source: nutchez-0.1/conf/nutch-default.xml @ 67

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
 Licensed to the Apache Software Foundation (ASF) under one or more
 contributor license agreements.  See the NOTICE file distributed with
 this work for additional information regarding copyright ownership.
 The ASF licenses this file to You under the Apache License, Version 2.0
 (the "License"); you may not use this file except in compliance with
 the License.  You may obtain a copy of the License at

     http://www.apache.org/licenses/LICENSE-2.0

 Unless required by applicable law or agreed to in writing, software
 distributed under the License is distributed on an "AS IS" BASIS,
 WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 See the License for the specific language governing permissions and
 limitations under the License.
-->
<!-- Do not modify this file directly.  Instead, copy entries that you -->
<!-- wish to modify from this file into nutch-site.xml and change them -->
<!-- there.  If nutch-site.xml does not already exist, create it.      -->

<configuration>

<!-- file properties -->

<property>
  <name>file.content.limit</name>
  <value>65536</value>
  <description>The length limit for downloaded content, in bytes.
  If this value is nonnegative (>=0), content longer than it will be truncated;
  otherwise, no truncation at all.
  </description>
</property>

<property>
  <name>file.content.ignored</name>
  <value>true</value>
  <description>If true, no file content will be saved during fetch.
  And it is probably what we want to set most of time, since file:// URLs
  are meant to be local and we can always use them directly at parsing
  and indexing stages. Otherwise file contents will be saved.
  !! NO IMPLEMENTED YET !!
  </description>
</property>

<!-- HTTP properties -->

<property>
  <name>http.agent.name</name>
  <value></value>
  <description>HTTP 'User-Agent' request header. MUST NOT be empty - 
  please set this to a single word uniquely related to your organization.

  NOTE: You should also check other related properties:

  http.robots.agents
  http.agent.description
  http.agent.url
  http.agent.email
  http.agent.version

  and set their values appropriately.

  </description>
</property>

<property>
  <name>http.robots.agents</name>
  <value>*</value>
  <description>The agent strings we'll look for in robots.txt files,
  comma-separated, in decreasing order of precedence. You should
  put the value of http.agent.name as the first agent name, and keep the
  default * at the end of the list. E.g.: BlurflDev,Blurfl,*
  </description>
</property>

<property>
  <name>http.robots.403.allow</name>
  <value>true</value>
  <description>Some servers return HTTP status 403 (Forbidden) if
  /robots.txt doesn't exist. This should probably mean that we are
  allowed to crawl the site nonetheless. If this is set to false,
  then such sites will be treated as forbidden.</description>
</property>

<property>
  <name>http.agent.description</name>
  <value></value>
  <description>Further description of our bot- this text is used in
  the User-Agent header.  It appears in parenthesis after the agent name.
  </description>
</property>

<property>
  <name>http.agent.url</name>
  <value></value>
  <description>A URL to advertise in the User-Agent header.  This will 
   appear in parenthesis after the agent name. Custom dictates that this
   should be a URL of a page explaining the purpose and behavior of this
   crawler.
  </description>
</property>

<property>
  <name>http.agent.email</name>
  <value></value>
  <description>An email address to advertise in the HTTP 'From' request
   header and User-Agent header. A good practice is to mangle this
   address (e.g. 'info at example dot com') to avoid spamming.
  </description>
</property>

<property>
  <name>http.agent.version</name>
  <value>Nutch-1.0</value>
  <description>A version string to advertise in the User-Agent 
   header.</description>
</property>

<property>
  <name>http.agent.host</name>
  <value></value>
  <description>Name or IP address of the host on which the Nutch crawler
  would be running. Currently this is used by 'protocol-httpclient'
  plugin.
  </description>
</property>

<property>
  <name>http.timeout</name>
  <value>10000</value>
  <description>The default network timeout, in milliseconds.</description>
</property>

<property>
  <name>http.max.delays</name>
  <value>100</value>
  <description>The number of times a thread will delay when trying to
  fetch a page.  Each time it finds that a host is busy, it will wait
  fetcher.server.delay.  After http.max.delays attepts, it will give
  up on the page for now.</description>
</property>

<property>
  <name>http.content.limit</name>
  <value>65536</value>
  <description>The length limit for downloaded content, in bytes.
  If this value is nonnegative (>=0), content longer than it will be truncated;
  otherwise, no truncation at all.
  </description>
</property>

<property>
  <name>http.proxy.host</name>
  <value></value>
  <description>The proxy hostname.  If empty, no proxy is used.</description>
</property>

<property>
  <name>http.proxy.port</name>
  <value></value>
  <description>The proxy port.</description>
</property>

<property>
  <name>http.proxy.username</name>
  <value></value>
  <description>Username for proxy. This will be used by
  'protocol-httpclient', if the proxy server requests basic, digest
  and/or NTLM authentication. To use this, 'protocol-httpclient' must
  be present in the value of 'plugin.includes' property.
  NOTE: For NTLM authentication, do not prefix the username with the
  domain, i.e. 'susam' is correct whereas 'DOMAIN\susam' is incorrect.
  </description>
</property>

<property>
  <name>http.proxy.password</name>
  <value></value>
  <description>Password for proxy. This will be used by
  'protocol-httpclient', if the proxy server requests basic, digest
  and/or NTLM authentication. To use this, 'protocol-httpclient' must
  be present in the value of 'plugin.includes' property.
  </description>
</property>

<property>
  <name>http.proxy.realm</name>
  <value></value>
  <description>Authentication realm for proxy. Do not define a value
  if realm is not required or authentication should take place for any
  realm. NTLM does not use the notion of realms. Specify the domain name
  of NTLM authentication as the value for this property. To use this,
  'protocol-httpclient' must be present in the value of
  'plugin.includes' property.
  </description>
</property>

<property>
  <name>http.auth.file</name>
  <value>httpclient-auth.xml</value>
  <description>Authentication configuration file for
  'protocol-httpclient' plugin.
  </description>
</property>

<property>
  <name>http.verbose</name>
  <value>false</value>
  <description>If true, HTTP will log more verbosely.</description>
</property>

<property>
  <name>http.redirect.max</name>
  <value>0</value>
  <description>The maximum number of redirects the fetcher will follow when
  trying to fetch a page. If set to negative or 0, fetcher won't immediately
  follow redirected URLs, instead it will record them for later fetching.
  </description>
</property>

<property>
  <name>http.useHttp11</name>
  <value>false</value>
  <description>NOTE: at the moment this works only for protocol-httpclient.
  If true, use HTTP 1.1, if false use HTTP 1.0 .
  </description>
</property>

<!-- FTP properties -->

<property>
  <name>ftp.username</name>
  <value>anonymous</value>
  <description>ftp login username.</description>
</property>

<property>
  <name>ftp.password</name>
  <value>anonymous@example.com</value>
  <description>ftp login password.</description>
</property>

<property>
  <name>ftp.content.limit</name>
  <value>65536</value> 
  <description>The length limit for downloaded content, in bytes.
  If this value is nonnegative (>=0), content longer than it will be truncated;
  otherwise, no truncation at all.
  Caution: classical ftp RFCs never defines partial transfer and, in fact,
  some ftp servers out there do not handle client side forced close-down very
  well. Our implementation tries its best to handle such situations smoothly.
  </description>
</property>

<property>
  <name>ftp.timeout</name>
  <value>60000</value>
  <description>Default timeout for ftp client socket, in millisec.
  Please also see ftp.keep.connection below.</description>
</property>

<property>
  <name>ftp.server.timeout</name>
  <value>100000</value>
  <description>An estimation of ftp server idle time, in millisec.
  Typically it is 120000 millisec for many ftp servers out there.
  Better be conservative here. Together with ftp.timeout, it is used to
  decide if we need to delete (annihilate) current ftp.client instance and
  force to start another ftp.client instance anew. This is necessary because
  a fetcher thread may not be able to obtain next request from queue in time
  (due to idleness) before our ftp client times out or remote server
  disconnects. Used only when ftp.keep.connection is true (please see below).
  </description>
</property>

<property>
  <name>ftp.keep.connection</name>
  <value>false</value>
  <description>Whether to keep ftp connection. Useful if crawling same host
  again and again. When set to true, it avoids connection, login and dir list
  parser setup for subsequent urls. If it is set to true, however, you must
  make sure (roughly):
  (1) ftp.timeout is less than ftp.server.timeout
  (2) ftp.timeout is larger than (fetcher.threads.fetch * fetcher.server.delay)
  Otherwise there will be too many "delete client because idled too long"
  messages in thread logs.</description>
</property>

<property>
  <name>ftp.follow.talk</name>
  <value>false</value>
  <description>Whether to log dialogue between our client and remote
  server. Useful for debugging.</description>
</property>

<!-- web db properties -->

<property>
  <name>db.default.fetch.interval</name>
  <value>30</value>
  <description>(DEPRECATED) The default number of days between re-fetches of a page.
  </description>
</property>

<property>
  <name>db.fetch.interval.default</name>
  <value>2592000</value>
  <description>The default number of seconds between re-fetches of a page (30 days).
  </description>
</property>

<property>
  <name>db.fetch.interval.max</name>
  <value>7776000</value>
  <description>The maximum number of seconds between re-fetches of a page
  (90 days). After this period every page in the db will be re-tried, no
  matter what is its status.
  </description>
</property>

<property>
  <name>db.fetch.schedule.class</name>
  <value>org.apache.nutch.crawl.DefaultFetchSchedule</value>
  <description>The implementation of fetch schedule. DefaultFetchSchedule simply
  adds the original fetchInterval to the last fetch time, regardless of
  page changes.</description>
</property>

<property>
  <name>db.fetch.schedule.adaptive.inc_rate</name>
  <value>0.4</value>
  <description>If a page is unmodified, its fetchInterval will be
  increased by this rate. This value should not
  exceed 0.5, otherwise the algorithm becomes unstable.</description>
</property>

<property>
  <name>db.fetch.schedule.adaptive.dec_rate</name>
  <value>0.2</value>
  <description>If a page is modified, its fetchInterval will be
  decreased by this rate. This value should not
  exceed 0.5, otherwise the algorithm becomes unstable.</description>
</property>

<property>
  <name>db.fetch.schedule.adaptive.min_interval</name>
  <value>60.0</value>
  <description>Minimum fetchInterval, in seconds.</description>
</property>

<property>
  <name>db.fetch.schedule.adaptive.max_interval</name>
  <value>31536000.0</value>
  <description>Maximum fetchInterval, in seconds (365 days).
  NOTE: this is limited by db.fetch.interval.max. Pages with
  fetchInterval larger than db.fetch.interval.max
  will be fetched anyway.</description>
</property>

<property>
  <name>db.fetch.schedule.adaptive.sync_delta</name>
  <value>true</value>
  <description>If true, try to synchronize with the time of page change.
  by shifting the next fetchTime by a fraction (sync_rate) of the difference
  between the last modification time, and the last fetch time.</description>
</property>

<property>
  <name>db.fetch.schedule.adaptive.sync_delta_rate</name>
  <value>0.3</value>
  <description>See sync_delta for description. This value should not
  exceed 0.5, otherwise the algorithm becomes unstable.</description>
</property>

<property>
  <name>db.update.additions.allowed</name>
  <value>true</value>
  <description>If true, updatedb will add newly discovered URLs, if false
  only already existing URLs in the CrawlDb will be updated and no new
  URLs will be added.
  </description>
</property>

<property>
  <name>db.ignore.internal.links</name>
  <value>true</value>
  <description>If true, when adding new links to a page, links from
  the same host are ignored.  This is an effective way to limit the
  size of the link database, keeping only the highest quality
  links.
  </description>
</property>

<property>
  <name>db.ignore.external.links</name>
  <value>false</value>
  <description>If true, outlinks leading from a page to external hosts
  will be ignored. This is an effective way to limit the crawl to include
  only initially injected hosts, without creating complex URLFilters.
  </description>
</property>

<property>
  <name>db.score.injected</name>
  <value>1.0</value>
  <description>The score of new pages added by the injector.
  </description>
</property>

<property>
  <name>db.score.link.external</name>
  <value>1.0</value>
  <description>The score factor for new pages added due to a link from
  another host relative to the referencing page's score. Scoring plugins
  may use this value to affect initial scores of external links.
  </description>
</property>

<property>
  <name>db.score.link.internal</name>
  <value>1.0</value>
  <description>The score factor for pages added due to a link from the
  same host, relative to the referencing page's score. Scoring plugins
  may use this value to affect initial scores of internal links.
  </description>
</property>

<property>
  <name>db.score.count.filtered</name>
  <value>false</value>
  <description>The score value passed to newly discovered pages is
  calculated as a fraction of the original page score divided by the
  number of outlinks. If this option is false, only the outlinks that passed
  URLFilters will count, if it's true then all outlinks will count.
  </description>
</property>

<property>
  <name>db.max.inlinks</name>
  <value>10000</value>
  <description>Maximum number of Inlinks per URL to be kept in LinkDb.
  If "invertlinks" finds more inlinks than this number, only the first
  N inlinks will be stored, and the rest will be discarded.
  </description>
</property>

<property>
  <name>db.max.outlinks.per.page</name>
  <value>100</value>
  <description>The maximum number of outlinks that we'll process for a page.
  If this value is nonnegative (>=0), at most db.max.outlinks.per.page outlinks
  will be processed for a page; otherwise, all outlinks will be processed.
  </description>
</property>

<property>
  <name>db.max.anchor.length</name>
  <value>100</value>
  <description>The maximum number of characters permitted in an anchor.
  </description>
</property>

<property>
  <name>db.fetch.retry.max</name>
  <value>3</value>
  <description>The maximum number of times a url that has encountered
  recoverable errors is generated for fetch.</description>
</property>

<property>
  <name>db.signature.class</name>
  <value>org.apache.nutch.crawl.MD5Signature</value>
  <description>The default implementation of a page signature. Signatures
  created with this implementation will be used for duplicate detection
  and removal.</description>
</property>

<property>
  <name>db.signature.text_profile.min_token_len</name>
  <value>2</value>
  <description>Minimum token length to be included in the signature.
  </description>
</property>

<property>
  <name>db.signature.text_profile.quant_rate</name>
  <value>0.01</value>
  <description>Profile frequencies will be rounded down to a multiple of
  QUANT = (int)(QUANT_RATE * maxFreq), where maxFreq is a maximum token
  frequency. If maxFreq > 1 then QUANT will be at least 2, which means that
  for longer texts tokens with frequency 1 will always be discarded.
  </description>
</property>

<!-- generate properties -->

<property>
  <name>generate.max.per.host</name>
  <value>-1</value>
  <description>The maximum number of urls per host in a single
  fetchlist.  -1 if unlimited.</description>
</property>

<property>
  <name>generate.max.per.host.by.ip</name>
  <value>false</value>
  <description>If false, same host names are counted. If true,
  hosts' IP addresses are resolved and the same IP-s are counted.
  
  -+-+-+- WARNING !!! -+-+-+-
  When set to true, Generator will create a lot of DNS lookup
  requests, rapidly. This may cause a DOS attack on
  remote DNS servers, not to mention increased external traffic
  and latency. For these reasons when using this option it is
  required that a local caching DNS be used.</description>
</property>

<property>
  <name>generate.update.crawldb</name>
  <value>false</value>
  <description>For highly-concurrent environments, where several
  generate/fetch/update cycles may overlap, setting this to true ensures
  that generate will create different fetchlists even without intervening
  updatedb-s, at the cost of running an additional job to update CrawlDB.
  If false, running generate twice without intervening
  updatedb will generate identical fetchlists.</description>
</property>

<!-- fetcher properties -->

<property>
  <name>fetcher.server.delay</name>
  <value>5.0</value>
  <description>The number of seconds the fetcher will delay between 
   successive requests to the same server.</description>
</property>

<property>
  <name>fetcher.server.min.delay</name>
  <value>0.0</value>
  <description>The minimum number of seconds the fetcher will delay between 
  successive requests to the same server. This value is applicable ONLY
  if fetcher.threads.per.host is greater than 1 (i.e. the host blocking
  is turned off).</description>
</property>

<property>
 <name>fetcher.max.crawl.delay</name>
 <value>30</value>
 <description>
 If the Crawl-Delay in robots.txt is set to greater than this value (in
 seconds) then the fetcher will skip this page, generating an error report.
 If set to -1 the fetcher will never skip such pages and will wait the
 amount of time retrieved from robots.txt Crawl-Delay, however long that
 might be.
 </description>
</property> 

<property>
  <name>fetcher.threads.fetch</name>
  <value>10</value>
  <description>The number of FetcherThreads the fetcher should use.
    This is also determines the maximum number of requests that are 
    made at once (each FetcherThread handles one connection).</description>
</property>

<property>
  <name>fetcher.threads.per.host</name>
  <value>1</value>
  <description>This number is the maximum number of threads that
    should be allowed to access a host at one time.</description>
</property>

<property>
  <name>fetcher.threads.per.host.by.ip</name>
  <value>true</value>
  <description>If true, then fetcher will count threads by IP address,
  to which the URL's host name resolves. If false, only host name will be
  used. NOTE: this should be set to the same value as
  "generate.max.per.host.by.ip" - default settings are different only for
  reasons of backward-compatibility.</description>
</property>

<property>
  <name>fetcher.verbose</name>
  <value>false</value>
  <description>If true, fetcher will log more verbosely.</description>
</property>

<property>
  <name>fetcher.parse</name>
  <value>true</value>
  <description>If true, fetcher will parse content.</description>
</property>

<property>
  <name>fetcher.store.content</name>
  <value>true</value>
  <description>If true, fetcher will store content.</description>
</property>

<!-- indexer properties -->

<property>
  <name>indexer.score.power</name>
  <value>0.5</value>
  <description>Determines the power of link analyis scores.  Each
  pages's boost is set to <i>score<sup>scorePower</sup></i> where
  <i>score</i> is its link analysis score and <i>scorePower</i> is the
  value of this parameter.  This is compiled into indexes, so, when
  this is changed, pages must be re-indexed for it to take
  effect.</description>
</property>

<property>
  <name>indexer.max.title.length</name>
  <value>100</value>
  <description>The maximum number of characters of a title that are indexed.
  </description>
</property>

<property>
  <name>indexer.max.tokens</name>
  <value>10000</value>
  <description>
  The maximum number of tokens that will be indexed for a single field
  in a document. This limits the amount of memory required for
  indexing, so that collections with very large files will not crash
  the indexing process by running out of memory.

  Note that this effectively truncates large documents, excluding
  from the index tokens that occur further in the document. If you
  know your source documents are large, be sure to set this value
  high enough to accomodate the expected size. If you set it to
  -1, then the only limit is your memory, but you should anticipate
  an OutOfMemoryError.
  </description>
</property>

<property>
  <name>indexer.mergeFactor</name>
  <value>50</value>
  <description>The factor that determines the frequency of Lucene segment
  merges. This must not be less than 2, higher values increase indexing
  speed but lead to increased RAM usage, and increase the number of
  open file handles (which may lead to "Too many open files" errors).
  NOTE: the "segments" here have nothing to do with Nutch segments, they
  are a low-level data unit used by Lucene.
  </description>
</property>

<property>
  <name>indexer.minMergeDocs</name>
  <value>50</value>
  <description>This number determines the minimum number of Lucene
  Documents buffered in memory between Lucene segment merges. Larger
  values increase indexing speed and increase RAM usage.
  </description>
</property>

<property>
  <name>indexer.maxMergeDocs</name>
  <value>2147483647</value>
  <description>This number determines the maximum number of Lucene
  Documents to be merged into a new Lucene segment. Larger values
  increase batch indexing speed and reduce the number of Lucene segments,
  which reduces the number of open file handles; however, this also
  decreases incremental indexing performance.
  </description>
</property>

<property>
  <name>indexer.termIndexInterval</name>
  <value>128</value>
  <description>Determines the fraction of terms which Lucene keeps in
  RAM when searching, to facilitate random-access.  Smaller values use
  more memory but make searches somewhat faster.  Larger values use
  less memory but make searches somewhat slower.
  </description>
</property>

<!-- indexingfilter plugin properties -->

<property>
  <name>indexingfilter.order</name>
  <value></value>
  <description>The order by which index filters are applied.
  If empty, all available index filters (as dictated by properties
  plugin-includes and plugin-excludes above) are loaded and applied in system
  defined order. If not empty, only named filters are loaded and applied
  in given order. For example, if this property has value:
  org.apache.nutch.indexer.basic.BasicIndexingFilter org.apache.nutch.indexer.more.MoreIndexingFilter
  then BasicIndexingFilter is applied first, and MoreIndexingFilter second.
  
  Filter ordering might have impact on result if one filter depends on output of
  another filter.
  </description>
</property>


<!-- analysis properties -->

<property>
  <name>analysis.common.terms.file</name>
  <value>common-terms.utf8</value>
  <description>The name of a file containing a list of common terms
  that should be indexed in n-grams.</description>
</property>

<!-- searcher properties -->

<property>
  <name>searcher.dir</name>
  <value>crawl</value>
  <description>
  Path to root of crawl.  This directory is searched (in
  order) for either the file search-servers.txt, containing a list of
  distributed search servers, or the directory "index" containing
  merged indexes, or the directory "segments" containing segment
  indexes.
  </description>
</property>

<property>
  <name>searcher.filter.cache.size</name>
  <value>16</value>
  <description>
  Maximum number of filters to cache.  Filters can accelerate certain
  field-based queries, like language, document format, etc.  Each
  filter requires one bit of RAM per page.  So, with a 10 million page
  index, a cache size of 16 consumes two bytes per page, or 20MB.
  </description>
</property>

<property>
  <name>searcher.filter.cache.threshold</name>
  <value>0.05</value>
  <description>
  Filters are cached when their term is matched by more than this
  fraction of pages.  For example, with a threshold of 0.05, and 10
  million pages, the term must match more than 1/20, or 50,000 pages.
  So, if out of 10 million pages, 50% of pages are in English, and 2%
  are in Finnish, then, with a threshold of 0.05, searches for
  "lang:en" will use a cached filter, while searches for "lang:fi"
  will score all 20,000 finnish documents.
  </description>
</property>

<property>
  <name>searcher.hostgrouping.rawhits.factor</name>
  <value>2.0</value>
  <description>
  A factor that is used to determine the number of raw hits
  initially fetched, before host grouping is done.
  </description>
</property>

<property>
  <name>searcher.summary.context</name>
  <value>5</value>
  <description>
  The number of context terms to display preceding and following
  matching terms in a hit summary.
  </description>
</property>

<property>
  <name>searcher.summary.length</name>
  <value>20</value>
  <description>
  The total number of terms to display in a hit summary.
  </description>
</property>

<property>
  <name>searcher.max.hits</name>
  <value>-1</value>
  <description>If positive, search stops after this many hits are
  found.  Setting this to small, positive values (e.g., 1000) can make
  searches much faster.  With a sorted index, the quality of the hits
  suffers little.</description>
</property>

<property>
  <name>searcher.max.time.tick_count</name>
  <value>-1</value>
  <description>If positive value is defined here, limit search time for
  every request to this number of elapsed ticks (see the tick_length
  property below). The total maximum time for any search request will be
  then limited to tick_count * tick_length milliseconds. When search time
  is exceeded, partial results will be returned, and the total number of
  hits will be estimated.
  </description>
</property>

<property>
  <name>searcher.max.time.tick_length</name>
  <value>200</value>
  <description>The number of milliseconds between ticks. Larger values
  reduce the timer granularity (precision). Smaller values bring more
  overhead.
  </description>
</property>

<property>
  <name>searcher.num.handlers</name>
  <value>10</value>
  <description>The number of handlers for the distributed search server.
  </description>
</property>

<property>
  <name>searcher.max.hits.per.page</name>
  <value>1000</value>
  <description> The maximum number of hits to show per page. -1 if
    unlimited. If the number of hits requested by the user (via
    hitsPerPage parameter in the query string) is more than the value
    specified in this property, then this value is assumed as the number
    of hits per page.
  </description>
</property>

<!-- URL normalizer properties -->

<property>
  <name>urlnormalizer.order</name>
  <value>org.apache.nutch.net.urlnormalizer.basic.BasicURLNormalizer org.apache.nutch.net.urlnormalizer.regex.RegexURLNormalizer</value>
  <description>Order in which normalizers will run. If any of these isn't
  activated it will be silently skipped. If other normalizers not on the
  list are activated, they will run in random order after the ones
  specified here are run.
  </description>
</property>

<property>
  <name>urlnormalizer.regex.file</name>
  <value>regex-normalize.xml</value>
  <description>Name of the config file used by the RegexUrlNormalizer class.
  </description>
</property>

<property>
  <name>urlnormalizer.loop.count</name>
  <value>1</value>
  <description>Optionally loop through normalizers several times, to make
  sure that all transformations have been performed.
  </description>
</property>

<!-- mime properties -->

<property>
  <name>mime.types.file</name>
  <value>tika-mimetypes.xml</value>
  <description>Name of file in CLASSPATH containing filename extension and
  magic sequence to mime types mapping information</description>
</property>

<property>
  <name>mime.type.magic</name>
  <value>true</value>
  <description>Defines if the mime content type detector uses magic resolution.
  </description>
</property>

<!-- plugin properties -->

<property>
  <name>plugin.folders</name>
  <value>plugins</value>
  <description>Directories where nutch plugins are located.  Each
  element may be a relative or absolute path.  If absolute, it is used
  as is.  If relative, it is searched for on the classpath.</description>
</property>

<property>
  <name>plugin.auto-activation</name>
  <value>true</value>
  <description>Defines if some plugins that are not activated regarding
  the plugin.includes and plugin.excludes properties must be automaticaly
  activated if they are needed by some actived plugins.
  </description>
</property>

<property>
  <name>plugin.includes</name>
  <value>protocol-http|urlfilter-regex|parse-(text|html|js)|index-(basic|anchor)|query-(basic|site|url)|response-(json|xml)|summary-basic|scoring-opic|urlnormalizer-(pass|regex|basic)</value>
  <description>Regular expression naming plugin directory names to
  include.  Any plugin not matching this expression is excluded.
  In any case you need at least include the nutch-extensionpoints plugin. By
  default Nutch includes crawling just HTML and plain text via HTTP,
  and basic indexing and search plugins. In order to use HTTPS please enable 
  protocol-httpclient, but be aware of possible intermittent problems with the 
  underlying commons-httpclient library.
  </description>
</property>

<property>
  <name>plugin.excludes</name>
  <value></value>
  <description>Regular expression naming plugin directory names to exclude.  
  </description>
</property>

<!-- parser properties -->

<property>
  <name>parse.plugin.file</name>
  <value>parse-plugins.xml</value>
  <description>The name of the file that defines the associations between
  content-types and parsers.</description>
</property>

<property>
  <name>parser.character.encoding.default</name>
  <value>windows-1252</value>
  <description>The character encoding to fall back to when no other information
  is available</description>
</property>

<property>
  <name>encodingdetector.charset.min.confidence</name>
  <value>-1</value>
  <description>A integer between 0-100 indicating minimum confidence value
  for charset auto-detection. Any negative value disables auto-detection.
  </description>
</property>

<property>
  <name>parser.caching.forbidden.policy</name>
  <value>content</value>
  <description>If a site (or a page) requests through its robot metatags
  that it should not be shown as cached content, apply this policy. Currently
  three keywords are recognized: "none" ignores any "noarchive" directives.
  "content" doesn't show the content, but shows summaries (snippets).
  "all" doesn't show either content or summaries.</description>
</property>


<property>
  <name>parser.html.impl</name>
  <value>neko</value>
  <description>HTML Parser implementation. Currently the following keywords
  are recognized: "neko" uses NekoHTML, "tagsoup" uses TagSoup.
  </description>
</property>

<property>
  <name>parser.html.form.use_action</name>
  <value>false</value>
  <description>If true, HTML parser will collect URLs from form action
  attributes. This may lead to undesirable behavior (submitting empty
  forms during next fetch cycle). If false, form action attribute will
  be ignored.</description>
</property>

<property>
  <name>parser.html.outlinks.ignore_tags</name>
  <value></value>
  <description>Comma separated list of HTML tags, from which outlinks 
  shouldn't be extracted. Nutch takes links from: a, area, form, frame, 
  iframe, script, link, img. If you add any of those tags here, it
  won't be taken. Default is empty list. Probably reasonable value
  for most people would be "img,script,link".</description>
</property>


<!-- urlfilter plugin properties -->

<property>
  <name>urlfilter.domain.file</name>
  <value>domain-urlfilter.txt</value>
  <description>Name of file on CLASSPATH containing either top level domains or
  hostnames used by urlfilter-domain (DomainURLFilter) plugin.</description>
</property>

<property>
  <name>urlfilter.regex.file</name>
  <value>regex-urlfilter.txt</value>
  <description>Name of file on CLASSPATH containing regular expressions
  used by urlfilter-regex (RegexURLFilter) plugin.</description>
</property>

<property>
  <name>urlfilter.automaton.file</name>
  <value>automaton-urlfilter.txt</value>
  <description>Name of file on CLASSPATH containing regular expressions
  used by urlfilter-automaton (AutomatonURLFilter) plugin.</description>
</property>

<property>
  <name>urlfilter.prefix.file</name>
  <value>prefix-urlfilter.txt</value>
  <description>Name of file on CLASSPATH containing url prefixes
  used by urlfilter-prefix (PrefixURLFilter) plugin.</description>
</property>

<property>
  <name>urlfilter.suffix.file</name>
  <value>suffix-urlfilter.txt</value>
  <description>Name of file on CLASSPATH containing url suffixes
  used by urlfilter-suffix (SuffixURLFilter) plugin.</description>
</property>

<property>
  <name>urlfilter.order</name>
  <value></value>
  <description>The order by which url filters are applied.
  If empty, all available url filters (as dictated by properties
  plugin-includes and plugin-excludes above) are loaded and applied in system
  defined order. If not empty, only named filters are loaded and applied
  in given order. For example, if this property has value:
  org.apache.nutch.urlfilter.regex.RegexURLFilter org.apache.nutch.urlfilter.prefix.PrefixURLFilter
  then RegexURLFilter is applied first, and PrefixURLFilter second.
  Since all filters are AND'ed, filter ordering does not have impact
  on end result, but it may have performance implication, depending
  on relative expensiveness of filters.
  </description>
</property>

<!-- scoring filters properties -->

<property>
  <name>scoring.filter.order</name>
  <value></value>
  <description>The order in which scoring filters are applied.
  This may be left empty (in which case all available scoring
  filters will be applied in the order defined in plugin-includes
  and plugin-excludes), or a space separated list of implementation
  classes.
  </description>
</property>

<!-- clustering extension properties -->

<property>
  <name>extension.clustering.hits-to-cluster</name>
  <value>100</value>
  <description>Number of snippets retrieved for the clustering extension
  if clustering extension is available and user requested results
  to be clustered.</description>
</property>

<property>
  <name>extension.clustering.extension-name</name>
  <value></value>
  <description>Use the specified online clustering extension. If empty,
  the first available extension will be used. The "name" here refers to an 'id'
  attribute of the 'implementation' element in the plugin descriptor XML
  file.</description>
</property>

<!-- ontology extension properties -->

<property>
  <name>extension.ontology.extension-name</name>
  <value></value>
  <description>Use the specified online ontology extension. If empty,
  the first available extension will be used. The "name" here refers to an 'id'
  attribute of the 'implementation' element in the plugin descriptor XML
  file.</description>
</property>

<property>
  <name>extension.ontology.urls</name>
  <value>
  </value>
  <description>Urls of owl files, separated by spaces, such as
  http://www.example.com/ontology/time.owl
  http://www.example.com/ontology/space.owl
  http://www.example.com/ontology/wine.owl
  Or
  file:/ontology/time.owl
  file:/ontology/space.owl
  file:/ontology/wine.owl
  You have to make sure each url is valid.
  By default, there is no owl file, so query refinement based on ontology
  is silently ignored.
  </description>
</property>

<!-- query-basic plugin properties -->

<property>
  <name>query.url.boost</name>
  <value>4.0</value>
  <description> Used as a boost for url field in Lucene query.
  </description>
</property>

<property>
  <name>query.anchor.boost</name>
  <value>2.0</value>
  <description> Used as a boost for anchor field in Lucene query.
  </description>
</property>

<property>
  <name>query.title.boost</name>
  <value>1.5</value>
  <description> Used as a boost for title field in Lucene query.
  </description>
</property>

<property>
  <name>query.host.boost</name>
  <value>2.0</value>
  <description> Used as a boost for host field in Lucene query.
  </description>
</property>

<property>
  <name>query.phrase.boost</name>
  <value>1.0</value>
  <description> Used as a boost for phrase in Lucene query.
  Multiplied by boost for field phrase is matched in.
  </description>
</property>

<!--
<property>
  <name>query.basic.description.boost</name>
  <value>1.0</value>
  <description> Declares a custom field and its boost to be added to the default fields of the Lucene query.
  </description>
</property>
-->

<!-- creative-commons plugin properties -->

<property>
  <name>query.cc.boost</name>
  <value>0.0</value>
  <description> Used as a boost for cc field in Lucene query.
  </description>
</property>

<!-- query-more plugin properties -->

<property>
  <name>query.type.boost</name>
  <value>0.0</value>
  <description> Used as a boost for type field in Lucene query.
  </description>
</property>

<!-- query-site plugin properties -->

<property>
  <name>query.site.boost</name>
  <value>0.0</value>
  <description> Used as a boost for site field in Lucene query.
  </description>
</property>

<!-- microformats-reltag plugin properties -->

<property>
  <name>query.tag.boost</name>
  <value>1.0</value>
  <description> Used as a boost for tag field in Lucene query.
  </description>
</property>

<!-- language-identifier plugin properties -->

<property>
  <name>lang.ngram.min.length</name>
  <value>1</value>
  <description> The minimum size of ngrams to uses to identify
  language (must be between 1 and lang.ngram.max.length).
  The larger is the range between lang.ngram.min.length and
  lang.ngram.max.length, the better is the identification, but
  the slowest it is.
  </description>
</property>

<property>
  <name>lang.ngram.max.length</name>
  <value>4</value>
  <description> The maximum size of ngrams to uses to identify
  language (must be between lang.ngram.min.length and 4).
  The larger is the range between lang.ngram.min.length and
  lang.ngram.max.length, the better is the identification, but
  the slowest it is.
  </description>
</property>

<property>
  <name>lang.analyze.max.length</name>
  <value>2048</value>
  <description> The maximum bytes of data to uses to indentify
  the language (0 means full content analysis).
  The larger is this value, the better is the analysis, but the
  slowest it is.
  </description>
</property>

<property>
  <name>query.lang.boost</name>
  <value>0.0</value>
  <description> Used as a boost for lang field in Lucene query.
  </description>
</property>

<!-- Temporary Hadoop 0.17.x workaround. -->

<property>
  <name>hadoop.job.history.user.location</name>
  <value>${hadoop.log.dir}/history/user</value>
  <description>Hadoop 0.17.x comes with a default setting to create
     user logs inside the output path of the job. This breaks some
     Hadoop classes, which expect the output to contain only
     part-XXXXX files. This setting changes the output to a
     subdirectory of the regular log directory.
  </description>
</property>

<!-- response writer properties -->

<property>
  <name>search.response.default.type</name>
  <value>xml</value>
  <description>
  The default response type returned if none is specified.
  </description>
</property>

<property>
  <name>search.response.default.lang</name>
  <value>en</value>
  <description>
  The default response language if none is specified.
  </description>
</property>

<property>
  <name>search.response.default.numrows</name>
  <value>10</value>
  <description>
  The default number of rows to return if none is specified.
  </description>
</property>

<property>
  <name>search.response.default.dedupfield</name>
  <value>site</value>
  <description>
  The default dedup field if none is specified.
  </description>
</property>

<property>
  <name>search.response.default.numdupes</name>
  <value>1</value>
  <description>
  The default number of duplicates returned if none is specified.
  </description>
</property>

<property>
  <name>searcher.response.maxage</name>
  <value>86400</value>
  <description>
  The maxage of a response in seconds. Used in caching headers.
  </description>
</property>

<property>
  <name>searcher.response.prettyprint</name>
  <value>true</value>
  <description>
  Should the response output be pretty printed.  Setting to true enables better
  debugging, false removes unneeded spaces and gives better throughput.
  </description>
</property>

</configuration>