(reader, "Format returned  null RecordReader");
    Text spreadSheetKey = new Text();
    ArrayWritable spreadSheetValue = new ArrayWritable(SpreadSheetCellDAO.class);
    assertTrue(reader.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 1");
    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.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 2");
    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.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 3");
    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.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 4");
    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.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 5");
    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.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 6");
    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.mapred.OfficeFormatHadoopExcelLowFootPrintSAXTest.java

License:Apache License

@Test
public void writeExcelOutputFormatExcel2013SingleSheetLowFootPrint() throws IOException {
    // one row string and three columns ("test1","test2","test3")
    // (String formattedValue, String comment, String formula, String address,String
    // sheetName)
    SpreadSheetCellDAO a1 = new SpreadSheetCellDAO("test1", "", "", "A1", "Sheet1");
    SpreadSheetCellDAO b1 = new SpreadSheetCellDAO("test2", "", "", "B1", "Sheet1");
    SpreadSheetCellDAO c1 = new SpreadSheetCellDAO("test3", "", "", "C1", "Sheet1");
    // empty row => nothing todo
    // one row numbers (1,2,3)
    SpreadSheetCellDAO a3 = new SpreadSheetCellDAO("", "", "1", "A3", "Sheet1");
    SpreadSheetCellDAO b3 = new SpreadSheetCellDAO("", "", "2", "B3", "Sheet1");
    SpreadSheetCellDAO c3 = new SpreadSheetCellDAO("", "", "3", "C3", "Sheet1");
    // one row formulas (=A3+B3)
    SpreadSheetCellDAO a4 = new SpreadSheetCellDAO("", "", "A3+B3", "A4", "Sheet1");
    // write/*  w ww .  j a  v  a 2  s .  c o m*/
    JobConf job = new JobConf(defaultConf);
    String fileName = "excel2013singlesheettestoutlowfootprint";
    String tmpDir = tmpPath.toString();
    Path outputPath = new Path(tmpDir);
    FileOutputFormat.setOutputPath(job, outputPath);
    // set generic outputformat settings
    job.set(JobContext.TASK_ATTEMPT_ID, attempt);
    // set locale to the one of the test data
    job.set("hadoopoffice.read.locale.bcp47", "de");
    // low footprint
    job.set("hadoopoffice.write.lowFootprint", "true");
    job.set("hadoopoffice.write.mimeType", "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"); // new
    // Excel
    // format,
    // anyway
    // default,
    // but
    // here
    // for
    // illustrative
    // purposes
    ExcelFileOutputFormat outputFormat = new ExcelFileOutputFormat();
    RecordWriter<NullWritable, SpreadSheetCellDAO> writer = outputFormat.getRecordWriter(null, job, fileName,
            null);
    assertNotNull(writer, "Format returned  null RecordWriter");
    writer.write(null, a1);
    writer.write(null, b1);
    writer.write(null, c1);
    writer.write(null, a3);
    writer.write(null, b3);
    writer.write(null, c3);
    writer.write(null, a4);
    writer.close(reporter);
    // try to read it again
    job = new JobConf(defaultConf);
    Path inputFile = new Path(tmpDir + File.separator + "_temporary" + File.separator + "0" + File.separator
            + "_temporary" + File.separator + attempt + File.separator + fileName + ".xlsx");
    FileInputFormat.setInputPaths(job, inputFile);
    // set locale to the one of the test data
    job.set("hadoopoffice.read.locale.bcp47", "de");
    ExcelFileInputFormat inputFormat = new ExcelFileInputFormat();
    inputFormat.configure(job);
    InputSplit[] inputSplits = inputFormat.getSplits(job, 1);
    assertEquals(1, inputSplits.length, "Only one split generated for Excel file");
    RecordReader<Text, ArrayWritable> reader = inputFormat.getRecordReader(inputSplits[0], job, reporter);
    assertNotNull(reader, "Format returned  null RecordReader");
    Text spreadSheetKey = new Text();
    ArrayWritable spreadSheetValue = new ArrayWritable(SpreadSheetCellDAO.class);
    assertTrue(reader.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 1");
    assertEquals("[" + fileName + ".xlsx]Sheet1!A1", spreadSheetKey.toString(),
            "Input Split for Excel file has keyname == \"[" + fileName + ".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("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.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 2");
    assertEquals(0, spreadSheetValue.get().length, "Input Split for Excel file contain row 2 and is empty");
    assertTrue(reader.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 3");
    assertEquals(3, spreadSheetValue.get().length, "Input Split for Excel file contain row 3 with 3 columns");
    assertEquals("1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 3 with cell 1 == \"1\"");
    assertEquals("2", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 3 with cell 2 == \"2\"");
    assertEquals("3", ((SpreadSheetCellDAO) spreadSheetValue.get()[2]).getFormattedValue(),
            "Input Split for Excel file contains row 3 with cell 3 == \"3\"");
    assertTrue(reader.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 4");
    assertEquals(1, spreadSheetValue.get().length, "Input Split for Excel file contain row 4 with 1 column");
    assertEquals("3", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 3 with cell 1 == \"3\"");
}

---

From source file:org.zuinnote.hadoop.office.format.mapred.OfficeFormatHadoopExcelLowFootPrintSAXTest.java

License:Apache License

@Test
public void writeExcelOutputFormatExcel2013SingleSheetEncryptedPositiveLowFootprint() throws IOException {
    // one row string and three columns ("test1","test2","test3")
    // (String formattedValue, String comment, String formula, String address,String
    // sheetName)
    SpreadSheetCellDAO a1 = new SpreadSheetCellDAO("test1", "", "", "A1", "Sheet1");
    SpreadSheetCellDAO b1 = new SpreadSheetCellDAO("test2", "", "", "B1", "Sheet1");
    SpreadSheetCellDAO c1 = new SpreadSheetCellDAO("test3", "", "", "C1", "Sheet1");
    // empty row => nothing todo
    // one row numbers (1,2,3)
    SpreadSheetCellDAO a3 = new SpreadSheetCellDAO("", "", "1", "A3", "Sheet1");
    SpreadSheetCellDAO b3 = new SpreadSheetCellDAO("", "", "2", "B3", "Sheet1");
    SpreadSheetCellDAO c3 = new SpreadSheetCellDAO("", "", "3", "C3", "Sheet1");
    // one row formulas (=A3+B3)
    SpreadSheetCellDAO a4 = new SpreadSheetCellDAO("", "", "A3+B3", "A4", "Sheet1");
    // write/*from   w  ww  .j  av a 2 s  .c  o  m*/
    JobConf job = new JobConf(defaultConf);
    String fileName = "excel2013singlesheettestoutencryptedpositivelowfootprint";
    String tmpDir = tmpPath.toString();
    Path outputPath = new Path(tmpDir);
    FileOutputFormat.setOutputPath(job, outputPath);
    // set generic outputformat settings
    job.set(JobContext.TASK_ATTEMPT_ID, attempt);
    // set locale to the one of the test data
    job.set("hadoopoffice.read.locale.bcp47", "de");

    // low footprint
    job.set("hadoopoffice.write.lowFootprint", "true");
    job.set("hadoopoffice.write.mimeType", "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"); // new
    // excel
    // format
    // security
    // for the new Excel format you need to decide on your own which algorithms are
    // secure
    job.set("hadoopoffice.write.security.crypt.encrypt.mode", "agile");
    job.set("hadoopoffice.write.security.crypt.encrypt.algorithm", "aes256");
    job.set("hadoopoffice.write.security.crypt.chain.mode", "cbc");
    job.set("hadoopoffice.write.security.crypt.hash.algorithm", "sha512");
    job.set("hadoopoffice.write.security.crypt.password", "test");
    ExcelFileOutputFormat outputFormat = new ExcelFileOutputFormat();
    RecordWriter<NullWritable, SpreadSheetCellDAO> writer = outputFormat.getRecordWriter(null, job, fileName,
            null);
    assertNotNull(writer, "Format returned  null RecordWriter");
    writer.write(null, a1);
    writer.write(null, b1);
    writer.write(null, c1);
    writer.write(null, a3);
    writer.write(null, b3);
    writer.write(null, c3);
    writer.write(null, a4);
    writer.close(reporter);
    // try to read it again
    job = new JobConf(defaultConf);
    Path inputFile = new Path(tmpDir + File.separator + "_temporary" + File.separator + "0" + File.separator
            + "_temporary" + File.separator + attempt + File.separator + fileName + ".xlsx");
    FileInputFormat.setInputPaths(job, inputFile);
    // set locale to the one of the test data
    job.set("hadoopoffice.read.locale.bcp47", "de");
    // you just need to provide the password to read encrypted data
    job.set("hadoopoffice.read.security.crypt.password", "test");
    ExcelFileInputFormat inputFormat = new ExcelFileInputFormat();
    inputFormat.configure(job);
    InputSplit[] inputSplits = inputFormat.getSplits(job, 1);
    assertEquals(1, inputSplits.length, "Only one split generated for Excel file");
    RecordReader<Text, ArrayWritable> reader = inputFormat.getRecordReader(inputSplits[0], job, reporter);
    assertNotNull(reader, "Format returned  null RecordReader");
    Text spreadSheetKey = new Text();
    ArrayWritable spreadSheetValue = new ArrayWritable(SpreadSheetCellDAO.class);
    assertTrue(reader.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 1");
    assertEquals("[" + fileName + ".xlsx]Sheet1!A1", spreadSheetKey.toString(),
            "Input Split for Excel file has keyname == \"[" + fileName + ".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("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.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 2");
    assertEquals(0, spreadSheetValue.get().length, "Input Split for Excel file contain row 2 and is empty");
    assertTrue(reader.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 3");
    assertEquals(3, spreadSheetValue.get().length, "Input Split for Excel file contain row 3 with 3 columns");
    assertEquals("1", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 3 with cell 1 == \"1\"");
    assertEquals("2", ((SpreadSheetCellDAO) spreadSheetValue.get()[1]).getFormattedValue(),
            "Input Split for Excel file contains row 3 with cell 2 == \"2\"");
    assertEquals("3", ((SpreadSheetCellDAO) spreadSheetValue.get()[2]).getFormattedValue(),
            "Input Split for Excel file contains row 3 with cell 3 == \"3\"");
    assertTrue(reader.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 4");
    assertEquals(1, spreadSheetValue.get().length, "Input Split for Excel file contain row 4 with 1 column");
    assertEquals("3", ((SpreadSheetCellDAO) spreadSheetValue.get()[0]).getFormattedValue(),
            "Input Split for Excel file contains row 3 with cell 1 == \"3\"");
}

---

From source file:org.zuinnote.hadoop.office.format.mapred.OfficeFormatHadoopExcelLowFootPrintSAXTest.java

License:Apache License

@Test
public void readExcelInputFormatExcel2013MultiSheetAllLowFootPrint() throws IOException {
    JobConf job = new JobConf(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2013testmultisheet.xlsx";
    String fileNameSpreadSheet = classLoader.getResource(fileName).getFile();
    Path file = new Path(fileNameSpreadSheet);
    FileInputFormat.setInputPaths(job, file);
    // set locale to the one of the test data
    job.set("hadoopoffice.read.locale.bcp47", "de");
    // low footprint
    job.set("hadoopoffice.read.lowFootprint", "true");

    job.set("hadoopoffice.read.lowFootprint.parser", "sax");
    ExcelFileInputFormat format = new ExcelFileInputFormat();
    format.configure(job);//  w  w  w . j a  va2s. c  o m
    InputSplit[] inputSplits = format.getSplits(job, 1);
    assertEquals(1, inputSplits.length, "Only one split generated for Excel file");
    RecordReader<Text, ArrayWritable> reader = format.getRecordReader(inputSplits[0], job, reporter);
    assertNotNull(reader, "Format returned  null RecordReader");
    Text spreadSheetKey = new Text();
    ArrayWritable spreadSheetValue = new ArrayWritable(SpreadSheetCellDAO.class);
    assertTrue(reader.next(spreadSheetKey, spreadSheetValue),
            "Input Split for Excel file contains row 1 (first sheet)");
    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.next(spreadSheetKey, spreadSheetValue),
            "Input Split for Excel file contains row 2 (first sheet)");
    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.next(spreadSheetKey, spreadSheetValue),
            "Input Split for Excel file contains row 3 (first sheet)");
    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.next(spreadSheetKey, spreadSheetValue),
            "Input Split for Excel file contains row 4 (first sheet)");
    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.next(spreadSheetKey, spreadSheetValue),
            "Input Split for Excel file contains row 5 (first sheet)");
    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.next(spreadSheetKey, spreadSheetValue),
            "Input Split for Excel file contains row 6 (first sheet)");
    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.next(spreadSheetKey, spreadSheetValue),
            "Input Split for Excel file contains row 7 (second sheet)");
    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.next(spreadSheetKey, spreadSheetValue),
            "Input Split for Excel file contains row 8 (second sheet)");
    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.next(spreadSheetKey, spreadSheetValue),
            "Input Split for Excel file contains row 9 (second sheet)");
    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.mapred.OfficeFormatHadoopExcelLowFootPrintSAXTest.java

License:Apache License

@Test
public void readExcelInputFormatExcel2003SingleSheetEncryptedPositiveLowFootprint() throws IOException {
    JobConf job = new JobConf(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2003encrypt.xls";
    String fileNameSpreadSheet = classLoader.getResource(fileName).getFile();
    Path file = new Path(fileNameSpreadSheet);
    FileInputFormat.setInputPaths(job, file);
    // set locale to the one of the test data
    job.set("hadoopoffice.read.locale.bcp47", "de");

    // low footprint
    job.set("hadoopoffice.read.lowFootprint", "true");
    // for decryption simply set the password
    job.set("hadoopoffice.read.security.crypt.password", "test");
    ExcelFileInputFormat format = new ExcelFileInputFormat();
    format.configure(job);/*  w w w.j a  v a2 s . c o  m*/
    InputSplit[] inputSplits = format.getSplits(job, 1);
    assertEquals(1, inputSplits.length, "Only one split generated for Excel file");
    RecordReader<Text, ArrayWritable> reader = format.getRecordReader(inputSplits[0], job, reporter);
    assertNotNull(reader, "Format returned  null RecordReader");
    Text spreadSheetKey = new Text();
    ArrayWritable spreadSheetValue = new ArrayWritable(SpreadSheetCellDAO.class);
    assertTrue(reader.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 1");
    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.mapred.OfficeFormatHadoopExcelLowFootPrintSAXTest.java

License:Apache License

@Test
public void readExcelInputFormatExcel2013SingleSheetEncryptedPositiveLowFootprint() throws IOException {
    JobConf job = new JobConf(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2013encrypt.xlsx";
    String fileNameSpreadSheet = classLoader.getResource(fileName).getFile();
    Path file = new Path(fileNameSpreadSheet);
    FileInputFormat.setInputPaths(job, file);
    // set locale to the one of the test data
    job.set("hadoopoffice.read.locale.bcp47", "de");
    // low footprint
    job.set("hadoopoffice.read.lowFootprint", "true");

    job.set("hadoopoffice.read.lowFootprint.parser", "sax");
    // for decryption simply set the password
    job.set("hadoopoffice.read.security.crypt.password", "test");
    ExcelFileInputFormat format = new ExcelFileInputFormat();
    format.configure(job);/*from   ww  w  .  ja  v a2 s . c  o  m*/
    InputSplit[] inputSplits = format.getSplits(job, 1);
    assertEquals(1, inputSplits.length, "Only one split generated for Excel file");
    RecordReader<Text, ArrayWritable> reader = format.getRecordReader(inputSplits[0], job, reporter);
    assertNotNull(reader, "Format returned  null RecordReader");
    Text spreadSheetKey = new Text();
    ArrayWritable spreadSheetValue = new ArrayWritable(SpreadSheetCellDAO.class);
    assertTrue(reader.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 1");
    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.mapred.OfficeFormatHadoopExcelLowFootPrintSAXTest.java

License:Apache License

@Test
public void readExcelInputFormatExcel2013EmptyRowsLowFootprint() throws IOException {
    JobConf job = new JobConf(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2013testemptyrows.xlsx";
    String fileNameSpreadSheet = classLoader.getResource(fileName).getFile();
    Path file = new Path(fileNameSpreadSheet);
    FileInputFormat.setInputPaths(job, file);
    // set locale to the one of the test data
    job.set("hadoopoffice.read.locale.bcp47", "de");

    // low footprint
    job.set("hadoopoffice.read.lowFootprint", "true");

    job.set("hadoopoffice.read.lowFootprint.parser", "sax");
    ExcelFileInputFormat format = new ExcelFileInputFormat();
    format.configure(job);/*from   ww  w  . j a v  a 2  s.c  o  m*/
    InputSplit[] inputSplits = format.getSplits(job, 1);
    assertEquals(1, inputSplits.length, "Only one split generated for Excel file");
    RecordReader<Text, ArrayWritable> reader = format.getRecordReader(inputSplits[0], job, reporter);
    assertNotNull(reader, "Format returned  null RecordReader");
    Text spreadSheetKey = new Text();
    ArrayWritable spreadSheetValue = new ArrayWritable(SpreadSheetCellDAO.class);
    assertTrue(reader.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 1");
    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.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 2");
    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.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 3");
    assertEquals(0, spreadSheetValue.get().length, "Input Split for Excel file contains row 3 with 0 columns");

    assertTrue(reader.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 4");
    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.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 5");
    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.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 6");
    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.mapred.OfficeFormatHadoopExcelLowFootPrintSAXTest.java

License:Apache License

@Test
public void readExcelInputFormatExcel2003EmptyRowsLowFootprint() throws IOException {
    JobConf job = new JobConf(defaultConf);
    ClassLoader classLoader = getClass().getClassLoader();
    String fileName = "excel2003testemptyrows.xls";
    String fileNameSpreadSheet = classLoader.getResource(fileName).getFile();
    Path file = new Path(fileNameSpreadSheet);
    FileInputFormat.setInputPaths(job, file);
    // set locale to the one of the test data
    job.set("hadoopoffice.read.locale.bcp47", "de");

    // low footprint
    job.set("hadoopoffice.read.lowFootprint", "true");

    ExcelFileInputFormat format = new ExcelFileInputFormat();
    format.configure(job);//from w w w  .j ava  2s.  c o  m
    InputSplit[] inputSplits = format.getSplits(job, 1);
    assertEquals(1, inputSplits.length, "Only one split generated for Excel file");
    RecordReader<Text, ArrayWritable> reader = format.getRecordReader(inputSplits[0], job, reporter);
    assertNotNull(reader, "Format returned  null RecordReader");
    Text spreadSheetKey = new Text();
    ArrayWritable spreadSheetValue = new ArrayWritable(SpreadSheetCellDAO.class);
    assertTrue(reader.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 1");
    assertEquals("[excel2003testemptyrows.xls]Sheet1!A1", spreadSheetKey.toString(),
            "Input Split for Excel file has keyname == \"[excel2003testemptyrows.xls]Sheet1!A1\"");
    assertEquals(0, spreadSheetValue.get().length, "Input Split for Excel file contains row 1 with 0 columns");

    assertTrue(reader.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 2");
    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.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 3");
    assertEquals(0, spreadSheetValue.get().length, "Input Split for Excel file contains row 3 with 0 columns");

    assertTrue(reader.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 4");
    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.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 5");
    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.next(spreadSheetKey, spreadSheetValue), "Input Split for Excel file contains row 6");
    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\"");
}

---

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