Constant Field Values
Contents
org.apache.*
-
org.apache.nutch.collection.CollectionManager
-
org.apache.nutch.collection.SubcollectionModifier and TypeConstant FieldValue
public static final String"blacklist"public static final String"subcollection"public static final String"subcollections"public static final String"id"public static final String"key"public static final String"name"public static final String"whitelist"
-
org.apache.nutch.crawl.CrawlDatumModifier and TypeConstant FieldValue
public static final String"crawl_fetch"public static final String"crawl_generate"public static final String"crawl_parse"public static final byte0x7public static final byte0x2public static final byte0x3public static final byte0x1fpublic static final byte0x6public static final byte0x8public static final byte0x9public static final byte0x5public static final byte0x4public static final byte0x1public static final byte0x25public static final byte0x3fpublic static final byte0x26public static final byte0x24public static final byte0x23public static final byte0x22public static final byte0x21public static final byte0x42public static final byte0x43public static final byte0x45public static final byte0x44public static final byte0x41 -
org.apache.nutch.crawl.CrawlDb
-
org.apache.nutch.crawl.CrawlDbFilter
-
org.apache.nutch.crawl.DeduplicationJob
-
org.apache.nutch.crawl.FetchScheduleModifier and TypeConstant FieldValue
public static final int86400public static final int1public static final int2public static final int0 -
org.apache.nutch.crawl.GeneratorModifier and TypeConstant FieldValue
public static final String"generate.update.crawldb"public static final String"generate.count.mode"public static final String"domain"public static final String"host"public static final String"generate.curTime"public static final String"crawl.gen.delay"public static final String"generate.expr"public static final String"generate.fetch.delay.expr"public static final String"generate.filter"public static final String"generate.hostdb"public static final String"generate.max.count"public static final String"generate.max.count.expr"public static final String"generate.max.num.segments"public static final String"generate.min.interval"public static final String"generate.min.score"public static final String"generate.normalise"public static final String"generate.restrict.status"public static final String"generate.topN" -
org.apache.nutch.crawl.InjectorModifier and TypeConstant FieldValue
public static final String"crawldb.inject.filter.normalize.all" -
org.apache.nutch.crawl.Injector.InjectMapper
-
org.apache.nutch.crawl.LinkDb
-
org.apache.nutch.crawl.LinkDbFilter
-
org.apache.nutch.crawl.MimeAdaptiveFetchSchedule
-
org.apache.nutch.crawl.URLPartitioner
-
org.apache.nutch.fetcher.Fetcher
-
org.apache.nutch.fetcher.FetchItemQueues
-
org.apache.nutch.hostdb.ReadHostDb
-
org.apache.nutch.hostdb.UpdateHostDbModifier and TypeConstant FieldValue
public static final String"hostdb.check.failed"public static final String"hostdb.check.known"public static final String"hostdb.check.new"public static final String"hostdb.crawldatum.processors"public static final String"hostdb.force.check"public static final String"hostdb.num.resolvers.threads"public static final String"hostdb.numeric.fields"public static final String"hostdb.percentiles"public static final String"hostdb.purge.failed.hosts.threshold"public static final String"hostdb.recheck.interval"public static final String"hostdb.string.fields"public static final String"hostdb.url.filter"public static final String"hostdb.url.limit"public static final String"hostdb.url.normalize"public static final String".locked"
-
org.apache.nutch.indexer.IndexerMapReduceModifier and TypeConstant FieldValue
public static final String"indexer.binary.base64"public static final String"indexer.delete"public static final String"indexer.delete.robots.noindex"public static final String"indexer.delete.skipped.by.indexingfilter"public static final String"indexer.nocommit"public static final String"indexer.additional.params"public static final String"indexer.skip.notmodified"public static final String"indexer.url.filters"public static final String"indexer.url.normalizers" -
org.apache.nutch.indexer.IndexingFilters
-
org.apache.nutch.indexer.NutchDocument
-
org.apache.nutch.indexer.NutchIndexAction
-
org.apache.nutch.indexer.feed.FeedIndexingFilter
-
org.apache.nutch.indexer.filter.MimeTypeIndexingFilter
-
org.apache.nutch.indexer.links.LinksIndexingFilter
-
org.apache.nutch.indexwriter.cloudsearch.CloudSearchConstants
-
org.apache.nutch.indexwriter.csv.CSVConstantsModifier and TypeConstant FieldValue
public static final String"charset"public static final String"escapechar"public static final String"separator"public static final String"fields"public static final String"maxfieldlength"public static final String"maxfieldvalues"public static final String"outpath"public static final String"quotechar"public static final String"valuesep"public static final String"header"
-
org.apache.nutch.indexwriter.dummy.DummyConstants
-
org.apache.nutch.indexwriter.elastic.ElasticConstantsModifier and TypeConstant FieldValue
public static final String"bulk.close.timeout"public static final String"exponential.backoff.millis"public static final String"exponential.backoff.retries"public static final String"host"public static final String"index"public static final String"max.bulk.docs"public static final String"max.bulk.size"public static final String"options"public static final String"password"public static final String"port"public static final String"scheme"public static final String"auth"public static final String"username"
-
org.apache.nutch.indexwriter.kafka.KafkaConstants
-
org.apache.nutch.indexwriter.opensearch1x.OpenSearch1xConstantsModifier and TypeConstant FieldValue
public static final String"bulk.close.timeout"public static final String"exponential.backoff.millis"public static final String"exponential.backoff.retries"public static final String"host"public static final String"index"public static final String"key.store.password"public static final String"key.store.path"public static final String"key.store.type"public static final String"max.bulk.docs"public static final String"max.bulk.size"public static final String"options"public static final String"password"public static final String"port"public static final String"scheme"public static final String"trust.store.password"public static final String"trust.store.path"public static final String"trust.store.type"public static final String"username"
-
org.apache.nutch.indexwriter.solr.SolrConstantsModifier and TypeConstant FieldValue
public static final String"auth.header.name"public static final String"auth.header.value"public static final String"collection"public static final String"commitSize"public static final String"password"public static final String"type"public static final String"url"public static final String"auth"public static final String"username"public static final String"weight.field"
-
org.apache.nutch.metadata.CreativeCommons
-
org.apache.nutch.metadata.DublinCoreModifier and TypeConstant FieldValue
public static final String"contributor"public static final String"coverage"public static final String"creator"public static final String"date"public static final String"description"public static final String"format"public static final String"identifier"public static final String"language"public static final String"modified"public static final String"publisher"public static final String"relation"public static final String"rights"public static final String"source"public static final String"subject"public static final String"title"public static final String"type" -
org.apache.nutch.metadata.Feed
-
org.apache.nutch.metadata.HttpHeadersModifier and TypeConstant FieldValue
public static final String"Client-Transfer-Encoding"public static final String"Content-Disposition"public static final String"Content-Encoding"public static final String"Content-Language"public static final String"Content-Length"public static final String"Content-Location"public static final String"Content-MD5"public static final String"Content-Type"public static final String"If-Modified-Since"public static final String"Last-Modified"public static final String"Location"public static final String"Transfer-Encoding"public static final String"User-Agent" -
org.apache.nutch.metadata.NutchModifier and TypeConstant FieldValue
public static final String"crawldb"public static final String"hostdb"public static final String"linkdb"public static final String"url_dir"public static final String"segment_dir"public static final String"segment"public static final String"all"public static final String"content"public static final String"caching.forbidden"public static final String"none"public static final String"CharEncodingForConversion"public static final String"storage.crawl.id"public static final String"content-language"public static final String"content-type"public static final String"fetchTime"public static final String"score"public static final String"title"public static final String"_fst_"public static final String"_ftk_"public static final String"fixedInterval"public static final String"_ngt_"public static final String"OriginalCharEncoding"public static final String"_pst_"public static final String"_repr_"public static final String"robots"public static final String"nutch.crawl.score"public static final String"nutch.segment.name"public static final String"nutch.content.digest"public static final String"progress"public static final String"result"
-
org.apache.nutch.metrics.LatencyTracker
-
org.apache.nutch.metrics.NutchMetricsModifier and TypeConstant FieldValue
public static final String"deleted_documents_total"public static final String"gone_records_removed_total"public static final String"orphan_records_removed_total"public static final String"urls_filtered_total"public static final String"documents_marked_duplicate_total"public static final String"empty_result_total"public static final String"fetched_total"public static final String"not_fetched_total"public static final String"errors_indexing_total"public static final String"errors_network_total"public static final String"errors_other_total"public static final String"errors_parsing_total"public static final String"errors_protocol_total"public static final String"errors_scoring_total"public static final String"errors_timeout_total"public static final String"errors_total"public static final String"errors_url_total"public static final String"above_exception_threshold_total"public static final String"bytes_downloaded_total"public static final String"filtered_total"public static final String"hit_by_throughput_threshold_total"public static final String"hit_by_timelimit_total"public static final String"hit_by_timeout_total"public static final String"hung_threads_total"public static final String"fetch_latency"public static final String"outlinks_detected_total"public static final String"outlinks_following_total"public static final String"redirect_count_exceeded_total"public static final String"redirect_deduplicated_total"public static final String"redirect_not_created_total"public static final String"robots_defer_visits_dropped_total"public static final String"robots_denied_maxcrawldelay_total"public static final String"robots_denied_total"public static final String"expr_rejected_total"public static final String"hosts_affected_per_host_overflow_total"public static final String"interval_rejected_total"public static final String"schedule_rejected_total"public static final String"score_too_low_total"public static final String"status_rejected_total"public static final String"url_filters_rejected_total"public static final String"urls_skipped_per_host_overflow_total"public static final String"wait_for_update_total"public static final String"nutch_cleaning"public static final String"nutch_commoncrawl_dumper"public static final String"nutch_crawldb"public static final String"nutch_crawldb_filter"public static final String"nutch_dedup"public static final String"nutch_domain_stats"public static final String"nutch_fetcher"public static final String"nutch_fetcher_outlinks"public static final String"nutch_generator"public static final String"nutch_hostdb"public static final String"nutch_indexer"public static final String"nutch_injector"public static final String"nutch_parser"public static final String"nutch_sitemap"public static final String"nutch_warc_exporter"public static final String"nutch_webgraph"public static final String"checked_hosts_total"public static final String"existing_known_host_total"public static final String"existing_unknown_host_total"public static final String"filtered_records_total"public static final String"new_known_host_total"public static final String"new_unknown_host_total"public static final String"purged_unknown_host_total"public static final String"rediscovered_host_total"public static final String"skipped_not_eligible_total"public static final String"total_hosts_total"public static final String"url_limit_not_reached_total"public static final String"deleted_by_indexing_filter_total"public static final String"deleted_duplicates_total"public static final String"deleted_failed_parse_total"public static final String"deleted_gone_total"public static final String"deleted_redirects_total"public static final String"deleted_robots_noindex_total"public static final String"indexed_total"public static final String"index_latency"public static final String"skipped_by_indexing_filter_total"public static final String"skipped_not_modified_total"public static final String"urls_filtered_total"public static final String"urls_injected_total"public static final String"urls_injected_unique_total"public static final String"urls_merged_total"public static final String"urls_purged_404_total"public static final String"urls_purged_filter_total"public static final String"__LATENCY__"public static final String"parse_latency"public static final String"existing_sitemap_entries_total"public static final String"failed_fetches_total"public static final String"filtered_sitemaps_from_hostname_total"public static final String"filtered_records_total"public static final String"sitemaps_from_hostname_total"public static final String"new_sitemap_entries_total"public static final String"sitemap_seeds_total"public static final String"missing_content_total"public static final String"missing_metadata_total"public static final String"omitted_empty_response_total"public static final String"records_generated_total"public static final String"added_links_total"public static final String"removed_links_total"
-
org.apache.nutch.microformats.reltag.RelTagParser
-
org.apache.nutch.net.URLFilters
-
org.apache.nutch.net.URLNormalizersModifier and TypeConstant FieldValue
public static final String"crawldb"public static final String"default"public static final String"fetcher"public static final String"generate_host_count"public static final String"indexer"public static final String"inject"public static final String"linkdb"public static final String"outlink"public static final String"partition"
-
org.apache.nutch.net.protocols.ProtocolLogUtilModifier and TypeConstant FieldValue
public static final String"http.log.exceptions.suppress.stack" -
org.apache.nutch.net.protocols.ResponseModifier and TypeConstant FieldValue
public static final String"_cipher_suites_"public static final String"nutch.fetch.time"public static final String"_ip_"public static final String"_protocol_versions_"public static final String"_request_"public static final String"_response.headers_"public static final String"http.content.truncated"public static final String"http.content.truncated.reason"
-
org.apache.nutch.net.urlnormalizer.basic.BasicURLNormalizer
-
org.apache.nutch.parse.HtmlParseFilters
-
org.apache.nutch.parse.ParseData
-
org.apache.nutch.parse.ParserFactory
-
org.apache.nutch.parse.ParseSegment
-
org.apache.nutch.parse.ParseStatusModifier and TypeConstant FieldValue
public static final byte0x2public static final short200public static final short203public static final short205public static final short204public static final short202public static final byte0x0public static final byte0x1public static final short100 -
org.apache.nutch.parse.ParseText
-
org.apache.nutch.parse.feed.FeedParser
-
org.apache.nutch.parsefilter.naivebayes.NaiveBayesParseFilter
-
org.apache.nutch.protocol.Content
-
org.apache.nutch.protocol.ProtocolStatusModifier and TypeConstant FieldValue
public static final int17public static final int23public static final int16public static final int2public static final int11public static final int12public static final int20public static final int14public static final int21public static final int10public static final int19public static final int15public static final int18public static final int1public static final int13public static final int22
-
org.apache.nutch.protocol.http.api.HttpBase
-
org.apache.nutch.protocol.httpclient.HttpAuthenticationFactory
-
org.apache.nutch.scoring.depth.DepthScoringFilter
-
org.apache.nutch.scoring.metadata.MetadataScoringFilter
-
org.apache.nutch.scoring.webgraph.LinkDatum
-
org.apache.nutch.scoring.webgraph.LinkDumper
-
org.apache.nutch.scoring.webgraph.WebGraph
-
org.apache.nutch.scoring.webgraph.WebGraph.OutlinkDb
-
org.apache.nutch.tools.CommonCrawlFormatWARC
-
org.apache.nutch.tools.WARCUtilsModifier and TypeConstant FieldValue
public static final String": "public static final String"conformsTo"public static final String"\r\n"public static final String"format"public static final String"hostname"public static final String"http-header-from"public static final String"http-header-user-agent"public static final String"ip"public static final String"operator"public static final String"robots"public static final String"software"protected static final String"X-Crawler-"
-
org.apache.nutch.tools.arc.ArcSegmentCreator
-
org.apache.nutch.tools.arc.ArcSegmentCreator.ArcSegmentCreatorMapper
-
org.apache.nutch.urlfilter.automaton.AutomatonURLFilter
-
org.apache.nutch.urlfilter.fast.FastURLFilter
-
org.apache.nutch.urlfilter.ignoreexempt.ExemptionUrlFilterModifier and TypeConstant FieldValue
public static final String"db.ignore.external.exemptions.file"
-
org.apache.nutch.urlfilter.regex.RegexURLFilter
-
org.apache.nutch.util.EncodingDetectorModifier and TypeConstant FieldValue
public static final String"encodingdetector.charset.min.confidence"public static final int-1 -
org.apache.nutch.util.JexlUtil
-
org.apache.nutch.util.NutchConfiguration
-
org.apache.nutch.util.SitemapProcessorModifier and TypeConstant FieldValue
public static final String"current"public static final String".locked"public static final String"sitemap.url.default.sitemap.xml"public static final String"sitemap.url.overwrite.existing"public static final String"sitemap.redir.max"public static final String"sitemap.size.max"public static final String"sitemap.strict.parsing"public static final String"sitemap.url.filter"public static final String"sitemap.url.normalize"