public class CqlBulkOutputFormat
extends org.apache.hadoop.mapreduce.OutputFormat<java.lang.Object,java.util.List<java.nio.ByteBuffer>>
implements org.apache.hadoop.mapred.OutputFormat<java.lang.Object,java.util.List<java.nio.ByteBuffer>>
CqlBulkOutputFormat acts as a Hadoop-specific
OutputFormat that allows reduce tasks to store keys (and corresponding
bound variable values) as CQL rows (and respective columns) in a given
table.
As is the case with the CqlOutputFormat,
you need to set the prepared statement in your
Hadoop job Configuration. The CqlConfigHelper class, through its
org.apache.cassandra.hadoop.ConfigHelper#setOutputPreparedStatement method, is provided to make this
simple.
you need to set the Keyspace. The ConfigHelper class, through its
ConfigHelper.setOutputColumnFamily(org.apache.hadoop.conf.Configuration, java.lang.String) method, is provided to make this
simple.
| Modifier and Type | Class and Description |
|---|---|
static class |
CqlBulkOutputFormat.NullOutputCommitter |
| Constructor and Description |
|---|
CqlBulkOutputFormat() |
| Modifier and Type | Method and Description |
|---|---|
void |
checkOutputSpecs(org.apache.hadoop.fs.FileSystem filesystem,
org.apache.hadoop.mapred.JobConf job)
Deprecated.
|
void |
checkOutputSpecs(org.apache.hadoop.mapreduce.JobContext context) |
static boolean |
getDeleteSourceOnSuccess(org.apache.hadoop.conf.Configuration conf) |
static java.util.Collection<java.lang.String> |
getIgnoreHosts(org.apache.hadoop.conf.Configuration conf)
Get the hosts to ignore as a collection of strings
|
org.apache.hadoop.mapreduce.OutputCommitter |
getOutputCommitter(org.apache.hadoop.mapreduce.TaskAttemptContext context) |
CqlBulkRecordWriter |
getRecordWriter(org.apache.hadoop.fs.FileSystem filesystem,
org.apache.hadoop.mapred.JobConf job,
java.lang.String name,
org.apache.hadoop.util.Progressable progress)
Deprecated.
|
CqlBulkRecordWriter |
getRecordWriter(org.apache.hadoop.mapreduce.TaskAttemptContext context)
Get the
RecordWriter for the given task. |
static java.lang.String |
getTableForAlias(org.apache.hadoop.conf.Configuration conf,
java.lang.String alias) |
static java.lang.String |
getTableInsertStatement(org.apache.hadoop.conf.Configuration conf,
java.lang.String columnFamily) |
static java.lang.String |
getTableSchema(org.apache.hadoop.conf.Configuration conf,
java.lang.String columnFamily) |
static void |
setDeleteSourceOnSuccess(org.apache.hadoop.conf.Configuration conf,
boolean deleteSrc) |
static void |
setIgnoreHosts(org.apache.hadoop.conf.Configuration conf,
java.lang.String... ignoreNodes)
Set the hosts to ignore.
|
static void |
setIgnoreHosts(org.apache.hadoop.conf.Configuration conf,
java.lang.String ignoreNodesCsv)
Set the hosts to ignore as comma delimited values.
|
static void |
setTableAlias(org.apache.hadoop.conf.Configuration conf,
java.lang.String alias,
java.lang.String columnFamily) |
static void |
setTableInsertStatement(org.apache.hadoop.conf.Configuration conf,
java.lang.String columnFamily,
java.lang.String insertStatement) |
static void |
setTableSchema(org.apache.hadoop.conf.Configuration conf,
java.lang.String columnFamily,
java.lang.String schema) |
@Deprecated public CqlBulkRecordWriter getRecordWriter(org.apache.hadoop.fs.FileSystem filesystem, org.apache.hadoop.mapred.JobConf job, java.lang.String name, org.apache.hadoop.util.Progressable progress) throws java.io.IOException
getRecordWriter in interface org.apache.hadoop.mapred.OutputFormat<java.lang.Object,java.util.List<java.nio.ByteBuffer>>java.io.IOExceptionpublic CqlBulkRecordWriter getRecordWriter(org.apache.hadoop.mapreduce.TaskAttemptContext context) throws java.io.IOException, java.lang.InterruptedException
RecordWriter for the given task.getRecordWriter in class org.apache.hadoop.mapreduce.OutputFormat<java.lang.Object,java.util.List<java.nio.ByteBuffer>>context - the information about the current task.RecordWriter to write the output for the job.java.io.IOExceptionjava.lang.InterruptedExceptionpublic void checkOutputSpecs(org.apache.hadoop.mapreduce.JobContext context)
checkOutputSpecs in class org.apache.hadoop.mapreduce.OutputFormat<java.lang.Object,java.util.List<java.nio.ByteBuffer>>@Deprecated
public void checkOutputSpecs(org.apache.hadoop.fs.FileSystem filesystem,
org.apache.hadoop.mapred.JobConf job)
throws java.io.IOException
checkOutputSpecs in interface org.apache.hadoop.mapred.OutputFormat<java.lang.Object,java.util.List<java.nio.ByteBuffer>>java.io.IOExceptionpublic org.apache.hadoop.mapreduce.OutputCommitter getOutputCommitter(org.apache.hadoop.mapreduce.TaskAttemptContext context)
throws java.io.IOException,
java.lang.InterruptedException
getOutputCommitter in class org.apache.hadoop.mapreduce.OutputFormat<java.lang.Object,java.util.List<java.nio.ByteBuffer>>java.io.IOExceptionjava.lang.InterruptedExceptionpublic static void setTableSchema(org.apache.hadoop.conf.Configuration conf,
java.lang.String columnFamily,
java.lang.String schema)
public static void setTableInsertStatement(org.apache.hadoop.conf.Configuration conf,
java.lang.String columnFamily,
java.lang.String insertStatement)
public static java.lang.String getTableSchema(org.apache.hadoop.conf.Configuration conf,
java.lang.String columnFamily)
public static java.lang.String getTableInsertStatement(org.apache.hadoop.conf.Configuration conf,
java.lang.String columnFamily)
public static void setDeleteSourceOnSuccess(org.apache.hadoop.conf.Configuration conf,
boolean deleteSrc)
public static boolean getDeleteSourceOnSuccess(org.apache.hadoop.conf.Configuration conf)
public static void setTableAlias(org.apache.hadoop.conf.Configuration conf,
java.lang.String alias,
java.lang.String columnFamily)
public static java.lang.String getTableForAlias(org.apache.hadoop.conf.Configuration conf,
java.lang.String alias)
public static void setIgnoreHosts(org.apache.hadoop.conf.Configuration conf,
java.lang.String ignoreNodesCsv)
conf - job configurationignoreNodesCsv - a comma delimited list of nodes to ignorepublic static void setIgnoreHosts(org.apache.hadoop.conf.Configuration conf,
java.lang.String... ignoreNodes)
conf - job configurationignoreNodes - the nodes to ignorepublic static java.util.Collection<java.lang.String> getIgnoreHosts(org.apache.hadoop.conf.Configuration conf)
conf - job configurationCopyright © 2018 The Apache Software Foundation