List of usage examples for org.apache.hadoop.mapreduce RecordReader nextKeyValue
public abstract boolean nextKeyValue() throws IOException, InterruptedException;
From source file:org.zuinnote.hadoop.office.format.mapreduce.OfficeFormatHadoopExcelLowFootPrintSAXTest.java
License:Apache License
@Test public void readExcelInputFormatExcel2013MultiSheetAllLowFootPrint() 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"); // low footprint conf.set("hadoopoffice.read.lowFootprint", "true"); conf.set("hadoopoffice.read.lowFootprint.parser", "sax"); Job job = Job.getInstance(conf);//from ww w. j a v 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 (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.OfficeFormatHadoopExcelLowFootPrintSAXTest.java
License:Apache License
@Test public void readExcelInputFormatExcel2003SingleSheetEncryptedPositiveLowFootprint() 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"); // low footprint conf.set("hadoopoffice.read.lowFootprint", "true"); // for decryption simply set the password conf.set("hadoopoffice.read.security.crypt.password", "test"); Job job = Job.getInstance(conf);//from w ww. j ava2s . 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("[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.OfficeFormatHadoopExcelLowFootPrintSAXTest.java
License:Apache License
@Test public void readExcelInputFormatExcel2013SingleSheetEncryptedPositiveLowFootprint() 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"); // low footprint conf.set("hadoopoffice.read.lowFootprint", "true"); conf.set("hadoopoffice.read.lowFootprint.parser", "sax"); // for decryption simply set the password conf.set("hadoopoffice.read.security.crypt.password", "test"); Job job = Job.getInstance(conf);//w w w.j ava 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("[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.OfficeFormatHadoopExcelLowFootPrintSAXTest.java
License:Apache License
@Test public void readExcelInputFormatExcel2003EmptyRowsLowFootprint() throws IOException, InterruptedException { Configuration conf = new Configuration(defaultConf); ClassLoader classLoader = getClass().getClassLoader(); String fileName = "excel2003testemptyrows.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"); // low footprint conf.set("hadoopoffice.read.lowFootprint", "true"); Job job = Job.getInstance(conf);//from www .ja 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("[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.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.OfficeFormatHadoopExcelLowFootPrintSAXTest.java
License:Apache License
@Test public void readExcelInputFormatExcel2013EmptyRowsLowFootprint() 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"); // low footprint conf.set("hadoopoffice.read.lowFootprint", "true"); conf.set("hadoopoffice.read.lowFootprint.parser", "sax"); Job job = Job.getInstance(conf);/*from www. j a v 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("[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.OfficeFormatHadoopExcelLowFootPrintSAXTest.java
License:Apache License
@Test public void writeExcelOutputFormatExcel2013SingleSheetLowFootprint() throws IOException, InterruptedException { // 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 va 2 s . com Job job = Job.getInstance(); Configuration conf = job.getConfiguration(); String fileName = "excel2013singlesheettestout"; String tmpDir = tmpPath.toString(); Path outputPath = new Path(tmpDir); conf.set("mapreduce.output.basename", fileName); // set locale to the one of the test data conf.set("hadoopoffice.read.locale.bcp47", "de"); // low footprint conf.set("hadoopoffice.write.lowFootprint", "true"); conf.set("hadoopoffice.write.mimeType", "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"); // new // Excel // format, // anyway // default, // but // here // for // illustrative // purposes conf.set(MRJobConfig.TASK_ATTEMPT_ID, attempt); conf.setInt(MRJobConfig.APPLICATION_ATTEMPT_ID, 0); conf.setInt(FileOutputCommitter.FILEOUTPUTCOMMITTER_ALGORITHM_VERSION, 1); FileOutputFormat.setOutputPath(job, outputPath); JobContext jContext = new JobContextImpl(conf, taskID.getJobID()); TaskAttemptContext context = new TaskAttemptContextImpl(conf, taskID); FileOutputCommitter committer = new FileOutputCommitter(outputPath, context); // setup committer.setupJob(jContext); committer.setupTask(context); // set generic outputformat settings ExcelFileOutputFormat outputFormat = new ExcelFileOutputFormat(); RecordWriter<NullWritable, SpreadSheetCellDAO> writer = outputFormat.getRecordWriter(context); 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(context); committer.commitTask(context); // try to read it again conf = new Configuration(defaultConf); job = Job.getInstance(conf); fileName = fileName + this.outputbaseAppendix; Path inputFile = new Path(tmpDir + File.separator + "_temporary" + File.separator + "0" + File.separator + taskAttempt + File.separator + fileName + ".xlsx"); FileInputFormat.setInputPaths(job, inputFile); // set locale to the one of the test data conf.set("hadoopoffice.read.locale.bcp47", "de"); ExcelFileInputFormat inputFormat = new ExcelFileInputFormat(); FileInputFormat.setInputPaths(job, inputFile); context = new TaskAttemptContextImpl(conf, new TaskAttemptID()); List<InputSplit> splits = inputFormat.getSplits(job); assertEquals(1, splits.size(), "Only one split generated for Excel file"); RecordReader<Text, ArrayWritable> reader = inputFormat.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("[" + 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.nextKeyValue(), "Input Split for Excel file contains row 2"); spreadSheetKey = reader.getCurrentKey(); spreadSheetValue = reader.getCurrentValue(); assertEquals(0, spreadSheetValue.get().length, "Input Split for Excel file contain row 2 and is empty"); assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 3"); spreadSheetKey = reader.getCurrentKey(); spreadSheetValue = reader.getCurrentValue(); 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.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 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.mapreduce.OfficeFormatHadoopExcelLowFootPrintSAXTest.java
License:Apache License
@Test public void writeExcelOutputFormatExcel2013SingleSheetEncryptedPositiveLowFootprint() throws IOException, InterruptedException { // 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 w w. ja va 2 s . c o m Job job = Job.getInstance(); Configuration conf = job.getConfiguration(); String fileName = "excel2013singlesheettestoutencryptedpositivelowfootprint"; String tmpDir = tmpPath.toString(); Path outputPath = new Path(tmpDir); conf.set("mapreduce.output.basename", fileName); // set generic outputformat settings // set locale to the one of the test data conf.set("hadoopoffice.read.locale.bcp47", "de"); // low footprint conf.set("hadoopoffice.write.lowFootprint", "true"); conf.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 conf.set("hadoopoffice.write.security.crypt.encrypt.mode", "agile"); conf.set("hadoopoffice.write.security.crypt.encrypt.algorithm", "aes256"); conf.set("hadoopoffice.write.security.crypt.chain.mode", "cbc"); conf.set("hadoopoffice.write.security.crypt.hash.algorithm", "sha512"); conf.set("hadoopoffice.write.security.crypt.password", "test"); conf.set(MRJobConfig.TASK_ATTEMPT_ID, attempt); conf.setInt(MRJobConfig.APPLICATION_ATTEMPT_ID, 0); conf.setInt(FileOutputCommitter.FILEOUTPUTCOMMITTER_ALGORITHM_VERSION, 1); FileOutputFormat.setOutputPath(job, outputPath); JobContext jContext = new JobContextImpl(conf, taskID.getJobID()); TaskAttemptContext context = new TaskAttemptContextImpl(conf, taskID); FileOutputCommitter committer = new FileOutputCommitter(outputPath, context); // setup committer.setupJob(jContext); committer.setupTask(context); ExcelFileOutputFormat outputFormat = new ExcelFileOutputFormat(); RecordWriter<NullWritable, SpreadSheetCellDAO> writer = outputFormat.getRecordWriter(context); 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(context); committer.commitTask(context); // try to read it again conf = new Configuration(defaultConf); job = Job.getInstance(conf); fileName = fileName + this.outputbaseAppendix; Path inputFile = new Path(tmpDir + File.separator + "_temporary" + File.separator + "0" + File.separator + taskAttempt + File.separator + fileName + ".xlsx"); // set locale to the one of the test data conf.set("hadoopoffice.read.locale.bcp47", "de"); // you just need to provide the password to read encrypted data conf.set("hadoopoffice.read.security.crypt.password", "test"); ExcelFileInputFormat inputFormat = new ExcelFileInputFormat(); FileInputFormat.setInputPaths(job, inputFile); context = new TaskAttemptContextImpl(conf, new TaskAttemptID()); List<InputSplit> splits = inputFormat.getSplits(job); assertEquals(1, splits.size(), "Only one split generated for Excel file"); RecordReader<Text, ArrayWritable> reader = inputFormat.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("[" + 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.nextKeyValue(), "Input Split for Excel file contains row 2"); spreadSheetKey = reader.getCurrentKey(); spreadSheetValue = reader.getCurrentValue(); assertEquals(0, spreadSheetValue.get().length, "Input Split for Excel file contain row 2 and is empty"); assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 3"); spreadSheetKey = reader.getCurrentKey(); spreadSheetValue = reader.getCurrentValue(); 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.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 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.mapreduce.OfficeFormatHadoopExcelLowFootPrintSAXTest.java
License:Apache License
@Test public void writeExcelOutputFormatExcel2013SingleSheetSignedPositive() throws IOException, InterruptedException { // 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/* ww w . j a v a2 s . co m*/ Job job = Job.getInstance(); Configuration conf = job.getConfiguration(); String fileName = "excel2013singlesheettestoutsignedpositive"; String tmpDir = tmpPath.toString(); Path outputPath = new Path(tmpDir); conf.set("mapreduce.output.basename", fileName); // set locale to the one of the test data conf.set("hadoopoffice.read.locale.bcp47", "de"); conf.set("hadoopoffice.write.mimeType", "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"); // new // Excel // format, // anyway // default, // but // here // for // illustrative // purposes /// signature String pkFileName = "testsigning.pfx"; // private key ClassLoader classLoader = getClass().getClassLoader(); String fileNameKeyStore = classLoader.getResource(pkFileName).getFile(); conf.set("hadoopoffice.write.security.sign.keystore.file", fileNameKeyStore); conf.set("hadoopoffice.write.security.sign.keystore.type", "PKCS12"); conf.set("hadoopoffice.write.security.sign.keystore.password", "changeit"); conf.set("hadoopoffice.write.security.sign.keystore.alias", "testalias"); conf.set("hadoopoffice.write.security.sign.hash.algorithm", "sha512"); conf.set(MRJobConfig.TASK_ATTEMPT_ID, attempt); conf.setInt(MRJobConfig.APPLICATION_ATTEMPT_ID, 0); conf.setInt(FileOutputCommitter.FILEOUTPUTCOMMITTER_ALGORITHM_VERSION, 1); FileOutputFormat.setOutputPath(job, outputPath); JobContext jContext = new JobContextImpl(conf, taskID.getJobID()); TaskAttemptContext context = new TaskAttemptContextImpl(conf, taskID); FileOutputCommitter committer = new FileOutputCommitter(outputPath, context); // setup committer.setupJob(jContext); committer.setupTask(context); // set generic outputformat settings ExcelFileOutputFormat outputFormat = new ExcelFileOutputFormat(); RecordWriter<NullWritable, SpreadSheetCellDAO> writer = outputFormat.getRecordWriter(context); 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(context); committer.commitTask(context); // try to read it again conf = new Configuration(defaultConf); job = Job.getInstance(conf); fileName = fileName + this.outputbaseAppendix; Path inputFile = new Path(tmpDir + File.separator + "_temporary" + File.separator + "0" + File.separator + taskAttempt + File.separator + fileName + ".xlsx"); FileInputFormat.setInputPaths(job, inputFile); // set locale to the one of the test data conf.set("hadoopoffice.read.locale.bcp47", "de"); conf.set("hadoopoffice.read.security.sign.verifysignature", "true"); ExcelFileInputFormat inputFormat = new ExcelFileInputFormat(); FileInputFormat.setInputPaths(job, inputFile); context = new TaskAttemptContextImpl(conf, new TaskAttemptID()); List<InputSplit> splits = inputFormat.getSplits(job); assertEquals(1, splits.size(), "Only one split generated for Excel file"); RecordReader<Text, ArrayWritable> reader = inputFormat.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("[" + 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.nextKeyValue(), "Input Split for Excel file contains row 2"); spreadSheetKey = reader.getCurrentKey(); spreadSheetValue = reader.getCurrentValue(); assertEquals(0, spreadSheetValue.get().length, "Input Split for Excel file contain row 2 and is empty"); assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 3"); spreadSheetKey = reader.getCurrentKey(); spreadSheetValue = reader.getCurrentValue(); 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.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 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.mapreduce.OfficeFormatHadoopExcelLowFootPrintSAXTest.java
License:Apache License
@Test public void writeExcelOutputFormatExcel2013SingleSheetLowFootprintSignedPositive() throws IOException, InterruptedException { // 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 ww w . ja v a 2 s. c om Job job = Job.getInstance(); Configuration conf = job.getConfiguration(); String fileName = "excel2013singlesheettestoutsignedpositive"; String tmpDir = tmpPath.toString(); Path outputPath = new Path(tmpDir); conf.set("mapreduce.output.basename", fileName); // set locale to the one of the test data conf.set("hadoopoffice.read.locale.bcp47", "de"); // low footprint conf.set("hadoopoffice.write.lowFootprint", "true"); conf.set("hadoopoffice.write.mimeType", "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"); // new // Excel // format, // anyway // default, // but // here // for // illustrative // purposes /// signature String pkFileName = "testsigning.pfx"; // private key ClassLoader classLoader = getClass().getClassLoader(); String fileNameKeyStore = classLoader.getResource(pkFileName).getFile(); conf.set("hadoopoffice.write.security.sign.keystore.file", fileNameKeyStore); conf.set("hadoopoffice.write.security.sign.keystore.type", "PKCS12"); conf.set("hadoopoffice.write.security.sign.keystore.password", "changeit"); conf.set("hadoopoffice.write.security.sign.keystore.alias", "testalias"); conf.set("hadoopoffice.write.security.sign.hash.algorithm", "sha512"); conf.set(MRJobConfig.TASK_ATTEMPT_ID, attempt); conf.setInt(MRJobConfig.APPLICATION_ATTEMPT_ID, 0); conf.setInt(FileOutputCommitter.FILEOUTPUTCOMMITTER_ALGORITHM_VERSION, 1); FileOutputFormat.setOutputPath(job, outputPath); JobContext jContext = new JobContextImpl(conf, taskID.getJobID()); TaskAttemptContext context = new TaskAttemptContextImpl(conf, taskID); FileOutputCommitter committer = new FileOutputCommitter(outputPath, context); // setup committer.setupJob(jContext); committer.setupTask(context); // set generic outputformat settings ExcelFileOutputFormat outputFormat = new ExcelFileOutputFormat(); RecordWriter<NullWritable, SpreadSheetCellDAO> writer = outputFormat.getRecordWriter(context); 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(context); committer.commitTask(context); // try to read it again conf = new Configuration(defaultConf); job = Job.getInstance(conf); fileName = fileName + this.outputbaseAppendix; Path inputFile = new Path(tmpDir + File.separator + "_temporary" + File.separator + "0" + File.separator + taskAttempt + File.separator + fileName + ".xlsx"); FileInputFormat.setInputPaths(job, inputFile); // set locale to the one of the test data conf.set("hadoopoffice.read.locale.bcp47", "de"); conf.set("hadoopoffice.read.security.sign.verifysignature", "true"); ExcelFileInputFormat inputFormat = new ExcelFileInputFormat(); FileInputFormat.setInputPaths(job, inputFile); context = new TaskAttemptContextImpl(conf, new TaskAttemptID()); List<InputSplit> splits = inputFormat.getSplits(job); assertEquals(1, splits.size(), "Only one split generated for Excel file"); RecordReader<Text, ArrayWritable> reader = inputFormat.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("[" + 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.nextKeyValue(), "Input Split for Excel file contains row 2"); spreadSheetKey = reader.getCurrentKey(); spreadSheetValue = reader.getCurrentValue(); assertEquals(0, spreadSheetValue.get().length, "Input Split for Excel file contain row 2 and is empty"); assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 3"); spreadSheetKey = reader.getCurrentKey(); spreadSheetValue = reader.getCurrentValue(); 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.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 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.mapreduce.OfficeFormatHadoopExcelLowFootPrintSAXTest.java
License:Apache License
@Test public void writeExcelOutputFormatExcel2013SingleSheetEncryptedPositiveLowFootprintSignedPositive() throws IOException, InterruptedException { // 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 a va2 s .c o m Job job = Job.getInstance(); Configuration conf = job.getConfiguration(); String fileName = "excel2013singlesheettestoutencryptedpositivelowfootprintsignedpositive"; String tmpDir = tmpPath.toString(); Path outputPath = new Path(tmpDir); conf.set("mapreduce.output.basename", fileName); // set generic outputformat settings // set locale to the one of the test data conf.set("hadoopoffice.read.locale.bcp47", "de"); // low footprint conf.set("hadoopoffice.write.lowFootprint", "true"); conf.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 conf.set("hadoopoffice.write.security.crypt.encrypt.mode", "agile"); conf.set("hadoopoffice.write.security.crypt.encrypt.algorithm", "aes256"); conf.set("hadoopoffice.write.security.crypt.chain.mode", "cbc"); conf.set("hadoopoffice.write.security.crypt.hash.algorithm", "sha512"); conf.set("hadoopoffice.write.security.crypt.password", "test"); /// signature String pkFileName = "testsigning.pfx"; // private key ClassLoader classLoader = getClass().getClassLoader(); String fileNameKeyStore = classLoader.getResource(pkFileName).getFile(); conf.set("hadoopoffice.write.security.sign.keystore.file", fileNameKeyStore); conf.set("hadoopoffice.write.security.sign.keystore.type", "PKCS12"); conf.set("hadoopoffice.write.security.sign.keystore.password", "changeit"); conf.set("hadoopoffice.write.security.sign.keystore.alias", "testalias"); conf.set("hadoopoffice.write.security.sign.hash.algorithm", "sha512"); conf.set(MRJobConfig.TASK_ATTEMPT_ID, attempt); conf.setInt(MRJobConfig.APPLICATION_ATTEMPT_ID, 0); conf.setInt(FileOutputCommitter.FILEOUTPUTCOMMITTER_ALGORITHM_VERSION, 1); FileOutputFormat.setOutputPath(job, outputPath); JobContext jContext = new JobContextImpl(conf, taskID.getJobID()); TaskAttemptContext context = new TaskAttemptContextImpl(conf, taskID); FileOutputCommitter committer = new FileOutputCommitter(outputPath, context); // setup committer.setupJob(jContext); committer.setupTask(context); ExcelFileOutputFormat outputFormat = new ExcelFileOutputFormat(); RecordWriter<NullWritable, SpreadSheetCellDAO> writer = outputFormat.getRecordWriter(context); 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(context); committer.commitTask(context); // try to read it again conf = new Configuration(defaultConf); job = Job.getInstance(conf); fileName = fileName + this.outputbaseAppendix; Path inputFile = new Path(tmpDir + File.separator + "_temporary" + File.separator + "0" + File.separator + taskAttempt + File.separator + fileName + ".xlsx"); // set locale to the one of the test data conf.set("hadoopoffice.read.locale.bcp47", "de"); // you just need to provide the password to read encrypted data conf.set("hadoopoffice.read.security.crypt.password", "test"); conf.set("hadoopoffice.read.security.sign.verifysignature", "true"); ExcelFileInputFormat inputFormat = new ExcelFileInputFormat(); FileInputFormat.setInputPaths(job, inputFile); context = new TaskAttemptContextImpl(conf, new TaskAttemptID()); List<InputSplit> splits = inputFormat.getSplits(job); assertEquals(1, splits.size(), "Only one split generated for Excel file"); RecordReader<Text, ArrayWritable> reader = inputFormat.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("[" + 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.nextKeyValue(), "Input Split for Excel file contains row 2"); spreadSheetKey = reader.getCurrentKey(); spreadSheetValue = reader.getCurrentValue(); assertEquals(0, spreadSheetValue.get().length, "Input Split for Excel file contain row 2 and is empty"); assertTrue(reader.nextKeyValue(), "Input Split for Excel file contains row 3"); spreadSheetKey = reader.getCurrentKey(); spreadSheetValue = reader.getCurrentValue(); 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.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 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\""); }