This is an automated email from the ASF dual-hosted git repository. lewismc pushed a commit to branch NUTCH-2292 in repository https://gitbox.apache.org/repos/asf/nutch.git
commit ecc60d7890e20ae822c848661ee2a6224f9fbe1d Merge: 2b93a66 2175c76 Author: Lewis John McGibbney <[email protected]> AuthorDate: Fri Feb 24 12:13:47 2017 -0800 Merge branch 'NUTCH-2292' of https://github.com/apache/nutch into NUTCH-2292 .gitignore | 6 + {src/bin => bin}/crawl | 0 {src/bin => bin}/nutch | 0 nutch-core/pom.xml | 522 +++++++++++++++++++++ .../apache/nutch/crawl/AbstractFetchSchedule.java | 0 .../apache/nutch/crawl/AdaptiveFetchSchedule.java | 0 .../java/org/apache/nutch/crawl/CrawlDatum.java | 0 .../main}/java/org/apache/nutch/crawl/CrawlDb.java | 0 .../java/org/apache/nutch/crawl/CrawlDbFilter.java | 0 .../java/org/apache/nutch/crawl/CrawlDbMerger.java | 0 .../java/org/apache/nutch/crawl/CrawlDbReader.java | 0 .../org/apache/nutch/crawl/CrawlDbReducer.java | 0 .../org/apache/nutch/crawl/DeduplicationJob.java | 0 .../apache/nutch/crawl/DefaultFetchSchedule.java | 0 .../java/org/apache/nutch/crawl/FetchSchedule.java | 0 .../apache/nutch/crawl/FetchScheduleFactory.java | 0 .../java/org/apache/nutch/crawl/Generator.java | 0 .../java/org/apache/nutch/crawl/Injector.java | 0 .../main}/java/org/apache/nutch/crawl/Inlink.java | 0 .../main}/java/org/apache/nutch/crawl/Inlinks.java | 0 .../main}/java/org/apache/nutch/crawl/LinkDb.java | 0 .../java/org/apache/nutch/crawl/LinkDbFilter.java | 0 .../java/org/apache/nutch/crawl/LinkDbMerger.java | 0 .../java/org/apache/nutch/crawl/LinkDbReader.java | 0 .../java/org/apache/nutch/crawl/MD5Signature.java | 0 .../nutch/crawl/MimeAdaptiveFetchSchedule.java | 0 .../java/org/apache/nutch/crawl/NutchWritable.java | 0 .../java/org/apache/nutch/crawl/Signature.java | 0 .../apache/nutch/crawl/SignatureComparator.java | 0 .../org/apache/nutch/crawl/SignatureFactory.java | 0 .../org/apache/nutch/crawl/TextMD5Signature.java | 0 .../apache/nutch/crawl/TextProfileSignature.java | 0 .../org/apache/nutch/crawl/URLPartitioner.java | 0 .../main}/java/org/apache/nutch/crawl/package.html | 0 .../java/org/apache/nutch/fetcher/FetchItem.java | 0 .../org/apache/nutch/fetcher/FetchItemQueue.java | 0 .../org/apache/nutch/fetcher/FetchItemQueues.java | 0 .../java/org/apache/nutch/fetcher/FetchNode.java | 0 .../java/org/apache/nutch/fetcher/FetchNodeDb.java | 0 .../java/org/apache/nutch/fetcher/Fetcher.java | 0 .../apache/nutch/fetcher/FetcherOutputFormat.java | 0 .../org/apache/nutch/fetcher/FetcherThread.java | 0 .../java/org/apache/nutch/fetcher/QueueFeeder.java | 0 .../java/org/apache/nutch/fetcher/package.html | 0 .../java/org/apache/nutch/hostdb/HostDatum.java | 0 .../java/org/apache/nutch/hostdb/ReadHostDb.java | 0 .../org/apache/nutch/hostdb/ResolverThread.java | 0 .../java/org/apache/nutch/hostdb/UpdateHostDb.java | 0 .../apache/nutch/hostdb/UpdateHostDbMapper.java | 0 .../apache/nutch/hostdb/UpdateHostDbReducer.java | 0 .../java/org/apache/nutch/indexer/CleaningJob.java | 0 .../java/org/apache/nutch/indexer/IndexWriter.java | 0 .../org/apache/nutch/indexer/IndexWriters.java | 0 .../org/apache/nutch/indexer/IndexerMapReduce.java | 0 .../apache/nutch/indexer/IndexerOutputFormat.java | 0 .../apache/nutch/indexer/IndexingException.java | 0 .../org/apache/nutch/indexer/IndexingFilter.java | 0 .../org/apache/nutch/indexer/IndexingFilters.java | 0 .../nutch/indexer/IndexingFiltersChecker.java | 0 .../java/org/apache/nutch/indexer/IndexingJob.java | 0 .../org/apache/nutch/indexer/NutchDocument.java | 0 .../java/org/apache/nutch/indexer/NutchField.java | 0 .../org/apache/nutch/indexer/NutchIndexAction.java | 0 .../java/org/apache/nutch/indexer/package.html | 0 .../org/apache/nutch/metadata/CreativeCommons.java | 0 .../java/org/apache/nutch/metadata/DublinCore.java | 0 .../main}/java/org/apache/nutch/metadata/Feed.java | 0 .../org/apache/nutch/metadata/HttpHeaders.java | 0 .../org/apache/nutch/metadata/MetaWrapper.java | 0 .../java/org/apache/nutch/metadata/Metadata.java | 0 .../java/org/apache/nutch/metadata/Nutch.java | 0 .../nutch/metadata/SpellCheckedMetadata.java | 0 .../java/org/apache/nutch/metadata/package.html | 0 .../org/apache/nutch/net/URLExemptionFilter.java | 0 .../org/apache/nutch/net/URLExemptionFilters.java | 0 .../main}/java/org/apache/nutch/net/URLFilter.java | 0 .../org/apache/nutch/net/URLFilterChecker.java | 0 .../org/apache/nutch/net/URLFilterException.java | 0 .../java/org/apache/nutch/net/URLFilters.java | 0 .../java/org/apache/nutch/net/URLNormalizer.java | 0 .../org/apache/nutch/net/URLNormalizerChecker.java | 0 .../java/org/apache/nutch/net/URLNormalizers.java | 0 .../java/org/apache/nutch/net/package-info.java | 0 .../apache/nutch/net/protocols/HttpDateFormat.java | 0 .../nutch/net/protocols/ProtocolException.java | 0 .../org/apache/nutch/net/protocols/Response.java | 0 .../apache/nutch/net/protocols/package-info.java | 0 .../java/org/apache/nutch/parse/HTMLMetaTags.java | 0 .../org/apache/nutch/parse/HtmlParseFilter.java | 0 .../org/apache/nutch/parse/HtmlParseFilters.java | 0 .../main}/java/org/apache/nutch/parse/Outlink.java | 0 .../org/apache/nutch/parse/OutlinkExtractor.java | 0 .../main}/java/org/apache/nutch/parse/Parse.java | 0 .../java/org/apache/nutch/parse/ParseCallable.java | 0 .../java/org/apache/nutch/parse/ParseData.java | 0 .../org/apache/nutch/parse/ParseException.java | 0 .../java/org/apache/nutch/parse/ParseImpl.java | 0 .../org/apache/nutch/parse/ParseOutputFormat.java | 0 .../org/apache/nutch/parse/ParsePluginList.java | 0 .../org/apache/nutch/parse/ParsePluginsReader.java | 0 .../java/org/apache/nutch/parse/ParseResult.java | 0 .../java/org/apache/nutch/parse/ParseSegment.java | 0 .../java/org/apache/nutch/parse/ParseStatus.java | 0 .../java/org/apache/nutch/parse/ParseText.java | 0 .../java/org/apache/nutch/parse/ParseUtil.java | 0 .../main}/java/org/apache/nutch/parse/Parser.java | 0 .../java/org/apache/nutch/parse/ParserChecker.java | 0 .../java/org/apache/nutch/parse/ParserFactory.java | 0 .../org/apache/nutch/parse/ParserNotFound.java | 0 .../java/org/apache/nutch/parse/package-info.java | 0 .../nutch/plugin/CircularDependencyException.java | 0 .../java/org/apache/nutch/plugin/Extension.java | 0 .../org/apache/nutch/plugin/ExtensionPoint.java | 0 .../nutch/plugin/MissingDependencyException.java | 0 .../java/org/apache/nutch/plugin/Pluggable.java | 0 .../main}/java/org/apache/nutch/plugin/Plugin.java | 0 .../org/apache/nutch/plugin/PluginClassLoader.java | 0 .../org/apache/nutch/plugin/PluginDescriptor.java | 0 .../apache/nutch/plugin/PluginManifestParser.java | 0 .../org/apache/nutch/plugin/PluginRepository.java | 0 .../nutch/plugin/PluginRuntimeException.java | 0 .../java/org/apache/nutch/plugin/package.html | 0 .../java/org/apache/nutch/protocol/Content.java | 0 .../java/org/apache/nutch/protocol/Protocol.java | 0 .../apache/nutch/protocol/ProtocolException.java | 0 .../org/apache/nutch/protocol/ProtocolFactory.java | 0 .../apache/nutch/protocol/ProtocolNotFound.java | 0 .../org/apache/nutch/protocol/ProtocolOutput.java | 0 .../org/apache/nutch/protocol/ProtocolStatus.java | 0 .../apache/nutch/protocol/RobotRulesParser.java | 0 .../org/apache/nutch/protocol/package-info.java | 0 .../nutch/scoring/AbstractScoringFilter.java | 0 .../org/apache/nutch/scoring/ScoringFilter.java | 0 .../nutch/scoring/ScoringFilterException.java | 0 .../org/apache/nutch/scoring/ScoringFilters.java | 0 .../org/apache/nutch/scoring/package-info.java | 0 .../apache/nutch/scoring/webgraph/LinkDatum.java | 0 .../apache/nutch/scoring/webgraph/LinkDumper.java | 0 .../apache/nutch/scoring/webgraph/LinkRank.java | 0 .../org/apache/nutch/scoring/webgraph/Node.java | 0 .../apache/nutch/scoring/webgraph/NodeDumper.java | 0 .../apache/nutch/scoring/webgraph/NodeReader.java | 0 .../nutch/scoring/webgraph/ScoreUpdater.java | 0 .../apache/nutch/scoring/webgraph/WebGraph.java | 0 .../nutch/scoring/webgraph/package-info.java | 0 .../nutch/segment/ContentAsTextInputFormat.java | 0 .../org/apache/nutch/segment/SegmentChecker.java | 0 .../apache/nutch/segment/SegmentMergeFilter.java | 0 .../apache/nutch/segment/SegmentMergeFilters.java | 0 .../org/apache/nutch/segment/SegmentMerger.java | 0 .../java/org/apache/nutch/segment/SegmentPart.java | 0 .../org/apache/nutch/segment/SegmentReader.java | 0 .../org/apache/nutch/segment/package-info.java | 0 .../java/org/apache/nutch/service/ConfManager.java | 0 .../java/org/apache/nutch/service/JobManager.java | 0 .../java/org/apache/nutch/service/NutchReader.java | 0 .../java/org/apache/nutch/service/NutchServer.java | 0 .../apache/nutch/service/impl/ConfManagerImpl.java | 0 .../org/apache/nutch/service/impl/JobFactory.java | 0 .../apache/nutch/service/impl/JobManagerImpl.java | 0 .../org/apache/nutch/service/impl/JobWorker.java | 0 .../org/apache/nutch/service/impl/LinkReader.java | 0 .../org/apache/nutch/service/impl/NodeReader.java | 0 .../service/impl/NutchServerPoolExecutor.java | 0 .../apache/nutch/service/impl/SequenceReader.java | 0 .../nutch/service/model/request/DbQuery.java | 0 .../nutch/service/model/request/JobConfig.java | 0 .../nutch/service/model/request/NutchConfig.java | 0 .../nutch/service/model/request/ReaderConfig.java | 0 .../nutch/service/model/request/SeedList.java | 0 .../nutch/service/model/request/SeedUrl.java | 0 .../service/model/response/FetchNodeDbInfo.java | 0 .../nutch/service/model/response/JobInfo.java | 0 .../service/model/response/NutchServerInfo.java | 0 .../nutch/service/resources/AbstractResource.java | 0 .../nutch/service/resources/AdminResource.java | 0 .../nutch/service/resources/ConfigResource.java | 0 .../apache/nutch/service/resources/DbResource.java | 0 .../nutch/service/resources/JobResource.java | 0 .../nutch/service/resources/ReaderResouce.java | 0 .../nutch/service/resources/SeedResource.java | 0 .../nutch/tools/AbstractCommonCrawlFormat.java | 0 .../java/org/apache/nutch/tools/Benchmark.java | 0 .../org/apache/nutch/tools/CommonCrawlConfig.java | 0 .../apache/nutch/tools/CommonCrawlDataDumper.java | 0 .../org/apache/nutch/tools/CommonCrawlFormat.java | 0 .../nutch/tools/CommonCrawlFormatFactory.java | 0 .../nutch/tools/CommonCrawlFormatJackson.java | 0 .../nutch/tools/CommonCrawlFormatJettinson.java | 0 .../nutch/tools/CommonCrawlFormatSimple.java | 0 .../apache/nutch/tools/CommonCrawlFormatWARC.java | 0 .../java/org/apache/nutch/tools/DmozParser.java | 0 .../java/org/apache/nutch/tools/FileDumper.java | 0 .../java/org/apache/nutch/tools/FreeGenerator.java | 0 .../java/org/apache/nutch/tools/ResolveUrls.java | 0 .../java/org/apache/nutch/tools/WARCUtils.java | 0 .../org/apache/nutch/tools/arc/ArcInputFormat.java | 0 .../apache/nutch/tools/arc/ArcRecordReader.java | 0 .../apache/nutch/tools/arc/ArcSegmentCreator.java | 0 .../org/apache/nutch/tools/arc/package-info.java | 0 .../java/org/apache/nutch/tools/package-info.java | 0 .../org/apache/nutch/tools/warc/WARCExporter.java | 0 .../org/apache/nutch/tools/warc/package-info.java | 0 .../java/org/apache/nutch/util/CommandRunner.java | 0 .../apache/nutch/util/CrawlCompletionStats.java | 0 .../java/org/apache/nutch/util/DeflateUtils.java | 0 .../main}/java/org/apache/nutch/util/DomUtil.java | 0 .../java/org/apache/nutch/util/DumpFileUtil.java | 0 .../org/apache/nutch/util/EncodingDetector.java | 0 .../main}/java/org/apache/nutch/util/FSUtils.java | 0 .../java/org/apache/nutch/util/GZIPUtils.java | 0 .../nutch/util/GenericWritableConfigurable.java | 0 .../java/org/apache/nutch/util/HadoopFSUtil.java | 0 .../main}/java/org/apache/nutch/util/JexlUtil.java | 0 .../main}/java/org/apache/nutch/util/LockUtil.java | 0 .../main}/java/org/apache/nutch/util/MimeUtil.java | 0 .../java/org/apache/nutch/util/NodeWalker.java | 0 .../org/apache/nutch/util/NutchConfiguration.java | 0 .../main}/java/org/apache/nutch/util/NutchJob.java | 0 .../java/org/apache/nutch/util/NutchTool.java | 0 .../java/org/apache/nutch/util/ObjectCache.java | 0 .../org/apache/nutch/util/PrefixStringMatcher.java | 0 .../nutch/util/ProtocolStatusStatistics.java | 0 .../java/org/apache/nutch/util/StringUtil.java | 0 .../org/apache/nutch/util/SuffixStringMatcher.java | 0 .../java/org/apache/nutch/util/TableUtil.java | 0 .../java/org/apache/nutch/util/TimingUtil.java | 0 .../org/apache/nutch/util/TrieStringMatcher.java | 0 .../main}/java/org/apache/nutch/util/URLUtil.java | 0 .../apache/nutch/util/domain/DomainStatistics.java | 0 .../org/apache/nutch/util/domain/DomainSuffix.java | 0 .../apache/nutch/util/domain/DomainSuffixes.java | 0 .../nutch/util/domain/DomainSuffixesReader.java | 0 .../apache/nutch/util/domain/TopLevelDomain.java | 0 .../java/org/apache/nutch/util/domain/package.html | 0 .../java/org/apache/nutch/util/package-info.java | 0 .../org/apache/nutch/webui/NutchUiApplication.java | 0 .../nutch/webui/NutchUiApplication.properties | 0 .../java/org/apache/nutch/webui/NutchUiServer.java | 0 .../org/apache/nutch/webui/client/NutchClient.java | 0 .../nutch/webui/client/NutchClientFactory.java | 0 .../nutch/webui/client/impl/CrawlingCycle.java | 0 .../webui/client/impl/CrawlingCycleListener.java | 0 .../nutch/webui/client/impl/NutchClientImpl.java | 0 .../nutch/webui/client/impl/RemoteCommand.java | 0 .../webui/client/impl/RemoteCommandBuilder.java | 0 .../webui/client/impl/RemoteCommandExecutor.java | 0 .../client/impl/RemoteCommandsBatchFactory.java | 0 .../nutch/webui/client/model/ConnectionStatus.java | 0 .../org/apache/nutch/webui/client/model/Crawl.java | 0 .../apache/nutch/webui/client/model/JobConfig.java | 0 .../apache/nutch/webui/client/model/JobInfo.java | 0 .../nutch/webui/client/model/NutchStatus.java | 0 .../nutch/webui/config/CustomDaoFactory.java | 0 .../nutch/webui/config/CustomTableCreator.java | 0 .../nutch/webui/config/NutchGuiConfiguration.java | 0 .../nutch/webui/config/SpringConfiguration.java | 0 .../org/apache/nutch/webui/model/NutchConfig.java | 0 .../apache/nutch/webui/model/NutchInstance.java | 0 .../org/apache/nutch/webui/model/SeedList.java | 0 .../java/org/apache/nutch/webui/model/SeedUrl.java | 0 .../apache/nutch/webui/pages/AbstractBasePage.html | 0 .../apache/nutch/webui/pages/AbstractBasePage.java | 0 .../apache/nutch/webui/pages/DashboardPage.html | 0 .../apache/nutch/webui/pages/DashboardPage.java | 0 .../org/apache/nutch/webui/pages/LogOutPage.java | 0 .../apache/nutch/webui/pages/SchedulingPage.java | 0 .../org/apache/nutch/webui/pages/SearchPage.java | 0 .../apache/nutch/webui/pages/StatisticsPage.java | 0 .../apache/nutch/webui/pages/UrlsUploadPage.java | 0 .../apache/nutch/webui/pages/UserSettingsPage.java | 0 .../webui/pages/assets/NutchUiCssReference.java | 0 .../nutch/webui/pages/assets/nutch-style.css | 0 .../webui/pages/components/ColorEnumLabel.java | 0 .../pages/components/ColorEnumLabelBuilder.java | 0 .../webui/pages/components/CpmIteratorAdapter.java | 0 .../nutch/webui/pages/crawls/CrawlPanel.html | 0 .../nutch/webui/pages/crawls/CrawlPanel.java | 0 .../nutch/webui/pages/crawls/CrawlsPage.html | 0 .../nutch/webui/pages/crawls/CrawlsPage.java | 0 .../nutch/webui/pages/instances/InstancePanel.html | 0 .../nutch/webui/pages/instances/InstancePanel.java | 0 .../nutch/webui/pages/instances/InstancesPage.html | 0 .../nutch/webui/pages/instances/InstancesPage.java | 0 .../nutch/webui/pages/menu/VerticalMenu.html | 0 .../nutch/webui/pages/menu/VerticalMenu.java | 0 .../nutch/webui/pages/seed/SeedListsPage.html | 0 .../nutch/webui/pages/seed/SeedListsPage.java | 0 .../apache/nutch/webui/pages/seed/SeedPage.html | 0 .../apache/nutch/webui/pages/seed/SeedPage.java | 0 .../nutch/webui/pages/settings/SettingsPage.html | 0 .../nutch/webui/pages/settings/SettingsPage.java | 0 .../apache/nutch/webui/service/CrawlService.java | 0 .../nutch/webui/service/NutchInstanceService.java | 0 .../apache/nutch/webui/service/NutchService.java | 0 .../nutch/webui/service/SeedListService.java | 0 .../nutch/webui/service/impl/CrawlServiceImpl.java | 0 .../service/impl/NutchInstanceServiceImpl.java | 0 .../nutch/webui/service/impl/NutchServiceImpl.java | 0 .../webui/service/impl/SeedListServiceImpl.java | 0 {src => nutch-core/src/main}/java/overview.html | 0 .../nutch/crawl/ContinuousCrawlTestUtil.java | 0 .../org/apache/nutch/crawl/CrawlDBTestUtil.java | 0 .../nutch/crawl/CrawlDbUpdateTestDriver.java | 0 .../org/apache/nutch/crawl/CrawlDbUpdateUtil.java | 0 .../org/apache/nutch/crawl/DummyWritable.java | 0 .../apache/nutch/crawl/TODOTestCrawlDbStates.java | 3 + .../nutch/crawl/TestAdaptiveFetchSchedule.java | 0 .../org/apache/nutch/crawl/TestCrawlDbFilter.java | 3 + .../org/apache/nutch/crawl/TestCrawlDbMerger.java | 3 + .../org/apache/nutch/crawl/TestCrawlDbStates.java | 3 + .../org/apache/nutch/crawl/TestGenerator.java | 3 + .../java}/org/apache/nutch/crawl/TestInjector.java | 3 + .../org/apache/nutch/crawl/TestLinkDbMerger.java | 0 .../apache/nutch/crawl/TestSignatureFactory.java | 0 .../org/apache/nutch/fetcher/TestFetcher.java | 3 + .../apache/nutch/indexer/TestIndexerMapReduce.java | 3 + .../apache/nutch/indexer/TestIndexingFilters.java | 3 + .../org/apache/nutch/metadata/TestMetadata.java | 0 .../nutch/metadata/TestSpellCheckedMetadata.java | 0 .../java}/org/apache/nutch/net/TestURLFilters.java | 3 + .../org/apache/nutch/net/TestURLNormalizers.java | 3 + .../apache/nutch/parse/TestOutlinkExtractor.java | 0 .../org/apache/nutch/parse/TestParseData.java | 0 .../org/apache/nutch/parse/TestParseText.java | 0 .../org/apache/nutch/parse/TestParserFactory.java | 3 + .../org/apache/nutch/parse/parse-plugin-test.xml | 0 .../apache/nutch/plugin/HelloWorldExtension.java | 0 .../org/apache/nutch/plugin/ITestExtension.java | 0 .../org/apache/nutch/plugin/SimpleTestPlugin.java | 0 .../org/apache/nutch/plugin/TestPluginSystem.java | 3 + .../org/apache/nutch/protocol/TestContent.java | 0 .../apache/nutch/protocol/TestProtocolFactory.java | 3 + .../apache/nutch/segment/TestSegmentMerger.java | 0 .../segment/TestSegmentMergerCrawlDatums.java | 0 .../org/apache/nutch/service/TestNutchServer.java | 0 .../org/apache/nutch/test/IntegrationTest.java | 6 + .../test/java/org/apache/nutch/test/TestUtils.java | 29 ++ .../nutch/tools/TestCommonCrawlDataDumper.java | 5 +- .../nutch/tools/proxy/AbstractTestbedHandler.java | 0 .../org/apache/nutch/tools/proxy/DelayHandler.java | 0 .../org/apache/nutch/tools/proxy/FakeHandler.java | 0 .../apache/nutch/tools/proxy/LogDebugHandler.java | 0 .../apache/nutch/tools/proxy/NotFoundHandler.java | 0 .../org/apache/nutch/tools/proxy/ProxyTestbed.java | 0 .../apache/nutch/tools/proxy/SegmentHandler.java | 0 .../org/apache/nutch/tools/proxy/package-info.java | 0 .../org/apache/nutch/util/DumpFileUtilTest.java | 0 .../apache/nutch/util/TestEncodingDetector.java | 0 .../java}/org/apache/nutch/util/TestGZIPUtils.java | 0 .../java}/org/apache/nutch/util/TestMimeUtil.java | 12 +- .../org/apache/nutch/util/TestNodeWalker.java | 0 .../apache/nutch/util/TestPrefixStringMatcher.java | 0 .../org/apache/nutch/util/TestStringUtil.java | 0 .../apache/nutch/util/TestSuffixStringMatcher.java | 0 .../java}/org/apache/nutch/util/TestTableUtil.java | 0 .../java}/org/apache/nutch/util/TestURLUtil.java | 0 .../org/apache/nutch/util/WritableTestUtils.java | 0 .../src/test/resources}/crawl-tests.xml | 0 .../src/test/resources}/domain-urlfilter.txt | 0 .../resources}/fetch-test-site/dup_of_pagea.html | 0 .../test/resources}/fetch-test-site/exception.html | 0 .../src/test/resources}/fetch-test-site/index.html | 0 .../fetch-test-site/nested_spider_trap.html | 0 .../src/test/resources}/fetch-test-site/pagea.html | 0 .../src/test/resources}/fetch-test-site/pageb.html | 0 .../src/test/resources}/fetch-test-site/robots.txt | 0 .../src/test/resources}/filter-all.txt | 0 .../src/test/resources}/log4j.properties | 0 .../src/test/resources}/nutch-site.xml | 0 .../src/test/resources}/test-mime-util/test.xlsx | Bin .../20150309101625/content/part-00000/.data.crc | Bin .../20150309101625/content/part-00000/.index.crc | Bin .../20150309101625/content/part-00000/data | Bin .../20150309101625/content/part-00000/index | Bin .../crawl_fetch/part-00000/.data.crc | Bin .../crawl_fetch/part-00000/.index.crc | Bin .../20150309101625/crawl_fetch/part-00000/data | Bin .../20150309101625/crawl_fetch/part-00000/index | Bin .../20150309101625/crawl_generate/.part-00000.crc | Bin .../20150309101625/crawl_generate/part-00000 | Bin .../20150309101625/crawl_parse/.part-00000.crc | Bin .../20150309101625/crawl_parse/part-00000 | Bin .../20150309101625/parse_data/part-00000/.data.crc | Bin .../parse_data/part-00000/.index.crc | Bin .../20150309101625/parse_data/part-00000/data | Bin .../20150309101625/parse_data/part-00000/index | Bin .../20150309101625/parse_text/part-00000/.data.crc | Bin .../parse_text/part-00000/.index.crc | Bin .../20150309101625/parse_text/part-00000/data | Bin .../20150309101625/parse_text/part-00000/index | Bin .../20150309101656/content/part-00000/.data.crc | Bin .../20150309101656/content/part-00000/.index.crc | Bin .../20150309101656/content/part-00000/data | Bin .../20150309101656/content/part-00000/index | Bin .../crawl_fetch/part-00000/.data.crc | Bin .../crawl_fetch/part-00000/.index.crc | Bin .../20150309101656/crawl_fetch/part-00000/data | Bin .../20150309101656/crawl_fetch/part-00000/index | Bin .../20150309101656/crawl_generate/.part-00000.crc | Bin .../20150309101656/crawl_generate/part-00000 | Bin .../20150309101656/crawl_parse/.part-00000.crc | Bin .../20150309101656/crawl_parse/part-00000 | Bin .../20150309101656/parse_data/part-00000/.data.crc | Bin .../parse_data/part-00000/.index.crc | Bin .../20150309101656/parse_data/part-00000/data | Bin .../20150309101656/parse_data/part-00000/index | Bin .../20150309101656/parse_text/part-00000/.data.crc | Bin .../parse_text/part-00000/.index.crc | Bin .../20150309101656/parse_text/part-00000/data | Bin .../20150309101656/parse_text/part-00000/index | Bin {src/plugin => nutch-plugins}/build-plugin.xml | 0 {src/plugin => nutch-plugins}/build.xml | 0 .../creativecommons/README.txt | 0 .../creativecommons/build.xml | 0 .../creativecommons/conf/crawl-urlfilter.txt | 0 .../creativecommons/conf/nutch-site.xml | 0 .../creativecommons}/ivy.xml | 0 .../creativecommons/plugin.xml | 0 nutch-plugins/creativecommons/pom.xml | 38 ++ .../creativecommons/nutch/CCIndexingFilter.java | 0 .../org/creativecommons/nutch/CCParseFilter.java | 0 .../java/org/creativecommons/nutch/package.html | 0 .../creativecommons/nutch/TestCCParseFilter.java | 10 +- .../src/test/resources}/anchor.html | 0 .../creativecommons/src/test/resources}/rdf.html | 0 .../creativecommons/src/test/resources}/rel.html | 0 {src/plugin => nutch-plugins}/feed/build.xml | 0 {src/plugin => nutch-plugins}/feed/ivy.xml | 0 {src/plugin => nutch-plugins}/feed/plugin.xml | 0 nutch-plugins/feed/pom.xml | 45 ++ .../nutch/indexer/feed/FeedIndexingFilter.java | 0 .../apache/nutch/indexer/feed/package-info.java | 0 .../org/apache/nutch/parse/feed/FeedParser.java | 0 .../org/apache/nutch/parse/feed/package-info.java | 0 .../apache/nutch/parse/feed/TestFeedParser.java | 0 .../feed/src/test/resources}/rsstest.rss | 0 {src/plugin => nutch-plugins}/headings/build.xml | 0 {src/plugin => nutch-plugins}/headings/ivy.xml | 0 {src/plugin => nutch-plugins}/headings/plugin.xml | 0 nutch-plugins/headings/pom.xml | 38 ++ .../nutch/parse/headings/HeadingsParseFilter.java | 0 .../apache/nutch/parse/headings/package-info.java | 0 .../index-anchor/build.xml | 0 .../index-anchor}/ivy.xml | 0 .../index-anchor/plugin.xml | 0 nutch-plugins/index-anchor/pom.xml | 38 ++ .../nutch/indexer/anchor/AnchorIndexingFilter.java | 0 .../org/apache/nutch/indexer/anchor/package.html | 0 .../indexer/anchor/TestAnchorIndexingFilter.java | 0 .../plugin => nutch-plugins}/index-basic/build.xml | 0 {src/plugin => nutch-plugins}/index-basic/ivy.xml | 0 .../index-basic/plugin.xml | 0 nutch-plugins/index-basic/pom.xml | 38 ++ .../nutch/indexer/basic/BasicIndexingFilter.java | 0 .../org/apache/nutch/indexer/basic/package.html | 0 .../indexer/basic/TestBasicIndexingFilter.java | 0 .../index-geoip/build-ivy.xml | 0 .../plugin => nutch-plugins}/index-geoip/build.xml | 0 {src/plugin => nutch-plugins}/index-geoip/ivy.xml | 0 .../index-geoip/plugin.xml | 0 nutch-plugins/index-geoip/pom.xml | 55 +++ .../nutch/indexer/geoip/GeoIPDocumentCreator.java | 0 .../nutch/indexer/geoip/GeoIPIndexingFilter.java | 0 .../apache/nutch/indexer/geoip/package-info.java | 0 .../plugin => nutch-plugins}/index-links/build.xml | 0 .../index-links}/ivy.xml | 0 .../index-links/plugin.xml | 0 nutch-plugins/index-links/pom.xml | 38 ++ .../nutch/indexer/links/LinksIndexingFilter.java | 0 .../indexer/links/TestLinksIndexingFilter.java | 0 .../java}/org/apache/nutch/parse/TestOutlinks.java | 0 .../index-metadata/build.xml | 0 .../index-metadata}/ivy.xml | 0 .../index-metadata/plugin.xml | 0 nutch-plugins/index-metadata/pom.xml | 38 ++ .../nutch/indexer/metadata/MetadataIndexer.java | 0 .../nutch/indexer/metadata/package-info.java | 0 {src/plugin => nutch-plugins}/index-more/build.xml | 0 .../index-more}/ivy.xml | 0 .../plugin => nutch-plugins}/index-more/plugin.xml | 0 nutch-plugins/index-more/pom.xml | 38 ++ .../nutch/indexer/more/MoreIndexingFilter.java | 0 .../org/apache/nutch/indexer/more/package.html | 0 .../nutch/indexer/more/TestMoreIndexingFilter.java | 0 .../index-replace/README.txt | 0 .../index-replace/build.xml | 0 .../index-replace}/ivy.xml | 0 .../index-replace/plugin.xml | 0 nutch-plugins/index-replace/pom.xml | 50 ++ .../nutch/indexer/replace/FieldReplacer.java | 0 .../nutch/indexer/replace/ReplaceIndexer.java | 0 .../apache/nutch/indexer/replace/package-info.java | 0 .../nutch/indexer/replace/TestIndexReplace.java | 0 .../src/test/resources}/testIndexReplace.html | 0 .../index-static/build.xml | 0 .../index-static}/ivy.xml | 0 .../index-static/plugin.xml | 0 nutch-plugins/index-static/pom.xml | 38 ++ .../indexer/staticfield/StaticFieldIndexer.java | 0 .../apache/nutch/indexer/staticfield/package.html | 0 .../staticfield/TestStaticFieldIndexerTest.java | 0 .../indexer-cloudsearch/README.md | 0 .../indexer-cloudsearch/build.xml | 0 .../indexer-cloudsearch/createCSDomain.sh | 0 .../indexer-cloudsearch/ivy.xml | 0 .../indexer-cloudsearch/plugin.xml | 0 nutch-plugins/indexer-cloudsearch/pom.xml | 45 ++ .../cloudsearch/CloudSearchConstants.java | 0 .../cloudsearch/CloudSearchIndexWriter.java | 0 .../indexwriter/cloudsearch/CloudSearchUtils.java | 0 .../indexer-dummy/build.xml | 0 .../indexer-dummy}/ivy.xml | 0 .../indexer-dummy/plugin.xml | 0 nutch-plugins/indexer-dummy/pom.xml | 38 ++ .../nutch/indexwriter/dummy/DummyIndexWriter.java | 0 .../nutch/indexwriter/dummy/package-info.java | 0 .../indexer-elastic/build-ivy.xml | 0 .../indexer-elastic/build.xml | 0 .../indexer-elastic/howto_upgrade_es.txt | 0 .../indexer-elastic/ivy.xml | 0 .../indexer-elastic/plugin.xml | 0 nutch-plugins/indexer-elastic/pom.xml | 45 ++ .../indexwriter/elastic/ElasticConstants.java | 0 .../indexwriter/elastic/ElasticIndexWriter.java | 0 .../nutch/indexwriter/elastic/package-info.java | 0 .../indexer-solr/build-ivy.xml | 0 .../indexer-solr/build.xml | 0 {src/plugin => nutch-plugins}/indexer-solr/ivy.xml | 0 .../indexer-solr/plugin.xml | 0 nutch-plugins/indexer-solr/pom.xml | 55 +++ .../nutch/indexwriter/solr/SolrConstants.java | 0 .../nutch/indexwriter/solr/SolrIndexWriter.java | 0 .../nutch/indexwriter/solr/SolrMappingReader.java | 0 .../apache/nutch/indexwriter/solr/SolrUtils.java | 0 .../nutch/indexwriter/solr/package-info.java | 0 .../language-identifier/build.xml | 0 .../language-identifier}/ivy.xml | 0 .../language-identifier/plugin.xml | 0 nutch-plugins/language-identifier/pom.xml | 38 ++ .../nutch/analysis/lang/HTMLLanguageParser.java | 0 .../analysis/lang/LanguageIndexingFilter.java | 0 .../nutch/analysis/lang/langmappings.properties | 0 .../org/apache/nutch/analysis/lang/package.html | 0 .../analysis/lang/TestHTMLLanguageParser.java | 0 .../java}/org/apache/nutch/analysis/lang/da.test | 0 .../java}/org/apache/nutch/analysis/lang/de.test | 0 .../java}/org/apache/nutch/analysis/lang/el.test | 0 .../java}/org/apache/nutch/analysis/lang/en.test | 0 .../java}/org/apache/nutch/analysis/lang/es.test | 0 .../java}/org/apache/nutch/analysis/lang/fi.test | 0 .../java}/org/apache/nutch/analysis/lang/fr.test | 0 .../java}/org/apache/nutch/analysis/lang/it.test | 0 .../java}/org/apache/nutch/analysis/lang/nl.test | 0 .../java}/org/apache/nutch/analysis/lang/pt.test | 0 .../java}/org/apache/nutch/analysis/lang/sv.test | 0 .../nutch/analysis/lang/test-referencial.txt | 0 .../lib-htmlunit/build-ivy.xml | 0 .../lib-htmlunit/build.xml | 0 {src/plugin => nutch-plugins}/lib-htmlunit/ivy.xml | 0 .../lib-htmlunit/plugin.xml | 0 nutch-plugins/lib-htmlunit/pom.xml | 55 +++ .../nutch/protocol/htmlunit/HtmlUnitWebDriver.java | 0 .../htmlunit/HtmlUnitWebWindowListener.java | 0 {src/plugin => nutch-plugins}/lib-http/build.xml | 0 .../lib-http}/ivy.xml | 0 {src/plugin => nutch-plugins}/lib-http/plugin.xml | 0 nutch-plugins/lib-http/pom.xml | 38 ++ .../nutch/protocol/http/api/BlockedException.java | 0 .../apache/nutch/protocol/http/api/HttpBase.java | 0 .../nutch/protocol/http/api/HttpException.java | 0 .../protocol/http/api/HttpRobotRulesParser.java | 0 .../apache/nutch/protocol/http/api/package.html | 0 .../protocol/http/api/TestRobotRulesParser.java | 0 .../lib-nekohtml/build.xml | 0 {src/plugin => nutch-plugins}/lib-nekohtml/ivy.xml | 0 .../lib-nekohtml/plugin.xml | 0 nutch-plugins/lib-nekohtml/pom.xml | 45 ++ .../lib-regex-filter/build.xml | 0 .../lib-regex-filter}/ivy.xml | 0 .../lib-regex-filter/plugin.xml | 0 nutch-plugins/lib-regex-filter/pom.xml | 54 +++ .../org/apache/nutch/urlfilter/api/RegexRule.java | 0 .../nutch/urlfilter/api/RegexURLFilterBase.java | 0 .../apache/nutch/urlfilter/api/package-info.java | 0 .../urlfilter/api/RegexURLFilterBaseTest.java | 0 .../lib-selenium/build-ivy.xml | 0 .../lib-selenium/build.xml | 0 .../lib-selenium/howto_upgrade_selenium.txt | 0 {src/plugin => nutch-plugins}/lib-selenium/ivy.xml | 0 .../lib-selenium/plugin.xml | 0 nutch-plugins/lib-selenium/pom.xml | 49 ++ .../nutch/protocol/selenium/HttpWebClient.java | 0 {src/plugin => nutch-plugins}/lib-xml/build.xml | 0 {src/plugin => nutch-plugins}/lib-xml/ivy.xml | 0 {src/plugin => nutch-plugins}/lib-xml/plugin.xml | 0 nutch-plugins/lib-xml/pom.xml | 38 ++ .../microformats-reltag/build.xml | 0 .../microformats-reltag}/ivy.xml | 0 .../microformats-reltag/plugin.xml | 0 nutch-plugins/microformats-reltag/pom.xml | 38 ++ .../microformats/reltag/RelTagIndexingFilter.java | 0 .../nutch/microformats/reltag/RelTagParser.java | 0 .../apache/nutch/microformats/reltag/package.html | 0 .../mimetype-filter/build.xml | 0 .../mimetype-filter}/ivy.xml | 0 .../mimetype-filter/plugin.xml | 0 nutch-plugins/mimetype-filter/pom.xml | 38 ++ .../indexer/filter/MimeTypeIndexingFilter.java | 0 .../indexer/filter/MimeTypeIndexingFilterTest.java | 0 .../src/test/resources}/allow-images.txt | 0 .../src/test/resources}/block-html.txt | 0 .../nutch-extensionpoints/build.xml | 0 .../nutch-extensionpoints}/ivy.xml | 0 .../nutch-extensionpoints/plugin.xml | 0 nutch-plugins/nutch-extensionpoints/pom.xml | 38 ++ {src/plugin => nutch-plugins}/parse-ext/build.xml | 0 {src/plugin => nutch-plugins}/parse-ext/command | 0 .../plugin/tld => nutch-plugins/parse-ext}/ivy.xml | 0 {src/plugin => nutch-plugins}/parse-ext/plugin.xml | 0 nutch-plugins/parse-ext/pom.xml | 38 ++ .../java/org/apache/nutch/parse/ext/ExtParser.java | 0 .../org/apache/nutch/parse/ext/package-info.java | 0 .../org/apache/nutch/parse/ext/TestExtParser.java | 0 {src/plugin => nutch-plugins}/parse-html/build.xml | 0 {src/plugin => nutch-plugins}/parse-html/ivy.xml | 0 .../plugin => nutch-plugins}/parse-html/plugin.xml | 0 nutch-plugins/parse-html/pom.xml | 49 ++ .../org/apache/nutch/parse/html/DOMBuilder.java | 0 .../apache/nutch/parse/html/DOMContentUtils.java | 0 .../apache/nutch/parse/html/HTMLMetaProcessor.java | 0 .../org/apache/nutch/parse/html/HtmlParser.java | 0 .../nutch/parse/html/XMLCharacterRecognizer.java | 0 .../java/org/apache/nutch/parse/html/package.html | 0 .../nutch/parse/html/TestDOMContentUtils.java | 0 .../apache/nutch/parse/html/TestHtmlParser.java | 0 .../nutch/parse/html/TestRobotsMetaProcessor.java | 0 {src/plugin => nutch-plugins}/parse-js/build.xml | 0 .../parse-js}/ivy.xml | 0 {src/plugin => nutch-plugins}/parse-js/plugin.xml | 0 nutch-plugins/parse-js/pom.xml | 38 ++ .../org/apache/nutch/parse/js/JSParseFilter.java | 0 .../org/apache/nutch/parse/js/package-info.java | 0 .../parse-metatags/README.txt | 0 .../parse-metatags/build.xml | 0 .../parse-metatags}/ivy.xml | 0 .../parse-metatags/plugin.xml | 0 nutch-plugins/parse-metatags/pom.xml | 38 ++ .../nutch/parse/metatags/MetaTagsParser.java | 0 .../apache/nutch/parse/metatags/package-info.java | 0 .../nutch/parse/metatags/TestMetatagParser.java | 0 .../src/test/resources}/testMetatags.html | 0 .../test/resources}/testMultivalueMetatags.html | 0 .../parse-replace/README.txt | 0 .../parse-replace/build.xml | 0 .../parse-replace}/ivy.xml | 0 .../parse-replace/plugin.xml | 0 nutch-plugins/parse-replace/pom.xml | 38 ++ .../apache/nutch/parse/replace/ReplaceParser.java | 0 .../apache/nutch/parse/replace/package-info.java | 0 .../nutch/parse/replace/TestParseReplace.java | 0 .../src/test/resources}/testParseReplace.html | 0 {src/plugin => nutch-plugins}/parse-swf/build.xml | 0 .../parse-swf}/ivy.xml | 0 .../parse-swf/lib/javaswf-LICENSE.txt | 0 .../parse-swf/lib/javaswf.jar | Bin {src/plugin => nutch-plugins}/parse-swf/plugin.xml | 0 nutch-plugins/parse-swf/pom.xml | 46 ++ .../java/org/apache/nutch/parse/swf/SWFParser.java | 0 .../org/apache/nutch/parse/swf/package-info.java | 0 .../org/apache/nutch/parse/swf/TestSWFParser.java | 0 .../parse-swf/src/test/resources}/test1.swf | Bin .../parse-swf/src/test/resources}/test1.txt | 0 .../parse-swf/src/test/resources}/test2.swf | Bin .../parse-swf/src/test/resources}/test2.txt | 0 .../parse-swf/src/test/resources}/test3.swf | Bin .../parse-swf/src/test/resources}/test3.txt | 0 .../parse-tika/build-ivy.xml | 0 {src/plugin => nutch-plugins}/parse-tika/build.xml | 0 .../parse-tika/howto_upgrade_tika.txt | 0 {src/plugin => nutch-plugins}/parse-tika/ivy.xml | 0 .../plugin => nutch-plugins}/parse-tika/plugin.xml | 0 nutch-plugins/parse-tika/pom.xml | 54 +++ .../parse/tika/BoilerpipeExtractorRepository.java | 0 .../org/apache/nutch/parse/tika/DOMBuilder.java | 0 .../apache/nutch/parse/tika/DOMContentUtils.java | 0 .../apache/nutch/parse/tika/HTMLMetaProcessor.java | 0 .../org/apache/nutch/parse/tika/TikaParser.java | 0 .../nutch/parse/tika/XMLCharacterRecognizer.java | 0 .../org/apache/nutch/parse/tika/package-info.java | 0 .../org/apache/nutch/tika/TestDOMContentUtils.java | 0 .../org/apache/nutch/tika/TestFeedParser.java | 0 .../org/apache/nutch/tika/TestImageMetadata.java | 0 .../org/apache/nutch/tika/TestMSWordParser.java | 0 .../java}/org/apache/nutch/tika/TestOOParser.java | 0 .../java}/org/apache/nutch/tika/TestPdfParser.java | 0 .../java}/org/apache/nutch/tika/TestRTFParser.java | 0 .../apache/nutch/tika/TestRobotsMetaProcessor.java | 0 .../parse-tika/src/test/resources}/encrypted.pdf | Bin .../parse-tika/src/test/resources}/nutch.html | 0 .../src/test/resources}/nutch_logo_tm.gif | Bin .../parse-tika/src/test/resources}/ootest.odt | Bin .../parse-tika/src/test/resources}/ootest.sxw | Bin .../parse-tika/src/test/resources}/ootest.txt | 0 .../parse-tika/src/test/resources}/pdftest.pdf | 0 .../parse-tika/src/test/resources}/rsstest.rss | 0 .../parse-tika/src/test/resources}/test.rtf | 0 .../parse-tika/src/test/resources}/word97.doc | Bin {src/plugin => nutch-plugins}/parse-zip/build.xml | 0 .../parse-zip}/ivy.xml | 0 {src/plugin => nutch-plugins}/parse-zip/plugin.xml | 0 nutch-plugins/parse-zip/pom.xml | 38 ++ .../java/org/apache/nutch/parse/zip/ZipParser.java | 0 .../apache/nutch/parse/zip/ZipTextExtractor.java | 0 .../org/apache/nutch/parse/zip/package-info.java | 0 .../org/apache/nutch/parse/zip/TestZipParser.java | 0 .../parse-zip/src/test/resources}/test.zip | Bin .../parsefilter-naivebayes/build-ivy.xml | 0 .../parsefilter-naivebayes/build.xml | 0 .../parsefilter-naivebayes/ivy.xml | 0 .../parsefilter-naivebayes/plugin.xml | 0 nutch-plugins/parsefilter-naivebayes/pom.xml | 38 ++ .../nutch/parsefilter/naivebayes/Classify.java | 0 .../naivebayes/NaiveBayesParseFilter.java | 0 .../apache/nutch/parsefilter/naivebayes/Train.java | 0 .../nutch/parsefilter/naivebayes/package-info.java | 0 .../parsefilter-regex/build.xml | 0 .../parsefilter-regex/ivy.xml | 0 .../parsefilter-regex/plugin.xml | 0 nutch-plugins/parsefilter-regex/pom.xml | 38 ++ .../nutch/parsefilter/regex/RegexParseFilter.java | 0 .../nutch/parsefilter/regex/package-info.java | 0 .../parsefilter/regex/TestRegexParseFilter.java | 0 .../src/test/resources}/regex-parsefilter.txt | 0 {src/plugin => nutch-plugins}/plugin.dtd | 0 nutch-plugins/plugin/pom.xml | 38 ++ nutch-plugins/pom.xml | 164 +++++++ .../protocol-file/build.xml | 0 .../protocol-file}/ivy.xml | 0 .../protocol-file/plugin.xml | 0 nutch-plugins/protocol-file/pom.xml | 38 ++ .../java/org/apache/nutch/protocol/file/File.java | 0 .../org/apache/nutch/protocol/file/FileError.java | 0 .../apache/nutch/protocol/file/FileException.java | 0 .../apache/nutch/protocol/file/FileResponse.java | 0 .../org/apache/nutch/protocol/file/package.html | 0 .../nutch/protocol/file/TestProtocolFile.java | 0 .../src/test/resources}/testprotocolfile.txt | 0 .../test/resources}/testprotocolfile_(encoded).txt | 0 .../protocol-ftp/build.xml | 0 {src/plugin => nutch-plugins}/protocol-ftp/ivy.xml | 0 .../protocol-ftp/plugin.xml | 0 nutch-plugins/protocol-ftp/pom.xml | 38 ++ .../java/org/apache/nutch/protocol/ftp/Client.java | 0 .../java/org/apache/nutch/protocol/ftp/Ftp.java | 0 .../org/apache/nutch/protocol/ftp/FtpError.java | 0 .../apache/nutch/protocol/ftp/FtpException.java | 0 .../protocol/ftp/FtpExceptionBadSystResponse.java | 0 .../ftp/FtpExceptionCanNotHaveDataConnection.java | 0 ...FtpExceptionControlClosedByForcedDataClose.java | 0 .../ftp/FtpExceptionUnknownForcedDataClose.java | 0 .../org/apache/nutch/protocol/ftp/FtpResponse.java | 0 .../nutch/protocol/ftp/FtpRobotRulesParser.java | 0 .../nutch/protocol/ftp/PrintCommandListener.java | 0 .../org/apache/nutch/protocol/ftp/package.html | 0 .../protocol-htmlunit/build.xml | 0 .../protocol-htmlunit/ivy.xml | 0 .../protocol-htmlunit/plugin.xml | 0 nutch-plugins/protocol-htmlunit/pom.xml | 51 ++ .../org/apache/nutch/protocol/htmlunit/Http.java | 0 .../nutch/protocol/htmlunit/HttpResponse.java | 0 .../apache/nutch/protocol/htmlunit/package.html | 0 .../protocol-http/build.xml | 0 .../protocol-http}/ivy.xml | 0 .../protocol-http/jsp/basic-http.jsp | 0 .../protocol-http/jsp/brokenpage.jsp | 0 .../protocol-http/jsp/redirect301.jsp | 0 .../protocol-http/jsp/redirect302.jsp | 0 .../protocol-http/plugin.xml | 0 nutch-plugins/protocol-http/pom.xml | 57 +++ .../java/org/apache/nutch/protocol/http/Http.java | 0 .../apache/nutch/protocol/http/HttpResponse.java | 0 .../org/apache/nutch/protocol/http/package.html | 0 .../src/test/conf/nutch-site-test.xml | 0 .../nutch/protocol/http/TestProtocolHttp.java | 0 .../protocol-httpclient/build.xml | 0 .../protocol-httpclient/ivy.xml | 0 .../protocol-httpclient/jsp/basic.jsp | 0 .../protocol-httpclient/jsp/cookies.jsp | 0 .../protocol-httpclient/jsp/digest.jsp | 0 .../protocol-httpclient/jsp/noauth.jsp | 0 .../protocol-httpclient/jsp/ntlm.jsp | 0 .../protocol-httpclient/plugin.xml | 0 nutch-plugins/protocol-httpclient/pom.xml | 62 +++ .../httpclient/DummySSLProtocolSocketFactory.java | 0 .../protocol/httpclient/DummyX509TrustManager.java | 0 .../org/apache/nutch/protocol/httpclient/Http.java | 0 .../protocol/httpclient/HttpAuthentication.java | 0 .../httpclient/HttpAuthenticationException.java | 0 .../httpclient/HttpAuthenticationFactory.java | 0 .../httpclient/HttpBasicAuthentication.java | 0 .../httpclient/HttpFormAuthConfigurer.java | 0 .../httpclient/HttpFormAuthentication.java | 0 .../nutch/protocol/httpclient/HttpResponse.java | 0 .../apache/nutch/protocol/httpclient/package.html | 0 .../src/test/conf/httpclient-auth-test.xml | 0 .../src/test/conf/nutch-site-test.xml | 0 .../httpclient/TestProtocolHttpClient.java | 0 .../protocol-interactiveselenium/README.md | 0 .../protocol-interactiveselenium/build-ivy.xml | 0 .../protocol-interactiveselenium/build.xml | 0 .../protocol-interactiveselenium}/ivy.xml | 0 .../protocol-interactiveselenium/plugin.xml | 0 nutch-plugins/protocol-interactiveselenium/pom.xml | 50 ++ .../nutch/protocol/interactiveselenium/Http.java | 0 .../protocol/interactiveselenium/HttpResponse.java | 0 .../handlers/DefalultMultiInteractionHandler.java | 0 .../handlers/DefaultClickAllAjaxLinksHandler.java | 0 .../handlers/DefaultHandler.java | 0 .../handlers/InteractiveSeleniumHandler.java | 0 .../protocol/interactiveselenium}/package.html | 0 .../protocol-selenium/README.md | 0 .../protocol-selenium/build-ivy.xml | 0 .../protocol-selenium/build.xml | 0 .../protocol-selenium}/ivy.xml | 0 .../protocol-selenium/plugin.xml | 0 nutch-plugins/protocol-selenium/pom.xml | 50 ++ .../org/apache/nutch/protocol/selenium/Http.java | 0 .../nutch/protocol/selenium/HttpResponse.java | 0 .../apache/nutch/protocol/selenium}/package.html | 0 .../scoring-depth/build.xml | 0 .../plugin => nutch-plugins}/scoring-depth/ivy.xml | 0 .../scoring-depth/plugin.xml | 0 nutch-plugins/scoring-depth/pom.xml | 38 ++ .../nutch/scoring/depth/DepthScoringFilter.java | 0 .../apache/nutch/scoring/depth/package-info.java | 0 .../scoring-link/build.xml | 0 .../scoring-link}/ivy.xml | 0 .../scoring-link/plugin.xml | 0 nutch-plugins/scoring-link/pom.xml | 38 ++ .../scoring/link/LinkAnalysisScoringFilter.java | 0 .../apache/nutch/scoring/link/package-info.java | 0 .../scoring-opic/build.xml | 0 .../scoring-opic}/ivy.xml | 0 .../scoring-opic/plugin.xml | 0 nutch-plugins/scoring-opic/pom.xml | 38 ++ .../nutch/scoring/opic/OPICScoringFilter.java | 0 .../apache/nutch/scoring/opic/package-info.java | 0 .../scoring-similarity/build-ivy.xml | 0 .../scoring-similarity/build.xml | 0 .../scoring-similarity/ivy.xml | 0 .../scoring-similarity/plugin.xml | 0 nutch-plugins/scoring-similarity/pom.xml | 45 ++ .../nutch/scoring/similarity/SimilarityModel.java | 0 .../similarity/SimilarityScoringFilter.java | 0 .../similarity/cosine/CosineSimilarity.java | 0 .../nutch/scoring/similarity/cosine/DocVector.java | 0 .../nutch/scoring/similarity/cosine/Model.java | 0 .../scoring/similarity/cosine/package-info.java | 0 .../similarity/util/LuceneAnalyzerUtil.java | 0 .../scoring/similarity/util/LuceneTokenizer.java | 0 .../scoring/similarity/util/package-info.java | 0 .../subcollection/README.txt | 0 .../subcollection/build.xml | 0 .../subcollection}/ivy.xml | 0 .../subcollection/plugin.xml | 0 nutch-plugins/subcollection/pom.xml | 38 ++ .../apache/nutch/collection/CollectionManager.java | 0 .../org/apache/nutch/collection/Subcollection.java | 0 .../java/org/apache/nutch/collection/package.html | 0 .../subcollection/SubcollectionIndexingFilter.java | 0 .../nutch/indexer/subcollection/package-info.java | 0 .../apache/nutch/collection/TestSubcollection.java | 0 {src/plugin => nutch-plugins}/tld/build.xml | 0 .../plugin/parse-ext => nutch-plugins/tld}/ivy.xml | 0 {src/plugin => nutch-plugins}/tld/plugin.xml | 0 nutch-plugins/tld/pom.xml | 38 ++ .../nutch/indexer/tld/TLDIndexingFilter.java | 0 .../java/org/apache/nutch/indexer/tld/package.html | 0 .../apache/nutch/scoring/tld/TLDScoringFilter.java | 0 .../java/org/apache/nutch/scoring/tld/package.html | 0 .../urlfilter-automaton/build.xml | 0 .../urlfilter-automaton/ivy.xml | 0 .../urlfilter-automaton/plugin.xml | 0 nutch-plugins/urlfilter-automaton/pom.xml | 58 +++ .../urlfilter/automaton/AutomatonURLFilter.java | 0 .../apache/nutch/urlfilter/automaton/package.html | 0 .../automaton/TestAutomatonURLFilter.java | 0 .../src/test/resources}/Benchmarks.rules | 0 .../src/test/resources}/Benchmarks.urls | 0 .../src/test/resources}/IntranetCrawling.rules | 0 .../src/test/resources}/IntranetCrawling.urls | 0 .../src/test/resources}/WholeWebCrawling.rules | 0 .../src/test/resources}/WholeWebCrawling.urls | 0 .../urlfilter-domain/build.xml | 0 .../urlfilter-domain}/ivy.xml | 0 .../urlfilter-domain/plugin.xml | 0 nutch-plugins/urlfilter-domain/pom.xml | 38 ++ .../nutch/urlfilter/domain/DomainURLFilter.java | 0 .../nutch/urlfilter/domain/package-info.java | 0 .../urlfilter/domain/TestDomainURLFilter.java | 0 .../urlfilter-domain/src/test/resources}/hosts.txt | 0 .../urlfilter-domainblacklist/build.xml | 0 .../urlfilter-domainblacklist}/ivy.xml | 0 .../urlfilter-domainblacklist/plugin.xml | 0 nutch-plugins/urlfilter-domainblacklist/pom.xml | 38 ++ .../domainblacklist/DomainBlacklistURLFilter.java | 0 .../urlfilter/domainblacklist/package-info.java | 0 .../TestDomainBlacklistURLFilter.java | 0 .../src/test/resources}/hosts.txt | 0 .../urlfilter-ignoreexempt/README.md | 0 .../urlfilter-ignoreexempt/build.xml | 0 .../urlfilter-ignoreexempt}/ivy.xml | 0 .../urlfilter-ignoreexempt/plugin.xml | 0 nutch-plugins/urlfilter-ignoreexempt/pom.xml | 45 ++ .../urlfilter/ignoreexempt/ExemptionUrlFilter.java | 0 .../nutch/urlfilter/ignoreexempt/package-info.java | 0 .../urlfilter-prefix/build.xml | 0 .../urlfilter-prefix}/ivy.xml | 0 .../urlfilter-prefix/plugin.xml | 0 nutch-plugins/urlfilter-prefix/pom.xml | 38 ++ .../nutch/urlfilter/prefix/PrefixURLFilter.java | 0 .../org/apache/nutch/urlfilter/prefix/package.html | 0 .../urlfilter/prefix/TestPrefixURLFilter.java | 0 .../urlfilter-regex/build.xml | 0 .../urlfilter-regex}/ivy.xml | 0 .../urlfilter-regex/plugin.xml | 0 nutch-plugins/urlfilter-regex/pom.xml | 53 +++ .../nutch/urlfilter/regex/RegexURLFilter.java | 0 .../org/apache/nutch/urlfilter/regex/package.html | 0 .../nutch/urlfilter/regex/TestRegexURLFilter.java | 0 .../src/test/resources}/Benchmarks.rules | 0 .../src/test/resources}/Benchmarks.urls | 0 .../src/test/resources}/IntranetCrawling.rules | 0 .../src/test/resources}/IntranetCrawling.urls | 0 .../src/test/resources}/WholeWebCrawling.rules | 0 .../src/test/resources}/WholeWebCrawling.urls | 0 .../src/test/resources}/nutch1838.rules | 0 .../src/test/resources}/nutch1838.urls | 0 .../urlfilter-suffix/build.xml | 0 .../urlfilter-suffix}/ivy.xml | 0 .../urlfilter-suffix/plugin.xml | 0 nutch-plugins/urlfilter-suffix/pom.xml | 38 ++ .../nutch/urlfilter/suffix/SuffixURLFilter.java | 0 .../nutch/urlfilter/suffix/package-info.java | 0 .../urlfilter/suffix/TestSuffixURLFilter.java | 0 .../urlfilter-validator/build.xml | 0 .../urlfilter-validator}/ivy.xml | 0 .../urlfilter-validator/plugin.xml | 0 nutch-plugins/urlfilter-validator/pom.xml | 38 ++ .../nutch/urlfilter/validator/UrlValidator.java | 0 .../apache/nutch/urlfilter/validator/package.html | 0 .../urlfilter/validator/TestUrlValidator.java | 0 {src/plugin => nutch-plugins}/urlmeta/build.xml | 0 .../urlmeta}/ivy.xml | 0 {src/plugin => nutch-plugins}/urlmeta/plugin.xml | 0 nutch-plugins/urlmeta/pom.xml | 38 ++ .../indexer/urlmeta/URLMetaIndexingFilter.java | 0 .../org/apache/nutch/indexer/urlmeta/package.html | 0 .../scoring/urlmeta/URLMetaScoringFilter.java | 0 .../org/apache/nutch/scoring/urlmeta/package.html | 0 .../urlnormalizer-ajax/build.xml | 0 .../urlnormalizer-ajax}/ivy.xml | 0 .../urlnormalizer-ajax/plugin.xml | 0 nutch-plugins/urlnormalizer-ajax/pom.xml | 38 ++ .../net/urlnormalizer/ajax/AjaxURLNormalizer.java | 0 .../urlnormalizer/ajax/TestAjaxURLNormalizer.java | 0 .../urlnormalizer-basic/build.xml | 0 .../urlnormalizer-basic}/ivy.xml | 0 .../urlnormalizer-basic/plugin.xml | 0 nutch-plugins/urlnormalizer-basic/pom.xml | 38 ++ .../urlnormalizer/basic/BasicURLNormalizer.java | 0 .../net/urlnormalizer/basic/package-info.java | 0 .../basic/TestBasicURLNormalizer.java | 0 .../urlnormalizer-host/build.xml | 0 .../urlnormalizer-host}/ivy.xml | 0 .../urlnormalizer-host/plugin.xml | 0 nutch-plugins/urlnormalizer-host/pom.xml | 38 ++ .../net/urlnormalizer/host/HostURLNormalizer.java | 0 .../nutch/net/urlnormalizer/host/package-info.java | 0 .../urlnormalizer/host/TestHostURLNormalizer.java | 0 .../src/test/resources}/hosts.txt | 0 .../urlnormalizer-pass/build.xml | 0 .../urlnormalizer-pass}/ivy.xml | 0 .../urlnormalizer-pass/plugin.xml | 0 nutch-plugins/urlnormalizer-pass/pom.xml | 38 ++ .../net/urlnormalizer/pass/PassURLNormalizer.java | 0 .../nutch/net/urlnormalizer/pass/package-info.java | 0 .../urlnormalizer/pass/TestPassURLNormalizer.java | 0 .../urlnormalizer-protocol/build.xml | 0 .../urlnormalizer-protocol}/ivy.xml | 0 .../urlnormalizer-protocol/plugin.xml | 0 nutch-plugins/urlnormalizer-protocol/pom.xml | 38 ++ .../protocol/ProtocolURLNormalizer.java | 0 .../protocol/TestProtocolURLNormalizer.java | 0 .../src/test/resources}/protocols.txt | 0 .../urlnormalizer-querystring/build.xml | 0 .../urlnormalizer-querystring}/ivy.xml | 0 .../urlnormalizer-querystring/plugin.xml | 0 nutch-plugins/urlnormalizer-querystring/pom.xml | 38 ++ .../querystring/QuerystringURLNormalizer.java | 0 .../urlnormalizer/querystring/package-info.java | 0 .../querystring/TestQuerystringURLNormalizer.java | 0 .../urlnormalizer-regex/build.xml | 0 .../urlnormalizer-regex}/ivy.xml | 0 .../urlnormalizer-regex/plugin.xml | 0 nutch-plugins/urlnormalizer-regex/pom.xml | 38 ++ .../urlnormalizer/regex/RegexURLNormalizer.java | 0 .../net/urlnormalizer/regex/package-info.java | 0 .../regex/TestRegexURLNormalizer.java | 0 .../test/resources}/regex-normalize-default.test | 0 .../test/resources}/regex-normalize-default.xml | 0 .../test/resources}/regex-normalize-scope1.test | 0 .../src/test/resources}/regex-normalize-scope1.xml | 0 .../urlnormalizer-slash/build.xml | 0 .../urlnormalizer-slash}/ivy.xml | 0 .../urlnormalizer-slash/plugin.xml | 0 nutch-plugins/urlnormalizer-slash/pom.xml | 38 ++ .../urlnormalizer/slash/SlashURLNormalizer.java | 0 .../slash/TestSlashURLNormalizer.java | 0 .../src/test/resources}/slashes.txt | 0 pom.xml | 157 +++++++ .../urlfilter-ignoreexempt/data/.donotdelete | 0 1023 files changed, 3734 insertions(+), 9 deletions(-) diff --cc nutch-core/src/test/java/org/apache/nutch/crawl/TestCrawlDbMerger.java index 7c4b2eb,599c353..bfb1581 --- a/nutch-core/src/test/java/org/apache/nutch/crawl/TestCrawlDbMerger.java +++ b/nutch-core/src/test/java/org/apache/nutch/crawl/TestCrawlDbMerger.java @@@ -37,10 -36,11 +38,11 @@@ import org.junit.After import org.junit.Assert; import org.junit.Before; import org.junit.Test; + import org.junit.experimental.categories.Category; public class TestCrawlDbMerger { - private static final Logger LOG = Logger.getLogger(CrawlDbMerger.class - .getName()); + private static final Logger LOG = LoggerFactory + .getLogger(MethodHandles.lookup().lookupClass()); String url10 = "http://example.com/"; String url11 = "http://example.com/foo"; -- To stop receiving notification emails like this one, please contact "[email protected]" <[email protected]>.
