org.apache.manifoldcf.agents.transformation.tika

Class TikaExtractor

java.lang.Object

org.apache.manifoldcf.core.connector.BaseConnector

org.apache.manifoldcf.agents.transformation.BaseTransformationConnector

org.apache.manifoldcf.agents.transformation.tika.TikaExtractor

All Implemented Interfaces:

org.apache.manifoldcf.agents.interfaces.IPipelineConnector, org.apache.manifoldcf.agents.interfaces.ITransformationConnector, org.apache.manifoldcf.core.interfaces.IConnector

public class TikaExtractor
extends org.apache.manifoldcf.agents.transformation.BaseTransformationConnector

This connector works as a transformation connector, but does nothing other than logging.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
protected static interface	TikaExtractor.DestinationStorage
protected static class	TikaExtractor.FileDestinationStorage
protected static class	TikaExtractor.MemoryDestinationStorage
protected static class	TikaExtractor.SpecPacker

Field Summary

Fields

Modifier and Type	Field and Description
static java.lang.String	_rcsid
protected static java.lang.String[]	activitiesList
protected static java.lang.String	ACTIVITY_EXTRACT
protected static long	inMemoryMaximumFile We handle up to 64K in memory; after that we go to disk.
protected java.lang.String	tikaConfig
protected TikaParser	tikaParser

Fields inherited from class org.apache.manifoldcf.core.connector.BaseConnector

currentContext, params

Fields inherited from interface org.apache.manifoldcf.agents.interfaces.IPipelineConnector

DOCUMENTSTATUS_ACCEPTED, DOCUMENTSTATUS_REJECTED

Constructor Summary

Constructors

Constructor and Description
TikaExtractor()

Method Summary

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.
boolean	checkDocumentIndexable(org.apache.manifoldcf.core.interfaces.VersionContext pipelineDescription, java.io.File localFile, org.apache.manifoldcf.agents.interfaces.IOutputCheckActivity checkActivity) Pre-determine whether a document (passed here as a File object) is acceptable or not.
boolean	checkLengthIndexable(org.apache.manifoldcf.core.interfaces.VersionContext pipelineDescription, long length, org.apache.manifoldcf.agents.interfaces.IOutputCheckActivity checkActivity) Pre-determine whether a document's length is acceptable.
boolean	checkMimeTypeIndexable(org.apache.manifoldcf.core.interfaces.VersionContext pipelineDescription, java.lang.String mimeType, org.apache.manifoldcf.agents.interfaces.IOutputCheckActivity checkActivity) Detect if a mime type is acceptable or not.
void	connect(org.apache.manifoldcf.core.interfaces.ConfigParams configParams) Connect.
void	disconnect()
protected static void	fillInBoilerplateSpecificationMap(java.util.Map<java.lang.String,java.lang.Object> paramMap, org.apache.manifoldcf.core.interfaces.Specification os)
protected static void	fillInExceptionsSpecificationMap(java.util.Map<java.lang.String,java.lang.Object> paramMap, org.apache.manifoldcf.core.interfaces.Specification os)
protected static void	fillInFieldMappingSpecificationMap(java.util.Map<java.lang.String,java.lang.Object> paramMap, org.apache.manifoldcf.core.interfaces.Specification os)
protected static void	fillInTikaConfigTab(java.util.Map<java.lang.String,java.lang.Object> velocityContext, org.apache.manifoldcf.core.interfaces.IHTTPOutput out, org.apache.manifoldcf.core.interfaces.ConfigParams parameters)
java.lang.String[]	getActivitiesList() Return a list of activities that this connector generates.
java.lang.String	getFormCheckJavascriptMethodName(int connectionSequenceNumber) Obtain the name of the form check javascript method to call.
java.lang.String	getFormPresaveCheckJavascriptMethodName(int connectionSequenceNumber) Obtain the name of the form presave check javascript method to call.
org.apache.manifoldcf.core.interfaces.VersionContext	getPipelineDescription(org.apache.manifoldcf.core.interfaces.Specification os) Get an output version string, given an output specification.
protected static int	handleIOException(java.io.IOException e)
protected static int	handleSaxException(org.xml.sax.SAXException e)
protected static int	handleTikaException(org.apache.tika.exception.TikaException e)
protected void	initializeTikaParser()
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.
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	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.

Methods inherited from class org.apache.manifoldcf.agents.transformation.BaseTransformationConnector

checkDateIndexable, checkURLIndexable, requestInfo

Methods inherited from class org.apache.manifoldcf.core.connector.BaseConnector

check, clearThreadContext, deinstall, getConfiguration, install, isConnected, outputConfigurationBody, outputConfigurationHeader, outputConfigurationHeader, pack, packFixedList, packList, packList, poll, processConfigurationPost, setThreadContext, unpack, unpackFixedList, unpackList, viewConfiguration

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface org.apache.manifoldcf.core.interfaces.IConnector

check, clearThreadContext, deinstall, getConfiguration, install, isConnected, poll, setThreadContext

Field Detail

_rcsid

public static final java.lang.String _rcsid

See Also:

Constant Field Values

ACTIVITY_EXTRACT

protected static final java.lang.String ACTIVITY_EXTRACT

See Also:

Constant Field Values

activitiesList

protected static final java.lang.String[] activitiesList

inMemoryMaximumFile

protected static final long inMemoryMaximumFile

We handle up to 64K in memory; after that we go to disk.

See Also:

Constant Field Values

tikaConfig

protected java.lang.String tikaConfig

tikaParser

protected TikaParser tikaParser

Constructor Detail

TikaExtractor

public TikaExtractor()

Method Detail

getActivitiesList

public java.lang.String[] getActivitiesList()

Return a list of activities that this connector generates. The connector does NOT need to be connected before this method is called.

Specified by:

getActivitiesList in interface org.apache.manifoldcf.agents.interfaces.ITransformationConnector

Overrides:

getActivitiesList in class org.apache.manifoldcf.agents.transformation.BaseTransformationConnector

Returns:

the set of activities.

getPipelineDescription

public org.apache.manifoldcf.core.interfaces.VersionContext getPipelineDescription(org.apache.manifoldcf.core.interfaces.Specification os)
                                                                            throws org.apache.manifoldcf.core.interfaces.ManifoldCFException,
                                                                                   org.apache.manifoldcf.agents.interfaces.ServiceInterruption

Get an output version string, given an output specification. The output version string is used to uniquely describe the pertinent details of the output specification and the configuration, to allow the Connector Framework to determine whether a document will need to be output again. Note that the contents of the document cannot be considered by this method, and that a different version string (defined in IRepositoryConnector) is used to describe the version of the actual document. This method presumes that the connector object has been configured, and it is thus able to communicate with the output data store should that be necessary.

Specified by:

getPipelineDescription in interface org.apache.manifoldcf.agents.interfaces.IPipelineConnector

Overrides:

getPipelineDescription in class org.apache.manifoldcf.agents.transformation.BaseTransformationConnector

Parameters:

os - is the current output specification for the job that is doing the crawling.

Returns:

a string, of unlimited length, which uniquely describes output configuration and specification in such a way that if two such strings are equal, the document will not need to be sent again to the output data store.

Throws:

org.apache.manifoldcf.core.interfaces.ManifoldCFException

org.apache.manifoldcf.agents.interfaces.ServiceInterruption

checkMimeTypeIndexable

public boolean checkMimeTypeIndexable(org.apache.manifoldcf.core.interfaces.VersionContext pipelineDescription,
                                      java.lang.String mimeType,
                                      org.apache.manifoldcf.agents.interfaces.IOutputCheckActivity checkActivity)
                               throws org.apache.manifoldcf.core.interfaces.ManifoldCFException,
                                      org.apache.manifoldcf.agents.interfaces.ServiceInterruption

Detect if a mime type is acceptable or not. This method is used to determine whether it makes sense to fetch a document in the first place.

Specified by:

checkMimeTypeIndexable in interface org.apache.manifoldcf.agents.interfaces.IPipelineConnector

Overrides:

checkMimeTypeIndexable in class org.apache.manifoldcf.agents.transformation.BaseTransformationConnector

Parameters:

pipelineDescription - is the document's pipeline version string, for this connection.

mimeType - is the mime type of the document.

checkActivity - is an object including the activities that can be performed by this method.

Returns:

true if the mime type can be accepted by this connector.

Throws:

org.apache.manifoldcf.core.interfaces.ManifoldCFException

org.apache.manifoldcf.agents.interfaces.ServiceInterruption

checkDocumentIndexable

public boolean checkDocumentIndexable(org.apache.manifoldcf.core.interfaces.VersionContext pipelineDescription,
                                      java.io.File localFile,
                                      org.apache.manifoldcf.agents.interfaces.IOutputCheckActivity checkActivity)
                               throws org.apache.manifoldcf.core.interfaces.ManifoldCFException,
                                      org.apache.manifoldcf.agents.interfaces.ServiceInterruption

Pre-determine whether a document (passed here as a File object) is acceptable or not. This method is used to determine whether a document needs to be actually transferred. This hook is provided mainly to support search engines that only handle a small set of accepted file types.

Specified by:

checkDocumentIndexable in interface org.apache.manifoldcf.agents.interfaces.IPipelineConnector

Overrides:

checkDocumentIndexable in class org.apache.manifoldcf.agents.transformation.BaseTransformationConnector

Parameters:

pipelineDescription - is the document's pipeline version string, for this connection.

localFile - is the local file to check.

checkActivity - is an object including the activities that can be done by this method.

Returns:

true if the file is acceptable, false if not.

Throws:

org.apache.manifoldcf.core.interfaces.ManifoldCFException

org.apache.manifoldcf.agents.interfaces.ServiceInterruption

checkLengthIndexable

public boolean checkLengthIndexable(org.apache.manifoldcf.core.interfaces.VersionContext pipelineDescription,
                                    long length,
                                    org.apache.manifoldcf.agents.interfaces.IOutputCheckActivity checkActivity)
                             throws org.apache.manifoldcf.core.interfaces.ManifoldCFException,
                                    org.apache.manifoldcf.agents.interfaces.ServiceInterruption

Pre-determine whether a document's length is acceptable. This method is used to determine whether to fetch a document in the first place.

Specified by:

checkLengthIndexable in interface org.apache.manifoldcf.agents.interfaces.IPipelineConnector

Overrides:

checkLengthIndexable in class org.apache.manifoldcf.agents.transformation.BaseTransformationConnector

Parameters:

pipelineDescription - is the document's pipeline version string, for this connection.

length - is the length of the document.

checkActivity - is an object including the activities that can be done by this method.

Returns:

true if the file is acceptable, false if not.

Throws:

org.apache.manifoldcf.core.interfaces.ManifoldCFException

org.apache.manifoldcf.agents.interfaces.ServiceInterruption

addOrReplaceDocumentWithException

public 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

Add (or replace) a document in the output data store using the connector. This method presumes that the connector object has been configured, and it is thus able to communicate with the output data store should that be necessary. The OutputSpecification is *not* provided to this method, because the goal is consistency, and if output is done it must be consistent with the output description, since that was what was partly used to determine if output should be taking place. So it may be necessary for this method to decode an output description string in order to determine what should be done.

Specified by:

addOrReplaceDocumentWithException in interface org.apache.manifoldcf.agents.interfaces.IPipelineConnector

Overrides:

addOrReplaceDocumentWithException in class org.apache.manifoldcf.agents.transformation.BaseTransformationConnector

Parameters:

documentURI - 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 - is 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.

Returns:

the document status (accepted or permanently rejected).

Throws:

java.io.IOException - only if there's a stream error reading the document data.

org.apache.manifoldcf.core.interfaces.ManifoldCFException

org.apache.manifoldcf.agents.interfaces.ServiceInterruption

getFormCheckJavascriptMethodName

public java.lang.String getFormCheckJavascriptMethodName(int connectionSequenceNumber)

Obtain the name of the form check javascript method to call.

Specified by:

getFormCheckJavascriptMethodName in interface org.apache.manifoldcf.agents.interfaces.IPipelineConnector

Overrides:

getFormCheckJavascriptMethodName in class org.apache.manifoldcf.agents.transformation.BaseTransformationConnector

Parameters:

connectionSequenceNumber - is the unique number of this connection within the job.

Returns:

the name of the form check javascript method.

getFormPresaveCheckJavascriptMethodName

public java.lang.String getFormPresaveCheckJavascriptMethodName(int connectionSequenceNumber)

Obtain the name of the form presave check javascript method to call.

Specified by:

getFormPresaveCheckJavascriptMethodName in interface org.apache.manifoldcf.agents.interfaces.IPipelineConnector

Overrides:

getFormPresaveCheckJavascriptMethodName in class org.apache.manifoldcf.agents.transformation.BaseTransformationConnector

Parameters:

connectionSequenceNumber - is the unique number of this connection within the job.

Returns:

the name of the form presave check javascript method.

outputConfigurationHeader

public 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

Output the configuration header section. This method is called in the head section of the connector's configuration page. Its purpose is to add the required tabs to the list, and to output any javascript methods that might be needed by the configuration editing HTML.

Specified by:

outputConfigurationHeader in interface org.apache.manifoldcf.core.interfaces.IConnector

Overrides:

outputConfigurationHeader in class org.apache.manifoldcf.core.connector.BaseConnector

Parameters:

threadContext - 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.

Throws:

org.apache.manifoldcf.core.interfaces.ManifoldCFException

java.io.IOException

outputConfigurationBody

public 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

Output the configuration body section. This method is called in the body section of the connector's configuration page. Its purpose is to present the required form elements for editing. The coder can presume that the HTML that is output from this configuration will be within appropriate <html>, <body>, and <form> tags. The name of the form is "editconnection".

Specified by:

outputConfigurationBody in interface org.apache.manifoldcf.core.interfaces.IConnector

Overrides:

outputConfigurationBody in class org.apache.manifoldcf.core.connector.BaseConnector

Parameters:

threadContext - 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.

Throws:

org.apache.manifoldcf.core.interfaces.ManifoldCFException

java.io.IOException

processConfigurationPost

public 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

Process a configuration post. This method is called at the start of the authority connector's configuration page, whenever there is a possibility that form data for a connection has been posted. Its purpose is to gather form information and modify the configuration parameters accordingly. The name of the posted form is "editconnection".

Specified by:

processConfigurationPost in interface org.apache.manifoldcf.core.interfaces.IConnector

Overrides:

processConfigurationPost in class org.apache.manifoldcf.core.connector.BaseConnector

Parameters:

threadContext - 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.

Returns:

null if all is well, or a string error message if there is an error that should prevent saving of the connection (and cause a redirection to an error page).

Throws:

org.apache.manifoldcf.core.interfaces.ManifoldCFException

connect

public void connect(org.apache.manifoldcf.core.interfaces.ConfigParams configParams)

Connect. The configuration parameters are included.

Specified by:

connect in interface org.apache.manifoldcf.core.interfaces.IConnector

Overrides:

connect in class org.apache.manifoldcf.core.connector.BaseConnector

Parameters:

configParams - are the configuration parameters for this connection.

disconnect

public void disconnect()
                throws org.apache.manifoldcf.core.interfaces.ManifoldCFException

Specified by:

disconnect in interface org.apache.manifoldcf.core.interfaces.IConnector

Overrides:

disconnect in class org.apache.manifoldcf.core.connector.BaseConnector

Throws:

org.apache.manifoldcf.core.interfaces.ManifoldCFException

initializeTikaParser

protected void initializeTikaParser()
                             throws org.apache.manifoldcf.core.interfaces.ManifoldCFException

Throws:

org.apache.manifoldcf.core.interfaces.ManifoldCFException

viewConfiguration

public 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

View configuration. This method is called in the body section of the authority connector's view configuration page. Its purpose is to present the connection information to the user. The coder can presume that the HTML that is output from this configuration will be within appropriate <html> and <body> tags.

Specified by:

viewConfiguration in interface org.apache.manifoldcf.core.interfaces.IConnector

Overrides:

viewConfiguration in class org.apache.manifoldcf.core.connector.BaseConnector

Parameters:

threadContext - 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.

Throws:

org.apache.manifoldcf.core.interfaces.ManifoldCFException

java.io.IOException

outputSpecificationHeader

public 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

Output the specification header section. This method is called in the head section of a job page which has selected a pipeline connection of the current type. Its purpose is to add the required tabs to the list, and to output any javascript methods that might be needed by the job editing HTML.

Specified by:

outputSpecificationHeader in interface org.apache.manifoldcf.agents.interfaces.IPipelineConnector

Overrides:

outputSpecificationHeader in class org.apache.manifoldcf.agents.transformation.BaseTransformationConnector

Parameters:

out - 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.

Throws:

org.apache.manifoldcf.core.interfaces.ManifoldCFException

java.io.IOException

outputSpecificationBody

public 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

Output the specification body section. This method is called in the body section of a job page which has selected a pipeline connection of the current type. Its purpose is to present the required form elements for editing. The coder can presume that the HTML that is output from this configuration will be within appropriate <html>, <body>, and <form> tags. The name of the form is "editjob".

Specified by:

outputSpecificationBody in interface org.apache.manifoldcf.agents.interfaces.IPipelineConnector

Overrides:

outputSpecificationBody in class org.apache.manifoldcf.agents.transformation.BaseTransformationConnector

Parameters:

out - 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.

Throws:

org.apache.manifoldcf.core.interfaces.ManifoldCFException

java.io.IOException

processSpecificationPost

public 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

Process a specification post. This method is called at the start of job's edit or view page, whenever there is a possibility that form data for a connection has been posted. Its purpose is to gather form information and modify the transformation specification accordingly. The name of the posted form is "editjob".

Specified by:

processSpecificationPost in interface org.apache.manifoldcf.agents.interfaces.IPipelineConnector

Overrides:

processSpecificationPost in class org.apache.manifoldcf.agents.transformation.BaseTransformationConnector

Parameters:

variableContext - 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.

Returns:

null if all is well, or a string error message if there is an error that should prevent saving of the job (and cause a redirection to an error page).

Throws:

org.apache.manifoldcf.core.interfaces.ManifoldCFException

viewSpecification

public 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

View specification. This method is called in the body section of a job's view page. Its purpose is to present the pipeline specification information to the user. The coder can presume that the HTML that is output from this configuration will be within appropriate <html> and <body>tags.

Specified by:

viewSpecification in interface org.apache.manifoldcf.agents.interfaces.IPipelineConnector

Overrides:

viewSpecification in class org.apache.manifoldcf.agents.transformation.BaseTransformationConnector

Parameters:

out - 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.

Throws:

org.apache.manifoldcf.core.interfaces.ManifoldCFException

java.io.IOException

fillInTikaConfigTab

protected static void fillInTikaConfigTab(java.util.Map<java.lang.String,java.lang.Object> velocityContext,
                                          org.apache.manifoldcf.core.interfaces.IHTTPOutput out,
                                          org.apache.manifoldcf.core.interfaces.ConfigParams parameters)

fillInFieldMappingSpecificationMap

protected static void fillInFieldMappingSpecificationMap(java.util.Map<java.lang.String,java.lang.Object> paramMap,
                                                         org.apache.manifoldcf.core.interfaces.Specification os)

fillInExceptionsSpecificationMap

protected static void fillInExceptionsSpecificationMap(java.util.Map<java.lang.String,java.lang.Object> paramMap,
                                                       org.apache.manifoldcf.core.interfaces.Specification os)

fillInBoilerplateSpecificationMap

protected static void fillInBoilerplateSpecificationMap(java.util.Map<java.lang.String,java.lang.Object> paramMap,
                                                        org.apache.manifoldcf.core.interfaces.Specification os)

handleTikaException

protected static int handleTikaException(org.apache.tika.exception.TikaException e)
                                  throws java.io.IOException,
                                         org.apache.manifoldcf.core.interfaces.ManifoldCFException,
                                         org.apache.manifoldcf.agents.interfaces.ServiceInterruption

Throws:

java.io.IOException

org.apache.manifoldcf.core.interfaces.ManifoldCFException

org.apache.manifoldcf.agents.interfaces.ServiceInterruption

handleSaxException

protected static int handleSaxException(org.xml.sax.SAXException e)
                                 throws java.io.IOException,
                                        org.apache.manifoldcf.core.interfaces.ManifoldCFException,
                                        org.apache.manifoldcf.agents.interfaces.ServiceInterruption

Throws:

java.io.IOException

org.apache.manifoldcf.core.interfaces.ManifoldCFException

org.apache.manifoldcf.agents.interfaces.ServiceInterruption

handleIOException

protected static int handleIOException(java.io.IOException e)
                                throws org.apache.manifoldcf.core.interfaces.ManifoldCFException

Throws:

org.apache.manifoldcf.core.interfaces.ManifoldCFException