org.webharvest.runtime
Class Scraper

java.lang.Object
  org.webharvest.runtime.Scraper

public class Scraper
extends java.lang.Object

Basic runtime class.

Field Summary

static int	STATUS_ERROR
static int	STATUS_EXIT
static int	STATUS_FINISHED
static int	STATUS_PAUSED
static int	STATUS_READY
static int	STATUS_RUNNING
static int	STATUS_STOPPED

Constructor Summary

Scraper(ScraperConfiguration configuration, java.lang.String workingDir)
Constructor.

Method Summary

void	addFunctionParam(java.lang.String name, Variable value)
void	addRunningFunction(CallProcessor callProcessor)
void	addRuntimeListener(ScraperRuntimeListener listener)
void	addVariablesToContext(java.util.Map map) Add all map values to the context.
void	addVariableToContext(java.lang.String name, java.lang.Object value) Adds parameter with specified name and value to the context.
void	clearFunctionParams()
void	continueExecution()
void	dispose()
void	execute()
Variable	execute(java.util.List<IElementDef> ops)
void	exitExecution(java.lang.String message)
void	finishExecutingProcessor()
ScraperConfiguration	getConfiguration()
java.sql.Connection	getConnection(java.lang.String jdbc, java.lang.String connection, java.lang.String username, java.lang.String password) Get connection from the connection pool, and first create one if necessery
ScraperContext	getContext()
java.util.Map	getFunctionParams()
HttpClientManager	getHttpClientManager()
org.apache.log4j.Logger	getLogger()
java.lang.String	getMessage()
BaseProcessor	getParentRunningProcessor(BaseProcessor processor)
CallProcessor	getRunningFunction()
HttpProcessor	getRunningHttpProcessor()
int	getRunningLevel()
BaseProcessor	getRunningProcessor()
BaseProcessor	getRunningProcessorOfType(java.lang.Class processorClazz)
RuntimeConfig	getRuntimeConfig()
org.webharvest.runtime.scripting.ScriptEngine	getScriptEngine()
org.webharvest.runtime.scripting.ScriptEngine	getScriptEngine(java.lang.String engineType)
int	getStatus()
java.lang.String	getWorkingDir()
void	informListenersAboutError(java.lang.Exception e) Inform all scraper listeners that an error has occured during scraper execution.
boolean	isDebugMode()
void	pauseExecution()
void	processorFinishedExecution(BaseProcessor processor, java.util.Map properties)
void	releaseDBConnections() Releases all DB connections from the pool.
void	removeRunningFunction()
void	removeRunningHttpProcessor()
void	removeRuntimeListener(ScraperRuntimeListener listener)
void	setDebug(boolean debug)
void	setExecutingProcessor(BaseProcessor processor)
void	setRunningHttpProcessor(HttpProcessor httpProcessor)
void	stopExecution()

Methods inherited from class java.lang.Object

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

Field Detail

STATUS_READY

public static final int STATUS_READY

See Also:

Constant Field Values

STATUS_RUNNING

public static final int STATUS_RUNNING

See Also:

Constant Field Values

STATUS_PAUSED

public static final int STATUS_PAUSED

See Also:

Constant Field Values

STATUS_FINISHED

public static final int STATUS_FINISHED

See Also:

Constant Field Values

STATUS_STOPPED

public static final int STATUS_STOPPED

See Also:

Constant Field Values

STATUS_ERROR

public static final int STATUS_ERROR

See Also:

Constant Field Values

STATUS_EXIT

public static final int STATUS_EXIT

See Also:

Constant Field Values

Constructor Detail

Scraper

public Scraper(ScraperConfiguration configuration,
               java.lang.String workingDir)

Constructor.

Parameters:

configuration -

workingDir -

Method Detail

addVariableToContext

public void addVariableToContext(java.lang.String name,
                                 java.lang.Object value)

Adds parameter with specified name and value to the context. This way some predefined variables can be put in runtime context before execution starts.

Parameters:

name -

value -

addVariablesToContext

public void addVariablesToContext(java.util.Map map)

Add all map values to the context.

Parameters:

map -

execute

public Variable execute(java.util.List<IElementDef> ops)

execute

public void execute()

getContext

public ScraperContext getContext()

getConfiguration

public ScraperConfiguration getConfiguration()

getWorkingDir

public java.lang.String getWorkingDir()

getHttpClientManager

public HttpClientManager getHttpClientManager()

addRunningFunction

public void addRunningFunction(CallProcessor callProcessor)

getRunningFunction

public CallProcessor getRunningFunction()

clearFunctionParams

public void clearFunctionParams()

addFunctionParam

public void addFunctionParam(java.lang.String name,
                             Variable value)

getFunctionParams

public java.util.Map getFunctionParams()

removeRunningFunction

public void removeRunningFunction()

getRunningHttpProcessor

public HttpProcessor getRunningHttpProcessor()

setRunningHttpProcessor

public void setRunningHttpProcessor(HttpProcessor httpProcessor)

removeRunningHttpProcessor

public void removeRunningHttpProcessor()

getRunningLevel

public int getRunningLevel()

isDebugMode

public boolean isDebugMode()

setDebug

public void setDebug(boolean debug)

getScriptEngine

public org.webharvest.runtime.scripting.ScriptEngine getScriptEngine()

getScriptEngine

public org.webharvest.runtime.scripting.ScriptEngine getScriptEngine(java.lang.String engineType)

getLogger

public org.apache.log4j.Logger getLogger()

getRunningProcessor

public BaseProcessor getRunningProcessor()

getParentRunningProcessor

public BaseProcessor getParentRunningProcessor(BaseProcessor processor)

Parameters:

processor - Processor whose parent is needed.

Returns:

Parent running processor of the specified running processor, or null if processor is not currently running or if it is top running processor.

getRunningProcessorOfType

public BaseProcessor getRunningProcessorOfType(java.lang.Class processorClazz)

Parameters:

processorClazz - Class of enclosing running processor.

Returns:

Parent running processor in the tree of specified class, or null if it doesn't exist.

getRuntimeConfig

public RuntimeConfig getRuntimeConfig()

getConnection

public java.sql.Connection getConnection(java.lang.String jdbc,
                                         java.lang.String connection,
                                         java.lang.String username,
                                         java.lang.String password)

Get connection from the connection pool, and first create one if necessery

Parameters:

jdbc - Name of JDBC class

connection - JDBC connection string

username - Username

password - Password

Returns:

JDBC connection used to access database

setExecutingProcessor

public void setExecutingProcessor(BaseProcessor processor)

finishExecutingProcessor

public void finishExecutingProcessor()

processorFinishedExecution

public void processorFinishedExecution(BaseProcessor processor,
                                       java.util.Map properties)

addRuntimeListener

public void addRuntimeListener(ScraperRuntimeListener listener)

removeRuntimeListener

public void removeRuntimeListener(ScraperRuntimeListener listener)

getStatus

public int getStatus()

stopExecution

public void stopExecution()

exitExecution

public void exitExecution(java.lang.String message)

getMessage

public java.lang.String getMessage()

pauseExecution

public void pauseExecution()

continueExecution

public void continueExecution()

informListenersAboutError

public void informListenersAboutError(java.lang.Exception e)

Inform all scraper listeners that an error has occured during scraper execution.

releaseDBConnections

public void releaseDBConnections()

Releases all DB connections from the pool.

dispose

public void dispose()