Package com.crawljax.core.configuration

Class CrawlRules.CrawlRulesBuilder

java.lang.Object

com.crawljax.core.configuration.CrawlRules.CrawlRulesBuilder

Enclosing class:

CrawlRules

public static final class CrawlRules.CrawlRulesBuilder
extends Object

Field Summary

Fields

Modifier and Type	Field	Description
private CrawlActionsBuilder	crawlActionsBuilder
private com.google.common.collect.ImmutableSortedSet.Builder<Eventable.EventType>	crawlEvents
private CrawljaxConfiguration.CrawljaxConfigurationBuilder	crawljaxBuilder
private CrawlRules	crawlRules
private com.google.common.collect.ImmutableSortedSet.Builder<String>	ignoredFrameIdentifiers
private com.google.common.collect.ImmutableList.Builder<Invariant>	invariants
private com.google.common.collect.ImmutableList.Builder<OracleComparator>	oracleComparators
private PreCrawlConfiguration.PreCrawlConfigurationBuilder	preCrawlConfig

Constructor Summary

Constructors

Modifier	Constructor	Description
private	CrawlRulesBuilder(CrawljaxConfiguration.CrawljaxConfigurationBuilder crawljaxBuilder)

Method Summary

Modifier and Type	Method	Description
PreCrawlConfiguration.PreCrawlConfigurationBuilder	addCrawlCondition(CrawlCondition... condition)
PreCrawlConfiguration.PreCrawlConfigurationBuilder	addCrawlCondition(String description, Condition crawlCondition)
CrawlRules.CrawlRulesBuilder	addEventType(Eventable.EventType... eventTypes)
CrawlRules.CrawlRulesBuilder	addInvariant(Invariant... invariant)
CrawlRules.CrawlRulesBuilder	addInvariant(String description, Condition condition)
CrawlRules.CrawlRulesBuilder	addOracleComparator(OracleComparator... oracle)
PreCrawlConfiguration.PreCrawlConfigurationBuilder	addWaitCondition(WaitCondition... condition)
CrawlRules.CrawlRulesBuilder	applyNonSelAdvantage(boolean applyNonSelAdv)
void	avoidDifferentBacktracking(boolean avoidDifferentBacktracking)
void	avoidUnrelatedBacktracking(boolean avoidUnrelatedBacktracking)
(package private) CrawlRules	build()
CrawlElement	click(String tagName)
CrawlRules.CrawlRulesBuilder	click(String... tagNames)
CrawlRules.CrawlRulesBuilder	clickDefaultElements()
CrawlRules.CrawlRulesBuilder	clickElementsInRandomOrder(boolean randomize)
CrawlRules.CrawlRulesBuilder	clickElementsWithClickEventHandler()
CrawlRules.CrawlRulesBuilder	clickOnce(boolean once)
CrawlRules.CrawlRulesBuilder	crawlFrames(boolean frames)
CrawlRules.CrawlRulesBuilder	crawlHiddenAnchors(boolean anchors)	Set Crawljax to click hidden anchors or not.
CrawlElement	dontClick(String tagName)
CrawlActionsBuilder.ExcludeByParentBuilder	dontClickChildrenOf(String tagName)
CrawlRules.CrawlRulesBuilder	dontCrawlFrame(String frame)
CrawljaxConfiguration.CrawljaxConfigurationBuilder	endRules()	Helper method for method chaining.
CrawlElement	enter(String tagName)
PreCrawlConfiguration.PreCrawlConfigurationBuilder	filterAttributeNames(String names)
CrawlRules.CrawlRulesBuilder	followExternalLinks(boolean follow)	Follow links in anchor tags that have an href element that points to an URL outside of this website.
CrawlRules.CrawlRulesBuilder	setBacktrackingRules(boolean avoidUnrelatedBacktracking, boolean avoidDifferentBacktracking, boolean useEquivalentReset)	avoiding differentbacktracking automatically stops unrelatedbacktracking
CrawlRules.CrawlRulesBuilder	setCrawlNearDuplicates(boolean crawlNearDuplicates)
CrawlRules.CrawlRulesBuilder	setCrawlPriorityMode(CrawlRules.CrawlPriorityMode crawlPriorityMode)
CrawlRules.CrawlRulesBuilder	setDelayNearDuplicateCrawling(boolean delayNearDuplicateCrawling)
CrawlRules.CrawlRulesBuilder	setFormFillMode(CrawlRules.FormFillMode formFillMode)
CrawlRules.CrawlRulesBuilder	setFormFillOrder(CrawlRules.FormFillOrder formFillOrder)
CrawlRules.CrawlRulesBuilder	setInputSpec(InputSpecification spec)
CrawlRules.CrawlRulesBuilder	setRestoreConnectedStates(boolean b)
private void	setupOracleComparatorsOrDefault()
CrawlRules.CrawlRulesBuilder	setUsefulFragmentRules(FragmentRules fragmentRules)
CrawlRules.CrawlRulesBuilder	skipExploredActions(boolean skipExploredActions, int maxRepeatExploredActions)	maxRepeat default value is 2
CrawlRules.CrawlRulesBuilder	testInvariantsWhileCrawling(boolean test)
void	useEquivalentReset(boolean useEquivalentReset)
CrawlRules.CrawlRulesBuilder	waitAfterEvent(long time, TimeUnit unit)
CrawlRules.CrawlRulesBuilder	waitAfterReloadUrl(long time, TimeUnit unit)

Methods inherited from class java.lang.Object

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

Field Detail

crawlRules

private final CrawlRules crawlRules

crawlActionsBuilder

private final CrawlActionsBuilder crawlActionsBuilder

preCrawlConfig

private final PreCrawlConfiguration.PreCrawlConfigurationBuilder preCrawlConfig

ignoredFrameIdentifiers

private final com.google.common.collect.ImmutableSortedSet.Builder<String> ignoredFrameIdentifiers

crawljaxBuilder

private final CrawljaxConfiguration.CrawljaxConfigurationBuilder crawljaxBuilder

crawlEvents

private final com.google.common.collect.ImmutableSortedSet.Builder<Eventable.EventType> crawlEvents

invariants

private final com.google.common.collect.ImmutableList.Builder<Invariant> invariants

oracleComparators

private final com.google.common.collect.ImmutableList.Builder<OracleComparator> oracleComparators

Constructor Detail

CrawlRulesBuilder

private CrawlRulesBuilder(CrawljaxConfiguration.CrawljaxConfigurationBuilder crawljaxBuilder)

Method Detail

setFormFillMode

public CrawlRules.CrawlRulesBuilder setFormFillMode(CrawlRules.FormFillMode formFillMode)

setFormFillOrder

public CrawlRules.CrawlRulesBuilder setFormFillOrder(CrawlRules.FormFillOrder formFillOrder)

setCrawlPriorityMode

public CrawlRules.CrawlRulesBuilder setCrawlPriorityMode(CrawlRules.CrawlPriorityMode crawlPriorityMode)

setCrawlNearDuplicates

public CrawlRules.CrawlRulesBuilder setCrawlNearDuplicates(boolean crawlNearDuplicates)

setDelayNearDuplicateCrawling

public CrawlRules.CrawlRulesBuilder setDelayNearDuplicateCrawling(boolean delayNearDuplicateCrawling)

applyNonSelAdvantage

public CrawlRules.CrawlRulesBuilder applyNonSelAdvantage(boolean applyNonSelAdv)

avoidUnrelatedBacktracking

public void avoidUnrelatedBacktracking(boolean avoidUnrelatedBacktracking)

avoidDifferentBacktracking

public void avoidDifferentBacktracking(boolean avoidDifferentBacktracking)

useEquivalentReset

public void useEquivalentReset(boolean useEquivalentReset)

skipExploredActions

public CrawlRules.CrawlRulesBuilder skipExploredActions(boolean skipExploredActions,
                                                        int maxRepeatExploredActions)

maxRepeat default value is 2

Parameters:

skipExploredActions -

maxRepeatExploredActions -

Returns:

setBacktrackingRules

public CrawlRules.CrawlRulesBuilder setBacktrackingRules(boolean avoidUnrelatedBacktracking,
                                                         boolean avoidDifferentBacktracking,
                                                         boolean useEquivalentReset)

avoiding differentbacktracking automatically stops unrelatedbacktracking

Parameters:

avoidUnrelatedBacktracking -

avoidDifferentBacktracking -

useEquivalentReset -

Returns:

setUsefulFragmentRules

public CrawlRules.CrawlRulesBuilder setUsefulFragmentRules(FragmentRules fragmentRules)

setRestoreConnectedStates

public CrawlRules.CrawlRulesBuilder setRestoreConnectedStates(boolean b)

dontCrawlFrame

public CrawlRules.CrawlRulesBuilder dontCrawlFrame(String frame)

Parameters:

frame - A frame that should be excluded from the DOM, before doing any other operations.

addEventType

public CrawlRules.CrawlRulesBuilder addEventType(Eventable.EventType... eventTypes)

Parameters:

eventTypes - Add an Eventable.EventType that should be triggered by Crawljax. If none are defined, it will only use Eventable.EventType.click

addInvariant

public CrawlRules.CrawlRulesBuilder addInvariant(Invariant... invariant)

addInvariant

public CrawlRules.CrawlRulesBuilder addInvariant(String description,
                                                 Condition condition)

Parameters:

description - The invariants description.

condition - The condition for the invariant.

See Also:

Invariant(String, Condition)

addOracleComparator

public CrawlRules.CrawlRulesBuilder addOracleComparator(OracleComparator... oracle)

addWaitCondition

public PreCrawlConfiguration.PreCrawlConfigurationBuilder addWaitCondition(WaitCondition... condition)

Parameters:

condition - add a WaitCondition.

addCrawlCondition

public PreCrawlConfiguration.PreCrawlConfigurationBuilder addCrawlCondition(CrawlCondition... condition)

Parameters:

condition - add a CrawlCondition

addCrawlCondition

public PreCrawlConfiguration.PreCrawlConfigurationBuilder addCrawlCondition(String description,
                                                                            Condition crawlCondition)

See Also:

CrawlCondition(String, Condition)

filterAttributeNames

public PreCrawlConfiguration.PreCrawlConfigurationBuilder filterAttributeNames(String names)

Parameters:

names - add an attribute name you want to filter before parsing the dom.

setInputSpec

public CrawlRules.CrawlRulesBuilder setInputSpec(InputSpecification spec)

testInvariantsWhileCrawling

public CrawlRules.CrawlRulesBuilder testInvariantsWhileCrawling(boolean test)

Parameters:

test - Test the invariants while crawling or not. Default is true.

clickOnce

public CrawlRules.CrawlRulesBuilder clickOnce(boolean once)

Parameters:

once - Set the crawler to interact with any element only once. Default is true

clickElementsInRandomOrder

public CrawlRules.CrawlRulesBuilder clickElementsInRandomOrder(boolean randomize)

Parameters:

randomize - Click candidate elements derived from the DOM in random order in stead of in the order that they are found.

crawlFrames

public CrawlRules.CrawlRulesBuilder crawlFrames(boolean frames)

Parameters:

frames - Crawl frames in a page. Default is true.

waitAfterReloadUrl

public CrawlRules.CrawlRulesBuilder waitAfterReloadUrl(long time,
                                                       TimeUnit unit)

Parameters:

time - The time to wait after a URL is loaded. Default is 500 milliseconds.

unit - The time unit.

waitAfterEvent

public CrawlRules.CrawlRulesBuilder waitAfterEvent(long time,
                                                   TimeUnit unit)

Parameters:

time - The time to wait after an event is fired. Default is 500 milliseconds.

unit - The time unit.

crawlHiddenAnchors

public CrawlRules.CrawlRulesBuilder crawlHiddenAnchors(boolean anchors)

Set Crawljax to click hidden anchors or not. Default is false.

Pro:

The benefit of clicking hidden anchors is that Crawljax isn't capable of clicking elements that are hidden for example because you have to hover another element first. This happens in most fold-out menus for example. Enabling this function allows Crawljax to find more states that are hidden this way.

Con:

If a anchor tag is never visible in the browser in any way, Crawljax will crawl it anyway. This makes the Crawl inconsistent with what the user experiences.

click

public CrawlElement click(String tagName)

Parameters:

tagName -

See Also:

CrawlActionsBuilder.click(java.lang.String)

enter

public CrawlElement enter(String tagName)

click

public CrawlRules.CrawlRulesBuilder click(String... tagNames)

Parameters:

tagNames -

Returns:

See Also:

CrawlActionsBuilder.click(java.lang.String[])

clickDefaultElements

public CrawlRules.CrawlRulesBuilder clickDefaultElements()

Returns:

See Also:

CrawlActionsBuilder.clickDefaultElements()

clickElementsWithClickEventHandler

public CrawlRules.CrawlRulesBuilder clickElementsWithClickEventHandler()

Returns:

See Also:

CrawlActionsBuilder.clickElementsWithClickEventHandler()

dontClick

public CrawlElement dontClick(String tagName)

See Also:

CrawlActionsBuilder.dontClick(java.lang.String)

dontClickChildrenOf

public CrawlActionsBuilder.ExcludeByParentBuilder dontClickChildrenOf(String tagName)

Parameters:

tagName -

See Also:

CrawlActionsBuilder.dontClickChildrenOf(java.lang.String)

followExternalLinks

public CrawlRules.CrawlRulesBuilder followExternalLinks(boolean follow)

Follow links in anchor tags that have an href element that points to an URL outside of this website. This does not prevent JavaScript from opening an external URL.

Once the browser reaches an external URL it will not accept that URL as a new state. Crawljax is not meant to crawl outside a website. This option exists so that you can check all URLs for 404 errors.

Parameters:

follow - Set to true to follow external urls. Default is false.

endRules

public CrawljaxConfiguration.CrawljaxConfigurationBuilder endRules()

Helper method for method chaining. Now you can do

 CrawljaxConfiguration.builderFor("http://example.com").crawlRules()
         .followExternalLinks(true).endRules().build();
 

Returns:

The CrawljaxConfiguration.CrawljaxConfigurationBuilder to make method chaining easier.

build

CrawlRules build()

setupOracleComparatorsOrDefault

private void setupOracleComparatorsOrDefault()