This is an automated email from the ASF dual-hosted git repository.
snagel pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/nutch.git
from e62a0b8e3 Merge pull request #855 from
sebastian-nagel/NUTCH-3116-dependency-upgrades
add 25f5610cc NUTCH-3112 Utilize parameterized logging
add bf54609d2 NUTCH-3112 Utilize parameterized logging
new 671b1e0ea Merge pull request #851 from
sebastian-nagel/NUTCH-3112-parameterized-logging
The 1 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails. The revisions
listed as "add" were already present in the repository and have only
been added to this reference.
Summary of changes:
.../apache/nutch/crawl/AbstractFetchSchedule.java | 4 +-
.../apache/nutch/crawl/AdaptiveFetchSchedule.java | 61 ++++++-----
src/java/org/apache/nutch/crawl/CrawlDb.java | 3 +-
src/java/org/apache/nutch/crawl/CrawlDbFilter.java | 4 +-
src/java/org/apache/nutch/crawl/CrawlDbMerger.java | 3 +-
src/java/org/apache/nutch/crawl/CrawlDbReader.java | 120 ++++++++++-----------
.../org/apache/nutch/crawl/CrawlDbReducer.java | 6 +-
.../org/apache/nutch/crawl/DeduplicationJob.java | 12 +--
.../apache/nutch/crawl/FetchScheduleFactory.java | 2 +-
src/java/org/apache/nutch/crawl/Generator.java | 35 +++---
src/java/org/apache/nutch/crawl/Injector.java | 13 ++-
src/java/org/apache/nutch/crawl/LinkDbFilter.java | 8 +-
src/java/org/apache/nutch/crawl/LinkDbMerger.java | 6 +-
src/java/org/apache/nutch/crawl/LinkDbReader.java | 2 +-
.../nutch/crawl/MimeAdaptiveFetchSchedule.java | 21 ++--
.../org/apache/nutch/crawl/URLPartitioner.java | 6 +-
src/java/org/apache/nutch/fetcher/FetchItem.java | 9 +-
.../org/apache/nutch/fetcher/FetchItemQueue.java | 14 +--
.../org/apache/nutch/fetcher/FetchItemQueues.java | 6 +-
src/java/org/apache/nutch/fetcher/Fetcher.java | 12 +--
.../org/apache/nutch/fetcher/FetcherThread.java | 54 ++++------
src/java/org/apache/nutch/fetcher/QueueFeeder.java | 4 +-
src/java/org/apache/nutch/hostdb/ReadHostDb.java | 9 +-
.../org/apache/nutch/hostdb/ResolverThread.java | 12 +--
src/java/org/apache/nutch/hostdb/UpdateHostDb.java | 11 +-
.../apache/nutch/hostdb/UpdateHostDbReducer.java | 10 +-
src/java/org/apache/nutch/indexer/CleaningJob.java | 24 +----
.../org/apache/nutch/indexer/IndexerMapReduce.java | 4 +-
.../nutch/indexer/IndexingFiltersChecker.java | 6 +-
src/java/org/apache/nutch/net/URLNormalizers.java | 8 +-
.../org/apache/nutch/parse/OutlinkExtractor.java | 10 +-
.../org/apache/nutch/parse/ParseOutputFormat.java | 9 +-
.../org/apache/nutch/parse/ParsePluginsReader.java | 32 ++----
src/java/org/apache/nutch/parse/ParseResult.java | 2 +-
src/java/org/apache/nutch/parse/ParseSegment.java | 23 ++--
src/java/org/apache/nutch/parse/ParseUtil.java | 44 ++++----
src/java/org/apache/nutch/parse/ParserChecker.java | 24 ++---
src/java/org/apache/nutch/parse/ParserFactory.java | 70 ++++++------
.../org/apache/nutch/plugin/PluginDescriptor.java | 2 +-
.../apache/nutch/plugin/PluginManifestParser.java | 2 +-
.../org/apache/nutch/plugin/PluginRepository.java | 6 +-
.../apache/nutch/protocol/RobotRulesParser.java | 7 +-
.../apache/nutch/scoring/webgraph/LinkDumper.java | 5 +-
.../apache/nutch/scoring/webgraph/LinkRank.java | 35 +++---
.../apache/nutch/scoring/webgraph/NodeDumper.java | 3 +-
.../nutch/scoring/webgraph/ScoreUpdater.java | 13 ++-
.../apache/nutch/scoring/webgraph/WebGraph.java | 29 +++--
.../org/apache/nutch/segment/SegmentChecker.java | 7 +-
.../apache/nutch/segment/SegmentMergeFilters.java | 6 +-
.../org/apache/nutch/segment/SegmentMerger.java | 4 +-
.../org/apache/nutch/segment/SegmentReader.java | 16 ++-
.../nutch/tools/AbstractCommonCrawlFormat.java | 4 +-
.../apache/nutch/tools/CommonCrawlDataDumper.java | 26 +++--
src/java/org/apache/nutch/tools/DmozParser.java | 22 ++--
src/java/org/apache/nutch/tools/FileDumper.java | 31 +++---
src/java/org/apache/nutch/tools/FreeGenerator.java | 4 +-
src/java/org/apache/nutch/tools/ResolveUrls.java | 16 +--
.../apache/nutch/tools/arc/ArcSegmentCreator.java | 37 +++----
.../org/apache/nutch/util/AbstractChecker.java | 4 +-
.../apache/nutch/util/CrawlCompletionStats.java | 2 +-
.../org/apache/nutch/util/DomainStatistics.java | 4 +-
.../org/apache/nutch/util/EncodingDetector.java | 17 ++-
src/java/org/apache/nutch/util/MimeUtil.java | 11 +-
src/java/org/apache/nutch/util/ObjectCache.java | 5 +-
.../nutch/util/ProtocolStatusStatistics.java | 2 +-
.../org/apache/nutch/util/SitemapProcessor.java | 7 +-
.../creativecommons/nutch/CCIndexingFilter.java | 8 +-
.../org/creativecommons/nutch/CCParseFilter.java | 17 +--
.../org/apache/nutch/parse/feed/FeedParser.java | 4 +-
.../nutch/indexer/anchor/AnchorIndexingFilter.java | 2 +-
.../nutch/indexer/more/MoreIndexingFilter.java | 8 +-
.../nutch/indexer/replace/FieldReplacer.java | 11 +-
.../nutch/indexer/replace/ReplaceIndexer.java | 14 +--
.../nutch/indexwriter/csv/CSVIndexWriter.java | 14 +--
.../indexwriter/elastic/ElasticIndexWriter.java | 2 +-
.../opensearch1x/OpenSearch1xIndexWriter.java | 2 +-
.../nutch/indexwriter/solr/SolrIndexWriter.java | 4 +-
.../nutch/analysis/lang/HTMLLanguageParser.java | 4 +-
.../apache/nutch/protocol/http/api/HttpBase.java | 34 +++---
.../protocol/http/api/HttpRobotRulesParser.java | 6 +-
.../nutch/urlfilter/api/RegexURLFilterBase.java | 12 +--
.../nutch/microformats/reltag/RelTagParser.java | 2 +-
.../indexer/filter/MimeTypeIndexingFilter.java | 8 +-
.../org/apache/nutch/parse/html/HtmlParser.java | 31 ++----
.../apache/nutch/parse/html/TestHtmlParser.java | 6 +-
.../org/apache/nutch/parse/js/JSParseFilter.java | 18 +---
.../nutch/parse/metatags/MetaTagsParser.java | 8 +-
.../parse/tika/BoilerpipeExtractorRepository.java | 12 ++-
.../org/apache/nutch/parse/tika/TikaParser.java | 2 +-
.../apache/nutch/parse/tika/TestHtmlParser.java | 6 +-
.../java/org/apache/nutch/parse/zip/ZipParser.java | 9 +-
.../apache/nutch/parse/zip/ZipTextExtractor.java | 5 +-
.../naivebayes/NaiveBayesParseFilter.java | 22 ++--
.../nutch/parsefilter/regex/RegexParseFilter.java | 19 ++--
.../java/org/apache/nutch/protocol/file/File.java | 4 +-
.../apache/nutch/protocol/file/FileResponse.java | 8 +-
.../org/apache/nutch/protocol/ftp/FtpResponse.java | 119 ++++++++------------
.../nutch/protocol/ftp/FtpRobotRulesParser.java | 8 +-
.../nutch/protocol/htmlunit/HttpResponse.java | 4 +-
.../apache/nutch/protocol/http/HttpResponse.java | 16 +--
.../httpclient/DummySSLProtocolSocketFactory.java | 4 +-
.../org/apache/nutch/protocol/httpclient/Http.java | 45 ++++----
.../httpclient/HttpFormAuthentication.java | 14 +--
.../protocol/interactiveselenium/HttpResponse.java | 16 ++-
.../nutch/protocol/selenium/HttpResponse.java | 4 +-
.../nutch/scoring/depth/DepthScoringFilter.java | 6 +-
.../apache/nutch/collection/CollectionManager.java | 18 +---
.../nutch/urlfilter/domain/DomainURLFilter.java | 5 +-
.../domaindenylist/DomainDenylistURLFilter.java | 8 +-
.../nutch/urlfilter/prefix/PrefixURLFilter.java | 2 +-
.../nutch/urlfilter/suffix/SuffixURLFilter.java | 2 +-
.../net/urlnormalizer/ajax/AjaxURLNormalizer.java | 4 +-
.../urlnormalizer/basic/BasicURLNormalizer.java | 6 +-
.../net/urlnormalizer/host/HostURLNormalizer.java | 14 +--
.../protocol/ProtocolURLNormalizer.java | 14 +--
.../urlnormalizer/regex/RegexURLNormalizer.java | 33 +++---
.../regex/TestRegexURLNormalizer.java | 13 ++-
.../urlnormalizer/slash/SlashURLNormalizer.java | 14 +--
.../nutch/crawl/ContinuousCrawlTestUtil.java | 22 ++--
.../org/apache/nutch/crawl/CrawlDBTestUtil.java | 4 +-
.../apache/nutch/crawl/TODOTestCrawlDbStates.java | 23 ++--
.../org/apache/nutch/crawl/TestCrawlDbMerger.java | 10 +-
.../org/apache/nutch/crawl/TestCrawlDbStates.java | 62 +++++------
.../org/apache/nutch/crawl/TestLinkDbMerger.java | 10 +-
.../segment/TestSegmentMergerCrawlDatums.java | 17 ++-
125 files changed, 763 insertions(+), 1086 deletions(-)