Spring for Apache Hadoop Schema
<?xml version="1.0" encoding="UTF-8"?> <xsd:schema xmlns="http://www.springframework.org/schema/hadoop" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:beans="http://www.springframework.org/schema/beans" xmlns:tool="http://www.springframework.org/schema/tool" targetNamespace="http://www.springframework.org/schema/hadoop" elementFormDefault="qualified" attributeFormDefault="unqualified" version="1.0.0"> <xsd:import namespace="http://www.springframework.org/schema/beans" /> <xsd:import namespace="http://www.springframework.org/schema/tool" /> <xsd:annotation> <xsd:documentation><![CDATA[ Defines the configuration elements for Spring Data Hadoop. ]]></xsd:documentation> </xsd:annotation> <!-- common attributes shared by Job executors NOT meant for extensibility - do NOT rely on this type as it might be removed in the future --> <xsd:complexType name="jobRunnerType"> <xsd:attribute name="id" type="xsd:ID" use="optional"> <xsd:annotation> <xsd:documentation><![CDATA[ Bean id.]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <!-- the job reference --> <xsd:attribute name="job-ref"> <xsd:annotation> <xsd:documentation source="java:org.apache.hadoop.mapreduce.Job"><![CDATA[ Hadoop Job. Multiple names can be specified using comma (,) as a separator.]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="org.apache.hadoop.mapreduce.Job" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="wait-for-completion" type="xsd:string" use="optional" default="true"> <xsd:annotation> <xsd:documentation><![CDATA[ Whether to synchronously wait for the job(s) to finish (the default) or not. ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="verbose" type="xsd:string" use="optional" default="true"/> <xsd:attribute name="kill-job-at-shutdown" type="xsd:string" use="optional" default="true"> <xsd:annotation> <xsd:documentation><![CDATA[ Whether the configured jobs should be 'killed' when the application shuts down (default) or not. For long-running or fire-and-forget jobs that live beyond the starting application, set this to false. Note that if 'wait-for-job' is true, this flag is considered to be true as otherwise the application cannot shut down (since it has to keep waiting for the job). ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="executor-ref" type="xsd:string" use="optional"> <xsd:annotation> <xsd:documentation source="java:java.util.concurrent.Executor"><![CDATA[ The task executor responsible for executing the task. By default SyncTaskExecutor is used, meaning the calling thread is used. While this replicates the Hadoop behavior, it prevents running jobs from being killed if the application shuts down. For fine-tuned control, a dedicated Executor is recommended. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="java:java.util.concurrent.Executor" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="scope" type="xsd:string" use="optional" /> </xsd:complexType> <xsd:element name="job-tasklet" type="jobRunnerType"> <xsd:annotation> <xsd:documentation><![CDATA[ Defines a Spring Batch tasklet for Hadoop Jobs. ]]> </xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:exports type="org.springframework.data.hadoop.mapreduce.JobTasklet"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:element> <xsd:element name="job-runner"> <xsd:annotation> <xsd:documentation><![CDATA[ Defines a runner for Hadoop jobs. ]]> </xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:exports type="org.springframework.data.hadoop.mapreduce.JobRunner"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> <xsd:complexType> <xsd:complexContent> <xsd:extension base="jobRunnerType"> <xsd:attribute name="run-at-startup" type="xsd:string" default="false"> <xsd:annotation> <xsd:documentation><![CDATA[ Whether the Job runs at startup or not (default). ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="pre-action" type="xsd:string" default=""> <xsd:annotation> <xsd:documentation><![CDATA[ Pre actions/beans to be called before running the action. Multiple bean names can be specified using comma-separated list.]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="post-action" type="xsd:string" default=""> <xsd:annotation> <xsd:documentation><![CDATA[ Post actions/beans to be called before running the action. Multiple bean names can be specified using comma-separated list.]]></xsd:documentation> </xsd:annotation> </xsd:attribute> </xsd:extension> </xsd:complexContent> </xsd:complexType> </xsd:element> <!-- common attributes shared by properties based configurations NOT meant for extensibility - do NOT rely on this type as it might be removed in the future --> <xsd:complexType name="propertiesConfigurableType" mixed="true"> <xsd:attribute name="properties-ref" type="xsd:string"> <xsd:annotation> <xsd:documentation><![CDATA[ Reference to a Properties object. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="java.util.Properties" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="properties-location" type="xsd:string"> <xsd:annotation> <xsd:documentation><![CDATA[ Properties location(s). Multiple locations can be specified using comma (,) as a separator. ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> </xsd:complexType> <xsd:element name="configuration"> <xsd:annotation> <xsd:documentation><![CDATA[ Defines a Hadoop Configuration. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:exports type="org.apache.hadoop.conf.Configuration"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> <xsd:complexType mixed="true"> <xsd:complexContent> <xsd:extension base="propertiesConfigurableType"> <xsd:attribute name="id" type="xsd:ID" use="optional"> <xsd:annotation> <xsd:documentation><![CDATA[ Bean id (default is "hadoopConfiguration"). ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="configuration-ref"> <xsd:annotation> <xsd:documentation source="java:org.apache.hadoop.conf.Configuration"><![CDATA[ Reference to another Hadoop configuration (useful for chaining)]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="org.apache.hadoop.conf.Configuration" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="resources"> <xsd:annotation> <xsd:documentation source="java:org.springframework.core.io.Resource"><![CDATA[ Hadoop Configuration resources. Multiple resources can be specified, using comma (,) as a separator.]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="direct"> <tool:expected-type type="org.springframework.core.io.Resource[]" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="register-url-handler" use="optional" default="false"> <xsd:annotation> <xsd:documentation><![CDATA[ Registers an HDFS url handler in the running VM. Note that this operation can be executed at most once in a given JVM hence the default is false. ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="depends-on" use="optional"><xsd:annotation><xsd:documentation> The names of the beans that this bean depends on being initialized. Typically used to guarantee the initialization of certain beans before the Hadoop cluster gets configured and started (directly or not through the use of its configuration and file-system). </xsd:documentation></xsd:annotation></xsd:attribute> <xsd:attribute name="file-system-uri" type="xsd:string"> <xsd:annotation> <xsd:documentation><![CDATA[ The default file-system address (host:port). Equivalent to 'fs.default.name' property.]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="job-tracker-uri" type="xsd:string"> <xsd:annotation> <xsd:documentation><![CDATA[ The Map/Reduce job tracker address (host:port). Equivalent to 'mapred.job.tracker' property.]]></xsd:documentation> </xsd:annotation> </xsd:attribute> </xsd:extension> </xsd:complexContent> </xsd:complexType> </xsd:element> <xsd:element name="file-system"> <xsd:annotation> <xsd:documentation><![CDATA[ Defines a HDFS file system. ]]> </xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:exports type="org.apache.hadoop.fs.FileSystem"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> <xsd:complexType> <xsd:attribute name="id" type="xsd:ID" use="optional"> <xsd:annotation> <xsd:documentation><![CDATA[ Bean id (default is "hadoopFs"). ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="configuration-ref" use="optional" default="hadoopConfiguration"> <xsd:annotation> <xsd:documentation source="java:org.apache.hadoop.conf.Configuration"><![CDATA[ Reference to the Hadoop Configuration. Defaults to 'hadoopConfiguration'.]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="org.apache.hadoop.conf.Configuration" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="uri" use="optional"> <xsd:annotation> <xsd:documentation><![CDATA[ The underlying HDFS system URI (by default the configuration settings will be used). ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="user" type="xsd:string"> <xsd:annotation> <xsd:documentation><![CDATA[ The security user (ugi) to use for impersonation at runtime. ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="close" type="xsd:string" default="true"> <xsd:annotation> <xsd:documentation><![CDATA[ Whether or not the Hadoop file systems should be closed once this factory is destroyed. True by default - should be turned off when running 'embedded' or if long running operations outlive the application context. ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="close-all" type="xsd:string" default="false"> <xsd:annotation> <xsd:documentation><![CDATA[ Whether or not to close all file-system instances inside a JVM at shutdown or not. Useful as a leak prevention when the app drives all of Hadoop. ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="depends-on" use="optional"><xsd:annotation><xsd:documentation> The names of the beans that this bean depends on being initialized. Typically used to guarantee the initialization of certain beans before the Hadoop cluster gets configured and started (directly or not through the use of its configuration and file-system). </xsd:documentation></xsd:annotation></xsd:attribute> </xsd:complexType> </xsd:element> <xsd:element name="resource-loader"> <xsd:annotation> <xsd:documentation><![CDATA[ Defines a HDFS-aware resource loader. ]]> </xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:exports type="org.springframework.data.hadoop.fs.HdfsResourceLoader"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> <xsd:complexType> <xsd:attribute name="id" type="xsd:ID" use="optional"> <xsd:annotation> <xsd:documentation><![CDATA[ Bean id (default is "hadoopResourceLoader"). ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="configuration-ref" use="optional" default="hadoopConfiguration"> <xsd:annotation> <xsd:documentation source="java:org.apache.hadoop.conf.Configuration"><![CDATA[ Reference to the Hadoop Configuration. Defaults to 'hadoopConfiguration'.]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="org.apache.hadoop.conf.Configuration" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="uri" use="optional"> <xsd:annotation> <xsd:documentation><![CDATA[ The underlying HDFS system URI (by default the configuration settings will be used). ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="file-system-ref"> <xsd:annotation> <xsd:documentation source="java:org.apache.hadoop.fs.FileSystem"><![CDATA[ Reference to the Hadoop FileSystem. Overrides the 'uri' or 'configuration-ref' properties.]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="org.apache.hadoop.fs.FileSystem" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="user" type="xsd:string"> <xsd:annotation> <xsd:documentation><![CDATA[ The security user (ugi) to use for impersonation at runtime. ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="use-codecs" type="xsd:string" use="optional" default="true"> <xsd:annotation> <xsd:documentation><![CDATA[ Indicates whether to use (or not) the codecs found inside the Hadoop configuration when accessing the resource input stream. By default, the codecs are used meaning the content of the stream backing the resource is decompressed on the fly (if a suitable decompressor is found). ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="depends-on" use="optional"><xsd:annotation><xsd:documentation> The names of the beans that this bean depends on being initialized. Typically used to guarantee the initialization of certain beans before the Hadoop cluster gets configured and started (directly or not through the use of its configuration and file-system). </xsd:documentation></xsd:annotation></xsd:attribute> </xsd:complexType> </xsd:element> <!-- generic options shared by the various jobs NOT meant for extensibility - do NOT rely on this type as it might be removed in the future --> <xsd:complexType name="genericOptionsType" mixed="true"> <xsd:complexContent> <xsd:extension base="propertiesConfigurableType"> <xsd:attribute name="archives"> <xsd:annotation> <xsd:appinfo> <xsd:documentation source="java:org.springframework.core.io.Resource"><![CDATA[ Archives to be unarchived to the cluster. Multiple resources can be specified, using comma (,) as a separator.]]></xsd:documentation> <tool:annotation kind="direct"> <tool:expected-type type="java:org.springframework.core.io.Resource[]" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="files"> <xsd:annotation> <xsd:appinfo> <xsd:documentation source="java:org.springframework.core.io.Resource"><![CDATA[ File resources to be copied to the cluster. Multiple resources can be specified, using comma (,) as a separator.]]></xsd:documentation> <tool:annotation kind="direct"> <tool:expected-type type="java:org.springframework.core.io.Resource[]" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="libs"> <xsd:annotation> <xsd:appinfo> <xsd:documentation source="java:org.springframework.core.io.Resource"><![CDATA[ Jar resources to include in the classpath. Multiple resources can be specified, using comma (,) as a separator.]]></xsd:documentation> <tool:annotation kind="direct"> <tool:expected-type type="java:org.springframework.core.io.Resource[]" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="user" type="xsd:string"> <xsd:annotation> <xsd:documentation><![CDATA[ The security user (ugi) to use for impersonation at runtime. ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> </xsd:extension> </xsd:complexContent> </xsd:complexType> <!-- common attributes shared by properties based configurations NOT meant for extensibility - do NOT rely on this type as it might be removed in the future --> <xsd:complexType name="jobType"> <xsd:complexContent> <xsd:extension base="genericOptionsType"> <xsd:attribute name="id" type="xsd:ID" use="required" /> <xsd:attribute name="scope" type="xsd:string" use="optional" /> <xsd:attribute name="mapper" default="org.apache.hadoop.mapreduce.Mapper"> <xsd:annotation> <xsd:appinfo> <tool:annotation kind="direct"> <tool:expected-type type="java.lang.Class" /> <tool:assignable-to type="org.apache.hadoop.mapreduce.Mapper" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="reducer" default="org.apache.hadoop.mapreduce.Reducer"> <xsd:annotation> <xsd:appinfo> <tool:annotation kind="direct"> <tool:expected-type type="java.lang.Class" /> <tool:assignable-to type="org.apache.hadoop.mapreduce.Reducer" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="combiner"> <xsd:annotation> <xsd:documentation><![CDATA[ The combiner class name. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="direct"> <tool:expected-type type="java.lang.Class" /> <tool:assignable-to type="org.apache.hadoop.mapreduce.Reducer" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="input-format"> <xsd:annotation> <xsd:appinfo> <tool:annotation kind="direct"> <tool:expected-type type="java.lang.Class" /> <tool:assignable-to type="org.apache.hadoop.mapreduce.InputFormat" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="output-format"> <xsd:annotation> <xsd:appinfo> <tool:annotation kind="direct"> <tool:expected-type type="java.lang.Class" /> <tool:assignable-to type="org.apache.hadoop.mapreduce.OutputFormat" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="partitioner"> <xsd:annotation> <xsd:appinfo> <tool:annotation kind="direct"> <tool:expected-type type="java.lang.Class" /> <tool:assignable-to type="org.apache.hadoop.mapreduce.Partitioner" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="input-path" use="optional"> <xsd:annotation> <xsd:appinfo> <tool:annotation kind="direct"> <tool:expected-type type="java.lang.String[]" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="output-path" use="optional"> <xsd:annotation> <xsd:appinfo> <tool:annotation kind="direct"> <tool:expected-type type="java.lang.String" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="number-reducers"> <xsd:annotation> <xsd:appinfo> <tool:annotation kind="direct"> <tool:expected-type type="java.lang.Integer" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="configuration-ref" default="hadoopConfiguration"> <xsd:annotation> <xsd:documentation source="java:org.apache.hadoop.conf.Configuration"><![CDATA[ Reference to the Hadoop Configuration. Defaults to 'hadoopConfiguration'.]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="org.apache.hadoop.conf.Configuration" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> </xsd:extension> </xsd:complexContent> </xsd:complexType> <xsd:element name="job"> <xsd:annotation> <xsd:documentation><![CDATA[ Defines a Hadoop Job. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:exports type="org.apache.hadoop.mapreduce.Job"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> <xsd:complexType> <xsd:complexContent mixed="true"> <xsd:extension base="jobType"> <xsd:attribute name="sort-comparator"> <xsd:annotation> <xsd:appinfo> <tool:annotation kind="direct"> <tool:expected-type type="java.lang.Class" /> <tool:assignable-to type="org.apache.hadoop.io.RawComparator" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="grouping-comparator"> <xsd:annotation> <xsd:appinfo> <tool:annotation kind="direct"> <tool:expected-type type="java.lang.Class" /> <tool:assignable-to type="org.apache.hadoop.io.RawComparator" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="key"> <xsd:annotation> <xsd:appinfo> <tool:annotation kind="direct"> <tool:expected-type type="java.lang.Class" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="value"> <xsd:annotation> <xsd:appinfo> <tool:annotation kind="direct"> <tool:expected-type type="java.lang.Class" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="map-key"> <xsd:annotation> <xsd:appinfo> <tool:annotation kind="direct"> <tool:expected-type type="java.lang.Class" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="map-value"> <xsd:annotation> <xsd:appinfo> <tool:annotation kind="direct"> <tool:expected-type type="java.lang.Class" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="codec"> <xsd:annotation> <xsd:appinfo> <tool:annotation kind="direct"> <tool:expected-type type="java.lang.Class" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="jar"> <xsd:annotation> <xsd:documentation><![CDATA[ Indicates the user jar for the map-reduce job. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:expected-type type="org.springframework.core.io.Resource" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="jar-by-class"> <xsd:annotation> <xsd:documentation><![CDATA[ Indicates the job's jar file by finding an example class location. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="direct"> <tool:expected-type type="java.lang.Class" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="working-dir"> <xsd:annotation> <xsd:documentation><![CDATA[ Indicates the job's working directory. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="direct"> <tool:expected-type type="java.lang.String" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="compress-output"> <xsd:annotation> <xsd:documentation><![CDATA[ Indicates whether the job output should be compressed or not. By default it is not set. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="direct"> <tool:expected-type type="java.lang.Boolean" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> </xsd:extension> </xsd:complexContent> </xsd:complexType> </xsd:element> <xsd:element name="streaming"> <xsd:annotation> <xsd:documentation><![CDATA[ Defines a Hadoop Streaming Job. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:exports type="org.apache.hadoop.mapreduce.Job"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> <xsd:complexType> <xsd:complexContent mixed="true"> <xsd:extension base="jobType"> <xsd:sequence> <xsd:element name="cmd-env" minOccurs="0" maxOccurs="1"> <xsd:annotation> <xsd:documentation><![CDATA[Environment variables (-cmdenv)]]></xsd:documentation> </xsd:annotation> </xsd:element> </xsd:sequence> </xsd:extension> </xsd:complexContent> </xsd:complexType> </xsd:element> <!-- common attributes shared by properties based configurations NOT meant for extensibility - do NOT rely on this type as it might be removed in the future --> <xsd:complexType name="hadoopRunnerType"> <xsd:complexContent mixed="true"> <xsd:extension base="genericOptionsType"> <xsd:sequence> <xsd:element name="arg" minOccurs="0" maxOccurs="unbounded"> <xsd:annotation> <xsd:documentation><![CDATA[ Tool argument.]]></xsd:documentation> </xsd:annotation> <xsd:complexType> <xsd:attribute name="value" type="xsd:string" use="required"/> </xsd:complexType> </xsd:element> </xsd:sequence> <xsd:attribute name="id" type="xsd:ID" use="optional"> <xsd:annotation> <xsd:documentation><![CDATA[ Bean id.]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="configuration-ref" default="hadoopConfiguration"> <xsd:annotation> <xsd:documentation source="java:org.apache.hadoop.conf.Configuration"><![CDATA[ Reference to the Hadoop Configuration. Defaults to 'hadoopConfiguration'.]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="org.apache.hadoop.conf.Configuration" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> </xsd:extension> </xsd:complexContent> </xsd:complexType> <!-- common attributes shared by properties based configurations NOT meant for extensibility - do NOT rely on this type as it might be removed in the future --> <xsd:complexType name="jarRunnerType"> <xsd:complexContent mixed="true"> <xsd:extension base="hadoopRunnerType"> <xsd:attribute name="jar" type="xsd:string" use="required"> <xsd:annotation> <xsd:documentation><![CDATA[ Indicates the jar (not required to be in the classpath). ]]></xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:expected-type type="org.springframework.core.io.Resource" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="main-class" type="xsd:string"> <xsd:annotation> <xsd:documentation><![CDATA[ Indicates the Jar entry/main class name. If not specified, the Main-Class (specified in the MANIFEST.MF), if present, is used instead. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="direct"> <tool:expected-type type="java.lang.Class" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="close-fs" type="xsd:string" default="true"> <xsd:annotation> <xsd:documentation><![CDATA[ Wherther to close or not, any file-systems created by the Jar execution. Default is true. Turn this off, if the jar uses the same file-system as the rest of the application. ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="scope" type="xsd:string" use="optional" /> </xsd:extension> </xsd:complexContent> </xsd:complexType> <xsd:element name="jar-runner"> <xsd:annotation> <xsd:documentation><![CDATA[ Executes a Hadoop Jar.]]></xsd:documentation> </xsd:annotation> <xsd:complexType> <xsd:complexContent mixed="true"> <xsd:extension base="jarRunnerType"> <xsd:attribute name="run-at-startup" type="xsd:string" default="false"> <xsd:annotation> <xsd:documentation><![CDATA[ Whether the Jar runs at startup or not (default). ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="pre-action" type="xsd:string" default=""> <xsd:annotation> <xsd:documentation><![CDATA[ Pre actions/beans to be called before running the action. Multiple bean names can be specified using comma-separated list.]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="post-action" type="xsd:string" default=""> <xsd:annotation> <xsd:documentation><![CDATA[ Post actions/beans to be called before running the action. Multiple bean names can be specified using comma-separated list.]]></xsd:documentation> </xsd:annotation> </xsd:attribute> </xsd:extension> </xsd:complexContent> </xsd:complexType> </xsd:element> <xsd:element name="jar-tasklet" type="jarRunnerType"> <xsd:annotation> <xsd:documentation><![CDATA[ Defines a Hadoop Jar Tasklet.]]></xsd:documentation> </xsd:annotation> </xsd:element> <!-- common attributes shared by properties based configurations NOT meant for extensibility - do NOT rely on this type as it might be removed in the future --> <xsd:complexType name="toolRunnerType"> <xsd:complexContent mixed="true"> <xsd:extension base="hadoopRunnerType"> <xsd:sequence> <xsd:element name="tool" minOccurs="0" maxOccurs="1"> <xsd:complexType> <xsd:sequence> <xsd:any namespace="##any" processContents="lax" minOccurs="1" maxOccurs="1"/> </xsd:sequence> </xsd:complexType> </xsd:element> </xsd:sequence> <xsd:attribute name="jar" type="xsd:string" use="optional"> <xsd:annotation> <xsd:documentation><![CDATA[ Indicates the jar (not required to be in the classpath) providing the Tool (and its dependencies). ]]></xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:expected-type type="org.springframework.core.io.Resource" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="tool-class" type="xsd:string"> <xsd:annotation> <xsd:documentation><![CDATA[ Indicates the Tool class name. This is useful when referring to an external jar (not required in the classpath). If not specified, the Main-Class (specified in the MANIFEST.MF), if present, is used instead. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="direct"> <tool:expected-type type="java.lang.Class" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="tool-ref"> <xsd:annotation> <xsd:documentation source="java:org.apache.hadoop.util.Tool"><![CDATA[ Reference to a Hadoop Tool instance.]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="org.apache.hadoop.util.Tool" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="close-fs" type="xsd:string" default="true"> <xsd:annotation> <xsd:documentation><![CDATA[ Wherther to close or not, any file-systems created by the Tool execution. Default is true. Turn this off, if the jar uses the same file-system as the rest of the application. ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="scope" type="xsd:string" use="optional" /> </xsd:extension> </xsd:complexContent> </xsd:complexType> <xsd:element name="tool-runner"> <xsd:annotation> <xsd:documentation><![CDATA[ Executes a Hadoop Tool.]]></xsd:documentation> </xsd:annotation> <xsd:complexType> <xsd:complexContent mixed="true"> <xsd:extension base="toolRunnerType"> <xsd:attribute name="run-at-startup" type="xsd:string" default="false"> <xsd:annotation> <xsd:documentation><![CDATA[ Whether the Tool runs at startup or not (default). ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="pre-action" type="xsd:string" default=""> <xsd:annotation> <xsd:documentation><![CDATA[ Pre actions/beans to be called before running the action. Multiple bean names can be specified using comma-separated list.]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="post-action" type="xsd:string" default=""> <xsd:annotation> <xsd:documentation><![CDATA[ Post actions/beans to be called before running the action. Multiple bean names can be specified using comma-separated list.]]></xsd:documentation> </xsd:annotation> </xsd:attribute> </xsd:extension> </xsd:complexContent> </xsd:complexType> </xsd:element> <xsd:element name="tool-tasklet" type="toolRunnerType"> <xsd:annotation> <xsd:documentation><![CDATA[ Defines a Hadoop Tool Tasklet.]]></xsd:documentation> </xsd:annotation> </xsd:element> <xsd:complexType name="entryType"> <xsd:attribute name="value" type="xsd:string" use="required"/> </xsd:complexType> <xsd:element name="cache"> <xsd:annotation> <xsd:documentation><![CDATA[ Configures Hadoop Distributed Cache. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:exports type="org.apache.hadoop.io.DistributedCacheFactoryBean"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> <xsd:complexType> <xsd:sequence minOccurs="1" maxOccurs="unbounded"> <xsd:choice> <xsd:element name="classpath" type="entryType"/> <xsd:element name="cache" type="entryType"/> <xsd:element name="local" type="entryType"/> </xsd:choice> </xsd:sequence> <xsd:attribute name="id" type="xsd:ID" use="optional"> <xsd:annotation> <xsd:documentation><![CDATA[ Bean id (default is "hadoopCache"). ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="create-symlink" type="xsd:string" default="false"/> <xsd:attribute name="configuration-ref" default="hadoopConfiguration"> <xsd:annotation> <xsd:documentation source="java:org.apache.hadoop.conf.Configuration"><![CDATA[ Reference to the Hadoop Configuration. Defaults to 'hadoopConfiguration'.]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="org.apache.hadoop.conf.Configuration" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="file-system-ref"> <xsd:annotation> <xsd:documentation source="java:org.apache.hadoop.fs.FileSystem"><![CDATA[ Reference to the Hadoop FileSystem.]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="org.apache.hadoop.fs.FileSystem" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> </xsd:complexType> </xsd:element> <xsd:complexType name="scriptType" mixed="true"> <xsd:attribute name="location" type="xsd:string"> <xsd:annotation> <xsd:documentation><![CDATA[ Location of the script. As an alternative one can inline the script by using a nested, text declaration.]]></xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:expected-type type="org.springframework.core.io.Resource"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> </xsd:complexType> <xsd:complexType name="scriptWithArgumentsType" mixed="true"> <xsd:complexContent> <xsd:extension base="scriptType"> <xsd:sequence> <xsd:element name="arguments" minOccurs="0" maxOccurs="1"> <xsd:annotation> <xsd:documentation><![CDATA[ Argument(s) to pass to this script. Defined in Properties format (key=value). ]]></xsd:documentation> </xsd:annotation> </xsd:element> </xsd:sequence> </xsd:extension> </xsd:complexContent> </xsd:complexType> <xsd:element name="pig-factory"> <xsd:annotation> <xsd:documentation><![CDATA[ Defines a Pig (Server) factory. The factory is thread-safe and allows creation of PigServer instances (which are not thread-safe). ]]> </xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:exports type="org.springframework.data.hadoop.pig.PigServerFactory"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> <xsd:complexType> <xsd:complexContent mixed="true"> <xsd:extension base="propertiesConfigurableType"> <xsd:sequence> <xsd:element name="script" type="scriptWithArgumentsType" minOccurs="0" maxOccurs="unbounded"> <xsd:annotation> <xsd:documentation><![CDATA[ Pig script.]]></xsd:documentation> </xsd:annotation> </xsd:element> </xsd:sequence> <xsd:attribute name="id" type="xsd:ID" use="optional"> <xsd:annotation> <xsd:documentation><![CDATA[ Bean id (default is "pigFactory"). ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="paths-to-skip"> <xsd:annotation> <xsd:documentation><![CDATA[ The path to be skipped while automatically shipping binaries for streaming. Multiple resources can be specified, using comma (,) as a separator. ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="parallelism" type="xsd:integer"/> <xsd:attribute name="validate-each-statement" type="xsd:string"/> <xsd:attribute name="job-priority" type="xsd:string"/> <xsd:attribute name="job-name" type="xsd:string"/> <xsd:attribute name="job-tracker" type="xsd:string"/> <xsd:attribute name="configuration-ref" default="hadoopConfiguration"> <xsd:annotation> <xsd:documentation source="java:org.apache.hadoop.conf.Configuration"><![CDATA[ Reference to the Hadoop Configuration. Defaults to 'hadoopConfiguration'. Can be tweaked through the 'configuration' element or the other attributes.]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="org.apache.hadoop.conf.Configuration" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="exec-type" default="MAPREDUCE"> <xsd:simpleType> <xsd:restriction base="xsd:string"> <xsd:enumeration value="MAPREDUCE"/> <xsd:enumeration value="LOCAL"/> </xsd:restriction> </xsd:simpleType> </xsd:attribute> <xsd:attribute name="user" type="xsd:string"> <xsd:annotation> <xsd:documentation><![CDATA[ The security user (ugi) to use for impersonation at runtime. ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> </xsd:extension> </xsd:complexContent> </xsd:complexType> </xsd:element> <!-- common attributes shared by Pig executors NOT meant for extensibility - do NOT rely on this type as it might be removed in the future --> <xsd:complexType name="pigRunnerType"> <xsd:sequence> <xsd:element name="script" type="scriptWithArgumentsType" minOccurs="0" maxOccurs="unbounded"> <xsd:annotation> <xsd:documentation><![CDATA[ Pig script.]]></xsd:documentation> </xsd:annotation> </xsd:element> </xsd:sequence> <xsd:attribute name="id" type="xsd:ID" use="optional"> <xsd:annotation> <xsd:documentation><![CDATA[ Bean id.]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="pig-factory-ref" type="xsd:string" use="optional" default="pigFactory"> <xsd:annotation> <xsd:documentation source="java:org.springframework.data.hadoop.pig.PigServerFactory"><![CDATA[ Reference to a PigServer factory. Defaults to 'pigFactory'. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="org.springframework.data.hadoop.pig.PigServerFactory" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="pig-template-ref" type="xsd:string" use="optional"> <xsd:annotation> <xsd:documentation source="java:org.springframework.data.hadoop.pig.PigTemplate"><![CDATA[ Reference to a PigTemplate. Alternative to 'pig-server-ref' attribute. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="org.springframework.data.hadoop.pig.PigTemplate" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="scope" type="xsd:string" use="optional" /> </xsd:complexType> <xsd:element name="pig-tasklet" type="pigRunnerType"> <xsd:annotation> <xsd:documentation><![CDATA[ Defines a PigTasklet. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:exports type="org.springframework.data.hadoop.pig.PigTasket"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:element> <xsd:element name="pig-runner"> <xsd:annotation> <xsd:documentation><![CDATA[ Runs Pig scripts. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:exports type="org.springframework.data.hadoop.pig.PigRunner"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> <xsd:complexType> <xsd:complexContent> <xsd:extension base="pigRunnerType"> <xsd:attribute name="run-at-startup" type="xsd:string" default="false"> <xsd:annotation> <xsd:documentation><![CDATA[ Whether the Pig script runs at startup or not (default). ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="pre-action" type="xsd:string" default=""> <xsd:annotation> <xsd:documentation><![CDATA[ Pre actions/beans to be called before running the action. Multiple bean names can be specified using comma-separated list.]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="post-action" type="xsd:string" default=""> <xsd:annotation> <xsd:documentation><![CDATA[ Post actions/beans to be called before running the action. Multiple bean names can be specified using comma-separated list.]]></xsd:documentation> </xsd:annotation> </xsd:attribute> </xsd:extension> </xsd:complexContent> </xsd:complexType> </xsd:element> <xsd:element name="pig-template"> <xsd:annotation> <xsd:documentation><![CDATA[ Creates a PigTemplate. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:exports type="org.springframework.data.hadoop.pig.PigTemplate"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> <xsd:complexType> <xsd:attribute name="id" type="xsd:ID" use="optional"> <xsd:annotation> <xsd:documentation><![CDATA[ Bean id (default is "pigTemplate"). ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="pig-factory-ref" type="xsd:string" use="optional" default="pigFactory"> <xsd:annotation> <xsd:documentation source="java:org.springframework.data.hadoop.pig.PigServerFactory"><![CDATA[ Reference to a PigServer factory. Defaults to 'pigFactory'. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="org.springframework.data.hadoop.pig.PigServerFactory" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> </xsd:complexType> </xsd:element> <!-- HBase --> <xsd:element name="hbase-configuration"> <xsd:complexType> <xsd:complexContent mixed="true"> <xsd:extension base="propertiesConfigurableType"> <xsd:annotation> <xsd:documentation><![CDATA[ Defines an HBase configuration. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:exports type="org.apache.hadoop.conf.Configuration"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> <xsd:attribute name="id" type="xsd:ID" use="optional"> <xsd:annotation> <xsd:documentation><![CDATA[ Bean id (default is "hbaseConfiguration"). ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="zk-quorum" type="xsd:string"> <xsd:annotation> <xsd:documentation><![CDATA[ HBase Zookeeper Quorum host(s). If not specified, the default value (picked the the classpath) is used.]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="org.apache.hadoop.conf.Configuration" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="zk-port" type="xsd:string"> <xsd:annotation> <xsd:documentation source="java:org.apache.hadoop.conf.Configuration"><![CDATA[ HBase Zookeeper port for clients to connect to. If not specified, the default value (picked from the classpath) is used.]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="org.apache.hadoop.conf.Configuration" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="stop-proxy" type="xsd:string" default="true"/> <xsd:attribute name="delete-connection" type="xsd:string" default="true"/> <xsd:attribute name="configuration-ref" default="hadoopConfiguration"> <xsd:annotation> <xsd:documentation source="java:org.apache.hadoop.conf.Configuration"><![CDATA[ Reference to the Hadoop configuration. Defaults to 'hadoopConfiguration'.]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="org.apache.hadoop.conf.Configuration" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> </xsd:extension> </xsd:complexContent> </xsd:complexType> </xsd:element> <!-- Hive --> <xsd:element name="hive-client-factory"> <xsd:complexType> <xsd:annotation> <xsd:documentation><![CDATA[ Defines a HiveClient factory for connecting to a Hive server through the Thrift protocol. The factory is thread-safe and allows creation of HiveClient instances (which are not thread-safe). ]]></xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:exports type="org.springframework.data.hadoop.hive.HiveClientFactory"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> <xsd:sequence> <xsd:element name="script" type="scriptWithArgumentsType" minOccurs="0" maxOccurs="unbounded"> <xsd:annotation> <xsd:documentation><![CDATA[ Hive script to be executed during start-up.]]></xsd:documentation> </xsd:annotation> </xsd:element> </xsd:sequence> <xsd:attribute name="id" type="xsd:ID" use="optional"> <xsd:annotation> <xsd:documentation><![CDATA[ Bean id (default is "hiveClientFactory"). ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="host" type="xsd:string" default="localhost"/> <xsd:attribute name="port" type="xsd:string" default="10000"/> </xsd:complexType> </xsd:element> <xsd:element name="hive-server"> <xsd:complexType> <xsd:complexContent mixed="true"> <xsd:extension base="propertiesConfigurableType"> <xsd:annotation> <xsd:documentation><![CDATA[ Defines an embedded Hive Server instance opened for access through the Thrift protocol. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:exports type="org.apache.thrift.server.TServer"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> <xsd:attribute name="id" type="xsd:ID" use="optional"> <xsd:annotation> <xsd:documentation><![CDATA[ Bean id (default is "hiveServer"). ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="port" type="xsd:string" default="10000"/> <xsd:attribute name="min-threads" type="xsd:string" default="5"/> <xsd:attribute name="max-threads" type="xsd:string" default="100"/> <xsd:attribute name="auto-startup" type="xsd:string" default="true"/> <xsd:attribute name="configuration-ref" default="hadoopConfiguration"> <xsd:annotation> <xsd:documentation source="java:org.apache.hadoop.conf.Configuration"><![CDATA[ Reference to the Hadoop configuration. Defaults to 'hadoopConfiguration'.]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="org.apache.hadoop.conf.Configuration" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> </xsd:extension> </xsd:complexContent> </xsd:complexType> </xsd:element> <xsd:complexType name="hiveRunnerType"> <xsd:sequence> <xsd:element name="script" type="scriptWithArgumentsType" minOccurs="0" maxOccurs="unbounded"> <xsd:annotation> <xsd:documentation><![CDATA[ Hive script.]]></xsd:documentation> </xsd:annotation> </xsd:element> </xsd:sequence> <xsd:attribute name="id" type="xsd:ID" use="optional"> <xsd:annotation> <xsd:documentation><![CDATA[ Bean id.]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="hive-client-factory-ref" type="xsd:string" use="optional" default="hiveClientFactory"> <xsd:annotation> <xsd:documentation source="java:org.springframework.data.hadoop.hive.HiveClientFactory"><![CDATA[ Reference to a HiveClient factory instance. Defaults to 'hiveClientFactory'. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="org.springframework.data.hadoop.hive.HiveClientFactory" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="hive-template-ref" type="xsd:string" use="optional"> <xsd:annotation> <xsd:documentation source="java:org.springframework.data.hadoop.hive.HiveTemplate"><![CDATA[ Reference to a HiveTemplate instance. Alternative to 'hive-client-factory-ref' attribute.. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="org.springframework.data.hadoop.hive.HiveTemplate" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="scope" type="xsd:string" use="optional" /> </xsd:complexType> <xsd:element name="hive-tasklet" type="hiveRunnerType"> <xsd:annotation> <xsd:documentation><![CDATA[ Defines a HiveTasklet. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:exports type="org.springframework.data.hadoop.hive.HiveTasket"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:element> <xsd:element name="hive-runner"> <xsd:annotation> <xsd:documentation><![CDATA[ Runs Hive scripts. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:exports type="org.springframework.data.hadoop.hive.HiveRunner"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> <xsd:complexType> <xsd:complexContent> <xsd:extension base="hiveRunnerType"> <xsd:attribute name="run-at-startup" type="xsd:string" default="false"> <xsd:annotation> <xsd:documentation><![CDATA[ Whether the Hive script runs at startup or not (default). ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="pre-action" type="xsd:string" default=""> <xsd:annotation> <xsd:documentation><![CDATA[ Pre actions/beans to be called before running the action. Multiple bean names can be specified using comma-separated list.]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="post-action" type="xsd:string" default=""> <xsd:annotation> <xsd:documentation><![CDATA[ Post actions/beans to be called before running the action. Multiple bean names can be specified using comma-separated list.]]></xsd:documentation> </xsd:annotation> </xsd:attribute> </xsd:extension> </xsd:complexContent> </xsd:complexType> </xsd:element> <xsd:element name="hive-template"> <xsd:annotation> <xsd:documentation><![CDATA[ Creates a HiveTemplate. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:exports type="org.springframework.data.hadoop.hive.HiveTemplate"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> <xsd:complexType> <xsd:attribute name="id" type="xsd:ID" use="optional"> <xsd:annotation> <xsd:documentation><![CDATA[ Bean id (default is "hiveTemplate"). ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="hive-client-factory-ref" default="hiveClientFactory"> <xsd:annotation> <xsd:documentation source="java:org.springframework.data.hadoop.hive.HiveClientFactory"><![CDATA[ Reference to HiveClient factory. Defaults to 'hiveClientFactory'.]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="org.springframework.data.hadoop.hive.HiveClientFactory" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> </xsd:complexType> </xsd:element> <!-- Script type - NOT mean to be reused outside this schema --> <xsd:complexType name="scriptingType" abstract="true" mixed="true"> <xsd:sequence> <xsd:element name="property" type="beans:propertyType" minOccurs="0" maxOccurs="unbounded"> <xsd:annotation> <xsd:documentation><![CDATA[ Property to pass to the script. Can be used to enhance or override the default properties. ]]></xsd:documentation> </xsd:annotation> </xsd:element> </xsd:sequence> <xsd:attribute name="location" type="xsd:string"> <xsd:annotation> <xsd:documentation><![CDATA[ The location of the script. Can be any resource on the local filesystem, web or even hdfs. ]]> </xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="language" type="xsd:string"> <xsd:annotation> <xsd:documentation><![CDATA[ The language used for executing the script. If no value is given, the script source extension is used to determine the scripting engine. ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="evaluate" default="ALWAYS"> <xsd:annotation> <xsd:documentation><![CDATA[ When to evaluate the script. 'ALWAYS' (default) evaluates the script on all invocations, 'IF_MODIFIED' if the script source has been modified since the last invocation and 'ONCE' only once for the duration of the application. ]]></xsd:documentation> </xsd:annotation> <xsd:simpleType> <xsd:restriction base="xsd:string"> <xsd:enumeration value="ONCE"/> <xsd:enumeration value="IF_MODIFIED"/> <xsd:enumeration value="ALWAYS"/> </xsd:restriction> </xsd:simpleType> </xsd:attribute> </xsd:complexType> <xsd:element name="script"> <xsd:complexType mixed="true"> <xsd:complexContent> <xsd:annotation> <xsd:documentation><![CDATA[ Dedicated scripting facility for interacting with Hadoop. Allows Groovy, JavaScript (Rhino), Ruby (JRuby), Python (Jython) or any JSR-223 scripting language to be used for executing commands against Hadoop, in particular its file system. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:exports type="java.lang.Object"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> <xsd:extension base="scriptingType"> <xsd:attribute name="id" type="xsd:ID" use="optional"> <xsd:annotation> <xsd:documentation><![CDATA[ Bean id (if no value is given, a name will be generated). ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="run-at-startup" type="xsd:string" default="false"> <xsd:annotation> <xsd:documentation><![CDATA[ Whether the script is evaluated automatically once the application context initializes or only when in use (the default). ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="scope" type="xsd:string" use="optional" /> <xsd:attribute name="configuration-ref" default="hadoopConfiguration"> <xsd:annotation> <xsd:documentation source="java:org.apache.hadoop.conf.Configuration"><![CDATA[ Reference to the Hadoop Configuration. Defaults to 'hadoopConfiguration'.]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="org.apache.hadoop.conf.Configuration" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="pre-action" type="xsd:string" default=""> <xsd:annotation> <xsd:documentation><![CDATA[ Pre actions/beans to be called before running the action. Multiple bean names can be specified using comma-separated list.]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="post-action" type="xsd:string" default=""> <xsd:annotation> <xsd:documentation><![CDATA[ Post actions/beans to be called before running the action. Multiple bean names can be specified using comma-separated list.]]></xsd:documentation> </xsd:annotation> </xsd:attribute> </xsd:extension> </xsd:complexContent> </xsd:complexType> </xsd:element> <xsd:element name="script-tasklet"> <xsd:complexType> <xsd:annotation> <xsd:documentation><![CDATA[ Defines a scripting Tasklet for interacting with Hadoop. Allows Groovy, JavaScript (Rhino), Ruby (JRuby), Python (Jython) or any JSR-223 scripting language to be used for executing commands against Hadoop, in particular its file system. ]]> </xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:exports type="java.lang.Object"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> <xsd:sequence> <xsd:element name="script" minOccurs="0" maxOccurs="1"> <xsd:annotation> <xsd:documentation><![CDATA[ Nested script declaration.]]></xsd:documentation> </xsd:annotation> <xsd:complexType mixed="true"> <xsd:complexContent> <xsd:extension base="scriptingType"/> </xsd:complexContent> </xsd:complexType> </xsd:element> </xsd:sequence> <xsd:attribute name="id" type="xsd:ID" use="optional"> <xsd:annotation> <xsd:documentation><![CDATA[ Bean id.]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="script-ref" type="xsd:string"> <xsd:annotation> <xsd:documentation><![CDATA[ Reference to a script declaration.]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="java.lang.Object" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="scope" type="xsd:string" use="optional" /> </xsd:complexType> </xsd:element> <!-- Cascading --> <xsd:complexType name="cascadingRunnerType"> <xsd:attribute name="id" type="xsd:ID" use="optional"> <xsd:annotation> <xsd:documentation><![CDATA[ Bean id.]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="unit-of-work-ref" type="xsd:string" use="required"> <xsd:annotation> <xsd:documentation source="java:cascading.manangement.UnitOfWork"><![CDATA[ Reference to a Cascading UnitOfWork (or uow) - that is a Cascade or sometimes a Flow. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="cascading.manangement.UnitOfWork" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="wait-for-completion" type="xsd:string" use="optional" default="true"> <xsd:annotation> <xsd:documentation><![CDATA[ Whether to synchronously wait for the unit of work to finish (the default) or not. ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="scope" type="xsd:string" use="optional" /> </xsd:complexType> <xsd:element name="cascading-tasklet" type="cascadingRunnerType"> <xsd:annotation> <xsd:documentation><![CDATA[ Defines a Spring Batch tasklet for Cascading. ]]> </xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:exports type="org.springframework.data.hadoop.cascading.CascadingTasklet"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:element> <xsd:element name="cascading-runner"> <xsd:annotation> <xsd:documentation><![CDATA[ Defines a runner for Cascading unit of work (typically Cascades). ]]> </xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:exports type="org.springframework.data.hadoop.cascading.CascadingRunner"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> <xsd:complexType> <xsd:complexContent> <xsd:extension base="cascadingRunnerType"> <xsd:attribute name="run-at-startup" type="xsd:string" default="false"> <xsd:annotation> <xsd:documentation><![CDATA[ Whether the Cascade runs at startup or not (default). ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="pre-action" type="xsd:string" default=""> <xsd:annotation> <xsd:documentation><![CDATA[ Pre actions/beans to be called before running the action. Multiple bean names can be specified using comma-separated list.]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="post-action" type="xsd:string" default=""> <xsd:annotation> <xsd:documentation><![CDATA[ Post actions/beans to be called before running the action. Multiple bean names can be specified using comma-separated list.]]></xsd:documentation> </xsd:annotation> </xsd:attribute> </xsd:extension> </xsd:complexContent> </xsd:complexType> </xsd:element> <xsd:element name="cascading-cascade"> <xsd:annotation> <xsd:documentation><![CDATA[ Defines a Cascading Cascade (an assembly of Flows). ]]></xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:exports type="org.springframework.data.hadoop.cascading.CascadeFactoryBean"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> <xsd:complexType> <xsd:complexContent mixed="true"> <xsd:extension base="propertiesConfigurableType"> <xsd:attribute name="id" type="xsd:ID" use="required"> <xsd:annotation> <xsd:documentation><![CDATA[ Bean id. ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="definition-ref" type="xsd:string" use="optional"> <xsd:annotation> <xsd:documentation source="java:cascading.cascade.CascadeDef"><![CDATA[ Reference to a Cascade definition. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="cascading.cascade.CascadeDef" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="flow-ref" type="xsd:string" use="optional"> <xsd:annotation> <xsd:documentation source="java:cascading.flow.Flow"><![CDATA[ Reference to a Cascading Flow. Multiple names can be specified using comma (,) as a separator. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="cascading.flow.Flow" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="configuration-ref" default="hadoopConfiguration"> <xsd:annotation> <xsd:documentation source="java:org.apache.hadoop.conf.Configuration"><![CDATA[ Reference to the Hadoop configuration. Defaults to 'hadoopConfiguration'.]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="org.apache.hadoop.conf.Configuration" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> </xsd:extension> </xsd:complexContent> </xsd:complexType> </xsd:element> <xsd:element name="cascading-flow"> <xsd:annotation> <xsd:documentation><![CDATA[ Defines a Cascading Hadoop Flow using a FlowDef. For declarative configuration of Sinks and Taps consider using the HadoopFlowFactoryBean directly. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:exports type="org.springframework.data.hadoop.cascading.HadoopFlowFactoryBean"/> </tool:annotation> </xsd:appinfo> </xsd:annotation> <xsd:complexType> <xsd:complexContent mixed="true"> <xsd:extension base="propertiesConfigurableType"> <xsd:attribute name="id" type="xsd:ID" use="required"> <xsd:annotation> <xsd:documentation><![CDATA[ Bean id. ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="definition-ref" type="xsd:string" use="required"> <xsd:annotation> <xsd:documentation source="java:cascading.flow.FlowDef"><![CDATA[ Reference to a Flow definition. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="cascading.flow.FlowDef" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="add-cascading-jars" type="xsd:string" use="optional" default="true"> <xsd:annotation> <xsd:documentation><![CDATA[ Indicates whether the Cascading library jars should be added to the flow classpath (through the DistributedCache). By default it is true. When running against a cluster where Cascading jars are already installed, turn this to false to avoid shipping the library jars with the job. ]]></xsd:documentation> </xsd:annotation> </xsd:attribute> <xsd:attribute name="jar" type="xsd:string" use="optional"> <xsd:annotation> <xsd:documentation><![CDATA[ Indicates the user jar (which can be outside the classpath) for this Flow. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation> <tool:expected-type type="org.springframework.core.io.Resource" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="jar-by-class" type="xsd:string" use="optional"> <xsd:annotation> <xsd:documentation><![CDATA[ Indicates the job's jar file by finding an example class location. ]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="direct"> <tool:expected-type type="java.lang.Class" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> <xsd:attribute name="write-dot" type="xsd:string" use="optional"/> <xsd:attribute name="configuration-ref" default="hadoopConfiguration"> <xsd:annotation> <xsd:documentation source="java:org.apache.hadoop.conf.Configuration"><![CDATA[ Reference to the Hadoop configuration. Defaults to 'hadoopConfiguration'.]]></xsd:documentation> <xsd:appinfo> <tool:annotation kind="ref"> <tool:expected-type type="org.apache.hadoop.conf.Configuration" /> </tool:annotation> </xsd:appinfo> </xsd:annotation> </xsd:attribute> </xsd:extension> </xsd:complexContent> </xsd:complexType> </xsd:element> </xsd:schema>