Repository: accumulo Updated Branches: refs/heads/master 9a9b2de83 -> 0904e5944
ACCUMULO-3403 Reinstate setZooKeeperInstance methods that accepts Strings. Project: http://git-wip-us.apache.org/repos/asf/accumulo/repo Commit: http://git-wip-us.apache.org/repos/asf/accumulo/commit/0904e594 Tree: http://git-wip-us.apache.org/repos/asf/accumulo/tree/0904e594 Diff: http://git-wip-us.apache.org/repos/asf/accumulo/diff/0904e594 Branch: refs/heads/master Commit: 0904e59440232cc0b1913dfba622d682fd6f68c8 Parents: 9a9b2de Author: Josh Elser <els...@apache.org> Authored: Thu Dec 11 17:47:38 2014 -0500 Committer: Josh Elser <els...@apache.org> Committed: Thu Dec 11 17:47:38 2014 -0500 ---------------------------------------------------------------------- .../core/client/mapred/AbstractInputFormat.java | 59 ++++++++++------ .../client/mapred/AccumuloOutputFormat.java | 73 ++++++++++++-------- .../client/mapreduce/AbstractInputFormat.java | 66 +++++++++++------- .../client/mapreduce/AccumuloOutputFormat.java | 72 +++++++++++-------- 4 files changed, 171 insertions(+), 99 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/accumulo/blob/0904e594/mapreduce/src/main/java/org/apache/accumulo/core/client/mapred/AbstractInputFormat.java ---------------------------------------------------------------------- diff --git a/mapreduce/src/main/java/org/apache/accumulo/core/client/mapred/AbstractInputFormat.java b/mapreduce/src/main/java/org/apache/accumulo/core/client/mapred/AbstractInputFormat.java index 3c86243..b83a024 100644 --- a/mapreduce/src/main/java/org/apache/accumulo/core/client/mapred/AbstractInputFormat.java +++ b/mapreduce/src/main/java/org/apache/accumulo/core/client/mapred/AbstractInputFormat.java @@ -75,11 +75,11 @@ public abstract class AbstractInputFormat<K,V> implements InputFormat<K,V> { /** * Sets the connector information needed to communicate with Accumulo in this job. - * + * * <p> * <b>WARNING:</b> The serialized token is stored in the configuration and shared with all MapReduce tasks. It is BASE64 encoded to provide a charset safe * conversion to a string, and is not intended to be secure. - * + * * @param job * the Hadoop job instance to be configured * @param principal @@ -94,10 +94,10 @@ public abstract class AbstractInputFormat<K,V> implements InputFormat<K,V> { /** * Sets the connector information needed to communicate with Accumulo in this job. - * + * * <p> * Stores the password in a file in HDFS and pulls that into the Distributed Cache in an attempt to be more secure than storing it in the Configuration. - * + * * @param job * the Hadoop job instance to be configured * @param principal @@ -112,7 +112,7 @@ public abstract class AbstractInputFormat<K,V> implements InputFormat<K,V> { /** * Determines if the connector has been configured. - * + * * @param job * the Hadoop context for the configured job * @return true if the connector has been configured, false otherwise @@ -125,7 +125,7 @@ public abstract class AbstractInputFormat<K,V> implements InputFormat<K,V> { /** * Gets the user name from the configuration. - * + * * @param job * the Hadoop context for the configured job * @return the user name @@ -138,7 +138,7 @@ public abstract class AbstractInputFormat<K,V> implements InputFormat<K,V> { /** * Gets the authenticated token from either the specified token file or directly from the configuration, whichever was used when the job was configured. - * + * * @param job * the Hadoop context for the configured job * @return the principal's authentication token @@ -152,7 +152,24 @@ public abstract class AbstractInputFormat<K,V> implements InputFormat<K,V> { /** * Configures a {@link org.apache.accumulo.core.client.ZooKeeperInstance} for this job. - * + * + * @param job + * the Hadoop job instance to be configured + * @param instanceName + * the Accumulo instance name + * @param zooKeepers + * a comma-separated list of zookeeper servers + * @since 1.5.0 + * @deprecated since 1.6.0; Use {@link #setZooKeeperInstance(JobConf, ClientConfiguration)} instead. + */ + @Deprecated + public static void setZooKeeperInstance(JobConf job, String instanceName, String zooKeepers) { + setZooKeeperInstance(job, new ClientConfiguration().withInstance(instanceName).withZkHosts(zooKeepers)); + } + + /** + * Configures a {@link org.apache.accumulo.core.client.ZooKeeperInstance} for this job. + * * @param job * the Hadoop job instance to be configured * @param clientConfig @@ -165,7 +182,7 @@ public abstract class AbstractInputFormat<K,V> implements InputFormat<K,V> { /** * Configures a {@link org.apache.accumulo.core.client.mock.MockInstance} for this job. - * + * * @param job * the Hadoop job instance to be configured * @param instanceName @@ -178,7 +195,7 @@ public abstract class AbstractInputFormat<K,V> implements InputFormat<K,V> { /** * Initializes an Accumulo {@link org.apache.accumulo.core.client.Instance} based on the configuration. - * + * * @param job * the Hadoop context for the configured job * @return an Accumulo instance @@ -192,7 +209,7 @@ public abstract class AbstractInputFormat<K,V> implements InputFormat<K,V> { /** * Sets the log level for this job. - * + * * @param job * the Hadoop job instance to be configured * @param level @@ -205,7 +222,7 @@ public abstract class AbstractInputFormat<K,V> implements InputFormat<K,V> { /** * Gets the log level from this configuration. - * + * * @param job * the Hadoop context for the configured job * @return the log level @@ -218,7 +235,7 @@ public abstract class AbstractInputFormat<K,V> implements InputFormat<K,V> { /** * Sets the {@link org.apache.accumulo.core.security.Authorizations} used to scan. Must be a subset of the user's authorization. Defaults to the empty set. - * + * * @param job * the Hadoop job instance to be configured * @param auths @@ -231,7 +248,7 @@ public abstract class AbstractInputFormat<K,V> implements InputFormat<K,V> { /** * Gets the authorizations to set for the scans from the configuration. - * + * * @param job * the Hadoop context for the configured job * @return the Accumulo scan authorizations @@ -244,7 +261,7 @@ public abstract class AbstractInputFormat<K,V> implements InputFormat<K,V> { /** * Initializes an Accumulo {@link org.apache.accumulo.core.client.impl.TabletLocator} based on the configuration. - * + * * @param job * the Hadoop context for the configured job * @return an Accumulo tablet locator @@ -259,7 +276,7 @@ public abstract class AbstractInputFormat<K,V> implements InputFormat<K,V> { // InputFormat doesn't have the equivalent of OutputFormat's checkOutputSpecs(JobContext job) /** * Check whether a configuration is fully configured to be used with an Accumulo {@link InputFormat}. - * + * * @param job * the Hadoop context for the configured job * @throws java.io.IOException @@ -272,7 +289,7 @@ public abstract class AbstractInputFormat<K,V> implements InputFormat<K,V> { /** * Fetches all {@link InputTableConfig}s that have been set on the given Hadoop job. - * + * * @param job * the Hadoop job instance to be configured * @return the {@link InputTableConfig} objects set on the job @@ -284,10 +301,10 @@ public abstract class AbstractInputFormat<K,V> implements InputFormat<K,V> { /** * Fetches a {@link InputTableConfig} that has been set on the configuration for a specific table. - * + * * <p> * null is returned in the event that the table doesn't exist. - * + * * @param job * the Hadoop job instance to be configured * @param tableName @@ -302,7 +319,7 @@ public abstract class AbstractInputFormat<K,V> implements InputFormat<K,V> { /** * An abstract base class to be used to create {@link org.apache.hadoop.mapred.RecordReader} instances that convert from Accumulo * {@link org.apache.accumulo.core.data.Key}/{@link org.apache.accumulo.core.data.Value} pairs to the user's K/V types. - * + * * Subclasses must implement {@link #next(Object, Object)} to update key and value, and also to update the following variables: * <ul> * <li>Key {@link #currentKey} (used for progress reporting)</li> @@ -316,7 +333,7 @@ public abstract class AbstractInputFormat<K,V> implements InputFormat<K,V> { /** * Configures the iterators on a scanner for the given table name. - * + * * @param job * the Hadoop job configuration * @param scanner http://git-wip-us.apache.org/repos/asf/accumulo/blob/0904e594/mapreduce/src/main/java/org/apache/accumulo/core/client/mapred/AccumuloOutputFormat.java ---------------------------------------------------------------------- diff --git a/mapreduce/src/main/java/org/apache/accumulo/core/client/mapred/AccumuloOutputFormat.java b/mapreduce/src/main/java/org/apache/accumulo/core/client/mapred/AccumuloOutputFormat.java index eba340b..a32a8b8 100644 --- a/mapreduce/src/main/java/org/apache/accumulo/core/client/mapred/AccumuloOutputFormat.java +++ b/mapreduce/src/main/java/org/apache/accumulo/core/client/mapred/AccumuloOutputFormat.java @@ -56,15 +56,15 @@ import org.apache.log4j.Logger; /** * This class allows MapReduce jobs to use Accumulo as the sink for data. This {@link OutputFormat} accepts keys and values of type {@link Text} (for a table * name) and {@link Mutation} from the Map and Reduce functions. - * + * * The user must specify the following via static configurator methods: - * + * * <ul> * <li>{@link AccumuloOutputFormat#setConnectorInfo(JobConf, String, AuthenticationToken)} * <li>{@link AccumuloOutputFormat#setConnectorInfo(JobConf, String, String)} * <li>{@link AccumuloOutputFormat#setZooKeeperInstance(JobConf, ClientConfiguration)} OR {@link AccumuloOutputFormat#setMockInstance(JobConf, String)} * </ul> - * + * * Other static methods are optional. */ public class AccumuloOutputFormat implements OutputFormat<Text,Mutation> { @@ -74,11 +74,11 @@ public class AccumuloOutputFormat implements OutputFormat<Text,Mutation> { /** * Sets the connector information needed to communicate with Accumulo in this job. - * + * * <p> * <b>WARNING:</b> The serialized token is stored in the configuration and shared with all MapReduce tasks. It is BASE64 encoded to provide a charset safe * conversion to a string, and is not intended to be secure. - * + * * @param job * the Hadoop job instance to be configured * @param principal @@ -93,10 +93,10 @@ public class AccumuloOutputFormat implements OutputFormat<Text,Mutation> { /** * Sets the connector information needed to communicate with Accumulo in this job. - * + * * <p> * Stores the password in a file in HDFS and pulls that into the Distributed Cache in an attempt to be more secure than storing it in the Configuration. - * + * * @param job * the Hadoop job instance to be configured * @param principal @@ -111,7 +111,7 @@ public class AccumuloOutputFormat implements OutputFormat<Text,Mutation> { /** * Determines if the connector has been configured. - * + * * @param job * the Hadoop context for the configured job * @return true if the connector has been configured, false otherwise @@ -124,7 +124,7 @@ public class AccumuloOutputFormat implements OutputFormat<Text,Mutation> { /** * Gets the principal from the configuration. - * + * * @param job * the Hadoop context for the configured job * @return the user name @@ -137,7 +137,7 @@ public class AccumuloOutputFormat implements OutputFormat<Text,Mutation> { /** * Gets the serialized token class from either the configuration or the token file. - * + * * @since 1.5.0 * @deprecated since 1.6.0; Use {@link #getAuthenticationToken(JobConf)} instead. */ @@ -148,7 +148,7 @@ public class AccumuloOutputFormat implements OutputFormat<Text,Mutation> { /** * Gets the serialized token from either the configuration or the token file. - * + * * @since 1.5.0 * @deprecated since 1.6.0; Use {@link #getAuthenticationToken(JobConf)} instead. */ @@ -159,7 +159,7 @@ public class AccumuloOutputFormat implements OutputFormat<Text,Mutation> { /** * Gets the authenticated token from either the specified token file or directly from the configuration, whichever was used when the job was configured. - * + * * @param job * the Hadoop job instance to be configured * @return the principal's authentication token @@ -173,9 +173,28 @@ public class AccumuloOutputFormat implements OutputFormat<Text,Mutation> { /** * Configures a {@link ZooKeeperInstance} for this job. - * + * + * @param job + * the Hadoop job instance to be configured + * @param instanceName + * the Accumulo instance name + * @param zooKeepers + * a comma-separated list of zookeeper servers + * @since 1.5.0 + * @deprecated since 1.6.0; Use {@link #setZooKeeperInstance(JobConf, ClientConfiguration)} instead. + */ + + @Deprecated + public static void setZooKeeperInstance(JobConf job, String instanceName, String zooKeepers) { + setZooKeeperInstance(job, new ClientConfiguration().withInstance(instanceName).withZkHosts(zooKeepers)); + } + + /** + * Configures a {@link ZooKeeperInstance} for this job. + * * @param job * the Hadoop job instance to be configured + * * @param clientConfig * client configuration for specifying connection timeouts, SSL connection options, etc. * @since 1.6.0 @@ -186,7 +205,7 @@ public class AccumuloOutputFormat implements OutputFormat<Text,Mutation> { /** * Configures a {@link MockInstance} for this job. - * + * * @param job * the Hadoop job instance to be configured * @param instanceName @@ -199,7 +218,7 @@ public class AccumuloOutputFormat implements OutputFormat<Text,Mutation> { /** * Initializes an Accumulo {@link Instance} based on the configuration. - * + * * @param job * the Hadoop context for the configured job * @return an Accumulo instance @@ -213,7 +232,7 @@ public class AccumuloOutputFormat implements OutputFormat<Text,Mutation> { /** * Sets the log level for this job. - * + * * @param job * the Hadoop job instance to be configured * @param level @@ -226,7 +245,7 @@ public class AccumuloOutputFormat implements OutputFormat<Text,Mutation> { /** * Gets the log level from this configuration. - * + * * @param job * the Hadoop context for the configured job * @return the log level @@ -240,7 +259,7 @@ public class AccumuloOutputFormat implements OutputFormat<Text,Mutation> { /** * Sets the default table name to use if one emits a null in place of a table name for a given mutation. Table names can only be alpha-numeric and * underscores. - * + * * @param job * the Hadoop job instance to be configured * @param tableName @@ -253,7 +272,7 @@ public class AccumuloOutputFormat implements OutputFormat<Text,Mutation> { /** * Gets the default table name from the configuration. - * + * * @param job * the Hadoop context for the configured job * @return the default table name @@ -267,7 +286,7 @@ public class AccumuloOutputFormat implements OutputFormat<Text,Mutation> { /** * Sets the configuration for for the job's {@link BatchWriter} instances. If not set, a new {@link BatchWriterConfig}, with sensible built-in defaults is * used. Setting the configuration multiple times overwrites any previous configuration. - * + * * @param job * the Hadoop job instance to be configured * @param bwConfig @@ -280,7 +299,7 @@ public class AccumuloOutputFormat implements OutputFormat<Text,Mutation> { /** * Gets the {@link BatchWriterConfig} settings. - * + * * @param job * the Hadoop context for the configured job * @return the configuration object @@ -293,10 +312,10 @@ public class AccumuloOutputFormat implements OutputFormat<Text,Mutation> { /** * Sets the directive to create new tables, as necessary. Table names can only be alpha-numeric and underscores. - * + * * <p> * By default, this feature is <b>disabled</b>. - * + * * @param job * the Hadoop job instance to be configured * @param enableFeature @@ -309,7 +328,7 @@ public class AccumuloOutputFormat implements OutputFormat<Text,Mutation> { /** * Determines whether tables are permitted to be created as needed. - * + * * @param job * the Hadoop context for the configured job * @return true if the feature is disabled, false otherwise @@ -322,10 +341,10 @@ public class AccumuloOutputFormat implements OutputFormat<Text,Mutation> { /** * Sets the directive to use simulation mode for this job. In simulation mode, no output is produced. This is useful for testing. - * + * * <p> * By default, this feature is <b>disabled</b>. - * + * * @param job * the Hadoop job instance to be configured * @param enableFeature @@ -338,7 +357,7 @@ public class AccumuloOutputFormat implements OutputFormat<Text,Mutation> { /** * Determines whether this feature is enabled. - * + * * @param job * the Hadoop context for the configured job * @return true if the feature is enabled, false otherwise http://git-wip-us.apache.org/repos/asf/accumulo/blob/0904e594/mapreduce/src/main/java/org/apache/accumulo/core/client/mapreduce/AbstractInputFormat.java ---------------------------------------------------------------------- diff --git a/mapreduce/src/main/java/org/apache/accumulo/core/client/mapreduce/AbstractInputFormat.java b/mapreduce/src/main/java/org/apache/accumulo/core/client/mapreduce/AbstractInputFormat.java index 40cdb14..2866896 100644 --- a/mapreduce/src/main/java/org/apache/accumulo/core/client/mapreduce/AbstractInputFormat.java +++ b/mapreduce/src/main/java/org/apache/accumulo/core/client/mapreduce/AbstractInputFormat.java @@ -79,11 +79,11 @@ public abstract class AbstractInputFormat<K,V> extends InputFormat<K,V> { /** * Sets the connector information needed to communicate with Accumulo in this job. - * + * * <p> * <b>WARNING:</b> The serialized token is stored in the configuration and shared with all MapReduce tasks. It is BASE64 encoded to provide a charset safe * conversion to a string, and is not intended to be secure. - * + * * @param job * the Hadoop job instance to be configured * @param principal @@ -98,10 +98,10 @@ public abstract class AbstractInputFormat<K,V> extends InputFormat<K,V> { /** * Sets the connector information needed to communicate with Accumulo in this job. - * + * * <p> * Stores the password in a file in HDFS and pulls that into the Distributed Cache in an attempt to be more secure than storing it in the Configuration. - * + * * @param job * the Hadoop job instance to be configured * @param principal @@ -116,7 +116,7 @@ public abstract class AbstractInputFormat<K,V> extends InputFormat<K,V> { /** * Determines if the connector has been configured. - * + * * @param context * the Hadoop context for the configured job * @return true if the connector has been configured, false otherwise @@ -129,7 +129,7 @@ public abstract class AbstractInputFormat<K,V> extends InputFormat<K,V> { /** * Gets the user name from the configuration. - * + * * @param context * the Hadoop context for the configured job * @return the user name @@ -142,7 +142,7 @@ public abstract class AbstractInputFormat<K,V> extends InputFormat<K,V> { /** * Gets the serialized token class from either the configuration or the token file. - * + * * @since 1.5.0 * @deprecated since 1.6.0; Use {@link #getAuthenticationToken(JobContext)} instead. */ @@ -153,7 +153,7 @@ public abstract class AbstractInputFormat<K,V> extends InputFormat<K,V> { /** * Gets the serialized token from either the configuration or the token file. - * + * * @since 1.5.0 * @deprecated since 1.6.0; Use {@link #getAuthenticationToken(JobContext)} instead. */ @@ -164,7 +164,7 @@ public abstract class AbstractInputFormat<K,V> extends InputFormat<K,V> { /** * Gets the authenticated token from either the specified token file or directly from the configuration, whichever was used when the job was configured. - * + * * @param context * the Hadoop context for the configured job * @return the principal's authentication token @@ -178,9 +178,27 @@ public abstract class AbstractInputFormat<K,V> extends InputFormat<K,V> { /** * Configures a {@link org.apache.accumulo.core.client.ZooKeeperInstance} for this job. - * + * * @param job * the Hadoop job instance to be configured + * @param instanceName + * the Accumulo instance name + * @param zooKeepers + * a comma-separated list of zookeeper servers + * @since 1.5.0 + * @deprecated since 1.6.0; Use {@link #setZooKeeperInstance(Job, ClientConfiguration)} instead. + */ + @Deprecated + public static void setZooKeeperInstance(Job job, String instanceName, String zooKeepers) { + setZooKeeperInstance(job, new ClientConfiguration().withInstance(instanceName).withZkHosts(zooKeepers)); + } + + /** + * Configures a {@link org.apache.accumulo.core.client.ZooKeeperInstance} for this job. + * + * @param job + * the Hadoop job instance to be configured + * * @param clientConfig * client configuration containing connection options * @since 1.6.0 @@ -191,7 +209,7 @@ public abstract class AbstractInputFormat<K,V> extends InputFormat<K,V> { /** * Configures a {@link org.apache.accumulo.core.client.mock.MockInstance} for this job. - * + * * @param job * the Hadoop job instance to be configured * @param instanceName @@ -204,7 +222,7 @@ public abstract class AbstractInputFormat<K,V> extends InputFormat<K,V> { /** * Initializes an Accumulo {@link org.apache.accumulo.core.client.Instance} based on the configuration. - * + * * @param context * the Hadoop context for the configured job * @return an Accumulo instance @@ -218,7 +236,7 @@ public abstract class AbstractInputFormat<K,V> extends InputFormat<K,V> { /** * Sets the log level for this job. - * + * * @param job * the Hadoop job instance to be configured * @param level @@ -231,7 +249,7 @@ public abstract class AbstractInputFormat<K,V> extends InputFormat<K,V> { /** * Gets the log level from this configuration. - * + * * @param context * the Hadoop context for the configured job * @return the log level @@ -244,7 +262,7 @@ public abstract class AbstractInputFormat<K,V> extends InputFormat<K,V> { /** * Sets the {@link org.apache.accumulo.core.security.Authorizations} used to scan. Must be a subset of the user's authorization. Defaults to the empty set. - * + * * @param job * the Hadoop job instance to be configured * @param auths @@ -256,7 +274,7 @@ public abstract class AbstractInputFormat<K,V> extends InputFormat<K,V> { /** * Gets the authorizations to set for the scans from the configuration. - * + * * @param context * the Hadoop context for the configured job * @return the Accumulo scan authorizations @@ -269,7 +287,7 @@ public abstract class AbstractInputFormat<K,V> extends InputFormat<K,V> { /** * Fetches all {@link InputTableConfig}s that have been set on the given job. - * + * * @param context * the Hadoop job instance to be configured * @return the {@link InputTableConfig} objects for the job @@ -281,10 +299,10 @@ public abstract class AbstractInputFormat<K,V> extends InputFormat<K,V> { /** * Fetches a {@link InputTableConfig} that has been set on the configuration for a specific table. - * + * * <p> * null is returned in the event that the table doesn't exist. - * + * * @param context * the Hadoop job instance to be configured * @param tableName @@ -298,7 +316,7 @@ public abstract class AbstractInputFormat<K,V> extends InputFormat<K,V> { /** * Initializes an Accumulo {@link org.apache.accumulo.core.client.impl.TabletLocator} based on the configuration. - * + * * @param context * the Hadoop context for the configured job * @param table @@ -315,7 +333,7 @@ public abstract class AbstractInputFormat<K,V> extends InputFormat<K,V> { // InputFormat doesn't have the equivalent of OutputFormat's checkOutputSpecs(JobContext job) /** * Check whether a configuration is fully configured to be used with an Accumulo {@link org.apache.hadoop.mapreduce.InputFormat}. - * + * * @param context * the Hadoop context for the configured job * @throws java.io.IOException @@ -329,7 +347,7 @@ public abstract class AbstractInputFormat<K,V> extends InputFormat<K,V> { /** * An abstract base class to be used to create {@link org.apache.hadoop.mapreduce.RecordReader} instances that convert from Accumulo * {@link org.apache.accumulo.core.data.Key}/{@link org.apache.accumulo.core.data.Value} pairs to the user's K/V types. - * + * * Subclasses must implement {@link #nextKeyValue()} and use it to update the following variables: * <ul> * <li>K {@link #currentK}</li> @@ -345,7 +363,7 @@ public abstract class AbstractInputFormat<K,V> extends InputFormat<K,V> { /** * Configures the iterators on a scanner for the given table name. - * + * * @param context * the Hadoop context for the configured job * @param scanner @@ -508,7 +526,7 @@ public abstract class AbstractInputFormat<K,V> extends InputFormat<K,V> { /** * Gets the splits of the tables that have been set on the job. - * + * * @param context * the configuration of the job * @return the splits from the tables based on the ranges. http://git-wip-us.apache.org/repos/asf/accumulo/blob/0904e594/mapreduce/src/main/java/org/apache/accumulo/core/client/mapreduce/AccumuloOutputFormat.java ---------------------------------------------------------------------- diff --git a/mapreduce/src/main/java/org/apache/accumulo/core/client/mapreduce/AccumuloOutputFormat.java b/mapreduce/src/main/java/org/apache/accumulo/core/client/mapreduce/AccumuloOutputFormat.java index cfe36c4..e220c00 100644 --- a/mapreduce/src/main/java/org/apache/accumulo/core/client/mapreduce/AccumuloOutputFormat.java +++ b/mapreduce/src/main/java/org/apache/accumulo/core/client/mapreduce/AccumuloOutputFormat.java @@ -57,15 +57,15 @@ import org.apache.log4j.Logger; /** * This class allows MapReduce jobs to use Accumulo as the sink for data. This {@link OutputFormat} accepts keys and values of type {@link Text} (for a table * name) and {@link Mutation} from the Map and Reduce functions. - * + * * The user must specify the following via static configurator methods: - * + * * <ul> * <li>{@link AccumuloOutputFormat#setConnectorInfo(Job, String, AuthenticationToken)} * <li>{@link AccumuloOutputFormat#setConnectorInfo(Job, String, String)} * <li>{@link AccumuloOutputFormat#setZooKeeperInstance(Job, ClientConfiguration)} OR {@link AccumuloOutputFormat#setMockInstance(Job, String)} * </ul> - * + * * Other static methods are optional. */ public class AccumuloOutputFormat extends OutputFormat<Text,Mutation> { @@ -75,11 +75,11 @@ public class AccumuloOutputFormat extends OutputFormat<Text,Mutation> { /** * Sets the connector information needed to communicate with Accumulo in this job. - * + * * <p> * <b>WARNING:</b> The serialized token is stored in the configuration and shared with all MapReduce tasks. It is BASE64 encoded to provide a charset safe * conversion to a string, and is not intended to be secure. - * + * * @param job * the Hadoop job instance to be configured * @param principal @@ -94,10 +94,10 @@ public class AccumuloOutputFormat extends OutputFormat<Text,Mutation> { /** * Sets the connector information needed to communicate with Accumulo in this job. - * + * * <p> * Stores the password in a file in HDFS and pulls that into the Distributed Cache in an attempt to be more secure than storing it in the Configuration. - * + * * @param job * the Hadoop job instance to be configured * @param principal @@ -112,7 +112,7 @@ public class AccumuloOutputFormat extends OutputFormat<Text,Mutation> { /** * Determines if the connector has been configured. - * + * * @param context * the Hadoop context for the configured job * @return true if the connector has been configured, false otherwise @@ -125,7 +125,7 @@ public class AccumuloOutputFormat extends OutputFormat<Text,Mutation> { /** * Gets the user name from the configuration. - * + * * @param context * the Hadoop context for the configured job * @return the user name @@ -138,7 +138,7 @@ public class AccumuloOutputFormat extends OutputFormat<Text,Mutation> { /** * Gets the serialized token class from either the configuration or the token file. - * + * * @since 1.5.0 * @deprecated since 1.6.0; Use {@link #getAuthenticationToken(JobContext)} instead. */ @@ -149,7 +149,7 @@ public class AccumuloOutputFormat extends OutputFormat<Text,Mutation> { /** * Gets the serialized token from either the configuration or the token file. - * + * * @since 1.5.0 * @deprecated since 1.6.0; Use {@link #getAuthenticationToken(JobContext)} instead. */ @@ -160,7 +160,7 @@ public class AccumuloOutputFormat extends OutputFormat<Text,Mutation> { /** * Gets the authenticated token from either the specified token file or directly from the configuration, whichever was used when the job was configured. - * + * * @param context * the Hadoop context for the configured job * @return the principal's authentication token @@ -174,9 +174,27 @@ public class AccumuloOutputFormat extends OutputFormat<Text,Mutation> { /** * Configures a {@link ZooKeeperInstance} for this job. - * + * + * @param job + * the Hadoop job instance to be configured + * @param instanceName + * the Accumulo instance name + * @param zooKeepers + * a comma-separated list of zookeeper servers + * @since 1.5.0 + * @deprecated since 1.6.0; Use {@link #setZooKeeperInstance(Job, ClientConfiguration)} instead. + */ + @Deprecated + public static void setZooKeeperInstance(Job job, String instanceName, String zooKeepers) { + setZooKeeperInstance(job, new ClientConfiguration().withInstance(instanceName).withZkHosts(zooKeepers)); + } + + /** + * Configures a {@link ZooKeeperInstance} for this job. + * * @param job * the Hadoop job instance to be configured + * * @param clientConfig * client configuration for specifying connection timeouts, SSL connection options, etc. * @since 1.6.0 @@ -187,7 +205,7 @@ public class AccumuloOutputFormat extends OutputFormat<Text,Mutation> { /** * Configures a {@link MockInstance} for this job. - * + * * @param job * the Hadoop job instance to be configured * @param instanceName @@ -200,7 +218,7 @@ public class AccumuloOutputFormat extends OutputFormat<Text,Mutation> { /** * Initializes an Accumulo {@link Instance} based on the configuration. - * + * * @param context * the Hadoop context for the configured job * @return an Accumulo instance @@ -214,7 +232,7 @@ public class AccumuloOutputFormat extends OutputFormat<Text,Mutation> { /** * Sets the log level for this job. - * + * * @param job * the Hadoop job instance to be configured * @param level @@ -227,7 +245,7 @@ public class AccumuloOutputFormat extends OutputFormat<Text,Mutation> { /** * Gets the log level from this configuration. - * + * * @param context * the Hadoop context for the configured job * @return the log level @@ -241,7 +259,7 @@ public class AccumuloOutputFormat extends OutputFormat<Text,Mutation> { /** * Sets the default table name to use if one emits a null in place of a table name for a given mutation. Table names can only be alpha-numeric and * underscores. - * + * * @param job * the Hadoop job instance to be configured * @param tableName @@ -254,7 +272,7 @@ public class AccumuloOutputFormat extends OutputFormat<Text,Mutation> { /** * Gets the default table name from the configuration. - * + * * @param context * the Hadoop context for the configured job * @return the default table name @@ -268,7 +286,7 @@ public class AccumuloOutputFormat extends OutputFormat<Text,Mutation> { /** * Sets the configuration for for the job's {@link BatchWriter} instances. If not set, a new {@link BatchWriterConfig}, with sensible built-in defaults is * used. Setting the configuration multiple times overwrites any previous configuration. - * + * * @param job * the Hadoop job instance to be configured * @param bwConfig @@ -281,7 +299,7 @@ public class AccumuloOutputFormat extends OutputFormat<Text,Mutation> { /** * Gets the {@link BatchWriterConfig} settings. - * + * * @param context * the Hadoop context for the configured job * @return the configuration object @@ -294,10 +312,10 @@ public class AccumuloOutputFormat extends OutputFormat<Text,Mutation> { /** * Sets the directive to create new tables, as necessary. Table names can only be alpha-numeric and underscores. - * + * * <p> * By default, this feature is <b>disabled</b>. - * + * * @param job * the Hadoop job instance to be configured * @param enableFeature @@ -310,7 +328,7 @@ public class AccumuloOutputFormat extends OutputFormat<Text,Mutation> { /** * Determines whether tables are permitted to be created as needed. - * + * * @param context * the Hadoop context for the configured job * @return true if the feature is disabled, false otherwise @@ -323,10 +341,10 @@ public class AccumuloOutputFormat extends OutputFormat<Text,Mutation> { /** * Sets the directive to use simulation mode for this job. In simulation mode, no output is produced. This is useful for testing. - * + * * <p> * By default, this feature is <b>disabled</b>. - * + * * @param job * the Hadoop job instance to be configured * @param enableFeature @@ -339,7 +357,7 @@ public class AccumuloOutputFormat extends OutputFormat<Text,Mutation> { /** * Determines whether this feature is enabled. - * + * * @param context * the Hadoop context for the configured job * @return true if the feature is enabled, false otherwise
