Search in sources :

Example 6 with Rule

use of org.codelibs.fess.crawler.rule.Rule in project fess-crawler by codelibs.

the class RuleManagerImplTest method test_getRule_sitemaps4.

public void test_getRule_sitemaps4() {
    final ResponseData responseData = new ResponseData();
    responseData.setUrl("http://www.example.com/sitemap1.txt.gz");
    File file = ResourceUtil.getResourceAsFile("sitemaps/sitemap1.xml.gz");
    responseData.setResponseBody(file, false);
    final Rule rule = ruleManager.getRule(responseData);
    assertNotNull(rule);
    assertEquals("sitemapsRule", rule.getRuleId());
    CloseableUtil.closeQuietly(responseData);
}
Also used : ResponseData(org.codelibs.fess.crawler.entity.ResponseData) Rule(org.codelibs.fess.crawler.rule.Rule) File(java.io.File)

Example 7 with Rule

use of org.codelibs.fess.crawler.rule.Rule in project fess-crawler by codelibs.

the class CrawlerThread method processResponse.

protected void processResponse(final UrlQueue<?> urlQueue, final ResponseData responseData) {
    // get a rule
    final Rule rule = crawlerContext.ruleManager.getRule(responseData);
    if (rule == null) {
        log(logHelper, LogType.NO_RULE, crawlerContext, urlQueue, responseData);
    } else {
        responseData.setRuleId(rule.getRuleId());
        final ResponseProcessor responseProcessor = rule.getResponseProcessor();
        if (responseProcessor == null) {
            log(logHelper, LogType.NO_RESPONSE_PROCESSOR, crawlerContext, urlQueue, responseData, rule);
        } else {
            responseProcessor.process(responseData);
        }
    }
}
Also used : Rule(org.codelibs.fess.crawler.rule.Rule) ResponseProcessor(org.codelibs.fess.crawler.processor.ResponseProcessor)

Example 8 with Rule

use of org.codelibs.fess.crawler.rule.Rule in project fess by codelibs.

the class FileListIndexUpdateCallbackImpl method processRequest.

protected String processRequest(final Map<String, String> paramMap, final Map<String, Object> dataMap, final String url, final CrawlerClient client) {
    final long startTime = System.currentTimeMillis();
    try (final ResponseData responseData = client.execute(RequestDataBuilder.newRequestData().get().url(url).build())) {
        if (responseData.getRedirectLocation() != null) {
            return responseData.getRedirectLocation();
        }
        responseData.setExecutionTime(System.currentTimeMillis() - startTime);
        if (dataMap.containsKey(Constants.SESSION_ID)) {
            responseData.setSessionId((String) dataMap.get(Constants.SESSION_ID));
        } else {
            responseData.setSessionId(paramMap.get(Constants.CRAWLING_INFO_ID));
        }
        final RuleManager ruleManager = SingletonLaContainer.getComponent(RuleManager.class);
        final Rule rule = ruleManager.getRule(responseData);
        if (rule == null) {
            logger.warn("No url rule. Data: {}", dataMap);
        } else {
            responseData.setRuleId(rule.getRuleId());
            final ResponseProcessor responseProcessor = rule.getResponseProcessor();
            if (responseProcessor instanceof DefaultResponseProcessor) {
                final Transformer transformer = ((DefaultResponseProcessor) responseProcessor).getTransformer();
                final ResultData resultData = transformer.transform(responseData);
                final byte[] data = resultData.getData();
                if (data != null) {
                    try {
                        @SuppressWarnings("unchecked") final Map<String, Object> responseDataMap = (Map<String, Object>) SerializeUtil.fromBinaryToObject(data);
                        dataMap.putAll(responseDataMap);
                    } catch (final Exception e) {
                        throw new CrawlerSystemException("Could not create an instance from bytes.", e);
                    }
                }
                // remove
                String[] ignoreFields;
                if (paramMap.containsKey("ignore.field.names")) {
                    ignoreFields = paramMap.get("ignore.field.names").split(",");
                } else {
                    ignoreFields = new String[] { Constants.INDEXING_TARGET, Constants.SESSION_ID };
                }
                stream(ignoreFields).of(stream -> stream.map(String::trim).forEach(s -> dataMap.remove(s)));
                indexUpdateCallback.store(paramMap, dataMap);
            } else {
                logger.warn("The response processor is not DefaultResponseProcessor. responseProcessor: {}, Data: {}", responseProcessor, dataMap);
            }
        }
        return null;
    } catch (final ChildUrlsException e) {
        throw new DataStoreCrawlingException(url, "Redirected to " + e.getChildUrlList().stream().map(RequestData::getUrl).collect(Collectors.joining(", ")), e);
    } catch (final Exception e) {
        throw new DataStoreCrawlingException(url, "Failed to add: " + dataMap, e);
    }
}
Also used : Constants(org.codelibs.fess.Constants) IndexingHelper(org.codelibs.fess.helper.IndexingHelper) ThreadPoolExecutor(java.util.concurrent.ThreadPoolExecutor) SearchEngineClient(org.codelibs.fess.es.client.SearchEngineClient) SerializeUtil(org.codelibs.core.io.SerializeUtil) DefaultResponseProcessor(org.codelibs.fess.crawler.processor.impl.DefaultResponseProcessor) Deque(java.util.Deque) CrawlerSystemException(org.codelibs.fess.crawler.exception.CrawlerSystemException) Transformer(org.codelibs.fess.crawler.transformer.Transformer) ArrayList(java.util.ArrayList) CrawlerClient(org.codelibs.fess.crawler.client.CrawlerClient) FessConfig(org.codelibs.fess.mylasta.direction.FessConfig) Map(java.util.Map) ResponseProcessor(org.codelibs.fess.crawler.processor.ResponseProcessor) LinkedList(java.util.LinkedList) ExecutorService(java.util.concurrent.ExecutorService) DataStoreCrawlingException(org.codelibs.fess.exception.DataStoreCrawlingException) QueryBuilders(org.opensearch.index.query.QueryBuilders) StreamUtil.stream(org.codelibs.core.stream.StreamUtil.stream) ResultData(org.codelibs.fess.crawler.entity.ResultData) RuleManager(org.codelibs.fess.crawler.rule.RuleManager) Rule(org.codelibs.fess.crawler.rule.Rule) LinkedBlockingQueue(java.util.concurrent.LinkedBlockingQueue) Collectors(java.util.stream.Collectors) TimeUnit(java.util.concurrent.TimeUnit) List(java.util.List) Logger(org.apache.logging.log4j.Logger) RequestData(org.codelibs.fess.crawler.entity.RequestData) ComponentUtil(org.codelibs.fess.util.ComponentUtil) SingletonLaContainer(org.lastaflute.di.core.SingletonLaContainer) ChildUrlsException(org.codelibs.fess.crawler.exception.ChildUrlsException) LogManager(org.apache.logging.log4j.LogManager) RequestDataBuilder(org.codelibs.fess.crawler.builder.RequestDataBuilder) CrawlerClientFactory(org.codelibs.fess.crawler.client.CrawlerClientFactory) ResponseData(org.codelibs.fess.crawler.entity.ResponseData) ChildUrlsException(org.codelibs.fess.crawler.exception.ChildUrlsException) Transformer(org.codelibs.fess.crawler.transformer.Transformer) ResponseData(org.codelibs.fess.crawler.entity.ResponseData) DefaultResponseProcessor(org.codelibs.fess.crawler.processor.impl.DefaultResponseProcessor) ResponseProcessor(org.codelibs.fess.crawler.processor.ResponseProcessor) CrawlerSystemException(org.codelibs.fess.crawler.exception.CrawlerSystemException) DataStoreCrawlingException(org.codelibs.fess.exception.DataStoreCrawlingException) ChildUrlsException(org.codelibs.fess.crawler.exception.ChildUrlsException) ResultData(org.codelibs.fess.crawler.entity.ResultData) DataStoreCrawlingException(org.codelibs.fess.exception.DataStoreCrawlingException) DefaultResponseProcessor(org.codelibs.fess.crawler.processor.impl.DefaultResponseProcessor) RequestData(org.codelibs.fess.crawler.entity.RequestData) CrawlerSystemException(org.codelibs.fess.crawler.exception.CrawlerSystemException) RuleManager(org.codelibs.fess.crawler.rule.RuleManager) Rule(org.codelibs.fess.crawler.rule.Rule) Map(java.util.Map)

Example 9 with Rule

use of org.codelibs.fess.crawler.rule.Rule in project fess-crawler by codelibs.

the class RuleManagerImplTest method test_getRule_sitemaps3.

public void test_getRule_sitemaps3() {
    final ResponseData responseData = new ResponseData();
    responseData.setUrl("http://www.example.com/sitemap1.txt");
    File file = ResourceUtil.getResourceAsFile("sitemaps/sitemap1.txt");
    responseData.setResponseBody(file, false);
    final Rule rule = ruleManager.getRule(responseData);
    assertNotNull(rule);
    assertEquals("sitemapsRule", rule.getRuleId());
    CloseableUtil.closeQuietly(responseData);
}
Also used : ResponseData(org.codelibs.fess.crawler.entity.ResponseData) Rule(org.codelibs.fess.crawler.rule.Rule) File(java.io.File)

Example 10 with Rule

use of org.codelibs.fess.crawler.rule.Rule in project fess-crawler by codelibs.

the class RuleManagerImplTest method test_checkRule.

public void test_checkRule() {
    final Rule rule = ruleManager.getRule(new ResponseData());
    assertNotNull(rule);
    assertEquals("fileRule", rule.getRuleId());
    final RegexRule rule2 = new RegexRule();
    rule2.setAllRequired(true);
    rule2.addRule("url", "http:.*");
    final RegexRule rule3 = new RegexRule();
    rule3.addRule("url", "http:.*");
    assertFalse(ruleManager.hasRule(rule2));
    assertFalse(ruleManager.hasRule(rule3));
    ruleManager.addRule(rule2);
    assertTrue(ruleManager.hasRule(rule2));
    assertFalse(ruleManager.hasRule(rule3));
    ruleManager.addRule(rule3);
    assertTrue(ruleManager.hasRule(rule2));
    assertTrue(ruleManager.hasRule(rule3));
    ruleManager.removeRule(rule2);
    assertFalse(ruleManager.hasRule(rule2));
    assertTrue(ruleManager.hasRule(rule3));
    ruleManager.removeRule(rule3);
    assertFalse(ruleManager.hasRule(rule2));
    assertFalse(ruleManager.hasRule(rule3));
}
Also used : ResponseData(org.codelibs.fess.crawler.entity.ResponseData) Rule(org.codelibs.fess.crawler.rule.Rule)

Aggregations

Rule (org.codelibs.fess.crawler.rule.Rule)11 ResponseData (org.codelibs.fess.crawler.entity.ResponseData)10 File (java.io.File)5 ResponseProcessor (org.codelibs.fess.crawler.processor.ResponseProcessor)4 Map (java.util.Map)3 CrawlerClient (org.codelibs.fess.crawler.client.CrawlerClient)3 CrawlerClientFactory (org.codelibs.fess.crawler.client.CrawlerClientFactory)3 ResultData (org.codelibs.fess.crawler.entity.ResultData)3 ChildUrlsException (org.codelibs.fess.crawler.exception.ChildUrlsException)3 CrawlerSystemException (org.codelibs.fess.crawler.exception.CrawlerSystemException)3 DefaultResponseProcessor (org.codelibs.fess.crawler.processor.impl.DefaultResponseProcessor)3 RuleManager (org.codelibs.fess.crawler.rule.RuleManager)3 Transformer (org.codelibs.fess.crawler.transformer.Transformer)3 ComponentUtil (org.codelibs.fess.util.ComponentUtil)3 ArrayList (java.util.ArrayList)2 List (java.util.List)2 ExecutorService (java.util.concurrent.ExecutorService)2 LinkedBlockingQueue (java.util.concurrent.LinkedBlockingQueue)2 ThreadPoolExecutor (java.util.concurrent.ThreadPoolExecutor)2 TimeUnit (java.util.concurrent.TimeUnit)2