Constant Field Values

Contents

• org.apache.*

org.apache.*

org.apache.nutch.collection.CollectionManager

Modifier and Type	Constant Field	Value
public static final String	DEFAULT_FILE_NAME	"subcollections.xml"

org.apache.nutch.collection.Subcollection

Modifier and Type	Constant Field	Value
public static final String	TAG_BLACKLIST	"blacklist"
public static final String	TAG_COLLECTION	"subcollection"
public static final String	TAG_COLLECTIONS	"subcollections"
public static final String	TAG_ID	"id"
public static final String	TAG_KEY	"key"
public static final String	TAG_NAME	"name"
public static final String	TAG_WHITELIST	"whitelist"

org.apache.nutch.crawl.CrawlDatum

Modifier and Type	Constant Field	Value
public static final String	FETCH_DIR_NAME	"crawl_fetch"
public static final String	GENERATE_DIR_NAME	"crawl_generate"
public static final String	PARSE_DIR_NAME	"crawl_parse"
public static final byte	STATUS_DB_DUPLICATE	7
public static final byte	STATUS_DB_FETCHED	2
public static final byte	STATUS_DB_GONE	3
public static final byte	STATUS_DB_MAX	31
public static final byte	STATUS_DB_NOTMODIFIED	6
public static final byte	STATUS_DB_ORPHAN	8
public static final byte	STATUS_DB_REDIR_PERM	5
public static final byte	STATUS_DB_REDIR_TEMP	4
public static final byte	STATUS_DB_UNFETCHED	1
public static final byte	STATUS_FETCH_GONE	37
public static final byte	STATUS_FETCH_MAX	63
public static final byte	STATUS_FETCH_NOTMODIFIED	38
public static final byte	STATUS_FETCH_REDIR_PERM	36
public static final byte	STATUS_FETCH_REDIR_TEMP	35
public static final byte	STATUS_FETCH_RETRY	34
public static final byte	STATUS_FETCH_SUCCESS	33
public static final byte	STATUS_INJECTED	66
public static final byte	STATUS_LINKED	67
public static final byte	STATUS_PARSE_META	68
public static final byte	STATUS_SIGNATURE	65

org.apache.nutch.crawl.CrawlDb

Modifier and Type	Constant Field	Value
public static final String	CRAWLDB_ADDITIONS_ALLOWED	"db.update.additions.allowed"
public static final String	CRAWLDB_PURGE_404	"db.update.purge.404"
public static final String	CRAWLDB_PURGE_ORPHANS	"db.update.purge.orphans"
public static final String	CURRENT_NAME	"current"
public static final String	LOCK_NAME	".locked"

org.apache.nutch.crawl.CrawlDbFilter

Modifier and Type	Constant Field	Value
public static final String	URL_FILTERING	"crawldb.url.filters"
public static final String	URL_NORMALIZING	"crawldb.url.normalizers"
public static final String	URL_NORMALIZING_SCOPE	"crawldb.url.normalizers.scope"

org.apache.nutch.crawl.DeduplicationJob

Modifier and Type	Constant Field	Value
protected static final String	DEDUPLICATION_COMPARE_ORDER	"deduplication.compare.order"
protected static final String	DEDUPLICATION_GROUP_MODE	"deduplication.group.mode"

org.apache.nutch.crawl.FetchSchedule

Modifier and Type	Constant Field	Value
public static final int	SECONDS_PER_DAY	86400
public static final int	STATUS_MODIFIED	1
public static final int	STATUS_NOTMODIFIED	2
public static final int	STATUS_UNKNOWN	0

org.apache.nutch.crawl.Generator

Modifier and Type	Constant Field	Value
public static final String	GENERATE_UPDATE_CRAWLDB	"generate.update.crawldb"
public static final String	GENERATOR_COUNT_MODE	"generate.count.mode"
public static final String	GENERATOR_COUNT_VALUE_DOMAIN	"domain"
public static final String	GENERATOR_COUNT_VALUE_HOST	"host"
public static final String	GENERATOR_CUR_TIME	"generate.curTime"
public static final String	GENERATOR_DELAY	"crawl.gen.delay"
public static final String	GENERATOR_EXPR	"generate.expr"
public static final String	GENERATOR_FETCH_DELAY_EXPR	"generate.fetch.delay.expr"
public static final String	GENERATOR_FILTER	"generate.filter"
public static final String	GENERATOR_HOSTDB	"generate.hostdb"
public static final String	GENERATOR_MAX_COUNT	"generate.max.count"
public static final String	GENERATOR_MAX_COUNT_EXPR	"generate.max.count.expr"
public static final String	GENERATOR_MAX_NUM_SEGMENTS	"generate.max.num.segments"
public static final String	GENERATOR_MIN_INTERVAL	"generate.min.interval"
public static final String	GENERATOR_MIN_SCORE	"generate.min.score"
public static final String	GENERATOR_NORMALISE	"generate.normalise"
public static final String	GENERATOR_RESTRICT_STATUS	"generate.restrict.status"
public static final String	GENERATOR_TOP_N	"generate.topN"

org.apache.nutch.crawl.Injector

Modifier and Type	Constant Field	Value
public static final String	URL_FILTER_NORMALIZE_ALL	"crawldb.inject.filter.normalize.all"

org.apache.nutch.crawl.Injector.InjectMapper

Modifier and Type	Constant Field	Value
public static final String	EQUAL_CHARACTER	"="
public static final String	TAB_CHARACTER	"\t"
public static final String	URL_NORMALIZING_SCOPE	"crawldb.url.normalizers.scope"

org.apache.nutch.crawl.LinkDb

Modifier and Type	Constant Field	Value
public static final String	CURRENT_NAME	"current"
public static final String	IGNORE_EXTERNAL_LINKS	"linkdb.ignore.external.links"
public static final String	IGNORE_INTERNAL_LINKS	"linkdb.ignore.internal.links"
public static final String	LOCK_NAME	".locked"

org.apache.nutch.crawl.LinkDbFilter

Modifier and Type	Constant Field	Value
public static final String	URL_FILTERING	"linkdb.url.filters"
public static final String	URL_NORMALIZING	"linkdb.url.normalizer"
public static final String	URL_NORMALIZING_SCOPE	"linkdb.url.normalizer.scope"

org.apache.nutch.crawl.MimeAdaptiveFetchSchedule

Modifier and Type	Constant Field	Value
public static final String	SCHEDULE_DEC_RATE	"db.fetch.schedule.adaptive.dec_rate"
public static final String	SCHEDULE_INC_RATE	"db.fetch.schedule.adaptive.inc_rate"
public static final String	SCHEDULE_MIME_FILE	"db.fetch.schedule.mime.file"

org.apache.nutch.crawl.URLPartitioner

Modifier and Type	Constant Field	Value
public static final String	PARTITION_MODE_DOMAIN	"byDomain"
public static final String	PARTITION_MODE_HOST	"byHost"
public static final String	PARTITION_MODE_IP	"byIP"
public static final String	PARTITION_MODE_KEY	"partition.url.mode"

org.apache.nutch.fetcher.Fetcher

Modifier and Type	Constant Field	Value
public static final String	CONTENT_REDIR	"content"
public static final int	PERM_REFRESH_TIME	5
public static final String	PROTOCOL_REDIR	"protocol"

org.apache.nutch.fetcher.FetchItemQueues

Modifier and Type	Constant Field	Value
public static final String	DEFAULT_ID	"default"
public static final String	QUEUE_MODE_DOMAIN	"byDomain"
public static final String	QUEUE_MODE_HOST	"byHost"
public static final String	QUEUE_MODE_IP	"byIP"

org.apache.nutch.hostdb.ReadHostDb

Modifier and Type	Constant Field	Value
public static final String	HOSTDB_DUMP_HEADER	"hostdb.dump.field.header"
public static final String	HOSTDB_DUMP_HOMEPAGES	"hostdb.dump.homepages"
public static final String	HOSTDB_DUMP_HOSTNAMES	"hostdb.dump.hostnames"
public static final String	HOSTDB_FILTER_EXPRESSION	"hostdb.filter.expression"

org.apache.nutch.hostdb.UpdateHostDb

Modifier and Type	Constant Field	Value
public static final String	HOSTDB_CHECK_FAILED	"hostdb.check.failed"
public static final String	HOSTDB_CHECK_KNOWN	"hostdb.check.known"
public static final String	HOSTDB_CHECK_NEW	"hostdb.check.new"
public static final String	HOSTDB_CRAWLDATUM_PROCESSORS	"hostdb.crawldatum.processors"
public static final String	HOSTDB_FORCE_CHECK	"hostdb.force.check"
public static final String	HOSTDB_NUM_RESOLVER_THREADS	"hostdb.num.resolvers.threads"
public static final String	HOSTDB_NUMERIC_FIELDS	"hostdb.numeric.fields"
public static final String	HOSTDB_PERCENTILES	"hostdb.percentiles"
public static final String	HOSTDB_PURGE_FAILED_HOSTS_THRESHOLD	"hostdb.purge.failed.hosts.threshold"
public static final String	HOSTDB_RECHECK_INTERVAL	"hostdb.recheck.interval"
public static final String	HOSTDB_STRING_FIELDS	"hostdb.string.fields"
public static final String	HOSTDB_URL_FILTERING	"hostdb.url.filter"
public static final String	HOSTDB_URL_LIMIT	"hostdb.url.limit"
public static final String	HOSTDB_URL_NORMALIZING	"hostdb.url.normalize"
public static final String	LOCK_NAME	".locked"

org.apache.nutch.indexer.IndexerMapReduce

Modifier and Type	Constant Field	Value
public static final String	INDEXER_BINARY_AS_BASE64	"indexer.binary.base64"
public static final String	INDEXER_DELETE	"indexer.delete"
public static final String	INDEXER_DELETE_ROBOTS_NOINDEX	"indexer.delete.robots.noindex"
public static final String	INDEXER_DELETE_SKIPPED	"indexer.delete.skipped.by.indexingfilter"
public static final String	INDEXER_NO_COMMIT	"indexer.nocommit"
public static final String	INDEXER_PARAMS	"indexer.additional.params"
public static final String	INDEXER_SKIP_NOTMODIFIED	"indexer.skip.notmodified"
public static final String	URL_FILTERING	"indexer.url.filters"
public static final String	URL_NORMALIZING	"indexer.url.normalizers"

org.apache.nutch.indexer.IndexingFilters

Modifier and Type	Constant Field	Value
public static final String	INDEXINGFILTER_ORDER	"indexingfilter.order"

org.apache.nutch.indexer.NutchDocument

Modifier and Type	Constant Field	Value
public static final byte	VERSION	2

org.apache.nutch.indexer.NutchIndexAction

Modifier and Type	Constant Field	Value
public static final byte	ADD	0
public static final byte	DELETE	1
public static final byte	UPDATE	2

org.apache.nutch.indexer.feed.FeedIndexingFilter

Modifier and Type	Constant Field	Value
public static final String	dateFormatStr	"yyyyMMddHHmm"

org.apache.nutch.indexer.filter.MimeTypeIndexingFilter

Modifier and Type	Constant Field	Value
public static final String	MIMEFILTER_REGEX_FILE	"mimetype.filter.file"

org.apache.nutch.indexer.links.LinksIndexingFilter

Modifier and Type	Constant Field	Value
public static final String	LINKS_INLINKS_HOST	"index.links.inlinks.host.ignore"
public static final String	LINKS_ONLY_HOSTS	"index.links.hosts.only"
public static final String	LINKS_OUTLINKS_HOST	"index.links.outlinks.host.ignore"

org.apache.nutch.indexwriter.cloudsearch.CloudSearchConstants

Modifier and Type	Constant Field	Value
public static final String	BATCH_DUMP	"batch.dump"
public static final String	ENDPOINT	"endpoint"
public static final String	MAX_DOCS_BATCH	"batch.maxSize"
public static final String	REGION	"region"

org.apache.nutch.indexwriter.csv.CSVConstants

Modifier and Type	Constant Field	Value
public static final String	CSV_CHARSET	"charset"
public static final String	CSV_ESCAPECHARACTER	"escapechar"
public static final String	CSV_FIELD_SEPARATOR	"separator"
public static final String	CSV_FIELDS	"fields"
public static final String	CSV_MAXFIELDLENGTH	"maxfieldlength"
public static final String	CSV_MAXFIELDVALUES	"maxfieldvalues"
public static final String	CSV_OUTPATH	"outpath"
public static final String	CSV_QUOTECHARACTER	"quotechar"
public static final String	CSV_VALUESEPARATOR	"valuesep"
public static final String	CSV_WITHHEADER	"header"

org.apache.nutch.indexwriter.dummy.DummyConstants

Modifier and Type	Constant Field	Value
public static final String	DELETE	"delete"
public static final String	PATH	"path"

org.apache.nutch.indexwriter.elastic.ElasticConstants

Modifier and Type	Constant Field	Value
public static final String	BULK_CLOSE_TIMEOUT	"bulk.close.timeout"
public static final String	EXPONENTIAL_BACKOFF_MILLIS	"exponential.backoff.millis"
public static final String	EXPONENTIAL_BACKOFF_RETRIES	"exponential.backoff.retries"
public static final String	HOSTS	"host"
public static final String	INDEX	"index"
public static final String	MAX_BULK_DOCS	"max.bulk.docs"
public static final String	MAX_BULK_LENGTH	"max.bulk.size"
public static final String	OPTIONS	"options"
public static final String	PASSWORD	"password"
public static final String	PORT	"port"
public static final String	SCHEME	"scheme"
public static final String	USE_AUTH	"auth"
public static final String	USER	"username"

org.apache.nutch.indexwriter.kafka.KafkaConstants

Modifier and Type	Constant Field	Value
public static final String	HOST	"host"
public static final String	KEY_SERIALIZER	"key.serializer"
public static final String	MAX_DOC_COUNT	"max.doc.count"
public static final String	PORT	"port"
public static final String	TOPIC	"topic"
public static final String	VALUE_SERIALIZER	"value.serializer"

org.apache.nutch.indexwriter.opensearch1x.OpenSearch1xConstants

Modifier and Type	Constant Field	Value
public static final String	BULK_CLOSE_TIMEOUT	"bulk.close.timeout"
public static final String	EXPONENTIAL_BACKOFF_MILLIS	"exponential.backoff.millis"
public static final String	EXPONENTIAL_BACKOFF_RETRIES	"exponential.backoff.retries"
public static final String	HOSTS	"host"
public static final String	INDEX	"index"
public static final String	KEY_STORE_PASSWORD	"key.store.password"
public static final String	KEY_STORE_PATH	"key.store.path"
public static final String	KEY_STORE_TYPE	"key.store.type"
public static final String	MAX_BULK_DOCS	"max.bulk.docs"
public static final String	MAX_BULK_LENGTH	"max.bulk.size"
public static final String	OPTIONS	"options"
public static final String	PASSWORD	"password"
public static final String	PORT	"port"
public static final String	SCHEME	"scheme"
public static final String	TRUST_STORE_PASSWORD	"trust.store.password"
public static final String	TRUST_STORE_PATH	"trust.store.path"
public static final String	TRUST_STORE_TYPE	"trust.store.type"
public static final String	USER	"username"

org.apache.nutch.indexwriter.solr.SolrConstants

Modifier and Type	Constant Field	Value
public static final String	AUTH_HEADER_NAME	"auth.header.name"
public static final String	AUTH_HEADER_VALUE	"auth.header.value"
public static final String	COLLECTION	"collection"
public static final String	COMMIT_SIZE	"commitSize"
public static final String	PASSWORD	"password"
public static final String	SERVER_TYPE	"type"
public static final String	SERVER_URLS	"url"
public static final String	USE_AUTH	"auth"
public static final String	USERNAME	"username"
public static final String	WEIGHT_FIELD	"weight.field"

org.apache.nutch.metadata.CreativeCommons

Modifier and Type	Constant Field	Value
public static final String	LICENSE_LOCATION	"License-Location"
public static final String	LICENSE_URL	"License-Url"
public static final String	WORK_TYPE	"Work-Type"

org.apache.nutch.metadata.DublinCore

Modifier and Type	Constant Field	Value
public static final String	CONTRIBUTOR	"contributor"
public static final String	COVERAGE	"coverage"
public static final String	CREATOR	"creator"
public static final String	DATE	"date"
public static final String	DESCRIPTION	"description"
public static final String	FORMAT	"format"
public static final String	IDENTIFIER	"identifier"
public static final String	LANGUAGE	"language"
public static final String	MODIFIED	"modified"
public static final String	PUBLISHER	"publisher"
public static final String	RELATION	"relation"
public static final String	RIGHTS	"rights"
public static final String	SOURCE	"source"
public static final String	SUBJECT	"subject"
public static final String	TITLE	"title"
public static final String	TYPE	"type"

org.apache.nutch.metadata.Feed

Modifier and Type	Constant Field	Value
public static final String	FEED	"feed"
public static final String	FEED_AUTHOR	"author"
public static final String	FEED_PUBLISHED	"published"
public static final String	FEED_TAGS	"tag"
public static final String	FEED_UPDATED	"updated"

org.apache.nutch.metadata.HttpHeaders

Modifier and Type	Constant Field	Value
public static final String	CLIENT_TRANSFER_ENCODING	"Client-Transfer-Encoding"
public static final String	CONTENT_DISPOSITION	"Content-Disposition"
public static final String	CONTENT_ENCODING	"Content-Encoding"
public static final String	CONTENT_LANGUAGE	"Content-Language"
public static final String	CONTENT_LENGTH	"Content-Length"
public static final String	CONTENT_LOCATION	"Content-Location"
public static final String	CONTENT_MD5	"Content-MD5"
public static final String	CONTENT_TYPE	"Content-Type"
public static final String	IF_MODIFIED_SINCE	"If-Modified-Since"
public static final String	LAST_MODIFIED	"Last-Modified"
public static final String	LOCATION	"Location"
public static final String	TRANSFER_ENCODING	"Transfer-Encoding"
public static final String	USER_AGENT	"User-Agent"

org.apache.nutch.metadata.Nutch

Modifier and Type	Constant Field	Value
public static final String	ARG_CRAWLDB	"crawldb"
public static final String	ARG_HOSTDB	"hostdb"
public static final String	ARG_LINKDB	"linkdb"
public static final String	ARG_SEEDDIR	"url_dir"
public static final String	ARG_SEEDNAME	"seedName"
public static final String	ARG_SEGMENTDIR	"segment_dir"
public static final String	ARG_SEGMENTS	"segment"
public static final String	CACHING_FORBIDDEN_ALL	"all"
public static final String	CACHING_FORBIDDEN_CONTENT	"content"
public static final String	CACHING_FORBIDDEN_KEY	"caching.forbidden"
public static final String	CACHING_FORBIDDEN_NONE	"none"
public static final String	CHAR_ENCODING_FOR_CONVERSION	"CharEncodingForConversion"
public static final String	CRAWL_ID_KEY	"storage.crawl.id"
public static final String	FETCH_EVENT_CONTENTLANG	"content-language"
public static final String	FETCH_EVENT_CONTENTTYPE	"content-type"
public static final String	FETCH_EVENT_FETCHTIME	"fetchTime"
public static final String	FETCH_EVENT_SCORE	"score"
public static final String	FETCH_EVENT_TITLE	"title"
public static final String	FETCH_STATUS_KEY	"_fst_"
public static final String	FETCH_TIME_KEY	"_ftk_"
public static final String	FIXED_INTERVAL_KEY	"fixedInterval"
public static final String	GENERATE_TIME_KEY	"_ngt_"
public static final String	ORIGINAL_CHAR_ENCODING	"OriginalCharEncoding"
public static final String	PROTO_STATUS_KEY	"_pst_"
public static final String	REPR_URL_KEY	"_repr_"
public static final String	ROBOTS_METATAG	"robots"
public static final String	SCORE_KEY	"nutch.crawl.score"
public static final String	SEGMENT_NAME_KEY	"nutch.segment.name"
public static final String	SIGNATURE_KEY	"nutch.content.digest"
public static final String	STAT_PROGRESS	"progress"
public static final String	VAL_RESULT	"result"

org.apache.nutch.microformats.reltag.RelTagParser

Modifier and Type	Constant Field	Value
public static final String	REL_TAG	"Rel-Tag"

org.apache.nutch.net.URLFilters

Modifier and Type	Constant Field	Value
public static final String	URLFILTER_ORDER	"urlfilter.order"

org.apache.nutch.net.URLNormalizers

Modifier and Type	Constant Field	Value
public static final String	SCOPE_CRAWLDB	"crawldb"
public static final String	SCOPE_DEFAULT	"default"
public static final String	SCOPE_FETCHER	"fetcher"
public static final String	SCOPE_GENERATE_HOST_COUNT	"generate_host_count"
public static final String	SCOPE_INDEXER	"indexer"
public static final String	SCOPE_INJECT	"inject"
public static final String	SCOPE_LINKDB	"linkdb"
public static final String	SCOPE_OUTLINK	"outlink"
public static final String	SCOPE_PARTITION	"partition"

org.apache.nutch.net.protocols.ProtocolLogUtil

Modifier and Type	Constant Field	Value
public static final String	HTTP_LOG_SUPPRESSION	"http.log.exceptions.suppress.stack"

org.apache.nutch.net.protocols.Response

Modifier and Type	Constant Field	Value
public static final String	CIPHER_SUITES	"_cipher_suites_"
public static final String	FETCH_TIME	"nutch.fetch.time"
public static final String	IP_ADDRESS	"_ip_"
public static final String	PROTOCOL_VERSIONS	"_protocol_versions_"
public static final String	REQUEST	"_request_"
public static final String	RESPONSE_HEADERS	"_response.headers_"
public static final String	TRUNCATED_CONTENT	"http.content.truncated"
public static final String	TRUNCATED_CONTENT_REASON	"http.content.truncated.reason"

org.apache.nutch.net.urlnormalizer.basic.BasicURLNormalizer

Modifier and Type	Constant Field	Value
public static final String	NORM_HOST_IDN	"urlnormalizer.basic.host.idn"
public static final String	NORM_HOST_TRIM_TRAILING_DOT	"urlnormalizer.basic.host.trim-trailing-dot"

org.apache.nutch.parse.HtmlParseFilters

Modifier and Type	Constant Field	Value
public static final String	HTMLPARSEFILTER_ORDER	"htmlparsefilter.order"

org.apache.nutch.parse.ParseData

Modifier and Type	Constant Field	Value
public static final String	DIR_NAME	"parse_data"

org.apache.nutch.parse.ParserFactory

Modifier and Type	Constant Field	Value
public static final String	DEFAULT_PLUGIN	"*"

org.apache.nutch.parse.ParseSegment

Modifier and Type	Constant Field	Value
public static final String	SKIP_TRUNCATED	"parser.skip.truncated"

org.apache.nutch.parse.ParseStatus

Modifier and Type	Constant Field	Value
public static final byte	FAILED	2
public static final short	FAILED_EXCEPTION	200
public static final short	FAILED_INVALID_FORMAT	203
public static final short	FAILED_MISSING_CONTENT	205
public static final short	FAILED_MISSING_PARTS	204
public static final short	FAILED_TRUNCATED	202
public static final byte	NOTPARSED	0
public static final byte	SUCCESS	1
public static final short	SUCCESS_REDIRECT	100

org.apache.nutch.parse.ParseText

Modifier and Type	Constant Field	Value
public static final String	DIR_NAME	"parse_text"

org.apache.nutch.parse.feed.FeedParser

Modifier and Type	Constant Field	Value
public static final String	CHARSET_UTF8	"charset=UTF-8"
public static final String	TEXT_PLAIN_CONTENT_TYPE	"text/plain; charset=UTF-8"

org.apache.nutch.parsefilter.naivebayes.NaiveBayesParseFilter

Modifier and Type	Constant Field	Value
public static final String	DICTFILE_MODELFILTER	"parsefilter.naivebayes.wordlist"
public static final String	TRAINFILE_MODELFILTER	"parsefilter.naivebayes.trainfile"

org.apache.nutch.protocol.Content

Modifier and Type	Constant Field	Value
public static final String	DIR_NAME	"content"

org.apache.nutch.protocol.ProtocolStatus

Modifier and Type	Constant Field	Value
public static final int	ACCESS_DENIED	17
public static final int	BLOCKED	23
public static final int	EXCEPTION	16
public static final int	FAILED	2
public static final int	GONE	11
public static final int	MOVED	12
public static final int	NOTFETCHING	20
public static final int	NOTFOUND	14
public static final int	NOTMODIFIED	21
public static final int	PROTO_NOT_FOUND	10
public static final int	REDIR_EXCEEDED	19
public static final int	RETRY	15
public static final int	ROBOTS_DENIED	18
public static final int	SUCCESS	1
public static final int	TEMP_MOVED	13
public static final int	WOULDBLOCK	22

org.apache.nutch.protocol.http.api.HttpBase

Modifier and Type	Constant Field	Value
public static final int	BUFFER_SIZE	8192

org.apache.nutch.protocol.httpclient.HttpAuthenticationFactory

Modifier and Type	Constant Field	Value
public static final String	WWW_AUTHENTICATE	"WWW-Authenticate"

org.apache.nutch.scoring.depth.DepthScoringFilter

Modifier and Type	Constant Field	Value
public static final int	DEFAULT_MAX_DEPTH	1000
public static final String	DEPTH_KEY	"_depth_"
public static final String	MAX_DEPTH_KEY	"_maxdepth_"

org.apache.nutch.scoring.metadata.MetadataScoringFilter

Modifier and Type	Constant Field	Value
public static final String	METADATA_CONTENT	"scoring.content.md"
public static final String	METADATA_DATUM	"scoring.db.md"
public static final String	METADATA_PARSED	"scoring.parse.md"

org.apache.nutch.scoring.webgraph.LinkDatum

Modifier and Type	Constant Field	Value
public static final byte	INLINK	1
public static final byte	OUTLINK	2

org.apache.nutch.scoring.webgraph.LinkDumper

Modifier and Type	Constant Field	Value
public static final String	DUMP_DIR	"linkdump"

org.apache.nutch.scoring.webgraph.WebGraph

Modifier and Type	Constant Field	Value
public static final String	INLINK_DIR	"inlinks"
public static final String	LOCK_NAME	".locked"
public static final String	NODE_DIR	"nodes"
public static final String	OLD_OUTLINK_DIR	"outlinks/old"
public static final String	OUTLINK_DIR	"outlinks/current"

org.apache.nutch.scoring.webgraph.WebGraph.OutlinkDb

Modifier and Type	Constant Field	Value
public static final String	URL_FILTERING	"webgraph.url.filters"
public static final String	URL_NORMALIZING	"webgraph.url.normalizers"

org.apache.nutch.service.resources.ConfigResource

Modifier and Type	Constant Field	Value
public static final String	DEFAULT	"default"

org.apache.nutch.tools.CommonCrawlFormatWARC

Modifier and Type	Constant Field	Value
public static final String	MAX_WARC_FILE_SIZE	"warc.file.size.max"
public static final String	TEMPLATE	"${prefix}-${timestamp17}-${serialno}"

org.apache.nutch.tools.WARCUtils

Modifier and Type	Constant Field	Value
public static final String	COLONSP	": "
public static final String	CONFORMS_TO	"conformsTo"
public static final String	CRLF	"\r\n"
public static final String	FORMAT	"format"
public static final String	HOSTNAME	"hostname"
public static final String	HTTP_HEADER_FROM	"http-header-from"
public static final String	HTTP_HEADER_USER_AGENT	"http-header-user-agent"
public static final String	IP	"ip"
public static final String	OPERATOR	"operator"
public static final String	ROBOTS	"robots"
public static final String	SOFTWARE	"software"
protected static final String	X_HIDE_HEADER	"X-Crawler-"

org.apache.nutch.tools.arc.ArcSegmentCreator

Modifier and Type	Constant Field	Value
public static final String	URL_VERSION	"arc.url.version"

org.apache.nutch.tools.arc.ArcSegmentCreator.ArcSegmentCreatorMapper

Modifier and Type	Constant Field	Value
public static final String	URL_VERSION	"arc.url.version"

org.apache.nutch.urlfilter.automaton.AutomatonURLFilter

Modifier and Type	Constant Field	Value
public static final String	URLFILTER_AUTOMATON_FILE	"urlfilter.automaton.file"
public static final String	URLFILTER_AUTOMATON_RULES	"urlfilter.automaton.rules"

org.apache.nutch.urlfilter.fast.FastURLFilter

Modifier and Type	Constant Field	Value
public static final String	URLFILTER_FAST_FILE	"urlfilter.fast.file"
public static final String	URLFILTER_FAST_MAX_LENGTH	"urlfilter.fast.url.max.length"
public static final String	URLFILTER_FAST_PATH_MAX_LENGTH	"urlfilter.fast.url.path.max.length"
public static final String	URLFILTER_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 String	DB_IGNORE_EXTERNAL_EXEMPTIONS_FILE	"db.ignore.external.exemptions.file"

org.apache.nutch.urlfilter.regex.RegexURLFilter

Modifier and Type	Constant Field	Value
public static final String	URLFILTER_REGEX_FILE	"urlfilter.regex.file"
public static final String	URLFILTER_REGEX_RULES	"urlfilter.regex.rules"

org.apache.nutch.util.EncodingDetector

Modifier and Type	Constant Field	Value
public static final String	MIN_CONFIDENCE_KEY	"encodingdetector.charset.min.confidence"
public static final int	NO_THRESHOLD	-1

org.apache.nutch.util.NutchConfiguration

Modifier and Type	Constant Field	Value
public static final String	UUID_KEY	"nutch.conf.uuid"

org.apache.nutch.util.SitemapProcessor

Modifier and Type	Constant Field	Value
public static final String	CURRENT_NAME	"current"
public static final String	LOCK_NAME	".locked"
public static final String	SITEMAP_ALWAYS_TRY_SITEMAPXML_ON_ROOT	"sitemap.url.default.sitemap.xml"
public static final String	SITEMAP_OVERWRITE_EXISTING	"sitemap.url.overwrite.existing"
public static final String	SITEMAP_REDIR_MAX	"sitemap.redir.max"
public static final String	SITEMAP_SIZE_MAX	"sitemap.size.max"
public static final String	SITEMAP_STRICT_PARSING	"sitemap.strict.parsing"
public static final String	SITEMAP_URL_FILTERING	"sitemap.url.filter"
public static final String	SITEMAP_URL_NORMALIZING	"sitemap.url.normalize"