edu.umd.cloud9.io
Class FileMerger
java.lang.Object
org.apache.hadoop.conf.Configured
edu.umd.cloud9.io.FileMerger
- All Implemented Interfaces:
- Configurable, Tool
public class FileMerger
- extends Configured
- implements Tool
|
Method Summary |
static String |
generateRandomString()
Generate a random string of default length. |
static String |
generateRandomString(int length)
Generate a random string of given length. |
static void |
main(String[] args)
|
static Path |
merge(Configuration configuration,
String inputPath,
String outputPath,
int mapperTasks,
boolean textFileFormat,
boolean deleteSource)
|
static Path |
mergeSequenceFiles(Configuration configuration,
String inputFiles,
String outputFile,
int numberOfMappers,
Class<? extends Writable> keyClass,
Class<? extends Writable> valueClass,
boolean deleteSource)
|
static Path |
mergeSequenceFiles(Configuration configuration,
String inputFiles,
String outputFile,
int numberOfMappers,
Class<? extends Writable> keyClass,
Class<? extends Writable> valueClass,
boolean deleteSource,
boolean deleteDestinationFileIfExist)
|
static Path |
mergeTextFiles(Configuration configuration,
String inputFiles,
String outputFile,
int numberOfMappers,
boolean deleteSource)
This method merges all files (in TextFormat) specified by the glob expression
inputFiles |
static Path |
mergeTextFiles(Configuration configuration,
String inputFiles,
String outputFile,
int numberOfMappers,
boolean deleteSource,
boolean deleteDestinationFileIfExist)
|
int |
run(String[] args)
|
RANDOM_GENERATOR
public static final Random RANDOM_GENERATOR
DEFAULT_RANDOM_STRING_LENGTH
public static final int DEFAULT_RANDOM_STRING_LENGTH
- See Also:
- Constant Field Values
PATH_INDICATOR
public static final String PATH_INDICATOR
- See Also:
- Constant Field Values
INTEGER_INDICATOR
public static final String INTEGER_INDICATOR
- See Also:
- Constant Field Values
HELP_OPTION
public static final String HELP_OPTION
- See Also:
- Constant Field Values
INPUT_OPTION
public static final String INPUT_OPTION
- See Also:
- Constant Field Values
OUTPUT_OPTION
public static final String OUTPUT_OPTION
- See Also:
- Constant Field Values
MAPPER_OPTION
public static final String MAPPER_OPTION
- See Also:
- Constant Field Values
REDUCER_OPTION
public static final String REDUCER_OPTION
- See Also:
- Constant Field Values
MERGE
public static final String MERGE
- See Also:
- Constant Field Values
LOCAL_MERGE_OPTION
public static final String LOCAL_MERGE_OPTION
- See Also:
- Constant Field Values
LOCAL_MERGE
public static final boolean LOCAL_MERGE
- See Also:
- Constant Field Values
DELETE_SOURCE_OPTION
public static final String DELETE_SOURCE_OPTION
- See Also:
- Constant Field Values
DELETE_SOURCE
public static final boolean DELETE_SOURCE
- See Also:
- Constant Field Values
TEXT_FILE_INPUT_FORMAT
public static final String TEXT_FILE_INPUT_FORMAT
- See Also:
- Constant Field Values
TEXT_FILE_INPUT
public static final boolean TEXT_FILE_INPUT
- See Also:
- Constant Field Values
FILE_CONTENT_DELIMITER
public static final String FILE_CONTENT_DELIMITER
- See Also:
- Constant Field Values
FileMerger
public FileMerger()
generateRandomString
public static String generateRandomString(int length)
- Generate a random string of given length.
- Parameters:
length -
- Returns:
generateRandomString
public static String generateRandomString()
- Generate a random string of default length.
- Returns:
mergeTextFiles
public static Path mergeTextFiles(Configuration configuration,
String inputFiles,
String outputFile,
int numberOfMappers,
boolean deleteSource)
throws IOException
- This method merges all files (in
TextFormat) specified by the glob expression
inputFiles
- Parameters:
inputFiles - outputFile - numberOfMappers - deleteSource -
- Returns:
-
- Throws:
IOException
mergeTextFiles
public static Path mergeTextFiles(Configuration configuration,
String inputFiles,
String outputFile,
int numberOfMappers,
boolean deleteSource,
boolean deleteDestinationFileIfExist)
throws IOException
- Throws:
IOException
mergeSequenceFiles
public static Path mergeSequenceFiles(Configuration configuration,
String inputFiles,
String outputFile,
int numberOfMappers,
Class<? extends Writable> keyClass,
Class<? extends Writable> valueClass,
boolean deleteSource)
throws IOException,
InstantiationException,
IllegalAccessException
- Throws:
IOException
InstantiationException
IllegalAccessException
mergeSequenceFiles
public static Path mergeSequenceFiles(Configuration configuration,
String inputFiles,
String outputFile,
int numberOfMappers,
Class<? extends Writable> keyClass,
Class<? extends Writable> valueClass,
boolean deleteSource,
boolean deleteDestinationFileIfExist)
throws IOException,
InstantiationException,
IllegalAccessException
- Throws:
IOException
InstantiationException
IllegalAccessException
run
public int run(String[] args)
throws IOException
- Specified by:
run in interface Tool
- Throws:
IOException
merge
public static Path merge(Configuration configuration,
String inputPath,
String outputPath,
int mapperTasks,
boolean textFileFormat,
boolean deleteSource)
throws IOException,
InstantiationException,
IllegalAccessException
- Throws:
IOException
InstantiationException
IllegalAccessException
main
public static void main(String[] args)
throws Exception
- Throws:
Exception