Constant Field Values

Contents

• org.apache.*

org.apache.*

org.apache.nutch.api.AdminResource

public static final String	DESCR	"Service admin actions"
public static final String	PATH	"admin"

org.apache.nutch.api.ConfResource

public static final String	DEFAULT_CONF	"default"
public static final String	DESCR	"Configuration manager"
public static final String	PATH	"confs"

org.apache.nutch.api.DbResource

public static final String	DESCR	"DB data streaming"
public static final String	PATH	"db"

org.apache.nutch.api.JobResource

public static final String	DESCR	"Job manager"
public static final String	PATH	"jobs"

org.apache.nutch.api.Params

public static final String	ARGS	"args"
public static final String	CMD	"cmd"
public static final String	CONF_ID	"conf"
public static final String	CRAWL_ID	"crawl"
public static final String	FORCE	"force"
public static final String	JOB_CMD_ABORT	"abort"
public static final String	JOB_CMD_GET	"get"
public static final String	JOB_CMD_STOP	"stop"
public static final String	JOB_ID	"job"
public static final String	JOB_TYPE	"type"
public static final String	PROP_NAME	"prop"
public static final String	PROP_VALUE	"value"
public static final String	PROPS	"props"

org.apache.nutch.collection.CollectionManager

public static final String

DEFAULT_FILE_NAME

"subcollections.xml"

org.apache.nutch.collection.Subcollection

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_NAME	"name"
public static final String	TAG_WHITELIST	"whitelist"

org.apache.nutch.crawl.CrawlStatus

public static final byte	STATUS_FETCHED	2
public static final byte	STATUS_GONE	3
public static final byte	STATUS_NOTMODIFIED	38
public static final byte	STATUS_REDIR_PERM	5
public static final byte	STATUS_REDIR_TEMP	4
public static final byte	STATUS_RETRY	34
public static final byte	STATUS_UNFETCHED	1

org.apache.nutch.crawl.DbUpdateReducer

public static final String

CRAWLDB_ADDITIONS_ALLOWED

"db.update.additions.allowed"

org.apache.nutch.crawl.FetchSchedule

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.GeneratorJob

public static final String	BATCH_ID	"generate.batch.id"
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_COUNT_VALUE_IP	"ip"
public static final String	GENERATOR_CUR_TIME	"generate.curTime"
public static final String	GENERATOR_DELAY	"crawl.gen.delay"
public static final String	GENERATOR_FILTER	"generate.filter"
public static final String	GENERATOR_MAX_COUNT	"generate.max.count"
public static final String	GENERATOR_MIN_SCORE	"generate.min.score"
public static final String	GENERATOR_NORMALISE	"generate.normalise"
public static final String	GENERATOR_RANDOM_SEED	"generate.partition.seed"
public static final String	GENERATOR_TOP_N	"generate.topN"

org.apache.nutch.crawl.URLPartitioner

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"
public static final String	PARTITION_URL_SEED	"partition.url.seed"

org.apache.nutch.fetcher.FetcherJob

public static final String	PARSE_KEY	"fetcher.parse"
public static final int	PERM_REFRESH_TIME	5
public static final String	PROTOCOL_REDIR	"protocol"
public static final String	RESUME_KEY	"fetcher.job.resume"
public static final String	THREADS_KEY	"fetcher.threads.fetch"

org.apache.nutch.host.HostDb

public static final int	DEFAULT_HOSTDB_CONCURRENCY_LEVEL	8
public static final int	DEFAULT_LRU_SIZE	100
public static final String	HOSTDB_CONCURRENCY_LEVEL	"hostdb.concurrency.level"
public static final String	HOSTDB_LRU_SIZE	"hostdb.lru.size"

org.apache.nutch.indexer.IndexingFilters

public static final String

INDEXINGFILTER_ORDER

"indexingfilter.order"

org.apache.nutch.indexer.NutchDocument

public static final byte

VERSION

1

org.apache.nutch.indexer.elastic.ElasticConstants

public static final String	CLUSTER	"elastic.cluster"
public static final String	ELASTIC_PREFIX	"elastic."
public static final String	INDEX	"elastic.index"
public static final String	MAX_BULK_DOCS	"elastic.max.bulk.docs"
public static final String	MAX_BULK_LENGTH	"elastic.max.bulk.size"

org.apache.nutch.indexer.feed.FeedIndexingFilter

public static final String

dateFormatStr

"yyyyMMddHHmm"

org.apache.nutch.indexer.solr.SolrConstants

public static final String	BOOST_FIELD	"boost"
public static final String	COMMIT_INDEX	"solr.commit.index"
public static final String	COMMIT_SIZE	"solr.commit.size"
public static final String	DIGEST_FIELD	"digest"
public static final String	ID_FIELD	"id"
public static final String	MAPPING_FILE	"solr.mapping.file"
public static final String	PASSWORD	"solr.auth.password"
public static final String	SERVER_URL	"solr.server.url"
public static final String	SOLR_PREFIX	"solr."
public static final String	TIMESTAMP_FIELD	"tstamp"
public static final String	URL_FIELD	"url"
public static final String	USE_AUTH	"solr.auth"
public static final String	USERNAME	"solr.auth.username"

org.apache.nutch.indexer.subcollection.SubcollectionIndexingFilter

public static final String

FIELD_NAME

"subcollection"

org.apache.nutch.metadata.CreativeCommons

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

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

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

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	LAST_MODIFIED	"Last-Modified"
public static final String	LOCATION	"Location"

org.apache.nutch.metadata.Nutch

public static final String	ALL_BATCH_ID_STR	"-all"
public static final String	ARG_BATCH	"batch"
public static final String	ARG_CLASS	"class"
public static final String	ARG_CRAWL	"crawl"
public static final String	ARG_CURTIME	"curTime"
public static final String	ARG_DEPTH	"depth"
public static final String	ARG_FILTER	"filter"
public static final String	ARG_FORCE	"force"
public static final String	ARG_NORMALIZE	"normalize"
public static final String	ARG_NUMTASKS	"numTasks"
public static final String	ARG_RESUME	"resume"
public static final String	ARG_SEEDDIR	"seedDir"
public static final String	ARG_SEEDLIST	"seed"
public static final String	ARG_SOLR	"solr"
public static final String	ARG_SORT	"sort"
public static final String	ARG_THREADS	"threads"
public static final String	ARG_TOPN	"topN"
public static final String	BATCH_NAME_KEY	"nutch.batch.name"
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_STATUS_KEY	"_fst_"
public static final String	FETCH_TIME_KEY	"_ftk_"
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	SCORE_KEY	"nutch.crawl.score"
public static final String	SIGNATURE_KEY	"nutch.content.digest"
public static final String	STAT_COUNTERS	"counters"
public static final String	STAT_JOBS	"jobs"
public static final String	STAT_MESSAGE	"msg"
public static final String	STAT_PHASE	"phase"
public static final String	STAT_PROGRESS	"progress"

org.apache.nutch.microformats.reltag.RelTagParser

public static final String

REL_TAG

"Rel-Tag"

org.apache.nutch.net.URLFilters

public static final String

URLFILTER_ORDER

"urlfilter.order"

org.apache.nutch.net.URLNormalizers

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_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.parse.ParseFilters

public static final String

HTMLPARSEFILTER_ORDER

"htmlparsefilter.order"

org.apache.nutch.parse.ParserFactory

public static final String

DEFAULT_PLUGIN

"*"

org.apache.nutch.parse.ParserJob

public static final String

SKIP_TRUNCATED

"parser.skip.truncated"

org.apache.nutch.parse.ParseStatusCodes

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_OK	0
public static final short	SUCCESS_REDIRECT	100

org.apache.nutch.parse.feed.FeedParser

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.protocol.Content

public static final String

DIR_NAME

"content"

org.apache.nutch.protocol.Protocol

public static final String	CHECK_BLOCKING	"protocol.plugin.check.blocking"
public static final String	CHECK_ROBOTS	"protocol.plugin.check.robots"

org.apache.nutch.protocol.ProtocolStatusCodes

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.ftp.Client

protected static final int	TERMINAL_TYPE	24
protected static final int	TERMINAL_TYPE_IS	0
protected static final int	TERMINAL_TYPE_SEND	1

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

public static final int

BUFFER_SIZE

8192

org.apache.nutch.protocol.httpclient.HttpAuthenticationFactory

public static final String

WWW_AUTHENTICATE

"WWW-Authenticate"

org.apache.nutch.tools.proxy.DelayHandler

public static final long

DEFAULT_DELAY

2000L

org.apache.nutch.urlfilter.automaton.AutomatonURLFilter

public static final String	URLFILTER_AUTOMATON_FILE	"urlfilter.automaton.file"
public static final String	URLFILTER_AUTOMATON_RULES	"urlfilter.automaton.rules"

org.apache.nutch.urlfilter.regex.RegexURLFilter

public static final String	URLFILTER_REGEX_FILE	"urlfilter.regex.file"
public static final String	URLFILTER_REGEX_RULES	"urlfilter.regex.rules"

org.apache.nutch.util.Bytes

public static final int	ESTIMATED_HEAP_TAX	16
public static final int	SIZEOF_BOOLEAN	1
public static final int	SIZEOF_BYTE	1
public static final int	SIZEOF_CHAR	2
public static final int	SIZEOF_DOUBLE	8
public static final int	SIZEOF_FLOAT	4
public static final int	SIZEOF_INT	4
public static final int	SIZEOF_LONG	8
public static final int	SIZEOF_SHORT	2
public static final String	UTF8_ENCODING	"UTF-8"

org.apache.nutch.util.EncodingDetector

public static final String	MIN_CONFIDENCE_KEY	"encodingdetector.charset.min.confidence"
public static final int	NO_THRESHOLD	-1

org.apache.nutch.util.NutchConfiguration

public static final String

UUID_KEY

"nutch.conf.uuid"

org.apache.nutch.util.domain.DomainSuffix

public static final float

DEFAULT_BOOST

1.0f