public class HDFSOutputConnector
extends org.apache.manifoldcf.agents.output.BaseOutputConnector
| Modifier and Type | Class and Description |
|---|---|
protected static class |
HDFSOutputConnector.CheckConnectionThread |
protected static class |
HDFSOutputConnector.CreateFileThread |
protected static class |
HDFSOutputConnector.DeleteFileThread |
protected static class |
HDFSOutputConnector.GetSessionThread |
static class |
HDFSOutputConnector.HDFSOutputSpecs |
| Modifier and Type | Field and Description |
|---|---|
static java.lang.String |
_rcsid |
protected static java.lang.String[] |
activitiesList |
static java.lang.String |
INGEST_ACTIVITY
Ingestion activity
|
protected long |
lastSessionFetch |
protected java.lang.String |
nameNodeHost |
protected java.lang.String |
nameNodePort |
protected java.lang.String |
nameNodeProtocol |
static java.lang.String |
REMOVE_ACTIVITY
Document removal activity
|
protected HDFSSession |
session |
protected static long |
timeToRelease |
protected java.lang.String |
user |
| Constructor and Description |
|---|
HDFSOutputConnector()
Constructor.
|
| Modifier and Type | Method and Description |
|---|---|
int |
addOrReplaceDocumentWithException(java.lang.String documentURI,
org.apache.manifoldcf.core.interfaces.VersionContext pipelineDescription,
org.apache.manifoldcf.agents.interfaces.RepositoryDocument document,
java.lang.String authorityNameString,
org.apache.manifoldcf.agents.interfaces.IOutputAddActivity activities)
Add (or replace) a document in the output data store using the connector.
|
java.lang.String |
check()
Test the connection.
|
protected void |
checkConnection() |
protected void |
closeSession() |
void |
connect(org.apache.manifoldcf.core.interfaces.ConfigParams configParams)
Connect.
|
protected void |
createFile(org.apache.hadoop.fs.Path path,
java.io.InputStream input,
org.apache.manifoldcf.agents.interfaces.IOutputAddActivity activities,
java.lang.String documentURI) |
protected void |
deleteFile(org.apache.hadoop.fs.Path path,
org.apache.manifoldcf.agents.interfaces.IOutputRemoveActivity activities,
java.lang.String documentURI) |
void |
disconnect()
Close the connection.
|
java.lang.String[] |
getActivitiesList()
Return the list of activities that this connector supports (i.e.
|
org.apache.manifoldcf.core.interfaces.VersionContext |
getPipelineDescription(org.apache.manifoldcf.core.interfaces.Specification spec)
Get an output version string, given an output specification.
|
protected HDFSSession |
getSession()
Set up a session
|
protected static void |
handleIOException(java.io.IOException e)
Handle IOException
|
protected static void |
handleURISyntaxException(java.net.URISyntaxException e)
Handle URISyntaxException
|
boolean |
isConnected()
This method is called to assess whether to count this connector instance should
actually be counted as being connected.
|
void |
outputConfigurationBody(org.apache.manifoldcf.core.interfaces.IThreadContext threadContext,
org.apache.manifoldcf.core.interfaces.IHTTPOutput out,
java.util.Locale locale,
org.apache.manifoldcf.core.interfaces.ConfigParams parameters,
java.lang.String tabName)
Output the configuration body section.
|
void |
outputConfigurationHeader(org.apache.manifoldcf.core.interfaces.IThreadContext threadContext,
org.apache.manifoldcf.core.interfaces.IHTTPOutput out,
java.util.Locale locale,
org.apache.manifoldcf.core.interfaces.ConfigParams parameters,
java.util.List<java.lang.String> tabsArray)
Output the configuration header section.
|
void |
outputSpecificationBody(org.apache.manifoldcf.core.interfaces.IHTTPOutput out,
java.util.Locale locale,
org.apache.manifoldcf.core.interfaces.Specification os,
int connectionSequenceNumber,
int actualSequenceNumber,
java.lang.String tabName)
Output the specification body section.
|
void |
outputSpecificationHeader(org.apache.manifoldcf.core.interfaces.IHTTPOutput out,
java.util.Locale locale,
org.apache.manifoldcf.core.interfaces.Specification os,
int connectionSequenceNumber,
java.util.List<java.lang.String> tabsArray)
Output the specification header section.
|
void |
poll() |
java.lang.String |
processConfigurationPost(org.apache.manifoldcf.core.interfaces.IThreadContext threadContext,
org.apache.manifoldcf.core.interfaces.IPostParameters variableContext,
java.util.Locale locale,
org.apache.manifoldcf.core.interfaces.ConfigParams parameters)
Process a configuration post.
|
java.lang.String |
processSpecificationPost(org.apache.manifoldcf.core.interfaces.IPostParameters variableContext,
java.util.Locale locale,
org.apache.manifoldcf.core.interfaces.Specification os,
int connectionSequenceNumber)
Process a specification post.
|
void |
removeDocument(java.lang.String documentURI,
java.lang.String outputDescription,
org.apache.manifoldcf.agents.interfaces.IOutputRemoveActivity activities)
Remove a document using the connector.
|
void |
viewConfiguration(org.apache.manifoldcf.core.interfaces.IThreadContext threadContext,
org.apache.manifoldcf.core.interfaces.IHTTPOutput out,
java.util.Locale locale,
org.apache.manifoldcf.core.interfaces.ConfigParams parameters)
View configuration.
|
void |
viewSpecification(org.apache.manifoldcf.core.interfaces.IHTTPOutput out,
java.util.Locale locale,
org.apache.manifoldcf.core.interfaces.Specification os,
int connectionSequenceNumber)
View specification.
|
checkDateIndexable, checkDocumentIndexable, checkLengthIndexable, checkMimeTypeIndexable, checkURLIndexable, getFormCheckJavascriptMethodName, getFormPresaveCheckJavascriptMethodName, noteAllRecordsRemoved, noteJobComplete, requestInfoclearThreadContext, deinstall, getConfiguration, install, outputConfigurationBody, outputConfigurationHeader, outputConfigurationHeader, pack, packFixedList, packList, packList, processConfigurationPost, setThreadContext, unpack, unpackFixedList, unpackList, viewConfigurationpublic static final java.lang.String _rcsid
public static final java.lang.String INGEST_ACTIVITY
public static final java.lang.String REMOVE_ACTIVITY
protected static final java.lang.String[] activitiesList
protected java.lang.String nameNodeProtocol
protected java.lang.String nameNodeHost
protected java.lang.String nameNodePort
protected java.lang.String user
protected HDFSSession session
protected long lastSessionFetch
protected static final long timeToRelease
public java.lang.String[] getActivitiesList()
getActivitiesList in interface org.apache.manifoldcf.agents.interfaces.IOutputConnectorgetActivitiesList in class org.apache.manifoldcf.agents.output.BaseOutputConnectorpublic void connect(org.apache.manifoldcf.core.interfaces.ConfigParams configParams)
connect in interface org.apache.manifoldcf.core.interfaces.IConnectorconnect in class org.apache.manifoldcf.core.connector.BaseConnectorconfigParams - is the set of configuration parameters, which
in this case describe the target appliance, basic auth configuration, etc. (This formerly came
out of the ini file.)public boolean isConnected()
isConnected in interface org.apache.manifoldcf.core.interfaces.IConnectorisConnected in class org.apache.manifoldcf.core.connector.BaseConnectorpublic void disconnect()
throws org.apache.manifoldcf.core.interfaces.ManifoldCFException
disconnect in interface org.apache.manifoldcf.core.interfaces.IConnectordisconnect in class org.apache.manifoldcf.core.connector.BaseConnectororg.apache.manifoldcf.core.interfaces.ManifoldCFExceptionpublic void poll()
throws org.apache.manifoldcf.core.interfaces.ManifoldCFException
poll in interface org.apache.manifoldcf.core.interfaces.IConnectorpoll in class org.apache.manifoldcf.core.connector.BaseConnectororg.apache.manifoldcf.core.interfaces.ManifoldCFExceptionprotected void closeSession()
throws org.apache.manifoldcf.core.interfaces.ManifoldCFException
org.apache.manifoldcf.core.interfaces.ManifoldCFExceptionprotected HDFSSession getSession() throws org.apache.manifoldcf.core.interfaces.ManifoldCFException, org.apache.manifoldcf.agents.interfaces.ServiceInterruption
org.apache.manifoldcf.core.interfaces.ManifoldCFExceptionorg.apache.manifoldcf.agents.interfaces.ServiceInterruptionpublic java.lang.String check()
throws org.apache.manifoldcf.core.interfaces.ManifoldCFException
check in interface org.apache.manifoldcf.core.interfaces.IConnectorcheck in class org.apache.manifoldcf.core.connector.BaseConnectororg.apache.manifoldcf.core.interfaces.ManifoldCFExceptionpublic org.apache.manifoldcf.core.interfaces.VersionContext getPipelineDescription(org.apache.manifoldcf.core.interfaces.Specification spec)
throws org.apache.manifoldcf.core.interfaces.ManifoldCFException,
org.apache.manifoldcf.agents.interfaces.ServiceInterruption
getPipelineDescription in interface org.apache.manifoldcf.agents.interfaces.IPipelineConnectorgetPipelineDescription in class org.apache.manifoldcf.agents.output.BaseOutputConnectorspec - is the current output specification for the job that is doing the crawling.org.apache.manifoldcf.core.interfaces.ManifoldCFExceptionorg.apache.manifoldcf.agents.interfaces.ServiceInterruptionpublic int addOrReplaceDocumentWithException(java.lang.String documentURI,
org.apache.manifoldcf.core.interfaces.VersionContext pipelineDescription,
org.apache.manifoldcf.agents.interfaces.RepositoryDocument document,
java.lang.String authorityNameString,
org.apache.manifoldcf.agents.interfaces.IOutputAddActivity activities)
throws org.apache.manifoldcf.core.interfaces.ManifoldCFException,
org.apache.manifoldcf.agents.interfaces.ServiceInterruption,
java.io.IOException
addOrReplaceDocumentWithException in interface org.apache.manifoldcf.agents.interfaces.IPipelineConnectoraddOrReplaceDocumentWithException in class org.apache.manifoldcf.agents.output.BaseOutputConnectordocumentURI - is the URI of the document. The URI is presumed to be the unique identifier which the output data store will use to process
and serve the document. This URI is constructed by the repository connector which fetches the document, and is thus universal across all output connectors.pipelineDescription - includes the description string that was constructed for this document by the getOutputDescription() method.document - is the document data to be processed (handed to the output data store).authorityNameString - is the name of the authority responsible for authorizing any access tokens passed in with the repository document. May be null.activities - is the handle to an object that the implementer of a pipeline connector may use to perform operations, such as logging processing activity,
or sending a modified document to the next stage in the pipeline.java.io.IOException - only if there's a stream error reading the document data.org.apache.manifoldcf.core.interfaces.ManifoldCFExceptionorg.apache.manifoldcf.agents.interfaces.ServiceInterruptionpublic void removeDocument(java.lang.String documentURI,
java.lang.String outputDescription,
org.apache.manifoldcf.agents.interfaces.IOutputRemoveActivity activities)
throws org.apache.manifoldcf.core.interfaces.ManifoldCFException,
org.apache.manifoldcf.agents.interfaces.ServiceInterruption
removeDocument in interface org.apache.manifoldcf.agents.interfaces.IOutputConnectorremoveDocument in class org.apache.manifoldcf.agents.output.BaseOutputConnectordocumentURI - is the URI of the document. The URI is presumed to be the unique identifier which the output data store will use to process
and serve the document. This URI is constructed by the repository connector which fetches the document, and is thus universal across all output connectors.outputDescription - is the last description string that was constructed for this document by the getOutputDescription() method above.activities - is the handle to an object that the implementer of an output connector may use to perform operations, such as logging processing activity.org.apache.manifoldcf.core.interfaces.ManifoldCFExceptionorg.apache.manifoldcf.agents.interfaces.ServiceInterruptionpublic void outputConfigurationHeader(org.apache.manifoldcf.core.interfaces.IThreadContext threadContext,
org.apache.manifoldcf.core.interfaces.IHTTPOutput out,
java.util.Locale locale,
org.apache.manifoldcf.core.interfaces.ConfigParams parameters,
java.util.List<java.lang.String> tabsArray)
throws org.apache.manifoldcf.core.interfaces.ManifoldCFException,
java.io.IOException
outputConfigurationHeader in interface org.apache.manifoldcf.core.interfaces.IConnectoroutputConfigurationHeader in class org.apache.manifoldcf.core.connector.BaseConnectorthreadContext - is the local thread context.out - is the output to which any HTML should be sent.parameters - are the configuration parameters, as they currently exist, for this connection being configured.tabsArray - is an array of tab names. Add to this array any tab names that are specific to the connector.org.apache.manifoldcf.core.interfaces.ManifoldCFExceptionjava.io.IOExceptionpublic void outputConfigurationBody(org.apache.manifoldcf.core.interfaces.IThreadContext threadContext,
org.apache.manifoldcf.core.interfaces.IHTTPOutput out,
java.util.Locale locale,
org.apache.manifoldcf.core.interfaces.ConfigParams parameters,
java.lang.String tabName)
throws org.apache.manifoldcf.core.interfaces.ManifoldCFException,
java.io.IOException
outputConfigurationBody in interface org.apache.manifoldcf.core.interfaces.IConnectoroutputConfigurationBody in class org.apache.manifoldcf.core.connector.BaseConnectorthreadContext - is the local thread context.out - is the output to which any HTML should be sent.parameters - are the configuration parameters, as they currently exist, for this connection being configured.tabName - is the current tab name.org.apache.manifoldcf.core.interfaces.ManifoldCFExceptionjava.io.IOExceptionpublic java.lang.String processConfigurationPost(org.apache.manifoldcf.core.interfaces.IThreadContext threadContext,
org.apache.manifoldcf.core.interfaces.IPostParameters variableContext,
java.util.Locale locale,
org.apache.manifoldcf.core.interfaces.ConfigParams parameters)
throws org.apache.manifoldcf.core.interfaces.ManifoldCFException
processConfigurationPost in interface org.apache.manifoldcf.core.interfaces.IConnectorprocessConfigurationPost in class org.apache.manifoldcf.core.connector.BaseConnectorthreadContext - is the local thread context.variableContext - is the set of variables available from the post, including binary file post information.parameters - are the configuration parameters, as they currently exist, for this connection being configured.org.apache.manifoldcf.core.interfaces.ManifoldCFExceptionpublic void viewConfiguration(org.apache.manifoldcf.core.interfaces.IThreadContext threadContext,
org.apache.manifoldcf.core.interfaces.IHTTPOutput out,
java.util.Locale locale,
org.apache.manifoldcf.core.interfaces.ConfigParams parameters)
throws org.apache.manifoldcf.core.interfaces.ManifoldCFException,
java.io.IOException
viewConfiguration in interface org.apache.manifoldcf.core.interfaces.IConnectorviewConfiguration in class org.apache.manifoldcf.core.connector.BaseConnectorthreadContext - is the local thread context.out - is the output to which any HTML should be sent.parameters - are the configuration parameters, as they currently exist, for this connection being configured.org.apache.manifoldcf.core.interfaces.ManifoldCFExceptionjava.io.IOExceptionpublic void outputSpecificationHeader(org.apache.manifoldcf.core.interfaces.IHTTPOutput out,
java.util.Locale locale,
org.apache.manifoldcf.core.interfaces.Specification os,
int connectionSequenceNumber,
java.util.List<java.lang.String> tabsArray)
throws org.apache.manifoldcf.core.interfaces.ManifoldCFException,
java.io.IOException
outputSpecificationHeader in interface org.apache.manifoldcf.agents.interfaces.IPipelineConnectoroutputSpecificationHeader in class org.apache.manifoldcf.agents.output.BaseOutputConnectorout - is the output to which any HTML should be sent.locale - is the preferred local of the output.os - is the current pipeline specification for this connection.connectionSequenceNumber - is the unique number of this connection within the job.tabsArray - is an array of tab names. Add to this array any tab names that are specific to the connector.org.apache.manifoldcf.core.interfaces.ManifoldCFExceptionjava.io.IOExceptionpublic void outputSpecificationBody(org.apache.manifoldcf.core.interfaces.IHTTPOutput out,
java.util.Locale locale,
org.apache.manifoldcf.core.interfaces.Specification os,
int connectionSequenceNumber,
int actualSequenceNumber,
java.lang.String tabName)
throws org.apache.manifoldcf.core.interfaces.ManifoldCFException,
java.io.IOException
outputSpecificationBody in interface org.apache.manifoldcf.agents.interfaces.IPipelineConnectoroutputSpecificationBody in class org.apache.manifoldcf.agents.output.BaseOutputConnectorout - is the output to which any HTML should be sent.locale - is the preferred local of the output.os - is the current pipeline specification for this job.connectionSequenceNumber - is the unique number of this connection within the job.actualSequenceNumber - is the connection within the job that has currently been selected.tabName - is the current tab name.org.apache.manifoldcf.core.interfaces.ManifoldCFExceptionjava.io.IOExceptionpublic java.lang.String processSpecificationPost(org.apache.manifoldcf.core.interfaces.IPostParameters variableContext,
java.util.Locale locale,
org.apache.manifoldcf.core.interfaces.Specification os,
int connectionSequenceNumber)
throws org.apache.manifoldcf.core.interfaces.ManifoldCFException
processSpecificationPost in interface org.apache.manifoldcf.agents.interfaces.IPipelineConnectorprocessSpecificationPost in class org.apache.manifoldcf.agents.output.BaseOutputConnectorvariableContext - contains the post data, including binary file-upload information.locale - is the preferred local of the output.os - is the current pipeline specification for this job.connectionSequenceNumber - is the unique number of this connection within the job.org.apache.manifoldcf.core.interfaces.ManifoldCFExceptionpublic void viewSpecification(org.apache.manifoldcf.core.interfaces.IHTTPOutput out,
java.util.Locale locale,
org.apache.manifoldcf.core.interfaces.Specification os,
int connectionSequenceNumber)
throws org.apache.manifoldcf.core.interfaces.ManifoldCFException,
java.io.IOException
viewSpecification in interface org.apache.manifoldcf.agents.interfaces.IPipelineConnectorviewSpecification in class org.apache.manifoldcf.agents.output.BaseOutputConnectorout - is the output to which any HTML should be sent.locale - is the preferred local of the output.connectionSequenceNumber - is the unique number of this connection within the job.os - is the current pipeline specification for this job.org.apache.manifoldcf.core.interfaces.ManifoldCFExceptionjava.io.IOExceptionprotected static void handleURISyntaxException(java.net.URISyntaxException e)
throws org.apache.manifoldcf.core.interfaces.ManifoldCFException,
org.apache.manifoldcf.agents.interfaces.ServiceInterruption
org.apache.manifoldcf.core.interfaces.ManifoldCFExceptionorg.apache.manifoldcf.agents.interfaces.ServiceInterruptionprotected static void handleIOException(java.io.IOException e)
throws org.apache.manifoldcf.core.interfaces.ManifoldCFException,
org.apache.manifoldcf.agents.interfaces.ServiceInterruption
org.apache.manifoldcf.core.interfaces.ManifoldCFExceptionorg.apache.manifoldcf.agents.interfaces.ServiceInterruptionprotected void createFile(org.apache.hadoop.fs.Path path,
java.io.InputStream input,
org.apache.manifoldcf.agents.interfaces.IOutputAddActivity activities,
java.lang.String documentURI)
throws org.apache.manifoldcf.core.interfaces.ManifoldCFException,
org.apache.manifoldcf.agents.interfaces.ServiceInterruption
org.apache.manifoldcf.core.interfaces.ManifoldCFExceptionorg.apache.manifoldcf.agents.interfaces.ServiceInterruptionprotected void deleteFile(org.apache.hadoop.fs.Path path,
org.apache.manifoldcf.agents.interfaces.IOutputRemoveActivity activities,
java.lang.String documentURI)
throws org.apache.manifoldcf.core.interfaces.ManifoldCFException,
org.apache.manifoldcf.agents.interfaces.ServiceInterruption
org.apache.manifoldcf.core.interfaces.ManifoldCFExceptionorg.apache.manifoldcf.agents.interfaces.ServiceInterruptionprotected void checkConnection()
throws org.apache.manifoldcf.core.interfaces.ManifoldCFException,
org.apache.manifoldcf.agents.interfaces.ServiceInterruption
org.apache.manifoldcf.core.interfaces.ManifoldCFExceptionorg.apache.manifoldcf.agents.interfaces.ServiceInterruption