Constant Field Values
Contents
org.apache.*
-
org.apache.nutch.collection.CollectionManager Modifier and Type Constant Field Value public static final StringDEFAULT_FILE_NAME"subcollections.xml" -
org.apache.nutch.collection.Subcollection Modifier and Type Constant Field Value public static final StringTAG_BLACKLIST"blacklist"public static final StringTAG_COLLECTION"subcollection"public static final StringTAG_COLLECTIONS"subcollections"public static final StringTAG_ID"id"public static final StringTAG_KEY"key"public static final StringTAG_NAME"name"public static final StringTAG_WHITELIST"whitelist"
-
org.apache.nutch.crawl.CrawlDatum Modifier and Type Constant Field Value public static final StringFETCH_DIR_NAME"crawl_fetch"public static final StringGENERATE_DIR_NAME"crawl_generate"public static final StringPARSE_DIR_NAME"crawl_parse"public static final byteSTATUS_DB_DUPLICATE7public static final byteSTATUS_DB_FETCHED2public static final byteSTATUS_DB_GONE3public static final byteSTATUS_DB_MAX31public static final byteSTATUS_DB_NOTMODIFIED6public static final byteSTATUS_DB_ORPHAN8public static final byteSTATUS_DB_REDIR_PERM5public static final byteSTATUS_DB_REDIR_TEMP4public static final byteSTATUS_DB_UNFETCHED1public static final byteSTATUS_FETCH_GONE37public static final byteSTATUS_FETCH_MAX63public static final byteSTATUS_FETCH_NOTMODIFIED38public static final byteSTATUS_FETCH_REDIR_PERM36public static final byteSTATUS_FETCH_REDIR_TEMP35public static final byteSTATUS_FETCH_RETRY34public static final byteSTATUS_FETCH_SUCCESS33public static final byteSTATUS_INJECTED66public static final byteSTATUS_LINKED67public static final byteSTATUS_PARSE_META68public static final byteSTATUS_SIGNATURE65 -
org.apache.nutch.crawl.CrawlDb Modifier and Type Constant Field Value public static final StringCRAWLDB_ADDITIONS_ALLOWED"db.update.additions.allowed"public static final StringCRAWLDB_PURGE_404"db.update.purge.404"public static final StringCRAWLDB_PURGE_ORPHANS"db.update.purge.orphans"public static final StringCURRENT_NAME"current"public static final StringLOCK_NAME".locked" -
org.apache.nutch.crawl.CrawlDbFilter Modifier and Type Constant Field Value public static final StringURL_FILTERING"crawldb.url.filters"public static final StringURL_NORMALIZING"crawldb.url.normalizers"public static final StringURL_NORMALIZING_SCOPE"crawldb.url.normalizers.scope" -
org.apache.nutch.crawl.DeduplicationJob Modifier and Type Constant Field Value protected static final StringDEDUPLICATION_COMPARE_ORDER"deduplication.compare.order"protected static final StringDEDUPLICATION_GROUP_MODE"deduplication.group.mode" -
org.apache.nutch.crawl.FetchSchedule Modifier and Type Constant Field Value public static final intSECONDS_PER_DAY86400public static final intSTATUS_MODIFIED1public static final intSTATUS_NOTMODIFIED2public static final intSTATUS_UNKNOWN0 -
org.apache.nutch.crawl.Generator Modifier and Type Constant Field Value public static final StringGENERATE_UPDATE_CRAWLDB"generate.update.crawldb"public static final StringGENERATOR_COUNT_MODE"generate.count.mode"public static final StringGENERATOR_COUNT_VALUE_DOMAIN"domain"public static final StringGENERATOR_COUNT_VALUE_HOST"host"public static final StringGENERATOR_CUR_TIME"generate.curTime"public static final StringGENERATOR_DELAY"crawl.gen.delay"public static final StringGENERATOR_EXPR"generate.expr"public static final StringGENERATOR_FETCH_DELAY_EXPR"generate.fetch.delay.expr"public static final StringGENERATOR_FILTER"generate.filter"public static final StringGENERATOR_HOSTDB"generate.hostdb"public static final StringGENERATOR_MAX_COUNT"generate.max.count"public static final StringGENERATOR_MAX_COUNT_EXPR"generate.max.count.expr"public static final StringGENERATOR_MAX_NUM_SEGMENTS"generate.max.num.segments"public static final StringGENERATOR_MIN_INTERVAL"generate.min.interval"public static final StringGENERATOR_MIN_SCORE"generate.min.score"public static final StringGENERATOR_NORMALISE"generate.normalise"public static final StringGENERATOR_RESTRICT_STATUS"generate.restrict.status"public static final StringGENERATOR_TOP_N"generate.topN" -
org.apache.nutch.crawl.Injector Modifier and Type Constant Field Value public static final StringURL_FILTER_NORMALIZE_ALL"crawldb.inject.filter.normalize.all" -
org.apache.nutch.crawl.Injector.InjectMapper Modifier and Type Constant Field Value public static final StringEQUAL_CHARACTER"="public static final StringTAB_CHARACTER"\t"public static final StringURL_NORMALIZING_SCOPE"crawldb.url.normalizers.scope" -
org.apache.nutch.crawl.LinkDb Modifier and Type Constant Field Value public static final StringCURRENT_NAME"current"public static final StringIGNORE_EXTERNAL_LINKS"linkdb.ignore.external.links"public static final StringIGNORE_INTERNAL_LINKS"linkdb.ignore.internal.links"public static final StringLOCK_NAME".locked" -
org.apache.nutch.crawl.LinkDbFilter Modifier and Type Constant Field Value public static final StringURL_FILTERING"linkdb.url.filters"public static final StringURL_NORMALIZING"linkdb.url.normalizer"public static final StringURL_NORMALIZING_SCOPE"linkdb.url.normalizer.scope" -
org.apache.nutch.crawl.MimeAdaptiveFetchSchedule Modifier and Type Constant Field Value public static final StringSCHEDULE_DEC_RATE"db.fetch.schedule.adaptive.dec_rate"public static final StringSCHEDULE_INC_RATE"db.fetch.schedule.adaptive.inc_rate"public static final StringSCHEDULE_MIME_FILE"db.fetch.schedule.mime.file" -
org.apache.nutch.crawl.URLPartitioner Modifier and Type Constant Field Value public static final StringPARTITION_MODE_DOMAIN"byDomain"public static final StringPARTITION_MODE_HOST"byHost"public static final StringPARTITION_MODE_IP"byIP"public static final StringPARTITION_MODE_KEY"partition.url.mode"
-
org.apache.nutch.fetcher.Fetcher Modifier and Type Constant Field Value public static final StringCONTENT_REDIR"content"public static final intPERM_REFRESH_TIME5public static final StringPROTOCOL_REDIR"protocol" -
org.apache.nutch.fetcher.FetchItemQueues Modifier and Type Constant Field Value public static final StringDEFAULT_ID"default"public static final StringQUEUE_MODE_DOMAIN"byDomain"public static final StringQUEUE_MODE_HOST"byHost"public static final StringQUEUE_MODE_IP"byIP"
-
org.apache.nutch.hostdb.ReadHostDb Modifier and Type Constant Field Value public static final StringHOSTDB_DUMP_HEADER"hostdb.dump.field.header"public static final StringHOSTDB_DUMP_HOMEPAGES"hostdb.dump.homepages"public static final StringHOSTDB_DUMP_HOSTNAMES"hostdb.dump.hostnames"public static final StringHOSTDB_FILTER_EXPRESSION"hostdb.filter.expression" -
org.apache.nutch.hostdb.UpdateHostDb Modifier and Type Constant Field Value public static final StringHOSTDB_CHECK_FAILED"hostdb.check.failed"public static final StringHOSTDB_CHECK_KNOWN"hostdb.check.known"public static final StringHOSTDB_CHECK_NEW"hostdb.check.new"public static final StringHOSTDB_CRAWLDATUM_PROCESSORS"hostdb.crawldatum.processors"public static final StringHOSTDB_FORCE_CHECK"hostdb.force.check"public static final StringHOSTDB_NUM_RESOLVER_THREADS"hostdb.num.resolvers.threads"public static final StringHOSTDB_NUMERIC_FIELDS"hostdb.numeric.fields"public static final StringHOSTDB_PERCENTILES"hostdb.percentiles"public static final StringHOSTDB_PURGE_FAILED_HOSTS_THRESHOLD"hostdb.purge.failed.hosts.threshold"public static final StringHOSTDB_RECHECK_INTERVAL"hostdb.recheck.interval"public static final StringHOSTDB_STRING_FIELDS"hostdb.string.fields"public static final StringHOSTDB_URL_FILTERING"hostdb.url.filter"public static final StringHOSTDB_URL_NORMALIZING"hostdb.url.normalize"public static final StringLOCK_NAME".locked"
-
org.apache.nutch.indexer.IndexerMapReduce Modifier and Type Constant Field Value public static final StringINDEXER_BINARY_AS_BASE64"indexer.binary.base64"public static final StringINDEXER_DELETE"indexer.delete"public static final StringINDEXER_DELETE_ROBOTS_NOINDEX"indexer.delete.robots.noindex"public static final StringINDEXER_DELETE_SKIPPED"indexer.delete.skipped.by.indexingfilter"public static final StringINDEXER_NO_COMMIT"indexer.nocommit"public static final StringINDEXER_PARAMS"indexer.additional.params"public static final StringINDEXER_SKIP_NOTMODIFIED"indexer.skip.notmodified"public static final StringURL_FILTERING"indexer.url.filters"public static final StringURL_NORMALIZING"indexer.url.normalizers" -
org.apache.nutch.indexer.IndexingFilters Modifier and Type Constant Field Value public static final StringINDEXINGFILTER_ORDER"indexingfilter.order" -
org.apache.nutch.indexer.NutchDocument Modifier and Type Constant Field Value public static final byteVERSION2 -
org.apache.nutch.indexer.NutchIndexAction Modifier and Type Constant Field Value public static final byteADD0public static final byteDELETE1public static final byteUPDATE2
-
org.apache.nutch.indexer.feed.FeedIndexingFilter Modifier and Type Constant Field Value public static final StringdateFormatStr"yyyyMMddHHmm"
-
org.apache.nutch.indexer.filter.MimeTypeIndexingFilter Modifier and Type Constant Field Value public static final StringMIMEFILTER_REGEX_FILE"mimetype.filter.file"
-
org.apache.nutch.indexer.links.LinksIndexingFilter Modifier and Type Constant Field Value public static final StringLINKS_INLINKS_HOST"index.links.inlinks.host.ignore"public static final StringLINKS_ONLY_HOSTS"index.links.hosts.only"public static final StringLINKS_OUTLINKS_HOST"index.links.outlinks.host.ignore"
-
org.apache.nutch.indexwriter.cloudsearch.CloudSearchConstants Modifier and Type Constant Field Value public static final StringBATCH_DUMP"batch.dump"public static final StringENDPOINT"endpoint"public static final StringMAX_DOCS_BATCH"batch.maxSize"public static final StringREGION"region"
-
org.apache.nutch.indexwriter.csv.CSVConstants Modifier and Type Constant Field Value public static final StringCSV_CHARSET"charset"public static final StringCSV_ESCAPECHARACTER"escapechar"public static final StringCSV_FIELD_SEPARATOR"separator"public static final StringCSV_FIELDS"fields"public static final StringCSV_MAXFIELDLENGTH"maxfieldlength"public static final StringCSV_MAXFIELDVALUES"maxfieldvalues"public static final StringCSV_OUTPATH"outpath"public static final StringCSV_QUOTECHARACTER"quotechar"public static final StringCSV_VALUESEPARATOR"valuesep"public static final StringCSV_WITHHEADER"header"
-
org.apache.nutch.indexwriter.dummy.DummyConstants Modifier and Type Constant Field Value public static final StringDELETE"delete"public static final StringPATH"path"
-
org.apache.nutch.indexwriter.elastic.ElasticConstants Modifier and Type Constant Field Value public static final StringBULK_CLOSE_TIMEOUT"bulk.close.timeout"public static final StringEXPONENTIAL_BACKOFF_MILLIS"exponential.backoff.millis"public static final StringEXPONENTIAL_BACKOFF_RETRIES"exponential.backoff.retries"public static final StringHOSTS"host"public static final StringINDEX"index"public static final StringMAX_BULK_DOCS"max.bulk.docs"public static final StringMAX_BULK_LENGTH"max.bulk.size"public static final StringOPTIONS"options"public static final StringPASSWORD"password"public static final StringPORT"port"public static final StringSCHEME"scheme"public static final StringUSE_AUTH"auth"public static final StringUSER"username"
-
org.apache.nutch.indexwriter.kafka.KafkaConstants Modifier and Type Constant Field Value public static final StringHOST"host"public static final StringKEY_SERIALIZER"key.serializer"public static final StringMAX_DOC_COUNT"max.doc.count"public static final StringPORT"port"public static final StringTOPIC"topic"public static final StringVALUE_SERIALIZER"value.serializer"
-
org.apache.nutch.indexwriter.opensearch1x.OpenSearch1xConstants Modifier and Type Constant Field Value public static final StringBULK_CLOSE_TIMEOUT"bulk.close.timeout"public static final StringEXPONENTIAL_BACKOFF_MILLIS"exponential.backoff.millis"public static final StringEXPONENTIAL_BACKOFF_RETRIES"exponential.backoff.retries"public static final StringHOSTS"host"public static final StringINDEX"index"public static final StringKEY_STORE_PASSWORD"key.store.password"public static final StringKEY_STORE_PATH"key.store.path"public static final StringKEY_STORE_TYPE"key.store.type"public static final StringMAX_BULK_DOCS"max.bulk.docs"public static final StringMAX_BULK_LENGTH"max.bulk.size"public static final StringOPTIONS"options"public static final StringPASSWORD"password"public static final StringPORT"port"public static final StringSCHEME"scheme"public static final StringTRUST_STORE_PASSWORD"trust.store.password"public static final StringTRUST_STORE_PATH"trust.store.path"public static final StringTRUST_STORE_TYPE"trust.store.type"public static final StringUSER"username"
-
org.apache.nutch.indexwriter.solr.SolrConstants Modifier and Type Constant Field Value public static final StringAUTH_HEADER_NAME"auth.header.name"public static final StringAUTH_HEADER_VALUE"auth.header.value"public static final StringCOLLECTION"collection"public static final StringCOMMIT_SIZE"commitSize"public static final StringPASSWORD"password"public static final StringSERVER_TYPE"type"public static final StringSERVER_URLS"url"public static final StringUSE_AUTH"auth"public static final StringUSERNAME"username"public static final StringWEIGHT_FIELD"weight.field"
-
org.apache.nutch.metadata.CreativeCommons Modifier and Type Constant Field Value public static final StringLICENSE_LOCATION"License-Location"public static final StringLICENSE_URL"License-Url"public static final StringWORK_TYPE"Work-Type" -
org.apache.nutch.metadata.DublinCore Modifier and Type Constant Field Value public static final StringCONTRIBUTOR"contributor"public static final StringCOVERAGE"coverage"public static final StringCREATOR"creator"public static final StringDATE"date"public static final StringDESCRIPTION"description"public static final StringFORMAT"format"public static final StringIDENTIFIER"identifier"public static final StringLANGUAGE"language"public static final StringMODIFIED"modified"public static final StringPUBLISHER"publisher"public static final StringRELATION"relation"public static final StringRIGHTS"rights"public static final StringSOURCE"source"public static final StringSUBJECT"subject"public static final StringTITLE"title"public static final StringTYPE"type" -
org.apache.nutch.metadata.Feed Modifier and Type Constant Field Value public static final StringFEED"feed"public static final StringFEED_AUTHOR"author"public static final StringFEED_PUBLISHED"published"public static final StringFEED_TAGS"tag"public static final StringFEED_UPDATED"updated" -
org.apache.nutch.metadata.HttpHeaders Modifier and Type Constant Field Value public static final StringCLIENT_TRANSFER_ENCODING"Client-Transfer-Encoding"public static final StringCONTENT_DISPOSITION"Content-Disposition"public static final StringCONTENT_ENCODING"Content-Encoding"public static final StringCONTENT_LANGUAGE"Content-Language"public static final StringCONTENT_LENGTH"Content-Length"public static final StringCONTENT_LOCATION"Content-Location"public static final StringCONTENT_MD5"Content-MD5"public static final StringCONTENT_TYPE"Content-Type"public static final StringIF_MODIFIED_SINCE"If-Modified-Since"public static final StringLAST_MODIFIED"Last-Modified"public static final StringLOCATION"Location"public static final StringTRANSFER_ENCODING"Transfer-Encoding"public static final StringUSER_AGENT"User-Agent" -
org.apache.nutch.metadata.Nutch Modifier and Type Constant Field Value public static final StringARG_CRAWLDB"crawldb"public static final StringARG_HOSTDB"hostdb"public static final StringARG_LINKDB"linkdb"public static final StringARG_SEEDDIR"url_dir"public static final StringARG_SEEDNAME"seedName"public static final StringARG_SEGMENTDIR"segment_dir"public static final StringARG_SEGMENTS"segment"public static final StringCACHING_FORBIDDEN_ALL"all"public static final StringCACHING_FORBIDDEN_CONTENT"content"public static final StringCACHING_FORBIDDEN_KEY"caching.forbidden"public static final StringCACHING_FORBIDDEN_NONE"none"public static final StringCHAR_ENCODING_FOR_CONVERSION"CharEncodingForConversion"public static final StringCRAWL_ID_KEY"storage.crawl.id"public static final StringFETCH_EVENT_CONTENTLANG"content-language"public static final StringFETCH_EVENT_CONTENTTYPE"content-type"public static final StringFETCH_EVENT_FETCHTIME"fetchTime"public static final StringFETCH_EVENT_SCORE"score"public static final StringFETCH_EVENT_TITLE"title"public static final StringFETCH_STATUS_KEY"_fst_"public static final StringFETCH_TIME_KEY"_ftk_"public static final StringFIXED_INTERVAL_KEY"fixedInterval"public static final StringGENERATE_TIME_KEY"_ngt_"public static final StringORIGINAL_CHAR_ENCODING"OriginalCharEncoding"public static final StringPROTO_STATUS_KEY"_pst_"public static final StringREPR_URL_KEY"_repr_"public static final StringROBOTS_METATAG"robots"public static final StringSCORE_KEY"nutch.crawl.score"public static final StringSEGMENT_NAME_KEY"nutch.segment.name"public static final StringSIGNATURE_KEY"nutch.content.digest"public static final StringSTAT_PROGRESS"progress"public static final StringVAL_RESULT"result"
-
org.apache.nutch.microformats.reltag.RelTagParser Modifier and Type Constant Field Value public static final StringREL_TAG"Rel-Tag"
-
org.apache.nutch.net.URLFilters Modifier and Type Constant Field Value public static final StringURLFILTER_ORDER"urlfilter.order" -
org.apache.nutch.net.URLNormalizers Modifier and Type Constant Field Value public static final StringSCOPE_CRAWLDB"crawldb"public static final StringSCOPE_DEFAULT"default"public static final StringSCOPE_FETCHER"fetcher"public static final StringSCOPE_GENERATE_HOST_COUNT"generate_host_count"public static final StringSCOPE_INDEXER"indexer"public static final StringSCOPE_INJECT"inject"public static final StringSCOPE_LINKDB"linkdb"public static final StringSCOPE_OUTLINK"outlink"public static final StringSCOPE_PARTITION"partition"
-
org.apache.nutch.net.protocols.ProtocolLogUtil Modifier and Type Constant Field Value public static final StringHTTP_LOG_SUPPRESSION"http.log.exceptions.suppress.stack" -
org.apache.nutch.net.protocols.Response Modifier and Type Constant Field Value public static final StringFETCH_TIME"nutch.fetch.time"public static final StringIP_ADDRESS"_ip_"public static final StringREQUEST"_request_"public static final StringRESPONSE_HEADERS"_response.headers_"public static final StringTRUNCATED_CONTENT"http.content.truncated"public static final StringTRUNCATED_CONTENT_REASON"http.content.truncated.reason"
-
org.apache.nutch.net.urlnormalizer.basic.BasicURLNormalizer Modifier and Type Constant Field Value public static final StringNORM_HOST_IDN"urlnormalizer.basic.host.idn"public static final StringNORM_HOST_TRIM_TRAILING_DOT"urlnormalizer.basic.host.trim-trailing-dot"
-
org.apache.nutch.parse.HtmlParseFilters Modifier and Type Constant Field Value public static final StringHTMLPARSEFILTER_ORDER"htmlparsefilter.order" -
org.apache.nutch.parse.ParseData Modifier and Type Constant Field Value public static final StringDIR_NAME"parse_data" -
org.apache.nutch.parse.ParserFactory Modifier and Type Constant Field Value public static final StringDEFAULT_PLUGIN"*" -
org.apache.nutch.parse.ParseSegment Modifier and Type Constant Field Value public static final StringSKIP_TRUNCATED"parser.skip.truncated" -
org.apache.nutch.parse.ParseStatus Modifier and Type Constant Field Value public static final byteFAILED2public static final shortFAILED_EXCEPTION200public static final shortFAILED_INVALID_FORMAT203public static final shortFAILED_MISSING_CONTENT205public static final shortFAILED_MISSING_PARTS204public static final shortFAILED_TRUNCATED202public static final byteNOTPARSED0public static final byteSUCCESS1public static final shortSUCCESS_REDIRECT100 -
org.apache.nutch.parse.ParseText Modifier and Type Constant Field Value public static final StringDIR_NAME"parse_text"
-
org.apache.nutch.parse.feed.FeedParser Modifier and Type Constant Field Value public static final StringCHARSET_UTF8"charset=UTF-8"public static final StringTEXT_PLAIN_CONTENT_TYPE"text/plain; charset=UTF-8"
-
org.apache.nutch.parsefilter.naivebayes.NaiveBayesParseFilter Modifier and Type Constant Field Value public static final StringDICTFILE_MODELFILTER"parsefilter.naivebayes.wordlist"public static final StringTRAINFILE_MODELFILTER"parsefilter.naivebayes.trainfile"
-
org.apache.nutch.protocol.Content Modifier and Type Constant Field Value public static final StringDIR_NAME"content" -
org.apache.nutch.protocol.ProtocolStatus Modifier and Type Constant Field Value public static final intACCESS_DENIED17public static final intBLOCKED23public static final intEXCEPTION16public static final intFAILED2public static final intGONE11public static final intMOVED12public static final intNOTFETCHING20public static final intNOTFOUND14public static final intNOTMODIFIED21public static final intPROTO_NOT_FOUND10public static final intREDIR_EXCEEDED19public static final intRETRY15public static final intROBOTS_DENIED18public static final intSUCCESS1public static final intTEMP_MOVED13public static final intWOULDBLOCK22
-
org.apache.nutch.protocol.http.api.HttpBase Modifier and Type Constant Field Value public static final intBUFFER_SIZE8192
-
org.apache.nutch.protocol.httpclient.HttpAuthenticationFactory Modifier and Type Constant Field Value public static final StringWWW_AUTHENTICATE"WWW-Authenticate"
-
org.apache.nutch.scoring.depth.DepthScoringFilter Modifier and Type Constant Field Value public static final intDEFAULT_MAX_DEPTH1000public static final StringDEPTH_KEY"_depth_"public static final StringMAX_DEPTH_KEY"_maxdepth_"
-
org.apache.nutch.scoring.metadata.MetadataScoringFilter Modifier and Type Constant Field Value public static final StringMETADATA_CONTENT"scoring.content.md"public static final StringMETADATA_DATUM"scoring.db.md"public static final StringMETADATA_PARSED"scoring.parse.md"
-
org.apache.nutch.scoring.webgraph.LinkDatum Modifier and Type Constant Field Value public static final byteINLINK1public static final byteOUTLINK2 -
org.apache.nutch.scoring.webgraph.LinkDumper Modifier and Type Constant Field Value public static final StringDUMP_DIR"linkdump" -
org.apache.nutch.scoring.webgraph.WebGraph Modifier and Type Constant Field Value public static final StringINLINK_DIR"inlinks"public static final StringLOCK_NAME".locked"public static final StringNODE_DIR"nodes"public static final StringOLD_OUTLINK_DIR"outlinks/old"public static final StringOUTLINK_DIR"outlinks/current" -
org.apache.nutch.scoring.webgraph.WebGraph.OutlinkDb Modifier and Type Constant Field Value public static final StringURL_FILTERING"webgraph.url.filters"public static final StringURL_NORMALIZING"webgraph.url.normalizers"
-
org.apache.nutch.service.resources.ConfigResource Modifier and Type Constant Field Value public static final StringDEFAULT"default"
-
org.apache.nutch.tools.CommonCrawlFormatWARC Modifier and Type Constant Field Value public static final StringMAX_WARC_FILE_SIZE"warc.file.size.max"public static final StringTEMPLATE"${prefix}-${timestamp17}-${serialno}" -
org.apache.nutch.tools.WARCUtils Modifier and Type Constant Field Value public static final StringCOLONSP": "public static final StringCONFORMS_TO"conformsTo"public static final StringCRLF"\r\n"public static final StringFORMAT"format"public static final StringHOSTNAME"hostname"public static final StringHTTP_HEADER_FROM"http-header-from"public static final StringHTTP_HEADER_USER_AGENT"http-header-user-agent"public static final StringIP"ip"public static final StringOPERATOR"operator"public static final StringROBOTS"robots"public static final StringSOFTWARE"software"protected static final StringX_HIDE_HEADER"X-Crawler-"
-
org.apache.nutch.tools.arc.ArcSegmentCreator Modifier and Type Constant Field Value public static final StringURL_VERSION"arc.url.version" -
org.apache.nutch.tools.arc.ArcSegmentCreator.ArcSegmentCreatorMapper Modifier and Type Constant Field Value public static final StringURL_VERSION"arc.url.version"
-
org.apache.nutch.urlfilter.automaton.AutomatonURLFilter Modifier and Type Constant Field Value public static final StringURLFILTER_AUTOMATON_FILE"urlfilter.automaton.file"public static final StringURLFILTER_AUTOMATON_RULES"urlfilter.automaton.rules"
-
org.apache.nutch.urlfilter.fast.FastURLFilter Modifier and Type Constant Field Value public static final StringURLFILTER_FAST_FILE"urlfilter.fast.file"public static final StringURLFILTER_FAST_MAX_LENGTH"urlfilter.fast.url.max.length"public static final StringURLFILTER_FAST_PATH_MAX_LENGTH"urlfilter.fast.url.path.max.length"public static final StringURLFILTER_FAST_QUERY_MAX_LENGTH"urlfilter.fast.url.query.max.length"
-
org.apache.nutch.urlfilter.ignoreexempt.ExemptionUrlFilter Modifier and Type Constant Field Value public static final StringDB_IGNORE_EXTERNAL_EXEMPTIONS_FILE"db.ignore.external.exemptions.file"
-
org.apache.nutch.urlfilter.regex.RegexURLFilter Modifier and Type Constant Field Value public static final StringURLFILTER_REGEX_FILE"urlfilter.regex.file"public static final StringURLFILTER_REGEX_RULES"urlfilter.regex.rules"
-
org.apache.nutch.util.EncodingDetector Modifier and Type Constant Field Value public static final StringMIN_CONFIDENCE_KEY"encodingdetector.charset.min.confidence"public static final intNO_THRESHOLD-1 -
org.apache.nutch.util.NutchConfiguration Modifier and Type Constant Field Value public static final StringUUID_KEY"nutch.conf.uuid" -
org.apache.nutch.util.SitemapProcessor Modifier and Type Constant Field Value public static final StringCURRENT_NAME"current"public static final StringLOCK_NAME".locked"public static final StringSITEMAP_ALWAYS_TRY_SITEMAPXML_ON_ROOT"sitemap.url.default.sitemap.xml"public static final StringSITEMAP_OVERWRITE_EXISTING"sitemap.url.overwrite.existing"public static final StringSITEMAP_REDIR_MAX"sitemap.redir.max"public static final StringSITEMAP_SIZE_MAX"sitemap.size.max"public static final StringSITEMAP_STRICT_PARSING"sitemap.strict.parsing"public static final StringSITEMAP_URL_FILTERING"sitemap.url.filter"public static final StringSITEMAP_URL_NORMALIZING"sitemap.url.normalize"
-
org.apache.nutch.util.domain.DomainSuffix Modifier and Type Constant Field Value public static final floatDEFAULT_BOOST1.0f