Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
NUTCH_SERVER |
"NUTCH_SERVER" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
DEFAULT |
"default" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
DEFAULT_FILE_NAME |
"subcollections.xml" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
TAG_BLACKLIST |
"blacklist" |
public static final java.lang.String |
TAG_COLLECTION |
"subcollection" |
public static final java.lang.String |
TAG_COLLECTIONS |
"subcollections" |
public static final java.lang.String |
TAG_ID |
"id" |
public static final java.lang.String |
TAG_NAME |
"name" |
public static final java.lang.String |
TAG_WHITELIST |
"whitelist" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
ATTR_CLASS |
"class" |
public static final java.lang.String |
ATTR_NAME |
"name" |
public static final java.lang.String |
ATTR_URL_PATTERN |
"url-pattern" |
public static final java.lang.String |
JSOUP_DOC_DEFAULT_FILE |
"jsoup-extractor.xml" |
public static final java.lang.String |
JSOUP_DOC_PROPERTY_FILE |
"jsoup.extractor.property.file" |
public static final java.lang.String |
TAG_ATTRIBUTE |
"attribute" |
public static final java.lang.String |
TAG_CSS_SELECTOR |
"css-selector" |
public static final java.lang.String |
TAG_DEFAULT_VALUE |
"default-value" |
public static final java.lang.String |
TAG_DOCUMENT |
"document" |
public static final java.lang.String |
TAG_FIELD |
"field" |
public static final java.lang.String |
TAG_FIELD_LIST |
"fields" |
public static final java.lang.String |
TAG_NORMALIZER |
"normalizer" |
public static final java.lang.String |
TAG_NORMALIZER_LIST |
"normalizers" |
public static final java.lang.String |
TAG_TYPE |
"type" |
public static final java.lang.String |
TAG_TYPE_LIST |
"types" |
Modifier and Type | Constant Field | Value |
---|---|---|
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 |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
CRAWLDB_ADDITIONS_ALLOWED |
"db.update.additions.allowed" |
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 |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
BATCH_ID |
"generate.batch.id" |
public static final java.lang.String |
GENERATE_COUNT |
"generate.count" |
public static final java.lang.String |
GENERATE_UPDATE_CRAWLDB |
"generate.update.crawldb" |
public static final java.lang.String |
GENERATOR_COUNT_MODE |
"generate.count.mode" |
public static final java.lang.String |
GENERATOR_COUNT_VALUE_DOMAIN |
"domain" |
public static final java.lang.String |
GENERATOR_COUNT_VALUE_HOST |
"host" |
public static final java.lang.String |
GENERATOR_COUNT_VALUE_IP |
"ip" |
public static final java.lang.String |
GENERATOR_CUR_TIME |
"generate.curTime" |
public static final java.lang.String |
GENERATOR_DELAY |
"crawl.gen.delay" |
public static final java.lang.String |
GENERATOR_FILTER |
"generate.filter" |
public static final java.lang.String |
GENERATOR_MAX_COUNT |
"generate.max.count" |
public static final java.lang.String |
GENERATOR_MIN_SCORE |
"generate.min.score" |
public static final java.lang.String |
GENERATOR_NORMALISE |
"generate.normalise" |
public static final java.lang.String |
GENERATOR_RANDOM_SEED |
"generate.partition.seed" |
public static final java.lang.String |
GENERATOR_SITEMAP |
"generate.sitemap" |
public static final java.lang.String |
GENERATOR_TOP_N |
"generate.topN" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
PARTITION_MODE_DOMAIN |
"byDomain" |
public static final java.lang.String |
PARTITION_MODE_HOST |
"byHost" |
public static final java.lang.String |
PARTITION_MODE_IP |
"byIP" |
public static final java.lang.String |
PARTITION_MODE_KEY |
"partition.url.mode" |
public static final java.lang.String |
PARTITION_URL_SEED |
"partition.url.seed" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
PARSE_KEY |
"fetcher.parse" |
public static final int |
PERM_REFRESH_TIME |
5 |
public static final java.lang.String |
PROTOCOL_REDIR |
"protocol" |
public static final java.lang.String |
RESUME_KEY |
"fetcher.job.resume" |
public static final java.lang.String |
SITEMAP |
"fetcher.job.sitemap" |
public static final java.lang.String |
SITEMAP_DETECT |
"fetcher.job.sitemap.detect" |
public static final java.lang.String |
THREADS_KEY |
"fetcher.threads.fetch" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final int |
DEFAULT_HOSTDB_CONCURRENCY_LEVEL |
8 |
public static final int |
DEFAULT_LRU_SIZE |
100 |
public static final java.lang.String |
HOSTDB_CONCURRENCY_LEVEL |
"hostdb.concurrency.level" |
public static final java.lang.String |
HOSTDB_LRU_SIZE |
"hostdb.lru.size" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
ARG_COMMIT |
"commit" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
IndexCleaningFilter_ORDER |
"IndexCleaningFilterhbase.order" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
INDEXINGFILTER_ORDER |
"indexingfilter.order" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final byte |
VERSION |
1 |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
BOOST_FIELD |
"boost" |
public static final java.lang.String |
COMMIT_INDEX |
"solr.commit.index" |
public static final java.lang.String |
COMMIT_SIZE |
"solr.commit.size" |
public static final java.lang.String |
DIGEST_FIELD |
"digest" |
public static final java.lang.String |
ID_FIELD |
"id" |
public static final java.lang.String |
MAPPING_FILE |
"solr.mapping.file" |
public static final java.lang.String |
PASSWORD |
"solr.auth.password" |
public static final java.lang.String |
SERVER_URL |
"solr.server.url" |
public static final java.lang.String |
SOLR_PREFIX |
"solr." |
public static final java.lang.String |
TIMESTAMP_FIELD |
"tstamp" |
public static final java.lang.String |
URL_FIELD |
"url" |
public static final java.lang.String |
USE_AUTH |
"solr.auth" |
public static final java.lang.String |
USERNAME |
"solr.auth.username" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
FIELD_NAME |
"subcollection" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
CLUSTER |
"elastic.cluster" |
public static final java.lang.String |
ELASTIC_PREFIX |
"elastic." |
public static final java.lang.String |
HOST |
"elastic.host" |
public static final java.lang.String |
INDEX |
"elastic.index" |
public static final java.lang.String |
MAX_BULK_DOCS |
"elastic.max.bulk.docs" |
public static final java.lang.String |
MAX_BULK_LENGTH |
"elastic.max.bulk.size" |
public static final java.lang.String |
PORT |
"elastic.port" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
BOOST_FIELD |
"boost" |
public static final java.lang.String |
COMMIT_INDEX |
"solr.commit.index" |
public static final java.lang.String |
COMMIT_SIZE |
"solr.commit.size" |
public static final java.lang.String |
DIGEST_FIELD |
"digest" |
public static final java.lang.String |
ID_FIELD |
"id" |
public static final java.lang.String |
MAPPING_FILE |
"solr.mapping.file" |
public static final java.lang.String |
PASSWORD |
"solr.auth.password" |
public static final java.lang.String |
SERVER_URL |
"solr.server.url" |
public static final java.lang.String |
SOLR_PREFIX |
"solr." |
public static final java.lang.String |
TIMESTAMP_FIELD |
"tstamp" |
public static final java.lang.String |
URL_FIELD |
"url" |
public static final java.lang.String |
USE_AUTH |
"solr.auth" |
public static final java.lang.String |
USERNAME |
"solr.auth.username" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
LICENSE_LOCATION |
"License-Location" |
public static final java.lang.String |
LICENSE_URL |
"License-Url" |
public static final java.lang.String |
WORK_TYPE |
"Work-Type" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
CONTRIBUTOR |
"contributor" |
public static final java.lang.String |
COVERAGE |
"coverage" |
public static final java.lang.String |
CREATOR |
"creator" |
public static final java.lang.String |
DATE |
"date" |
public static final java.lang.String |
DESCRIPTION |
"description" |
public static final java.lang.String |
FORMAT |
"format" |
public static final java.lang.String |
IDENTIFIER |
"identifier" |
public static final java.lang.String |
LANGUAGE |
"language" |
public static final java.lang.String |
MODIFIED |
"modified" |
public static final java.lang.String |
PUBLISHER |
"publisher" |
public static final java.lang.String |
RELATION |
"relation" |
public static final java.lang.String |
RIGHTS |
"rights" |
public static final java.lang.String |
SOURCE |
"source" |
public static final java.lang.String |
SUBJECT |
"subject" |
public static final java.lang.String |
TITLE |
"title" |
public static final java.lang.String |
TYPE |
"type" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
FEED |
"feed" |
public static final java.lang.String |
FEED_AUTHOR |
"author" |
public static final java.lang.String |
FEED_PUBLISHED |
"published" |
public static final java.lang.String |
FEED_TAGS |
"tag" |
public static final java.lang.String |
FEED_UPDATED |
"updated" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
CONTENT_DISPOSITION |
"Content-Disposition" |
public static final java.lang.String |
CONTENT_ENCODING |
"Content-Encoding" |
public static final java.lang.String |
CONTENT_LANGUAGE |
"Content-Language" |
public static final java.lang.String |
CONTENT_LENGTH |
"Content-Length" |
public static final java.lang.String |
CONTENT_LOCATION |
"Content-Location" |
public static final java.lang.String |
CONTENT_MD5 |
"Content-MD5" |
public static final java.lang.String |
CONTENT_TYPE |
"Content-Type" |
public static final java.lang.String |
LAST_MODIFIED |
"Last-Modified" |
public static final java.lang.String |
LOCATION |
"Location" |
public static final java.lang.String |
TRANSFER_ENCODING |
"Transfer-Encoding" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
ALL_BATCH_ID_STR |
"-all" |
public static final java.lang.String |
ARG_BATCH |
"batch" |
public static final java.lang.String |
ARG_CLASS |
"class" |
public static final java.lang.String |
ARG_CRAWL |
"crawl" |
public static final java.lang.String |
ARG_CURTIME |
"curTime" |
public static final java.lang.String |
ARG_DEPTH |
"depth" |
public static final java.lang.String |
ARG_FILTER |
"filter" |
public static final java.lang.String |
ARG_FORCE |
"force" |
public static final java.lang.String |
ARG_NORMALIZE |
"normalize" |
public static final java.lang.String |
ARG_NUMTASKS |
"numTasks" |
public static final java.lang.String |
ARG_RESUME |
"resume" |
public static final java.lang.String |
ARG_SEEDDIR |
"seedDir" |
public static final java.lang.String |
ARG_SEEDLIST |
"seed" |
public static final java.lang.String |
ARG_SITEMAP |
"sitemap" |
public static final java.lang.String |
ARG_SITEMAP_DETECT |
"stmDetect" |
public static final java.lang.String |
ARG_SOLR |
"solr" |
public static final java.lang.String |
ARG_SORT |
"sort" |
public static final java.lang.String |
ARG_THREADS |
"threads" |
public static final java.lang.String |
ARG_TOPN |
"topN" |
public static final java.lang.String |
BATCH_NAME_KEY |
"nutch.batch.name" |
public static final java.lang.String |
CACHING_FORBIDDEN_ALL |
"all" |
public static final java.lang.String |
CACHING_FORBIDDEN_CONTENT |
"content" |
public static final java.lang.String |
CACHING_FORBIDDEN_KEY |
"caching.forbidden" |
public static final java.lang.String |
CACHING_FORBIDDEN_NONE |
"none" |
public static final java.lang.String |
CHAR_ENCODING_FOR_CONVERSION |
"CharEncodingForConversion" |
public static final java.lang.String |
CRAWL_ID_KEY |
"storage.crawl.id" |
public static final java.lang.String |
FETCH_STATUS_KEY |
"_fst_" |
public static final java.lang.String |
FETCH_TIME_KEY |
"_ftk_" |
public static final java.lang.String |
GENERATE_TIME_KEY |
"_ngt_" |
public static final java.lang.String |
ORIGINAL_CHAR_ENCODING |
"OriginalCharEncoding" |
public static final java.lang.String |
PROTO_STATUS_KEY |
"_pst_" |
public static final java.lang.String |
REPR_URL_KEY |
"_repr_" |
public static final java.lang.String |
SCORE_KEY |
"nutch.crawl.score" |
public static final java.lang.String |
SIGNATURE_KEY |
"nutch.content.digest" |
public static final java.lang.String |
STAT_COUNTERS |
"counters" |
public static final java.lang.String |
STAT_JOBS |
"jobs" |
public static final java.lang.String |
STAT_MESSAGE |
"msg" |
public static final java.lang.String |
STAT_PHASE |
"phase" |
public static final java.lang.String |
STAT_PROGRESS |
"progress" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
REL_TAG |
"Rel-Tag" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
URLFILTER_ORDER |
"urlfilter.order" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
SCOPE_CRAWLDB |
"crawldb" |
public static final java.lang.String |
SCOPE_DEFAULT |
"default" |
public static final java.lang.String |
SCOPE_FETCHER |
"fetcher" |
public static final java.lang.String |
SCOPE_GENERATE_HOST_COUNT |
"generate_host_count" |
public static final java.lang.String |
SCOPE_INJECT |
"inject" |
public static final java.lang.String |
SCOPE_LINKDB |
"linkdb" |
public static final java.lang.String |
SCOPE_OUTLINK |
"outlink" |
public static final java.lang.String |
SCOPE_PARTITION |
"partition" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
HTMLPARSEFILTER_ORDER |
"htmlparsefilter.order" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
DEFAULT_PLUGIN |
"*" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
SKIP_TRUNCATED |
"parser.skip.truncated" |
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_OK |
0 |
public static final short |
SUCCESS_REDIRECT |
100 |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
PARSE_META_PREFIX |
"meta_" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
DIR_NAME |
"content" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
CHECK_BLOCKING |
"protocol.plugin.check.blocking" |
public static final java.lang.String |
CHECK_ROBOTS |
"protocol.plugin.check.robots" |
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 |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final int |
BUFFER_SIZE |
8192 |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
WWW_AUTHENTICATE |
"WWW-Authenticate" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final long |
DEFAULT_DELAY |
2000L |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
URLFILTER_AUTOMATON_FILE |
"urlfilter.automaton.file" |
public static final java.lang.String |
URLFILTER_AUTOMATON_RULES |
"urlfilter.automaton.rules" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
URLFILTER_REGEX_FILE |
"urlfilter.regex.file" |
public static final java.lang.String |
URLFILTER_REGEX_RULES |
"urlfilter.regex.rules" |
Modifier and Type | Constant Field | Value |
---|---|---|
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 java.lang.String |
UTF8_ENCODING |
"UTF-8" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
MIN_CONFIDENCE_KEY |
"encodingdetector.charset.min.confidence" |
public static final int |
NO_THRESHOLD |
-1 |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
UUID_KEY |
"nutch.conf.uuid" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final float |
DEFAULT_BOOST |
1.0f |
Copyright © 2019 The Apache Software Foundation