Package com.crawljax.core.state

Examples of com.crawljax.core.state.StateVertex

380
381
382
383
384
385
386
387
388
389
390
391
      context.getSession().addCrawlPath(crawlpath.immutableCopy());
    }
  }

  private void parseCurrentPageForCandidateElements() {
    StateVertex currentState = stateMachine.getCurrentState();
    LOG.debug("Parsing DOM of state {} for candidate elements", currentState.getName());
    ImmutableList<CandidateElement> extract = candidateExtractor.extract(currentState);
   
    plugins.runPreStateCrawlingPlugins(context, extract, currentState);
    candidateActionCache.addActions(extract, currentState);
  }
View Full Code Here
425
426
427
428
429
430
431
432
433
  private void goBackOneState() {
    LOG.debug("Going back one state");
    CrawlPath currentPath = crawlpath.immutableCopy();
    crawlpath = null;
    StateVertex current = stateMachine.getCurrentState();
    reset();
    follow(currentPath, current);
  }
View Full Code Here
440
441
442
443
444
445
446
447
448
449
450
451
452
453
   */
  public StateVertex crawlIndex() {
    LOG.debug("Setting up vertex of the index page");
    browser.goToUrl(url);
    plugins.runOnUrlLoadPlugins(context);
    StateVertex index =
            StateMachine.createIndex(url.toExternalForm(), browser.getStrippedDom(),
                    stateComparator.getStrippedDom(browser));
    Preconditions.checkArgument(index.getId() == StateVertex.INDEX_ID,
            "It seems some the index state is crawled more than once.");

    LOG.debug("Parsing the index for candidate elements");
    ImmutableList<CandidateElement> extract = candidateExtractor.extract(index);

View Full Code Here
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
  }

  private void follow(CrawlPath path, StateVertex targetState)
          throws StateUnreachableException,
          CrawljaxException {
    StateVertex curState = context.getSession().getInitialState();

    for (Eventable clickable : path) {

      checkCrawlConditions(targetState);

      LOG.debug("Backtracking by executing {} on element: {}", clickable.getEventType(),
              clickable);

      boolean switched = stateMachine.changeState(clickable.getTargetStateVertex());
      if (!switched) {
        throw new StateUnreachableException(targetState, "Could not switch states");
      }
      curState = clickable.getTargetStateVertex();
      crawlpath.add(clickable);
      handleInputElements(clickable);
      if (fireEvent(clickable)) {
        if (crawlerLeftDomain()) {
          throw new StateUnreachableException(targetState,
                  "Domain left while following path");
        }
        int depth = crawlDepth.incrementAndGet();
        LOG.info("Crawl depth is now {}", depth);
        plugins.runOnRevisitStatePlugins(context, curState);

      } else {
        throw new StateUnreachableException(targetState, "couldn't fire eventable "
                + clickable);
      }

      checkCrawlConditions(targetState);
    }

    if (!curState.equals(targetState)) {
      throw new StateUnreachableException(targetState,
              "The path didn't result in the desired state but in state "
                      + curState.getName());
    }
  }
View Full Code Here
341
342
343
344
345
346
347
348
349
350
351
  private void inspectNewState(Eventable event) {
    if (crawlerLeftDomain()) {
      LOG.debug("The browser left the domain. Going back one state...");
      goBackOneState();
    } else {
      StateVertex newState = stateMachine.newStateFor(browser);
      if (domChanged(event, newState)) {
        inspectNewDom(event, newState);
      } else {
        LOG.debug("Dom unchanged");
      }
View Full Code Here
375
376
377
378
379
380
381
382
383
384
385
386
      context.getSession().addCrawlPath(crawlpath.immutableCopy());
    }
  }

  private void parseCurrentPageForCandidateElements() {
    StateVertex currentState = stateMachine.getCurrentState();
    LOG.debug("Parsing DOM of state {} for candidate elements", currentState.getName());
    ImmutableList<CandidateElement> extract = candidateExtractor.extract(currentState);

    plugins.runPreStateCrawlingPlugins(context, extract, currentState);

    candidateActionCache.addActions(extract, currentState);
View Full Code Here
422
423
424
425
426
427
428
429
430
  private void goBackOneState() {
    LOG.debug("Going back one state");
    CrawlPath currentPath = crawlpath.immutableCopy();
    crawlpath = null;
    StateVertex current = stateMachine.getCurrentState();
    reset();
    follow(currentPath, current);
  }
View Full Code Here
437
438
439
440
441
442
443
444
445
446
447
448
449
   */
  public StateVertex crawlIndex() {
    LOG.debug("Setting up vertex of the index page");
    browser.goToUrl(url);
    plugins.runOnUrlLoadPlugins(context);
    StateVertex index = StateMachine.createIndex(url.toExternalForm(), browser.getDom(),
            stateComparator.getStrippedDom(browser));
    Preconditions.checkArgument(index.getId() == StateVertex.INDEX_ID,
            "It seems some the index state is crawled more than once.");

    LOG.debug("Parsing the index for candidate elements");
    ImmutableList<CandidateElement> extract = candidateExtractor.extract(index);

View Full Code Here
61
62
63
64
65
66
67
68
69
70
71
  @Override
  public CrawlSession call() {
    setMaximumCrawlTimeIfNeeded();
    plugins.runPreCrawlingPlugins(config);
    CrawlTaskConsumer firstConsumer = consumerFactory.get();
    StateVertex firstState = firstConsumer.crawlIndex();
    crawlSessionProvider.setup(firstState);
    plugins.runOnNewStatePlugins(firstConsumer.getContext(), firstState);
    executeConsumers(firstConsumer);
    return crawlSessionProvider.get();
  }
View Full Code Here
166
167
168
169
170
171
172
173
174
175
176
    assertThat(config.getCrawlRules().followExternalLinks(), is(true));
    assertThat(extract, hasSize(3));
  }

  private List<CandidateElement> extractFromTestFile(CandidateElementExtractor extractor) {
    StateVertex currentState = Mockito.mock(StateVertex.class);
    String file = "/candidateElementExtractorTest/domWithOneExternalAndTwoInternal.html";
    URL dom = Resources.getResource(getClass(), file);
    browser.goToUrl(dom);
    List<CandidateElement> extract = extractor.extract(currentState);
    return extract;
View Full Code Here
TOP

Related Classes of com.crawljax.core.state.StateVertex

  • com.crawljax.browser.matchers.StateFlowGraphMatchers
  • com.crawljax.core.CandidateCrawlAction
  • com.crawljax.core.CandidateElement
  • com.crawljax.core.CandidateElementExtractorTest
  • com.crawljax.core.CrawlController
  • com.crawljax.core.CrawlControllerTest
  • com.crawljax.core.Crawler
  • com.crawljax.core.CrawlSession
  • com.crawljax.core.CrawlTaskConsumer
  • com.crawljax.core.InitialCrawler
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.